IEEE transactions on medical imaging最新文献

{"title":"PARDA: A Perceive-Act-Reflect-Distill Agent for Source-Free Unsupervised Domain Adaptation.","authors":"Yulong Shi, Shijie Li, Ziyi Li, Lin Qi, Shouliang Qi, Ting Liu, Wei Qian","doi":"10.1109/TMI.2026.3744091","DOIUrl":"10.1109/TMI.2026.3744091","url":null,"abstract":"<p><p>Source-Free Unsupervised Domain Adaptation (SFUDA) has emerged as a critical paradigm for addressing severe domain shifts in medical image segmentation under strict data privacy constraints, where source data are inaccessible. However, existing SFUDA methods primarily rely on static, open-loop adaptation pipelines, lacking the ability to actively perceive target domain characteristics and use reflection to correct accumulated errors. Meanwhile, Vision Foundation Models (VFMs) and Vision Language Models (VLMs) exhibit strong generalization across modalities and anatomies, yet their high computational inference overhead and deployment constraints prevent direct adoption on clinical edge devices. In this work, we propose PARDA, a VLM-coupled closed-loop SFUDA framework for medical image segmentation. PARDA reformulates SFUDA as a closed-loop decision-making process, in which the method actively perceives target domain characteristics, acts by coordinating semantic and geometric VFMs to generate pseudo-labels, reflects on the reliability of its anatomical and structural representations to guide refinement, and finally distills the acquired adaptation knowledge into a lightweight student model. This design enables PARDA to mitigate error accumulation while preserving data privacy and inference efficiency. We conduct a comprehensive SFUDA evaluation covering 13 cross-modality domain adaptation directions and 24 anatomical targets across diverse organs and imaging modalities. Experimental results demonstrate that PARDA achieves robust and universal domain adaptation while distilling the adaptation results into a lightweight student model for resource-constrained inference.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149225607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Noise2Match: Self-Supervised Low-Dose CT Denoising via Adaptive Inter-Slice Matching.","authors":"Langrui Zhou, Guang Li, Xinyu Huang, Ziteng Zhou, Zuyang Huang, Hongming Shan, Shouhua Luo, Ning Gu","doi":"10.1109/TMI.2026.3744092","DOIUrl":"10.1109/TMI.2026.3744092","url":null,"abstract":"<p><p>With the rapid development of deep learning, supervised convolutional neural network methods have greatly improved the performance of low-dose computed tomography (CT) denoising. However, they require paired noisy-clean training data, which is difficult to obtain in practice. Some classic self-supervised denoising methods rely on the assumption of pixel-wise independent noise, making them ineffective for correlated noise in low-dose CT (LDCT) images. Considering the high similarity and weaker noise correlation between adjacent CT slices, several recently proposed self-supervised methods use adjacent LDCT slices for training. Nevertheless, these approaches fail to effectively account for the non-rigid mis-alignment between slices caused by anatomical variation, hindering them from satisfying the equal-mean condition required by the classic Noise2Noise framework. In this paper, we propose Noise2Match, a self-supervised LDCT denoising method based on adaptive inter-slice matching. Noise2Match introduces an inter-slice matching network to model the label transition process between adjacent slices, and then applies correction to the denoiser's outputs to better satisfy the equal-mean condition. We theoretically prove that, under idealized conditions, training Noise2Match using adjacent LDCT slices is equivalent to supervised training with paired noisy-clean images. We further find that Noise2Match can also effectively perform low-dose cone-beam CT (CBCT) denoising, which could be attributed to its correction operation that reduces inter-slice noise correlation. To the best of our knowledge, Noise2Match is the first effective image-domain self-supervised method for low-dose CBCT. Extensive experiments demonstrate that Noise2Match outperforms existing image-domain self-supervised methods, offering broader applicability and higher practical value.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149208370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Latent Interpolation Learning Using Diffusion Models for Cardiac Volume Reconstruction.","authors":"Niklas Bubeck, Suprosanna Shit, Chen Chen, Can Zhao, Pengfei Guo, Dong Yang, Georg Zitzlsberger, Daguang Xu, Bernhard Kainz, Daniel Rueckert, Jiazhen Pan","doi":"10.1109/TMI.2026.3743631","DOIUrl":"https://doi.org/10.1109/TMI.2026.3743631","url":null,"abstract":"<p><p>Cardiac Magnetic Resonance (CMR) imaging is a critical tool for diagnosing and managing cardiovascular disease, yet its utility is often limited by the sparse acquisition of 2D short-axis slices, resulting in incomplete volumetric information. Accurate 3D reconstruction from these sparse slices is essential for comprehensive cardiac assessment, but existing methods face challenges, including reliance on predefined interpolation schemes (e.g., linear or spherical), computational inefficiency, and dependence on additional semantic inputs such as segmentation labels or motion data. To address these limitations, we propose a novel Cardiac Latent Interpolation Diffusion (CaLID) framework that introduces three key innovations. First, we present a data-driven interpolation scheme based on diffusion models, which can capture complex, non-linear relationships between sparse slices and improves reconstruction accuracy. Second, we design a computationally efficient method that operates in the latent space and speeds up generative 3D whole-heart upsampling time by a factor of 24, reducing computational overhead compared to previous methods. Third, with only sparse 2D CMR images as input, our method achieves SOTA performance against baseline methods, eliminating the need for auxiliary input such as morphological guidance, thus simplifying workflows. We further extend our method to 2D+T data, enabling the effective modeling of spatiotemporal dynamics and ensuring temporal coherence. Extensive volumetric evaluations and downstream segmentation tasks demonstrate that CaLID achieves superior reconstruction quality and efficiency. By addressing the fundamental limitations of existing approaches, our framework advances the state of the art for spatio and spatiotemporal whole-heart reconstruction, offering a robust and clinically practical solution for cardiovascular imaging. The code is available at https://github.com/niklasbubeck/calid.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149198656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TSMCA-Net: A Multi-Granular Cross-Attention Framework for Cross-Session EEG-fNIRS Decoding.","authors":"Tao Zheng, Yongtao Zhou, Muzi Xu, Jiaqi Zhang, Peizhe Zhao, Qiang Yang, Caizhi Liao","doi":"10.1109/TMI.2026.3743615","DOIUrl":"https://doi.org/10.1109/TMI.2026.3743615","url":null,"abstract":"<p><p>We propose TSMCA-Net, a lightweight cross-session EEG-fNIRS decoder that achieves state-of-the-art accuracy with <1M parameters-70.6% fewer than the strongest baseline-while maintaining sub-8ms inference latency. TSMCA-Net decomposes multimodal interactions into three complementary views-temporal-spatial (TS), temporal-modal (TM), and spatial-modal (SM)-through structured multi-view factorization that separates heterogeneous dependency axes while preserving cross-branch information sharing. A Dynamic Multi-Scale Context module adaptively aggregates spatial dependencies on a unified scalp topology, while a causal lag modeling strategy captures delayed hemodynamic responses under strict temporal causality. An asymmetric cross-attention mechanism then integrates the multi-granular representations for role-aware fusion. Under a leave-one-session-out protocol on two public datasets, TSMCA-Net achieves the highest mean accuracy across three cognitive paradigms (71.41% MI, 86.36% MA, 80.30% WG), outperforming all 12 baselines in absolute accuracy and achieving statistical significance in 31 of 36 pairwise comparisons (p<0.05). Perturbation experiments demonstrate 38%-62% smaller accuracy degradation under simulated spatial perturbations.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149198578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated \"Corruptions\"- An EndoVis'24 Challenge.","authors":"Hao Ding, Yuqian Zhang, Tuxun Lu, Ruixing Liang, Hongchao Shu, Lalithkumar Seenivasan, Yonghao Long, Qi Dou, Cong Gao, Yicheng Leng, Seok Bong Yoo, Eung-Joo Lee, Zijian Wu, Yuxin Chen, Septimiu E Salcudean, Samra Irshad, Shadi Albarqouni, Seong Tae Kim, Yueyi Sun, An Wang, Long Bai, Hongliang Ren, Ihsan Ullah, Ho-Gun Ha, Attaullah Khan, Hyunki Lee, Satoshi Kondo, Satoshi Kasai, Kousuke Hirasawa, Sita Tailor, Ricardo Sanchez-Matilla, Imanol Luengo, Tianhao Fu, Jun Ma, Bo Wang, Marcos Fernandez-Rodriguez, Estevao Lima, Joao L Vilaca, Negin Ghamsarian, Klaus Schoeffmann, Raphael Sznitman, Mathias Unberath","doi":"10.1109/TMI.2026.3742752","DOIUrl":"10.1109/TMI.2026.3742752","url":null,"abstract":"<p><p>Surgical data science has seen rapid ad vancement with the excellent performance of end-to-end deep neural networks (DNNs). Despite their successes, DNNs have been proven susceptible to minor \"corrup tions,\" substantially impairing the model's performance, introducing a major concern for the translation of cutting-edge technology, especially in high-stakes scenarios. We introduce the SegSTRONG-C challenge dedicated to better understanding model deterioration under unforeseen but plausible non-adversarial \"corruption\" and the capabilities of contemporary methods that seek to improve it. Built on a dataset generated through counterfactual robotic replay, SegSTRONG-C provides paired clean and \"corrupted\" samples, enabling reproducible evaluation of model robustness. Participants are challenged to train tool segmentation algorithms on \"uncorrupted\" data and evaluate them on \"corrupted\" test domains for the binary robot tool segmentation task. Through comprehensive baseline experiments and participating submissions from widespread community engagement, SegSTRONG-C reveals key themes for model failure and identifies promising directions for improving robustness. The performance of challenge winners, achieving an average 0.9394 DSC and 0.9301 NSD across the unreleased test sets with \"corruption\" types: bleeding, smoke, and low brightness. This highlights how prior knowledge, customized training strategies, and architectural choice can be leveraged to improve robustness. In conclusion, the SegSTRONG-C challenge has identified practical approaches for enhancing model robustness. However, most approaches rely on conventional techniques that have known limitations. Looking ahead, we advocate for expanding intellectual diversity and creativity in non-adversarial robustness beyond data augmentation, calling for new paradigms that enhance universal robustness to unforeseen \"corruptions\" to facilitate richer applications in surgical data science.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149187074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Style-Prior Enhanced-and-Selective Mamba with Class-Oriented Contrastive Learning for Posterior Subcapsular Cataract Grading.","authors":"Zunjie Xiao, Tianhang Liu, Xiao Wu, Yinglin Zhang, Lingxi Hu, Risa Higashita, Jiang Liu","doi":"10.1109/TMI.2026.3742811","DOIUrl":"https://doi.org/10.1109/TMI.2026.3742811","url":null,"abstract":"<p><p>Posterior subcapsular cataract (PSC) is a leading cause of blindness and vision impairment globally. Precise PSC grading is critical for immediate treatment and opacity progression observation. Recent studies have suggested the great potential of anterior segment optical coherence tomography (AS-OCT) images in objectively investigating the opacities of PSC compared to conventional slit-lamp examinations with clinical features such as average and maximum. However, the irregular morphology and diffuse distribution modeling of its opacities in AS-OCT images present two significant challenges for precise PSC grading, which have not been addressed previously. To address these challenges, we propose a novel Style-Prior Enhanced-and-Selective State Space Model (SPES-SSM), which effectively captures the irregular morphology and diffuse opacity distribution representations by leveraging the potential of SSM and multi-scale convolution concurrently; and then employs the well-designed style-prior enhanced-and-selective representation block to estimate the relative significances of these two representation types via useful clinical feature (e.g., average and maximum) prior exploration of PSC. By stacking SPES-SSM modules, we construct SPES-Mamba for automated PSC grading based on AS-OCT images. To enhance our SPES-Mamba's reliability and further improve its PSC grading results, we design a class-oriented contrastive learning (COCL), which explores the potential of the ranking matrix of label distance from the aspect of class-averaging. Extensive experiments demonstrate that SPES-Mamba and COCL significantly outperform state-of-the-art methods in terms of PSC grading results and reliability.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149187076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EyeGraph: A Multi-granularity Medical Vision-Language Foundation Model with Knowledge Graph Reasoning for Ophthalmic Interpretation.","authors":"Zhiyuan Cai, Yiwei Ren, Yixiang Liu, Jialin Li, Yijin Huang, Pujin Cheng, Li Lin, Danli Shi, Mingguang He, Hao Chen, Xiaoying Tang","doi":"10.1109/TMI.2026.3742614","DOIUrl":"https://doi.org/10.1109/TMI.2026.3742614","url":null,"abstract":"<p><p>The exponential growth of large vision-language models (VLMs) has created significant opportunities for advancing multimodal artificial intelligence in specialized domains such as ophthalmology. However, progress in ophthalmic VLMs remains limited, primarily due to the lack of large-scale, high-quality image-text pairs. Moreover, existing VLMs frequently generate hallucinations, leading to uncertainty and unreliability that are unacceptable in clinical practice. To address the data scarcity issue, we introduce IT-Retinal, a dedicated ophthalmic Vision Question Answering (VQA) dataset that providesmultigranularity tasks and high-quality long-form textual content in image-text pairs. To mitigate hallucinations, we propose EyeGraph, a framework for ophthalmic VLMs that consists of two training stages, targeted pre-training and fine-tuning, and one inference stage that integrates Graph of Thought (GoT) and Think on Graph (ToG) reasoning, referred to as G2T. This design enables EyeGraph to incorporate structured external knowledge, constrain the output space, and produce more clinically consistent results. Extensive experiments demonstrate that EyeGraph achieves state-of-the-art performance across seven clinically relevant benchmarks, spanning disease diagnosis, structural detection and localization, and report generation. Notably, the proposed G2T reasoning module consistently improves the factual consistency and reliability of ophthalmic report generation. All source code, along with an interactive demo, is publicly available at: https://github.com/ZardCAI/EyeGraph.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149187109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decoupling Multi-Contrast Super-Resolution: Self-Supervised Implicit Re-Representation for Unpaired Cross-Modal Synthesis.","authors":"Yinzhe Wu, Hongyu Rui, Fanwen Wang, Jiahao Huang, Zhenxuan Zhang, Haosen Zhang, Zi Wang, Guang Yang","doi":"10.1109/TMI.2026.3739662","DOIUrl":"10.1109/TMI.2026.3739662","url":null,"abstract":"<p><p>Multi-contrast super-resolution (MCSR) is crucial for enhancing MRI but current deep learning methods are limited. They typically require large, paired low- and high-resolution (LR/HR) training datasets, which are scarce, and are trained for fixed upsampling scales. While recent self-supervised methods remove the paired data requirement, they fail to leverage valuable population-level priors. In this work, we propose a novel, decoupled MCSR framework that resolves both limitations. We reformulate MCSR into two stages: (1) an unpaired cross-modal synthesis (uCMS) module, trained once on unpaired population data to learn a robust anatomical prior; and (2) a lightweight, patient-specific implicit re-representation (IrR) module. This IrR module is optimized in a self-supervised manner to fuse the population prior with the subject's own LR target data. This design uniquely fuses population-level knowledge with patient-specific fidelity without requiring paired target-domain LR/HR training data or paired cross-modal HR reference-target training data. Here, 'unpaired' refers to the population-level training setting; at subject-specific inference, as in standard MCSR, the method uses a matched HR reference image from another contrast together with the subject's LR target image. By building the IrR module on an implicit neural representation, our framework is also inherently scale-agnostic. Our method demonstrates superior quantitative performance on different datasets, with exceptional robustness at extreme scales (16×, 32×), a regime where competing methods fail. Our work presents a data-efficient, flexible, and computationally lightweight paradigm for MCSR, enabling high-fidelity, arbitrary-scale reconstruction without the need for paired population-level supervision.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149149308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretation","authors":"Jinhui Lou;Yan Yang;Zhou Yu;Zhenqi Fu;Weidong Han;Qingming Huang;Jun Yu","doi":"10.1109/TMI.2026.3713585","DOIUrl":"10.1109/TMI.2026.3713585","url":null,"abstract":"Chest X-ray (CXR) plays a pivotal role in clinical diagnosis, and a variety of task-specific and foundation models have been developed for CXR interpretation. However, these models often struggle to adapt to new diagnostic tasks and complex reasoning scenarios. Recently, LLM-based agents have emerged as a promising paradigm for CXR analysis, enhancing model’s capability via tool coordination, multi-step reasoning, and team collaboration, etc. However, existing agents often rely on a single diagnostic pipeline and lack mechanisms for assessing tools’ reliability, limiting their adaptability and credibility. To this end, we propose CXRAgent, a director-orchestrated, multi-stage agent for CXR interpretation, where a central director coordinates the following stages: 1) Tool Invocation: The agent strategically orchestrates a set of CXR-analysis tools, with outputs normalized and verified by the Evidence-driven Validator (EDV), grounding diagnostic outputs with visual evidence to support reliable downstream diagnosis; 2) Diagnostic Planning: Guided by task requirements and intermediate findings, the agent formulates a targeted diagnostic plan, assembles an expert team, defines member roles, and coordinates their interactions to enable adaptive collaborative reasoning; 3) Collaborative Decision-making: The agent integrates insights from the expert team with accumulated contextual memories, synthesizing them into an evidence-backed conclusion. Experiments on diverse tasks show that CXRAgent achieves strong performance with reliable visual grounding, attaining overall accuracies of 67.0% on CheXbench and 75.6% on Medical-CXR-VQA, and a RaTEScore of 0.569 on MIMIC-CXR for report generation. Code and data are available at this <uri>https://github.com/laojiahuo2003/CXRAgent/</uri>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"45 10","pages":"5014-5027"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148458262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diffusion-Based Quality Control of Medical Image Segmentations Across Organs","authors":"Vincenzo Marcianò;Hava Chaptoukaev;Virginia Fernandez;M. Jorge Cardoso;Michela Antonelli;Sébastien Ourselin;Maria A. Zuluaga","doi":"10.1109/TMI.2026.3714697","DOIUrl":"10.1109/TMI.2026.3714697","url":null,"abstract":"Medical image segmentation using deep learning (DL) has enabled the development of automated analysis pipelines for large-scale population studies. However, state-of-the-art DL methods are prone to hallucinations, which can result in anatomically implausible segmentations. With manual correction impractical at scale, automated quality control (QC) techniques have to address the challenge. While promising, existing QC methods are organ-specific, limiting their generalizability and usability beyond their original intended task. To overcome this limitation, we propose <italic>no-new Quality Control (nnQC)</i>, a robust QC framework based on a diffusion-generative paradigm that self-adapts to any input organ dataset. Central to nnQC is a novel <italic>Team of Experts (ToE)</i> architecture, where two specialized <italic>experts</i> independently encode 3D spatial awareness, represented by the relative spatial position of an axial slice, and anatomical information derived from visual features from the original image. A weighted conditional module dynamically combines the pair of independent embeddings, or <italic>opinions</i> to condition the sampling mechanism within a diffusion process, enabling the generation of a spatially aware pseudo-ground truth for predicting QC scores. Within its framework, nnQC integrates <italic>fingerprint</i> adaptation to ensure adaptability across organs, datasets, and imaging modalities. We evaluated nnQC on seven organs using fifteen publicly available datasets. Our results demonstrate that nnQC consistently outperforms state-of-the-art methods across all experiments, including cases where segmentation masks are highly degraded or completely missing, confirming its versatility and effectiveness across different organs.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"45 10","pages":"5072-5083"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148474893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}