This repository contains Projectwork ⬇️ undertaken for the partial fulfillment of Deep Learning Module and ETCS Creditpoints @OpenCampus.sh.

Thoractic disease Detection on Chest X-ray Images

Objective : To train and explore Deep learning models for Medical Radiology Assistance ( Classification and Detection of Thorax Diseases) using Chest X-ray datasets.

---

🔰 Index

1. Datasets

2. Implementation

3. References

---

💠 1. Datasets

• NIH Clinical Center Chest x-ray datasets y | National Institutes of Health (NIH)

  • ⬇️ Download Here
  • ⚠️ Incase of warning with Image folder !! : run python Utils/download.py

💻 2. Implementaition

Status /Progress

• Exploration of Datasets

• Exploartion of Application Domain and Challenges [Concepts: @AI for medical Diagnosis (coursera)]

  • Class Imabalance Problem
  • Patient Overlap
  • Explore Evaluation Metrics

• Data Processing

  • Data Preprocessing
  • Image Processing
  • Image Data Generator and Loaders

• Mnist-D CNN Multiclass-Classifier

• Multi-label Multi-Output Classifier Subset

• Multi-label Multi-Output Classifier Main

• Transfer Learning

  • Densenet-121

• Model Evaluation

  • Subset Dataset
  • Full Dataset

• Local to Colab setup

📑 3. References

• [1. ] ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases
• [2. ] CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays [arXiv:1711.05225v3 [cs.CV] 25 Dec 2017]
• [3.] Densely Connected Convolutional Networks [arXiv:1608.06993v5 [cs.CV] 28 Jan 2018]
• [4.] Coursera - AI for medical Diagnosis
• [5.] Chest xray12 dataset problems : Single Radiologist Label Accuracy