Automatic Pancreatic Cyst Lesion Segmentation on EUS Images Using a Deep-Learning Approach
The automatic segmentation of the pancreatic cyst lesion (PCL) is essential for the automated diagnosis of pancreatic cyst lesions on endoscopic ultrasonography (EUS) images. In this study, we proposed a deep-learning approach for PCL segmentation on EUS images. We employed the Attention U-Net model...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/1/245 |
| _version_ | 1797497579601133568 |
|---|---|
| author | Seok Oh Young-Jae Kim Young-Taek Park Kwang-Gi Kim |
| author_facet | Seok Oh Young-Jae Kim Young-Taek Park Kwang-Gi Kim |
| author_sort | Seok Oh |
| collection | DOAJ |
| description | The automatic segmentation of the pancreatic cyst lesion (PCL) is essential for the automated diagnosis of pancreatic cyst lesions on endoscopic ultrasonography (EUS) images. In this study, we proposed a deep-learning approach for PCL segmentation on EUS images. We employed the Attention U-Net model for automatic PCL segmentation. The Attention U-Net was compared with the Basic U-Net, Residual U-Net, and U-Net++ models. The Attention U-Net showed a better dice similarity coefficient (DSC) and intersection over union (IoU) scores than the other models on the internal test. Although the Basic U-Net showed a higher DSC and IoU scores on the external test than the Attention U-Net, there was no statistically significant difference. On the internal test of the cross-over study, the Attention U-Net showed the highest DSC and IoU scores. However, there was no significant difference between the Attention U-Net and Residual U-Net or between the Attention U-Net and U-Net++. On the external test of the cross-over study, all models showed no significant difference from each other. To the best of our knowledge, this is the first study implementing segmentation of PCL on EUS images using a deep-learning approach. Our experimental results show that a deep-learning approach can be applied successfully for PCL segmentation on EUS images. |
| first_indexed | 2024-03-10T03:21:14Z |
| format | Article |
| id | doaj.art-8bbcdc6e49c9464c90836e214791b8e8 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T03:21:14Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8bbcdc6e49c9464c90836e214791b8e82023-11-23T12:19:16ZengMDPI AGSensors1424-82202021-12-0122124510.3390/s22010245Automatic Pancreatic Cyst Lesion Segmentation on EUS Images Using a Deep-Learning ApproachSeok Oh0Young-Jae Kim1Young-Taek Park2Kwang-Gi Kim3Gil Medical Center, Department of Biomedical Engineering, Gachon University College of Medicine, Incheon 21565, KoreaGil Medical Center, Department of Biomedical Engineering, Gachon University College of Medicine, Incheon 21565, KoreaHIRA Research Institute, Health Insurance Review & Assessment Service (HIRA), Wonju-si 26465, KoreaGil Medical Center, Department of Biomedical Engineering, Gachon University College of Medicine, Incheon 21565, KoreaThe automatic segmentation of the pancreatic cyst lesion (PCL) is essential for the automated diagnosis of pancreatic cyst lesions on endoscopic ultrasonography (EUS) images. In this study, we proposed a deep-learning approach for PCL segmentation on EUS images. We employed the Attention U-Net model for automatic PCL segmentation. The Attention U-Net was compared with the Basic U-Net, Residual U-Net, and U-Net++ models. The Attention U-Net showed a better dice similarity coefficient (DSC) and intersection over union (IoU) scores than the other models on the internal test. Although the Basic U-Net showed a higher DSC and IoU scores on the external test than the Attention U-Net, there was no statistically significant difference. On the internal test of the cross-over study, the Attention U-Net showed the highest DSC and IoU scores. However, there was no significant difference between the Attention U-Net and Residual U-Net or between the Attention U-Net and U-Net++. On the external test of the cross-over study, all models showed no significant difference from each other. To the best of our knowledge, this is the first study implementing segmentation of PCL on EUS images using a deep-learning approach. Our experimental results show that a deep-learning approach can be applied successfully for PCL segmentation on EUS images.https://www.mdpi.com/1424-8220/22/1/245pancreatic cyst lesionsegmentationcomputer-aided diagnosisdeep learningendoscopic ultrasonography |
| spellingShingle | Seok Oh Young-Jae Kim Young-Taek Park Kwang-Gi Kim Automatic Pancreatic Cyst Lesion Segmentation on EUS Images Using a Deep-Learning Approach Sensors pancreatic cyst lesion segmentation computer-aided diagnosis deep learning endoscopic ultrasonography |
| title | Automatic Pancreatic Cyst Lesion Segmentation on EUS Images Using a Deep-Learning Approach |
| title_full | Automatic Pancreatic Cyst Lesion Segmentation on EUS Images Using a Deep-Learning Approach |
| title_fullStr | Automatic Pancreatic Cyst Lesion Segmentation on EUS Images Using a Deep-Learning Approach |
| title_full_unstemmed | Automatic Pancreatic Cyst Lesion Segmentation on EUS Images Using a Deep-Learning Approach |
| title_short | Automatic Pancreatic Cyst Lesion Segmentation on EUS Images Using a Deep-Learning Approach |
| title_sort | automatic pancreatic cyst lesion segmentation on eus images using a deep learning approach |
| topic | pancreatic cyst lesion segmentation computer-aided diagnosis deep learning endoscopic ultrasonography |
| url | https://www.mdpi.com/1424-8220/22/1/245 |
| work_keys_str_mv | AT seokoh automaticpancreaticcystlesionsegmentationoneusimagesusingadeeplearningapproach AT youngjaekim automaticpancreaticcystlesionsegmentationoneusimagesusingadeeplearningapproach AT youngtaekpark automaticpancreaticcystlesionsegmentationoneusimagesusingadeeplearningapproach AT kwanggikim automaticpancreaticcystlesionsegmentationoneusimagesusingadeeplearningapproach |