- P. K. P. Sandamal and G. R. Perera · ICTAR, AI and Data Science Synergy track
Enhancing Lung Cancer Diagnosis with a Custom-Designed Convolutional Neural Network
A custom CNN for classifying lung CT scans, built to be smaller and faster to train than established pre-trained models. It reached 98.55% accuracy against 97.67% for ResNet50 and 66.15% for VGG16. Data came from Kaggle and Teaching Hospital Anuradhapura, balanced with SMOTE and augmentation, and evaluated by cross-validation on precision, recall and F1.
Read the paper
P. K. P. Sandamal and G. R. Perera · ICTAR, AI and Data Science Synergy track
Enhancing Lung Cancer Diagnosis with a Custom-Designed Convolutional Neural Network
A custom CNN for classifying lung CT scans, built to be smaller and faster to train than established pre-trained models. It reached 98.55% accuracy against 97.67% for ResNet50 and 66.15% for VGG16. Data came from Kaggle and Teaching Hospital Anuradhapura, balanced with SMOTE and augmentation, and evaluated by cross-validation on precision, recall and F1.
Read the paperRead the paper
Enhancing Lung Cancer Diagnosis with a Custom-Designed Convolutional Neural NetworkICTAR 2024 · International Conference on Transformative Applied ResearchPage 1 of 5
How the models compared
98.55%
Custom CNN
97.67%
ResNet50
66.15%
VGG16