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

Role of dietary patterns and inter-meal intervals in hypopharyngeal cancer: A case-control study from Assam, India.

The Indian journal of medical research·2026
Same author

Tryptanthrin: Synthetic advances and therapeutic horizons of a privileged scaffold.

European journal of medicinal chemistry·2026
Same author

Smartphone-Based Oral Lesion Image Segmentation Using Deep Learning.

Journal of imaging informatics in medicine·2025
Same author

Deep learning for early diagnosis of oral cancer via smartphone and DSLR image analysis: a systematic review.

Expert review of medical devices·2024
Same author

"A rare case of bladder myiasis mimicking radiation cystitis-A first case report".

Clinical case reports·2024
Same author

Handloomed fabrics recognition with deep learning.

Scientific reports·2024

Related Experiment Video

Updated: Jan 8, 2026

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

747

An Interpretable Hybrid AI Model for Breast Fine Needle Aspiration Cytology Image Classification.

Manjula Kalita1, Lipi B Mahanta2, Anup Kumar Das3

  • 1Department of Computer Science & Engineering, Girijananda Chowdhury University, Guwahati, India.

Journal of Medical Systems
|December 11, 2025
PubMed
Summary

A new hybrid AI model combining deep learning and machine learning significantly improves breast cancer detection from fine needle aspiration cytology images. This AI tool achieves high accuracy and sensitivity, aiding pathologists in diagnosis.

Keywords:
Breast cancer detectionDeep learningExplainable AIFine needle aspiration cytologyHybrid architecture

More Related Videos

X-ray Visualization of Intraductal Ethanol-based Ablative Infusion for Prevention of Breast Cancer in Rabbit Models
08:16

X-ray Visualization of Intraductal Ethanol-based Ablative Infusion for Prevention of Breast Cancer in Rabbit Models

Published on: September 12, 2025

791
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

8.6K

Related Experiment Videos

Last Updated: Jan 8, 2026

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

747
X-ray Visualization of Intraductal Ethanol-based Ablative Infusion for Prevention of Breast Cancer in Rabbit Models
08:16

X-ray Visualization of Intraductal Ethanol-based Ablative Infusion for Prevention of Breast Cancer in Rabbit Models

Published on: September 12, 2025

791
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

8.6K

Area of Science:

  • Oncology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Fine needle aspiration cytology (FNAC) is a valuable diagnostic tool for breast lesions, often surpassing mammography in accuracy for breast cancer prediction.
  • Deep learning and classical machine learning offer advanced methods for enhancing diagnostic accuracy in medical imaging.
  • Hybrid approaches combining deep learning feature extraction with machine learning classification show promise for complex diagnostic tasks.

Purpose of the Study:

  • To develop and evaluate hybrid deep learning and machine learning models for binary classification of breast fine needle aspiration cytology images.
  • To assess the performance of various hybrid architectures in terms of accuracy, sensitivity, and specificity for breast cancer detection.
  • To validate the clinical interpretability and trustworthiness of the best-performing model using expert pathologist review.

Main Methods:

  • Eighteen hybrid architectures were developed, integrating deep learning models (Inception-V3, MobileNet-V2, DenseNet-121) for feature extraction with machine learning classifiers (SVM, Decision Tree, k-NN).
  • A dataset of 427 FNAC images was augmented to 2,866 images, comprising benign and malignant samples.
  • The Grad-CAM technique was employed for model explainability and clinical validation by expert pathologists.

Main Results:

  • The hybrid model combining MobileNet-V2 and DenseNet-121 feature extraction with an SVM classifier achieved the highest internal test accuracy (98.26%).
  • This top-performing model demonstrated superior sensitivity (97.95%) and specificity (98.48%).
  • The explainability model achieved 95% positive clinical validation from expert pathologists, confirming its interpretability and clinical utility.

Conclusions:

  • Hybrid AI models integrating deep learning and machine learning offer a powerful approach for accurate breast cancer detection using FNAC images.
  • The proposed hybrid model demonstrates high diagnostic performance and clinical interpretability, supporting its potential for clinical decision-making.
  • Explainable AI methods are crucial for building trust and facilitating the adoption of AI tools in clinical practice.