Use Deep Learning model to diagnose 14 pathologies on Chest X-Ray and use GradCAM Model Interpretation Method

COVID-19 Detection Using Chest X-Ray

Classification and Gradient-based Localization of Chest Radiographs using PyTorch.

This project utilizes a sophisticated deep learning model trained to classify breast ultrasound images into three categories: benign, malignant, or normal, thus determining the presence of breast cancer.

Image classification on Satellite Dataset-RSI-CB256 with torchvision models.

Models Supported: DenseNet121, DenseNet161, DenseNet169, DenseNet201 and DenseNet264 (1D and 2D version with DEMO for Classification and Regression)

Independent Research Project on Automatic Detection Of Lumpy Skin Disease Using Deep Learning Techniques.

Leveraging the recent advances in machine learning and availability of public medical imaging datasets, we created a Free Online X-Ray Diagnostic Tool using deep learning that can determine the X-ray type and visualize the pathology.

This research enhances early disease diagnosis by analyzing retinal blood vessels in fundus images using deep learning. It employs eight pre-trained CNN models and Explainable AI techniques.

Medical Images processing

Stack of REST APIs built on Flask for serving requests to MAMMORY (App), deployed on Azure with GitHub Actions (CI/CD)

A binary classification model for pneumonia detection from chest X-rays using transfer learning with DenseNet121, achieving high training accuracy (~95%) and demonstrating applicability of AI in medical diagnostics.

Employing Error Level Analysis (ELA) and Edge Detection techniques, this project aims to identify potential image forgery by analyzing discrepancies in error levels and abrupt intensity changes within images.

For Korean speech emotion detect, this model is trained by Korean dataset. There is no enough Korean dataset, so i tried to make this repo.

Ensemble based transfer learning approach for accurately classifying common thoracic diseases from Chest X-Rays

This repository is used to create Machine Learning models. Building three kinds of models that include covid detection, fruit and vegetable nutrition content, and general disease detection.

Using Pytorch Lightning and Torchxrayvision's Pretrained Densenet121 Models

Diabetic Foot Ulcer Classification using Deep Learning to classify Diabetic Foot Ulcer images and Healthy Skin images.

Building a powerful Neural network that can classify Natural Scenes around the world

Eye Disease Detection using Transfer Learning (DenseNet-121, EfficientNetB3, VGG-16, Resnet-152)

TensorFlow-Android 经典模型从理论到实战（微课视频版）

Densenet121 skin disease classification (PyTorch) + Streamlit demo

Multi-class HER2 IHC breast cancer classification using CNN and DenseNet121 with SHAP and Grad-CAM for model interpretability

Retinal disease detection using optical coherence tomography (OCT) and deep neural networks.

Innovation and Entrepreneurship Training Program for college students in 2019, ZengJin

Translating-Silence is a real-time sign language translator that uses computer vision and machine learning to convert Indian Sign Language (ISL) gestures into text. Designed for accessibility, it captures gestures via webcam and outputs live text, helping bridge communication gaps for the deaf and hard-of-hearing communities.

"Covid19-Detector" is a Django-ReactJS Web App with an Artificial Intelligence. It can detect COVID-19 from CT Scan Images using CNN based on DenseNet121 architecture.

oral_cancer_detection

deep learning models that detect the degrees of Alzheimer’s disease. applying various types of convolutional neural networks like SqueezeNet, DenseNet121 and VGG19 on ADNI dataset .

Multi-disease segmentation chest X-rays by YOLO and DenseNet121, CoAtNet models