1
|
Hernández-Vázquez MA, Hernández-Rodríguez YM, Cortes-Rojas FD, Bayareh-Mancilla R, Cigarroa-Mayorga OE. Hybrid Feature Mammogram Analysis: Detecting and Localizing Microcalcifications Combining Gabor, Prewitt, GLCM Features, and Top Hat Filtering Enhanced with CNN Architecture. Diagnostics (Basel) 2024; 14:1691. [PMID: 39125567 PMCID: PMC11311263 DOI: 10.3390/diagnostics14151691] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2024] [Revised: 07/31/2024] [Accepted: 08/01/2024] [Indexed: 08/12/2024] Open
Abstract
Breast cancer is a prevalent malignancy characterized by the uncontrolled growth of glandular epithelial cells, which can metastasize through the blood and lymphatic systems. Microcalcifications, small calcium deposits within breast tissue, are critical markers for early detection of breast cancer, especially in non-palpable carcinomas. These microcalcifications, appearing as small white spots on mammograms, are challenging to identify due to potential confusion with other tissues. This study hypothesizes that a hybrid feature extraction approach combined with Convolutional Neural Networks (CNNs) can significantly enhance the detection and localization of microcalcifications in mammograms. The proposed algorithm employs Gabor, Prewitt, and Gray Level Co-occurrence Matrix (GLCM) kernels for feature extraction. These features are input to a CNN architecture designed with maxpooling layers, Rectified Linear Unit (ReLU) activation functions, and a sigmoid response for binary classification. Additionally, the Top Hat filter is used for precise localization of microcalcifications. The preprocessing stage includes enhancing contrast using the Volume of Interest Look-Up Table (VOI LUT) technique and segmenting regions of interest. The CNN architecture comprises three convolutional layers, three ReLU layers, and three maxpooling layers. The training was conducted using a balanced dataset of digital mammograms, with the Adam optimizer and binary cross-entropy loss function. Our method achieved an accuracy of 89.56%, a sensitivity of 82.14%, and a specificity of 91.47%, outperforming related works, which typically report accuracies around 85-87% and sensitivities between 76 and 81%. These results underscore the potential of combining traditional feature extraction techniques with deep learning models to improve the detection and localization of microcalcifications. This system may serve as an auxiliary tool for radiologists, enhancing early detection capabilities and potentially reducing diagnostic errors in mass screening programs.
Collapse
Affiliation(s)
- Miguel Alejandro Hernández-Vázquez
- Departamento de Tecnologías Avanzadas, UPIITA-Instituto Politécnico Nacional, Av. Instituto Politécnico Nacional 2580, Ciudad de México 07340, Mexico (Y.M.H.-R.)
| | - Yazmín Mariela Hernández-Rodríguez
- Departamento de Tecnologías Avanzadas, UPIITA-Instituto Politécnico Nacional, Av. Instituto Politécnico Nacional 2580, Ciudad de México 07340, Mexico (Y.M.H.-R.)
| | - Fausto David Cortes-Rojas
- Departamento de Ingeniería Eléctrica/Sección de Bioelectrónica, Centro de Investigación y de Estudios Avanzados del IPN, Av. Instituto Politécnico Nacional 2508, Col. San Pedro Zacatenco, Gustavo A. Madero, Ciudad de México 07360, Mexico;
| | - Rafael Bayareh-Mancilla
- Departamento de Tecnologías Avanzadas, UPIITA-Instituto Politécnico Nacional, Av. Instituto Politécnico Nacional 2580, Ciudad de México 07340, Mexico (Y.M.H.-R.)
| | - Oscar Eduardo Cigarroa-Mayorga
- Departamento de Tecnologías Avanzadas, UPIITA-Instituto Politécnico Nacional, Av. Instituto Politécnico Nacional 2580, Ciudad de México 07340, Mexico (Y.M.H.-R.)
| |
Collapse
|
2
|
Bobowicz M, Rygusik M, Buler J, Buler R, Ferlin M, Kwasigroch A, Szurowska E, Grochowski M. Attention-Based Deep Learning System for Classification of Breast Lesions-Multimodal, Weakly Supervised Approach. Cancers (Basel) 2023; 15:2704. [PMID: 37345041 DOI: 10.3390/cancers15102704] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2023] [Revised: 05/02/2023] [Accepted: 05/05/2023] [Indexed: 06/23/2023] Open
Abstract
Breast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering-constrained Attention Multiple Instance Learning (CLAM) classifier able to train under data scarcity effectively. We used a private dataset with 1174 non-cancer and 794 cancer images labelled at the image level with pathological ground truth confirmation. We used feature extractors (ResNet-18, ResNet-34, ResNet-50 and EfficientNet-B0) pre-trained on ImageNet. The best results were achieved with multimodal-view classification using both CC and MLO images simultaneously, resized by half, with a patch size of 224 px and an overlap of 0.25. It resulted in AUC-ROC = 0.896 ± 0.017, F1-score 81.8 ± 3.2, accuracy 81.6 ± 3.2, precision 82.4 ± 3.3, and recall 81.6 ± 3.2. Evaluation with the Chinese Mammography Database, with 5-fold cross-validation, patient-wise breakdowns, and transfer learning, resulted in AUC-ROC 0.848 ± 0.015, F1-score 78.6 ± 2.0, accuracy 78.4 ± 1.9, precision 78.8 ± 2.0, and recall 78.4 ± 1.9. The CLAM algorithm's attentional maps indicate the features most relevant to the algorithm in the images. Our approach was more effective than in many other studies, allowing for some explainability and identifying erroneous predictions based on the wrong premises.
Collapse
Affiliation(s)
- Maciej Bobowicz
- 2nd Department of Radiology, Medical University of Gdansk, 80-214 Gdansk, Poland
| | - Marlena Rygusik
- 2nd Department of Radiology, Medical University of Gdansk, 80-214 Gdansk, Poland
| | - Jakub Buler
- Department of Intelligent Control Systems and Decision Support, Faculty of Electrical and Control Engineering, Gdansk University of Technology, 80-233 Gdansk, Poland
| | - Rafał Buler
- Department of Intelligent Control Systems and Decision Support, Faculty of Electrical and Control Engineering, Gdansk University of Technology, 80-233 Gdansk, Poland
| | - Maria Ferlin
- Department of Intelligent Control Systems and Decision Support, Faculty of Electrical and Control Engineering, Gdansk University of Technology, 80-233 Gdansk, Poland
| | - Arkadiusz Kwasigroch
- Department of Intelligent Control Systems and Decision Support, Faculty of Electrical and Control Engineering, Gdansk University of Technology, 80-233 Gdansk, Poland
| | - Edyta Szurowska
- 2nd Department of Radiology, Medical University of Gdansk, 80-214 Gdansk, Poland
| | - Michał Grochowski
- Department of Intelligent Control Systems and Decision Support, Faculty of Electrical and Control Engineering, Gdansk University of Technology, 80-233 Gdansk, Poland
| |
Collapse
|
3
|
Praveen SP, Srinivasu PN, Shafi J, Wozniak M, Ijaz MF. ResNet-32 and FastAI for diagnoses of ductal carcinoma from 2D tissue slides. Sci Rep 2022; 12:20804. [PMID: 36460697 PMCID: PMC9716161 DOI: 10.1038/s41598-022-25089-2] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2022] [Accepted: 11/23/2022] [Indexed: 12/03/2022] Open
Abstract
Carcinoma is a primary source of morbidity in women globally, with metastatic disease accounting for most deaths. Its early discovery and diagnosis may significantly increase the odds of survival. Breast cancer imaging is critical for early identification, clinical staging, management choices, and treatment planning. In the current study, the FastAI technology is used with the ResNet-32 model to precisely identify ductal carcinoma. ResNet-32 is having few layers comparted to majority of its counterparts with almost identical performance. FastAI offers a rapid approximation toward the outcome for deep learning models via GPU acceleration and a faster callback mechanism, which would result in faster execution of the model with lesser code and yield better precision in classifying the tissue slides. Residual Network (ResNet) is proven to handle the vanishing gradient and effective feature learning better. Integration of two computationally efficient technologies has yielded a precision accuracy with reasonable computational efforts. The proposed model has shown considerable efficiency in the evaluating parameters like sensitivity, specificity, accuracy, and F1 Score against the other dominantly used deep learning models. These insights have shown that the proposed approach might assist practitioners in analyzing Breast Cancer (BC) cases appropriately, perhaps saving future complications and death. Clinical and pathological analysis and predictive accuracy have been improved with digital image processing.
Collapse
Affiliation(s)
- S Phani Praveen
- Department of Computer Science and Engineering, Prasad V Potluri Siddhartha Institute of Technology, Vijayawada, 520007, India
| | - Parvathaneni Naga Srinivasu
- Department of Computer Science and Engineering, Prasad V Potluri Siddhartha Institute of Technology, Vijayawada, 520007, India
| | - Jana Shafi
- Department of Computer Science, College of Arts and Science, Prince Sattam bin Abdul Aziz University, Wadi Ad-Dawasir, 11991, Saudi Arabia
| | - Marcin Wozniak
- Faculty of Applied Mathematics, Silesian University of Technology, 44-100, Gliwice, Poland.
| | - Muhammad Fazal Ijaz
- Department of Mechanical Engineering, Faculty of Engineering and Information Technology, The University of Melbourne, Grattam Street, Parkville, VIC, 3010, Australia.
| |
Collapse
|
4
|
Arooj S, Atta-ur-Rahman, Zubair M, Khan MF, Alissa K, Khan MA, Mosavi A. Breast Cancer Detection and Classification Empowered With Transfer Learning. Front Public Health 2022; 10:924432. [PMID: 35859776 PMCID: PMC9289190 DOI: 10.3389/fpubh.2022.924432] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2022] [Accepted: 05/31/2022] [Indexed: 11/29/2022] Open
Abstract
Cancer is a major public health issue in the modern world. Breast cancer is a type of cancer that starts in the breast and spreads to other parts of the body. One of the most common types of cancer that kill women is breast cancer. When cells become uncontrollably large, cancer develops. There are various types of breast cancer. The proposed model discussed benign and malignant breast cancer. In computer-aided diagnosis systems, the identification and classification of breast cancer using histopathology and ultrasound images are critical steps. Investigators have demonstrated the ability to automate the initial level identification and classification of the tumor throughout the last few decades. Breast cancer can be detected early, allowing patients to obtain proper therapy and thereby increase their chances of survival. Deep learning (DL), machine learning (ML), and transfer learning (TL) techniques are used to solve many medical issues. There are several scientific studies in the previous literature on the categorization and identification of cancer tumors using various types of models but with some limitations. However, research is hampered by the lack of a dataset. The proposed methodology is created to help with the automatic identification and diagnosis of breast cancer. Our main contribution is that the proposed model used the transfer learning technique on three datasets, A, B, C, and A2, A2 is the dataset A with two classes. In this study, ultrasound images and histopathology images are used. The model used in this work is a customized CNN-AlexNet, which was trained according to the requirements of the datasets. This is also one of the contributions of this work. The results have shown that the proposed system empowered with transfer learning achieved the highest accuracy than the existing models on datasets A, B, C, and A2.
Collapse
|