SCI-AIDE : High-fidelity Few-shot Histopathology Image Synthesis for Rare Cancer Diagnosis

Related tags

Deep LearningSCI-AIDE
Overview

SCI-AIDE : High-fidelity Few-shot Histopathology Image Synthesis for Rare Cancer Diagnosis

Pretrained Models

In this work, we created synthetic tissue microscopy images using few-shot learning and developed a digital pathology pipeline called SCI-AIDE to improve diagnostic accuracy. Since rare cancers encompass a very large group of tumours, we used childhood cancer histopathology images to develop and test our system. Our computational experiments demonstrate that the synthetic images significantly enhances performance of various AI classifiers.

Example Results

Real and Synthetic Images

Dataset

In this study, we conducted experiments using histopathological whole slide images(WSIs) of five rare childhood cancer types and their sub-types, namely ependymoma (anaplastic, myxopapillary, subependymoma and no-subtype), medulloblastoma (anaplastic, desmoplastic and no-subtype), Wilms tumour, also known as nephroblastoma (epithelial, blastomatous, stromal, Wilms epithelial-stromal, epithelial-blastomatous and blastomatous-stromal), pilocytic astrocytoma and Ewing sarcoma.

Tumour histopathology WSIs are collected at Ege University, Turkey and Aperio AT2 scanner digitised the WSIs at 20× magnification. WSIs will be available publicly soon

Prerequisites

  • Linux (Tested on Red Hat Enterprise Linux 8.5)
  • NVIDIA GPU (Tested on Nvidia GeForce RTX 3090 Ti x 4 on local workstations, and Nvidia A100 GPUs on TRUBA
  • Python (3.9.7), matplotlib (3.4.3), numpy (1.21.2), opencv (4.5.3), openslide-python (1.1.1), openslides (3.4.1), pandas (1.3.3), pillow (8.3.2), PyTorch (1.9.0), scikit-learn (1.0), scipy (1.7.1), tensorboardx (2.4), torchvision (0.10.1).

Getting started

  • Clone this repo:
git clone https://github.com/ekurtulus/SCI-AIDE.git
cd SCI-AIDE
  • Install PyTorch 3.9 and other dependencies (e.g., PyTorch).

  • For pip users, please type the command pip install -r requirements.txt.

  • For Conda users, you can create a new Conda environment using conda env create -f environment.yml.

Synthetic Images Generation

  • Clone FastGAN repo:
git clone https://github.com/odegeasslbc/FastGAN-pytorch.git
cd FastGAN-pytorch
  • Train the FastGAN model:
python classifer.py --path $REAL_IMAGE_DIR --iter 100000 --batch_size 16
  • Inference the FastGAN model:
python eval.py --ckpt $CKPT_PATH --n_sample $NUMBERS_OF_SAMPLE
  • Train the SCI-AIDE model:
python train.py --datapath $DATAPATH_PATH --model $MODEL --savepath $SAVING_PATH --task $TRAINING_TASK

The list of other arguments is as follows:

  • --lr : Learning rate (default: 5e-5)

  • --opt : Optimizers ( "Adam", "SGD", "RMSprop", "AdamW" , default= "SGD")

  • --batch-size : Batch size (default: 32)

  • --halftensor : Mixed presicion acivaiton

  • --epochs : Numbers of epochs

  • --scheduler : Learning scheduler ( "cosine", "multiplicative" , default="cosine")

  • --augmentation : Augmentation selection ( "randaugment", "autoaugment", "augmix", "none", default= "randaugment" )

  • --memory : Data reading selection ( "none", "cached", default= "none" )

  • Evaluation the SCI-AIDE model:

python wsi_attention.py --datapath $DATAPATH_PATH --model $MODEL --model_weights $MODEL_WEIGHT --output $OUTPUT_PATH --name $NAME --num_classes $NUM_CLASSES

The list of other arguments is as follows:

  • --attention_level : ("pixel", "patch", default="patch)

  • --cam : CAM selection ( "GradCAM", "ScoreCAM", "GradCAMPlusPlus", "AblationCAM", "XGradCAM", "EigenCAM", "FullGrad", default="EigenCAM" )

  • Diagnosis WSI with the SCI-AIDE model:

python wsi_diagnosis.py --task $DIAGNOSIS_TASK --datapath $WSI_PATH --output $OUTPUT_PATH --config $CONFIG_FILE_PATH --name $NAME

The list of other arguments is as follows:

  • --overlap : Patches overlaping raito (default :0 )
  • --patch_size : WSI oatching size (default : 1024 )
  • --heatmap : Heatmap inference activation
  • --white_threshold : White pathch elimiantion ration (default :0.3)

Apply a pre-trained SCI-AIDE model and evaluate

For reproducability, you can download the pretrained models for each algorithm here.

Issues

  • Please report all issues on the public forum.

License

© This code is made available under the GPLv3 License and is available for non-commercial academic purposes.

Reference

If you find our work useful in your research or if you use parts of this code please consider citing our paper:


Acknowledgments

Our code is developed based on pytorch-image-models. We also thank pytorch-fid for FID computation, and FastGAN-pytorch for the PyTorch implementation of FastGAN used in our single-image translation setting.

You might also like...
Deep generative modeling for time-stamped heterogeneous data, enabling high-fidelity models for a large variety of spatio-temporal domains.
Deep generative modeling for time-stamped heterogeneous data, enabling high-fidelity models for a large variety of spatio-temporal domains.

Neural Spatio-Temporal Point Processes [arxiv] Ricky T. Q. Chen, Brandon Amos, Maximilian Nickel Abstract. We propose a new class of parameterizations

《Towards High Fidelity Face Relighting with Realistic Shadows》(CVPR 2021)
《Towards High Fidelity Face Relighting with Realistic Shadows》(CVPR 2021)

Towards High Fidelity Face-Relighting with Realistic Shadows Andrew Hou, Ze Zhang, Michel Sarkis, Ning Bi, Yiying Tong, Xiaoming Liu. In CVPR, 2021. T

HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks
HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

HiFiGAN Denoiser This is a Unofficial Pytorch implementation of the paper HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep F

Tensorflow python implementation of
Tensorflow python implementation of "Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos"

Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos This repository is the official tensorflow python implementation

UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

UnivNet UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation. Training python train.py --c

Unofficial PyTorch Implementation of UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
Unofficial PyTorch Implementation of UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

UnivNet UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation This is an unofficial PyTorch

Unofficial PyTorch Implementation of UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
Unofficial PyTorch Implementation of UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

UnivNet UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation This is an unofficial PyTorch

A two-stage U-Net for high-fidelity denoising of historical recordings
A two-stage U-Net for high-fidelity denoising of historical recordings

A two-stage U-Net for high-fidelity denoising of historical recordings Official repository of the paper (not submitted yet): E. Moliner and V. Välimäk

PyTorch Implementation of DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs
PyTorch Implementation of DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs

DiffGAN-TTS - PyTorch Implementation PyTorch implementation of DiffGAN-TTS: High

Owner
Emirhan Kurtuluş
Emirhan Kurtuluş
A PyTorch implementation of "Signed Graph Convolutional Network" (ICDM 2018).

SGCN ⠀ A PyTorch implementation of Signed Graph Convolutional Network (ICDM 2018). Abstract Due to the fact much of today's data can be represented as

Benedek Rozemberczki 251 Nov 30, 2022
Official implementation of NeurIPS'2021 paper TransformerFusion

TransformerFusion: Monocular RGB Scene Reconstruction using Transformers Project Page | Paper | Video TransformerFusion: Monocular RGB Scene Reconstru

Aljaz Bozic 118 Dec 25, 2022
Deep-learning-roadmap - All You Need to Know About Deep Learning - A kick-starter

Deep Learning - All You Need to Know Sponsorship To support maintaining and upgrading this project, please kindly consider Sponsoring the project deve

Instill AI 4.4k Dec 26, 2022
Automatic detection and classification of Covid severity degree in LUS (lung ultrasound) scans

Final-Project Final project in the Technion, Biomedical faculty, by Mor Ventura, Dekel Brav & Omri Magen. Subproject 1: Automatic Detection of LUS Cha

Mor Ventura 1 Dec 18, 2021
ICCV2021 Expert-Goal Trajectory Prediction

ICCV 2021: Where are you heading? Dynamic Trajectory Prediction with Expert Goal Examples This repository contains the code for the paper Where are yo

hz 21 Dec 12, 2022
Code for the paper "Next Generation Reservoir Computing"

Next Generation Reservoir Computing This is the code for the results and figures in our paper "Next Generation Reservoir Computing". They are written

OSU QuantInfo Lab 105 Dec 20, 2022
The official implementation of NeurIPS 2021 paper: Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks

Introduction This repository includes the source code for "Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks", which is pu

machen 11 Nov 27, 2022
A PyTorch implementation of the continual learning experiments with deep neural networks

Brain-Inspired Replay A PyTorch implementation of the continual learning experiments with deep neural networks described in the following paper: Brain

182 Dec 27, 2022
A PyTorch version of You Only Look at One-level Feature object detector

PyTorch_YOLOF A PyTorch version of You Only Look at One-level Feature object detector. The input image must be resized to have their shorter side bein

Jianhua Yang 25 Dec 30, 2022
Weakly- and Semi-Supervised Panoptic Segmentation (ECCV18)

Weakly- and Semi-Supervised Panoptic Segmentation by Qizhu Li*, Anurag Arnab*, Philip H.S. Torr This repository demonstrates the weakly supervised gro

Qizhu Li 159 Dec 20, 2022
Simulation environments for the CrazyFlie quadrotor: Used for Reinforcement Learning and Sim-to-Real Transfer

Phoenix-Drone-Simulation An OpenAI Gym environment based on PyBullet for learning to control the CrazyFlie quadrotor: Can be used for Reinforcement Le

Sven Gronauer 8 Dec 07, 2022
PyTorch implementation of Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution, IJCNN 2021.

GCResNet PyTorch implementation of Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution, IJCNN 2021. The code will

11 May 19, 2022
Source code to accompany Defunctland's video "FASTPASS: A Complicated Legacy"

Shapeland Simulator Source code to accompany Defunctland's video "FASTPASS: A Complicated Legacy" Download the video at https://www.youtube.com/watch?

TouringPlans.com 70 Dec 14, 2022
Tensorflow implementation of Semi-supervised Sequence Learning (https://arxiv.org/abs/1511.01432)

Transfer Learning for Text Classification with Tensorflow Tensorflow implementation of Semi-supervised Sequence Learning(https://arxiv.org/abs/1511.01

DONGJUN LEE 82 Oct 22, 2022
An pytorch implementation of Masked Autoencoders Are Scalable Vision Learners

An pytorch implementation of Masked Autoencoders Are Scalable Vision Learners This is a coarse version for MAE, only make the pretrain model, the fine

FlyEgle 214 Dec 29, 2022
A project to make Amazon Echo respond to sign language using your webcam

Making Alexa respond to Sign Language using Tensorflow.js Try the live demo Read the Blog Post on Tensorflow's Blog Coming Soon Watch the video This p

Abhishek Singh 444 Jan 03, 2023
Measures input lag without dedicated hardware, performing motion detection on recorded or live video

What is InputLagTimer? This tool can measure input lag by analyzing a video where both the game controller and the game screen can be seen on a webcam

Bruno Gonzalez 4 Aug 18, 2022
PINN Burgers - 1D Burgers equation simulated by PINN

PINN(s): Physics-Informed Neural Network(s) for Burgers equation This is an impl

ShotaDEGUCHI 1 Feb 12, 2022
Repo for "TableParser: Automatic Table Parsing with Weak Supervision from Spreadsheets" at [email protected]

TableParser Repo for "TableParser: Automatic Table Parsing with Weak Supervision from Spreadsheets" at DS3 Lab 11 Dec 13, 2022