Performance of a Deep Learning System for Automatic Diagnosis of Protruding Lesions in Colon Capsule Endoscopy
Background: Colon capsule endoscopy (CCE) is an alternative for patients unwilling or with contraindications for conventional colonoscopy. Colorectal cancer screening may benefit greatly from widespread acceptance of a non-invasive tool such as CCE. However, reviewing CCE exams is a time-consuming p...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/6/1445 |
| _version_ | 1827660958464475136 |
|---|---|
| author | Miguel Mascarenhas João Afonso Tiago Ribeiro Hélder Cardoso Patrícia Andrade João P. S. Ferreira Miguel Mascarenhas Saraiva Guilherme Macedo |
| author_facet | Miguel Mascarenhas João Afonso Tiago Ribeiro Hélder Cardoso Patrícia Andrade João P. S. Ferreira Miguel Mascarenhas Saraiva Guilherme Macedo |
| author_sort | Miguel Mascarenhas |
| collection | DOAJ |
| description | Background: Colon capsule endoscopy (CCE) is an alternative for patients unwilling or with contraindications for conventional colonoscopy. Colorectal cancer screening may benefit greatly from widespread acceptance of a non-invasive tool such as CCE. However, reviewing CCE exams is a time-consuming process, with risk of overlooking important lesions. We aimed to develop an artificial intelligence (AI) algorithm using a convolutional neural network (CNN) architecture for automatic detection of colonic protruding lesions in CCE images. An anonymized database of CCE images collected from a total of 124 patients was used. This database included images of patients with colonic protruding lesions or patients with normal colonic mucosa or with other pathologic findings. A total of 5715 images were extracted for CNN development. Two image datasets were created and used for training and validation of the CNN. The AUROC for detection of protruding lesions was 0.99. The sensitivity, specificity, PPV and NPV were 90.0%, 99.1%, 98.6% and 93.2%, respectively. The overall accuracy of the network was 95.3%. The developed deep learning algorithm accurately detected protruding lesions in CCE images. The introduction of AI technology to CCE may increase its diagnostic accuracy and acceptance for screening of colorectal neoplasia. |
| first_indexed | 2024-03-10T00:00:48Z |
| format | Article |
| id | doaj.art-db8d36a8dd294842a442920751361aee |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T00:00:48Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-db8d36a8dd294842a442920751361aee2023-11-23T16:18:18ZengMDPI AGDiagnostics2075-44182022-06-01126144510.3390/diagnostics12061445Performance of a Deep Learning System for Automatic Diagnosis of Protruding Lesions in Colon Capsule EndoscopyMiguel Mascarenhas0João Afonso1Tiago Ribeiro2Hélder Cardoso3Patrícia Andrade4João P. S. Ferreira5Miguel Mascarenhas Saraiva6Guilherme Macedo7Department of Gastroenterology, São João University Hospital, Alameda Professor Hernâni Monteiro, 4200-427 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, Alameda Professor Hernâni Monteiro, 4200-427 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, Alameda Professor Hernâni Monteiro, 4200-427 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, Alameda Professor Hernâni Monteiro, 4200-427 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, Alameda Professor Hernâni Monteiro, 4200-427 Porto, PortugalDepartment of Mechanical Engineering, Faculty of Engineering of the University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, PortugalManopH Gastroenterology Clinic, Rua Sá da Bandeira 752, 4000-432 Porto, PortugalDepartment of Gastroenterology, São João University Hospital, Alameda Professor Hernâni Monteiro, 4200-427 Porto, PortugalBackground: Colon capsule endoscopy (CCE) is an alternative for patients unwilling or with contraindications for conventional colonoscopy. Colorectal cancer screening may benefit greatly from widespread acceptance of a non-invasive tool such as CCE. However, reviewing CCE exams is a time-consuming process, with risk of overlooking important lesions. We aimed to develop an artificial intelligence (AI) algorithm using a convolutional neural network (CNN) architecture for automatic detection of colonic protruding lesions in CCE images. An anonymized database of CCE images collected from a total of 124 patients was used. This database included images of patients with colonic protruding lesions or patients with normal colonic mucosa or with other pathologic findings. A total of 5715 images were extracted for CNN development. Two image datasets were created and used for training and validation of the CNN. The AUROC for detection of protruding lesions was 0.99. The sensitivity, specificity, PPV and NPV were 90.0%, 99.1%, 98.6% and 93.2%, respectively. The overall accuracy of the network was 95.3%. The developed deep learning algorithm accurately detected protruding lesions in CCE images. The introduction of AI technology to CCE may increase its diagnostic accuracy and acceptance for screening of colorectal neoplasia.https://www.mdpi.com/2075-4418/12/6/1445colon capsule endoscopyartificial intelligenceconvolutional neural networkcolorectal neoplasia |
| spellingShingle | Miguel Mascarenhas João Afonso Tiago Ribeiro Hélder Cardoso Patrícia Andrade João P. S. Ferreira Miguel Mascarenhas Saraiva Guilherme Macedo Performance of a Deep Learning System for Automatic Diagnosis of Protruding Lesions in Colon Capsule Endoscopy Diagnostics colon capsule endoscopy artificial intelligence convolutional neural network colorectal neoplasia |
| title | Performance of a Deep Learning System for Automatic Diagnosis of Protruding Lesions in Colon Capsule Endoscopy |
| title_full | Performance of a Deep Learning System for Automatic Diagnosis of Protruding Lesions in Colon Capsule Endoscopy |
| title_fullStr | Performance of a Deep Learning System for Automatic Diagnosis of Protruding Lesions in Colon Capsule Endoscopy |
| title_full_unstemmed | Performance of a Deep Learning System for Automatic Diagnosis of Protruding Lesions in Colon Capsule Endoscopy |
| title_short | Performance of a Deep Learning System for Automatic Diagnosis of Protruding Lesions in Colon Capsule Endoscopy |
| title_sort | performance of a deep learning system for automatic diagnosis of protruding lesions in colon capsule endoscopy |
| topic | colon capsule endoscopy artificial intelligence convolutional neural network colorectal neoplasia |
| url | https://www.mdpi.com/2075-4418/12/6/1445 |
| work_keys_str_mv | AT miguelmascarenhas performanceofadeeplearningsystemforautomaticdiagnosisofprotrudinglesionsincoloncapsuleendoscopy AT joaoafonso performanceofadeeplearningsystemforautomaticdiagnosisofprotrudinglesionsincoloncapsuleendoscopy AT tiagoribeiro performanceofadeeplearningsystemforautomaticdiagnosisofprotrudinglesionsincoloncapsuleendoscopy AT heldercardoso performanceofadeeplearningsystemforautomaticdiagnosisofprotrudinglesionsincoloncapsuleendoscopy AT patriciaandrade performanceofadeeplearningsystemforautomaticdiagnosisofprotrudinglesionsincoloncapsuleendoscopy AT joaopsferreira performanceofadeeplearningsystemforautomaticdiagnosisofprotrudinglesionsincoloncapsuleendoscopy AT miguelmascarenhassaraiva performanceofadeeplearningsystemforautomaticdiagnosisofprotrudinglesionsincoloncapsuleendoscopy AT guilhermemacedo performanceofadeeplearningsystemforautomaticdiagnosisofprotrudinglesionsincoloncapsuleendoscopy |