Brian Anthony

Shan Chen, Mingye Gao, Kuleen Sasse et al. · harvard

Background: Large language models (LLMs) are trained to follow directions, but this introduces a vulnerability to blindly comply with user requests even if they generate wrong information. In medicine, this could accelerate the generation of misinformation that impacts human well-being. Objectives/Methods: We analyzed compliance to requests to generate misleading content about medications in settings where models know the request is illogical. We investigated whether in-context directions and instruction-tuning of LLMs to prioritize logical reasoning over compliance reduced misinformation risk. Results: While all frontier LLMs complied with misinformation requests, both prompt-based and parameter-based approaches can improve the detection of logic flaws in requests and prevent the dissemination of medical misinformation. Conclusion: Shifting LLMs to prioritize logic over compliance could reduce risks of exploitation for medical misinformation.

Zhuorui Zhang, Roger Pallarès-López, Xuan Wu et al.

Ultrasound is the most widely used real-time imaging modality in clinical practice, yet per-frame video annotation remains a major bottleneck: expert labels are scarce and costly, and image appearance varies with speckle, shadowing, attenuation, and operator-dependent probe pose. This is especially limiting because clinically relevant information is often dynamic, from left-ventricular motion in echocardiography to muscle and bone kinematics in musculoskeletal imaging. Population atlases can amortize annotation cost by registering observations to a shared canonical coordinate system, but existing neural atlas methods mainly target single videos, small test-time image sets, or object-centric image collections. We introduce a cohort-scale neural atlas for ultrasound video: a single canonical chart with per-video Generative Latent Optimization embeddings, trained jointly over thousands of frames in DINOv3 feature space. Across five cardiac and musculoskeletal datasets with point landmarks and segmentation masks, our method learns coherent canonical templates and enables accurate atlas-space annotation transfer. On EchoNet-Dynamic and MSK-Bone, it supports single- and few-shot transfer with accuracy competitive with strong dense-correspondence baselines, while training in minutes on a single consumer GPU. The learned embeddings are interpretable: linear projections reveal structured cohort variation, image-decoder interpolation produces anatomically plausible intermediate frames, and test-time latent inversion reconstructs held-out frames through the atlas. These results suggest that cohort-scale neural atlases offer a practical, interpretable representation for reducing expert annotation burden in ultrasound video analysis.

Praneeth Namburi, Roger Pallarès-López, Jessica Rosendorf et al.

Ultrasound technology enables safe, non-invasive imaging of dynamic tissue behavior, making it a valuable tool in medicine, biomechanics, and sports science. However, accurately tracking tissue motion in B-mode ultrasound remains challenging due to speckle noise, low edge contrast, and out-of-plane movement. These challenges complicate the task of tracking anatomical landmarks over time, which is essential for quantifying tissue dynamics in many clinical and research applications. This manuscript introduces DUSTrack (Deep learning and optical flow-based toolkit for UltraSound Tracking), a semi-automated framework for tracking arbitrary points in B-mode ultrasound videos. We combine deep learning with optical flow to deliver high-quality and robust tracking across diverse anatomical structures and motion patterns. The toolkit includes a graphical user interface that streamlines the generation of high-quality training data and supports iterative model refinement. It also implements a novel optical-flow-based filtering technique that reduces high-frequency frame-to-frame noise while preserving rapid tissue motion. DUSTrack demonstrates superior accuracy compared to contemporary zero-shot point trackers and performs on par with specialized methods, establishing its potential as a general and foundational tool for clinical and biomechanical research. We demonstrate DUSTrack's versatility through three use cases: cardiac wall motion tracking in echocardiograms, muscle deformation analysis during reaching tasks, and fascicle tracking during ankle plantarflexion. As an open-source solution, DUSTrack offers a powerful, flexible framework for point tracking to quantify tissue motion from ultrasound videos. DUSTrack is available at https://github.com/praneethnamburi/DUSTrack.

Mingye Gao, Aman Varshney, Shan Chen et al.

Cancer clinical trials often face challenges in recruitment and engagement due to a lack of participant-facing informational and educational resources. This study investigated the potential of Large Language Models (LLMs), specifically GPT4, in generating patient-friendly educational content from clinical trial informed consent forms. Using data from ClinicalTrials.gov, we employed zero-shot learning for creating trial summaries and one-shot learning for developing multiple-choice questions, evaluating their effectiveness through patient surveys and crowdsourced annotation. Results showed that GPT4-generated summaries were both readable and comprehensive, and may improve patients' understanding and interest in clinical trials. The multiple-choice questions demonstrated high accuracy and agreement with crowdsourced annotators. For both resource types, hallucinations were identified that require ongoing human oversight. The findings demonstrate the potential of LLMs "out-of-the-box" to support the generation of clinical trial education materials with minimal trial-specific engineering, but implementation with a human-in-the-loop is still needed to avoid misinformation risks.

Zhuorui Zhang, Roger Pallarès-López, Praneeth Namburi et al.

Acquiring per-frame video annotations remains a primary bottleneck for deploying computer vision in specialized domains such as medical imaging, where expert labeling is slow and costly. Label propagation offers a natural solution, yet existing approaches face fundamental limitations. Video trackers and segmentation models can propagate labels within a single sequence but require per-video initialization and cannot generalize across videos. Classic correspondence pipelines operate on detector-chosen keypoints and struggle in low-texture scenes, while dense feature matching and one-shot segmentation methods enable cross-video propagation but lack spatiotemporal smoothness and unified support for both point and mask annotations. We present Match4Annotate, a lightweight framework for both intra-video and inter-video propagation of point and mask annotations. Our method fits a SIREN-based implicit neural representation to DINOv3 features at test time, producing a continuous, high-resolution spatiotemporal feature field, and learns a smooth implicit deformation field between frame pairs to guide correspondence matching. We evaluate on three challenging clinical ultrasound datasets. Match4Annotate achieves state-of-the-art inter-video propagation, outperforming feature matching and one-shot segmentation baselines, while remaining competitive with specialized trackers for intra-video propagation. Our results show that lightweight, test-time-optimized feature matching pipelines have the potential to offer an efficient and accessible solution for scalable annotation workflows.

Shan Chen, Jack Gallifant, Mingye Gao et al.

Large language models (LLMs) are increasingly essential in processing natural languages, yet their application is frequently compromised by biases and inaccuracies originating in their training data. In this study, we introduce Cross-Care, the first benchmark framework dedicated to assessing biases and real world knowledge in LLMs, specifically focusing on the representation of disease prevalence across diverse demographic groups. We systematically evaluate how demographic biases embedded in pre-training corpora like $ThePile$ influence the outputs of LLMs. We expose and quantify discrepancies by juxtaposing these biases against actual disease prevalences in various U.S. demographic groups. Our results highlight substantial misalignment between LLM representation of disease prevalence and real disease prevalence rates across demographic subgroups, indicating a pronounced risk of bias propagation and a lack of real-world grounding for medical applications of LLMs. Furthermore, we observe that various alignment methods minimally resolve inconsistencies in the models' representation of disease prevalence across different languages. For further exploration and analysis, we make all data and a data visualization tool available at: www.crosscare.net.

Micha Feigin, Daniel Freedman, Brian W. Anthony

Objective: Ultrasound elastography is gaining traction as an accessible and useful diagnostic tool for such things as cancer detection and differentiation and thyroid disease diagnostics. Unfortunately, state of the art shear wave imaging techniques, essential to promote this goal, are limited to high-end ultrasound hardware due to high power requirements; are extremely sensitive to patient and sonographer motion, and generally, suffer from low frame rates. Motivated by research and theory showing that longitudinal wave sound speed carries similar diagnostic abilities to shear wave imaging, we present an alternative approach using single sided pressure-wave sound speed measurements from channel data. Methods: In this paper, we present a single-sided sound speed inversion solution using a fully convolutional deep neural network. We use simulations for training, allowing the generation of limitless ground truth data. Results: We show that it is possible to invert for longitudinal sound speed in soft tissue at high frame rates. We validate the method on simulated data. We present highly encouraging results on limited real data. Conclusion: Sound speed inversion on channel data has significant potential, made possible in real time with deep learning technologies. Significance: Specialized shear wave ultrasound systems remain inaccessible in many locations. longitudinal sound speed and deep learning technologies enable an alternative approach to diagnosis based on tissue elasticity. High frame rates are possible.