Investigation of Radiation-Induced Toxicity in Head and Neck Cancer Patients through Radiomics and Machine Learning: A Systematic Review

Genetic profiling in radiotherapy: a comprehensive review

This comprehensive review explores the pivotal role of radiotherapy in cancer treatment, emphasizing the diverse applications of genetic profiling. The review highlights genetic markers for predicting radiation toxicity, enabling personalized treatment planning. It delves into the impact of genetic profiling on radiotherapy strategies across various cancer types, discussing research findings related to treatment response, prognosis, and therapeutic resistance. The integration of genetic profiling is shown to transform cancer treatment paradigms, offering insights into personalized radiotherapy regimens and guiding decisions in cases where standard protocols may fall short. Ultimately, the review underscores the potential of genetic profiling to enhance patient outcomes and advance precision medicine in oncology.

Radiomics Beyond the Hype: A Critical Evaluation Toward Oncologic Clinical Use

Radiomics is a promising and fast-developing field within oncology that involves the mining of quantitative high-dimensional data from medical images. Radiomics has the potential to transform cancer management, whereby radiomics data can be used to aid early tumor characterization, prognosis, risk stratification, treatment planning, treatment response assessment, and surveillance. Nevertheless, certain challenges have delayed the clinical adoption and acceptability of radiomics in routine clinical practice. The objectives of this report are to (a) provide a perspective on the translational potential and potential impact of radiomics in oncology; (b) explore frequent challenges and mistakes in its derivation, encompassing study design, technical requirements, standardization, model reproducibility, transparency, data sharing, privacy concerns, quality control, as well as the complexity of multistep processes resulting in less radiologist-friendly interfaces; (c) discuss strategies to overcome these challenges and mistakes; and (d) propose measures to increase the clinical use and acceptability of radiomics, taking into account the different perspectives of patients, health care workers, and health care systems. Keywords: Radiomics, Oncology, Cancer Management, Artificial Intelligence © RSNA, 2024.

Predicting the need for a replan in oropharyngeal cancer: A radiomic, clinical, and dosimetric model

BACKGROUND

Patients with oropharyngeal cancer (OPC) treated with chemoradiation can experience weight loss and tumor shrinkage, altering the prescribed treatment. Treatment replanning ensures patients do not receive excessive doses to normal tissue. However, it is a time- and resource-intensive process, as it takes 1 to 2 weeks to acquire a new treatment plan, and during this time, overtreatment of normal tissues could lead to increased toxicities. Currently, there are limited prognostic factors to determine which patients will require a replan. There remains an unmet need for predictive models to assist in identifying patients who could benefit from the knowledge of a replan prior to treatment.

PURPOSE

We aimed to develop and evaluate a CT-based radiomic model, integrating clinical and dosimetric information, to predict the need for a replan prior to treatment.

METHODS

A dataset of patients (n = 315) with OPC treated with chemoradiation was used for this study. The dataset was split into independent training (n = 220) and testing (n = 95) datasets. Tumor volumes and organs at risk (OARs) were contoured on planning CT images. PyRadiomics was used to compute radiomic image features (n = 1218) on the original and filtered images from each of the primary tumor, nodal volumes, and ipsilateral and contralateral parotid glands. Nine clinical features and nine dose features extracted from the OARs were collected and those significantly (p < 0.05) associated with the need for a replan in the training dataset were used in a baseline model. Random forest feature selection was applied to select the optimal radiomic features to predict replanning. Logistic regression, Naïve Bayes, support vector machine, and random forest classifiers were built using the non-correlated selected radiomic, clinical, and dose features on the training dataset and performance was assessed in the testing dataset. The area under the curve (AUC) was used to assess the prognostic value.

RESULTS

A total of 78 patients (25%) required a replan. Smoking status, nodal stage, base of tongue subsite, and larynx mean dose were found to be significantly associated with the need for a replan in the training dataset and incorporated into the baseline model, as well as into the combined models. Five predictive radiomic features were selected (one nodal volume, one primary tumor, two ipsilateral and one contralateral parotid gland). The baseline model comprised of clinical and dose features alone achieved an AUC of 0.66 [95% CI: 0.51-0.79] in the testing dataset. The random forest classifier was the top-performing radiomics model and achieved an AUC of 0.82 [0.75-0.89] in the training dataset and an AUC of 0.78 [0.68-0.87] in the testing dataset, which significantly outperformed the baseline model (p = 0.023, testing dataset).

CONCLUSIONS

This is the first study to use radiomics from the primary tumor, nodal volumes, and parotid glands for the prediction of replanning for patients with OPC. Radiomic features augmented clinical and dose features for predicting the need for a replan in our testing dataset. Once validated, this model has the potential to assist physicians in identifying patients that may benefit from a replan, allowing for better resource allocation and reduced toxicities.

Impact of radiation dose on patient-reported acute taste alteration in a prospective observational study cohort in head and neck squamous cell cancer (HNSCC)

PURPOSE

Taste alteration (TA) is a frequent acute side effect of radiation treatment in HNSCC patients. Principal aim of our study was to investigate dosimetric parameters in relation to patient-assessed taste impairment in a prospective cohort treated with intensity-modulated radiotherapy.

METHODS

All patients with locally advanced HNSCC and amenable to radical treatment were included. Chemotherapy-induced taste alteration scale (CITAS), EORTC QLQ-C30 and QLQ-HN43 questionnaires at baseline (T0), 3 weeks (T1) and 3 months (T2) after radiotherapy conclusion were used to assess taste impairment. Base of tongue, submandibular glands (SG), parotid glands (PG) and taste buds, along with anterior and medium third of the tongue, were considered as organs at risk and thus delineated according to consensus guidelines. The mean dose to the above-mentioned structures was correlated with patient-reported outcomes.

RESULTS

Between September 2019 and November 2020, 33 patients were recruited, 31 of which analyzed. 71% had oropharyngeal carcinoma, mostly HPV-related (60%). All were treated with tomotherapy. 77.4% had concurrent cisplatin. Mean scores of general taste alterations, global health status and dry mouth and sticky saliva were assessed. The mean doses to the anterior third, medium third and base of the tongue were 23.85, 35.50 and 47.67 Gy, respectively. Taste buds received 32.72 Gy; right and left parotid 25 and 23 Gy; right and left submandibular glands 47.8 and 39.4 Gy. At univariate analysis, dysgeusia correlated with SG mean dose (95% CI 0-0.02 p = 0.05) and PG mean dose (95% CI 0-0.02 p = 0.05); dry mouth with mean dose to anterior (95% CI 0.03-1.47 p = 0.04) and medium third (95% CI 0.02-0.93 p = 0.04) of the tongue, to taste buds (95% CI 0.06-0.96 p = 0.03) and to SGs (95% CI 0.06-0.63 p = 0.02); pain mouth with mean dose to taste buds (95% CI 0-0.02 p = 0.04), to SGs (95% CI 0-0.03 p = 0.03) and to base tongue (95% CI 0-0.02 p = 0.02).

CONCLUSIONS

Our analysis supports the influence of dose distribution on the development of TA in HNSCC patients. The contribution of dose to taste buds and tongue subvolumes remains unclear and worthy of further investigation.

Artificial Intelligence in Head and Neck Cancer: A Systematic Review of Systematic Reviews

INTRODUCTION

Several studies have emphasized the potential of artificial intelligence (AI) and its subfields, such as machine learning (ML), as emerging and feasible approaches to optimize patient care in oncology. As a result, clinicians and decision-makers are faced with a plethora of reviews regarding the state of the art of applications of AI for head and neck cancer (HNC) management. This article provides an analysis of systematic reviews on the current status, and of the limitations of the application of AI/ML as adjunctive decision-making tools in HNC management.

METHODS

Electronic databases (PubMed, Medline via Ovid, Scopus, and Web of Science) were searched from inception until November 30, 2022. The study selection, searching and screening processes, inclusion, and exclusion criteria followed the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines. A risk of bias assessment was conducted using a tailored and modified version of the Assessment of Systematic Review (AMSTAR-2) tool and quality assessment using the Risk of Bias in Systematic Reviews (ROBIS) guidelines.

RESULTS

Of the 137 search hits retrieved, 17 fulfilled the inclusion criteria. This analysis of systematic reviews revealed that the application of AI/ML as a decision aid in HNC management can be thematized as follows: (1) detection of precancerous and cancerous lesions within histopathologic slides; (2) prediction of the histopathologic nature of a given lesion from various sources of medical imaging; (3) prognostication; (4) extraction of pathological findings from imaging; and (5) different applications in radiation oncology. In addition, the challenges in implementation of AI/ML models for clinical evaluations include the lack of standardized methodological guidelines for the collection of clinical images, development of these models, reporting of their performance, external validation procedures, and regulatory frameworks.

CONCLUSION

At present, there is a paucity of evidence to suggest the adoption of these models in clinical practice due to the aforementioned limitations. Therefore, this manuscript highlights the need for development of standardized guidelines to facilitate the adoption and implementation of these models in the daily clinical practice. In addition, adequately powered, prospective, randomized controlled trials are urgently needed to further assess the potential of AI/ML models in real-world clinical settings for the management of HNC.

Radiomics and dosiomics-based prediction of radiotherapy-induced xerostomia in head and neck cancer patients

BACKGROUND AND AIM

Dose-response modeling for radiotherapy-induced xerostomia in head and neck cancer (HN) patients is a promising frontier for personalized therapy. Feature extraction from diagnostic and therapeutic images (radiomics and dosiomics features) can be used for data-driven response modeling. The aim of this study is to develop xerostomia predictive models based on radiomics-dosiomics features.

METHODS

Data from the cancer imaging archive (TCIA) for 31 HN cancer patients were employed. For all patients, parotid CT radiomics features were extracted, utilizing Lasso regression for feature selection and multivariate modeling. The models were developed by selected features from pretreatment (CT1), mid-treatment (CT2), post-treatment (CT3), and delta features (ΔCT2-1, ΔCT3-1, ΔCT3-2). We also considered dosiomics features extracted from the parotid dose distribution images (Dose model). Thus, combination models of radio-dosiomics (CT + dose & ΔCT + dose) were developed. Moreover, clinical, and dose-volume histogram (DVH) models were built. Nested 10-fold cross-validation was used to assess the predictive classification of patients into those with and without xerostomia, and the area under the receiver operative characteristic curve (AUC) was used to compare the predictive power of the models. The sensitivity and accuracy of models also were obtained.

RESULTS

In total, 59 parotids were assessed, and 13 models were developed. Our results showed three models with AUC of 0.89 as most predictive, namely ΔCT2-1 + Dose (Sensitivity 0.99, Accuracy 0.94 & Specificity 0.86), CT3 model (Sensitivity 0.96, Accuracy 0.94 & Specificity 0.86) and DVH (Sensitivity 0.93, Accuracy 0.89 & Specificity 0.84). These models were followed by Clinical (AUC 0.89, Sensitivity 0.81, Accuracy 0.97 & Specificity 0.89) and CT2 & Dose (AUC 0.86, Sensitivity 0.97, Accuracy 0.87 & Specificity 0.82). The Dose model (developed by dosiomics features only) had AUC, Sensitivity, Specificity, and Accuracy of 0.72, 0.98, 0.33, and 0.79 respectively.

CONCLUSION

Quantitative features extracted from diagnostic imaging during and after radiotherapy alone or in combination with dosiomics markers obtained from dose distribution images can be used for radiotherapy response modeling, opening up prospects for personalization of therapies toward improved therapeutic outcomes.

Computational Intelligence in Cancer Diagnostics: A Contemporary Review of Smart Phone Apps, Current Problems, and Future Research Potentials

Cancer is a dangerous and sometimes life-threatening disease that can have several negative consequences for the body, is a leading cause of mortality, and is becoming increasingly difficult to detect. Each form of cancer has its own set of traits, symptoms, and therapies, and early identification and management are important for a positive prognosis. Doctors utilize a variety of approaches to detect cancer, depending on the kind and location of the tumor. Imaging tests such as X-rays, Computed Tomography scans, Magnetic Resonance Imaging scans, and Positron Emission Tomography (PET) scans, which may provide precise pictures of the body's interior structures to spot any abnormalities, are some of the tools that doctors use to diagnose cancer. This article evaluates computational-intelligence approaches and provides a means to impact future work by focusing on the relevance of machine learning and deep learning models such as K Nearest Neighbour (KNN), Support Vector Machine (SVM), Naïve Bayes, Decision Tree, Deep Neural Network, Deep Boltzmann machine, and so on. It evaluates information from 114 studies using Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR). This article explores the advantages and disadvantages of each model and provides an outline of how they are used in cancer diagnosis. In conclusion, artificial intelligence shows significant potential to enhance cancer imaging and diagnosis, despite the fact that there are a number of clinical issues that need to be addressed.

Machine learning for the prediction of toxicities from head and neck cancer treatment: A systematic review with meta-analysis

INTRODUCTION

The aim of the present systematic review (SR) is to summarize Machine Learning (ML) models currently used to predict head and neck cancer (HNC) treatment-related toxicities, and to understand the impact of image biomarkers (IBMs) in prediction models (PMs). The present SR was conducted following the guidelines of the PRISMA 2022 and registered in PROSPERO database (CRD42020219304).

METHODS

The acronym PICOS was used to develop the focused review question (Can PMs accurately predict HNC treatment toxicities?) and the eligibility criteria. The inclusion criteria enrolled Prediction Model Studies (PMSs) with patient cohorts that were treated for HNC and developed toxicities. Electronic database search encompassed PubMed, EMBASE, Scopus, Cochrane Library, Web of Science, LILACS, and Gray Literature (Google Scholar and ProQuest). Risk of Bias (RoB) was assessed through PROBAST and the results were synthesized based on the data format (with and without IBMs) to allow comparison.

RESULTS

A total of 28 studies and 4,713 patients were included. Xerostomia was the most frequently investigated toxicity (17; 60.71 %). Sixteen (57.14 %) studies reported using radiomics features in combination with clinical or dosimetrics/dosiomics for modelling. High RoB was identified in 23 studies. Meta-analysis (MA) showed an area under the receiver operating characteristics curve (AUROC) of 0.82 for models with IBMs and 0.81 for models without IBMs (p value < 0.001), demonstrating no difference among IBM- and non-IBM-based models.

DISCUSSION

The development of a PM based on sample-specific features represents patient selection bias and may affect a model's performance. Heterogeneity of the studies as well as non-standardized metrics prevent proper comparison of studies, and the absence of an independent/external test does not allow the evaluation of the model's generalization ability.

CONCLUSION

IBM-featured PMs are not superior to PMs based on non-IBM predictors. The evidence was appraised as of low certainty.

Systematic review of the radiomics quality score applications: an EuSoMII Radiomics Auditing Group Initiative

OBJECTIVE

The main aim of the present systematic review was a comprehensive overview of the Radiomics Quality Score (RQS)-based systematic reviews to highlight common issues and challenges of radiomics research application and evaluate the relationship between RQS and review features.

METHODS

The literature search was performed on multiple medical literature archives according to PRISMA guidelines for systematic reviews that reported radiomic quality assessment through the RQS. Reported scores were converted to a 0-100% scale. The Mann-Whitney and Kruskal-Wallis tests were used to compare RQS scores and review features.

RESULTS

The literature research yielded 345 articles, from which 44 systematic reviews were finally included in the analysis. Overall, the median of RQS was 21.00% (IQR = 11.50). No significant differences of RQS were observed in subgroup analyses according to targets (oncological/not oncological target, neuroradiology/body imaging focus and one imaging technique/more than one imaging technique, characterization/prognosis/detection/other).

CONCLUSIONS

Our review did not reveal a significant difference of quality of radiomic articles reported in systematic reviews, divided in different subgroups. Furthermore, low overall methodological quality of radiomics research was found independent of specific application domains. While the RQS can serve as a reference tool to improve future study designs, future research should also be aimed at improving its reliability and developing new tools to meet an ever-evolving research space.

KEY POINTS

• Radiomics is a promising high-throughput method that may generate novel imaging biomarkers to improve clinical decision-making process, but it is an inherently complex analysis and often lacks reproducibility and generalizability. • The Radiomics Quality Score serves a necessary role as the de facto reference tool for assessing radiomics studies. • External auditing of radiomics studies, in addition to the standard peer-review process, is valuable to highlight common limitations and provide insights to improve future study designs and practical applicability of the radiomics models.

Predictive value of clinical and radiomic features for radiation therapy response in patients with lymph node-positive head and neck cancer

BACKGROUND

Prediction of survival and radiation therapy response is challenging in head and neck cancer with metastatic lymph nodes (LNs). Here we developed novel radiomics- and clinical-based predictive models.

METHODS

Volumes of interest of LNs were employed for radiomic features extraction. Radiomic and clinical features were investigated for their predictive value relatively to locoregional failure (LRF), progression-free survival (PFS), and overall survival (OS) and used to build multivariate models.

RESULTS

Hundred and six subjects were suitable for final analysis. Univariate analysis identified two radiomic features significantly predictive for LRF, and five radiomic features plus two clinical features significantly predictive for both PFS and OS. The area under the curve of receiver operating characteristic curve combining clinical and radiomic predictors for PFS and OS resulted 0.71 (95%CI: 0.60-0.83) and 0.77 (95%CI: 0.64-0.89).

CONCLUSIONS

Radiomic and clinical features resulted to be independent predictive factors, but external independent validation is mandatory to support these findings.

[18F]FDG PET/CT in head and neck squamous cell carcinoma: a head-to-head between visual point-scales and the added value of multi-modality imaging

BACKGROUND

Head and neck squamous cell carcinoma (HNSCC) represents the 6th leading cancer worldwide. In most cases, patients present a locally advanced disease at diagnosis and non-surgical curative treatment is considered the standard of care. Nowadays, [¹⁸F]FDG PET/CT is a validated tool in post-treatment evaluation, with a high level of evidence. However, to standardize imaging response, several visual scales have been proposed with none of them approved yet. The study's aim is a head-to-head comparison between the diagnostic performance of the Hopkins criteria, the Deauville score, and the new proposed Cuneo score, to establish their prognostic role. Secondly, we investigate the possible value of semiquantitative analysis, evaluating SUV_max and ΔSUV_max of the lymph node with the highest uptake on the restaging PET scan. Moreover, we also considered morphological features using the product of diameters measured on the co-registered CT images to assess the added value of hybrid imaging.

METHODS

We performed a retrospective analysis on histologically proven HNSCC patients who underwent baseline and response assessment [¹⁸F]FDG PET/CT. Post-treatment scans were reviewed according to Hopkins, Deauville, and Cuneo criteria, assigning a score to the primary tumor site and lymph nodes. A per-patient final score for each scale was chosen, corresponding to the highest score between the two sites. Diagnostic performance was then calculated for each score considering any evidence of locoregional progression in the first 3 months as the gold standard. Survival analysis was performed using the Kaplan-Meier method. SUV_max and its delta, as well as the product of diameters of the lymph node with the highest uptake at post-treatment scan, if present, were calculated.

RESULTS

A total of 43 patients were finally included in the study. Sensitivity, specificity, PPV, NPV, and accuracy were 87%, 86%, 76%, 92%, and 86% for the Hopkins score, whereas 93%, 79%, 70%, 96%, and 84% for the Deauville score, respectively. Conversely, the Cuneo score reached the highest specificity and PPV (93% and 78%, respectively) but the lowest sensitivity (47%), NPV (76%), and accuracy (77%). Each scale significantly correlated with PFS and OS. The ROC analysis of the combination of SUV_max and the product of diameters of the highest lymph node on the restaging PET scan reached an AUC of 0.822. The multivariate analysis revealed the Cuneo criteria and the product of diameters as prognostic factors for PFS.

CONCLUSIONS

Each visual score statistically correlated with prognosis thus demonstrating the reliability of point-scale criteria in HNSCC. The novel Cuneo score showed the highest specificity, but the lowest sensibility compared to Hopkins and Deauville criteria. Furthermore, the combination of PET data with morphological features could support the evaluation of equivocal cases.

Assessing the generalisability of radiomics features previously identified as predictive of radiation-induced sticky saliva and xerostomia

Background and purpose

While core to the scientific approach, reproducibility of experimental results is challenging in radiomics studies. A recent publication identified radiomics features that are predictive of late irradiation-induced toxicity in head and neck cancer (HNC) patients. In this study, we assessed the generalisability of these findings.

Materials and Methods

The procedure described in the publication in question was applied to a cohort of 109 HNC patients treated with 50-70 Gy in 20-35 fractions using helical radiotherapy although there were inherent differences between the two patient populations and methodologies. On each slice of the planning CT with delineated parotid and submandibular glands, the imaging features that were previously identified as predictive of moderate-to-severe xerostomia and sticky saliva 12 months post radiotherapy (Xer12m and SS12m) were calculated. Specifically, Short Run Emphasis (SRE) and maximum CT intensity (maxHU) were evaluated for improvement in prediction of Xer12m and SS12m respectively, compared to models solely using baseline toxicity and mean dose to the salivary glands.

Results

None of the associations previously identified as statistically significant and involving radiomics features in univariate or multivariate models could be reproduced on our cohort.

Conclusion

The discrepancies observed between the results of the two studies delineate limits to the generalisability of the previously reported findings. This may be explained by the differences in the approaches, in particular the imaging characteristics and subsequent methodological implementation. This highlights the importance of external validation, high quality reporting guidelines and standardisation protocols to ensure generalisability, replication and ultimately clinical implementation.

Utility of adding Radiomics to clinical features in predicting the outcomes of radiotherapy for head and neck cancer using machine learning

BACKGROUND

Radiomics involves the extraction of quantitative information from annotated Computed-Tomography (CT) images, and has been used to predict outcomes in Head and Neck Squamous Cell Carcinoma (HNSCC). Subjecting combined Radiomics and Clinical features to Machine Learning (ML) could offer better predictions of clinical outcomes. This study is a comparative performance analysis of ML models with Clinical, Radiomics, and Clinico-Radiomic datasets for predicting four outcomes of HNSCC treated with Curative Radiation Therapy (RT): Distant Metastases, Locoregional Recurrence, New Primary, and Residual Disease.

METHODOLOGY

The study used retrospective data of 311 HNSCC patients treated with radiotherapy between 2013-2018 at our centre. Binary prediction models were developed for the four outcomes with Clinical-only, Clinico-Radiomic, and Radiomics-only datasets, using three different ML classification algorithms namely, Random Forest (RF), Kernel Support Vector Machine (KSVM), and XGBoost. The best-performing ML algorithms of the three dataset groups was then compared.

RESULTS

The Clinico-Radiomic dataset using KSVM classifier provided the best prediction. Predicted mean testing accuracy for Distant Metastases, Locoregional Recurrence, New Primary, and Residual Disease was 97%, 72%, 99%, and 96%, respectively. The mean area under the receiver operating curve (AUC) was calculated and displayed for all the models using three dataset groups.

CONCLUSION

Clinico-Radiomic dataset improved the predictive ability of ML models over clinical features alone, while models built using Radiomics performed poorly. Radiomics data could therefore effectively supplement clinical data in predicting outcomes.

Gaps and Opportunities of Artificial Intelligence Applications for Pediatric Oncology in European Research: A Systematic Review of Reviews and a Bibliometric Analysis

The application of artificial intelligence (AI) systems is emerging in many fields in recent years, due to the increased computing power available at lower cost. Although its applications in various branches of medicine, such as pediatric oncology, are many and promising, its use is still in an embryonic stage. The aim of this paper is to provide an overview of the state of the art regarding the AI application in pediatric oncology, through a systematic review of systematic reviews, and to analyze current trends in Europe, through a bibliometric analysis of publications written by European authors. Among 330 records found, 25 were included in the systematic review. All papers have been published since 2017, demonstrating only recent attention to this field. The total number of studies included in the selected reviews was 674, with a third including an author with a European affiliation. In bibliometric analysis, 304 out of the 978 records found were included. Similarly, the number of publications began to dramatically increase from 2017. Most explored AI applications regard the use of diagnostic images, particularly radiomics, as well as the group of neoplasms most involved are the central nervous system tumors. No evidence was found regarding the use of AI for process mining, clinical pathway modeling, or computer interpreted guidelines to improve the healthcare process. No robust evidence is yet available in any of the domains investigated by systematic reviews. However, the scientific production in Europe is significant and consistent with the topics covered in systematic reviews at the global level. The use of AI in pediatric oncology is developing rapidly with promising results, but numerous gaps and challenges persist to validate its utilization in clinical practice. An important limitation is the need for large datasets for training algorithms, calling for international collaborative studies.

Novel Imaging Biomarkers to Assess Oncologic Treatment-Related Changes

Cancer therapeutics cause various treatment-related changes that may impact patient follow-up and disease monitoring. Although atypical responses such as pseudoprogression may be misinterpreted as treatment nonresponse, other changes, such as hyperprogressive disease seen with immunotherapy, must be recognized early for timely management. Radiation necrosis in the brain is a known response to radiotherapy and must be distinguished from local tumor recurrence. Radiotherapy can also cause adverse effects such as pneumonitis and local tissue toxicity. Systemic therapies, like chemotherapy and targeted therapies, are known to cause long-term cardiovascular effects. Thus, there is a need for robust biomarkers to identify, distinguish, and predict cancer treatment-related changes. Radiomics, which refers to the high-throughput extraction of subvisual features from radiologic images, has been widely explored for disease classification, risk stratification, and treatment-response prediction. Lately, there has been much interest in investigating the role of radiomics to assess oncologic treatment-related changes. We review the utility and various applications of radiomics in identifying and distinguishing atypical responses to treatments, as well as in predicting adverse effects. Although artificial intelligence tools show promise, several challenges-including multi-institutional clinical validation, deployment in health care settings, and artificial-intelligence bias-must be addressed for seamless clinical translation of these tools.

Radiomics as a New Frontier of Imaging for Cancer Prognosis: A Narrative Review

The evaluation of the efficacy of different therapies is of paramount importance for the patients and the clinicians in oncology, and it is usually possible by performing imaging investigations that are interpreted, taking in consideration different response evaluation criteria. In the last decade, texture analysis (TA) has been developed in order to help the radiologist to quantify and identify parameters related to tumor heterogeneity, which cannot be appreciated by the naked eye, that can be correlated with different endpoints, including cancer prognosis. The aim of this work is to analyze the impact of texture in the prediction of response and in prognosis stratification in oncology, taking into consideration different pathologies (lung cancer, breast cancer, gastric cancer, hepatic cancer, rectal cancer). Key references were derived from a PubMed query. Hand searching and clinicaltrials.gov were also used. This paper contains a narrative report and a critical discussion of radiomics approaches related to cancer prognosis in different fields of diseases.