Automatic Detection of Small Intestinal Hookworms in Capsule Endoscopy Images Based on a Convolutional Neural Network
Ancylostomiasis is a fairly common small bowel parasite disease identified by capsule endoscopy (CE) for which a computer-aided clinical detection method has not been established. We sought to develop an artificial intelligence system with a convolutional neural network (CNN) to automatically detect...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Gastroenterology Research and Practice |
| Online Access: | http://dx.doi.org/10.1155/2021/5682288 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832565686863396864 |
|---|---|
| author | Tao Gan Yulin Yang Shuaicheng Liu Bing Zeng Jinlin Yang Kai Deng Junchao Wu Li Yang |
| author_facet | Tao Gan Yulin Yang Shuaicheng Liu Bing Zeng Jinlin Yang Kai Deng Junchao Wu Li Yang |
| author_sort | Tao Gan |
| collection | DOAJ |
| description | Ancylostomiasis is a fairly common small bowel parasite disease identified by capsule endoscopy (CE) for which a computer-aided clinical detection method has not been established. We sought to develop an artificial intelligence system with a convolutional neural network (CNN) to automatically detect hookworms in CE images. We trained a deep CNN system based on a YOLO-V4 (You Look Only Once-Version4) detector using 11236 CE images of hookworms. We assessed its performance by calculating the area under the receiver operating characteristic curve and its sensitivity, specificity, and accuracy using an independent test set of 10,529 small-bowel images including 531 images of hookworms. The trained CNN system required 403 seconds to evaluate 10,529 test images. The area under the curve for the detection of hookworms was 0.972 (95% confidence interval (CI), 0.967-0.978). The sensitivity, specificity, and accuracy of the CNN system were 92.2%, 91.1%, and 91.2%, respectively, at a probability score cut-off of 0.485. We developed and validated a CNN-based system for detecting hookworms in CE images. By combining this high-accuracy, high-speed, and oversight-preventing system with other CNN systems, we hope it will become an important supplement for detecting intestinal abnormalities in CE images. This trial is registered with ChiCTR2000034546 (a clinical research of artificial-intelligence-aided diagnosis for hookworms in small intestine by capsule endoscope images). |
| format | Article |
| id | doaj-art-f1475280869c4717891cd3e4dec19e38 |
| institution | Kabale University |
| issn | 1687-630X |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Gastroenterology Research and Practice |
| spelling | doaj-art-f1475280869c4717891cd3e4dec19e382025-02-03T01:07:06ZengWileyGastroenterology Research and Practice1687-630X2021-01-01202110.1155/2021/5682288Automatic Detection of Small Intestinal Hookworms in Capsule Endoscopy Images Based on a Convolutional Neural NetworkTao Gan0Yulin Yang1Shuaicheng Liu2Bing Zeng3Jinlin Yang4Kai Deng5Junchao Wu6Li Yang7Department of Gastroenterology and HepatologySchool of Information and Communication EngineeringSchool of Information and Communication EngineeringSchool of Information and Communication EngineeringDepartment of Gastroenterology and HepatologyDepartment of Gastroenterology and HepatologyDepartment of Gastroenterology and HepatologyDepartment of Gastroenterology and HepatologyAncylostomiasis is a fairly common small bowel parasite disease identified by capsule endoscopy (CE) for which a computer-aided clinical detection method has not been established. We sought to develop an artificial intelligence system with a convolutional neural network (CNN) to automatically detect hookworms in CE images. We trained a deep CNN system based on a YOLO-V4 (You Look Only Once-Version4) detector using 11236 CE images of hookworms. We assessed its performance by calculating the area under the receiver operating characteristic curve and its sensitivity, specificity, and accuracy using an independent test set of 10,529 small-bowel images including 531 images of hookworms. The trained CNN system required 403 seconds to evaluate 10,529 test images. The area under the curve for the detection of hookworms was 0.972 (95% confidence interval (CI), 0.967-0.978). The sensitivity, specificity, and accuracy of the CNN system were 92.2%, 91.1%, and 91.2%, respectively, at a probability score cut-off of 0.485. We developed and validated a CNN-based system for detecting hookworms in CE images. By combining this high-accuracy, high-speed, and oversight-preventing system with other CNN systems, we hope it will become an important supplement for detecting intestinal abnormalities in CE images. This trial is registered with ChiCTR2000034546 (a clinical research of artificial-intelligence-aided diagnosis for hookworms in small intestine by capsule endoscope images).http://dx.doi.org/10.1155/2021/5682288 |
| spellingShingle | Tao Gan Yulin Yang Shuaicheng Liu Bing Zeng Jinlin Yang Kai Deng Junchao Wu Li Yang Automatic Detection of Small Intestinal Hookworms in Capsule Endoscopy Images Based on a Convolutional Neural Network Gastroenterology Research and Practice |
| title | Automatic Detection of Small Intestinal Hookworms in Capsule Endoscopy Images Based on a Convolutional Neural Network |
| title_full | Automatic Detection of Small Intestinal Hookworms in Capsule Endoscopy Images Based on a Convolutional Neural Network |
| title_fullStr | Automatic Detection of Small Intestinal Hookworms in Capsule Endoscopy Images Based on a Convolutional Neural Network |
| title_full_unstemmed | Automatic Detection of Small Intestinal Hookworms in Capsule Endoscopy Images Based on a Convolutional Neural Network |
| title_short | Automatic Detection of Small Intestinal Hookworms in Capsule Endoscopy Images Based on a Convolutional Neural Network |
| title_sort | automatic detection of small intestinal hookworms in capsule endoscopy images based on a convolutional neural network |
| url | http://dx.doi.org/10.1155/2021/5682288 |
| work_keys_str_mv | AT taogan automaticdetectionofsmallintestinalhookwormsincapsuleendoscopyimagesbasedonaconvolutionalneuralnetwork AT yulinyang automaticdetectionofsmallintestinalhookwormsincapsuleendoscopyimagesbasedonaconvolutionalneuralnetwork AT shuaichengliu automaticdetectionofsmallintestinalhookwormsincapsuleendoscopyimagesbasedonaconvolutionalneuralnetwork AT bingzeng automaticdetectionofsmallintestinalhookwormsincapsuleendoscopyimagesbasedonaconvolutionalneuralnetwork AT jinlinyang automaticdetectionofsmallintestinalhookwormsincapsuleendoscopyimagesbasedonaconvolutionalneuralnetwork AT kaideng automaticdetectionofsmallintestinalhookwormsincapsuleendoscopyimagesbasedonaconvolutionalneuralnetwork AT junchaowu automaticdetectionofsmallintestinalhookwormsincapsuleendoscopyimagesbasedonaconvolutionalneuralnetwork AT liyang automaticdetectionofsmallintestinalhookwormsincapsuleendoscopyimagesbasedonaconvolutionalneuralnetwork |