Status : Verified
Personal Name | Dumbrique, Jakov Ivan Savellano |
---|---|
Resource Title | A Machine Learning System for Pneumothorax Detection and Segmentation from Chest X-ray Radiographs using a Patch-based Fully Convolutional Encoder-Decoder Network |
Date Issued | 18 November 2024 |
Abstract | Pneumothorax, a life-threatening condition characterized by air accumulation in the pleural cavity, requires early and accurate detection for optimal patient outcomes. Chest X-ray radiographs are a common diagnostic tool due to their speed and affordability. However, detecting pneumothorax can be challenging for radiologists because the sole visual indicator is often a thin displaced pleural line. This research addresses this challenge by developing an end-to-end machine learning system for real-time chest X-ray radiograph analysis. Users can upload chest X-ray radiographs to our system and receive instant predictions from our novel deep learning architecture. This architecture combines the advantages of fully convolutional neural networks (FCNNs) and Vision Transformers (ViTs) while using only convolutional modules to avoid the quadratic complexity of ViT's self-attention mechanism. It utilizes a patch-based encoder-decoder structure with skip connections to effectively combine high-level and low-level features. Compared to prior research and baseline FCNNs, our model demonstrates significantly higher accuracy in detection and segmentation while maintaining computational efficiency. This is evident on two datasets: (1) the SIIM-ACR Pneumothorax Segmentation dataset and (2) a novel dataset we curated from The Medical City, a private hospital in the Philippines. Ablation studies further reveal that using a mixed Tversky and Focal loss function significantly improves performance compared to using solely the Tversky loss. Our findings suggest our model has the potential to improve diagnostic accuracy and efficiency in pneumothorax detection, potentially aiding radiologists in clinical settings. |
Degree Course | Master of Science in Computer Science |
Language | English |
Keyword | pneumothorax, automatic image segmentation, deep learning, convolutional neural network, Vision Transformer, lung pathology detection, chest X-rays, diagnostic radiology, machine learning system |
Material Type | Thesis/Dissertation |
Preliminary Pages
Category : I - Has patentable or registrable invention of creation.
Access Permission : Limited Access