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.

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.

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.

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.

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.

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.

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.

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.

Prospective deployment of an automated implementation solution for artificial intelligence translation to clinical radiation oncology.

Introduction: Artificial intelligence (AI)-based technologies embody countless solutions in radiation oncology, yet translation of AI-assisted software tools to actual clinical environments remains unrealized. We present the Deep Learning On-Demand Assistant (DL-ODA), a fully automated, end-to-end clinical platform that enables AI interventions for any disease site featuring an automated model-training pipeline, auto-segmentations, and QA reporting. Materials and methods: We developed, tested, and prospectively deployed the DL-ODA system at a large university affiliated hospital center. Medical professionals activate the DL-ODA via two pathways (1): On-Demand, used for immediate AI decision support for a patient-specific treatment plan, and (2) Ambient, in which QA is provided for all daily radiotherapy (RT) plans by comparing DL segmentations with manual delineations and calculating the dosimetric impact. To demonstrate the implementation of a new anatomy segmentation, we used the model-training pipeline to generate a breast segmentation model based on a large clinical dataset. Additionally, the contour QA functionality of existing models was assessed using a retrospective cohort of 3,399 lung and 885 spine RT cases. Ambient QA was performed for various disease sites including spine RT and heart for dosimetric sparing. Results: Successful training of the breast model was completed in less than a day and resulted in clinically viable whole breast contours. For the retrospective analysis, we evaluated manual-versus-AI similarity for the ten most common structures. The DL-ODA detected high similarities in heart, lung, liver, and kidney delineations but lower for esophagus, trachea, stomach, and small bowel due largely to incomplete manual contouring. The deployed Ambient QAs for heart and spine sites have prospectively processed over 2,500 cases and 230 cases over 9 months and 5 months, respectively, automatically alerting the RT personnel. Discussion: The DL-ODA capabilities in providing universal AI interventions were demonstrated for On-Demand contour QA, DL segmentations, and automated model training, and confirmed successful integration of the system into a large academic radiotherapy department. The novelty of deploying the DL-ODA as a multi-modal, fully automated end-to-end AI clinical implementation solution marks a significant step towards a generalizable framework that leverages AI to improve the efficiency and reliability of RT systems.