Papers for

medical device software developers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Pediatric ECMO care improved with safer offline learning method

Support-Constrained Offline Policy Improvement for Pediatric ECMO from Limited Clinical Data

Abstract: Managing children on ECMO (Extracorporeal Membrane Oxygenation) requires balancing short-term physiological stability with the long-term goal of preventing neurological injury. Standard reinforcement learning can propose risky, out-of-distribution actions, while imitation learning is limited to reproducing clinician behavior. We introduce Support-Constrained Fitted Q-Iteration (FQI-SC), an offline reinforcement learning framework that cautiously improves upon expert behavior by restricting optimization to empirically supported state-action pairs and defaulting to the clinician baseline in low-data regions. On 78 pediatric trajectories totaling over 6,000 hours of clinical data, we evaluate our framework using Fitted Q-Evaluation (FQE) and a behavioral disagreement. Additionally, we formalize the performance-safety trade-off by introducing a unified Balance Score ($S(π)$). Our empirical evaluation shows that support-constrained policy improves the Balance Score by 38\% relative to FQI, improves estimated value by 1.28 FQE units over imitation learning, and reduces disagreement with clinician actions by 71\% relative to FQI.

Thu 12 NovMachine Learning
The gist
Treating children on ECMO is tricky because doctors need to keep kids stable but also avoid long-term brain problems. The authors created a new computer method that carefully learns from past doctor decisions without trying risky new actions. This method improves treatment plans by sticking to what is known and safe, while still making better decisions than just copying doctors. Tests on real ECMO data showed this method works better and agrees more with clinician choices than other approaches.
Open → 2611.17134v1

SurgStreamer enables video-based surgical event detection and alerting

SurgStreamer: proactive, request-driven monitoring of surgical video streams with structured state and a reusable reasoning layer

Abstract: Surgical teams could benefit from assistants that watch the video for requested events, such as "tell me when the clip applier appears during Calot triangle dissection", and answer questions about what has already happened. We formalise this task as request-driven event detection with exact semantics and causal alert decisions, and present SurgStreamer. It separates procedure-specific perception, which maps the 1-FPS stream to a structured state over tools, actions and phases, from procedure-agnostic reasoning, which evaluates a formal monitoring condition over this state and an event memory, either with exact rules or with a small controller that addresses entities through pointers rather than names. We evaluate this monitoring core with gold conditions. On a pre-registered, sealed test set of 12 laparoscopic cholecystectomies, SurgStreamer reached a macro event-F1 of 0.598 over full procedures. On identical 75-s windows with only the window available to every method, it scored 0.677. The tested configurations of the streaming vision-language model OneStreamer-4B, including ones fine-tuned on SurgStreamer's state or on video with an adapted vision encoder, scored at most 0.540 (Holm-adjusted p <= 0.012). At three external centres, re-training only perception raised performance on held-out procedures from 0.239 to 0.470. On a new procedure, pituitary surgery, controller weights trained on cholecystectomy matched an in-domain controller on oracle state (0.947 vs 0.938). On predicted state they missed the pre-registered non-inferiority margin (-0.024 [-0.040, -0.008]) unless the alert thresholds were re-calibrated. The results support separating perception from reasoning and point to perception under distribution shift as the main limitation.

Thu 15 OctComputer Vision and Pattern Recognition
The gist
Surgical teams often need help recognizing important events during operations by watching video feeds. The authors developed SurgStreamer, which watches surgery videos at a set speed and tracks tools, actions, and stages in a structured way. It then uses a separate reasoning system to detect and alert teams about specific requested events, like when a certain tool appears. Tests showed SurgStreamer can recognize events better than some advanced AI methods, especially if its perception part is retrained for different hospitals or surgeries. This means watching surgery videos can be split into understanding the video and making decisions based on that understanding.
Open → 2610.21895v1

SurgiCLAW improves precision skill control for brain surgery robots

SurgiCLAW: An Interpretable Atomic-Skill Agent for Precision Robotic Micromanipulation

Abstract: Recent multimodal large language models (MLLMs) and vision--language--action models have provided robots with new capabilities for long-horizon task understanding and planning. In surgical robotics, however, end-to-end prediction of low-level actions remains limited by insufficient precision, opaque decisions, and scarce data. This paper presents SurgiCLAW, a hierarchical skill-based framework for precision surgical manipulation. SurgiCLAW confines an MLLM to intraoperative visual understanding, structured explanation, and atomic surgical-skill selection, while delegating physical execution to verifiable deterministic control programs. For brain--machine-interface implantation, a representative high-precision surgical task, we construct a state-to-skill invocation dataset and expand it through visual and state perturbations. The model first learns structured skill invocation through supervised fine-tuning and is then optimized using three rewards for action correctness, operation prerequisites, and format validity, improving action selection, operational safety, and output parseability. We evaluate subtask success, offline model comparison, real-robot performance, and ablations. On a fixed test set, SurgiCLAW achieves 94.6% skill-selection accuracy and 93.0% macro-averaged F1 (Macro-F1). Across 50 closed-loop real-robot implantation trials, it achieves an 88.0% task success rate.

Sun 11 OctRoboticsArtificial Intelligence
The gist
Robots performing delicate brain surgeries need to make very precise and safe movements. The authors created SurgiCLAW, a system that uses a language model to decide the right small surgical steps by understanding images during surgery. It then relies on reliable control programs to carry out these steps accurately. Tested on actual robots, SurgiCLAW was able to pick the right actions most of the time and complete complex surgical tasks successfully. This approach combines smart decision-making with guaranteed accurate execution.
Open → 2610.15766v1

Federated learning improves infant movement analysis with uncertainty measure

Uncertainty-Aware Federated Learning for Infant Movement Analysis

Abstract: Infant movement analysis provides valuable biomarkers for the early identification of neurodevelopmental disorders. Recent advances in deep learning have enabled automated analysis of infant movements from video-derived skeletal representations, achieving performance comparable to expert assessment for tasks such as General Movement Assessment (GMA). However, most existing approaches rely on centralized training, requiring data from multiple institutions to be collected and stored at a single site. Such assumptions are often impractical in clinical settings due to privacy, governance, and data-sharing constraints. To address these challenges, we present, to the best of our knowledge, the first federated learning framework for automated infant movement analysis and General Movement Assessment using skeletal motion data. As a clinically relevant use case, the proposed framework is evaluated on fidgety movement classification. To quantify model confidence, Monte Carlo (MC) Dropout is employed to estimate predictive uncertainty during inference. Building upon this, we propose an Uncertainty-Aware Federated Averaging (UA-FedAvg) strategy that incorporates predictive entropy derived from MC-Dropout into the federated aggregation process, enabling client contributions to be adjusted according to their predictive uncertainty. Experiments were conducted using a cross-subject evaluation protocol under a three-client federated learning setting. Results demonstrate that federated learning substantially improves classification performance compared with independently trained local models while achieving performance approaching that of centralized training. Furthermore, UA-FedAvg and its variant incorporating validation loss generally outperform conventional FedAvg across the evaluated data-split configurations.

Fri 25 SeptMachine LearningArtificial IntelligenceComputer Vision and Pattern Recognition
The gist
Identifying early signs of brain development problems in babies can be done by watching how they move, which is usually hard and needs expert eyes. The authors created a way for computers at different hospitals to learn from baby movement data without sharing it all in one place, protecting privacy. They also found a way for the computer models to know which hospitals have more reliable data and give those more influence. Their tests show this approach works nearly as well as having all data in one spot and better than each hospital learning alone.
Open → 2609.31463v1

U-PEN Mamba improves retinal vessel segmentation with efficient global context

U-PEN Mamba: Progressive Expansion with Selective State-Space Modeling for Efficient Retinal Vessel Segmentation

Abstract: Accurate retinal vessel segmentation is important for computer-aided ophthalmic analysis, yet thin vessels, low contrast, and severe foreground-background imbalance remain challenging for encoder-decoder networks. This paper presents U-PEN Mamba, a U-shaped retinal vessel segmentation architecture that couples progressive nonlinear feature expansion with selective state-space modeling. The proposed network enriches local vessel responses with progressive expansion, models long-range spatial dependencies through a Mamba Global Context (MGC) block with linear sequence complexity, and uses attention-based decoder fusion to recover fine vascular boundaries. We evaluate U-PEN Mamba on CHASE DB1 and DRIVE using a consistent patch-based preprocessing pipeline and compare it with convolutional, attention-based, transformer-based, and Mamba-based segmentation baselines. U-PEN Mamba obtains the best mean intersection over union among the compared methods, achieving 0.8394 on CHASE DB1 and 0.8221 on DRIVE, with Dice scores of 0.8187 and 0.8078, respectively, using 21.6M trainable parameters. Ablation studies show that the MGC block contributes the largest gain over the U-Net baseline, while projection dimension and state size provide practical accuracy-efficiency control. These results indicate that selective state-space modeling is a promising global-context mechanism for parameter-efficient retinal vessel segmentation. Code is available at: https://github.com/areyesan/UPEN_Mamba.

Mon 21 SeptComputer Vision and Pattern Recognition
The gist
Identifying the tiny blood vessels in eye images is important for eye health analysis but is difficult due to faint signals and image complexity. The authors created U-PEN Mamba, a computer program that improves this by expanding how it looks at local details step-by-step and including a special block to understand wider patterns efficiently. This helps the system better outline thin vessels and handle difficult parts of the image. Tests show it outperforms other methods on standard retina image datasets with reasonable model size. This approach can help build better tools for automatic eye disease diagnosis.
Open → 2609.24049v1

OphBiWSSD improves eye surgery action detection with faster modeling

OphBiWSSD: Scaling Temporal Action Localization in Ophthalmic Surgeries with Bidirectional Weight-tied State Space Duality

Abstract: High-frequency surgical maneuvers in ophthalmology necessitate high-fidelity temporal modeling, yet characterizing long-range procedural dependencies remains computationally prohibitive for attention-based architectures. Existing models often require aggressive temporal downsampling, which compromises the detection of fine-grained action boundaries and instrument-tissue interactions. To address these scalability constraints, we present OphBiWSSD, a framework that reformulates surgical temporal action localization leveraging Bidirectional State Space Duality. By employing a weight-tied selective scan mechanism that incorporates both preceding and succeeding surgical contexts, our approach facilitates the global synthesis of non-causal temporal cues with linear complexity. This streamlined architecture is well-suited to capture the bidirectional dependencies present in ophthalmic workflows, effectively bridging the gap between local boundary precision and long-range procedural context without incurring the quadratic memory overhead of traditional Transformers. Extensive experiments on the OphNet benchmark demonstrate that OphBiWSSD achieves state-of-the-art temporal localization performance, with mean Average Precisions of 44.42% on phases and 43.08% on operations, surpassing the baselines by 6.80% and 6.66%, respectively. Empirical validation indicates that our approach ensures precise temporal localization and offers a computationally viable pathway for deploying surgical intelligence systems in clinical environments. The code is publicly available at https://github.com/yo3nglau/OphBiWSSD.

Fri 11 SeptComputer Vision and Pattern Recognition
The gist
Eye surgeries involve very quick and precise movements that are hard to analyze because current computer models struggle to understand long and detailed sequences without slowing down too much. The authors created OphBiWSSD, a method that looks at surgical videos both forwards and backwards in time, which helps it spot important moments more accurately and faster than previous systems. This new approach uses a clever way to handle information efficiently, making it possible to monitor surgical steps closely without using too much computer memory. Their tests show it works better than earlier methods on a benchmark for eye surgery videos. This research could help build smarter tools that assist surgeons during operations.
Open → 2609.12409v1