SunZheng's repositories
ITKMinimalPathExtraction
Vessel and tube centerline extraction
GLIA-Net
A segmentation network for intracranial aneurysm on CTA images using pytorch
DeepCenterline
Model for finding a centerline distance map of blood vessel segmentations to then be fed into a graph minimum path extractor to find the centerlines of a vessel using PyTorch. It uses a Residual UNet (Convolutional AutoEncoder) type architecture.
BET
Bet for CT
Deep-learning-with-simulated-data-in-vascular-segmentation
Brain vessel segmentation program based on Residual UNet
ITKElastix
An ITK Python interface to elastix, a toolbox for rigid and nonrigid registration of images
batchgenerators
A framework for data augmentation for 2D and 3D image classification and segmentation
FastSurfer
PyTorch implementation of FastSurferCNN
FAE
FeAture Explorer
ORG-Atlases
ORG Fiber Clustering White Matter Atlas
CTseg
Brain CT segmentation and normalisation, implemented in MATLAB.
Recursive-Cascaded-Networks
[ICCV 2019] Recursive Cascaded Networks for Unsupervised Medical Image Registration
CT_BET
Robust Brain Extraction Tool for CT Head Images
AI-LAB
This repository contains a docker image that I use to develop my artificial intelligence applications in an uncomplicated fashion. Python, TensorFlow, PyTorch, ONNX, Keras, OpenCV, TensorRT, Numpy, Jupyter notebook... :whale2::fire:
Automatic-recognition-of-lung-opacities-region-on-chest-radiographs
肺部不透明区域识别Chest radiograph (CXR) is one of the common radiological examinations used to screen and diagnose many lung diseases. Most pulmonary diseases usually present on CXR as one or more opacities or less transparent areas of the lung. However, it is a difficult task to identify opacities areas accurately. This project designs an algorithm to assist clinicians in diagnosis.
pytorch-doc-zh
Pytorch 中文文档
raster-images
栅格化图像算法,优化标注边缘
classify-for-cervical
pytorch宫颈图像分类
Accurate-localization-of-key-points-Scleral-Spur-based-on-VGG19-on-ACA-and-measurement-of-relevant
In previous studies, classification tasks were completed, and the ACA was divided into three categories: open, closed, and narrow. However, it is important to locate the scleral-spur of open angle and narrow angle and measure the relevant parameters.
Back-Propagation-Neural-Network-Classification-Algorithm-of-ECG-Signal
In the ECG automatic classification system, the accuracy of classification has always been an important part of scholars'research. Therefore, BP neural network is used to classify and recognize ECG signals in ECG automatic classification system.
pytorch-lesson-zh
pytorch 包教不包会
code-of-learn-deep-learning-with-pytorch
This is code of book "Learn Deep Learning with PyTorch"
Faster_RCNN_for_Open_Images_Dataset_Keras
Faster R-CNN for Open Images Dataset by Keras
mra_blood_vessel_segmentation
Cerebral MRA Blood Vessel Segmentation, using Image Projections and Neural Networks
ACA-Localization-Classification
在UBM图像中,首先自动定位房角隐窝的顶点,然后拟合出房角内侧边缘,并计算出房角隐窝角度、定性分析虹膜形态以及虹膜根部灰度特征等参数,最后基于Spaeth分级法将前房角分为开闭窄三类。
Iris-location-Algorithm
A method of gray value of unit sector area is proposed to solve the problem of iris localization.First, in this method, a rectangular area containing pupil is segmented by gray-scale projection algorithm, meanwhile,the OTSU algorithm is used to determine the threshold of this rectangular area and segment the pupil. With respect to outer location in a certain direction, a sector area in the direction needs to be segmented according to the pupil center. Then the gray value of each concentric sector ring is calculated by setting steps to 5 pixels,and the abscissa values of the position where the maximum change in gray value is calculated as the radius in that direction.The location of boundary points in other directions is also applied by this method.Finally, these points are filtered and used to fit outer boundary of iris. The results shows that the iris image segmented by this method can achieve good result with good application and reference value.
Distance-of-point_to_point
Distance of a pair of opposite_point