Multi-CNN Deep Feature Fusion and Stacking Ensemble Classifier for Breast Ultrasound Lesion Classification

Objective: To develop and validate a robust machine learning model for classifying breast ultrasound images into benign, malignant, and normal categories, aiming to enhance diagnostic accuracy using advanced feature extraction and ensemble learning techniques. Methods: A dataset comprising 2233 ima...

Full description

Saved in:
Bibliographic Details
Main Authors: Kemal PANÇ, Sümeyye SEKMEN
Format: Article
Language:English
Published: Galenos Yayinevi 2025-08-01
Series:Forbes Tıp Dergisi
Subjects:
Online Access:https://forbestip.org/articles/multi-cnn-deep-feature-fusion-and-stacking-ensemble-classifier-for-breast-ultrasound-lesion-classification/doi/forbes.galenos.2025.02360
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849393362253119488
author Kemal PANÇ
Sümeyye SEKMEN
author_facet Kemal PANÇ
Sümeyye SEKMEN
author_sort Kemal PANÇ
collection DOAJ
description Objective: To develop and validate a robust machine learning model for classifying breast ultrasound images into benign, malignant, and normal categories, aiming to enhance diagnostic accuracy using advanced feature extraction and ensemble learning techniques. Methods: A dataset comprising 2233 images from five public datasets was utilized. After masking regions of interest, deep features were extracted using pre-trained VGG16, ResNet50V2, and EfficientNetB3 models, and concatenated. A multi-step feature selection process involving principal component analysis, recursive feature elimination with LightGBM, and partial least squares discriminant analysis was applied. A stacking ensemble classifier, integrating LightGBM, XGBoost, CatBoost, and random forest with a logistic regression meta-learner, was trained using 5-fold cross-validation on a 75% training set (balanced with synthetic minority oversampling technique), and evaluated on a 25% test set. Results: The model achieved a macro average area under the curve-receiver operating characteristic (AUC-ROC) of 0.956 and an F1-score of 0.88 on the test set. Benign class results were AUC: 0.984, F1: 0.93, and normal class results were AUC: 0.969, F1: 0.92. The results for the malignant class were AUC: 0.916, F1 score: 0.79. Feature importance analysis showed that ResNet50V2 had the highest contribution to the model’s performance. Conclusion: The proposed approach, combining multi-convolutional neural network deep feature fusion, optimized feature selection, and ensemble stacking, shows significant potential for automated breast ultrasound classification, especially for benign and normal cases. While promising for clinical decision support, the model’s lower sensitivity for malignant lesions necessitates further refinement.
format Article
id doaj-art-e8985272ba2145c8a4e7eda635453067
institution Kabale University
issn 2757-5241
language English
publishDate 2025-08-01
publisher Galenos Yayinevi
record_format Article
series Forbes Tıp Dergisi
spelling doaj-art-e8985272ba2145c8a4e7eda6354530672025-08-20T03:40:26ZengGalenos YayineviForbes Tıp Dergisi2757-52412025-08-016214715510.4274/forbes.galenos.2025.02360Multi-CNN Deep Feature Fusion and Stacking Ensemble Classifier for Breast Ultrasound Lesion ClassificationKemal PANÇ0https://orcid.org/0000-0002-3951-7344Sümeyye SEKMEN1https://orcid.org/0000-0003-1609-6775Karakoçan State Hospital, Clinic of Radiology, Elazığ, TürkiyePatnos State Hospital, Clinic of Radiology, Ağrı, TürkiyeObjective: To develop and validate a robust machine learning model for classifying breast ultrasound images into benign, malignant, and normal categories, aiming to enhance diagnostic accuracy using advanced feature extraction and ensemble learning techniques. Methods: A dataset comprising 2233 images from five public datasets was utilized. After masking regions of interest, deep features were extracted using pre-trained VGG16, ResNet50V2, and EfficientNetB3 models, and concatenated. A multi-step feature selection process involving principal component analysis, recursive feature elimination with LightGBM, and partial least squares discriminant analysis was applied. A stacking ensemble classifier, integrating LightGBM, XGBoost, CatBoost, and random forest with a logistic regression meta-learner, was trained using 5-fold cross-validation on a 75% training set (balanced with synthetic minority oversampling technique), and evaluated on a 25% test set. Results: The model achieved a macro average area under the curve-receiver operating characteristic (AUC-ROC) of 0.956 and an F1-score of 0.88 on the test set. Benign class results were AUC: 0.984, F1: 0.93, and normal class results were AUC: 0.969, F1: 0.92. The results for the malignant class were AUC: 0.916, F1 score: 0.79. Feature importance analysis showed that ResNet50V2 had the highest contribution to the model’s performance. Conclusion: The proposed approach, combining multi-convolutional neural network deep feature fusion, optimized feature selection, and ensemble stacking, shows significant potential for automated breast ultrasound classification, especially for benign and normal cases. While promising for clinical decision support, the model’s lower sensitivity for malignant lesions necessitates further refinement.https://forbestip.org/articles/multi-cnn-deep-feature-fusion-and-stacking-ensemble-classifier-for-breast-ultrasound-lesion-classification/doi/forbes.galenos.2025.02360breast ultrasounddeep learningcomputer-aided diagnosisensemble learningimage classification
spellingShingle Kemal PANÇ
Sümeyye SEKMEN
Multi-CNN Deep Feature Fusion and Stacking Ensemble Classifier for Breast Ultrasound Lesion Classification
Forbes Tıp Dergisi
breast ultrasound
deep learning
computer-aided diagnosis
ensemble learning
image classification
title Multi-CNN Deep Feature Fusion and Stacking Ensemble Classifier for Breast Ultrasound Lesion Classification
title_full Multi-CNN Deep Feature Fusion and Stacking Ensemble Classifier for Breast Ultrasound Lesion Classification
title_fullStr Multi-CNN Deep Feature Fusion and Stacking Ensemble Classifier for Breast Ultrasound Lesion Classification
title_full_unstemmed Multi-CNN Deep Feature Fusion and Stacking Ensemble Classifier for Breast Ultrasound Lesion Classification
title_short Multi-CNN Deep Feature Fusion and Stacking Ensemble Classifier for Breast Ultrasound Lesion Classification
title_sort multi cnn deep feature fusion and stacking ensemble classifier for breast ultrasound lesion classification
topic breast ultrasound
deep learning
computer-aided diagnosis
ensemble learning
image classification
url https://forbestip.org/articles/multi-cnn-deep-feature-fusion-and-stacking-ensemble-classifier-for-breast-ultrasound-lesion-classification/doi/forbes.galenos.2025.02360
work_keys_str_mv AT kemalpanc multicnndeepfeaturefusionandstackingensembleclassifierforbreastultrasoundlesionclassification
AT sumeyyesekmen multicnndeepfeaturefusionandstackingensembleclassifierforbreastultrasoundlesionclassification