A deep learning based framework for the classification of multi- class capsule gastroscope image in gastroenterologic diagnosis
Purpose: The purpose of this paper is to develop a method to automatic classify capsule gastroscope image into three categories to prevent high-risk factors for carcinogenesis, such as atrophic gastritis (AG). The purpose of this research work is to develop a deep learning framework based on transfe...
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-11-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2022.1060591/full |
| _version_ | 1797983811133243392 |
|---|---|
| author | Ping Xiao Ping Xiao Yuhang Pan Feiyue Cai Feiyue Cai Haoran Tu Junru Liu Xuemei Yang Huanling Liang Xueqing Zou Li Yang Jueni Duan Long Xv Lijuan Feng Zhenyu Liu Yun Qian Yu Meng Jingfeng Du Xi Mei Ting Lou Xiaoxv Yin Zhen Tan Zhen Tan |
| author_facet | Ping Xiao Ping Xiao Yuhang Pan Feiyue Cai Feiyue Cai Haoran Tu Junru Liu Xuemei Yang Huanling Liang Xueqing Zou Li Yang Jueni Duan Long Xv Lijuan Feng Zhenyu Liu Yun Qian Yu Meng Jingfeng Du Xi Mei Ting Lou Xiaoxv Yin Zhen Tan Zhen Tan |
| author_sort | Ping Xiao |
| collection | DOAJ |
| description | Purpose: The purpose of this paper is to develop a method to automatic classify capsule gastroscope image into three categories to prevent high-risk factors for carcinogenesis, such as atrophic gastritis (AG). The purpose of this research work is to develop a deep learning framework based on transfer learning to classify capsule gastroscope image into three categories: normal gastroscopic image, chronic erosive gastritis images, and ulcer gastric image.Method: In this research work, we proposed deep learning framework based on transfer learning to classify capsule gastroscope image into three categories: normal gastroscopic image, chronic erosive gastritis images, and ulcer gastric image. We used VGG- 16, ResNet-50, and Inception V3 pre-trained models, fine-tuned them and adjust hyperparameters according to our classification problem.Results: A dataset containing 380 images was collected for each capsule gastroscope image category, and divided into training set and test set in a ratio of 70%, and 30% respectively, and then based on the dataset, three methods, including as VGG- 16, ResNet-50, and Inception v3 are used. We achieved highest accuracy of 94.80% by using VGG- 16 to diagnose and classify capsule gastroscopic images into three categories: normal gastroscopic image, chronic erosive gastritis images, and ulcer gastric image. Our proposed approach classified capsule gastroscope image with respectable specificity and accuracy.Conclusion: The primary technique and industry standard for diagnosing and treating numerous stomach problems is gastroscopy. Capsule gastroscope is a new screening tool for gastric diseases. However, a number of elements, including image quality of capsule endoscopy, the doctors’ experience and fatigue, limit its effectiveness. Early identification is necessary for high-risk factors for carcinogenesis, such as atrophic gastritis (AG). Our suggested framework will help prevent incorrect diagnoses brought on by low image quality, individual experience, and inadequate gastroscopy inspection coverage, among other factors. As a result, the suggested approach will raise the standard of gastroscopy. Deep learning has great potential in gastritis image classification for assisting with achieving accurate diagnoses after endoscopic procedures. |
| first_indexed | 2024-04-11T06:53:07Z |
| format | Article |
| id | doaj.art-21448ac8f0674e3facdafb67b8c8f918 |
| institution | Directory Open Access Journal |
| issn | 1664-042X |
| language | English |
| last_indexed | 2024-04-11T06:53:07Z |
| publishDate | 2022-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj.art-21448ac8f0674e3facdafb67b8c8f9182022-12-22T04:39:07ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2022-11-011310.3389/fphys.2022.10605911060591A deep learning based framework for the classification of multi- class capsule gastroscope image in gastroenterologic diagnosisPing Xiao0Ping Xiao1Yuhang Pan2Feiyue Cai3Feiyue Cai4Haoran Tu5Junru Liu6Xuemei Yang7Huanling Liang8Xueqing Zou9Li Yang10Jueni Duan11Long Xv12Lijuan Feng13Zhenyu Liu14Yun Qian15Yu Meng16Jingfeng Du17Xi Mei18Ting Lou19Xiaoxv Yin20Zhen Tan21Zhen Tan22Health Management Center, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaDepartment of Otorhinolaryngology Head and Neck Surgery, Shenzhen Children’s Hospital, Shenzhen, ChinaHealth Management Center, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaHealth Management Center, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaShenzhen Nanshan District General Practice Alliance, Shenzhen, ChinaGroup International Division, Shenzhen Senior High School, Shenzhen, ChinaHealth Management Center, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaHealth Management Center, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaHealth Management Center, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaHealth Management Center, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaHealth Management Center, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaHealth Management Center, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaDepartment of Gastroenterology and Hepatology, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaDepartment of Gastroenterology and Hepatology, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaDepartment of Gastroenterology and Hepatology, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaDepartment of Gastroenterology and Hepatology, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaDepartment of Gastroenterology and Hepatology, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaDepartment of Gastroenterology and Hepatology, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaHealth Management Center, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaHealth Management Center, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaSchool of Public Health, Huazhong University of Science and Technology, Wuhan, ChinaHealth Management Center, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University, Shenzhen, ChinaShenzhen Nanshan District General Practice Alliance, Shenzhen, ChinaPurpose: The purpose of this paper is to develop a method to automatic classify capsule gastroscope image into three categories to prevent high-risk factors for carcinogenesis, such as atrophic gastritis (AG). The purpose of this research work is to develop a deep learning framework based on transfer learning to classify capsule gastroscope image into three categories: normal gastroscopic image, chronic erosive gastritis images, and ulcer gastric image.Method: In this research work, we proposed deep learning framework based on transfer learning to classify capsule gastroscope image into three categories: normal gastroscopic image, chronic erosive gastritis images, and ulcer gastric image. We used VGG- 16, ResNet-50, and Inception V3 pre-trained models, fine-tuned them and adjust hyperparameters according to our classification problem.Results: A dataset containing 380 images was collected for each capsule gastroscope image category, and divided into training set and test set in a ratio of 70%, and 30% respectively, and then based on the dataset, three methods, including as VGG- 16, ResNet-50, and Inception v3 are used. We achieved highest accuracy of 94.80% by using VGG- 16 to diagnose and classify capsule gastroscopic images into three categories: normal gastroscopic image, chronic erosive gastritis images, and ulcer gastric image. Our proposed approach classified capsule gastroscope image with respectable specificity and accuracy.Conclusion: The primary technique and industry standard for diagnosing and treating numerous stomach problems is gastroscopy. Capsule gastroscope is a new screening tool for gastric diseases. However, a number of elements, including image quality of capsule endoscopy, the doctors’ experience and fatigue, limit its effectiveness. Early identification is necessary for high-risk factors for carcinogenesis, such as atrophic gastritis (AG). Our suggested framework will help prevent incorrect diagnoses brought on by low image quality, individual experience, and inadequate gastroscopy inspection coverage, among other factors. As a result, the suggested approach will raise the standard of gastroscopy. Deep learning has great potential in gastritis image classification for assisting with achieving accurate diagnoses after endoscopic procedures.https://www.frontiersin.org/articles/10.3389/fphys.2022.1060591/fullcapsule gastroscopegastric diseasesdiagnosisdeep learningtransfer learning |
| spellingShingle | Ping Xiao Ping Xiao Yuhang Pan Feiyue Cai Feiyue Cai Haoran Tu Junru Liu Xuemei Yang Huanling Liang Xueqing Zou Li Yang Jueni Duan Long Xv Lijuan Feng Zhenyu Liu Yun Qian Yu Meng Jingfeng Du Xi Mei Ting Lou Xiaoxv Yin Zhen Tan Zhen Tan A deep learning based framework for the classification of multi- class capsule gastroscope image in gastroenterologic diagnosis Frontiers in Physiology capsule gastroscope gastric diseases diagnosis deep learning transfer learning |
| title | A deep learning based framework for the classification of multi- class capsule gastroscope image in gastroenterologic diagnosis |
| title_full | A deep learning based framework for the classification of multi- class capsule gastroscope image in gastroenterologic diagnosis |
| title_fullStr | A deep learning based framework for the classification of multi- class capsule gastroscope image in gastroenterologic diagnosis |
| title_full_unstemmed | A deep learning based framework for the classification of multi- class capsule gastroscope image in gastroenterologic diagnosis |
| title_short | A deep learning based framework for the classification of multi- class capsule gastroscope image in gastroenterologic diagnosis |
| title_sort | deep learning based framework for the classification of multi class capsule gastroscope image in gastroenterologic diagnosis |
| topic | capsule gastroscope gastric diseases diagnosis deep learning transfer learning |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2022.1060591/full |
| work_keys_str_mv | AT pingxiao adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT pingxiao adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT yuhangpan adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT feiyuecai adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT feiyuecai adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT haorantu adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT junruliu adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT xuemeiyang adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT huanlingliang adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT xueqingzou adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT liyang adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT jueniduan adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT longxv adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT lijuanfeng adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT zhenyuliu adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT yunqian adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT yumeng adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT jingfengdu adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT ximei adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT tinglou adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT xiaoxvyin adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT zhentan adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT zhentan adeeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT pingxiao deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT pingxiao deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT yuhangpan deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT feiyuecai deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT feiyuecai deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT haorantu deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT junruliu deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT xuemeiyang deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT huanlingliang deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT xueqingzou deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT liyang deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT jueniduan deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT longxv deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT lijuanfeng deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT zhenyuliu deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT yunqian deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT yumeng deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT jingfengdu deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT ximei deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT tinglou deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT xiaoxvyin deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT zhentan deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis AT zhentan deeplearningbasedframeworkfortheclassificationofmulticlasscapsulegastroscopeimageingastroenterologicdiagnosis |