マルチスケールネスト型 Residual UNetに基づく肺CTにおける多段階気道セグメンテーション
本稿では、複雑な気道構造を正確にセグメント化するため、マルチスケールネスト型 Residual UNet（MNR-UNet）と重み付きBreakage-Aware Loss（wBAL）を組み合わせた新しい3段階セグメンテーション手法を提案する。
Enhancing Hierarchical Transformers for Whole Brain Segmentation with Intracranial Measurements Integration
The core message of this article is to enhance the existing hierarchical transformer-based model, UNesT, for whole brain segmentation by integrating the estimation of total intracranial volume (TICV) and posterior fossa volume (PFV) alongside the segmentation of 132 brain regions.
A Clinical-oriented Multi-level Contrastive Learning Method for Accurate Disease Diagnosis from Low-quality Medical Images
A clinical-oriented multi-level contrastive learning framework that enhances the model's capacity to extract lesion features and discriminate between lesion and low-quality factors, enabling more accurate disease diagnosis from low-quality medical images.
Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models
This paper aims to advance 3D medical image analysis by leveraging multi-modal large language models (MLLMs). It presents a large-scale 3D multi-modal medical dataset, M3D-Data, and proposes M3D-LaMed, a versatile MLLM for 3D medical image analysis. The authors also introduce a new 3D multi-modal medical benchmark, M3D-Bench, to facilitate automatic evaluation across eight tasks.
MaxViT-UNet: A Hybrid Encoder-Decoder Architecture for Efficient Medical Image Segmentation
The proposed MaxViT-UNet framework utilizes a hybrid encoder-decoder architecture with multi-axis attention to effectively capture local and global features for accurate medical image segmentation.