arXiv 1806.023182018-06-06cs.CV

Adaptive feature recombination and recalibration for semantic segmentation: application to brain tumor segmentation in MRI

University of Minho（米尼奥大学）；CMEMS-UMinho Research Unit, University of Minho（米尼奥大学CMEMS-UMinho研究中心）；Centro Algoritmi, University of Minho（米尼奥大学阿尔戈里蒂米中心）

Sérgio Pereira, Victor Alves, Carlos A. Silva

备注：: Accepted at MICCAI 2018
DOI：: 10.1007/978-3-030-00931-1_81

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Convolutional neural networks (CNNs) have been successfully used for brain tumor segmentation, specifically, fully convolutional networks (FCNs). FCNs can segment a set of voxels at once, having a direct spatial correspondence between units in feature maps (FMs) at a given location and the corresponding classified voxels. In convolutional layers, FMs are merged to create new FMs, so, channel combination is crucial. However, not all FMs have the same relevance for a given class. Recently, in classification problems, Squeeze-and-Excitation (SE) blocks have been proposed to re-calibrate FMs as a whole, and suppress the less informative ones. However, this is not optimal in FCN due to the spatial correspondence between units and voxels. In this article, we propose feature recombination through linear expansion and compression to create more complex features for semantic segmentation. Additionally, we propose a segmentation SE (SegSE) block for feature recalibration that collects contextual information, while maintaining the spatial meaning. Finally, we evaluate the proposed methods in brain tumor segmentation, using publicly available data.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Adaptive feature recombination and recalibration for semantic segmentation with Fully Convolutional Networks

CMEMS-UMinho Research Unit, University of Minho（米尼奥大学CMEMS-UMinho研究单元）；Centro Algoritmi, University of Minho（米尼奥大学算法中心）

Fully Convolutional Networks have been achieving remarkable results in image semantic segmentation, while being efficient. Such efficiency results from the capability of segmenting several voxels in a single forward pass. So, there is a direct spatial correspondence between a unit in a feature map and the voxel in the same location. In a convolutional layer, the kernel spans over all channels and extracts information from them. We observe that linear recombination of feature maps by increasing the number of channels followed by compression may enhance their discriminative power. Moreover, not …

2020-06-19cs.CVeess.IV

multiPI-TransBTS：基于多物理信息的多路径学习框架用于脑肿瘤图像分割

multiPI-TransBTS: A Multi-Path Learning Framework for Brain Tumor Image Segmentation Based on Multi-Physical Information

Chongqing University of Posts and Telecommunications（重庆邮电大学）；Chongqing Engineering Research Center of Software Quality Assurance, Testing and Assessment（重庆市软件质量保证与测评工程技术研究中心）

提出multiPI-TransBTS，一种融合多物理信息的Transformer框架，通过多分支编码器、自适应特征融合和任务特定特征引入，在BraTS2019/2020上超越现有方法，提升脑肿瘤分割精度。

2024-09-18cs.CVeess.IV

T-MPEDNet：揭示用于肿瘤和肝脏分割的、具备特征重校准的 Transformer 感知多尺度渐进式编码器-解码器网络的协同作用

T-MPEDNet: Unveiling the Synergy of Transformer-aware Multiscale Progressive Encoder-Decoder Network with Feature Recalibration for Tumor and Liver Segmentation

Department of Computer Science and Engineering, Indian Institute of Technology (IIT) Indore, Indore 453552, India（计算机科学与工程系，印度理工学院（IIT）印尔德，印尔德453552，印度）；Department of Electrical Engineering, Indian Institute of Technology (IIT) Indore, Indore 453552, India（电气工程系，印度理工学院（IIT）印尔德，印尔德453552，印度）

本文提出 T-MPEDNet，通过渐进式编解码、Transformer 动态注意力、多尺度特征与边界细化提升 CT 中肝脏及肿瘤分割性能，并在 LiTS 和 3DIRCADb 上优于十二种方法。

2025-07-25cs.CV

Dino-NestedUNet：通过密集解码解锁基础视觉编码器用于病理肿瘤肿块分割

Dino-NestedUNet: Unlocking Foundation Vision Encoders for Pathology Tumor Bulk Segmentation via Dense Decoding

Department of Pathology, College of Medicine, The Ohio State University Wexner Medical Center, Columbus, OH, USA（病理学系，医学学院，俄亥俄州立大学韦克斯纳医学中心，哥伦布，OH，USA）；Department of Biomedical Engineering, The Ohio State University, Columbus, OH, USA（生物医学工程系，俄亥俄州立大学，哥伦布，OH，USA）

本文提出Dino-NestedUNet框架，通过预训练DINOv3编码器与密集密集解码器结合，改进病理肿瘤肿块分割的边界精度，实验证明其在跨域迁移中的有效性。

2026-04-27cs.CV

ESKNet：一种用于乳腺肿瘤分割的增强型自适应选择核卷积

ESKNet-An enhanced adaptive selection kernel convolution for breast tumors segmentation

Nankai University（南开大学）；Tianjin Medical University（天津医科大学）；PLA General Hospital（解放军总医院）；Civil Aviation General Hospital（民航总医院）

针对乳腺超声肿瘤形状尺寸多变导致分割困难的问题，提出融合多区域表示并进行通道与空间自适应重校准的增强选择核卷积，嵌入深度监督 U-net，在三个公开数据集上优于12种现有方法。

2024-01-20cs.CVeess.IV

LATUP-Net：一种用于脑肿瘤分割的轻量级3D注意力U-Net与并行卷积网络

LATUP-Net: A Lightweight 3D Attention U-Net with Parallel Convolutions for Brain Tumor Segmentation

School of Computer Science and Informatics, Cardiff University（卡迪夫大学计算机科学与信息学院）；College of Engineering and Computer Science, Jazan University（贾赞大学工程与计算机科学学院）

本文提出轻量级3D注意力U-Net模型LATUP-Net，通过并行卷积和注意力机制在显著降低计算资源的同时实现高精度脑肿瘤分割，并在BraTS数据集上取得优异性能。

2024-11-25cs.CVeess.IV

更多相关论文收起更多论文

分层灌注图谱用于胶质瘤分子分型中的肿瘤异质性建模

Hierarchical Perfusion Graphs for Tumor Heterogeneity Modeling in Glioma Molecular Subtyping

Interdisciplinary Program in Bioengineering, Seoul National University, Seoul, South Korea（生物工程跨学科项目，首尔国立大学，首尔，韩国）；Interdisciplinary Program in Cancer Biology, Seoul National University College of Medicine, Seoul, South Korea（癌症生物学跨学科项目，首尔国立大学医学院，首尔，韩国）；Dept. of Biomedical Sciences, Seoul National University, Seoul, South Korea（生物医学科学系，首尔国立大学，首尔，韩国）；Dept. of Electronic Engineering, Soongsil University, Seoul, South Korea（电子工程系，顺世大学，首尔，韩国）；Dept. of Radiology, Seoul National University Hospital, Seoul, South Korea（放射科，首尔国立大学医院，首尔，韩国）；Dept. of Radiology, Seoul National University College of Medicine, Seoul, South Korea（放射科，首尔国立大学医学院，首尔，韩国）；Healthcare AI Research Institute, Seoul National University Hospital, Seoul, South Korea（医疗人工智能研究院，首尔国立大学医院，首尔，韩国）

本文提出HiPerfGNN框架，通过学习灌注动态数据构建分层图谱，用于胶质瘤分子分型，实现了高准确率的分子亚型预测。

2026-06-23cs.CV

Bayesian Conditional GAN for MRI Brain Image Synthesis

As a powerful technique in medical imaging, image synthesis is widely used in applications such as denoising, super resolution and modality transformation etc. Recently, the revival of deep neural networks made immense progress in the field of medical imaging. Although many deep leaning based models have been proposed to improve the image synthesis accuracy, the evaluation of the model uncertainty, which is highly important for medical applications, has been a missing part. In this work, we propose to use Bayesian conditional generative adversarial network (GAN) with concrete dropout to improv…

2021-04-22cs.CVeess.IV

USE-Net: incorporating Squeeze-and-Excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets

University of Milano-Bicocca（米兰比可卡大学）；Italian National Research Council（意大利国家研究委员会）；University of Cambridge（剑桥大学）；Cancer Research UK Cambridge Centre（英国癌症研究中心剑桥中心）；The University of Tokyo（东京大学）；Wellcome Trust Sanger Institute（惠康基金会桑格研究所）

Prostate cancer is the most common malignant tumors in men but prostate Magnetic Resonance Imaging (MRI) analysis remains challenging. Besides whole prostate gland segmentation, the capability to differentiate between the blurry boundary of the Central Gland (CG) and Peripheral Zone (PZ) can lead to differential diagnosis, since tumor's frequency and severity differ in these regions. To tackle the prostate zonal segmentation task, we propose a novel Convolutional Neural Network (CNN), called USE-Net, which incorporates Squeeze-and-Excitation (SE) blocks into U-Net. Especially, the SE blocks ar…

2019-07-17cs.CVcs.LG