Tunable U-Net implementation in PyTorch

3D Unet biomedical segmentation model powered by tensorpack with fast io speed

Python based dashboard for real-time Electrical Impedance Tomography including image reconstruction using Back Projection, Graz Consensus and Gauss Newton methods

Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images

ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection

Datasets, Transforms and Utilities specific to Biomedical Imaging

Connected components on multilabel 3D & 2D images. Handles 26, 18, and 6 connected variants.

Codes that I have written to complete promise12 prostate segmentation competition.

Euclidean distance transform for multi-label 3D anisotropic images using marching parabolas.

Detecting Pneumonia in Chest X-ray Images using Convolutional Neural Network and Pretrained Models

A PyTorch-based library for working with 3D and 2D convolutional neural networks, with focus on semantic segmentation of volumetric biomedical image data

Read and write Neuroglancer datasets programmatically.

Skeletonize densely labeled 3D image segmentations with TEASAR.

PyTorch Connectomics: segmentation toolbox for EM connectomics

Transfer Learning with DCNNs (DenseNet, Inception V3, Inception-ResNet V2, VGG16) for skin lesions classification

Dijkstra's Shortest Path for 6, 18, and 26-Connected 3D (Volumetric) Image Volumes

Rank3 Code for ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection, Task 3

Smart India Hackathon 2019 project given by the Department of Atomic Energy

Mesh-based Monte Carlo (MMC)

WMH segmentaion with unet, dilated_unet, and with ideas from denseNet

Marching Cubes & Mesh Simplification on multi-label 3D images.

Remap, mask, renumber, unique, and in-place transposition of 3D labeled images.

Segmenting WSIs using Deep Convolutional Neural Networks

Cancer Detection from Microscopic Images by Fine-tuning Pre-trained Models ("Inception") for new class labels

A brain MRI segmentation tool that provides accurate robust segmentation of problematic brain regions across the neurodegenerative spectrum. The methodology is generalisable to perform well with the typical variance in MRI acquisition parameters and other factors that influence image contrast.

A highly configurable toolkit for training 3D/2D CNNs and general Neural Networks, based on Theano

JS biomedical 3D image stack. Fast CPU rendering. Easy web app integration.

An algorithm used for white blood cell nuclei segmentation

Handling whole-slide images with region-level annotations.

Binary Pattern Dictionary Learning for gene activation in microscopy images