An explainable AI-driven deep neural network for accurate breast cancer detection from histopathological and ultrasound images
Abstract Breast cancer represents a significant global health challenge, which makes it essential to detect breast cancer early and accurately to improve patient prognosis and reduce mortality rates. However, traditional diagnostic processes relying on manual analysis of medical images are inherentl...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-97718-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849731046439911424 |
|---|---|
| author | Md. Romzan Alom Fahmid Al Farid Muhammad Aminur Rahaman Anichur Rahman Tanoy Debnath Abu Saleh Musa Miah Sarina Mansor |
| author_facet | Md. Romzan Alom Fahmid Al Farid Muhammad Aminur Rahaman Anichur Rahman Tanoy Debnath Abu Saleh Musa Miah Sarina Mansor |
| author_sort | Md. Romzan Alom |
| collection | DOAJ |
| description | Abstract Breast cancer represents a significant global health challenge, which makes it essential to detect breast cancer early and accurately to improve patient prognosis and reduce mortality rates. However, traditional diagnostic processes relying on manual analysis of medical images are inherently complex and subject to variability between observers, highlighting the urgent need for robust automated breast cancer detection systems. While deep learning has demonstrated potential, many current models struggle with limited accuracy and lack of interpretability. This research introduces the Deep Neural Breast Cancer Detection (DNBCD) model, an explainable AI-based framework that utilizes deep learning methods for classifying breast cancer using histopathological and ultrasound images. The proposed model employs Densenet121 as a foundation, integrating customized Convolutional Neural Network (CNN) layers including GlobalAveragePooling2D, Dense, and Dropout layers along with transfer learning to achieve both high accuracy and interpretability for breast cancer diagnosis. The proposed DNBCD model integrates several preprocessing techniques, including image normalization and resizing, and augmentation techniques to enhance the model’s robustness and address class imbalances using class weight. It employs Grad-CAM (Gradient-weighted Class Activation Mapping) to offer visual justifications for its predictions, increasing trust and transparency among healthcare providers. The model was assessed using two benchmark datasets: Breakhis-400x (B-400x) and Breast Ultrasound Images Dataset (BUSI) containing 1820 and 1578 images, respectively. We systematically divided the datasets into training (70%), testing (20%,) and validation (10%) sets, ensuring efficient model training and evaluation obtaining accuracies of 93.97% for B-400x dataset having benign and malignant classes and 89.87% for BUSI dataset having benign, malignant, and normal classes for breast cancer detection. Experimental results demonstrate that the proposed DNBCD model significantly outperforms existing state-of-the-art approaches with potential uses in clinical environments. We also made all the materials publicly accessible for the research community at: https://github.com/romzanalom/XAI-Based-Deep-Neural-Breast-Cancer-Detection . |
| format | Article |
| id | doaj-art-aac58c82935a4b96b5e39789e29cbcbc |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-aac58c82935a4b96b5e39789e29cbcbc2025-08-20T03:08:40ZengNature PortfolioScientific Reports2045-23222025-05-0115113410.1038/s41598-025-97718-5An explainable AI-driven deep neural network for accurate breast cancer detection from histopathological and ultrasound imagesMd. Romzan Alom0Fahmid Al Farid1Muhammad Aminur Rahaman2Anichur Rahman3Tanoy Debnath4Abu Saleh Musa Miah5Sarina Mansor6Department of Computer Science and Engineering, Green University of Bangladesh (GUB)Faculty of Artificial Intelligence and Engineering, Multimedia UniversityDepartment of Computer Science and Engineering, Green University of Bangladesh (GUB)Department of Computer Science and Engineering, National Institute of Textile Engineering and Research (NITER), Constituent Institute of the University of DhakaDepartment of Computer Science, Stony Brook UniversityDepartment of Computer Science and Engineering, Bangladesh Army University of Science and Technology (BAUST)Faculty of Artificial Intelligence and Engineering, Multimedia UniversityAbstract Breast cancer represents a significant global health challenge, which makes it essential to detect breast cancer early and accurately to improve patient prognosis and reduce mortality rates. However, traditional diagnostic processes relying on manual analysis of medical images are inherently complex and subject to variability between observers, highlighting the urgent need for robust automated breast cancer detection systems. While deep learning has demonstrated potential, many current models struggle with limited accuracy and lack of interpretability. This research introduces the Deep Neural Breast Cancer Detection (DNBCD) model, an explainable AI-based framework that utilizes deep learning methods for classifying breast cancer using histopathological and ultrasound images. The proposed model employs Densenet121 as a foundation, integrating customized Convolutional Neural Network (CNN) layers including GlobalAveragePooling2D, Dense, and Dropout layers along with transfer learning to achieve both high accuracy and interpretability for breast cancer diagnosis. The proposed DNBCD model integrates several preprocessing techniques, including image normalization and resizing, and augmentation techniques to enhance the model’s robustness and address class imbalances using class weight. It employs Grad-CAM (Gradient-weighted Class Activation Mapping) to offer visual justifications for its predictions, increasing trust and transparency among healthcare providers. The model was assessed using two benchmark datasets: Breakhis-400x (B-400x) and Breast Ultrasound Images Dataset (BUSI) containing 1820 and 1578 images, respectively. We systematically divided the datasets into training (70%), testing (20%,) and validation (10%) sets, ensuring efficient model training and evaluation obtaining accuracies of 93.97% for B-400x dataset having benign and malignant classes and 89.87% for BUSI dataset having benign, malignant, and normal classes for breast cancer detection. Experimental results demonstrate that the proposed DNBCD model significantly outperforms existing state-of-the-art approaches with potential uses in clinical environments. We also made all the materials publicly accessible for the research community at: https://github.com/romzanalom/XAI-Based-Deep-Neural-Breast-Cancer-Detection .https://doi.org/10.1038/s41598-025-97718-5Breast cancerXAIDNBCDCNNTransfer learningBreakhis-400x |
| spellingShingle | Md. Romzan Alom Fahmid Al Farid Muhammad Aminur Rahaman Anichur Rahman Tanoy Debnath Abu Saleh Musa Miah Sarina Mansor An explainable AI-driven deep neural network for accurate breast cancer detection from histopathological and ultrasound images Scientific Reports Breast cancer XAI DNBCD CNN Transfer learning Breakhis-400x |
| title | An explainable AI-driven deep neural network for accurate breast cancer detection from histopathological and ultrasound images |
| title_full | An explainable AI-driven deep neural network for accurate breast cancer detection from histopathological and ultrasound images |
| title_fullStr | An explainable AI-driven deep neural network for accurate breast cancer detection from histopathological and ultrasound images |
| title_full_unstemmed | An explainable AI-driven deep neural network for accurate breast cancer detection from histopathological and ultrasound images |
| title_short | An explainable AI-driven deep neural network for accurate breast cancer detection from histopathological and ultrasound images |
| title_sort | explainable ai driven deep neural network for accurate breast cancer detection from histopathological and ultrasound images |
| topic | Breast cancer XAI DNBCD CNN Transfer learning Breakhis-400x |
| url | https://doi.org/10.1038/s41598-025-97718-5 |
| work_keys_str_mv | AT mdromzanalom anexplainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages AT fahmidalfarid anexplainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages AT muhammadaminurrahaman anexplainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages AT anichurrahman anexplainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages AT tanoydebnath anexplainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages AT abusalehmusamiah anexplainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages AT sarinamansor anexplainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages AT mdromzanalom explainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages AT fahmidalfarid explainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages AT muhammadaminurrahaman explainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages AT anichurrahman explainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages AT tanoydebnath explainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages AT abusalehmusamiah explainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages AT sarinamansor explainableaidrivendeepneuralnetworkforaccuratebreastcancerdetectionfromhistopathologicalandultrasoundimages |