# PREDICTING PROSTATE CANCER STATE WITH BIOPSY IMAGES

<img src="https://render.fineartamerica.com/images/rendered/search/print/8/6.5/break/images-medium-5/cell-no14-angela-canada-hopkins.jpg" alt="Drawing" style="width: 650px;"/>

<br>A web application using to GANS model to generate cancerous regions and determine the stage from biopsy images.

## PROJECT INTRODUCTION

### Prostate cancer and how is it graded?
With more than 1 million new diagnoses reported every year, prostate cancer (PCa) is the second most common cancer among males worldwide that results in more than 350,000 deaths annually. The key to decreasing mortality is developing more precise diagnostics. Diagnosis of PCa is based on the grading of prostate tissue biopsies. These tissue samples are examined by a pathologist and scored according to the Gleason grading system. Develop models for detecting PCa on images of prostate tissue samples, and estimate severity of the disease using the most extensive multi-center dataset on Gleason grading yet available.

<img src='https://storage.googleapis.com/kaggle-media/competitions/PANDA/Screen%20Shot%202020-04-08%20at%202.03.53%20PM.png' alt='Drawing' style='width:650px;'/>

<br>More detail on the dataset: https://www.kaggle.com/c/prostate-cancer-grade-assessment/overview

<img src='https://upload.wikimedia.org/wikipedia/commons/thumb/b/bc/Gleasonscore.jpg/1024px-Gleasonscore.jpg' alt='Drawing' style='width:650px;'/>

### What is Pix2Pix and why is it used?
<br>Image-To-Image Translation is a process for translating one representation of an image into another representation. Pix2Pix network is basically a Conditional GANs (cGAN) that learn the mapping from an input image to output an image. The benefit of the Pix2Pix model is that compared to other GANs for conditional image generation, it is relatively simple and capable of generating large high-quality images across a variety of image translation tasks.

## PROJECT GOAL

This project aims to use Pix2Pix (cGAN) to alleviate cancerous region detection problem. To be more precise, given a biopsy images of the prostate tissues and generate a mask image highlighting the cancerous regions.

## PROJECT TIMELINE
[TIMELINE](https://docs.google.com/spreadsheets/d/1EIJJqvHrnx835WH9k5qevz6LrbYZE3S0TW6VKhYdygY/edit?usp=sharing)

## SUPPLEMENT READING

[Pix2Pix Network, An Image-To-Image Translation Using Conditional GANs (cGANs)](https://medium.com/towards-artificial-intelligence/pix2pix-network-an-image-to-image-translation-using-conditional-gans-cgans-8a08b661d206)

[CycleGAN and Pix2Pix for biopsy images](https://www.biorxiv.org/content/10.1101/2020.01.07.897801v2.full.pdf)

[How to Implement Pix2Pix GAN Models From Scratch With Keras](https://machinelearningmastery.com/how-to-implement-pix2pix-gan-models-from-scratch-with-keras/)