Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Apr 11, 2026

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

Explainable deep learning-based lung cancer diagnosis using clinically-guided local interpretable model-agnostic

Shahab Ul Hassan^1,2, Said Jadid Abdulkadir^3,4, Hitham Seddig Alhussian^3,4

¹Department of Computing, Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia. shahab_22009928@utp.edu.my.

Scientific Reports

|April 9, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Physics-informed gaussian process regression for reproducible and uncertainty-aware CO2 injectivity prediction.

PloS one·2026

Same author

Chaotic Lévy and adaptive restart enhance the Manta Ray foraging optimizer for gene feature selection.

Scientific reports·2025

Same author

Grad-CAM (Gradient-weighted Class Activation Mapping): A systematic literature review.

Computers in biology and medicine·2025

Same author

Periodontitis bone loss detection in panoramic radiographs using modified YOLOv7.

PeerJ. Computer science·2025

Same author

Enhancing fake news detection with transformer-based deep learning: A multidisciplinary approach.

PloS one·2025

Same author

Artificial intelligence-driven cybersecurity: enhancing malicious domain detection using attention-based deep learning model with optimization algorithms.

Scientific reports·2025

This study introduces adaptive superpixel local interpretable model-agnostic explanations (ASP-LIME) for deep learning in lung cancer detection. ASP-LIME provides accurate and interpretable insights into AI diagnostic decisions, enhancing clinical trust.

Area of Science:

Medical Imaging
Artificial Intelligence
Computational Pathology

Background:

Lung cancer is a leading cause of cancer deaths globally, necessitating improved diagnostic tools.
Deep learning (DL) models show promise in medical image classification but lack interpretability, hindering clinical use.

Purpose of the Study:

To develop a novel explanation framework, adaptive superpixel perturbation-based local interpretable model-agnostic explanations (ASP-LIME), for interpretable DL in lung cancer diagnosis.
To generate faithful and localized explanations for DL predictions in medical imaging.

Main Methods:

The study proposes ASP-LIME, enhancing the original LIME with adaptive superpixel segmentation, stratified perturbation, lung region masking, and post-processing.
A custom convolutional neural network, MedDeepNet, was developed for lung cancer classification.

Keywords:

Deep learning Explainable AI (XAI)LIME Lung cancer Medical imaging Visualization

Related Experiment Videos

Last Updated: Apr 11, 2026

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

The framework was evaluated on a public lung image dataset.

Main Results:

MedDeepNet achieved high performance: 99.84% accuracy, 99.66% recall, 99.82% precision, 99.74% specificity, and 99.74% F1-score.
ASP-LIME demonstrated high fidelity and localization, with deletion score 0.0300, insertion score 0.9622, and Area Between Perturbation Curves (ABPC) 0.9661.
The explanation method outperformed typical benchmarks for interpretability.

Conclusions:

The ASP-LIME framework provides consistent and interpretable explanations for DL models in medical imaging.
This enhances the understanding of AI decision-making processes, fostering clinical adoption of DL tools for lung cancer diagnosis.