Advancement in Tuberculosis Detection Using Deep Learning Models
"Explore the state of advancement in tuberculosis detection presented by Manal Karmoude, including dataset distribution, preprocessing pipeline, class imbalance handling, ResNet model architectures, and performance evaluation using ResNet-34 and ResNet-18 models. Discover the application of CLAHE for enhanced image processing. Dive into the innovative techniques reshaping tuberculosis diagnosis and treatment. View visuals and insights into the latest advancements in the AI4TB project."
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
AI4TB State of Advancement Presented by : Manal Karmoude Submitted at : 19/12/2024
Dataset : Class Distribution: - Normal Cases: ? "These represent healthy individuals with no signs of tuberculosis." - Tuberculous Cases: 700 images "Images of individuals diagnosed with tuberculosis, highlighting areas of infection." 3,500 images
Dataset : Preprocessing Pipeline for Chest X-ray Dataset : Resizing: All images are resized to 224x224 to standardize input dimensions for the ResNet model. Normalization: Applied per-channel normalization with: Mean: [0.5, 0.5, 0.5] Standard Deviation: [0.5, 0.5, 0.5]
Dataset : Class Imbalance Handling: Class Weights: Normal: 1/3500 Tuberculous: 1/700
Model Architecture : Pretrained Model: Base Model: ResNet-34 Base Model : ResNet-18 Modified for Binary Classification: Final Fully Connected Layer adjusted to classify: Normal Tuberculous
Model ResNet34 : Batch Size Epochs Class Imbalance Validation Loss Validation Accuracy 32 10 Addressed using Class Weights (Normal: 1/3500, Tuberculous: 1/700) 0.0430 99.29%
Model ResNet18 : Batch Size Epochs Class Imbalance Validation Loss Validation Accuracy 32 10 Addressed using Class Weights (Normal: 1/3500, Tuberculous: 1/700) 0.0076 95.32%
Apply CLAHE (Contrast Limited Adaptive Histogram Equalization) :
