Wilfrid Laurier University
TaylorKAN-ViT: Parameter-Efficient Vision Transformers for Medical Image Classification
Abstract
dc:descriptionEffective and interpretable classification of medical images remains a critical challenge in computer-aided diagnosis, particularly in data-scarce and resource-constrained clinical settings where traditional deep learning models prove impractical. This study addresses the fundamental barrier to Vision Transformer adoption in medical imaging—massive parameter counts and data requirements—through a systematic two-phase methodology. Phase 1 evaluates three spline-based Kolmogorov–Arnold Network (KAN) variants to identify the optimal nonlinear approximation function for parameter-efficient medical image classification: SBTAYLOR-KAN (B-splines with Taylor series), SBRBF-KAN (B-splines with Radial Basis Functions), and SBWAVELET-KAN (B-splines with Morlet wavelets). Comprehensive experiments across brain MRI, chest X-rays, and tuberculosis datasets—without any image preprocessing beyond the datasets' original published forms—establish SBTAYLOR-KAN as the superior architecture, achieving up to 98.93% accuracy with only 2,872 parameters (>99% reduction versus ResNet50's ~24.18M) while maintaining 86% accuracy using merely 30% training data. Statistical validation through kappa coefficients, Matthews correlation, and cross-dataset generalization confirms its robustness and data efficiency. Building directly on these findings, Phase 2 integrates the optimal Taylor-KAN formulation into a Vision Transformer architecture, yielding TaylorKAN-ViT—an ultra-compact model that fundamentally reimagines efficient transformer design through a KAN-first approach. Unlike conventional ViTs that retrofit parameter reduction techniques while retaining MLP-heavy architectures, TaylorKAN-ViT replaces all nonlinear feed-forward mappings with the Taylor-series-approximated KAN modules identified in Phase 1. This enables dual-scale feature learning: KAN transformations capture fine-grained local patterns within image patches, while self-attention mechanisms model long-range global dependencies across the entire image. Despite comprising only 88.9K parameters and 4.9G FLOPs—representing ~99.3% parameter reduction compared to recent medical ViTs (MedKAFormer-T: 12.47M, MedViTV2-T: 12.3M)—TaylorKAN-ViT achieves competitive performance across four diverse benchmarks: 94.36% accuracy on PneumoniaMNIST, 95.90% on CPNX-ray, 61.00% on PAD-UFES-20, and 70.50% on Kvasir. The model demonstrates stable generalization even under limited-data and class-imbalanced conditions. These results demonstrate that clinical-grade medical image classification is achievable without large-scale models, establishing TaylorKAN-ViT as a practical, deployable solution for edge devices, mobile platforms, and resource-limited healthcare environments.
Degree
thesis:*- Name thesis:degree_name
- Master of Applied Computing
- Discipline thesis:degree_discipline
- Physics and Computer Science
- Grantor dc:publisher
- Wilfrid Laurier University
- Year dc:date.available
- 2026
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Fatema, Kaniz
- Mohammed, Dr. Emad
- Sehra, Dr. Sukhjit Singh
- Contributors dc:contributor
-
- Dr. Emad Mohammed
- Dr. Sukhjit Singh Sehra
Subjects
dc:subject × 9Rights
dc:rights- Statement dc:rights
-
- 2 Publicly accessible
- Language dc:language
- en
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://scholars.wlu.ca/etd/2901