ConPro introduces a self‑supervised pretraining method for vessel segmentation in digital subtraction angiography (DSA) by using a contrast projection target— the normalized drop of each pixel below its temporal median. On the DIAS and DSCA datasets, ConPro outperforms training from scratch across 10%, 20%, and 50% labeled data, and it is the best among compared methods on DSCA at 20% and 50% labels. When combined with semi‑supervised training, ConPro‑derived weights boost the UniMatch baseline by 0.5–2.0 Dice points and 0.9–2.3 clDice points, achieving 75.4 Dice on DIAS and 81.3 on DSCA.
By Xinge Guo, Yuanhao Wang, Liqi Shu, Yang Liu, Min Xu
The paper introduces VasoMIM, a vascular anatomy‑aware masked image modeling framework for X‑ray angiogram analysis, which uses an anatomy‑guided masking strategy and an anatomical consistency loss to learn robust vascular representations. It also presents XA‑170K, the largest pre‑training dataset for X‑ray angiograms. Experiments on six datasets and four downstream tasks show that VasoMIM outperforms existing methods and achieves state‑of‑the‑art performance.
By De-Xing Huang, Chaohui Yu, Xiao-Hu Zhou, Tian-Yu Xiang, Qin-Yi Zhang, Mei-Jiang Gui, Rui-Ze Ma, Chen-Yu Wang, Nu-Fang Xiao, Fan Wang, Zeng-Guang Hou
arXiv:2608.31073v1 Announce Type: new
Abstract: Whole-heart segmentation (WHS) in computed tomography (CT) and magnetic resonance imaging (MRI) is affected by acquisition shifts and heterogeneous car...
By Jiacheng Wang, Ivana Isgum, Ipek Oguz
Med-AR introduces two autoregressive vision‑language models, Med‑AR‑8B and Med‑AR‑2B, pretrained on structured radiology reports, abnormality‑focused text, and region annotations to address long‑tailed chest X‑ray classification. The models outperform existing contrastive, self‑supervised, and supervised encoders—including Med‑CLIP, CheXFound, EVA‑Base, ARK, and BioViL‑T—across PadChest, MIMIC‑CXR, and CheXpert, achieving higher mean AUROC and AUPRC for head, medium, and tail findings and lower excess area under the risk‑coverage curve. Med‑AR also demonstrates improved selective‑prediction performance, with Med‑AR‑8B raising tail‑label mean AUPRC on MIMIC‑CXR from 0.1033 to 0.1441 and Med‑AR‑2B delivering the strongest discrimination on PadChest.
By Janhavi Prabhu, Sahil, Akshay V, Shivam Shukla, Manoj Tadepalli, Preetham Putha
arXiv:2610.32730v1 Announce Type: new
Abstract: Coronary artery disease remains a leading cause of mortality, with stenosis detection from invasive X-ray Coronary Angiography (XCA) critical for diagn...
By Haobo Zhu, Mojtaba Lashgari, Jason Chai, Giovanni Luigi De Maria, Vicente Grau, Abhirup Banerjee
L2GSSL is a self‑supervised learning framework designed for volumetric healthcare data, particularly CT scans. It decomposes pretraining into intra‑slice and inter‑slice representation spaces, using a slice encoder for local, view‑invariant features and a global encoder to aggregate tokens for volumetric context. On the LIDC‑IDRI lung nodule malignancy classification task, L2GSSL achieves high AUROC scores with only 10–25% of labels, outperforming other self‑supervised baselines and approaching the performance of fully supervised models.
By Po-Cheng Cheng, Hung-Hsuan Chen
arXiv:2608. 12086v1 Announce Type: cross Abstract: 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.
By Nikolette Pedersen, Regitze Sydendal, Veronika Cheplygina, Th\'eo Sourget
arXiv:2607. 11287v1 Announce Type: cross Abstract: Comprehensive quantification of cardiac structures from computed tomography (CT) remains limited not by data availability but by the scalability of measurements, which makes routine use impractical.
By Pooya Mohammadi Kazaj, Leo Fridolin Weber, Wen Xie, Seyed Amir Ahmad Safavi-Naini, Anselm Stark, Giovanni Baj, Ali Mokhtari, Toshiya Yoshida, Christoph Ryffel, Taishi Okuno, Yoshihiro Akashi, Ronny R. Buechel, Thomas Pilgrim, Waldo Valenzuela, George C. M. Siontis, Xiaowei Xu, Moritz Hundertmark, Stephan Windecker, Christoph Grani, Isaac Shiri
arXiv:2607. 22139v1 Announce Type: cross Abstract: Accurate pixel-level classification of coronary angiograms is critical for cardiovascular disease assessment, yet the field lacks standardized evaluation protocols.
By Dominik Bernard Lau, Hubert Malinowski, Jerzy Szyjut, Adam Brzeski, Tomasz Dziubich, Rados{\l}aw Targo\'nski, Tomasz Figatowski, Natalia Zieli\'nska
arXiv:2609.21412v1 Announce Type: new
Abstract: Medical image segmenters often get worse when sites, scanner vendors, or protocols change. Continual test-time adaptation (CTTA) addresses this problem...
By Ruijie Huang
The study investigates when adding zero‑shot pseudo‑labels from vision‑language models (VLMs) to small expert‑labelled medical imaging datasets ceases to improve, and may even degrade, classifier performance. Across three benchmarks—PatchCamelyon, ISIC 2019, and NIH ChestX‑ray14—the crossover point occurs after roughly 20–50, 100, and 250–500 expert labels, respectively, with additional pseudo‑labels reducing macro‑AUC by up to 0.14 points. The analysis shows that the VLM’s labeling quality, rather than the student model size, limits performance, and a simple bias‑variance rule can predict the benefit of pseudo‑labels in most settings.
By Bruce Changlong Xu, Jose K. James, Alexander J. Ryu
The study investigates how refined annotations versus model training changes affect pulmonary embolism segmentation performance. By re‑annotating 149 CT pulmonary angiography cases and evaluating two pretrained nnU-Net models, the authors find that improving annotation quality increases the Dice similarity coefficient (DSC) by 0.143–0.188, far exceeding the 0.028 DSC change from altering training datasets. A new human‑referenced benchmark model (nnPE) was trained and publicly released, though it performed below all annotators in paired comparisons.
By Qihang Sun, Zhongxiao Liu, Bailiang Jian, Shenman Qiu, Jingyuan Wang, Lei Zhang, Lixiang Xie, Jiazhen Pan, Christian Wachinger