arXiv subjects

Stephanie E. Combs

Publications and source records attributed to Stephanie E. Combs.

12 recordsLinked to original sources

arXiv2026

Atomic Fact-Checking Increases Clinician Trust in Large Language Model Recommendations for Oncology Decision Support: A Randomized Controlled Trial

Question: Does atomic fact-checking, which decomposes AI treatment recommendations into individually verifiable claims linked to source guideline documents, increase clinician trust compared to traditional explainability approaches? Findings: In this randomized trial of 356 clinicians generating 7,476 trust ratings, atomic fact-checking produced a large effect on trust (Cohen's d = 0.94), increasing the proportion of clinicians expressing trust from 26.9% to 66.5%. Traditional transparency mechanisms showed a dose-response gradient of improvement over baseline (d = 0.25 to 0.50). Meaning: Decomposing AI recommendations into individually verifiable claims linked to source guidelines produces substantially higher clinician trust than traditional explainability approaches in high-stakes clinical decisions.

cs.CL↗

arXiv2026

Deep-Learning Atlas Registration for Melanoma Brain Metastases: Preserving Pathology While Enabling Cohort-Level Analyses

Melanoma brain metastases (MBM) are common and spatially heterogeneous lesions, complicating cohort-level analyses due to anatomical variability and differing MRI protocols. We propose a fully differentiable, deep-learning-based deformable registration framework that aligns individual pathological brains to a common atlas while preserving metastatic tissue without requiring lesion masks or preprocessing. Missing anatomical correspondences caused by metastases are handled through a forward-model similarity metric based on distance-transformed anatomical labels, combined with a volume-preserving regularization term to ensure deformation plausibility. Registration performance was evaluated using Dice coefficient (DSC), Hausdorff distance (HD), average symmetric surface distance (ASSD), and Jacobian-based measures. The method was applied to 209 MBM patients from three centres, enabling standardized mapping of metastases to anatomical, arterial, and perfusion atlases. The framework achieved high registration accuracy across datasets (DSC 0.89-0.92, HD 6.79-7.60 mm, ASSD 0.63-0.77 mm) while preserving metastatic volumes. Spatial analysis demonstrated significant over-representation of MBM in the cerebral cortex and putamen, under-representation in white matter, and consistent localization near the gray-white matter junction. No arterial territory showed increased metastasis frequency after volume correction. This approach enables robust atlas registration of pathological brain MRI without lesion masks and supports reproducible multi-centre analyses. Applied to MBM, it confirms and refines known spatial predilections, particularly preferential seeding near the gray-white matter junction and cortical regions. The publicly available implementation facilitates reproducible research and extension to other brain tumours and neurological pathologies.

cs.CV↗

arXiv2025

Improving Reliability and Explainability of Medical Question Answering through Atomic Fact Checking in Retrieval-Augmented LLMs

Large language models (LLMs) exhibit extensive medical knowledge but are prone to hallucinations and inaccurate citations, which pose a challenge to their clinical adoption and regulatory compliance. Current methods, such as Retrieval Augmented Generation, partially address these issues by grounding answers in source documents, but hallucinations and low fact-level explainability persist. In this work, we introduce a novel atomic fact-checking framework designed to enhance the reliability and explainability of LLMs used in medical long-form question answering. This method decomposes LLM-generated responses into discrete, verifiable units called atomic facts, each of which is independently verified against an authoritative knowledge base of medical guidelines. This approach enables targeted correction of errors and direct tracing to source literature, thereby improving the factual accuracy and explainability of medical Q&A. Extensive evaluation using multi-reader assessments by medical experts and an automated open Q&A benchmark demonstrated significant improvements in factual accuracy and explainability. Our framework achieved up to a 40% overall answer improvement and a 50% hallucination detection rate. The ability to trace each atomic fact back to the most relevant chunks from the database provides a granular, transparent explanation of the generated responses, addressing a major gap in current medical AI applications. This work represents a crucial step towards more trustworthy and reliable clinical applications of LLMs, addressing key prerequisites for clinical application and fostering greater confidence in AI-assisted healthcare.

cs.CL↗

arXiv2025

Commissioning, characterization and first high dose rate irradiations at a compact X-ray tube for microbeam and minibeam radiation therapy

Minibeam and microbeam radiation therapy promise improved treatment outcomes through reduced normal tissue toxicity at better tumor control rates. The lack of suitable compact radiation sources limits the clinical application of minibeams to superficial tumors and renders it impossible for microbeams. We developed the first prototype of a compact line-focus X-ray tube (LFXT) with technology potentially suitable for clinical translation of minibeams and microbeams. We give an overview of the commissioning process preceding first operation, present optical and radiological focal spot characterization methods, and dosimetric measurements. Additionally, we report on first preclinical in vitro cell and in vivo mouse brain irradiations conducted with the LFXT prototype. The LFXT was high voltage conditioned up to 300 kV.The focal spot characterization resulted in a strongly eccentric electron distribution with a width of 72.3 $μ$m. Dosimetry showed sharp microbeam dose profiles with steep lateral penumbras and a peak-to-valley dose ratio above 10 throughout a 70 mm thick PMMA phantom. An open-field dose rate of 4.3 Gy/s was measured at an acceleration voltage of 150 kV and a beam current of 17.4 mA at 150 mm distance from the focal spot. In vitro and in vivo experiments demonstrated the feasibility of the LFXT for minibeam and microbeam applications with field sizes of 1.5-2 cm. The mice displayed no observable side effects after whole-brain 260 $μ$m-minibeam irradiation. We successfully constructed and commissioned the first proof-of-concept LFXT prototype. Dosimetric characterizations of the achieved microbeam field showed the superiority of the LFXT compared to conventional X-ray tubes in terms of beam quality. In future developments, the remaining limitations of the prototype will be addressed for improved minibeam and first ever microbeam radiation therapy in a clinical setting.

physics.med-ph↗

arXiv2025

Prediction of Local Failure after Stereotactic Radiotherapy in Melanoma Brain Metastases Using Ensemble Learning on Clinical, Dosimetric, and Radiomic Data

Background: This study aimed to predict lesion-specific outcomes after stereotactic radiotherapy (SRT) in patients with brain metastases from malignant melanoma (MBM), using clinical, dosimetric, and pretherapeutic MRI data. Methods: In this multicenter retrospective study, 517 MBM from 130 patients treated with single-fraction or hypofractionated SRT at three centers were analyzed. From contrast-enhanced T1-weighted MRI, 1576 radiomic features (RF) were extracted per lesion - 788 from the gross tumor volume (GTV) and 788 from a 3 mm peritumoral margin. Clinical, dosimetric and RF data from one center were used for feature selection and model development via nested cross-validation employing an ensemble learning approach; external validation used data from the other two centers. Results: Local failure occurred in 72/517 lesions (13.9%). Predictive models based on clinical data, RF, or a combination of both achieved c-indices of 0.60 +/- 0.15, 0.65 +/- 0.11, and 0.65 +/- 0.12, respectively. RF-based models outperformed the clinical models; dosimetric data alone were not predictive. Most predictive RF originated from the peritumoral margin (92%) versus GTV (76%). On the first external dataset, all models performed similarly (c-index: 0.60-0.63), but generalization was poor on the second (c-index < 0.50), likely due to differences in patient characteristics and imaging protocols. Conclusions: Pretherapeutic MRI features, particularly from the peritumoral region, show promise for predicting lesion-specific outcomes in MBM after SRT. Their consistent contribution suggests biologically relevant information that may support individualized treatment planning. Combined with clinical data, these markers offer prognostic insight, though generalizability remains limited by data heterogeneity.

physics.med-ph↗

arXiv2025

CADS: A Comprehensive Anatomical Dataset and Segmentation for Whole-Body Anatomy in Computed Tomography

Accurate delineation of anatomical structures in volumetric CT scans is crucial for diagnosis and treatment planning. While AI has advanced automated segmentation, current approaches typically target individual structures, creating a fragmented landscape of incompatible models with varying performance and disparate evaluation protocols. Foundational segmentation models address these limitations by providing a holistic anatomical view through a single model. Yet, robust clinical deployment demands comprehensive training data, which is lacking in existing whole-body approaches, both in terms of data heterogeneity and, more importantly, anatomical coverage. In this work, rather than pursuing incremental optimizations in model architecture, we present CADS, an open-source framework that prioritizes the systematic integration, standardization, and labeling of heterogeneous data sources for whole-body CT segmentation. At its core is a large-scale dataset of 22,022 CT volumes with complete annotations for 167 anatomical structures, representing a significant advancement in both scale and coverage, with 18 times more scans than existing collections and 60% more distinct anatomical targets. Building on this diverse dataset, we develop the CADS-model using established architectures for accessible and automated full-body CT segmentation. Through comprehensive evaluation across 18 public datasets and an independent real-world hospital cohort, we demonstrate advantages over SoTA approaches. Notably, thorough testing of the model's performance in segmentation tasks from radiation oncology validates its direct utility for clinical interventions. By making our large-scale dataset, our segmentation models, and our clinical software tool publicly available, we aim to advance robust AI solutions in radiology and make comprehensive anatomical analysis accessible to clinicians and researchers alike.

eess.IV↗

arXiv2024

Full-body deep learning-based automated contouring of contrast-enhanced murine organs for small animal irradiator CBCT

Purpose. To alleviate the manual contouring burden, deep learning (DL) based automated contouring has been explored. However, due to the poor contrast resolution of preclinical irradiator CBCT, these methods have been limited to high contrast - minimally anatomically complex - structures such as the heart and lungs. Thus, low contrast abdominal CBCT DL-based segmentation has yet to be addressed. In this work we explore a DL-based model in conjunction with iodine-based contrast agent approach to allow precise automatic contouring of mouse abdominal, thorax, and skeletal structures in under a second. Methods. A DL U-net-like architecture was trained to contour mice organs in small animal radiation research platform CBCT scans. 41 mice were contoured by a human expert, using semi-automatic segmentation methods, after injection of iodine contrast agent, establishing a ground truth for the DL model. The model was trained on a dataset of 26 mice, while 2 mice were used for validation, tuning the model during training, and 15 mice used for performance evaluation testing. The model consists of a pre-processor, and a post-processor for volumetric reconstruction of the DL-predicted probability maps. Model performance was evaluated using both qualitative and distance metrics, including the dice similarity score, precision score, Hausdorff Distance (HD), and mean surface distance (MSD). Results. Performance of the DL-based iodine contrast-enhanced model provided high quality predicted contours in under a second, with the median for all organs being reported: dice $>$ 91\%, precision $>$ 95\%, HD50 $<$ 1.0 mm, and MSD $<$ 1.41 mm. Conclusion. The proposed combination of a DL-based and iodine contrast-enhanced model proved as a viable method to vastly improve efficiency of small animal CBCT image-guided RT preclinical trials.

physics.med-ph↗

arXiv2023

All Sizes Matter: Improving Volumetric Brain Segmentation on Small Lesions

Brain metastases (BMs) are the most frequently occurring brain tumors. The treatment of patients having multiple BMs with stereo tactic radiosurgery necessitates accurate localization of the metastases. Neural networks can assist in this time-consuming and costly task that is typically performed by human experts. Particularly challenging is the detection of small lesions since they are often underrepresented in exist ing approaches. Yet, lesion detection is equally important for all sizes. In this work, we develop an ensemble of neural networks explicitly fo cused on detecting and segmenting small BMs. To accomplish this task, we trained several neural networks focusing on individual aspects of the BM segmentation problem: We use blob loss that specifically addresses the imbalance of lesion instances in terms of size and texture and is, therefore, not biased towards larger lesions. In addition, a model using a subtraction sequence between the T1 and T1 contrast-enhanced sequence focuses on low-contrast lesions. Furthermore, we train additional models only on small lesions. Our experiments demonstrate the utility of the ad ditional blob loss and the subtraction sequence. However, including the specialized small lesion models in the ensemble deteriorates segmentation results. We also find domain-knowledge-inspired postprocessing steps to drastically increase our performance in most experiments. Our approach enables us to submit a competitive challenge entry to the ASNR-MICCAI BraTS Brain Metastasis Challenge 2023.

eess.IV↗

arXiv2022

A unified 3D framework for Organs at Risk Localization and Segmentation for Radiation Therapy Planning

Automatic localization and segmentation of organs-at-risk (OAR) in CT are essential pre-processing steps in medical image analysis tasks, such as radiation therapy planning. For instance, the segmentation of OAR surrounding tumors enables the maximization of radiation to the tumor area without compromising the healthy tissues. However, the current medical workflow requires manual delineation of OAR, which is prone to errors and is annotator-dependent. In this work, we aim to introduce a unified 3D pipeline for OAR localization-segmentation rather than novel localization or segmentation architectures. To the best of our knowledge, our proposed framework fully enables the exploitation of 3D context information inherent in medical imaging. In the first step, a 3D multi-variate regression network predicts organs' centroids and bounding boxes. Secondly, 3D organ-specific segmentation networks are leveraged to generate a multi-organ segmentation map. Our method achieved an overall Dice score of $0.9260\pm 0.18 \%$ on the VISCERAL dataset containing CT scans with varying fields of view and multiple organs.

cs.CV↗

arXiv2021

Evaluating the Robustness of Self-Supervised Learning in Medical Imaging

Self-supervision has demonstrated to be an effective learning strategy when training target tasks on small annotated data-sets. While current research focuses on creating novel pretext tasks to learn meaningful and reusable representations for the target task, these efforts obtain marginal performance gains compared to fully-supervised learning. Meanwhile, little attention has been given to study the robustness of networks trained in a self-supervised manner. In this work, we demonstrate that networks trained via self-supervised learning have superior robustness and generalizability compared to fully-supervised learning in the context of medical imaging. Our experiments on pneumonia detection in X-rays and multi-organ segmentation in CT yield consistent results exposing the hidden benefits of self-supervision for learning robust feature representations.

cs.CV↗

arXiv2020

Deep Learning Based HPV Status Prediction for Oropharyngeal Cancer Patients

We investigated the ability of deep learning models for imaging based HPV status detection. To overcome the problem of small medical datasets we used a transfer learning approach. A 3D convolutional network pre-trained on sports video clips was fine tuned such that full 3D information in the CT images could be exploited. The video pre-trained model was able to differentiate HPV-positive from HPV-negative cases with an area under the receiver operating characteristic curve (AUC) of 0.81 for an external test set. In comparison to a 3D convolutional neural network (CNN) trained from scratch and a 2D architecture pre-trained on ImageNet the video pre-trained model performed best.

eess.IV↗

arXiv2020

Deep Reinforcement Learning for Organ Localization in CT

Robust localization of organs in computed tomography scans is a constant pre-processing requirement for organ-specific image retrieval, radiotherapy planning, and interventional image analysis. In contrast to current solutions based on exhaustive search or region proposals, which require large amounts of annotated data, we propose a deep reinforcement learning approach for organ localization in CT. In this work, an artificial agent is actively self-taught to localize organs in CT by learning from its asserts and mistakes. Within the context of reinforcement learning, we propose a novel set of actions tailored for organ localization in CT. Our method can use as a plug-and-play module for localizing any organ of interest. We evaluate the proposed solution on the public VISCERAL dataset containing CT scans with varying fields of view and multiple organs. We achieved an overall intersection over union of 0.63, an absolute median wall distance of 2.25 mm, and a median distance between centroids of 3.65 mm.

eess.IV↗