The paper introduces a method for generalizable brain tumor segmentation in the BraTS 2026 Challenge. It builds on the nnU-Net framework with a large residual encoder, adding semi‑supervised learning via pseudo‑labels and a tumor‑aware deformable augmentation that locally deforms lesions while preserving surrounding anatomy. The approach improves Dice and NSD scores across all tumor regions compared to labeled‑only baselines, demonstrating the complementary benefits of self‑training and the proposed augmentation.
By Henrique Zan Grande, Jeovane Honorio Alves, Rayson Laroca, Andre Gustavo Hochuli
arXiv:2505.03380v2 Announce Type: replace
Abstract: Accurate delineation of tumors and surrounding organs-at-risk is essential for radiotherapy, surgery and treatment response assessment, yet remains...
By Haonan Wang, Jiaji Mao, Lehan Wang, Qixiang Zhang, Marawan Elbatel, Yi Qin, Huijun Hu, Baoxun Li, Wenhui Deng, Weifeng Qin, Hongrui Li, Jialin Liang, Jun Shen, Xiaomeng Li
arXiv:2608. 13690v1 Announce Type: cross Abstract: 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 context.
By Rafi Ibn Sultan, Hui Zhu, Chengyin Li, Dongxiao Zhu
Multi-parametric MRI is the gold standard for neuro-oncology, yet acquiring complete 4-modality protocols may be unfeasible in real-world clinical practice. When handling missing modalities, existing...
arXiv:2611.06701v1 Announce Type: new
Abstract: Deep learning methods for pathology are constrained by the limited availability and high cost of large-scale pixel-level annotations. Synthetic data ca...
By Sicheng Yang, Rui Tang, Haipeng Zhou, Hongqiu Wang, Zhaohu Xing, Jianda Ma, Lie Dai, Guang Yang, Lei Zhu
CAPS is a Clinically‑Verifiable Anatomy‑Prioritized Synthesis framework designed to impute missing MRI modalities for brain tumor segmentation. It uses a hybrid loss (L₁ + L_AFP + L_DualDice) to preserve deep anatomical features and topological boundaries, achieving high synthesis fidelity and robust segmentation (82.38% mean Dice) on the BraTS Adult Glioma dataset. The method also generalizes well to unseen cohorts and has been validated by blinded radiologists, who report improved image quality and clinical utility.
By Cecilia Diana-Albelda, Arthur Longuefosse, Mario Rub\'en Paz Campos, \'Alvaro Garc\'ia-Mart\'in, Jesus Bescos
NV-Generate-BodyMask is a 3D latent diffusion model that generates whole-body CT segmentation masks with precise control over organ anatomy, tumor burden, and patient demographics. It operates in the compressed latent space of a frozen mask autoencoder, producing 256³ volumetric label maps conditioned on a 19‑dimensional vector via Adaptive Group Normalization and cross‑attention. Trained on 8,571 masks from 26 cohorts, the model achieves high Spearman correlations for organ size, excellent tumor recall for several lesion types, and strong demographic alignment.
By Can Zhao, Pengfei Guo, Dong Yang, Yufan He, Yucheng Tang, Ahmed Harouni, Benjamin Simon, Mason Belue, Stephanie Harmon, Baris Turkbey, Daguang Xu
arXiv:2603. 09448v2 Announce Type: replace-cross Abstract: Delineating the clinical target volume (CTV) in radiotherapy involves complex margins constrained by tumor location and anatomical barriers.
By Yoon Jo Kim, Wonyoung Cho, Jongmin Lee, Han Joo Chae, Hyunki Park, Sang Hoon Seo, Jae Myung Noh, Kyungmi Yang, Dongryul Oh, Jin Sung Kim
arXiv:2608.24364v1 Announce Type: new
Abstract: Self-supervised pretraining enables transferable representations for medical imaging, yet most CT encoders remain biased toward coarse semantic underst...
By Sebasti\'an Gonz\'alez, Karen Sanchez, Jos\'e M. Saavedra, Marcelo Pizarro, Bernard Ghanem
arXiv:2602.14512v3 Announce Type: replace
Abstract: Autoregressive pretraining has been key to the scalability of large language models, yet medical generative foundation models remain predominantly...
By Zhicheng He, Yunpeng Zhao, Junde Wu, Ziwei Niu, Ziyue Wang, Bohan Li, Zijun Li, Lanfen Lin, Nan Liu, Yueming Jin
arXiv:2609.17169v1 Announce Type: cross
Abstract: Forecasting anatomical changes such as tumor growth and neurodegeneration is a challenging generative vision task. Morphological evolution is subtle...
By Anna Oliveras, Roger Mar\'i, Rafael Redondo, Oriol Guardi\`a, Cynthia Ifeyinwa Ugwu, Ana Tost, Bhalaji Nagarajan, Carolina Migliorelli, Vicent Ribas, Petia Radeva
Self-supervised pretraining enables transferable representations for medical imaging, yet most CT encoders remain biased toward coarse semantic understanding, limiting their sensitivity to fine-graine...