Research Article
From Black-Box to Explainability: Advancing AI in Lung Cancer Detection with Robust XAI Methods
@INPROCEEDINGS{10.4108/eai.19-12-2025.2366243, author={Rashmi Ranga and Ashish Girdhar}, title={From Black-Box to Explainability: Advancing AI in Lung Cancer Detection with Robust XAI Methods}, proceedings={Proceedings of the 1st International Conference on Computational Techniques in Data Science, IICTDS 2025, 19-20 December 2025, Chandigarh, India}, publisher={EAI}, proceedings_a={IICTDS}, year={2026}, month={11}, keywords={Lung cancer Artificial intelligence Machine learning Explainable AI Medical imaging}, doi={10.4108/eai.19-12-2025.2366243} }- Rashmi Ranga
Ashish Girdhar
Year: 2026
From Black-Box to Explainability: Advancing AI in Lung Cancer Detection with Robust XAI Methods
IICTDS
EAI
DOI: 10.4108/eai.19-12-2025.2366243
Abstract
Explainable Artificial Intelligence or XAI aims to improve the interpretability and transparency of AI systems and in particular deep learning models which can be explained in terms of their reasoning. The proposed study is aimed at exploring the ways XAI can be used to identify lung cancer and establish the trust of doctors due to increased transparency. It discusses various XAI techniques deployed in medical imaging and compares them with the traditional black-box AI models. The paper focuses on the issues with the existing XAI methods and highlights the necessity to enhance deep learning models with the interpretability tools. In addition, the paper highlights the importance of designing dynamic, user-friendly interfaces and standardizing frameworks which could be used to evaluate the quality and usability of AI explanations in clinical practice. In general, XAI progress is highly promising in developing explainable lung cancer diagnostic systems that can improve early detection.