SAC-Net: Learning with weak and noisy labels in histopathology image segmentation [0.03%]
基于弱监督和噪声标签的病理图像分割学习模型Sac-net
Ruoyu Guo,Kunzi Xie,Maurice Pagnucco et al.
Ruoyu Guo et al.
Deep convolutional neural networks have been highly effective in segmentation tasks. However, segmentation becomes more difficult when training images include many complex instances to segment, such as the task of nuclei segmentation in his...
Axial and radial axonal diffusivities and radii from single encoding strongly diffusion-weighted MRI [0.03%]
单次编码强扩散加权MRI的轴向和径向轴突扩散率及半径
Marco Pizzolato,Erick Jorge Canales-Rodríguez,Mariam Andersson et al.
Marco Pizzolato et al.
We enable the estimation of the per-axon axial diffusivity from single encoding, strongly diffusion-weighted, pulsed gradient spin echo data. Additionally, we improve the estimation of the per-axon radial diffusivity compared to estimates b...
Diffusion MRI data analysis assisted by deep learning synthesized anatomical images (DeepAnat) [0.03%]
基于深度学习合成解剖图像的扩散MRI数据分析（DeepAnat）
Ziyu Li,Qiuyun Fan,Berkin Bilgic et al.
Ziyu Li et al.
Diffusion MRI is a useful neuroimaging tool for non-invasive mapping of human brain microstructure and structural connections. The analysis of diffusion MRI data often requires brain segmentation, including volumetric segmentation and cereb...
SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining [0.03%]
SynthSeg：无需重新训练即可对任何对比度和分辨率的脑MRI扫描进行分割
Benjamin Billot,Douglas N Greve,Oula Puonti et al.
Benjamin Billot et al.
Despite advances in data augmentation and transfer learning, convolutional neural networks (CNNs) difficultly generalise to unseen domains. When segmenting brain scans, CNNs are highly sensitive to changes in resolution and contrast: even w...
Unpaired mesh-to-image translation for 3D fluorescent microscopy images of neurons [0.03%]
用于神经元三维荧光显微图像的不配对网格到图像转换问题研究
Mihael Cudic,Jeffrey S Diamond,J Alison Noble
Mihael Cudic
While Generative Adversarial Networks (GANs) can now reliably produce realistic images in a multitude of imaging domains, they are ill-equipped to model thin, stochastic textures present in many large 3D fluorescent microscopy (FM) images a...
Ziteng Liu,Wenpeng Gao,Jiahua Zhu et al.
Ziteng Liu et al.
Image-guided surgery has been proven to enhance the accuracy and safety of minimally invasive surgery (MIS). Nonrigid deformation tracking of soft tissue is one of the main challenges in image-guided MIS owing to the existence of tissue def...
Dense regression activation maps for lesion segmentation in CT scans of COVID-19 patients [0.03%]
用于COVID-19患者CT扫描病变分割的稠密回归激活图
Weiyi Xie,Colin Jacobs,Jean-Paul Charbonnier et al.
Weiyi Xie et al.
Automatic lesion segmentation on thoracic CT enables rapid quantitative analysis of lung involvement in COVID-19 infections. However, obtaining a large amount of voxel-level annotations for training segmentation networks is prohibitively ex...
Generalized pancreatic cancer diagnosis via multiple instance learning and anatomically-guided shape normalization [0.03%]
基于多重实例学习和解剖结构引导的形状归一化的泛化胰腺癌诊断方法
Jiaqi Qu,Xunbin Wei,Xiaohua Qian
Jiaqi Qu
Pancreatic cancer is a highly malignant cancer type with a high mortality rate. As no obvious symptoms are associated with this cancer type, most of the diagnoses are made when the patients are already in a late stage. In this work, we prop...
Automatic uncertainty-based quality controlled T1 mapping and ECV analysis from native and post-contrast cardiac T1 mapping images using Bayesian vision transformer [0.03%]
基于不确定性质量控制的原发和对比后心脏T1图谱分析的自动贝叶斯视觉变压器法熵聚类ECV计算方法
Tewodros Weldebirhan Arega,Stéphanie Bricq,François Legrand et al.
Tewodros Weldebirhan Arega et al.
Deep learning-based methods for cardiac MR segmentation have achieved state-of-the-art results. However, these methods can generate incorrect segmentation results which can lead to wrong clinical decisions in the downstream tasks. Automatic...
Triplet attention and dual-pool contrastive learning for clinic-driven multi-label medical image classification [0.03%]
基于临床的多标签医学图像分类的 triplet 门注意和双池对比学习方法
Yuhan Zhang,Luyang Luo,Qi Dou et al.
Yuhan Zhang et al.
Multi-label classification (MLC) can attach multiple labels on single image, and has achieved promising results on medical images. But existing MLC methods still face challenging clinical realities in practical use, such as: (1) medical ris...