1
|
Liu H, Cui G, Luo Y, Guo Y, Zhao L, Wang Y, Subasi A, Dogan S, Tuncer T. Artificial Intelligence-Based Breast Cancer Diagnosis Using Ultrasound Images and Grid-Based Deep Feature Generator. Int J Gen Med 2022; 15:2271-2282. [PMID: 35256855 PMCID: PMC8898057 DOI: 10.2147/ijgm.s347491] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2021] [Accepted: 01/11/2022] [Indexed: 01/30/2023] Open
Abstract
Purpose Breast cancer is a prominent cancer type with high mortality. Early detection of breast cancer could serve to improve clinical outcomes. Ultrasonography is a digital imaging technique used to differentiate benign and malignant tumors. Several artificial intelligence techniques have been suggested in the literature for breast cancer detection using breast ultrasonography (BUS). Nowadays, particularly deep learning methods have been applied to biomedical images to achieve high classification performances. Patients and Methods This work presents a new deep feature generation technique for breast cancer detection using BUS images. The widely known 16 pre-trained CNN models have been used in this framework as feature generators. In the feature generation phase, the used input image is divided into rows and columns, and these deep feature generators (pre-trained models) have applied to each row and column. Therefore, this method is called a grid-based deep feature generator. The proposed grid-based deep feature generator can calculate the error value of each deep feature generator, and then it selects the best three feature vectors as a final feature vector. In the feature selection phase, iterative neighborhood component analysis (INCA) chooses 980 features as an optimal number of features. Finally, these features are classified by using a deep neural network (DNN). Results The developed grid-based deep feature generation-based image classification model reached 97.18% classification accuracy on the ultrasonic images for three classes, namely malignant, benign, and normal. Conclusion The findings obviously denoted that the proposed grid deep feature generator and INCA-based feature selection model successfully classified breast ultrasonic images.
Collapse
Affiliation(s)
- Haixia Liu
- Department of Ultrasound, Cangzhou Central Hospital, Cangzhou, Hebei Province, 061000, People's Republic of China
| | - Guozhong Cui
- Department of Surgical Oncology, Cangzhou Central Hospital, Cangzhou, Hebei Province, 061000, People's Republic of China
| | - Yi Luo
- Medical Statistics Room, Cangzhou Central Hospital, Cangzhou, Hebei Province, 061000, People's Republic of China
| | - Yajie Guo
- Department of Ultrasound, Cangzhou Central Hospital, Cangzhou, Hebei Province, 061000, People's Republic of China
| | - Lianli Zhao
- Department of Internal Medicine teaching and research group, Cangzhou Central Hospital, Cangzhou, Hebei Province, 061000, China
| | - Yueheng Wang
- Department of Ultrasound, The Second Hospital of Hebei MedicalUniversity, Shijiazhuang, Hebei Province, 050000, People's Republic of China
| | - Abdulhamit Subasi
- Institute of Biomedicine, Faculty of Medicine, University of Turku, Turku, 20520, Finland.,Department of Computer Science, College of Engineering, Effat University, Jeddah, 21478, Saudi Arabia
| | - Sengul Dogan
- Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, 23119, Turkey
| | - Turker Tuncer
- Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, 23119, Turkey
| |
Collapse
|
2
|
Razik MA, Alsubaie AM, Alsetri HM, Albassam KA, Alkhurayyif AO, Altamimi MM, Alanazi SM. Clinical and histopathological features of breast tumors in women: a cross-sectional study at three hospitals in the Kingdom of Saudi Arabia. Pan Afr Med J 2021; 39:267. [PMID: 34707768 PMCID: PMC8520403 DOI: 10.11604/pamj.2021.39.267.30341] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2021] [Accepted: 08/13/2021] [Indexed: 12/31/2022] Open
Abstract
Introduction there is a dearth of data on the epidemiology of breast tumors in the Kingdom of Saudi Arabia (KSA). This study aimed to determine the demographics, clinical patterns, and their association with histopathological types of breast tumors among females presently residing in KSA. Methods a multi-centric, cross-sectional study including female patients with symptoms suggestive of breast tumor was conducted at three hospitals in KSA from February 2019 to February 2020. The patient´s electronic health records were used to collect information related to their demographics, clinical findings including comordbities and symptoms and investigations. Binary logistic regression models were used to determine factors associated with the breast tumors. Results a total of 270 female patients were included in the study. The most frequently encountered symptom was a breast lump (95.9%, n = 259), followed by pain (18.9%, n = 51). More than half the population (53%, n = 143) had a histopathological diagnosis of fibroadenoma. Multivariate analysis revealed that patients > 46 years of age were less likely to present with fibroadenoma (AOR: 0.049 95% CI 0.02 - 0.15; p < 0.005). Those in the 31 - 45 years age group were less likely to present with ductal/lobular/papillary carcinomacompared to the less than 30 years group (AOR: 0.42, 95% CI 0.18 - 0.97; p = 0.04). Conclusion in this population of Saudi women with symptoms suggestive of breast tumor, those aged less than 40 years were more likely to have a fibroadenoma whereas those above 40 years were more likely to have breast cancer.
Collapse
Affiliation(s)
- Mohamed Abdel Razik
- General Surgery Department, College of Medicine, Prince Sattam Bin Abdulaziz University, Al-Kharj, Saudi Arabia
| | | | | | | | | | | | | |
Collapse
|