Cargando…

Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP

Retinoblastoma is a rare and aggressive form of childhood eye cancer that requires prompt diagnosis and treatment to prevent vision loss and even death. Deep learning models have shown promising results in detecting retinoblastoma from fundus images, but their decision-making process is often consid...

Descripción completa

Detalles Bibliográficos
Autores principales: Aldughayfiq, Bader, Ashfaq, Farzeen, Jhanjhi, N. Z., Humayun, Mamoona
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10253103/
https://www.ncbi.nlm.nih.gov/pubmed/37296784
http://dx.doi.org/10.3390/diagnostics13111932
_version_ 1785056327609876480
author Aldughayfiq, Bader
Ashfaq, Farzeen
Jhanjhi, N. Z.
Humayun, Mamoona
author_facet Aldughayfiq, Bader
Ashfaq, Farzeen
Jhanjhi, N. Z.
Humayun, Mamoona
author_sort Aldughayfiq, Bader
collection PubMed
description Retinoblastoma is a rare and aggressive form of childhood eye cancer that requires prompt diagnosis and treatment to prevent vision loss and even death. Deep learning models have shown promising results in detecting retinoblastoma from fundus images, but their decision-making process is often considered a “black box” that lacks transparency and interpretability. In this project, we explore the use of LIME and SHAP, two popular explainable AI techniques, to generate local and global explanations for a deep learning model based on InceptionV3 architecture trained on retinoblastoma and non-retinoblastoma fundus images. We collected and labeled a dataset of 400 retinoblastoma and 400 non-retinoblastoma images, split it into training, validation, and test sets, and trained the model using transfer learning from the pre-trained InceptionV3 model. We then applied LIME and SHAP to generate explanations for the model’s predictions on the validation and test sets. Our results demonstrate that LIME and SHAP can effectively identify the regions and features in the input images that contribute the most to the model’s predictions, providing valuable insights into the decision-making process of the deep learning model. In addition, the use of InceptionV3 architecture with spatial attention mechanism achieved high accuracy of 97% on the test set, indicating the potential of combining deep learning and explainable AI for improving retinoblastoma diagnosis and treatment.
format Online
Article
Text
id pubmed-10253103
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-102531032023-06-10 Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP Aldughayfiq, Bader Ashfaq, Farzeen Jhanjhi, N. Z. Humayun, Mamoona Diagnostics (Basel) Article Retinoblastoma is a rare and aggressive form of childhood eye cancer that requires prompt diagnosis and treatment to prevent vision loss and even death. Deep learning models have shown promising results in detecting retinoblastoma from fundus images, but their decision-making process is often considered a “black box” that lacks transparency and interpretability. In this project, we explore the use of LIME and SHAP, two popular explainable AI techniques, to generate local and global explanations for a deep learning model based on InceptionV3 architecture trained on retinoblastoma and non-retinoblastoma fundus images. We collected and labeled a dataset of 400 retinoblastoma and 400 non-retinoblastoma images, split it into training, validation, and test sets, and trained the model using transfer learning from the pre-trained InceptionV3 model. We then applied LIME and SHAP to generate explanations for the model’s predictions on the validation and test sets. Our results demonstrate that LIME and SHAP can effectively identify the regions and features in the input images that contribute the most to the model’s predictions, providing valuable insights into the decision-making process of the deep learning model. In addition, the use of InceptionV3 architecture with spatial attention mechanism achieved high accuracy of 97% on the test set, indicating the potential of combining deep learning and explainable AI for improving retinoblastoma diagnosis and treatment. MDPI 2023-06-01 /pmc/articles/PMC10253103/ /pubmed/37296784 http://dx.doi.org/10.3390/diagnostics13111932 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Aldughayfiq, Bader
Ashfaq, Farzeen
Jhanjhi, N. Z.
Humayun, Mamoona
Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP
title Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP
title_full Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP
title_fullStr Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP
title_full_unstemmed Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP
title_short Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP
title_sort explainable ai for retinoblastoma diagnosis: interpreting deep learning models with lime and shap
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10253103/
https://www.ncbi.nlm.nih.gov/pubmed/37296784
http://dx.doi.org/10.3390/diagnostics13111932
work_keys_str_mv AT aldughayfiqbader explainableaiforretinoblastomadiagnosisinterpretingdeeplearningmodelswithlimeandshap
AT ashfaqfarzeen explainableaiforretinoblastomadiagnosisinterpretingdeeplearningmodelswithlimeandshap
AT jhanjhinz explainableaiforretinoblastomadiagnosisinterpretingdeeplearningmodelswithlimeandshap
AT humayunmamoona explainableaiforretinoblastomadiagnosisinterpretingdeeplearningmodelswithlimeandshap