End-to-end reproducible AI pipelines in radiology using the cloud.

Artificial intelligence (AI) algorithms hold the potential to revolutionize radiology. However, a significant portion of the published literature lacks transparency and reproducibility, which hampers sustained progress toward clinical translation. Although several reporting guidelines have been proposed, identifying practical means to address these issues remains challenging. Here, we show the potential of cloud-based infrastructure for implementing and sharing transparent and reproducible AI-based radiology pipelines. We demonstrate end-to-end reproducibility from retrieving cloud-hosted data, through data pre-processing, deep learning inference, and post-processing, to the analysis and reporting of the final results. We successfully implement two distinct use cases, starting from recent literature on AI-based biomarkers for cancer imaging. Using cloud-hosted data and computing, we confirm the findings of these studies and extend the validation to previously unseen data for one of the use cases. Furthermore, we provide the community with transparent and easy-to-extend examples of pipelines impactful for the broader oncology field. Our approach demonstrates the potential of cloud resources for implementing, sharing, and using reproducible and transparent AI pipelines, which can accelerate the translation into clinical solutions.

A roadmap for modelling radiation-induced cardiac disease.

Cardiac risk mitigation is a major priority in improving outcomes for cancer survivors as advances in cancer screening and treatments continue to decrease cancer mortality. More than half of adult cancer patients will be treated with radiotherapy (RT); therefore it is crucial to develop a framework for how to assess and predict radiation-induced cardiac disease (RICD). Historically, RICD was modelled solely using whole heart metrics such as mean heart dose. However, data over the past decade has identified cardiac substructures which outperform whole heart metrics in predicting for significant cardiac events. Additionally, non-RT factors such as pre-existing cardiovascular risk factors and toxicity from other therapies contribute to risk of future cardiac events. In this review, we aim to discuss the current evidence and knowledge gaps in predicting RICD and provide a roadmap for the development of comprehensive models based on three interrelated components, (1) baseline CV risk assessment, (2) cardiac substructure radiation dosimetry linked with cardiac-specific outcomes and (3) novel biomarker development.

Feasibility of Left Anterior Descending Coronary Artery Sparing Radiation Therapy for Locally Advanced Lung Cancer.

Efforts to mitigate radiation therapy (RT)-associated cardiotoxicity have focused on constraining mean heart dose. However, recent studies have shown greater predictive power with cardiac substructure dose metrics, such as the left anterior descending (LAD) coronary artery volume (V) receiving 15 Gy (V15Gy) ≥10%. Herein, we investigated the feasibility of LAD radiation sparing in contemporary intensity modulated RT (IMRT)/volumetric modulated arc therapy (VMAT) lung cancer plans. Single institution retrospective analysis of 54 patients with locally advanced lung cancer treated with thoracic RT was conducted between February 2018 and August 2021. After excluding 33 (5 = non-IMRT/VMAT or intentionally LAD-optimized; 28 = LAD V15Gy <10%), 21 plans with LAD V15Gy ≥10% were identified for LAD reoptimization with intent to meet LAD V15Gy <10% while maintaining meeting organ at risk (OAR) metrics and target coverage with original plan parameters. Dosimetric variables were compared using paired t tests. Most patients (57.1%, 12/21) were treated with definitive RT, 8 of 21 patients (38.1%) with postoperative RT, and 1 with neoadjuvant RT. The median prescribed RT dose was 60 Gy (range, 50.4-66 Gy) in 30 fractions (range, 28-33 fractions). LAD reoptimized plans (vs original) led to significant reductions in mean LAD V15Gy (39.4% ± 13.9% vs 9.4% ± 13.0%; P < .001) and mean LAD dose (12.9 Gy ± 4.6 Gy vs 7.6 Gy ± 2.8 Gy; P < .001). Most (85.7%; 18/21) LAD reoptimized plans achieved LAD V15Gy <10%. There were no statistically significant differences in overall lung, esophageal, or spinal cord dose metrics. Only 1 reoptimization (1/21) exceeded an OAR constraint that was initially met in the original plan. To our knowledge, this is the first report describing the feasibility of LAD-optimized lung cancer RT planning using the newly identified LAD V15Gy constraint. We observed that LAD V15Gy <10% is achievable in more than 85% of plans initially exceeding this constraint, with minimal dosimetric tradeoffs. Our results support the feasibility of routine incorporation of the LAD as an OAR in modern thoracic IMRT/VMAT planning.

Lung sparing in MR-guided non-adaptive SBRT treatment of peripheral lung tumors.

Objective.We aim to: (1) quantify the benefits of lung sparing using non-adaptive magnetic resonance guided stereotactic body radiotherapy (MRgSBRT) with advanced motion management for peripheral lung cancers compared to conventional x-ray guided SBRT (ConvSBRT); (2) establish a practical decision-making guidance metric to assist a clinician in selecting the appropriate treatment modality.Approach.Eleven patients with peripheral lung cancer who underwent breath-hold, gated MRgSBRT on an MR-guided linear accelerator (MR linac) were studied. Four-dimensional computed tomography (4DCT)-based retrospective planning using an internal target volume (ITV) was performed to simulate ConvSBRT, which were evaluated against the original MRgSBRT plans. Metrics analyzed included planning target volume (PTV) coverage, various lung metrics and the generalized equivalent unform dose (gEUD). A dosimetric predictor for achievable lung metrics was derived to assist future patient triage across modalities.Main results.PTV coverage was high (median V100% > 98%) and comparable for both modalities. MRgSBRT had significantly lower lung doses as measured by V20 (median 3.2% versus 4.2%), mean lung dose (median 3.3 Gy versus 3.8 Gy) and gEUD. Breath-hold, gated MRgSBRT resulted in an average reduction of 47% in PTV volume and an average increase of 19% in lung volume. Strong correlation existed between lung metrics and the ratio of PTV to lung volumes (RPTV/Lungs) for both modalities, indicating that RPTV/Lungsmay serve as a good predictor for achievable lung metrics without the need for pre-planning. A threshold value of RPTV/Lungs< 0.035 is suggested to achieve V20 < 10% using ConvSBRT. MRgSBRT should otherwise be considered if the threshold cannot be met.Significance.The benefits of lung sparing using MRgSBRT were quantified for peripheral lung tumors; RPTV/Lungswas found to be an effective predictor for achievable lung metrics across modalities. RPTV/Lungscan assist a clinician in selecting the appropriate modality without the need for labor-intensive pre-planning, which has significant practical benefit for a busy clinic.

The ASCENT Trial: a phase 2 study of induction and consolidation afatinib and chemoradiation with or without surgery in stage III EGFR-mutant NSCLC.

BACKGROUND: The role of tyrosine kinase inhibitors (TKIs) in early-stage and metastatic oncogene-driven non-small cell lung cancer (NSCLC) is established, but it remains unknown how best to integrate TKIs with concurrent chemoradiotherapy (cCRT) in locally advanced disease. The phase 2 ASCENT trial assessed the efficacy and safety of afatinib and cCRT with or without surgery in locally advanced epidermal growth factor receptor (EGFR)-mutant NSCLC. PATIENTS AND METHODS: Adults ≥18 years with histologically confirmed stage III (AJCC 7th edition) NSCLC with activating EGFR mutations were enrolled at Mass General and Dana-Farber/Brigham Cancer Centers, Boston, Massachusetts. Patients received induction afatinib 40 mg daily for 2 months, then cisplatin 75 mg/m2 and pemetrexed 500 mg/m2 IV every 3 weeks during RT (definitive or neoadjuvant dosing). Patients with resectable disease underwent surgery. All patients were offered consolidation afatinib for 2 years. The primary endpoint was the objective response rate (ORR) to induction TKI. Secondary endpoints were safety, conversion to operability, progression-free survival (PFS), and overall survival (OS). Analyses were performed on the intention-to-treat population. RESULTS: Nineteen patients (median age 56 years; 74% female) were enrolled. ORR to induction afatinib was 63%. Seventeen patients received cCRT; 2/9 previously unresectable became resectable. Ten underwent surgery; 6 had a major or complete pathological response. Thirteen received consolidation afatinib. With a median follow-up of 5.0 years, median PFS and OS were 2.6 (95% CI, 1.4-3.1) and 5.8 years (2.9-NR), respectively. Sixteen recurred or died; 6 recurrences were isolated to CNS. The median time to progression after stopping consolidation TKI was 2.9 months (95% CI, 1.1-7.2). Four developed grade 2 pneumonitis. There were no treatment-related deaths. CONCLUSION: We explored the efficacy of combining TKI with cCRT in oncogene-driven NSCLC. Induction TKI did not compromise subsequent receipt of multimodality therapy. PFS was promising, but the prevalence of CNS-only recurrences and rapid progression after TKI discontinuation speak to unmet needs in measuring and eradicating micrometastatic disease.

Body Composition in Advanced Non-Small Cell Lung Cancer Treated With Immunotherapy.

Importance: The association between body composition (BC) and cancer outcomes is complex and incompletely understood. Previous research in non-small-cell lung cancer (NSCLC) has been limited to small, single-institution studies and yielded promising, albeit heterogeneous, results. Objectives: To evaluate the association of BC with oncologic outcomes in patients receiving immunotherapy for advanced or metastatic NSCLC. Design, Setting, and Participants: This comprehensive multicohort analysis included clinical data from cohorts receiving treatment at the Dana-Farber Brigham Cancer Center (DFBCC) who received immunotherapy given alone or in combination with chemotherapy and prospectively collected data from the phase 1/2 Study 1108 and the chemotherapy arm of the phase 3 MYSTIC trial. Baseline and follow-up computed tomography (CT) scans were collected and analyzed using deep neural networks for automatic L3 slice selection and body compartment segmentation (skeletal muscle [SM], subcutaneous adipose tissue [SAT], and visceral adipose tissue). Outcomes were compared based on baseline BC measures or their change at the first follow-up scan. The data were analyzed between July 2022 and April 2023. Main Outcomes and Measures: Hazard ratios (HRs) for the association of BC measurements with overall survival (OS) and progression-free survival (PFS). Results: A total of 1791 patients (878 women [49%]) with NSCLC were analyzed, of whom 487 (27.2%) received chemoimmunotherapy at DFBCC (DFBCC-CIO), 825 (46.1%) received ICI monotherapy at DFBCC (DFBCC-IO), 222 (12.4%) were treated with durvalumab monotherapy on Study 1108, and 257 (14.3%) were treated with chemotherapy on MYSTIC; median (IQR) ages were 65 (58-74), 66 (57-71), 65 (26-87), and 63 (30-84) years, respectively. A loss in SM mass, as indicated by a change in the L3 SM area, was associated with worse oncologic outcome across patient groups (HR, 0.59 [95% CI, 0.43-0.81] and 0.61 [95% CI, 0.47-0.79] for OS and PFS, respectively, in DFBCC-CIO; HR, 0.74 [95% CI, 0.60-0.91] for OS in DFBCC-IO; HR, 0.46 [95% CI, 0.33-0.64] and 0.47 [95% CI, 0.34-0.64] for OS and PFS, respectively, in Study 1108; HR, 0.76 [95% CI, 0.61-0.96] for PFS in the MYSTIC trial). This association was most prominent among male patients, with a nonsignificant association among female patients in the MYSTIC trial and DFBCC-CIO cohorts on Kaplan-Meier analysis. An increase of more than 5% in SAT density, as quantified by the average CT attenuation in Hounsfield units of the SAT compartment, was associated with poorer OS in 3 patient cohorts (HR, 0.61 [95% CI, 0.43-0.86] for DFBCC-CIO; HR, 0.62 [95% CI, 0.49-0.79] for DFBCC-IO; and HR, 0.56 [95% CI, 0.40-0.77] for Study 1108). The change in SAT density was also associated with PFS for DFBCC-CIO (HR, 0.73; 95% CI, 0.54-0.97). This was primarily observed in female patients on Kaplan-Meier analysis. Conclusions and Relevance: The results of this multicohort study suggest that loss in SM mass during systemic therapy for NSCLC is a marker of poor outcomes, especially in male patients. SAT density changes are also associated with prognosis, particularly in female patients. Automated CT-derived BC measurements should be considered in determining NSCLC prognosis.

Foundation model for cancer imaging biomarkers.

Foundation models in deep learning are characterized by a single large-scale model trained on vast amounts of data serving as the foundation for various downstream tasks. Foundation models are generally trained using self-supervised learning and excel in reducing the demand for training samples in downstream applications. This is especially important in medicine, where large labelled datasets are often scarce. Here, we developed a foundation model for cancer imaging biomarker discovery by training a convolutional encoder through self-supervised learning using a comprehensive dataset of 11,467 radiographic lesions. The foundation model was evaluated in distinct and clinically relevant applications of cancer imaging-based biomarkers. We found that it facilitated better and more efficient learning of imaging biomarkers and yielded task-specific models that significantly outperformed conventional supervised and other state-of-the-art pretrained implementations on downstream tasks, especially when training dataset sizes were very limited. Furthermore, the foundation model was more stable to input variations and showed strong associations with underlying biology. Our results demonstrate the tremendous potential of foundation models in discovering new imaging biomarkers that may extend to other clinical use cases and can accelerate the widespread translation of imaging biomarkers into clinical settings.

Edge roughness quantifies impact of physician variation on training and performance of deep learning auto-segmentation models for the esophagus.

Manual segmentation of tumors and organs-at-risk (OAR) in 3D imaging for radiation-therapy planning is time-consuming and subject to variation between different observers. Artificial intelligence (AI) can assist with segmentation, but challenges exist in ensuring high-quality segmentation, especially for small, variable structures, such as the esophagus. We investigated the effect of variation in segmentation quality and style of physicians for training deep-learning models for esophagus segmentation and proposed a new metric, edge roughness, for evaluating/quantifying slice-to-slice inconsistency. This study includes a real-world cohort of 394 patients who each received radiation therapy (mainly for lung cancer). Segmentation of the esophagus was performed by 8 physicians as part of routine clinical care. We evaluated manual segmentation by comparing the length and edge roughness of segmentations among physicians to analyze inconsistencies. We trained eight multiple- and individual-physician segmentation models in total, based on U-Net architectures and residual backbones. We used the volumetric Dice coefficient to measure the performance for each model. We proposed a metric, edge roughness, to quantify the shift of segmentation among adjacent slices by calculating the curvature of edges of the 2D sagittal- and coronal-view projections. The auto-segmentation model trained on multiple physicians (MD1-7) achieved the highest mean Dice of 73.7 ± 14.8%. The individual-physician model (MD7) with the highest edge roughness (mean ± SD: 0.106 ± 0.016) demonstrated significantly lower volumetric Dice for test cases compared with other individual models (MD7: 58.5 ± 15.8%, MD6: 67.1 ± 16.8%, p < 0.001). A multiple-physician model trained after removing the MD7 data resulted in fewer outliers (e.g., Dice ≤ 40%: 4 cases for MD1-6, 7 cases for MD1-7, Ntotal = 394). While we initially detected this pattern in a single clinician, we validated the edge roughness metric across the entire dataset. The model trained with the lowest-quantile edge roughness (MDER-Q1, Ntrain = 62) achieved significantly higher Dice (Ntest = 270) than the model trained with the highest-quantile ones (MDER-Q4, Ntrain = 62) (MDER-Q1: 67.8 ± 14.8%, MDER-Q4: 62.8 ± 15.7%, p < 0.001). This study demonstrates that there is significant variation in style and quality in manual segmentations in clinical care, and that training AI auto-segmentation algorithms from real-world, clinical datasets may result in unexpectedly under-performing algorithms with the inclusion of outliers. Importantly, this study provides a novel evaluation metric, edge roughness, to quantify physician variation in segmentation which will allow developers to filter clinical training data to optimize model performance.

Large language models to identify social determinants of health in electronic health records.

Social determinants of health (SDoH) play a critical role in patient outcomes, yet their documentation is often missing or incomplete in the structured data of electronic health records (EHRs). Large language models (LLMs) could enable high-throughput extraction of SDoH from the EHR to support research and clinical care. However, class imbalance and data limitations present challenges for this sparsely documented yet critical information. Here, we investigated the optimal methods for using LLMs to extract six SDoH categories from narrative text in the EHR: employment, housing, transportation, parental status, relationship, and social support. The best-performing models were fine-tuned Flan-T5 XL for any SDoH mentions (macro-F1 0.71), and Flan-T5 XXL for adverse SDoH mentions (macro-F1 0.70). Adding LLM-generated synthetic data to training varied across models and architecture, but improved the performance of smaller Flan-T5 models (delta F1 + 0.12 to +0.23). Our best-fine-tuned models outperformed zero- and few-shot performance of ChatGPT-family models in the zero- and few-shot setting, except GPT4 with 10-shot prompting for adverse SDoH. Fine-tuned models were less likely than ChatGPT to change their prediction when race/ethnicity and gender descriptors were added to the text, suggesting less algorithmic bias (p < 0.05). Our models identified 93.8% of patients with adverse SDoH, while ICD-10 codes captured 2.0%. These results demonstrate the potential of LLMs in improving real-world evidence on SDoH and assisting in identifying patients who could benefit from resource support.

Widening the therapeutic window for central and ultra-central thoracic oligometastatic disease with stereotactic MR-guided adaptive radiation therapy (SMART).

BACKGROUND/PURPOSE: Central/ultra-central thoracic tumors are challenging to treat with stereotactic radiotherapy due potential high-grade toxicity. Stereotactic MR-guided adaptive radiation therapy (SMART) may improve the therapeutic window through motion control with breath-hold gating and real-time MR-imaging as well as the option for daily online adaptive replanning to account for changes in target and/or organ-at-risk (OAR) location. MATERIALS/METHODS: 26 central (19 ultra-central) thoracic oligoprogressive/oligometastatic tumors treated with isotoxic (OAR constraints-driven) 5-fraction SMART (median 50 Gy, range 35-60) between 10/2019-10/2022 were reviewed. Central tumor was defined as tumor within or touching 2 cm around proximal tracheobronchial tree (PBT) or adjacent to mediastinal/pericardial pleura. Ultra-central was defined as tumor abutting the PBT, esophagus, or great vessel. Hard OAR constraints observed were ≤ 0.03 cc for PBT V40, great vessel V52.5, and esophagus V35. Local failure was defined as tumor progression/recurrence within the planning target volume. RESULTS: Tumor abutted the PBT in 31 %, esophagus in 31 %, great vessel in 65 %, and heart in 42 % of cases. 96 % of fractions were treated with reoptimized plan, necessary to meet OAR constraints (80 %) and/or target coverage (20 %). Median follow-up was 19 months (27 months among surviving patients). Local control (LC) was 96 % at 1-year and 90 % at 2-years (total 2/26 local failure). 23 % had G2 acute toxicities (esophagitis, dysphagia, anorexia, nausea) and one (4 %) had G3 acute radiation dermatitis. There were no G4-5 acute toxicities. There was no symptomatic pneumonitis and no G2 + late toxicities. CONCLUSION: Isotoxic 5-fraction SMART resulted in high rates of LC and minimal toxicity. This approach may widen the therapeutic window for high-risk oligoprogressive/oligometastatic thoracic tumors.

Stereotactic Magnetic Resonance-guided Adaptive Radiation Therapy for Localized Kidney Cancer: Early Outcomes from a Prospective Phase 1 Trial and Supplemental Cohort.

Stereotactic magnetic resonance (MR)-guided adaptive radiotherapy (SMART) for renal cell carcinoma may result in more precise treatment delivery through the capabilities for improved image quality, daily adaptive planning, and accounting for respiratory motion during treatment with real-time MR tracking. In this study, we aimed to characterize the safety and feasibility of SMART for localized kidney cancer. Twenty patients with localized kidney cancer (ten treated in a prospective phase 1 trial and ten in the supplemental cohort) were treated to 40 Gy in five fractions on a 0.35 T MR-guided linear accelerator with daily adaptive planning and a cine MR-guided inspiratory breath hold technique. The median follow-up time was 17 mo (interquartile range: 13-20 months). A single patient developed local failure at 30 mo. No grade ≥3 adverse events were reported. The mean decrease in estimated glomerular filtration rate was -1.8 ml/min/1.73 m2 (95% confidence interval or CI [-6.6 to 3.1 ml/min/1.73 m2]), and the mean decrease in tumor diameter was -0.20 cm (95% CI [-0.6 to 0.2 cm]) at the last follow-up. Anterior location and overlap of the 25 or 28 Gy isodose line with gastrointestinal organs at risk were predictive of the benefit from online adaptive planning. Kidney SMART is feasible and, at the early time point evaluated in this study, was well tolerated with minimal decline in renal function. More studies are warranted to further evaluate the safety and efficacy of this technique. PATIENT SUMMARY: For patients with localized renal cell carcinoma who are not surgical candidates, stereotactic magnetic resonance--guided adaptive radiotherapy is a feasible and safe noninvasive treatment option that results in minimal impact on kidney function.

Automated temporalis muscle quantification and growth charts for children through adulthood.

Lean muscle mass (LMM) is an important aspect of human health. Temporalis muscle thickness is a promising LMM marker but has had limited utility due to its unknown normal growth trajectory and reference ranges and lack of standardized measurement. Here, we develop an automated deep learning pipeline to accurately measure temporalis muscle thickness (iTMT) from routine brain magnetic resonance imaging (MRI). We apply iTMT to 23,876 MRIs of healthy subjects, ages 4 through 35, and generate sex-specific iTMT normal growth charts with percentiles. We find that iTMT was associated with specific physiologic traits, including caloric intake, physical activity, sex hormone levels, and presence of malignancy. We validate iTMT across multiple demographic groups and in children with brain tumors and demonstrate feasibility for individualized longitudinal monitoring. The iTMT pipeline provides unprecedented insights into temporalis muscle growth during human development and enables the use of LMM tracking to inform clinical decision-making.

Decoding biological age from face photographs using deep learning.

Because humans age at different rates, a person's physical appearance may yield insights into their biological age and physiological health more reliably than their chronological age. In medicine, however, appearance is incorporated into medical judgments in a subjective and non-standardized fashion. In this study, we developed and validated FaceAge, a deep learning system to estimate biological age from easily obtainable and low-cost face photographs. FaceAge was trained on data from 58,851 healthy individuals, and clinical utility was evaluated on data from 6,196 patients with cancer diagnoses from two institutions in the United States and The Netherlands. To assess the prognostic relevance of FaceAge estimation, we performed Kaplan Meier survival analysis. To test a relevant clinical application of FaceAge, we assessed the performance of FaceAge in end-of-life patients with metastatic cancer who received palliative treatment by incorporating FaceAge into clinical prediction models. We found that, on average, cancer patients look older than their chronological age, and looking older is correlated with worse overall survival. FaceAge demonstrated significant independent prognostic performance in a range of cancer types and stages. We found that FaceAge can improve physicians' survival predictions in incurable patients receiving palliative treatments, highlighting the clinical utility of the algorithm to support end-of-life decision-making. FaceAge was also significantly associated with molecular mechanisms of senescence through gene analysis, while age was not. These findings may extend to diseases beyond cancer, motivating using deep learning algorithms to translate a patient's visual appearance into objective, quantitative, and clinically useful measures.

Pneumonitis in Patients Receiving Thoracic Radiotherapy and Osimertinib: A Multi-Institutional Study.

Introduction: Thoracic radiotherapy (TRT) is increasingly used in patients receiving osimertinib for advanced NSCLC, and the risk of pneumonitis is not established. We investigated the risk of pneumonitis and potential risk factors in this population. Methods: We performed a multi-institutional retrospective analysis of patients under active treatment with osimertinib who received TRT between April 2016 and July 2022 at two institutions. Clinical characteristics, including whether osimertinib was held during TRT and pneumonitis incidence and grade (Common Terminology Criteria for Adverse Events version 5.0) were documented. Logistic regression analysis was performed to identify risk factors associated with grade 2 or higher (2+) pneumonitis. Results: The median follow-up was 10.2 months (range: 1.9-53.2). Of 102 patients, 14 (13.7%) developed grade 2+ pneumonitis, with a median time to pneumonitis of 3.2 months (range: 1.5-6.3). Pneumonitis risk was not significantly increased in patients who continued osimertinib during TRT compared with patients who held osimertinib during TRT (9.1% versus 15.0%, p = 0.729). Three patients (2.9%) had grade 3 pneumonitis, none had grade 4, and two patients had grade 5 events (2.0%, diagnosed 3.2 mo and 4.4 mo post-TRT). Mean lung dose was associated with the development of grade 2+ pneumonitis in multivariate analysis (OR = 1.19, p = 0.021). Conclusions: Although the overall rate of pneumonitis in patients receiving TRT and osimertinib was relatively low, there was a small risk of severe toxicity. The mean lung dose was associated with an increased risk of developing pneumonitis. These findings inform decision-making for patients and providers.

Foundation Models for Quantitative Biomarker Discovery in Cancer Imaging.

Foundation models represent a recent paradigm shift in deep learning, where a single large-scale model trained on vast amounts of data can serve as the foundation for various downstream tasks. Foundation models are generally trained using self-supervised learning and excel in reducing the demand for training samples in downstream applications. This is especially important in medicine, where large labeled datasets are often scarce. Here, we developed a foundation model for imaging biomarker discovery by training a convolutional encoder through self-supervised learning using a comprehensive dataset of 11,467 radiographic lesions. The foundation model was evaluated in distinct and clinically relevant applications of imaging-based biomarkers. We found that they facilitated better and more efficient learning of imaging biomarkers and yielded task-specific models that significantly outperformed their conventional supervised counterparts on downstream tasks. The performance gain was most prominent when training dataset sizes were very limited. Furthermore, foundation models were more stable to input and inter-reader variations and showed stronger associations with underlying biology. Our results demonstrate the tremendous potential of foundation models in discovering novel imaging biomarkers that may extend to other clinical use cases and can accelerate the widespread translation of imaging biomarkers into clinical settings.

Development and Validation of an Automated Image-Based Deep Learning Platform for Sarcopenia Assessment in Head and Neck Cancer.

Importance: Sarcopenia is an established prognostic factor in patients with head and neck squamous cell carcinoma (HNSCC); the quantification of sarcopenia assessed by imaging is typically achieved through the skeletal muscle index (SMI), which can be derived from cervical skeletal muscle segmentation and cross-sectional area. However, manual muscle segmentation is labor intensive, prone to interobserver variability, and impractical for large-scale clinical use. Objective: To develop and externally validate a fully automated image-based deep learning platform for cervical vertebral muscle segmentation and SMI calculation and evaluate associations with survival and treatment toxicity outcomes. Design, Setting, and Participants: For this prognostic study, a model development data set was curated from publicly available and deidentified data from patients with HNSCC treated at MD Anderson Cancer Center between January 1, 2003, and December 31, 2013. A total of 899 patients undergoing primary radiation for HNSCC with abdominal computed tomography scans and complete clinical information were selected. An external validation data set was retrospectively collected from patients undergoing primary radiation therapy between January 1, 1996, and December 31, 2013, at Brigham and Women's Hospital. The data analysis was performed between May 1, 2022, and March 31, 2023. Exposure: C3 vertebral skeletal muscle segmentation during radiation therapy for HNSCC. Main Outcomes and Measures: Overall survival and treatment toxicity outcomes of HNSCC. Results: The total patient cohort comprised 899 patients with HNSCC (median [range] age, 58 [24-90] years; 140 female [15.6%] and 755 male [84.0%]). Dice similarity coefficients for the validation set (n = 96) and internal test set (n = 48) were 0.90 (95% CI, 0.90-0.91) and 0.90 (95% CI, 0.89-0.91), respectively, with a mean 96.2% acceptable rate between 2 reviewers on external clinical testing (n = 377). Estimated cross-sectional area and SMI values were associated with manually annotated values (Pearson r = 0.99; P < .001) across data sets. On multivariable Cox proportional hazards regression, SMI-derived sarcopenia was associated with worse overall survival (hazard ratio, 2.05; 95% CI, 1.04-4.04; P = .04) and longer feeding tube duration (median [range], 162 [6-1477] vs 134 [15-1255] days; hazard ratio, 0.66; 95% CI, 0.48-0.89; P = .006) than no sarcopenia. Conclusions and Relevance: This prognostic study's findings show external validation of a fully automated deep learning pipeline to accurately measure sarcopenia in HNSCC and an association with important disease outcomes. The pipeline could enable the integration of sarcopenia assessment into clinical decision making for individuals with HNSCC.

Use of Artificial Intelligence Chatbots for Cancer Treatment Information.

This survey study examines the performance of a large language model chatbot in providing cancer treatment recommendations that are concordant with National Comprehensive Cancer Network guidelines.

Acute toxicity comparison of magnetic resonance-guided adaptive versus fiducial or computed tomography-guided non-adaptive prostate stereotactic body radiotherapy: A systematic review and meta-analysis.

BACKGROUND: Stereotactic body radiotherapy (SBRT) is gaining wider adoption for prostate cancer management but there remain significant toxicity risks when delivering prostate SBRT with standard techniques. Magnetic resonance-guided daily adaptive SBRT (MRg-A-SBRT) offers technological advantages in precision of radiation dose delivery, but the toxicity profile associated with MRg-A-SBRT compared to more standardly used fiducial or computed tomography-guided non-adaptive prostate SBRT (CT-SBRT) remains unknown. METHODS: A meta-analysis to compare acute toxicity rates associated with MRg-A-SBRT and CT-SBRT for prostate cancer was performed in compliance with PRISMA guidelines. MEDLINE (PubMed) and Google Scholar were searched for prospective studies of prostate SBRT that were published between January 1, 2018 and August 31, 2022. Random effects and fixed effects models were used to estimate pooled toxicity rates, and meta-regression was performed to compare toxicity between MRg-A-SBRT and CT-SBRT study groups. RESULTS: Twenty-nine prospective studies were identified that met the inclusion criteria and included a total of 2547 patients. The pooled estimates for acute grade 2 or higher (G2+) genitourinary (GU) and gastrointestinal (GI) toxicity for MRg-A-SBRT were 16% (95% confidence interval [CI], 10%-24%) and 4% (95% CI, 2%-7%) and for CT-SBRT they were 28% (95% CI, 23%-33%) and 9% (95% CI, 6%-12%), respectively. On meta-regression, the odds ratios for acute G2+ GU and GI toxicities comparing MRg-A-SBRT and CT-SBRT were 0.56 (95% CI, 0.33-0.97, p = .04) and 0.40 (95% CI, 0.17-0.96, p = .04), respectively. CONCLUSION: MRg-A-SBRT is associated with a significantly reduced risk of acute G2+ GU or GI toxicity compared to CT-SBRT. Longer follow-up will be needed to evaluate late toxicity and disease control outcomes. PLAIN LANGUAGE SUMMARY: Magnetic resonance imaging-guided daily adaptive prostate stereotactic radiation (MRg-A-SBRT) is a treatment that may allow for delivery of prostate radiation more precisely than other radiotherapy techniques, but it is unknown whether this reduces side effects compared to standardly used computed tomography-guided SBRT (CT-SBRT). In this systematic review and meta-analysis combining data from 29 clinical trials including 2547 patients, it was found that the risk of short-term urinary side effects was reduced by 44% and the risk of short-term bowel side effects was reduced by 60% with MRg-A-SBRT compared to CT-SBRT.

Natural Language Processing to Automatically Extract the Presence and Severity of Esophagitis in Notes of Patients Undergoing Radiotherapy.

PURPOSE: Radiotherapy (RT) toxicities can impair survival and quality of life, yet remain understudied. Real-world evidence holds potential to improve our understanding of toxicities, but toxicity information is often only in clinical notes. We developed natural language processing (NLP) models to identify the presence and severity of esophagitis from notes of patients treated with thoracic RT. METHODS: Our corpus consisted of a gold-labeled data set of 1,524 clinical notes from 124 patients with lung cancer treated with RT, manually annotated for Common Terminology Criteria for Adverse Events (CTCAE) v5.0 esophagitis grade, and a silver-labeled data set of 2,420 notes from 1,832 patients from whom toxicity grades had been collected as structured data during clinical care. We fine-tuned statistical and pretrained Bidirectional Encoder Representations from Transformers-based models for three esophagitis classification tasks: task 1, no esophagitis versus grade 1-3; task 2, grade ≤1 versus >1; and task 3, no esophagitis versus grade 1 versus grade 2-3. Transferability was tested on 345 notes from patients with esophageal cancer undergoing RT. RESULTS: Fine-tuning of PubMedBERT yielded the best performance. The best macro-F1 was 0.92, 0.82, and 0.74 for tasks 1, 2, and 3, respectively. Selecting the most informative note sections during fine-tuning improved macro-F1 by ≥2% for all tasks. Silver-labeled data improved the macro-F1 by ≥3% across all tasks. For the esophageal cancer notes, the best macro-F1 was 0.73, 0.74, and 0.65 for tasks 1, 2, and 3, respectively, without additional fine-tuning. CONCLUSION: To our knowledge, this is the first effort to automatically extract esophagitis toxicity severity according to CTCAE guidelines from clinical notes. This provides proof of concept for NLP-based automated detailed toxicity monitoring in expanded domains.