侵略者
发表于 2025-3-23 12:11:17
Eye-Guided Dual-Path Network for Multi-organ Segmentation of Abdomend. To address this issue, we propose a novel network for abdominal multi-organ segmentation, which incorporates radiologists’ gaze information to boost high-precision segmentation and weaken the demand for high-cost manual labels. Our network includes three special designs: 1) a dual-path encoder to
CLAMP
发表于 2025-3-23 13:58:39
Scribble-Based 3D Multiple Abdominal Organ Segmentation via Triple-Branch Multi-Dilated Network withes from different receptive fields that are complementary to each other to generate high-quality soft pseudo labels. For more stable unsupervised learning, we use voxel-wise uncertainty to rectify the soft pseudo labels and then supervise the outputs of each decoder. To further regularize the networ
Noisome
发表于 2025-3-23 21:26:32
Geometry-Adaptive Network for Robust Detection of Placenta Accreta Spectrum DisordersThe GA-RF module aggregates the multi-scale RoI features based on the geometry distribution of proposals. Moreover, we develop a Lesion-aware Detection Head (LA-Head) to leverage high-quality predictions to iteratively refine inaccurate annotations with a novel multiple instance learning paradigm. E
和平主义
发表于 2025-3-24 00:31:58
Mammo-Net: Integrating Gaze Supervision and Interactive Information in Multi-view Mammogram Classifidirectional fusion learning (BFL) to more effectively fuse multi-view information. Experimental results demonstrate that our proposed model significantly improves both mammogram classification performance and interpretability through incorporation of gaze data and cross-view interactive information.
Expressly
发表于 2025-3-24 03:58:20
http://reply.papertrans.cn/63/6293/629223/629223_15.png
Blasphemy
发表于 2025-3-24 06:38:31
http://reply.papertrans.cn/63/6293/629223/629223_16.png
保全
发表于 2025-3-24 12:28:56
Towards Expert-Amateur Collaboration: Prototypical Label Isolation Learning for Left Atrium Segmentae in the high-level feature space, the self-ensembling teacher model isolates clean and noisy labeled voxels by exploiting their relative feature distances to the class prototypes via multi-scale voting. Then, the student follows the teacher’s instruction for adaptive learning, wherein the clean vox
Blatant
发表于 2025-3-24 15:06:49
http://reply.papertrans.cn/63/6293/629223/629223_18.png
jocular
发表于 2025-3-24 22:09:15
http://reply.papertrans.cn/63/6293/629223/629223_19.png
逢迎白雪
发表于 2025-3-24 23:32:46
http://reply.papertrans.cn/63/6293/629223/629223_20.png