Supervisor

Kislay Raj

Programme

MSc in Data Analytics

Subject

Computer Science

Abstract

Chest radiography (CXR) is the primary imaging tool for respiratory diseases, but interpretation can be time-consuming and requires expertise. This study compares a small custom CNN (Victorio) with three transfer-learning models (MobileNetV2, EfficientNet-B0, ResNet-50) for three-class CXR classification (normal, pneumonia, tuberculosis) and evaluates deployment on a Kubernetes cluster. Using a balanced dataset of ~13,500 CXRs, models were trained with ImageNet pre-training and from scratch. Transfer-learning models achieved near-perfect accuracy (99–100%) and AUROC, while the custom CNN reached 87–91%. Explainability analyses confirmed models focused on relevant pulmonary regions. Kubernetes deployment showed low latency, with most delays due to service overhead rather than computation. Findings indicate transfer-learning CNNs offer superior diagnostic performance without prohibitive deployment costs, supporting their practical use in clinical settings.

Date of Award

2025

Full Publication Date

2025

Access Rights

open access

Document Type

Capstone Project

Resource Type

thesis

Included in

Data Science Commons

Share

COinS