Federated Learning-Based Detection of Invasive Carcinoma of No Special Type with Histopathological Images
Invasive carcinoma of no special type (IC-NST) is known to be one of the most prevalent kinds of breast cancer, hence the growing research interest in studying automated systems that can detect the presence of breast tumors and appropriately classify them into subtypes. Machine learning (ML) and, mo...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/7/1669 |
| _version_ | 1797433678128742400 |
|---|---|
| author | Bless Lord Y. Agbley Jianping Li Md Altab Hossin Grace Ugochi Nneji Jehoiada Jackson Happy Nkanta Monday Edidiong Christopher James |
| author_facet | Bless Lord Y. Agbley Jianping Li Md Altab Hossin Grace Ugochi Nneji Jehoiada Jackson Happy Nkanta Monday Edidiong Christopher James |
| author_sort | Bless Lord Y. Agbley |
| collection | DOAJ |
| description | Invasive carcinoma of no special type (IC-NST) is known to be one of the most prevalent kinds of breast cancer, hence the growing research interest in studying automated systems that can detect the presence of breast tumors and appropriately classify them into subtypes. Machine learning (ML) and, more specifically, deep learning (DL) techniques have been used to approach this problem. However, such techniques usually require massive amounts of data to obtain competitive results. This requirement makes their application in specific areas such as health problematic as privacy concerns regarding the release of patients’ data publicly result in a limited number of publicly available datasets for the research community. This paper proposes an approach that leverages federated learning (FL) to securely train mathematical models over multiple clients with local IC-NST images partitioned from the breast histopathology image (BHI) dataset to obtain a global model. First, we used residual neural networks for automatic feature extraction. Then, we proposed a second network consisting of Gabor kernels to extract another set of features from the IC-NST dataset. After that, we performed a late fusion of the two sets of features and passed the output through a custom classifier. Experiments were conducted for the federated learning (FL) and centralized learning (CL) scenarios, and the results were compared. Competitive results were obtained, indicating the positive prospects of adopting FL for IC-NST detection. Additionally, fusing the Gabor features with the residual neural network features resulted in the best performance in terms of accuracy, F1 score, and area under the receiver operation curve (AUC-ROC). The models show good generalization by performing well on another domain dataset, the breast cancer histopathological (BreakHis) image dataset. Our method also outperformed other methods from the literature. |
| first_indexed | 2024-03-09T10:20:25Z |
| format | Article |
| id | doaj.art-8915d037892b4f04afad1e5f36603db0 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T10:20:25Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-8915d037892b4f04afad1e5f36603db02023-12-01T22:04:08ZengMDPI AGDiagnostics2075-44182022-07-01127166910.3390/diagnostics12071669Federated Learning-Based Detection of Invasive Carcinoma of No Special Type with Histopathological ImagesBless Lord Y. Agbley0Jianping Li1Md Altab Hossin2Grace Ugochi Nneji3Jehoiada Jackson4Happy Nkanta Monday5Edidiong Christopher James6School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Innovation and Entrepreneurship, Chengdu University, Chengdu 610106, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaInvasive carcinoma of no special type (IC-NST) is known to be one of the most prevalent kinds of breast cancer, hence the growing research interest in studying automated systems that can detect the presence of breast tumors and appropriately classify them into subtypes. Machine learning (ML) and, more specifically, deep learning (DL) techniques have been used to approach this problem. However, such techniques usually require massive amounts of data to obtain competitive results. This requirement makes their application in specific areas such as health problematic as privacy concerns regarding the release of patients’ data publicly result in a limited number of publicly available datasets for the research community. This paper proposes an approach that leverages federated learning (FL) to securely train mathematical models over multiple clients with local IC-NST images partitioned from the breast histopathology image (BHI) dataset to obtain a global model. First, we used residual neural networks for automatic feature extraction. Then, we proposed a second network consisting of Gabor kernels to extract another set of features from the IC-NST dataset. After that, we performed a late fusion of the two sets of features and passed the output through a custom classifier. Experiments were conducted for the federated learning (FL) and centralized learning (CL) scenarios, and the results were compared. Competitive results were obtained, indicating the positive prospects of adopting FL for IC-NST detection. Additionally, fusing the Gabor features with the residual neural network features resulted in the best performance in terms of accuracy, F1 score, and area under the receiver operation curve (AUC-ROC). The models show good generalization by performing well on another domain dataset, the breast cancer histopathological (BreakHis) image dataset. Our method also outperformed other methods from the literature.https://www.mdpi.com/2075-4418/12/7/1669breast cancerdeep learningfederated learninginvasive carcinoma of no special typewhole slide imageshistopathological image analysis |
| spellingShingle | Bless Lord Y. Agbley Jianping Li Md Altab Hossin Grace Ugochi Nneji Jehoiada Jackson Happy Nkanta Monday Edidiong Christopher James Federated Learning-Based Detection of Invasive Carcinoma of No Special Type with Histopathological Images Diagnostics breast cancer deep learning federated learning invasive carcinoma of no special type whole slide images histopathological image analysis |
| title | Federated Learning-Based Detection of Invasive Carcinoma of No Special Type with Histopathological Images |
| title_full | Federated Learning-Based Detection of Invasive Carcinoma of No Special Type with Histopathological Images |
| title_fullStr | Federated Learning-Based Detection of Invasive Carcinoma of No Special Type with Histopathological Images |
| title_full_unstemmed | Federated Learning-Based Detection of Invasive Carcinoma of No Special Type with Histopathological Images |
| title_short | Federated Learning-Based Detection of Invasive Carcinoma of No Special Type with Histopathological Images |
| title_sort | federated learning based detection of invasive carcinoma of no special type with histopathological images |
| topic | breast cancer deep learning federated learning invasive carcinoma of no special type whole slide images histopathological image analysis |
| url | https://www.mdpi.com/2075-4418/12/7/1669 |
| work_keys_str_mv | AT blesslordyagbley federatedlearningbaseddetectionofinvasivecarcinomaofnospecialtypewithhistopathologicalimages AT jianpingli federatedlearningbaseddetectionofinvasivecarcinomaofnospecialtypewithhistopathologicalimages AT mdaltabhossin federatedlearningbaseddetectionofinvasivecarcinomaofnospecialtypewithhistopathologicalimages AT graceugochinneji federatedlearningbaseddetectionofinvasivecarcinomaofnospecialtypewithhistopathologicalimages AT jehoiadajackson federatedlearningbaseddetectionofinvasivecarcinomaofnospecialtypewithhistopathologicalimages AT happynkantamonday federatedlearningbaseddetectionofinvasivecarcinomaofnospecialtypewithhistopathologicalimages AT edidiongchristopherjames federatedlearningbaseddetectionofinvasivecarcinomaofnospecialtypewithhistopathologicalimages |