Interpretability in AI for Early Lung Cancer Diagnosis: Fostering Confidence in Healthcare

Sukanya Walishetti, Subhasareddy Khot, Shreya Marihal, Prathmesh Kittur, Shantala Giraddi, Prema T. Akkasaligar

2025

Abstract

Lung cancer represents a significant cause of death, making early detection essential for better survival rates. Lung nodules, which are small tissue masses in the lungs, can be initial indicators of lung cancer but are often difficult to detect in chest X-rays due to their subtle appearance and potential overlap with normal anatomical features. Analyzing these images manually is both error-prone and inefficient, often leading to discrepancies. This research integrates convolutional neural networks (CNNs), specifically ResNet-18 and MobileNetV4, with explainable AI techniques such as Grad-CAM to overcome these challenges. The ResNet-18 model demonstrates high accuracy in nodule classification, while MobileNetV4 also shows strong performance, highlighting the potential of deep learning in this area. Grad-CAM is used to provide interpretability by visually highlighting the regions of chest X-rays that influence the model’s predictions. This transparency is essential for gaining trust from medical professionals, as it addresses the clinical need for accountability and supports more informed diagnostic decisions.

Paper Citation

in Harvard Style

Walishetti S., Khot S., Marihal S., Kittur P., Giraddi S. and Akkasaligar P. (2025). Interpretability in AI for Early Lung Cancer Diagnosis: Fostering Confidence in Healthcare. In Proceedings of the 3rd International Conference on Futuristic Technology - Volume 3: INCOFT; ISBN 978-989-758-763-4, SciTePress, pages 143-151. DOI: 10.5220/0013610300004664

in Bibtex Style

@conference{incoft25,
author={Sukanya Walishetti and Subhasareddy Khot and Shreya Marihal and Prathmesh Kittur and Shantala Giraddi and Prema T. Akkasaligar},
title={Interpretability in AI for Early Lung Cancer Diagnosis: Fostering Confidence in Healthcare},
booktitle={Proceedings of the 3rd International Conference on Futuristic Technology - Volume 3: INCOFT},
year={2025},
pages={143-151},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013610300004664},
isbn={978-989-758-763-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Futuristic Technology - Volume 3: INCOFT
TI - Interpretability in AI for Early Lung Cancer Diagnosis: Fostering Confidence in Healthcare
SN - 978-989-758-763-4
AU - Walishetti S.
AU - Khot S.
AU - Marihal S.
AU - Kittur P.
AU - Giraddi S.
AU - Akkasaligar P.
PY - 2025
SP - 143
EP - 151
DO - 10.5220/0013610300004664
PB - SciTePress