Inspired by a Kaggle dataset, this AI model predicts if an x-ray image shows pneumonia signs or not. The model was trained mainly using tensorflow and scikit-learn.

Use EuXFEL detector geometry to assemble images

DESKTOP data processing and visualization for the x-ray pixel cameras outputs ---> Python, Tkinter, Pandas, Numpy

"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024)

This project uses PyTorch to classify bone fractures. As well as fine-tuning some famous CNN architectures (like VGG 19, MobileNetV3, RegNet,...), we designed our own architecture. Additionally, we used Transformer architectures (such as Vision Transformer and Swin Transformer). This dataset is Bone Fracture Multi-Region X-ray, available on Kaggle.

List of datasets and papers in X-ray security images (Computer vision/Machine Learning)

automate the analysis of the modulation transfer function (MTF)

"Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis" (Arxir 2024)

XrayVision Benchmark: Benchmarking of X-ray Security Imaging Datasets

MTFKKU website

Capturing clinical structure of the spine from an X-Ray with a Python GUI.

Deep learning and segmentation in sex classification from left hand X-ray images in pediatric patients: how zero-shot Segment Anything Model (SAM) can improve medical image analysis

Pneumonia detection system using Convolutional Neural Networks (CNNs) on chest X-ray images. The project leverages the Xception pre-trained model and achieves an accuracy of 84.13%.

Bruker's TOPAS X-ray diffraction calculations parser

Convolutional networks for x-ray chest classification

Developed a model to predict bounding boxes around the heart in X-ray images using deep learning techniques.

Built a Convolutional Neural Network (CNN) model to classify X-ray images for pneumonia detection.

The preparation for the Lung X-Ray Mask Segmentation project included the use of augmentation methods like flipping to improve the dataset, along with measures to ensure data uniformity and quality. The model architecture was explored with two types of ResNets: the traditional CNN layers and Depthwise Separable.

A deep learning model that uses X-ray images of pediatric patients to identify whether or not they have pneumonia.