Imaging-based Machine-learning Models to Predict Clinical Outcomes and Identify Biomarkers in Pancreatic Cancer: A Scoping Review

Radiomics in esophagogastric junction cancer: A scoping review of current status and advances

PURPOSE

This scoping review aimed to understand the advances in radiomics in esophagogastric junction (EGJ) cancer and assess the current status of radiomics in EGJ cancer.

METHODS

We conducted systematic searches of PubMed, Embase, and Web of Science databases from January 18, 2012, to January 15, 2023, to identify radiomics articles related to EGJ cancer. Two researchers independently screened the literature, extracted data, and assessed the quality of the studies using the Radiomics Quality Score (RQS) and the METhodological RadiomICs Score (METRICS) tool, respectively.

RESULTS

A total of 120 articles were retrieved from the three databases, and after screening, only six papers met the inclusion criteria. These studies investigated the role of radiomics in differentiating adenocarcinoma from squamous carcinoma, diagnosing T-stage, evaluating HER2 overexpression, predicting response to neoadjuvant therapy, and prognosis in EGJ cancer. The median score percentage of RQS was 34.7% (range from 22.2% to 38.9%). The median score percentage of METRICS was 71.2% (range from 58.2% to 84.9%).

CONCLUSION

Although there is a considerable difference between the RQS and METRICS scores of the included literature, we believe that the research value of radiomics in EGJ cancer has been revealed. In the future, while actively exploring more diagnostic, prognostic, and biological correlation studies in EGJ cancer, greater emphasis should be placed on the standardization and clinical application of radiomics.

Pathological Complete Response in Patients With Resected Pancreatic Adenocarcinoma After Preoperative Chemotherapy

Importance

Preoperative chemo(radio)therapy is increasingly used in patients with localized pancreatic adenocarcinoma, leading to pathological complete response (pCR) in a small subset of patients. However, multicenter studies with in-depth data about pCR are lacking.

Objective

To investigate the incidence, outcome, and risk factors of pCR after preoperative chemo(radio)therapy.

Design, Setting, and Participants

This observational, international, multicenter cohort study assessed all consecutive patients with pathology-proven localized pancreatic adenocarcinoma who underwent resection after 2 or more cycles of chemotherapy (with or without radiotherapy) in 19 centers from 8 countries (January 1, 2010, to December 31, 2018). Data collection was performed from February 1, 2020, to April 30, 2022, and analyses from January 1, 2022, to December 31, 2023. Median follow-up was 19 months.

Exposures

Preoperative chemotherapy (with or without radiotherapy) followed by resection.

Main Outcomes and Measures

The incidence of pCR (defined as absence of vital tumor cells in the sampled pancreas specimen after resection), its association with OS from surgery, and factors associated with pCR. Factors associated with overall survival (OS) and pCR were investigated with Cox proportional hazards and logistic regression models, respectively.

Results

Overall, 1758 patients (mean [SD] age, 64 [9] years; 879 [50.0%] male) were studied. The rate of pCR was 4.8% (n = 85), and pCR was associated with OS (hazard ratio, 0.46; 95% CI, 0.26-0.83). The 1-, 3-, and 5-year OS rates were 95%, 82%, and 63% in patients with pCR vs 80%, 46%, and 30% in patients without pCR, respectively (P < .001). Factors associated with pCR included preoperative multiagent chemotherapy other than (m)FOLFIRINOX ([modified] leucovorin calcium [folinic acid], fluorouracil, irinotecan hydrochloride, and oxaliplatin) (odds ratio [OR], 0.48; 95% CI, 0.26-0.87), preoperative conventional radiotherapy (OR, 2.03; 95% CI, 1.00-4.10), preoperative stereotactic body radiotherapy (OR, 8.91; 95% CI, 4.17-19.05), radiologic response (OR, 13.00; 95% CI, 7.02-24.08), and normal(ized) serum carbohydrate antigen 19-9 after preoperative therapy (OR, 3.76; 95% CI, 1.79-7.89).

Conclusions and Relevance

This international, retrospective cohort study found that pCR occurred in 4.8% of patients with resected localized pancreatic adenocarcinoma after preoperative chemo(radio)therapy. Although pCR does not reflect cure, it is associated with improved OS, with a doubled 5-year OS of 63% compared with 30% in patients without pCR. Factors associated with pCR related to preoperative chemo(radio)therapy regimens and anatomical and biological disease response features may have implications for treatment strategies that require validation in prospective studies because they may not universally apply to all patients with pancreatic adenocarcinoma.

Application of artificial intelligence radiomics in the diagnosis, treatment, and prognosis of hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer, with an increasing incidence and poor prognosis. In the past decade, artificial intelligence (AI) technology has undergone rapid development in the field of clinical medicine, bringing the advantages of efficient data processing and accurate model construction. Promisingly, AI-based radiomics has played an increasingly important role in the clinical decision-making of HCC patients, providing new technical guarantees for prediction, diagnosis, and prognostication. In this review, we evaluated the current landscape of AI radiomics in the management of HCC, including its diagnosis, individual treatment, and survival prognosis. Furthermore, we discussed remaining challenges and future perspectives regarding the application of AI radiomics in HCC.

Minimum and Optimal CA19-9 Response After Two Months Induction Chemotherapy in Patients With Locally Advanced Pancreatic Cancer: A Nationwide Multicenter Study

OBJECTIVE

This nationwide multicenter study aimed to define clinically relevant thresholds of relative serum CA19-9 response after 2 months of induction chemotherapy in patients with locally advanced pancreatic cancer (LAPC).

BACKGROUND

CA19-9 is seen as leading biomarker for response evaluation in patients with LAPC, but early clinically useful cut-offs are lacking.

METHODS

All consecutive patients with LAPC after 4 cycles (m)FOLFIRINOX or 2 cycles gemcitabine-nab-paclitaxel induction chemotherapy (±radiotherapy) with CA19-9 ≥5 U/mL at baseline were analyzed (2015-2019). The association of CA19-9 response with median OS (mOS) was evaluated for different CA19-9 cut-off points. Minimum and optimal CA19-9 response were established via log-rank test. Predictors for OS were analyzed using COX regression analysis.

RESULTS

Overall, 212 patients were included, of whom 42 (19.8%) underwent resection. Minimum CA19-9 response demonstrating a clinically significant median OS difference (12.7 vs. 19.6 months) was seen at ≥40% CA19-9 decrease. The optimal cutoff for CA19-9 response was ≥60% decrease (21.7 vs. 14.0 mo, P =0.021). Only for patients with elevated CA19-9 levels at baseline (n=184), CA19-9 decrease ≥60% [hazard ratio (HR)=0.59, 95% CI, 0.36-0.98, P =0.042] was independently associated with prolonged OS, as were SBRT (HR=0.42, 95% CI, 0.25-0.70; P =0.001), and resection (HR=0.25, 95% CI, 0.14-0.46, P <0.001), and duration of chemotherapy (HR=0.75, 95% CI, 0.69-0.82, P <0.001).

CONCLUSIONS

CA19-9 decrease of ≥60% following induction chemotherapy as optimal response cut-off in patients with LAPC is an independent predictor for OS when CA19-9 is increased at baseline. Furthermore, ≥40% is the minimum cut-off demonstrating survival benefit. These cut-offs may be used when discussing treatment strategies during early response evaluation.

Delta Radiomic Features Predict Resection Margin Status and Overall Survival in Neoadjuvant-Treated Pancreatic Cancer Patients

BACKGROUND

Neoadjuvant therapy (NAT) emerged as the standard of care for patients with pancreatic ductal adenocarcinoma (PDAC) who undergo surgery; however, surgery is morbid, and tools to predict resection margin status (RMS) and prognosis in the preoperative setting are needed. Radiomic models, specifically delta radiomic features (DRFs), may provide insight into treatment dynamics to improve preoperative predictions.

METHODS

We retrospectively collected clinical, pathological, and surgical data (patients with resectable, borderline, locally advanced, and metastatic disease), and pre/post-NAT contrast-enhanced computed tomography (CT) scans from PDAC patients at the University of Texas Southwestern Medical Center (UTSW; discovery) and Humanitas Hospital (validation cohort). Gross tumor volume was contoured from CT scans, and 257 radiomics features were extracted. DRFs were calculated by direct subtraction of pre/post-NAT radiomic features. Cox proportional models and binary prediction models, including/excluding clinical variables, were constructed to predict overall survival (OS), disease-free survival (DFS), and RMS.

RESULTS

The discovery and validation cohorts comprised 58 and 31 patients, respectively. Both cohorts had similar clinical characteristics, apart from differences in NAT (FOLFIRINOX vs. gemcitabine/nab-paclitaxel; p < 0.05) and type of surgery resections (pancreatoduodenectomy, distal or total pancreatectomy; p < 0.05). The model that combined clinical variables (pre-NAT carbohydrate antigen (CA) 19-9, the change in CA19-9 after NAT (∆CA19-9), and resectability status) and DRFs outperformed the clinical feature-based models and other radiomics feature-based models in predicting OS (UTSW: 0.73; Humanitas: 0.66), DFS (UTSW: 0.75; Humanitas: 0.64), and RMS (UTSW 0.73; Humanitas: 0.69).

CONCLUSIONS

Our externally validated, predictive/prognostic delta-radiomics models, which incorporate clinical variables, show promise in predicting the risk of predicting RMS in NAT-treated PDAC patients and their OS or DFS.

Serum CEA as a Prognostic Marker for Overall Survival in Patients with Localized Pancreatic Adenocarcinoma and Non-Elevated CA19-9 Levels Treated with FOLFIRINOX as Initial Treatment: A TAPS Consortium Study

INTRODUCTION

About 25% of patients with localized pancreatic adenocarcinoma have non-elevated serum carbohydrate antigen (CA) 19-9 levels at baseline, hampering evaluation of response to preoperative treatment. Serum carcinoembryonic antigen (CEA) is a potential alternative.

METHODS

This retrospective cohort study from five referral centers included consecutive patients with localized pancreatic adenocarcinoma (2012-2019), treated with one or more cycles of (m)FOLFIRINOX, and non-elevated CA19-9 levels (i.e., < 37 U/mL) at baseline. Cox regression analyses were performed to assess prognostic factors for overall survival (OS), including CEA level at baseline, restaging, and dynamics.

RESULTS

Overall, 277 patients were included in this study. CEA at baseline was elevated (≥5 ng/mL) in 53 patients (33%) and normalized following preoperative therapy in 14 patients (26%). In patients with elevated CEA at baseline, median OS in patients with CEA normalization following preoperative therapy was 33 months versus 19 months in patients without CEA normalization (p = 0.088). At time of baseline, only elevated CEA was independently associated with (worse) OS (hazard ratio [HR] 1.44, 95% confidence interval [CI] 1.04-1.98). At time of restaging, elevated CEA at baseline was still the only independent predictor for (worse) OS (HR 1.44, 95% CI 1.04-1.98), whereas elevated CEA at restaging (HR 1.16, 95% CI 0.77-1.77) was not.

CONCLUSIONS

Serum CEA was elevated in one-third of patients with localized pancreatic adenocarcinoma having non-elevated CA19-9 at baseline. At both time of baseline and time of restaging, elevated serum CEA measured at baseline was the only predictor for (worse) OS. Therefore, serum CEA may be a useful tool for decision making at both initial staging and time of restaging in patients with non-elevated CA19-9.

Preoperative chemotherapy, radiotherapy and surgical decision-making in patients with borderline resectable and locally advanced pancreatic cancer

Surgical resection combined with systemic chemotherapy is the cornerstone of treatment for patients with localized pancreatic cancer. Upfront surgery is considered suboptimal in cases with extensive vascular involvement, which can be classified as either borderline resectable pancreatic cancer or locally advanced pancreatic cancer. In these patients, FOLFIRINOX or gemcitabine plus nab-paclitaxel chemotherapy is currently used as preoperative chemotherapy and is eventually combined with radiotherapy. Thus, more patients might reach 5-year overall survival. Patient selection for chemotherapy, radiotherapy and subsequent surgery is based on anatomical, biological and conditional parameters. Current guidelines and clinical practices vary considerably regarding preoperative chemotherapy and radiotherapy, response evaluation, and indications for surgery. In this Review, we provide an overview of the clinical evidence regarding disease staging, preoperative therapy, response evaluation and surgery in patients with borderline resectable pancreatic cancer or locally advanced pancreatic cancer. In addition, a clinical work-up is proposed based on the available evidence and guidelines. We identify knowledge gaps and outline a proposed research agenda.

Advancing equitable and personalized cancer care: Novel applications and priorities of artificial intelligence for fairness and inclusivity in the patient care workflow

Patient care workflows are highly multimodal and intertwined: the intersection of data outputs provided from different disciplines and in different formats remains one of the main challenges of modern oncology. Artificial Intelligence (AI) has the potential to revolutionize the current clinical practice of oncology owing to advancements in digitalization, database expansion, computational technologies, and algorithmic innovations that facilitate discernment of complex relationships in multimodal data. Within oncology, radiation therapy (RT) represents an increasingly complex working procedure, involving many labor-intensive and operator-dependent tasks. In this context, AI has gained momentum as a powerful tool to standardize treatment performance and reduce inter-observer variability in a time-efficient manner. This review explores the hurdles associated with the development, implementation, and maintenance of AI platforms and highlights current measures in place to address them. In examining AI's role in oncology workflows, we underscore that a thorough and critical consideration of these challenges is the only way to ensure equitable and unbiased care delivery, ultimately serving patients' survival and quality of life.

Machine learning algorithm integrates bulk and single-cell transcriptome sequencing to reveal immune-related personalized therapy prediction features for pancreatic cancer

Pancreatic cancer (PC) is a digestive malignancy with worse overall survival. Tumor immune environment (TIME) alters the progression and proliferation of various solid tumors. Hence, we aimed to detect the TIME-related classifier to facilitate the personalized treatment of PC. Based on the 1612 immune-related genes (IRGs), we classified patients into Immune_rich and Immune_desert subgroups via consensus clustering. Patients in distinct subtypes exhibited a difference in sensitivity to immune checkpoint blockers (ICB). Next, the immune-related signature (IRS) model was established based on 8 IRGs (SYT12, TNNT1, TRIM46, SMPD3, ANLN, AFF3, CXCL9 and RP1L1) and validated its predictive efficiency in multiple cohorts. RT-qPCR experiments demonstrated the differential expression of 8 IRGs between tumor and normal cell lines. Patients who gained lower IRS score tended to be more sensitive to chemotherapy and immunotherapy, and obtained better overall survival compared to those with higher IRS scores. Moreover, scRNA-seq analysis revealed that fibroblast and ductal cells might affect malignant tumor cells via MIF-(CD74+CD44) and SPP1-CD44 axis. Eventually, we identified eight therapeutic targets and one agent for IRS high patients. Our study screened out the specific regulation pattern of TIME in PC, and shed light on the precise treatment of PC.

Radiomics in Carotid Plaque: A Systematic Review and Radiomics Quality Score Assessment

Imaging modalities provide information on plaque morphology and vulnerability; however, they are operator dependent and miss a great deal of microscopic information. Recently, many radiomics models for carotid plaque that identify unstable plaques and predict cardiovascular outcomes have been proposed. This systematic review was aimed at assessing whether radiomics is a reliable and reproducible method for the clinical prediction of carotid plaque. A systematic search was conducted to identify studies published in PubMed and Cochrane library from January 1, 2001, to September 30, 2022. Both retrospective and prospective studies that developed and/or validated machine learning models based on radiomics data to classify or predict carotid plaques were included. The general characteristics of each included study were selected, and the methodological quality of radiomics reports and risk of bias were evaluated using the radiomics quality score (RQS) tool and Quality Assessment of Diagnostic Accuracy Studies-2, respectively. Two investigators independently reviewed each study, and the consensus data were used for analysis. A total of 2429 patients from 16 studies were included. The mean area under the curve of radiomics models for diagnostic or predictive performance of the included studies was 0.88 ± 0.02, with a range of 0.741-0.989. The mean RQS was 9.25 (standard deviation: 6.04), representing 25.7% of the possible maximum value of 36, whereas the lowest point was -2, and the highest score was 22. Radiomics models have revealed additional information on patients with carotid plaque, but with respect to methodological quality, radiomics reports are still in their infancy, and many hurdles need to be overcome.

A Machine Learning Approach Using [18F]FDG PET-Based Radiomics for Prediction of Tumor Grade and Prognosis in Pancreatic Neuroendocrine Tumor

PURPOSE

We sought to develop and validate machine learning (ML) models for predicting tumor grade and prognosis using 2-[18F]fluoro-2-deoxy-D-glucose ([18F]FDG) positron emission tomography (PET)-based radiomics and clinical features in patients with pancreatic neuroendocrine tumors (PNETs).

PROCEDURES

A total of 58 patients with PNETs who underwent pretherapeutic [18F]FDG PET/computed tomography (CT) were retrospectively enrolled. PET-based radiomics extracted from segmented tumor and clinical features were selected to develop prediction models by the least absolute shrinkage and selection operator feature selection method. The predictive performances of ML models using neural network (NN) and random forest algorithms were compared by the areas under the receiver operating characteristic curves (AUROCs) and validated by stratified five-fold cross validation.

RESULTS

We developed two separate ML models for predicting high-grade tumors (Grade 3) and tumors with poor prognosis (disease progression within two years). The integrated models consisting of clinical and radiomic features with NN algorithm showed the best performances than the other models (stand-alone clinical or radiomics models). The performance metrics of the integrated model by NN algorithm were AUROC of 0.864 in the tumor grade prediction model and AUROC of 0.830 in the prognosis prediction model. In addition, AUROC of the integrated clinico-radiomics model with NN was significantly higher than that of tumor maximum standardized uptake model in predicting prognosis (P < 0.001).

CONCLUSIONS

Integration of clinical features and [18F]FDG PET-based radiomics using ML algorithms improved the prediction of high-grade PNET and poor prognosis in a non-invasive manner.

Future of Artificial Intelligence Applications in Cancer Care: A Global Cross-Sectional Survey of Researchers

Cancer significantly contributes to global mortality, with 9.3 million annual deaths. To alleviate this burden, the utilization of artificial intelligence (AI) applications has been proposed in various domains of oncology. However, the potential applications of AI and the barriers to its widespread adoption remain unclear. This study aimed to address this gap by conducting a cross-sectional, global, web-based survey of over 1000 AI and cancer researchers. The results indicated that most respondents believed AI would positively impact cancer grading and classification, follow-up services, and diagnostic accuracy. Despite these benefits, several limitations were identified, including difficulties incorporating AI into clinical practice and the lack of standardization in cancer health data. These limitations pose significant challenges, particularly regarding testing, validation, certification, and auditing AI algorithms and systems. The results of this study provide valuable insights for informed decision-making for stakeholders involved in AI and cancer research and development, including individual researchers and research funding agencies.

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.

Artificial Intelligence in Oncology: Current Capabilities, Future Opportunities, and Ethical Considerations

The promise of highly personalized oncology care using artificial intelligence (AI) technologies has been forecasted since the emergence of the field. Cumulative advances across the science are bringing this promise to realization, including refinement of machine learning- and deep learning algorithms; expansion in the depth and variety of databases, including multiomics; and the decreased cost of massively parallelized computational power. Examples of successful clinical applications of AI can be found throughout the cancer continuum and in multidisciplinary practice, with computer vision-assisted image analysis in particular having several U.S. Food and Drug Administration-approved uses. Techniques with emerging clinical utility include whole blood multicancer detection from deep sequencing, virtual biopsies, natural language processing to infer health trajectories from medical notes, and advanced clinical decision support systems that combine genomics and clinomics. Substantial issues have delayed broad adoption, with data transparency and interpretability suffering from AI's "black box" mechanism, and intrinsic bias against underrepresented persons limiting the reproducibility of AI models and perpetuating health care disparities. Midfuture projections of AI maturation involve increasing a model's complexity by using multimodal data elements to better approximate an organic system. Far-future positing includes living databases that accumulate all aspects of a person's health into discrete data elements; this will fuel highly convoluted modeling that can tailor treatment selection, dose determination, surveillance modality and schedule, and more. The field of AI has had a historical dichotomy between its proponents and detractors. The successful development of recent applications, and continued investment in prospective validation that defines their impact on multilevel outcomes, has established a momentum of accelerated progress.