This is the official repository for our CVPR 2023 paper 'Task-Specific Fine-Tuning via Variational Information Bottleneck for Weakly-Supervised Pathology Whole Slide Image Classification'.

TIANCHI 天池 “数字人体”视觉挑战赛——宫颈癌风险智能诊断 算法赛道 LLLLC队代码 4/2359

Based on our paper "Cervical Cytology Classification Using PCA & GWO Enhanced Deep Features Selection" published in SN Computer Science

It will be the supporting scripts for tct project.

A fuzzy distance-based ensemble of deep models for cervical cancer detection published in Computer Methods and Programs in Biomedicine, Elsevier

Implementation of STN (Spatial Transformer Network) and ICSTN (Inverse Compositional Spatial Transformer Networks) in Tensorlayer to predict transformation parameters from 2D images.

Based on our paper on "A Fuzzy Rank-based Ensemble of CNN Models for Classification of Cervical Cytology" published in Nature- Scientific Reports.

Official Pytorch Implementation of our new paper 'Predicting Lymph Node Metastasis from Primary Cervical Cancer Based on Deep Learning in Histopathological Images.'

Implementation of our paper "Cervical Cytology Classification Using PCA & GWO Enhanced Deep Features Selection"

Latex scripts to compile my PhD thesis

Ridge Estimation of Vector Auto-Regressive (VAR) Processes

Classification of cervical cancer using SVM is done on Herlev Pap Smear

https://ieeexplore.ieee.org/abstract/document/9432382

Image classification of Pap-smears

Cervical Cancer detection using Image Processing Techniques

Finding Multiple Cutpoints for Continuous Variables for Cox Model, Use Lasso Model For Full Cox Model Selection

A novel deep network named IgrNet, which can model the relationships of pathological features of cervical cells from the same specimen by a technology of intra-group reference.

PhD thesis supplementary materials

Project Phoenix uses deep learning to classify cervical cell images into five key diagnostic categories. Inspired by the myth of the Phoenix—rebirth through fire—this project aims to catch early signs of disease, turning data into second chances and diagnosis into hope.

Exploratory study on Cervical Cancer: verifying known causal relations and assessing risk factors from women medical history datasets.