📊 Medical Imaging AI Weekly Papers

Segmentation · Generation · Detection · AI Agent · Registration · Dose Calculation
🕐 2026-08-20 08:11:24 (UTC+8)
📅 2026-08-20 📄 54 Papers 🤖 arXiv API + AI Summary
📚 Archive

🔬 Medical Image Segmentation

7条
Uncertainty estimation is critical for the safe clinical deployment of deep learning in medical image segmentation, with aleatoric uncertainty theoretically designed to capture irreducible data ambigu
👤 Simon Baur, Arne Schernich, Ekin Böke, Wojciech Samek et al. (5 authors) 📅 2026-08-14 🔗 arXiv 📄 PDF
Purpose: Deep learning-based medical image segmentation has achieved remarkable success, yet purely data-driven approaches often fail to exploit the rich mathematical structure inherent in medical ima
👤 Jing Zhu, Ye Wang, Fumin Wang 📅 2026-08-12 🔗 arXiv 📄 PDF
Recent 3D foundation models provide powerful feature representations for point cloud learning by controlling spatial granularity. However, relying on a fixed spatial granularity severely limits genera
👤 Carla Salazar, Lazaros Nalpantidis 📅 2026-08-18 🔗 arXiv 📄 PDF
Accurate 3D tooth segmentation forms the cornerstone of digital dentistry, yet it remains a formidable challenge due to the inherent intricacy of real-world dentitions, such as crowding, misaligned te
👤 Xianghan Wei, Jianwen Lou, Zhiguo Lu, Hairong Jin et al. (5 authors) 📅 2026-08-18 🔗 arXiv 📄 PDF
X-ray imaging can be approximately modeled as the projection of an underlying volumetric attenuation field, with each measurement recording the accumulated attenuation along a corresponding ray path.
👤 Yifei Wu, Yicheng Wu, Qiang Ma, Qi Chen et al. (8 authors) 📅 2026-08-18 🔗 arXiv 📄 PDF
Dense voxel-level annotation remains a major bottleneck in 3D medical image segmentation. Single-slice propagation methods such as Sli2Vol reduce this burden by propagating one annotated seed slice th
👤 Md Rakibul Haque, Tushar Kataria, Shireen Y. Elhabian 📅 2026-08-12 🔗 arXiv 📄 PDF
Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it last changed state, or why it was relocated remain d
👤 Ke Ma, Yamin Mao, Weiming Li, Shuai Tan et al. (8 authors) 📅 2026-08-11 🔗 arXiv 📄 PDF

🩺 Medical Image Detection & Diagnosis

28条
Despite the rapid progress of deep neural networks in visual recognition, their adoption in high-risk medical applications remains limited due to reliability and robustness concerns. Models may exploi
👤 Shenhav Nadir, Meir Yossef Levi, Eyal Gofer, Guy Gilboa 📅 2026-08-18 🔗 arXiv 📄 PDF
Deep snake is a promising family of instance segmentation methods that accurately predicts object-level contours, thereby overcoming common pixel-level misclassification issues such as mask cavities a
👤 Ruicheng Zhang, Jianhui Lei, Kaiwen Shen, Haowei Guo et al. (9 authors) 📅 2026-08-18 🔗 arXiv 📄 PDF
Corrupted, inconsistent, or anomalous data silently threatens the safety and reliability of medical AI. Despite growing regulatory recognition of dataset quality assurance (QA) for high-risk medical A
👤 Chiara Tappermann, Steffen Renisch, Lars Ole Schwen, Hans Meine et al. (6 authors) 📅 2026-08-17 🔗 arXiv 📄 PDF
Instance-level lesion detection has been an increasingly larger focal point in medical image segmentation besides the more standard voxel-level overlap. Still, most pipelines are trained and post-proc
👤 Qinghui Liu, Jon André Ottesen, Atle Bjørnerud, Kyrre Eeg Emblem 📅 2026-08-17 🔗 arXiv 📄 PDF
Medical foundation models improve generalization when training AI models with limited labeled data, but remain confined to a single specialty, such as pathology or radiology, and to either sparse or d
👤 J. Raphael Schäfer, Kai Geissler, Till Nicke, Chiara Tappermann et al. (30 authors) 📅 2026-08-17 🔗 arXiv 📄 PDF
Scintillators are indispensable for the detection of X-rays, $γ$-rays, and energetic particles in applications ranging from medical imaging and security screening to high-energy physics. A major limit
👤 Priyankar Pandey, Subrahmanyam Mantha, Harish N S Krishnamoorthy 📅 2026-08-17 🔗 arXiv 📄 PDF
Rapid point-of-care diagnostics that operate directly on whole blood can accelerate clinical decision-making by bypassing complex sample preprocessing and centralized laboratory infrastructure. Howeve
👤 Mihye Lee, Rajesh Ghosh, Artem Goncharov, Rui-Chian Tang et al. (13 authors) 📅 2026-08-15 🔗 arXiv 📄 PDF
Prostate cancer claims a life every 80 seconds. Early detection is needed to prevent disease progression, and both PSA density calculation and biopsy decisions rely on knowing the exact boundary of th
👤 Ayusha Abbas, Saram Abbas, Kabita Adhikari 📅 2026-08-14 🔗 arXiv 📄 PDF
Whole Slide Image (WSI) analysis has been widely studied for cancer diagnosis. Conventionally, a gigapixel WSI is divided into small patches and processed by Multiple Instance Learning (MIL) models. H
👤 Quoc Anh Nguyen, Sunhong Park, Jin Tae Kwak 📅 2026-08-14 🔗 arXiv 📄 PDF
Peripheral nerves buried beneath intact tissue are difficult to visualize during surgery and remain inaccessible to white light wide-field imaging and other surface optical imaging methods. Existing O
👤 Yihan Wang, Ruilin You, Shaobai Li, Jiabin Chen et al. (7 authors) 📅 2026-08-13 🔗 arXiv 📄 PDF
Vision-language models, such as contrastive language-image pre-training (CLIP)-based approaches, have reached state-of-the-art (SOTA) results in medical artificial intelligence. However, recent work r
👤 Nikolette Pedersen, Regitze Sydendal, Veronika Cheplygina, Théo Sourget 📅 2026-08-12 🔗 arXiv 📄 PDF
We present a novel causal approach to interpretability for computer vision models that dynamically masks the input image prior to classification. The interpretability of deep learning predictions is c
👤 Benjamin Formby, Kuang-Ching Wang, D Hudson Smith 📅 2026-08-12 🔗 arXiv 📄 PDF
Zero-shot anomaly detection (ZSAD) aims to identify anomalies in unseen domains, a setting that is particularly critical for industrial and medical applications where domain shifts are prevalent. Howe
👤 Jimin Roh, DongKyu Kim, Suk-Ju Kang 📅 2026-08-12 🔗 arXiv 📄 PDF
Alzheimer's disease is a leading cause of death with no cure. Therefore, early detection is critical to slow progression and preserve quality of life. Diagnosis relies on medical history, cognitive te
👤 Hiram Zuniga, Ulises Orozco-Rosas, Kenia Picos 📅 2026-08-12 🔗 arXiv 📄 PDF
Retinal diseases are a leading cause of irreversible vision impairment, making early and accurate diagnosis essential for effective treatment. Optical Coherence Tomography (OCT) serves as a critical i
👤 Cheng Cheng, Jin Hong 📅 2026-08-18 🔗 arXiv 📄 PDF
Intra-tumoural heterogeneity (ITH) reflects spatial variation in tumour biology and is an important determinant of tumour behaviour, prognosis, and treatment response. Radiomics and deep learning have
👤 Yue Xia, Euijoon Ahn, Tian Xia, Yuan Yuan et al. (6 authors) 📅 2026-08-18 🔗 arXiv 📄 PDF
Reliable endoscopic polyp reporting requires integrating quantitative lesion sizing, standardized Paris classification, and clinically meaningful morphological description within a single record. Gene
👤 Ruijie Yang, Yan Zhu, Peiyao Fu, Siyuan Li et al. (10 authors) 📅 2026-08-16 🔗 arXiv 📄 PDF
Hepatocellular carcinoma (HCC) is the third leading cause of cancer-related mortality worldwide, with early detection improving survival from <20\% to >70\%. The standardized LI-RADS criteria establis
👤 Pranav Kulkarni, Nikhil Shah, Amritansh Suryavanshi, Jana Delfino et al. (12 authors) 📅 2026-08-14 🔗 arXiv 📄 PDF
Positron emission tomography (PET) imaging suffers from limited spatial resolution and low signal-to-noise ratio, which can compromise quantitative accuracy and lesion detectability. Deep learning-bas
👤 Boxiao Yu, Savas Ozdemir, Yang Xing, Fumio Hashimoto et al. (11 authors) 📅 2026-08-13 🔗 arXiv 📄 PDF
Computer-aided detection (CADe) systems for colonoscopy promise to reduce clinical miss rates, yet reliable real-world deployment remains elusive. This translational gap stems in part from a structura
👤 Sebastian Doerrich, Andreas Franz Schwab, Francesco Di Salvo, Shyam Nandan Rai et al. (6 authors) 📅 2026-08-13 🔗 arXiv 📄 PDF
Deep networks segment brain tumours accurately in-distribution, but can fail silently when the input differs from their training data. That risk is central to clinical deployment and is the premise of
👤 Riya Deepak Shet, Le Zhang 📅 2026-08-13 🔗 arXiv 📄 PDF
Thyroid ultrasound diagnosis requires coordinated lesion localization, measurement, risk stratification and reporting, yet most AI systems address these tasks in isolation and provide limited support
👤 Haifan Gong, Shiyu Chen, Bodong Wang, Yuqi Wang et al. (14 authors) 📅 2026-08-12 🔗 arXiv 📄 PDF
Automated lesion segmentation in whole-body PET/CT imaging can assist clinicians with cancer detection, staging, and treatment planning across radiotracers and cancer types. However, training lesion s
👤 Biratal Raj Wagle, Bashirul Azam Biswas, Grant Chau, Matthew E. Maeder et al. (8 authors) 📅 2026-08-11 🔗 arXiv 📄 PDF
A key issue in using AI for pathology diagnosis is what image information should be given to the AI and how limited analysis resources should be used. This study compares two ways of processing differ
👤 Tatsuaki Tsuruyama 📅 2026-08-11 🔗 arXiv 📄 PDF
Skin cancer diagnosis from dermoscopic images remains challenging due to high intra-class variability, inter-class similarity, class imbalance, and the limited interpretability of deep learning models
👤 Rofiqul Islam, Lilatul Ferdouse 📅 2026-08-11 🔗 arXiv 📄 PDF
Colorectal cancer (CRC) remains one of the leading causes of cancer-related mortality worldwide, predominantly arising from precancerous polyps. Accurate detection, segmentation, and endoscopic and hi
👤 Hamidreza Bolhasani, Hamidreza Rastad, Amir Mohammad Akbari, Mohammad Tashakoripour et al. (7 authors) 📅 2026-08-11 🔗 arXiv 📄 PDF
Breast lesion detection in mammography remains a challenging task due to variations in image quality, lesion appearance, and population demographics across datasets. While current object detectors suc
👤 Dinh Tan Nguyen, Hoang Quan Dang, Chen Zhang, Sai Ho Ling 📅 2026-08-11 🔗 arXiv 📄 PDF
Hyperparameter optimization (HPO) can materially affect the performance of deep learning (DL) image classifiers, but there is little empirical guidance on how to derive the validation signal that driv
👤 Ljubomir Buturovic 📅 2026-08-10 🔗 arXiv 📄 PDF

🤖 Medical AI Agent & VLM

17条
Medical vision-language models (Med-VLMs) have demonstrated strong performance on medical visual question answering, yet they remain prone to hallucination, generating clinically unsupported statement
👤 Yifan Lu, Adinath Dukre, Abhijit Das, Ziyun Zou et al. (7 authors) 📅 2026-08-18 🔗 arXiv 📄 PDF
Long-horizon agents are beginning to automate complete workflows that produce code, reports, and research artifacts. Medical imaging workflows are multi-stage and data-sensitive, while expert trajecto
👤 Junqi Liu, Yufan He, Yexiao He, Pengfei Guo et al. (12 authors) 📅 2026-08-17 🔗 arXiv 📄 PDF
Neural networks for seismic fault segmentation are often borrowed from computer vision and medical imaging domains where they train under relatively much larger labeled data resources. Optimizing thei
👤 Shehram Baig, Ahmad Mustafa 📅 2026-08-14 🔗 arXiv 📄 PDF
Medical image segmentation is still largely treated as a vision-only problem, although clinical interpretation often relies on textual knowledge of anatomy, location, appearance, and surrounding conte
👤 Rafi Ibn Sultan, Hui Zhu, Chengyin Li, Dongxiao Zhu 📅 2026-08-13 🔗 arXiv 📄 PDF
We introduce a Polish-language medical visual question answering (VQA) benchmark, built from Polish Board Certification Examination questions for licensed physicians and dentists pursuing specialist c
👤 Jakub Pokrywka, Łukasz Grzybowski, Antoni Lasik, Marek Kubis et al. (6 authors) 📅 2026-08-13 🔗 arXiv 📄 PDF
In medical imaging, the clinical value of Computed Tomography (CT) lies not only in depicting current disease status, but crucially in enabling longitudinal comparison of serial scans to determine dis
👤 Kegeng Tang, Jingbo Wang, Shaogang Ren, Zihao Wang 📅 2026-08-12 🔗 arXiv 📄 PDF
Medical visual agents can use tools to inspect images and retrieve external knowledge, but indiscriminate tool use may introduce noisy or misleading evidence. Reliable diagnosis therefore requires not
👤 Shengzhi Wang, Jun Yang, Kai Wu, Xiaozhong Ji et al. (14 authors) 📅 2026-08-11 🔗 arXiv 📄 PDF
While vision-language models dominate medical representation learning, unstructured text lacks the dense, quantitative diagnostic phenotypes inherent in structured clinical tables. However, existing m
👤 Yingsheng Liu, Haiming Li, Jingmin Zhu, Jiajun Sun et al. (9 authors) 📅 2026-08-11 🔗 arXiv 📄 PDF
Reliable medical image understanding requires models to connect clinical language and visual reasoning with pixel-level grounding. Yet medical vision-language models often lack precise localization, w
👤 Haoyu Yang, Meixing Shi, Zengjie Chen, Haoran Sun et al. (8 authors) 📅 2026-08-10 🔗 arXiv 📄 PDF
Purpose: To develop and evaluate a locally deployed multi-agent AI system for radiology report structuring and quality assurance. Materials and Methods: This retrospective study included 638 radiology
👤 Iryna Hartsock, Cesar Lam, Christopher Otteni, Aliya Qayyum et al. (7 authors) 📅 2026-08-18 🔗 arXiv 📄 PDF
Radiology report generation has matured almost entirely on 2D chest radiographs, where the default route to better reports is a larger backbone or a pre-training one on medical data. We revisit that a
👤 Jianyu Sun, Zhenxuan Zhang, Guang Yang, Peter J. Lally 📅 2026-08-18 🔗 arXiv 📄 PDF
A radiologist reading a model's output faces two problems. The model returns a number and no reason, and any system that turns that number into readable prose can quietly add claims the model never ma
👤 Vignesh Nagarajan, Sriram Venkatapathy 📅 2026-08-17 🔗 arXiv 📄 PDF
Radiology reports describe findings and locations in free text, but downstream search and analysis require these relations in a fixed schema. Learning this extraction requires labels that are unevenly
👤 Flint Xiaofeng Fan, Cheston Tan, Yew-Soon Ong, Roger Wattenhofer 📅 2026-08-17 🔗 arXiv 📄 PDF
Scheduling follow-up Computed Tomography (CT) examinations requires balancing two competing objectives: assigning patients as close as possible to their recommended examination dates while ensuring an
👤 Ludovico Ambrosi, Chandra Bortolotto, Sara Cambiaghi, Luisa Carone et al. (6 authors) 📅 2026-08-13 🔗 arXiv 📄 PDF
Pulmonary nodule malignancy prediction typically depends on image-trained specialist deep learning (DL) models that require substantial annotated imaging data and task-specific training. We investigat
👤 Md Rabiul Islam, Samir Abdaljalil, Erchin Serpedin, Hasan Kurban 📅 2026-08-11 🔗 arXiv 📄 PDF
Automated radiology report generation is advancing rapidly in response to the shortage of radiologists, yet unlike a perception model, existing generation models offer no control over the sensitivity-
👤 Ying Jin, Noel C. F. Codella, John Corring, Mu Wei et al. (6 authors) 📅 2026-08-11 🔗 arXiv 📄 PDF
Public chest X-ray repositories are widely used to train medical AI systems, yet their labels are typically extracted from radiology reports rather than verified directly on images. As a result, repos
👤 Yesika Alexandra Agudelo-Londoño, Jhon Wilmer Pino-Román, Brahian Carrera Rodríguez, José Miguel Castañeda-Bedoya et al. (12 authors) 📅 2026-08-10 🔗 arXiv 📄 PDF

🔄 Medical Image Registration

2条
Deformable image registration models implicitly encode deformation priors through their parametrization and optimization. In this work, we conduct a validation study on continuous registration methods
👤 Hengjie Liu, Chushu Shen, Dan Ruan, Ke Sheng 📅 2026-08-17 🔗 arXiv 📄 PDF
Anatomical image registration commonly relies on a sequential pipeline where an affine alignment is estimated first and then held fixed while a non-rigid diffeomorphic deformation is applied. This two
👤 Anton François, Rayane Mouhli, Thomas Pierron 📅 2026-08-11 🔗 arXiv 📄 PDF