key: cord-0066053-dupqgu2o
authors: Nardone, Valerio; Boldrini, Luca; Grassi, Roberta; Franceschini, Davide; Morelli, Ilaria; Becherini, Carlotta; Loi, Mauro; Greto, Daniela; Desideri, Isacco
title: Radiomics in the Setting of Neoadjuvant Radiotherapy: A New Approach for Tailored Treatment
date: 2021-07-17
journal: Cancers (Basel)
DOI: 10.3390/cancers13143590
sha: 8091646b2d2a3f9ef334b686f37e3bce816926bb
doc_id: 66053
cord_uid: dupqgu2o

SIMPLE SUMMARY: This review based on a literature search aims at showing the impact of Texture Analysis in the prediction of response to neoadjuvant radiotherapy and/or chemoradiotherapy. The manuscript explores radiomics approaches in different fields of neoadjuvant radiotherapy, including esophageal cancer, lung cancer, sarcoma and rectal cancer in order to shed a light in the setting of neoadjuvant radiotherapy that can be used to tailor the best subsequent therapeutical strategy. ABSTRACT: Introduction: Neoadjuvant radiotherapy is currently used mainly in locally advanced rectal cancer and sarcoma and in a subset of non-small cell lung cancer and esophageal cancer, whereas in other diseases it is under investigation. The evaluation of the efficacy of the induction strategy is made possible by performing imaging investigations before and after the neoadjuvant therapy and is usually challenging. In the last decade, texture analysis (TA) has been developed to help the radiologist to quantify and identify the parameters related to tumor heterogeneity, which cannot be appreciated by the naked eye. The aim of this narrative is to review the impact of TA on the prediction of response to neoadjuvant radiotherapy and or chemoradiotherapy. Materials and Methods: Key references were derived from a PubMed query. Hand searching and ClinicalTrials.gov were also used. Results: This paper contains a narrative report and a critical discussion of radiomics approaches in different fields of neoadjuvant radiotherapy, including esophageal cancer, lung cancer, sarcoma, and rectal cancer. Conclusions: Radiomics can shed a light on the setting of neoadjuvant therapies that can be used to tailor subsequent approaches or even to avoid surgery in the future. At the same, these results need to be validated in prospective and multicenter trials.

Radiotherapy (RT) represents one of the most effective anticancer agents, which can be used either alone or in combination with other strategies (surgery, chemotherapy, and immunotherapy). It aims either to cure the patient (curative radiotherapy), to reduce the risk of locoregional relapse after surgery (adjuvant radiotherapy), to facilitate and to improve the results of surgery (neoadjuvant radiotherapy), or to relieve symptoms if a cure feature-based radiomics workflow usually relies on image preprocessing and region-ofinterest (ROI) segmentation, followed by feature extraction. Radiomics features are based on a huge number of different mathematical operations; thus, a large number (even more than 1000) of features can be extracted from a single ROI. These features can be divided in different subgroups, as follows:

(a) Shape features: these features refer to the geometric properties of the ROI (volume, diameter, sphericity, and compacity); (b) Histogram-based features: these features are calculated from the general histogram of the Hounsfield Unit (HU) of the ROI, such as the mean, median, skewness, and kurtosis. These features do not consider the spatial orientation of the voxels; (c) Second-order texture features: these features consider the statistical relationship between neighboring voxels or groups of voxels within the segmented lesion. These features can be extracted from several matrices, such as the gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GRLLM), and neighborhood gray-level different matrix (NGLDM); (d) Higher-order texture features: these parameters use additional image filters, using specific mathematical transformations that can highlight specific aspects of the ROI. The filter used can be wavelet or Fourier transforms, fractal analysis, and Laplacian of Gaussian;

Deep learning-based radiomics, conversely, use neural networks or auto-encoders to generate and identify important features from input data [34] . Deep learning is an application of Artificial intelligence (AI) that represents a set of computational algorithms that are able to learn the patterns in the data provided in order to make predictions on other data sets. The application areas include image segmentation and phenotyping, radiomic signature discovery, clinical outcome prediction, and many other processes. With this AI approach, radiomics can handle a massive amount of data and at the same time can directly analyze the imaging to design the proper radiomic features.

A trimodal approach with neoadjuvant chemoradiotherapy (nCRT) followed by surgery is the treatment of choice in locally advanced esophageal cancer (EC).

A clinical evaluation of the response is made with different imaging techniques (MRI, CT, and PET) and can classify the response according to the RECIST criteria [35] [36] [37] [38] [39] [40] . With these premises, radiomic analysis has been used in this setting with the aim to predict the response of the neoadjuvant strategy [37] .

In patients treated for locally advanced EC, temporal changes in tumor volume (before and after nCRT) were correlated with pathological response, although the predictive value of this parameter was modest, with no correlation with overall survival [35] . Sun et al. [37] found that several histogram parameters calculated on DCE-MRI can be used in evaluating and predicting the nCRT response.

CT images are mostly used to extract morphologic information of EC, but recent studies suggest that quantitative image features can provide additional information correlated to tumor response and prognosis [41] [42] [43] .

On the other hand, metabolic imaging has been found to be more accurate in evaluating the response to nCRT. Most 18F-FDG PET studies in EC quantify metabolic tumor activity solely by using the maximum standardized uptake value (SUVmax) [44, 45] . However, this approach does not characterize the total activity nor heterogeneity of the 18F-FDG uptake for the entire tumor [46, 47] . Recent studies suggest that spatial image information provides additional information than SUVmax [48] [49] [50] [51] .

It has been hypothesized that tumors could be rendered more homogeneous following treatment due to a reduction in cellular density and interstitial pressure and to normalization of the vasculature with improved intra-tumor perfusion and oxygenation [43] . Studies that performed imaging before and after treatment reported that tumor heterogeneity generally decreased following treatment [43, 52] . Simoni et al. found that metabolic TV (MTV) in poor responders was significantly higher than in good responders (38.6 mL vs. 17.7 mL, p = 0.02) [53] . Yip et al. reported that delta-radiomics calculated within MTV60% were the least correlated with pathological response. Instead, temporal changes in tumor 18F-FDG distribution after nCRT assessed by delta-second-order radiomics (∆RLM textures) were correlated to the OS [54] .

In a study of Beukinga et al., the most predictive textural features were Long Run Low Gray-Level (LRLGLe)-PET and Run-Percentage (RP)-CT. LRLGLe-PET depends on long runs (coarse texture) with low gray levels and was higher (i.e., low and homogeneous 18F-FDG uptake) for complete responders and lower (i.e., high and heterogeneous 18F-FDG uptake) for incomplete responders, possibly due to tumor hypoxia and necrosis [55] .

In a French study, Hatt et al. assessed the value of MTV, entropy, dissimilarity, highintensity large-area emphasis, and zone percentage for the prediction of OS of 112 patients with EC who underwent definitive CRT or nCRT followed by surgery [56] . MTV and heterogeneity had a less prognostic value in EC (vs. non-small cell lung cancer), which was attributed to smaller overall volumes. The local dissimilarity parameter appeared most predictive for OS.

Current research is focused on a correlation between the biological tumor markers from pre-treatment tumor biopsies and F-FDG PET-based radiomic features. The prediction model from Beukinga et al. tried to correlate HER2 and the CD44 expression and F-FDG PET-based radiomic features in predicting a complete response (pCR) to nCRT; it showed promising ability to identify pCR [57] . Analysis of texture within tumors on medical imaging, such as CT, MRI, and PET, is emerging as a potential biomarker to predict prognosis and treatment response in patients with EC. These findings could increase our capability to predict and evaluate the nCRT response and optimize treatment planning.

Lung cancer represents the leading cause of cancer death and its treatment rely on different strategies, often used in combination, such as radiotherapy, surgery, chemotherapy, and immunotherapy [58] [59] [60] [61] . Medical imaging is pivotal in all the different phases of lung cancer management, from diagnosis to the evaluation of the efficacy of different approaches, as well as in the subsequent follow-up [62] [63] [64] [65] [66] [67] [68] [69] .

A significant body of literature is available regarding the role of textural analysis in lung cancer. Radiomic features have been used both for diagnosis (discrimination of malignant nature of lung nodules, histology prediction, and genomic analysis) and for outcome prediction, particularly after definitive chemo-radiotherapy (CT-RT) or stereotactic body radiation therapy (SBRT) [70] [71] [72] [73] [74] [75] [76] [77] [78] [79] . On the other hand, few studies focused on neoadjuvant radiotherapy, possibly because of the controversial benefit of adding surgery after CT-RT [80, 81] . The largest available series included 127 stage II-III NSCLC patients treated with neoadjuvant chemoradiotherapy (CT-RT) followed by surgical resection. Texture analysis was conducted on primary tumors with features extracted from planning CT. The endpoint of the analysis was a pathologic response and gross residual disease. Seven features (one shape feature, three second-order features, and three higher-order features) were predictive for pathologic gross residual disease (AUC > 0.6, p-value < 0.05) and one for pathologic complete response (one higher-order feature) (AUC = 0.63, p-value = 0.01). These features suggested that a spherical disproportionality of the primary tumor site (i.e., more complex shape) was a predictor of pathological response, while spherical tumors and tumors with large flat zones were more likely to be linked with residual disease [82] . The same group conducted another analysis on a similar population, analyzing also features from pathologic lymph nodes. Radiomics analysis was performed on 85 primary tumors and 178 lymph nodes with the same endpoints as above (pathologic response and gross residual disease). A mix of clinical variables and conventional and radiomic features were used to create a predictive model. The model built from the radiomic features was the best at predicting pathologic response (AUC 0.68, p < 0.05), while a mixed clinical and radiomic model was better performing for gross residual disease (AUC 0.73, p < 0.05). The authors concluded that the features extracted from the lymph nodes were more informative than those derived by primary tumors [83] .

A small study analyzing PET-CT included 13 patients on a prospective clinical trial of trimodal therapy for resectable locally advanced NSCLC. A true texture analysis was not performed; however, pre-and post-chemo-radiotherapy SUV was not correlated with any clinical endpoint (pathologic complete response, PFS, and OS) [84] .

Chong et al. performed a texture analysis on a mixed population with NSCLC treated with neoadjuvant chemo-radiotherapy (CT-RT) or neoadjuvant EGFR-inhibitor. Focusing on the CT-RT group, 28 patients were included in the study. A pre-operative CT was used for analysis, and the endpoint again was a pathologic response. In the univariate analysis, tumor volume, mass, kurtosis, and skewness were significant predictors of pathologic response, although only kurtosis maintained its significance in the multivariate analysis (OR 1.107, p = 0.009). ROC analysis showed that the AUC for kurtosis was 0.943 and that the optimal cut-off value of percent change of kurtosis for predicting pathologic response was less than −23 (sensitivity, 87.5%; specificity, 84.3%) [85] .

More recently, Khorrami et al. conducted a textural analysis on 90 stage IIIA NSCLC patients treated with neoadjuvant CT-RT, followed by surgical resection. Pretreatment CT scans were used for features extraction. Patients were randomly split into two sets, one for training and one for testing.

Interestingly, the authors analyzed the features not only from primary tumors, but also from the peritumoral region (defined as a 15 mm dilation from primary nodule) to identify a possible predicting role of the tumor microenvironment.

Thirteen intratumoral and peritumoral radiomic texture features were found to be predictive of major pathologic response and were used to define a classifier with an AUC of 0.90 ± 0.025 within the training set, and an AUC = 0.86 in the test set. This signature was also predictive for OS (HR = 11.18, 95% CI = 3.17, 44.1; p-value = 0.008) and DFS (HR = 2.78, 95% CI = 1.11, 4.12; p-value = 0.0042) in the testing set. The combination of peritumoral and intratumoral features performed better than a clustering built only on intratumoral features.

The results of this study highlight that heterogeneous enhancement and disruption of textural patterns within and outside the nodules (better identified by Law Laplacian and Laws features) can predict not only response, but also patients' prognosis [86] .

Identifying patients who respond completely to chemoradiation and who do not require additional invasive local therapy, also considering the controversial role of surgery in this scenario, is an unmet clinical need.

The intrinsic potential of texture analysis in predicting a response after neoadjuvant CT-RT is plain. However, available studies are not enough to consider radiomics as a ready and easily accessible clinical biomarker. Larger studies, with a higher number of patients and with external validation, are needed before radiomic analysis could be clinically implemented. Analyzing available data, a special attention in future research should be paid to nodal and peritumoral features, which are potentially even more predictive than primary tumor analysis.

Soft tissue sarcomas (STS) are a group of mesenchymal malignancies encompassing a wide array of distinct clinical entities, including over 50 different histological subtypes [87] . Due to their rarity and non-specific clinical presentation (mostly consisting of slowlygrowing indolent swellings in limbs or trunk), a differential diagnosis with benign tumors is challenging and may result in a significant delay to curative treatment, consisting of wide surgical excision in absence of metastatic dissemination [87, 88] . Furthermore, their intrinsic heterogeneity is also displayed by variable levels of genomic profile complexity and structural architecture, resulting in different clinical presentations and inconsistent responses to standard treatments [88] [89] [90] . Unfortunately, one among the major predictors of outcome in operable patients-tumor histological grading-may be underestimated by tumor biopsy [91] . This is a relevant issue, since tumor grade determination may guide treatment management: low-grade STSs may be treated with planned marginal excision, sparing patients from more extensive surgery [92] , while detection of high-grade disease may serve as a decision criteria for pre-operative treatment intensification [93, 94] . Moreover, while the additional benefit of adjuvant chemotherapy is questioned and limited to a subset of high-risk patients, no consensual criteria have been provided to define this population; clinical [95] and genomic [96] classifiers have been proposed, although their use have not been implemented in clinical practice yet.

Hence, there is an urgent need to identify novel and readily available biomarkers to improve diagnosis, predict the disease course, and possibly define a tailored pattern of care in patients at high risk of disease relapse [88] . Radiomics may provide a valuable source of information in STS patients. Due to its non-invasive nature, radiomics may quickly discern benign from malignant lesions, timely addressing the need for further investigation; secondarily, it may provide an appropriate histopathologic grade determination on the whole tumor bulk, thus overcoming the limitations of tumor biopsy in accounting for intratumor heterogeneity; finally, identification of specific signatures correlated with outcome may allow prediction of relapse risk and eligibility for further interventions.

Improvement in differential diagnosis of malignancy have been reported by several authors [97, 98] . In particular radiomics-based differentiation between soft-tissue lipoma and well-differentiated liposarcoma [99, 100] was demonstrated despite similar radiologic and pathologic presentation, often requiring molecular analysis of MDM2 amplification status; interestingly, superior performance of a machine-learning classifier as compared to trained radiologists has been shown [101] . Similarly, radiomic features allowed to distinguish myxoma from myxofibrosarcoma [102] and atypical leiomyoma from uterine sarcoma [103] [104] [105] .

Machine-learning algorithms proved also useful in the prediction of histopathologic grade. Using CT-or MRI-based radiomics, different signatures associated with high-grade disease were identified [106] [107] [108] [109] [110] [111] [112] ; in some cases, integration with clinical features resulted in the establishment of a prognostic nomogram for risk stratification [108] .

A radiomic approach may be used to improve prediction of patients' outcome. RM texture analysis alone [113, 114] or combined with PET/CT metabolic data [115, 116] was associated with metastatic relapse and specific signatures were identified for prediction of survival [117, 118] . Radiomic analysis was also applied on surveillance MRI in patients undergoing follow-up after surgical resection [119] , resulting in improved detection and characterization of local recurrence [120] .

Concerning prediction of sensitivity to treatment, preliminary results reported adequate concordance between radiomic features and response to neoadjuvant chemotherapy [121] or chemoradiation [122] , as well as exclusive chemotherapy in unresectable patients [119, 123] .

On the other hand, while radiomics analysis correlated with adipocytic maturation following neoadjuvant chemotherapy in myxoid/round cells liposarcomas, it occurred independently from the chemotherapy regimen and was not correlated with metastasisfree survival [124] ; similarly, radiomics was insufficient to predict the response from hypofractionated pre-operative RT [125] .

Despite promising preliminary results, no radiomic signature for sarcoma has been implemented to date in clinical practice. Multiple issues have been detected in the pathway to translation from exploratory analysis into standard of care, ranging from lack of external validation and replicability, consistency, and cost-effectiveness of the imaging biomarkers proposed at present [126] . While these shortcomings are partially motivated by the complex workflow and relevant technical requirements needed for the development and elaboration of radiomic signatures, further effort is required for successful translation into clinical use.

Adequately predicting the response to neoadjuvant chemoradiotherapy (nCRT) in rectal cancer represents a key factor in order to achieve a fully personalized treatment approach, especially in the case of locally advanced disease presentation, which constitute a well-established indication for radiation therapy [127] . The identification of biomarkers able to predict patients' outcomes (i.e., response to nCRT) currently represents a priority in the radiotherapy research landscape, and imaging-derived response predictors are a topic of active investigation [128] [129] [130] [131] [132] [133] .

Thanks to the extensive use of MRI as a staging imaging technique for this specific disease, the imaging community rapidly focused its research efforts on it and the first preliminary observations have been published since the early 2000 s. These first studies generally aimed to correlate the response to neoadjuvant treatments with the Gross Tumor Volume's (GTV) morphological modifications, mainly taking advantage of the high image quality provided by MRI [134] [135] [136] and also proposing to address the metabolic information disclosed by PET-CT staging imaging [137, 138] .

The recent development of TA and radiomics-based image analysis have introduced new predictive modelling techniques and offered promising insights for quantitative imaging characterization of rectal cancer, when compared to the mere volumetric assessment [139] .

Most of the papers available in the literature focus on the response to nCRT prediction, using several imaging and modelling techniques. Handcrafted radiomics is used in the largest majority of these studies, achieving overall satisfactory results even when compared to more advanced machine learning approaches (i.e., deep learning) [34].

Nevertheless, the obtained level of evidence is still unfortunately low and inconclusive, mainly due to the overall low quality of these studies, as pointed out by two recent reviews that highlight the limited replicability and reproducibility of the available models [140, 141] .

Furthermore, the largest majority of the published papers does not meet the minimal technical quality criteria, such as the ones proposed by the RQS and QUADAS-2 standards [142, 143] . In this context, it has also to be said that this issue suffers from the initial enthusiasm that researchers have addressed to radiomics and TA analysis, publishing several exploratory papers on very limited cohorts of patients and often using non-standardized, and thus not reproducible analysis pipelines.

Furthermore, only few models are based on a properly selected reduced number of features that make their applicability easier and more straightforward, while the majority gathers hundreds of variables.

Among the different imaging techniques used, it is evident that staging MRI represents the one of choice for TA and radiomics studies in general, primarily thanks to the large availability of images and to the prominent current role fulfilled by MRI in the framework of the international rectal cancer management guidelines as the imaging gold standard for disease staging [144] .

Response to therapy (e.g., tumor downstaging and pathological complete response, pCR) represents the most common outcomes of these models, whose main part focuses on the use of T2w and Diffusion Weighted Imaging (DWI), while the use of Dynamic Contrast Enhanced (DCE) images is still less common [141] .

Interestingly, the largest majority of the published MRI radiomics studies takes into account histogram features (considered alone or in more advanced models based also on textural, shape, and filtered ones), supporting systematic investigations in this direction [28, .

Unfortunately, no consensus has been reached in the literature about the role and the potential biological correlates of the radiomics features that have been identified in the studies published so far. In their recent review, Staal and colleagues systematically point out this pitfall, shedding a light on the complex translational impact of the published observations, but also pointing out interesting correlations that deserve to be further explored, such as the one between tumor heterogeneity, image homogeneity, and generally favorable patients' outcomes [141] .

Besides traditional diagnostic imaging, the recent introduction of MR-guided radiotherapy (MRgRT) paves the way to innovative clinical approaches, including promising modelling applications for hybrid imaging TA and radiomics analysis [173] [174] [175] . Although the published evidence is still scarce and exploratory, rectal cancer hybrid imaging appears indeed to have significant potentialities for the set-up of radiomics-based prediction models. A first hypothesis generating experience identified two delta radiomics features (∆L_least and ∆glnu) as possible candidate predictors of a complete response (cCR) after rectal cancer neoadjuvant therapy using 0.35 T setup images [28] . The model was then externally validated using independent cohorts and achieved remarkable performances for both cCR and pCR (accuracy for cCR prediction: ∆Lleast = 81% and ∆glnu = 63%; accuracy for pCR prediction: ∆Lleast 79% and ∆glnu = 40%), confirming the interest in applying radiomics to hybrid MR images [150] . These observations may lead to a new generation of innovative trials, personalizing a patient's treatment based on imaging-based prediction results (clinical trials NCT04815694).

Besides MRI-based investigations, a more limited number of papers explore the performances of PET-CT for response prediction, obtaining overall unsatisfactory results in terms of prediction performances, probably due to technical reasons relative to PET imaging formats that still remain unsolved [176] [177] [178] [179] [180] .

Radiomics and TA therefore represent a promising field of investigation for rectal cancer and may support the continuous development of accurate prediction models, integrating the variables extracted from different omics domains in a holistic and fully personalized treatment approach [181, 182] .

All the above-mentioned studies have shown the promising direction of using radiomics in the field of neoadjuvant therapies. Despite an impressive number of retrospective studies, the number of prospective clinical trials investigating the potential role of texture analysis in neoadjuvant radiotherapy remains inexplicably low (see Table 1 ). There still are major limitations to solve before TA can be successfully applied in the clinical management of cancer patients. More specifically, the current major pitfalls in TA are the lack of image standardization, the lack of feature extraction standardization, the problems related to data sharing, and the distrust of the clinicians in the black box approach.

All the variations in scanning devices, acquisition protocols, and parameters of reconstructions may impact on the process of feature extraction and analysis. Although different standardization techniques may calibrate and overcome partially this problem [183] [184] [185] [186] , the ideal solution is to standardize the image acquisition in dedicated prospective trials.

Similarly, the process of feature extraction is often challenging and can lead to several biases that impact the reliability of the TA parameters among different institutions. Hopefully, with the help of artificial intelligence and the optimization of machine learning approaches, the limitations of feature extraction (ROI segmentation, feature selection, and endpoint correlation) should be overcome in the foreseeable future [187] [188] [189] [190] [191] .

At the same time, sample size in TA research represents a drawback in current research, as most studies cited above cover a limited number of patients. The use of big data, instead, could overcome this problem, and could ensure a higher statistical significance in the interpretation of the data. Thus, several efforts should be made in the development of high-number and high-quality shared databases in the future. These datasets require joint efforts by both companies and institutions, such as the Cancer Learning Intelligence Network for Quality and Flatiron Health and the Cancer Imaging Archive. At the same time, the development and maintenance of such shared databases require high standards of security, in order to respect patients' privacy and actual law order in terms of data sharing and data privacy.

The texture parameters are somehow difficult to describe and to refer to known clinical variables; as a consequence, TA looks like a black box to clinicians, as the connection between the TA parameters and the endpoints is not fully understood. Nonetheless, more should be done in order to correlate radiomics to the underlying clinical and molecular connotation with approaches such as radiogenomics; at the same time, more should be learned about artificial intelligence and radiomics by the clinicians [192, 193] .

Currently, many researchers are investigating methods to diminish the black box perception [194] . These two processes together can help to empty the gap and to remove the black box uncertainties, in order to promote TA towards clinical practice.

Despite these pitfalls, TA analysis can still aspire to become an optimal surrogate biomarker. In this context, research efforts should be concentrated precisely on the field of neoadjuvant therapies. In this setting, in fact, it is easier to test different approaches because the endpoint is usually the pathological response, which is more immediate to accomplish. In this field, the clinicians could trust more easily in radiomics, if they are called to test an effective and reliable model. For this reason, neoadjuvant therapy represents the ideal playground for TA and a higher number of prospective trials should be ideated and conducted in the next future.

Finally, future combination of radiomics analysis in the setting of immunotherapy is needed in the next years. This interesting challenge is particularly important, as imaging is always used in the clinical management of cancer patients, and TA may in the future provide useful information regarding the molecular characteristics of cancer, which may differ from a biopsy due to the accumulation of multiple genetic mutations and epigenetic alterations. 

Neoadjuvant chemotherapy with FOLFIRINOX and preoperative chemoradiotherapy for patients with locally advanced rectal cancer (UNICANCER-PRODIGE 23): A multicentre, randomised, open-label, phase 3 trial

Short-course radiotherapy followed by chemotherapy before total mesorectal excision (TME) versus preoperative chemoradiotherapy, TME, and optional adjuvant chemotherapy in locally advanced rectal cancer (RAPIDO): A randomised, open-label

Preoperative radiotherapy plus surgery versus surgery alone for patients with primary retroperitoneal sarcoma (EORTC-62092: STRASS): A multicentre, open-label, randomised, phase 3 trial

RACE-trial: Neoadjuvant radiochemotherapy versus chemotherapy for patients with locally advanced, potentially resectable adenocarcinoma of the gastroesophageal junction-A randomized phase III joint study of the AIO, ARO and DGAV

Neoadjuvant chemotherapy versus neoadjuvant chemoradiotherapy for locally advanced oesophageal squamous cell carcinoma: A single-Centre, open-label, randomized, controlled, clinical trial (HCHTOG1903)

Optimizing Survival of Patients with Marginally Operable Stage IIIA Non-Small-Cell Lung Cancer Receiving Chemoradiotherapy with or Without Surgery

Neoadjuvant radiotherapy for locally advanced and high-risk breast cancer

RECIST 1.1-Update and clarification: From the RECIST committee

Relationship between the Temporal Changes in Positron-Emission-Tomography-Imaging-Based Textural Features and Pathologic Response and Survival in Esophageal Cancer Patients

Predicting Response to Neoadjuvant Chemoradiotherapy in Esophageal Cancer with Textural Features Derived from Pretreatment (18)F-FDG PET/CT Imaging

18F-FDG PET uptake characterization through texture analysis: Investigating the complementary nature of heterogeneity and functional tumor volume in a multi-cancer site patient cohort

Addition of HER2 and CD44 to (18)F-FDG PET-based clinico-radiomic models enhances prediction of neoadjuvant chemoradiotherapy response in esophageal cancer

How to Increase the Efficacy of Immunotherapy in NSCLC and HNSCC: Role of Radiation Therapy

The effects of radiotherapy on the survival of patients with unresectable non-small cell lung cancer

Hypofractionated radiation therapy in the management of locally advanced NSCLC: A narrative review of the literature on behalf of the Italian Association of Radiation Oncology (AIRO)-Lung Working Group

Locally advanced inoperable primary or recurrent non-small cell lung cancer treated with 4-week hypofractionated radiation therapy (3 Gy/fraction)

18F-FDG PET/CT and whole-body MRI diagnostic performance in M staging for non-small cell lung cancer: A systematic review and meta-analysis

Update on nodal staging in non-small cell lung cancer with integrated positron emission tomography/computed tomography: A meta-analysis

FDG PET for the detection of non-small-cell lung cancer (NSCLC): A protocol for a network meta-analysis of diagnostic test accuracy

Developments in the management of bone metastases with interventional radiology

Validation of DWI in assessment of radiotreated bone metastases in elderly patients

Mesenchymal stromal cells having inactivated RB1 survive following low irradiation and accumulate damaged DNA: Hints for side effects following radiotherapy

Radiomics predicts survival of patients with advanced non-small cell lung cancer undergoing PD-1 blockade using Nivolumab

Is multidisciplinary management possible in the treatment of lung cancer? A report from three Italian meetings

Clinical applications of textural analysis in non-small cell lung cancer

Radiomics in NSCLC: State of the art and a proposal for harmonization of methodology

Role of artificial intelligence in the care of patients with nonsmall cell lung cancer

Radiogenomics of lung cancer

Radiomics for Response and Outcome Assessment for Non-Small Cell Lung Cancer

Imaging-Based Prediction of Molecular Therapy Targets in NSCLC by Radiogenomics and AI Approaches: A Systematic Review

Imaging of adrenal incidentaloma: Our experience

Improving image quality with model-based iterative reconstruction algorithm for chest CT in children with reduced contrast concentration

Minor components of micropapillary and solid subtypes in lung invasive adenocarcinoma (≤3 cm): PET/CT findings and correlations with lymph node metastasis

Classification of lung nodules based on CT images using squeeze-and-excitation network and aggregated residual transformations

Radiotherapy plus chemotherapy with or without surgical resection for stage III non-small-cell lung cancer: A phase III randomised controlled trial

Randomized controlled trial of resection versus radiotherapy after induction chemotherapy in stage IIIA-N2 non-small-cell lung cancer

Radiomic phenotype features predict pathological response in non-small cell lung cancer

Radiomic-Based Pathological Response Prediction from Primary Tumors and Lymph Nodes in NSCLC

Tumor volume as a potential imaging-based risk-stratification factor in trimodality therapy for locally advanced non-small cell lung cancer

Quantitative CT variables enabling response prediction in neoadjuvant therapy with EGFR-TKIs: Are they different from those in neoadjuvant concurrent chemoradiotherapy

Predicting pathologic response to neoadjuvant chemoradiation in resectable stage III non-small cell lung cancer patients using computed tomography radiomic features

The pathology of soft tissue sarcomas

Soft tissue sarcomas in the precision medicine era: New advances in clinical practice and future perspectives

A matched cohort study of radio-chemotherapy versus radiotherapy alone in soft tissue sarcoma patients

Influence of age and subtype in outcome of operable liposarcoma

The role of core needle biopsy in the diagnosis of suspected soft tissue tumours

UK guidelines for the management of soft tissue sarcomas

Neoadjuvant treatment of soft tissue sarcoma

Soft tissue sarcomas: New opportunity of treatment with PARP inhibitors?

High-risk soft tissue sarcomas treated with perioperative chemotherapy: Improving prognostic classification in a randomised clinical trial

Validated prediction of clinical outcome in sarcomas and multiple types of cancer on the basis of a gene expression signature related to genome complexity

Diffusion-weighted imaging for the cellularity assessment and matrix characterization of soft tissue tumour

Whole-tumor 3D volumetric MRI-based radiomics approach for distinguishing between benign and malignant soft tissue tumors

MRI-based radiomics to predict lipomatous soft tissue tumors malignancy: A pilot study

Radiomics approach to distinguish between well differentiated liposarcomas and lipomas on MRI

Radiomics and Machine Learning Differentiate Soft-Tissue Lipoma and Liposarcoma Better than Musculoskeletal Radiologists

Radiomic features from MRI distinguish myxomas from myxofibrosarcomas

Preliminary utilization of radiomics in differentiating uterine sarcoma from atypical leiomyoma: Comparison on diagnostic efficacy of MRI features and radiomic features

Preoperative Differentiation of Uterine Sarcoma from Leiomyoma: Comparison of Three Models Based on Different Segmentation Volumes Using Radiomics

A combined radiomics and clinical variables model for prediction of malignancy in T2 hyperintense uterine mesenchymal tumors on MRI

Magnetic Resonance Imaging-Based Radiomics Nomogram for Prediction of the Histopathological Grade of Soft Tissue Sarcomas: A Two-Center Study

Soft Tissue Sarcoma: Preoperative MRI-Based Radiomics and Machine Learning May Be Accurate Predictors of Histopathologic Grade

Tumor grading of soft tissue sarcomas using MRI-based radiomics

Radiomics and Machine Learning with Multiparametric Preoperative MRI May Accurately Predict the Histopathological Grades of Soft Tissue Sarcomas

CT-based radiomic features predict tumor grading and have prognostic value in patients with soft tissue sarcomas treated with neoadjuvant radiation therapy

Soft Tissue Sarcomas: Preoperative Predictive Histopathological Grading Based on Radiomics of MRI

Radiomic analysis of soft tissues sarcomas can distinguish intermediate from high-grade lesions

Radiomics-based machine-learning method for prediction of distant metastasis from soft-tissue sarcomas

Can radiomics improve the prediction of metastatic relapse of myxoid/round cell liposarcomas?

Deep multi-modality collaborative learning for distant metastases predication in PET-CT soft-tissue sarcoma studies

A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities

Prognostic Assessment in High-Grade Soft-Tissue Sarcoma Patients: A Comparison of Semantic Image Analysis and Radiomics

MRI Radiomic Features Are Independently Associated With Overall Survival in Soft Tissue Sarcoma

CT-response patterns and the role of CT-textural features in inoperable abdominal/retroperitoneal soft tissue sarcomas treated with trabectedin

Local recurrence of soft tissue sarcoma: A radiomic analysis

T2 -based MRI Delta-radiomics improve response prediction in soft-tissue sarcomas treated by neoadjuvant chemotherapy

Response assessment to neoadjuvant therapy in soft tissue sarcomas: Using CT texture analysis in comparison to tumor size, density, and perfusion

CT-morphologic and CT-textural patterns of response in inoperable soft tissue sarcomas treated with pazopanib-a preliminary retrospective cohort study

Magnetic resonance imaging assessment of chemotherapy-related adipocytic maturation in myxoid/round cell liposarcomas: Specificity and prognostic value

Treatment effect prediction for sarcoma patients treated with preoperative radiotherapy using radiomics features from longitudinal diffusion-weighted MRIs

Systematic review of sarcomas radiomics studies: Bridging the gap between concepts and clinical applications?

ESMO Consensus Guidelines for management of patients with colon and rectal cancer. a personalized approach to clinical decision making

Construction of the Prediction Model for Locally Advanced Rectal Cancer Following Neoadjuvant Chemoradiotherapy Based on Pretreatment Tumor-Infiltrating Macrophage-Associated Biomarkers

Prognostic and predictive value of neutrophil-tolymphocyte ratio after curative rectal cancer resection: A systematic review and meta-analysis

Gut Microbiome Components Predict Response to Neoadjuvant Chemoradiotherapy in Patients with Locally Advanced Rectal Cancer: A Prospective

Trends in combined radio-chemotherapy for locally advanced rectal cancer: A survey among radiation oncology centers of Sicily region on behalf of AIRO

Dynamic contrast-enhanced magnetic resonance imaging in locally advanced rectal cancer: Role of perfusion parameters in the assessment of response to treatment

A comparative analysis between radiation dose intensification and conventional fractionation in neoadjuvant locally advanced rectal cancer: A monocentric prospective observational study

Usefulness of magnetic resonance volumetric evaluation in predicting response to preoperative concurrent chemoradiotherapy in patients with resectable rectal cancer

Rectal cancer: MR imaging before neoadjuvant chemotherapy and radiation therapy for prediction of tumor-free circumferential resection margins and long-term survival

Locally advanced rectal cancer: MR imaging in prediction of response after preoperative chemotherapy and radiation therapy

18F-FDG PET is an early predictor of pathologic tumor response to preoperative radiochemotherapy in locally advanced rectal cancer

The predictive value of metabolic response to preoperative radiochemotherapy in locally advanced rectal cancer measured by PET/CT

Radiomics and Magnetic Resonance Imaging of Rectal Cancer: From Engineering to Clinical Practice

Predicting pathological response to chemoradiotherapy for rectal cancer: A systematic review

Radiomics for the Prediction of Treatment Outcome and Survival in Patients with Colorectal Cancer: A Systematic Review

QUADAS-2: A revised tool for the quality assessment of diagnostic accuracy studies

Radiomics: The bridge between medical imaging and personalized medicine

Diagnostic accuracy of MRI for assessment of T category, lymph node metastases, and circumferential resection margin involvement in patients with rectal cancer: A systematic review and meta-analysis

Pre-Treatment T2-WI Based Radiomics Features for Prediction of Locally Advanced Rectal Cancer Non-Response to Neoadjuvant Chemoradiotherapy: A Preliminary Study

Radiomic Features of Primary Rectal Cancers on Baseline T(2)-Weighted MRI Are Associated With Pathologic Complete Response to Neoadjuvant Chemoradiation: A Multisite Study

MR-based artificial intelligence model to assess response to therapy in locally advanced rectal cancer

Deep learning-based radiomic features for improving neoadjuvant chemoradiation response prediction in locally advanced rectal cancer

Magnetic resonance based texture parameters as potential imaging biomarkers for predicting long-term survival in locally advanced rectal cancer treated by chemoradiotherapy

Delta radiomics for rectal cancer response prediction using low field magnetic resonance guided radiotherapy: An external validation

Potential of MR histogram analyses for prediction of response to chemotherapy in patients with colorectal hepatic metastases

Radiomics analysis of multiparametric MRI for prediction of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer

Fractal-based radiomic approach to predict complete pathological response after chemo-radiotherapy in rectal cancer

Magnetic Resonance, Vendor-independent, Intensity Histogram Analysis Predicting Pathologic Complete Response After Radiochemotherapy of Rectal Cancer

Development of a Joint Prediction Model Based on Both the Radiomics and Clinical Factors for Predicting the Tumor Response to Neoadjuvant Chemoradiotherapy in Patients with Locally Advanced Rectal Cancer

Haralick−s texture features for the prediction of response to therapy in colorectal cancer: A preliminary study

Multi-modal radiomics model to predict treatment response to neoadjuvant chemotherapy for locally advanced rectal cancer

Machine Learning-based Analysis of Rectal Cancer MRI Radiomics for Prediction of Metachronous Liver Metastasis

Locally advanced rectal cancer: Predicting non-responders to neoadjuvant chemoradiotherapy using apparent diffusion coefficient textures

MRI texture analysis in predicting treatment response to neoadjuvant chemoradiotherapy in rectal cancer

Novel radiomic signature as a prognostic biomarker for locally advanced rectal cancer

Texture analysis as imaging biomarker of tumoral response to neoadjuvant chemoradiotherapy in rectal cancer patients studied with 3-T magnetic resonance

Performance of diffusion-weighted imaging, perfusion imaging, and texture analysis in predicting tumoral response to neoadjuvant chemoradiotherapy in rectal cancer patients studied with 3T MR: Initial experience

Magnetic-Resonance-Imaging Texture Analysis Predicts Early Progression in Rectal Cancer Patients Undergoing Neoadjuvant Chemoradiation

Rectal Cancer: Assessment of Neoadjuvant Chemoradiation Outcome based on Radiomics of Multiparametric MRI

Intravoxel Incoherent Motion-derived Histogram Metrics for Assessment of Response after Combined Chemotherapy and Radiation Therapy in Rectal Cancer: Initial Experience and Comparison between Single-Section and Volumetric Analyses

Could perfusion heterogeneity at dynamic contrast-enhanced MRI be used to predict rectal cancer sensitivity to chemoradiotherapy?

MRI features and texture analysis for the early prediction of therapeutic response to neoadjuvant chemoradiotherapy and tumor recurrence of locally advanced rectal cancer

Clinical utility of radiomics at baseline rectal MRI to predict complete response of rectal cancer after chemoradiation therapy

Radiomics of MRI for pretreatment prediction of pathologic complete response, tumor regression grade, and neoadjuvant rectal score in patients with locally advanced rectal cancer undergoing neoadjuvant chemoradiation: An international multicenter study

MRI T2-weighted sequences-based texture analysis (TA) as a predictor of response to neoadjuvant chemo-radiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC)

Primary and post-chemoradiotherapy MRI detection of extramural venous invasion in rectal cancer: The role of diffusion-weighted imaging

MR-Guided Radiotherapy for Rectal Cancer: Current Perspective on

MR-guided radiotherapy in rectal cancer: First clinical experience of an innovative technology

Online MR guided radiotherapy for rectal cancer

)F-FDG PET/CT for Therapy Response Assessment and Prognosis in Patients with Locally Advanced Rectal Cancer

Prediction of neoadjuvant radiation chemotherapy response and survival using pretreatment [(18)F]FDG PET/CT scans in locally advanced rectal cancer

FDG PET/CT radiomics for predicting the outcome of locally advanced rectal cancer

Pretreatment CT and PET radiomics predicting rectal cancer patients in response to neoadjuvant chemoradiotherapy

Predicting locally advanced rectal cancer response to neoadjuvant therapy with (18)F-FDG PET and MRI radiomics features

Personalized radiotherapy: Concepts, biomarkers and trial design

The Role of Artificial Intelligence in Managing Multimorbidity and Cancer

Stability of radiomic features in CT perfusion maps

Quantitative radiomics studies for tissue characterization: A review of technology and methodological procedures

Texture Analysis Challenges: Influence of Acquisition and Reconstruction Parameters: A Comprehensive Review

Buvat, I. A Postreconstruction Harmonization Method for Multicenter Radiomic Studies in PET

Deep Learning-based Image Conversion of CT Reconstruction Kernels Improves Radiomics Reproducibility for Pulmonary Nodules or Masses

El Naqa, I. Machine and deep learning methods for radiomics

Application of Radiomics for the Prediction of Radiation-Induced Toxicity in the IMRT Era: Current State-of-the-Art

Artificial Intelligence in radiotherapy: State of the art and future directions

The Rise of Radiomics and Implications for Oncologic Management

Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology

Overcoming Interpretability in Deep Learning Cancer Classification

Funding: This research was funded by SIRM foundation.

The authors declare no conflict of interest.