Computer-Aided Bacillus Detection in Whole-Slide Pathological Images Using a Deep Convolutional Neural Network
Mycobacterial infections continue to greatly affect global health and result in challenging histopathological examinations using digital whole-slide images (WSIs), histopathological methods could be made more convenient. However, screening for stained bacilli is a highly laborious task for pathologi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/12/4059 |
| _version_ | 1827715207023034368 |
|---|---|
| author | Chung-Ming Lo Yu-Hung Wu Yu-Chuan (Jack) Li Chieh-Chi Lee |
| author_facet | Chung-Ming Lo Yu-Hung Wu Yu-Chuan (Jack) Li Chieh-Chi Lee |
| author_sort | Chung-Ming Lo |
| collection | DOAJ |
| description | Mycobacterial infections continue to greatly affect global health and result in challenging histopathological examinations using digital whole-slide images (WSIs), histopathological methods could be made more convenient. However, screening for stained bacilli is a highly laborious task for pathologists due to the microscopic and inconsistent appearance of bacilli. This study proposed a computer-aided detection (CAD) system based on deep learning to automatically detect acid-fast stained mycobacteria. A total of 613 bacillus-positive image blocks and 1202 negative image blocks were cropped from WSIs (at approximately 20 × 20 pixels) and divided into training and testing samples of bacillus images. After randomly selecting 80% of the samples as the training set and the remaining 20% of samples as the testing set, a transfer learning mechanism based on a deep convolutional neural network (DCNN) was applied with a pretrained AlexNet to the target bacillus image blocks. The transferred DCNN model generated the probability that each image block contained a bacillus. A probability higher than 0.5 was regarded as positive for a bacillus. Consequently, the DCNN model achieved an accuracy of 95.3%, a sensitivity of 93.5%, and a specificity of 96.3%. For samples without color information, the performances were an accuracy of 73.8%, a sensitivity of 70.7%, and a specificity of 75.4%. The proposed DCNN model successfully distinguished bacilli from other tissues with promising accuracy. Meanwhile, the contribution of color information was revealed. This information will be helpful for pathologists to establish a more efficient diagnostic procedure. |
| first_indexed | 2024-03-10T19:13:12Z |
| format | Article |
| id | doaj.art-95cf4ee41bbb4cc49c91c09a4cd0eed8 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T19:13:12Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-95cf4ee41bbb4cc49c91c09a4cd0eed82023-11-20T03:35:46ZengMDPI AGApplied Sciences2076-34172020-06-011012405910.3390/app10124059Computer-Aided Bacillus Detection in Whole-Slide Pathological Images Using a Deep Convolutional Neural NetworkChung-Ming Lo0Yu-Hung Wu1Yu-Chuan (Jack) Li2Chieh-Chi Lee3Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei 110, TaiwanDepartment of Dermatology, Mackay Memorial Hospital, Taipei 104, TaiwanGraduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei 110, TaiwanGraduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei 110, TaiwanMycobacterial infections continue to greatly affect global health and result in challenging histopathological examinations using digital whole-slide images (WSIs), histopathological methods could be made more convenient. However, screening for stained bacilli is a highly laborious task for pathologists due to the microscopic and inconsistent appearance of bacilli. This study proposed a computer-aided detection (CAD) system based on deep learning to automatically detect acid-fast stained mycobacteria. A total of 613 bacillus-positive image blocks and 1202 negative image blocks were cropped from WSIs (at approximately 20 × 20 pixels) and divided into training and testing samples of bacillus images. After randomly selecting 80% of the samples as the training set and the remaining 20% of samples as the testing set, a transfer learning mechanism based on a deep convolutional neural network (DCNN) was applied with a pretrained AlexNet to the target bacillus image blocks. The transferred DCNN model generated the probability that each image block contained a bacillus. A probability higher than 0.5 was regarded as positive for a bacillus. Consequently, the DCNN model achieved an accuracy of 95.3%, a sensitivity of 93.5%, and a specificity of 96.3%. For samples without color information, the performances were an accuracy of 73.8%, a sensitivity of 70.7%, and a specificity of 75.4%. The proposed DCNN model successfully distinguished bacilli from other tissues with promising accuracy. Meanwhile, the contribution of color information was revealed. This information will be helpful for pathologists to establish a more efficient diagnostic procedure.https://www.mdpi.com/2076-3417/10/12/4059digital pathologywhole-slide imagesmycobacterial infectionconvolutional neural network |
| spellingShingle | Chung-Ming Lo Yu-Hung Wu Yu-Chuan (Jack) Li Chieh-Chi Lee Computer-Aided Bacillus Detection in Whole-Slide Pathological Images Using a Deep Convolutional Neural Network Applied Sciences digital pathology whole-slide images mycobacterial infection convolutional neural network |
| title | Computer-Aided Bacillus Detection in Whole-Slide Pathological Images Using a Deep Convolutional Neural Network |
| title_full | Computer-Aided Bacillus Detection in Whole-Slide Pathological Images Using a Deep Convolutional Neural Network |
| title_fullStr | Computer-Aided Bacillus Detection in Whole-Slide Pathological Images Using a Deep Convolutional Neural Network |
| title_full_unstemmed | Computer-Aided Bacillus Detection in Whole-Slide Pathological Images Using a Deep Convolutional Neural Network |
| title_short | Computer-Aided Bacillus Detection in Whole-Slide Pathological Images Using a Deep Convolutional Neural Network |
| title_sort | computer aided bacillus detection in whole slide pathological images using a deep convolutional neural network |
| topic | digital pathology whole-slide images mycobacterial infection convolutional neural network |
| url | https://www.mdpi.com/2076-3417/10/12/4059 |
| work_keys_str_mv | AT chungminglo computeraidedbacillusdetectioninwholeslidepathologicalimagesusingadeepconvolutionalneuralnetwork AT yuhungwu computeraidedbacillusdetectioninwholeslidepathologicalimagesusingadeepconvolutionalneuralnetwork AT yuchuanjackli computeraidedbacillusdetectioninwholeslidepathologicalimagesusingadeepconvolutionalneuralnetwork AT chiehchilee computeraidedbacillusdetectioninwholeslidepathologicalimagesusingadeepconvolutionalneuralnetwork |