Papers for

medical device companies

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.

Hybrid quantum machine learning boosts liver disease detection accuracy

KQML-Liver: Interpretable Hybrid Quantum Machine Learning with Kolmogorov-Arnold Networks for Liver Disease Classification

Abstract: Liver disease remains a major global health concern, highlighting the need for reliable and accessible early detection methods. Although recent advances in machine learning, deep learning and quantum machine learning (QML) have introduced promising diagnostic tools, many approaches suffer from limited interpretability and inflated performance caused by data leakage or overly simplistic evaluation protocols. These constraints reduce their reliability in real-world clinical practice. This paper proposes KQML-Liver, a hybrid framework that integrates QML with Kolmogorov-Arnold Networks (KANs) to enhance predictive performance and interpretability. The architecture combines parameterized quantum circuits for expressive feature representation with KAN-based functional mappings that capture nonlinear relationships in an interpretable manner. Evaluated on the Indian Liver Patient Dataset (ILPD) under a rigorous preprocessing protocol preventing data leakage, the proposed model achieves 82% classification accuracy and 100% recall, detecting all positive cases, outperforming existing baselines while providing improved transparency in clinical predictions. These results suggest that hybrid KAN-quantum architectures offer a promising direction for interpretable AI-assisted medical diagnosis.

Wed 11 NovMachine LearningArtificial Intelligence
The gist
Liver disease can be hard to detect early, which makes treatment difficult. The authors developed a new approach combining quantum computing techniques with special networks to better identify liver disease from patient data. Their method not only improved how well the disease was detected but also made the decision process easier to understand by doctors. This could help medical professionals trust and use AI tools more confidently in diagnosing liver problems.
Open → 2611.15241v1

Medical images translated without paired training while preserving anatomy

Anatomy-Preserving Unpaired Medical Image Translation via Shared Latent Anchoring

Abstract: Unpaired medical image-to-image translation requires synthesizing target-modality images from source-modality images without aligned supervision. Existing methods learn a direct source-to-target mapping that entangles structure preservation and appearance generation within a single model, often distorting clinically meaningful anatomy in the translated output. We argue that these two objectives should be decoupled entirely: anatomical structure should be captured independently of generation, and the generator should operate only on a frozen structural representation. To this end, we propose a two-stage framework for unpaired medical image translation. In the first stage, we learn a shared structure space by training a structure encoder-decoder on source images, target images, and structural masks jointly, using mask reconstruction to anchor the latent space to modality-agnostic anatomy. For source images without mask annotations, a target-domain memory bank provides soft structural supervision via prototype retrieval. In the second stage, a conditional flow model learns to render target-domain appearance under fixed structural conditions. This ensures the generator inherits target appearance statistics and can focus entirely on structural conditioning rather than learning appearance from scratch. We validate our framework on OCT-to-OCTA synthesis and brain MR-to-CT translation. Our method outperforms all unpaired baselines on both tasks and, despite requiring no paired supervision, also surpasses paired baselines, improving PSNR by up to 11.2% and SSIM by up to 26.4% on OCT-to-OCTA, and achieving consistent gains across whole-image, soft-tissue, and bone regions on MR-to-CT. The project repository is available on GitHub.

Fri 6 NovComputer Vision and Pattern Recognition
The gist
Converting medical images from one type to another usually requires matched pairs of images for training, but this is hard to get. The authors propose a method that separates learning the body’s anatomical structure from adding the new image appearance, which helps keep important details intact. They first teach a model to understand body structures across image types, then generate new images based on this stable structure. Tests on eye and brain scans show this approach produces clearer, more accurate translated images than existing methods, even those trained with pairs.
Open → 2611.10236v1

Ai helps doctors interpret heart ultrasound images better and faster

Multimodal Generative AI Assists Comprehensive Echocardiographic Interpretation

Abstract: Echocardiography is the cornerstone of cardiovascular diagnostics, yet its global utility is constrained by a critical shortage of experienced interpreters. Current artificial intelligence (AI) solutions remain limited, typically operating as opaque "black boxes" or focusing on narrow tasks that fail to capture the holistic, guideline-driven reasoning of a clinician. Here we introduce EchoChat, a generative multimodal vision-language model that performs comprehensive echocardiographic analysis to support clinician interpretation. By emulating the cognitive workflow of a cardiologist, EchoChat integrates vast medical knowledge with a chain-of-thought reasoning mechanism to explicitly ground its conclusions in visual evidence. Trained on echocardiography-instruction pairs from 46,358 examinations, our model establishes a new state-of-the-art across diverse cohorts from six international medical centers. It supports the broadest diagnostic scope of 33 cardiac conditions and findings, including 15 newly added conditions for which it achieves an average F1 of 73.7% across available external evaluations. It surpasses existing best-performing foundation models in cardiac condition recognition (improving average recall by 13.54% on shared tasks) and quantification (average R2 score increase of 0.275 on shared tasks). Furthermore, in a source-blinded echocardiographer reader study, echocardiography reports co-generated with EchoChat were rated higher in diagnostic accuracy and completeness by two senior echocardiographers, and improved diagnostic performance from 72.78% to 82.75% in terms of F1 score over routine-reader only reports. These results demonstrate that integrating clinical reasoning into multimodal AI can democratize specialist expertise and transform the standard of cardiovascular care.

Fri 23 OctComputer Vision and Pattern Recognition
The gist
Heart ultrasound tests help doctors see how your heart works, but it takes special training to read them well. The authors created EchoChat, a smart AI that looks at heart ultrasound images and explains what it sees, like a doctor would. It learned from many past tests and can recognize over 30 heart conditions more accurately than previous AI tools. When doctors used EchoChat's help, their reports were more complete and correct. This AI could make expert heart care easier to access worldwide.
Open → 2610.32880v1

Markerless spinal tracking validated using routine intraoperative X-rays

Bridging the Markerless Tracking Validation Gap: Intraoperative X-ray Workflow Integration

Abstract: Markerless intraoperative tracking of spinal anatomy via RGB-D sensors is a promising alternative to invasive bone-anchored fiducials, yet no existing clinical dataset provides independent subsurface ground truth for validating these methods. We address this gap with a clinically viable pipeline that derives per-vertebra 6-DoF pose from routine intraoperative C-arm fluoroscopy, co-registered to the RGB-D camera frame through a multimodal fiducial array detectable in both imaging modalities. Critically, the pipeline requires no additional radiation, instrumentation, or deviation from standard surgical workflows, relying solely on the fluoroscopic images already acquired during routine level checks. A calibrated transform chain links the vertebral pose recovered via multi-view 2D-3D CT-to-fluoroscopy registration to the RGB-D coordinate frame, enabling direct comparison of any markerless registration estimate against a subsurface reference. Ex vivo validation against optically tracked ovine vertebrae confirms end-to-end accuracy of 2.06 +- 0.29 mm and 3.35 +- 0.93 degrees, sufficient to serve as independent ground truth for methods with substantially larger errors. We demonstrate the pipeline's utility by evaluating two markerless registration strategies on clinical data spanning 11 vertebrae across 1,500 frames from three surgical sequences: the first such evaluation against an independent subsurface reference in a clinical setting. The proposed framework provides reusable infrastructure for benchmarking emerging markerless tracking methods on real surgical data.

Thu 15 OctComputer Vision and Pattern Recognition
The gist
Tracking the spine during surgery without attaching markers to bones is safer but hard to check for accuracy. The authors created a method that uses regular X-ray images taken during surgery to find the exact position of each vertebra and matches this to data from a special camera. This approach doesn't require extra equipment, changes to surgery, or additional X-rays. They tested it on animal bones and surgical data, showing it works reliably to measure how well markerless tracking methods perform.
Open → 2610.21696v1

Focus improves diagnosis of brain tissue during surgery

FOCUS: A Subspecialty Foundation Model for Intraoperative Central Nervous System Pathology

Abstract: Intraoperative frozen-section diagnosis of central nervous system (CNS) lesions guides surgical decisions but is challenged by artefacts, diagnostic complexity and time constraints. Most pathology foundation models have limited exposure to CNS frozen tissue. Here we present FOCUS, a subspecialty foundation model pretrained on 27,930 frozen-sections enriched for CNS tissue. FOCUS led 11 internal diagnostic and 12 biomarker-prediction tasks, with mean AUCs of 0.969 and 0.877, respectively, retaining leading performance in temporal and external cohorts. To provide more comprehensive diagnostic information, we further organized ten diagnostic tasks into a WHO-aligned diagnostic hierarchy and separately evaluated FOCUS for lymphoma detection, a critical task for intraoperative surgical decision-making. In reader assessments by six neuropathologists, FOCUS assistance enabled junior readers to approach or exceed unassisted senior readers in hierarchical diagnosis and raised junior readers' lymphoma sensitivity from 81.6% to 94.7%. FOCUS could improve diagnostic accuracy and granularity, inform lymphoma-related resection decisions and provide provisional molecular information. Such capabilities highlight the potential of FOCUS to provide robust, clinically actionable support for intraoperative CNS pathology.

Mon 12 OctComputer Vision and Pattern Recognition
The gist
Diagnosing brain tissue samples during surgery is very hard because the samples may have artefacts and decisions must be fast. The authors created FOCUS, a specialized AI model trained on many frozen brain tissue samples to help with these diagnoses. It performs very well on many diagnostic tasks, including detecting lymphoma, which is important during surgery. When junior doctors used FOCUS, their accuracy improved to match or beat expert doctors. This tool could help surgeons make better decisions during brain operations.
Open → 2610.16914v1

SurgFlow improves surgical robot tool targeting using 3D object motion

SurgFlow: 3D Object-Centric Contact Flow for Surgical Robot Manipulation

Abstract: Paired video-action demonstrations enable autonomous surgical behavior, but such data is scarce: robots perform roughly 1% of surgeries, while video-only data is abundant. Learning 3D object flow offers an embodiment-agnostic way to utilize video data, but flow alone specifies how an object should move, not where and when the tool should engage it, a distinction that is critical in surgery. We introduce SurgFlow, a framework that learns 3D Object-Centric Contact Flow from stereo surgical video without action labels. For each object point, it predicts a future 3D trajectory and contact scores. We extract targets via 3D tracking and tool-object proximity, train a flow matching generator to predict them, and use predicted contact to trigger grasp and release while optimizing end effector motion from flow. On the da Vinci Research Kit (dVRK), SurgFlow succeeds in 37 of 39 stage evaluations across tissue retraction, bimanual reveal, needle pickup, and handover, outperforming baselines trained on equal data with or without action labels. Zero-shot transfer to a humanoid-based laparoscopic robot achieves 85% and 70% average success under similar and novel camera viewpoints, respectively.

Sun 27 SeptRobotics
The gist
Surgical robots need to know not just how objects move but also when and where to touch them during surgery, which is a tough problem. The authors created SurgFlow, a system that learns from stereo surgery videos to predict both 3D object movements and when surgical tools should contact those objects without needing labeled actions. SurgFlow was tested on a common surgical robot, where it succeeded in almost all tasks, and it also worked well when transferred to a different robot and camera views. This approach helps surgical robots better understand and interact with tissues during procedures using widely available video data.
Open → 2609.33237v1

Foundation models show mixed reliability on retinal image tasks

FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs

Abstract: Progress in AI-based retinal image analysis has advanced with foundation models, yet evaluating their reliability remains challenging. Performance reported on a single dataset does not capture how models behave under dataset shift, across clinical definitions, or for different patient subgroups. This limitation is particularly critical in medical imaging analysis, where robustness, calibration, and fairness are essential for safe deployment. We introduce FOCUS (Foundation Ophthalmic Cross-Dataset Understanding under Shift), a cross-dataset benchmark for evaluating retinal fundus models that considers vision-only encoder models (VM), vision-language dual-encoder models (VLM), and multimodal large language models (MLLM). FOCUS harmonizes binary diabetic retinopathy, referable diabetic retinopathy, and glaucomatous optic neuropathy tasks across ten public datasets spanning diverse geographies, acquisition conditions, and label protocols. The benchmark evaluates models through a unified analysis layer that measures ranking performance, calibration, subgroup disparities, and image-quality robustness. We present a large-scale evaluation covering 532 base configurations and 228 MLLM configurations adapted through supervised fine-tuning with low-rank adaptation (LoRA). Results show that no model family consistently dominates across tasks and datasets: general VM encoders achieve the strongest average ranking performance, medical MLLMs are competitive but variable, and dual encoder VLMs benefit substantially from lightweight adaptation. Fine-tuning improves in-domain performance but exhibits heterogeneous transfer to external datasets, particularly in calibration. These findings demonstrate that retinal model evaluation is inherently multidimensional. FOCUS provides a practical framework and public benchmark to assess generalization, reliability, and robustness beyond single-dataset leaderboards

Sun 27 SeptComputer Vision and Pattern RecognitionArtificial Intelligence
The gist
Retinal image analysis helps detect eye diseases but AI models often struggle when tested on different patient groups or types of images. The authors created a benchmark called FOCUS that tests many AI models across multiple eye disease datasets from different places and imaging conditions. Their results show no single type of model works best everywhere; some models perform well generally, while others need fine-tuning to improve. This work helps to better understand how reliable and fair AI models are for eye disease diagnosis in diverse real-world settings.
Open → 2609.33158v1