Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Foundation-Model-Driven Skin Lesion Segmentation and Classification Using SAM-Adapters and Vision Transformers.

Diagnostics (Basel, Switzerland)·2026
Same author

TNFR-LSTM: A Deep Intelligent Model for Identification of Tumour Necroses Factor Receptor (TNFR) Activity.

IET systems biology·2025
Same author

InGSA: integrating generalized self-attention in CNN for Alzheimer's disease classification.

Frontiers in artificial intelligence·2025
Same author

eNSMBL-PASD: Spearheading early autism spectrum disorder detection through advanced genomic computational frameworks utilizing ensemble learning models.

Digital health·2025
Same author

Enhancing Cancerous Gene Selection and Classification for High-Dimensional Microarray Data Using a Novel Hybrid Filter and Differential Evolutionary Feature Selection.

Cancers·2024
Same author

Exploring the efficacy of GRU model in classifying the signal to noise ratio of microgrid model.

Scientific reports·2024
Same journal

Posterior capsule rupture with complete lens dislocation into the vitreous cavity caused by blunt trauma: a case report.

Frontiers in medicine·2026
Same journal

Case Report: Heparin resistance as the harbinger of heparin-induced thrombocytopenia in acute pulmonary embolism.

Frontiers in medicine·2026
Same journal

Trends and variation in use of end-tidal carbon dioxide during in-hospital cardiac arrest: an observational cohort study.

Frontiers in medicine·2026
Same journal

From virtual pregnancy to digital twin obstetrics: multimodal data integration for personalized prediction of pregnancy complications.

Frontiers in medicine·2026
Same journal

Immunotherapy with or without low-intensity chemotherapy versus conventional chemotherapy as first-line treatment for newly diagnosed B-ALL patients fit for intensive chemotherapy: a propensity score-matched study.

Frontiers in medicine·2026
Same journal

Hypertension and frailty in older adults: a bibliometric analysis and knowledge mapping based on Web of Science, Scopus, and PubMed (1973-2025).

Frontiers in medicine·2026
See all related articles

Related Experiment Video

Updated: Jun 27, 2025

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors
03:05

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

1.0K

Explainable AI-driven model for gastrointestinal cancer classification.

Faisal Binzagr1

  • 1Department of Computer Science, King Abdulaziz University, Rabigh, Saudi Arabia.

Frontiers in Medicine
|April 30, 2024
PubMed
Summary
This summary is machine-generated.

Explainable AI (XAI) enhances cancer cell detection by addressing the "black box" issue. Using SHAP with a hybrid CNN model on the KvasirV2 dataset achieved 93.17% accuracy, improving clinical trust.

Keywords:
SHAPensemble learningexplainable AIgastrointestinal cancertransfer learning

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
Intraoperative Gastroscopy for Tumor Localization in Laparoscopic Surgery for Gastric Adenocarcinoma
10:31

Intraoperative Gastroscopy for Tumor Localization in Laparoscopic Surgery for Gastric Adenocarcinoma

Published on: August 9, 2016

12.8K

Related Experiment Videos

Last Updated: Jun 27, 2025

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors
03:05

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

1.0K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
Intraoperative Gastroscopy for Tumor Localization in Laparoscopic Surgery for Gastric Adenocarcinoma
10:31

Intraoperative Gastroscopy for Tumor Localization in Laparoscopic Surgery for Gastric Adenocarcinoma

Published on: August 9, 2016

12.8K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computational Pathology

Background:

  • AI-assisted cancer cell detection faces clinical adoption challenges due to opaque decision-making processes.
  • Explainable Artificial Intelligence (XAI) is crucial for building trust by providing transparency in AI predictions.
  • The "black box" nature of AI hinders its integration into clinical workflows.

Purpose of the Study:

  • To enhance the interpretability of AI models for cancer cell detection using Explainable Artificial Intelligence (XAI).
  • To investigate the effectiveness of the SHapley Additive exPlanations (SHAP) method for explaining AI predictions in cancer pathology.
  • To develop and evaluate a hybrid deep learning model for accurate and explainable cancer cell detection.

Main Methods:

  • A hybrid deep learning model was developed, combining predictions from three Convolutional Neural Networks (CNNs): InceptionV3, InceptionResNetV2, and VGG16.
  • The model was trained on the KvasirV2 dataset, which contains pathological images indicative of cancer.
  • The SHapley Additive exPlanations (SHAP) technique was applied to interpret the predictions of the trained hybrid model.

Main Results:

  • The hybrid CNN model achieved a high accuracy of 93.17% and an F1 score of 97% in detecting cancer-related pathological symptoms.
  • SHAP analysis provided visual explanations for the model's predictions, highlighting image regions influencing the classification.
  • The study demonstrated the successful application of XAI to demystify the AI decision-making process in cancer cell detection.

Conclusions:

  • The integration of XAI, specifically SHAP, significantly improves the transparency and trustworthiness of AI-driven cancer detection systems.
  • Hybrid CNN models combined with XAI offer a robust approach for accurate and interpretable cancer cell detection in clinical settings.
  • This work addresses key barriers to AI adoption in healthcare by providing explainable predictions, fostering clinician confidence.