Medical
-
Not What You Meant: Can LLMs Follow a Specified Negation Semantics?
2026-09-23 08:14:47Qiming Bao, Agnieszka Mensfelt, Michael J. Witbrock, Kostas StathisAbstract
Negation does not carry a uniform interpretation across domains. In legal, regulatory, and medical reasoning, the intended interpretation depends on the reading in force -- open- versus closed-world, two- versus three-valued, and credulous versus skeptical. We study which reading of negation large language models adopt by default and whether they can override that preference when a different reading is explicitly specified. To this end, we introduce NAFBench, a procedural generator of solver-certified instances spanning four semantic viewpoints: SLDNF, well-founded semantics (WFS), and credulous and skeptical reasoning under stable-model semantics. The generator emits ground normal logic programs with controlled depth, width, and cycle structure. Each program is solved under all four viewpoints using SWI-Prolog, a well-founded semantics solver, and clingo, yielding up to four divergent labels. The programs are then verbalized into natural language under multiple framings and rule orderings that leave the answer invariant. The results expose a consistent gap. Across open-source models, following a specified negation semantics remains unsolved: the strongest models score 59--74% across the four semantic viewpoints, while the weakest score 31--67%. All models are order-sensitive on more than half of logically identical rule shufflings, while the two weaker models frequently overcommit on well-founded "undefined." Two frontier models reach 100% on the main fixed-complexity evaluation set, and a third, o4-mini, is near-perfect, falling only to 81% on well-founded "undefined." Delegating reasoning to a solver, fine-tuning on certified traces, or forcing an explicit three-valued verdict each partly closes the gap.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27517
PDF
-
NV-Reason-CT: 3D Visual Language Model for CT Analysis
2026-09-23 08:09:54Andriy Myronenko, Dong Yang, Yucheng Tang, Baris Turkbey, Benjamin Simon, Stephanie Harmon, Rikhil Makwana, Mariam Aboian, Sena Azamat, Ibrahim Ethem Hamamci, Sezgin Er, Bjoern Menze, Marc Edgar, Yufan He, Pengfei Guo, Daguang XuAbstract
We present NV-Reason-CT, a generative vision--language model for chest and abdominal CT combining native 3D visual encoding with radiologist-guided reasoning. The model couples a native 3D vision transformer with a language model, passing all visual tokens and their explicit 3D coordinates into language decoding without further spatial token merging. This retains volumetric spatial information within the vision encoder and through the language model's positional encoding during joint processing with text. We train on a curated corpus of approximately 550,000 multimodal instruction examples from 70,111 unique CT image inputs, combining standardized reports, abnormality-focused and anatomy-specific questions, multi-turn interactions, and radiologist-authored reasoning from recorded and transcribed expert CT interpretations. Expert annotations provide direct supervision and guide additional report-grounded synthetic reasoning. End-to-end supervised fine-tuning (SFT) is followed by Group Relative Policy Optimization (GRPO), with verifiable rewards over chest and abdominal abnormality sets. The model supports abnormality classification, report generation, and interactive reasoning with reviewable observations, differential diagnoses, and uncertainty. Evaluation spans public CT benchmarks and a held-out NIH cohort. On CT-RATE, NV-Reason-CT achieves a macro-F1 of 0.614 and macro-AUROC of 0.871 without a task-specific classification head; generated reports achieve a report-derived macro-F1 of 0.592. In a preliminary study with expert radiologists, AI-assisted review received favorable confidence ratings and was associated with a 50% reduction in average reported interpretation and reporting time. We release the model and training code to support reproducible research on explainable AI for volumetric medical imaging.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27511
PDF
-
Alignment Inertia: Auditing the Durability of Training Data Influence Through Policy Override Resistance
2026-09-23 04:12:29Renata Barreto, Markelle Roesti, Mohammad TahaeiAbstract
Platform operators increasingly rely on system prompts and fine-tuning to govern model behavior, yet it remains unclear how reliably these interventions override behavior inherited from prior training. We propose Override Success Rate (OSR) and alignment inertia to measure when operator interventions succeed or fail to change prior behavior. We evaluate zero-shot prompting and LoRA fine-tuning across Llama and Mistral in medical misinformation and hate speech. Alignment inertia persists across both models but varies by model, domain, and policy direction. Notably, in Mistral's restrictive hate-speech condition, LoRA increased inertia by 46.5 percentage points, showing that fine-tuning can reinforce rather than override prior behavior. We also use TRAK to test whether inertia is associated with weaker adaptation signals. TRAK achieves AUC of at least 0.85 in 7 of 8 conditions and outperforms model confidence, TF-IDF similarity, and embedding similarity as a predictor of inertia. These results provide an operator-facing audit of where prior training constrains downstream model governance.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27333
PDF
-
Learning Spectral Allocation: A Fractional Diffusion Framework for Adaptive Volumetric Segmentation
2026-09-23 01:29:46Yi-Hui Shen, Tie-Qiang LiAbstract
We address adaptive computation in 3D medical image segmentation: instead of designing another backbone, we ask how much spectral mixing each network stage needs and let optimization answer. We derive FHEAT, a two-parameter operator family, from the discrete cosine transform (DCT) solution of a fractional heat equation. A fractional order alpha and a diffusion strength D govern the operator, and at D=0 it is exactly the identity. Reparametrized by the semigroup time tau = D*alpha, same-resolution instances compose exactly, so any distribution of diffusion across same-resolution stages amounts to a single Sobolev-type regularizer of learned strength. This identity limit lets the optimizer of each layer, not the designer, decide whether global mixing is needed and how sharp it should be. We instantiate FHEAT in a lightweight U-shaped architecture (Light-UNETR) paired with a Kolmogorov-Arnold mixer (KAN3D) with adaptive rational activations, yielding FHEAT-Seg. At 5% to 20% label rates on three public benchmarks, training produces gradient-driven spectral sparsification: seven of the eight stage-level operators drive D to zero, and the survivor saturates at the sharpest low-pass (alpha ~ 0.9) in the decoder layer feeding the semi-supervised attention map. The retired layers become exact identity shortcuts at inference, cutting FLOPs from 4.29G to 0.90G (a 79% drop) at 0.975M parameters. Under a standard semi-supervised protocol, FHEAT-Seg reaches Dice scores of 90.47% (left atrium), 78.79% (Pancreas-CT), and 81.90% (BraTS 2019), ahead of five semi-supervised methods and the Light-UNETR baseline. The large variant also surpasses Light-UNETR-L under full supervision (Dice 93.09%, 85.11%, and 87.19%) with 2.851M parameters and 55.75G FLOPs. These results suggest that the allocation of spectral computation is a learnable property of optimization dynamics, not a manual design commitment.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27217
PDF
-
Fine Wrist Control as a Marker of Surgical Teleoperation Expertise
2026-09-22 23:46:19Mary Kate Gale, Shujiro Shobayashi, Sangeet Satpathy, Nitsan Davidor, Ilana Nisky, Allison OkamuraAbstract
Unlike most intensely physical pursuits, surgical robotic teleoperation training focuses primarily on task outcomes rather than surgeon body posture or biomechanics during task completion. Toward the question of the role of biomechanics in surgical expertise, we sought to characterize the articular motion of expert teleoperators as compared to novice users. Twenty-seven novices and nine experts completed a non-medical cylinder-on-peg transfer task while their upper limb biomechanics were recorded via motion trackers. During more difficult motions, experts stabilized their wrist motion more than novices, while maintaining adequate range of motion in their shoulder and elbow and completing the task significantly faster than novices. This marker of expertise suggests the importance of attention to user biomechanics during teleoperation of surgical robots.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27160
PDF
-
COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference
2026-09-22 18:10:07Norah Alballa, Wenxuan Zhang, Salma Kharrat, Fares Fourati, Zafar Ayyub Qazi, Mohamed Elhoseiny, Marco CaniniAbstract
No single Large Language Model (LLM) is uniformly reliable across queries, motivating multi-model inference systems that either route among models or combine their outputs. However, routing stops after selecting an initial model, while dense collaboration invokes peers on every query. We show that collaboration is non-monotonic: peers can recover failures that no model solves alone, but can also corrupt initially correct answers. We introduce COMED (Controlled Model Escalation for Multi-LLM Deliberation), a post-anchor controller for selective cross-model collaboration. COMED uses anchor self-consistency, router margin, and a lightweight peer probe to accept confident answers, verify ambiguous cases, and escalate only when collaboration is likely beneficial. We formalize this trade-off with a rescue-harm decomposition showing that selective collaboration improves when rescued errors outweigh collaboration-induced harms. Across medical, scientific, and general reasoning benchmarks, COMED improves fixed and routed anchors in all 16 open-weight settings, with gains up to +10.7 percentage points on MedQA while invoking fewer models and using fewer decoded tokens than dense collaboration. On HLE with frontier models, COMED improves GPT-5.5 from 23.1% to 28.1%, outperforming dense collaboration and achieving the best results.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26913
PDF
-
GAD-MambaUNet: Direction-Group Mamba with Gradient-Adaptive DINOv3 Distillation for Lightweight Medical Image Segmentation
2026-09-22 17:20:33Fang Wang, Huitao Li, Wenhan Chao, Zheng Zhuo, Xinxin YangAbstract
In this paper, we proposed GAD-MambaUNet, a lightweight medical image segmentation network that combines efficient local modeling, direction--group state-space interaction, and training-time foundation-model supervision. To improve contextual modeling in compact segmentation networks, we introduced Direction-Group Graph Selective Scan (DG-GSS), which treated scan-direction and channel-group responses as graph nodes and enabled structured information exchange before multi-directional fusion. We further incorporated DINOv3-GAD supervision, where a frozen DINOv3 teacher provided semantic guidance during training, and Gradient-Adaptive Distillation dynamically regulated the distillation strength. GAD-MambaUNet achieves a favorable accuracy--efficiency balance compared with representative lightweight and general segmentation methods. Ablation studies further verify the effectiveness of DG-GSS and training-time DINOv3-GAD supervision. In future work, we will explore more flexible teacher--student alignment strategies and extend the proposed framework to more diverse medical segmentation scenarios, such as multi-class and multi-modal segmentation tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26729
PDF
-
A Data-Interventional Framework for Auditing Privacy and Fairness in Generative Medical Imaging
2026-09-22 15:55:44Mischa Dombrowski, Bernhard KainzAbstract
Diffusion-based synthetic data generation offers a promising route for sharing medical imaging data without releasing sensitive patient records. However, generative models face a fundamental tension between privacy and fairness: they may memorize rare training samples, leading to privacy risks, or fail to reproduce underrepresented features, resulting in unfair synthetic distributions. While prior work has largely focused on either memorization or fairness in isolation, their interaction remains insufficiently understood. In this work, we introduce a data-interventional framework to systematically analyze privacy and fairness in diffusion models. We discuss synthetic anatomical fingerprints (SAFs), rare and manually injected image features, as controlled probes to study whether models generalize sensitive attributes across identities, memorize training samples, or suppress rare signals entirely. Across multiple conditioning modalities, we observe a consistent behavior: models either forget these fingerprints or memorize the entire image in which they appear, but do not generalize them to novel images. To support large-scale auditing where explicit sample extraction is infeasible, we further introduce the indicator metric t', which estimates a model's susceptibility to memorization by exploiting the internal structure of the diffusion process. By comparing conditioning signals of varying surprisal, we reveal a clear relationship between conditioning rarity and memorization behavior. Highly surprising conditioning signals act as retrieval keys that amplify memorization, whereas low-surprisal conditioning signals systematically suppress rare features, even when these appear repeatedly in the training data. Our findings provide actionable insights and concrete mitigation strategies for safe and fair synthetic medical data sharing. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26623
PDF
-
MMAP: Multimodal Missing-Aware Pretraining for Longitudinal Alzheimer's Prediction
2026-09-22 15:50:42Fiona Kekwick, Matthew Baugh, Bernhard Kainz, Paul M. Matthews, Wenjia BaiAbstract
Clinical decision making heavily relies on predicting the disease progression trajectory by seeking to understand patient's health status which is characterised by multimodal medical data. AI holds great potential for learning useful representations from multimodal medical data to predict disease progression and aid clinical decision making. However, development of predictive AI models is constrained by missing modalities and incomplete tabular data frequently occurring in medical datasets. In addition, disease labels alone may only provide limited supervisory signals for learning representations from high-dimensional multimodal data. Here, we present MMAP, a novel Multimodal Missing-aware Alignment Pretraining method for learning image-tabular representations from incomplete data. An image encoder is pretrained with efficient sigmoid contrastive learning combined with generative reconstruction. A tabular encoder is built upon a tabular foundation model. A missing token generator enables the two encoders to take incomplete data as input, enabling the model to be robust against missing modalities, either with missing images or missing tabular data. We evaluate the clinical usefulness of the learnt multimodal representations on two challenging longitudinal clinical tasks for Alzheimer's disease: predicting disease stage conversion and predicting amyloid status. The proposed method outperforms strong multimodal and unimodal baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26617
PDF
-
Foundation model embeddings capture pre-diagnostic changes on screening mammograms
2026-09-22 15:42:43Kalina P. Slavkova, Eric Brattain, Aditya Gowd, Akash Pattnaik, Jean-Benoit Delbrouck, Matthew Morgan, Julie Bauml, Javid Abderezaei, Khan SiddiquiAbstract
Foundation model embeddings of screening mammograms may encode pre-diagnostic tissue change without task-specific adaptation. We tested whether embeddings move faster along a data-derived "cancer direction" in women later biopsied for cancer than in matched screen-negative controls, and whether this depends on pretraining domain. We studied 1,773 biopsied women (785 malignant, 988 biopsy-negative) and 1,773 matched controls, each with at least two annual screening exams before their index exam. An identical pipeline was applied to four 2D models: Mammo-CLIP (MC, out-of-distribution mammography), HOPPR (in-distribution mammography), MedImageInsight (MII, general medical imaging), and BiomedCLIP (biomedical vision-language pretraining on literature figures). Breast-level embeddings quantified longitudinal movement along the cancer direction. We compared cases and controls using a between-patient design with complementary mixed-effects analysis, and biopsied versus healthy contralateral breasts within patients. Under matched modality in MII embedding space, malignant cases drifted significantly faster than controls in the first two screening intervals preceding the index exam; biopsy-negative cases showed significance only in the first. MC differences were significant in the first interval for both biopsy groups. Within-patient comparisons showed a broadly similar pattern, with MC significance extending to the second interval in both groups and HOPPR showing significance at interval 1. BiomedCLIP showed no significant differences in either design or biopsy group. Overall, directional embedding velocity emerges as a property of clinically grounded rather than general biomedical pretraining, showing that foundation model embeddings can encode pre-diagnostic mammographic change without task-specific adaptation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26605
PDF
-
Radiomics--Foundation Fusion for Interpretable RCC Classification: Internal Benchmarking and Exploratory External Transfer
2026-09-22 15:25:59Yuan Liang, Fangyijie Wang, Kathleen M. Curran, Gu\'enol\'e Silvestre, Sourav Bhattacharjee, Abraham CampbellAbstract
Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced CT remains clinically challenging because clear cell RCC (ccRCC) and non-clear cell RCC often show overlapping imaging appearances. This study evaluates whether foundation representations reduce reliance on handcrafted radiomics, or whether radiomics remains complementary for interpretable tumour characterisation. We compared radiomics, conventional CNN features, MedicalNet-pretrained features, MedVAE representations, and fusion variants for binary ccRCC classification on KiTS23, reporting area under the receiver operating characteristic curve (AUC) with bootstrap confidence intervals and average precision (AP) as a complementary class-imbalance-sensitive metric. We further assessed branch-removal ablation, TCGA/AIMI external transfer, and interpretability using radiomics permutation importance and gate-level analysis. Internally, 3D MedVAE gated fusion achieved the best performance, with an AUC of 82.7% and AP of 92.2%. On the external TCGA cohort, the same model achieved an AUC of 79.5% and AP of 98.9%, although specificity remains uncertain because only two external non-ccRCC cases were available. Gate analysis showed a radiomics-dominant fusion regime, suggesting that foundation representations acted as case-dependent refinement signals rather than replacements for structured tumour descriptors. These findings support radiomics as a complementary and clinically interpretable component of CT-based RCC characterisation in the foundation-model era.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26578
PDF
-
PP-Net: A Hybrid Physical-Prior Neural Network for Scattered Light Removal in Biomedical Images on Embedded Devices
2026-09-22 14:19:16Yongfei Guo, Tingjin Chu, Mengzhuo Liu, Hongwei Lou, Yuanhao GongAbstract
Scattered light is common in biomedical images, yet its removal remains challenging. The difficulty arises from three aspects: first, aligned scattered-light-free biomedical ground truth is often unavailable; second, scattering is coupled with weak illumination and sensor-induced noise; and third, many learning-based restoration models are computationally expensive for embedded devices in Internet of Medical Things (IoMT) scenarios. To address these issues, this paper proposes PP-Net, a hybrid physical-prior neural network for biomedical scattered light removal. The proposed method consists of three components: DFN-Net suppresses sensor-induced noise, ASAP estimates the scattering map and recovers a physics-based prior map, and GF-Net refines the prior map by fusing it with the denoised observation. To reduce the dependence on paired biomedical ground truth, a progressive synthetic training and cross-domain transfer strategy is developed. Experiments show that the physical-prior branch improves the peak signal-to-noise ratio (PSNR) by up to 1.26 dB on paired synthetic benchmarks. Under joint noise-and-scattering degradation, PP-Net improves PSNR by more than 10.8 dB and the structural similarity index measure (SSIM) by more than 0.62 compared with representative baseline methods. On real W2S biomedical images, the proposed method reduces the average Natural Image Quality Evaluator (NIQE) score by 43.3\%. Edge deployment with RKNN conversion and INT8 quantization achieves an average inference latency of approximately 200 ms per $512\times512$ image over 360 test images. These results demonstrate that PP-Net provides an effective and deployable solution for microscopic imaging, endoscopic inspection, and edge-assisted biomedical analysis in IoMT scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26474
PDF
-
How to Estimate Whether You Have Found Several Needles in a Haystack: Measuring Calibration in Multi-Label Text Classification
2026-09-22 14:15:54Sophie Henning, Georg Hofmann, Alexander Schulte, Alexander Fraser, Annemarie FriedrichAbstract
A key factor in deciding whether to trust an automatic prediction is its confidence score, which should be calibrated to match the actual probability of the prediction being correct. Most confidence calibration metrics target binary or multi-class tasks, while multi-label calibration remains largely underexplored. Multi-label classification tasks, such as assigning medical codes to clinical notes or determining news topics, are usually dominated by a large number of negatives, i.e., labels that do not apply. We show that existing binning schemes to compute label-wise expected calibration error either underestimate the error, simply reflect label frequency, or suffer from many bins with very few instances. To achieve trustworthy label-wise calibration errors, we propose a new binning scheme that gives equal weight to positive and negative label assignments. Our empirical study demonstrates that in contrast to existing binning schemes, our new scheme results in meaningful estimates of calibration error in hierarchical and in extreme multi-label classification. We also show that calibrating confidence scores of large language models for multi-label predictions is an open challenge. Our detailed analysis lays the foundation for further research by providing a solid evaluation metric for measuring calibration in multi-label classification.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26468
PDF
-
Shaft-Configuration-Adaptive Catheter Tip Position Estimation via Motor-History Conditioned Residual Learning
2026-09-22 12:12:54Peihan Zhang, Michael C. Yip, Ankur Kapoor, Young-Ho KimAbstract
Tendon-driven continuum manipulators are widely used in medical applications, where accurate tip-position estimation is essential for precise navigation and instrument positioning. However, patient anatomy and procedural setup impose task-dependent unknown shaft configurations, while friction, slack, and compliance introduce hysteresis, making tip estimation challenging. This paper presents a motor-history-conditioned gated recurrent unit (GRU) residual estimator for three-dimensional catheter tip estimation without direct shaft-configuration sensing. First, an initial multidirectional sweep strategy is applied to calibrate a geometric catheter model backbone, and encode the motor-angle and drive-torque response into a shaft-configuration context vector. During subsequent motion, the context conditions a GRU that predicts a task-space residual correcting this backbone, relying on motor measurements alone. The context remains fixed for the current shaft configuration, while the recurrent state captures the evolving actuation history. Across four disposable intra-cardiac echocardiography catheters and 16 bent shaft configurations, the method achieves 3.3mm open-loop tip RMSE, a 59% reduction relative to the constant-curvature baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26304
PDF
-
Faithful Faithfulness Evaluations: Challenges & Pitfalls Learned from a Breast MRI Case Study
2026-09-22 10:34:51Peachapong Poolpol, Henrik H. J. Detjen, Eike PetersenAbstract
Saliency maps are widely used to explain deep learning predictions in medical imaging, yet visually plausible explanations do not necessarily reflect a model's true decision process and may therefore mislead clinicians. We investigate this problem using a Vision Transformer-based breast MRI classifier trained on the ODELIA Breast MRI Challenge dataset and evaluate multiple saliency methods, including Last-layer Attention, Attention Rollout, Grad-SAM, Gradient Attention Rollout, GMAR, Grad-CAM, and HiResCAM. Our study highlights two often-overlooked challenges in perturbation-based faithfulness evaluation. First, method rankings depend strongly on the perturbation strategy, varying across intensity-based perturbations and transformer-based attention masking. Second, benchmarking saliency methods requires distinguishing between class-specific and class-agnostic explanations. To enable fair comparisons, we introduce non-class-specific variants of gradient-based methods and evaluate both settings separately. Across protocols, Grad-CAM and Gradient Attention Rollout consistently emerged as the strongest class-specific methods, although their relative ranking depended on the evaluation design. These findings expose important limitations of current saliency-based explainability approaches and highlight the need for more robust and standardized evaluation frameworks for trustworthy clinical AI systems.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25978
PDF
-
BELXTR: Biomedical Entity Linking via Contextualized Token Retrieval
2026-09-22 08:23:54Samuele Garda, Ulf LeserAbstract
Biomedical Entity Linking disambiguates mentions to entities in a knowledge base (KB), making it the cornerstone of information extraction pipelines. While embedding-based models are a popular approach for the task, they suffer from a key limitation. They compress mentions (and entities) into a single vector, forcing the model to average away crucial fine-grained differences. We present BELXTR, a novel embedding model based on the multi-vector (a.k.a. late interaction) architecture, which allows to leverage token-level matching information. BELXTR extends the original XTR model to biomedical entity linking by integrating an existing task-specific training objective and exploring active query expansion. Experiments across ten corpora and five KBs show that BELXTR improves upon current state-of-the-art in half of the corpora with an average improvement of 5pp recall@1. The largest gains are reported on the challenging cross-species gene disambiguation subtask, where BELXTR outperforms an LLM-powered retrieve-and-rerank pipeline and closely approaches a specialized rule-based system. Our results highlight multi-vector models as a practical alternative to hard-to-maintain rule-based systems or in scenarios where LLM-based reranking is too costly as in PubMed-scale mining. The code to reproduce our experiments can be found at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25859
PDF
-
Less Is More in the Long Tail: Stage-Adaptive Sample Selection for Annotation-Efficient Dense Prediction
2026-09-22 08:16:11Xiaofei Du, Lei Zhang, Shuyu Yan, Manning Wang, Zhijian SongAbstract
Deep learning performance generally improves with increasing training data, yet this scaling is fundamentally constrained by annotation cost in large-scale dense prediction tasks with long-tailed category distributions, where pixel- or voxel-level annotation is prohibitively expensive. We propose SASS (Stage-Adaptive Sample Selection), a stage-adaptive data-selection framework for pool-based active learning in long-tailed dense prediction. SASS combines three components: label-free self-supervised gradient scoring, prior-guided category rebalancing with validation-driven feedback, and stage-adaptive acquisition aligned with model training dynamics. This design avoids candidate ground-truth masks during gradient scoring while making acquisition responsive to long-tail imbalance and evolving representations. We evaluate SASS on a multimodal 3D medical segmentation testbed comprising over 100,000 samples spanning 108 anatomical structures. SASS recovers 98.3% of full-dataset performance with a 40% training-pool annotation budget, outperforming BADGE by 5.1 percentage points. Moreover, SASS exhibits a statistically supported less-is-more pattern, surpassing full-dataset training at the Hard-group level and, at the structure level, for the pancreas and gallbladder. More broadly, SASS shows that annotation-efficient learning depends not only on which samples are selected, but also on how the annotation budget is distributed across categories and when model-derived scores begin to guide selection.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25850
PDF
-
MedVLA: A Hierarchical Vision-Language-Action Framework for Closed-Loop Precision Medical Robot Manipulation
2026-09-22 06:50:10Junjie Xie, Chuxuan He, Angen Ye, Yujia Song, Dapeng ZhangAbstract
Precision medical robotics demands adaptive decision-making under strict safety, interpretability, and execution constraints. Although recent Vision-Language-Action (VLA) models show strong multimodal reasoning ability, their continuous action generation paradigm is not well suited for precision medical tasks, where reliable closed-loop operation may also depend on non-action system function calls. To address this gap, we propose MedVLA, a hierarchical framework that couples high-level multimodal reasoning with low-level function-constrained execution. We further introduce a scalable multi-agent pipeline to generate skill-oriented chain-of-thought(CoT) data for structured training. Built on different multimodal large-model backbones, MedVLA consistently improves performance after fine-tuning, demonstrating the effectiveness of the proposed framework across model variants. Under identical initial conditions, we perform 100 closed-loop flexible electrode implantation trials. The results show that MedVLA achieves a 95.0\% task success rate, substantially outperforming representative VLA baselines, including OpenVLA (8\%) and $\pi_0$ (15\%), in accuracy, stability, and safety. These results indicate that structured reasoning with constrained function-level execution is a practical route toward deployable precision medical robotics.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25756
PDF
-
SAMI3D-DW: Interactive Segmentation of Any 3D Medical Images
2026-09-22 06:25:11Ping Gong, Shiyuan Su, Fandong Zhang, Xinchen Han, Haowei Sun, Yiming Li, Yizhou YuAbstract
Interactive segmentation of 3D medical images supports quantitative analysis of anatomical structures and disease while allowing users to specify and refine their targets. Despite substantial progress by nnInteractive and VISTA3D, reliable segmentation across diverse clinical targets remains challenging, particularly for complex anatomical structures and the heterogeneous, long-tailed spectrum of pathology. We present SAMI3D-DW V1 (hereafter SAMI3D-DW), an interactive 3D segmentation model trained on Deepwise's large-scale proprietary medical image datasets. We evaluate the model under simulated user interactions on a CT/MR benchmark comprising 4,326 cases from 219 source datasets, spanning 107 anatomical and pathological categories, organized by a medical taxonomy and evaluated with a category-balanced DSC score. SAMI3D-DW achieves the highest category-macro Dice among evaluated methods in both interaction modes. With one point, it scores 0.5764 versus 0.5315 for nnInteractive, the strongest baseline, rising to 0.7771 versus 0.7494 with five points. With bounding-box initialization, the scores are 0.7130 versus 0.6530. After five corrective clicks, SAMI3D-DW reaches 0.8002 versus 0.7868, making it the only evaluated box-compatible model to exceed 0.80. For radiologists and clinicians, SAMI3D-DW enables segmentation of complex anatomical structures, including intracranial vessel trees on CT and MR angiography, with a few clicks. In a preliminary in-house comparison involving neurofibromatosis type 1 (NF1), SAMI3D-DW-assisted tumor annotation took minutes per case and approximately one-fifteenth of the time required for manual annotation, highlighting its potential to support volumetric treatment-response assessment.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25743
PDF
-
Decoupling Disease, Covariates, and Individual Variability: A Unified Disentanglement Framework for Medical Image Classification
2026-09-22 04:02:00Shengjie Zhang, Jinglin Zhang, Zhuangzhuang Jiang, Ziqi Yu, Yipin Zhang, Qi Zhang, Xiang Chen, Haibo Yang, Fei Gao, Longbiao Cui, Yuan Zhou, Xiao-Yong Zhang, Alzheimer's Disease Neuroimaging InitiativeAbstract
Accurately isolating disease-related features from confounding covariates (e.g., age, gender, site) and individual variations remains a fundamental challenge in medical image classification. Traditional regression-based approaches may ignore non-linear relations between image features and true covariates. To overcome this issue, we present a generalized Medical Imaging Disentanglement Learning (MedIDL) framework. MedIDL maps image features into three mutually orthogonal latent spaces through specialized disentanglement heads: a disease classification head guided by a supervised loss, a covariate-alignment head constrained by cross-subject similarity matching, and a Gaussian head absorbing individual variations. We evaluated our framework across 7 datasets encompassing diverse imaging modalities. MedIDL outperforms state-of-the-art supervised and self-supervised classification methods in accuracy across all datasets. Association analyses demonstrate that MedIDL successfully isolates target-specific latent representations. Gradient-based interpretability mappings localize pathognomonic patterns aligning with established clinical literature.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25650
PDF
