Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks
Automated bowel sound (BS) analysis methods were already well developed by the early 2000s. Accuracy of ~90% had been achieved by several teams using various analytical approaches. Clinical research on BS had revealed their high potential in the non-invasive investigation of irritable bowel syndrome...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/22/7602 |
| _version_ | 1797508449962033152 |
|---|---|
| author | Jakub Ficek Kacper Radzikowski Jan Krzysztof Nowak Osamu Yoshie Jaroslaw Walkowiak Robert Nowak |
| author_facet | Jakub Ficek Kacper Radzikowski Jan Krzysztof Nowak Osamu Yoshie Jaroslaw Walkowiak Robert Nowak |
| author_sort | Jakub Ficek |
| collection | DOAJ |
| description | Automated bowel sound (BS) analysis methods were already well developed by the early 2000s. Accuracy of ~90% had been achieved by several teams using various analytical approaches. Clinical research on BS had revealed their high potential in the non-invasive investigation of irritable bowel syndrome to study gastrointestinal motility and in a surgical setting. This article proposes a novel methodology for the analysis of BS using hybrid convolutional and recursive neural networks. It is one of the first methods of using deep learning to be widely explored. We have developed an experimental pipeline and evaluated our results with a new dataset collected using a device with a dedicated contact microphone. Data have been collected at night-time, which is the most interesting period from a neurogastroenterological point of view. Previous works had ignored this period and instead kept brief records only during the day. Our algorithm can detect bowel sounds with an accuracy >93%. Moreover, we have achieved a very high specificity (>97%), crucial in diagnosis. The results have been checked with a medical professional, and they successfully support clinical diagnosis. We have developed a client-server system allowing medical practitioners to upload the recordings from their patients and have them analyzed online. This system is available online. Although BS research is technologically mature, it still lacks a uniform methodology, an international forum for discussion, and an open platform for data exchange, and therefore it is not commonly used. Our server could provide a starting point for establishing a common framework in BS research. |
| first_indexed | 2024-03-10T05:05:05Z |
| format | Article |
| id | doaj.art-81992e7d88854053ab89b148fe3c6054 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T05:05:05Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-81992e7d88854053ab89b148fe3c60542023-11-23T01:26:29ZengMDPI AGSensors1424-82202021-11-012122760210.3390/s21227602Analysis of Gastrointestinal Acoustic Activity Using Deep Neural NetworksJakub Ficek0Kacper Radzikowski1Jan Krzysztof Nowak2Osamu Yoshie3Jaroslaw Walkowiak4Robert Nowak5Institute of Computer Science, Warsaw University of Technology, 00-665 Warsaw, PolandInstitute of Computer Science, Warsaw University of Technology, 00-665 Warsaw, PolandDepartment of Pediatric Gastroenterology and Metabolic Diseases, Poznan University of Medical Sciences, 60-572 Poznan, PolandGraduate School of Information, Production and Systems, Waseda University, Tokyo 169-8050, JapanDepartment of Pediatric Gastroenterology and Metabolic Diseases, Poznan University of Medical Sciences, 60-572 Poznan, PolandInstitute of Computer Science, Warsaw University of Technology, 00-665 Warsaw, PolandAutomated bowel sound (BS) analysis methods were already well developed by the early 2000s. Accuracy of ~90% had been achieved by several teams using various analytical approaches. Clinical research on BS had revealed their high potential in the non-invasive investigation of irritable bowel syndrome to study gastrointestinal motility and in a surgical setting. This article proposes a novel methodology for the analysis of BS using hybrid convolutional and recursive neural networks. It is one of the first methods of using deep learning to be widely explored. We have developed an experimental pipeline and evaluated our results with a new dataset collected using a device with a dedicated contact microphone. Data have been collected at night-time, which is the most interesting period from a neurogastroenterological point of view. Previous works had ignored this period and instead kept brief records only during the day. Our algorithm can detect bowel sounds with an accuracy >93%. Moreover, we have achieved a very high specificity (>97%), crucial in diagnosis. The results have been checked with a medical professional, and they successfully support clinical diagnosis. We have developed a client-server system allowing medical practitioners to upload the recordings from their patients and have them analyzed online. This system is available online. Although BS research is technologically mature, it still lacks a uniform methodology, an international forum for discussion, and an open platform for data exchange, and therefore it is not commonly used. Our server could provide a starting point for establishing a common framework in BS research.https://www.mdpi.com/1424-8220/21/22/7602sound analysisbowel soundsgastroenterologymachine learningneural networkdeep learning |
| spellingShingle | Jakub Ficek Kacper Radzikowski Jan Krzysztof Nowak Osamu Yoshie Jaroslaw Walkowiak Robert Nowak Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks Sensors sound analysis bowel sounds gastroenterology machine learning neural network deep learning |
| title | Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks |
| title_full | Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks |
| title_fullStr | Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks |
| title_full_unstemmed | Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks |
| title_short | Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks |
| title_sort | analysis of gastrointestinal acoustic activity using deep neural networks |
| topic | sound analysis bowel sounds gastroenterology machine learning neural network deep learning |
| url | https://www.mdpi.com/1424-8220/21/22/7602 |
| work_keys_str_mv | AT jakubficek analysisofgastrointestinalacousticactivityusingdeepneuralnetworks AT kacperradzikowski analysisofgastrointestinalacousticactivityusingdeepneuralnetworks AT jankrzysztofnowak analysisofgastrointestinalacousticactivityusingdeepneuralnetworks AT osamuyoshie analysisofgastrointestinalacousticactivityusingdeepneuralnetworks AT jaroslawwalkowiak analysisofgastrointestinalacousticactivityusingdeepneuralnetworks AT robertnowak analysisofgastrointestinalacousticactivityusingdeepneuralnetworks |