DCS-UNet: Dual-Path Framework for Segmentation of Reflux Esophagitis Lesions from Endoscopic Images with U-Net-Based Segmentation and Color/Texture Analysis
Automatic analysis of medical images and endoscopic images, in particular, is an attractive research topic in recent years. To achieve this goal, many tasks must be conducted for example lesion detection, segmentation, and classification. However, existing methods for such problems still face challe...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
World Scientific Publishing
2023-05-01
|
| Series: | Vietnam Journal of Computer Science |
| Subjects: | |
| Online Access: | https://www.worldscientific.com/doi/10.1142/S2196888822500385 |
| _version_ | 1797824104642904064 |
|---|---|
| author | Thanh-Hai Tran Danh Huy Vu Duc Huy Tran Khanh Linh Do Phuong Thao Nguyen Van Tuan Nguyen Long Thuy Nguyen Nguyen Khang Ho Hai Vu Viet Hang Dao |
| author_facet | Thanh-Hai Tran Danh Huy Vu Duc Huy Tran Khanh Linh Do Phuong Thao Nguyen Van Tuan Nguyen Long Thuy Nguyen Nguyen Khang Ho Hai Vu Viet Hang Dao |
| author_sort | Thanh-Hai Tran |
| collection | DOAJ |
| description | Automatic analysis of medical images and endoscopic images, in particular, is an attractive research topic in recent years. To achieve this goal, many tasks must be conducted for example lesion detection, segmentation, and classification. However, existing methods for such problems still face challenges due to the spreading characteristic of the lesions as well as some artifacts caused by motion, specularities, low contrast, bubbles, debris, bodily fluid, and blood. As a consequence, single segmentation or detection could not deal with those issues. Besides, although deep learning has achieved impressive results in many tasks, lacking a large annotated dataset could lead to overfitting problems. In this paper, we tackle these issues by taking particular characteristics of lesions of interest and advantages of deep segmentation models into account. We propose a dual-path framework (namely, DCS-UNet) that combines both segmentation and classification. We first segment lesions from the image using U-Net architecture with different encoder backbones (ResNet-50, VGG-16, DenseNet-201). The segmented regions will be then refined in the second path where we classify every patch in the whole image or the Inner or Outer regions extended from the contours given by the segmentation results. For the refinement scheme, we utilize the color-dependent and texture features as doctors’ advice and deploy the support vector machine (SVM) technique to classify a patch into disease region or not. Extensive experiments were conducted on three datasets of gastroesophageal reflux disease (GERD) endoscopic images as GradeM, GradeA, GradeB, which are defined as modified Los Angeles classification. The experimental results show the improvements of the proposed method compared to the single U-Net or a segmentation using the hand-designed features-based scheme. The proposed method improves mDice and mIoU by 0.5% and 0.36% on GradeA dataset, which is the most challenging dataset with ambiguous separations of GERD vs. normal regions, and by 0.82% and 0.81% on GradeM dataset, which is clearer to segment GERD regions. This proposed framework shows the potential to develop a diagnosis assistance system to help endoscopists reduce burden in examining GERD in the future. |
| first_indexed | 2024-03-13T10:34:02Z |
| format | Article |
| id | doaj.art-69c9ae42d7394ba79359b92a67e3662d |
| institution | Directory Open Access Journal |
| issn | 2196-8888 2196-8896 |
| language | English |
| last_indexed | 2024-03-13T10:34:02Z |
| publishDate | 2023-05-01 |
| publisher | World Scientific Publishing |
| record_format | Article |
| series | Vietnam Journal of Computer Science |
| spelling | doaj.art-69c9ae42d7394ba79359b92a67e3662d2023-05-18T07:44:22ZengWorld Scientific PublishingVietnam Journal of Computer Science2196-88882196-88962023-05-01100221724210.1142/S2196888822500385DCS-UNet: Dual-Path Framework for Segmentation of Reflux Esophagitis Lesions from Endoscopic Images with U-Net-Based Segmentation and Color/Texture AnalysisThanh-Hai Tran0Danh Huy Vu1Duc Huy Tran2Khanh Linh Do3Phuong Thao Nguyen4Van Tuan Nguyen5Long Thuy Nguyen6Nguyen Khang Ho7Hai Vu8Viet Hang Dao9School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, VietnamSchool of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, VietnamSchool of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, VietnamSchool of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, VietnamSchool of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, VietnamSchool of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, VietnamSchool of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, VietnamSchool of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, VietnamSchool of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, VietnamInstitute of Gastroenterology and Hepatology, Hanoi Medical University Hospital, Hanoi, VietnamAutomatic analysis of medical images and endoscopic images, in particular, is an attractive research topic in recent years. To achieve this goal, many tasks must be conducted for example lesion detection, segmentation, and classification. However, existing methods for such problems still face challenges due to the spreading characteristic of the lesions as well as some artifacts caused by motion, specularities, low contrast, bubbles, debris, bodily fluid, and blood. As a consequence, single segmentation or detection could not deal with those issues. Besides, although deep learning has achieved impressive results in many tasks, lacking a large annotated dataset could lead to overfitting problems. In this paper, we tackle these issues by taking particular characteristics of lesions of interest and advantages of deep segmentation models into account. We propose a dual-path framework (namely, DCS-UNet) that combines both segmentation and classification. We first segment lesions from the image using U-Net architecture with different encoder backbones (ResNet-50, VGG-16, DenseNet-201). The segmented regions will be then refined in the second path where we classify every patch in the whole image or the Inner or Outer regions extended from the contours given by the segmentation results. For the refinement scheme, we utilize the color-dependent and texture features as doctors’ advice and deploy the support vector machine (SVM) technique to classify a patch into disease region or not. Extensive experiments were conducted on three datasets of gastroesophageal reflux disease (GERD) endoscopic images as GradeM, GradeA, GradeB, which are defined as modified Los Angeles classification. The experimental results show the improvements of the proposed method compared to the single U-Net or a segmentation using the hand-designed features-based scheme. The proposed method improves mDice and mIoU by 0.5% and 0.36% on GradeA dataset, which is the most challenging dataset with ambiguous separations of GERD vs. normal regions, and by 0.82% and 0.81% on GradeM dataset, which is clearer to segment GERD regions. This proposed framework shows the potential to develop a diagnosis assistance system to help endoscopists reduce burden in examining GERD in the future.https://www.worldscientific.com/doi/10.1142/S2196888822500385Lesion detectionendoscopic imagefeature extractionimage segmentationU-Netmachine learning |
| spellingShingle | Thanh-Hai Tran Danh Huy Vu Duc Huy Tran Khanh Linh Do Phuong Thao Nguyen Van Tuan Nguyen Long Thuy Nguyen Nguyen Khang Ho Hai Vu Viet Hang Dao DCS-UNet: Dual-Path Framework for Segmentation of Reflux Esophagitis Lesions from Endoscopic Images with U-Net-Based Segmentation and Color/Texture Analysis Vietnam Journal of Computer Science Lesion detection endoscopic image feature extraction image segmentation U-Net machine learning |
| title | DCS-UNet: Dual-Path Framework for Segmentation of Reflux Esophagitis Lesions from Endoscopic Images with U-Net-Based Segmentation and Color/Texture Analysis |
| title_full | DCS-UNet: Dual-Path Framework for Segmentation of Reflux Esophagitis Lesions from Endoscopic Images with U-Net-Based Segmentation and Color/Texture Analysis |
| title_fullStr | DCS-UNet: Dual-Path Framework for Segmentation of Reflux Esophagitis Lesions from Endoscopic Images with U-Net-Based Segmentation and Color/Texture Analysis |
| title_full_unstemmed | DCS-UNet: Dual-Path Framework for Segmentation of Reflux Esophagitis Lesions from Endoscopic Images with U-Net-Based Segmentation and Color/Texture Analysis |
| title_short | DCS-UNet: Dual-Path Framework for Segmentation of Reflux Esophagitis Lesions from Endoscopic Images with U-Net-Based Segmentation and Color/Texture Analysis |
| title_sort | dcs unet dual path framework for segmentation of reflux esophagitis lesions from endoscopic images with u net based segmentation and color texture analysis |
| topic | Lesion detection endoscopic image feature extraction image segmentation U-Net machine learning |
| url | https://www.worldscientific.com/doi/10.1142/S2196888822500385 |
| work_keys_str_mv | AT thanhhaitran dcsunetdualpathframeworkforsegmentationofrefluxesophagitislesionsfromendoscopicimageswithunetbasedsegmentationandcolortextureanalysis AT danhhuyvu dcsunetdualpathframeworkforsegmentationofrefluxesophagitislesionsfromendoscopicimageswithunetbasedsegmentationandcolortextureanalysis AT duchuytran dcsunetdualpathframeworkforsegmentationofrefluxesophagitislesionsfromendoscopicimageswithunetbasedsegmentationandcolortextureanalysis AT khanhlinhdo dcsunetdualpathframeworkforsegmentationofrefluxesophagitislesionsfromendoscopicimageswithunetbasedsegmentationandcolortextureanalysis AT phuongthaonguyen dcsunetdualpathframeworkforsegmentationofrefluxesophagitislesionsfromendoscopicimageswithunetbasedsegmentationandcolortextureanalysis AT vantuannguyen dcsunetdualpathframeworkforsegmentationofrefluxesophagitislesionsfromendoscopicimageswithunetbasedsegmentationandcolortextureanalysis AT longthuynguyen dcsunetdualpathframeworkforsegmentationofrefluxesophagitislesionsfromendoscopicimageswithunetbasedsegmentationandcolortextureanalysis AT nguyenkhangho dcsunetdualpathframeworkforsegmentationofrefluxesophagitislesionsfromendoscopicimageswithunetbasedsegmentationandcolortextureanalysis AT haivu dcsunetdualpathframeworkforsegmentationofrefluxesophagitislesionsfromendoscopicimageswithunetbasedsegmentationandcolortextureanalysis AT viethangdao dcsunetdualpathframeworkforsegmentationofrefluxesophagitislesionsfromendoscopicimageswithunetbasedsegmentationandcolortextureanalysis |