GIFCOS-DT: One Stage Detection of Gastrointestinal Tract Lesions From Endoscopic Images With Distance Transform
This study aims at developing a computer-aided diagnostic system based on deep learning techniques for detecting various typical lesions during endoscopic examinations in the human gastrointestinal tract. We propose a lesion detection model, namely called GIFCOS-DT, that is built upon a one-stage ba...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10744010/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846170381277200384 |
|---|---|
| author | Thanh-Hai Tran Danh Huy Vu Minh Hanh Tran Viet Hang Dao Hai Vu Thi Thuy Nguyen |
| author_facet | Thanh-Hai Tran Danh Huy Vu Minh Hanh Tran Viet Hang Dao Hai Vu Thi Thuy Nguyen |
| author_sort | Thanh-Hai Tran |
| collection | DOAJ |
| description | This study aims at developing a computer-aided diagnostic system based on deep learning techniques for detecting various typical lesions during endoscopic examinations in the human gastrointestinal tract. We propose a lesion detection model, namely called GIFCOS-DT, that is built upon a one-stage backbone for object detection (Fully Convolutional One-Stage Object Detection - FCOS). For the proposed model, to deal with the diverse shapes and appearance of the lesions, we introduce a new loss function based on Distance Transform, that better describes the elongated or curved shapes of lesions than the common loss functions like Intersection of Union or centroid loss. We then deploy the detection model on an embedded device that connects to the endoscopic machine to assist endoscopists during examinations. A multithread technique is employed to accelerate the processing times of all steps of the system. Extensive experiments have been conducted on two challenging datasets, the benchmark dataset (Kvasir-SEG) and our newly collected dataset (IGH_GIEndoLesion-SEG), which include various typical lesions of the gastrointestinal (GI) tract (reflux esophagitis, esophageal cancer, helicobacter pylori negative gastritis, helicobacter pylori positive gastritis, gastric cancer, duodenal ulcer, and colorectal polyps). Experimental results show that our proposed methods outperform the original FCOS by 4.2% and 7.2% on Kvasir-SEG and our collected dataset respectively in terms of the average <inline-formula> <tex-math notation="LaTeX">$AP_{50}$ </tex-math></inline-formula> score. On the Kvasir-SEG dataset, the GIFCOS-DT outperforms state-of-the-art detectors such as Faster R-CNN, DETR, YOLOv3, and YOLOv4. Our developed supporting system for lesion detection can run at 14.85 FPS on an embedded Jetson AGX Xavier or 31.92 FPS on an RTX 3090. The detection results of various types of lesions are promising, mostly on malignant lesions such as gastric cancers. The proposed system can be deployed as an assistant tool in endoscopy to reduce missed detection of lesions. Our code is available at <uri>https://github.com/hanhtran201/GIFCOS-DT</uri>. |
| format | Article |
| id | doaj-art-6a8510d696824d0697cea734b60cd2f3 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6a8510d696824d0697cea734b60cd2f32024-11-12T00:01:38ZengIEEEIEEE Access2169-35362024-01-011216369816371410.1109/ACCESS.2024.349183310744010GIFCOS-DT: One Stage Detection of Gastrointestinal Tract Lesions From Endoscopic Images With Distance TransformThanh-Hai Tran0https://orcid.org/0000-0003-3133-3361Danh Huy Vu1https://orcid.org/0009-0006-8469-6552Minh Hanh Tran2https://orcid.org/0009-0000-1505-5758Viet Hang Dao3https://orcid.org/0000-0002-3685-9496Hai Vu4https://orcid.org/0000-0003-2880-4417Thi Thuy Nguyen5https://orcid.org/0000-0002-9358-6201School 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, VietnamHanoi Medical University Hospital, Hanoi, VietnamSchool of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, VietnamSchool of Science, Engineering & Technology, RMIT University, Ho Chi Minh, VietnamThis study aims at developing a computer-aided diagnostic system based on deep learning techniques for detecting various typical lesions during endoscopic examinations in the human gastrointestinal tract. We propose a lesion detection model, namely called GIFCOS-DT, that is built upon a one-stage backbone for object detection (Fully Convolutional One-Stage Object Detection - FCOS). For the proposed model, to deal with the diverse shapes and appearance of the lesions, we introduce a new loss function based on Distance Transform, that better describes the elongated or curved shapes of lesions than the common loss functions like Intersection of Union or centroid loss. We then deploy the detection model on an embedded device that connects to the endoscopic machine to assist endoscopists during examinations. A multithread technique is employed to accelerate the processing times of all steps of the system. Extensive experiments have been conducted on two challenging datasets, the benchmark dataset (Kvasir-SEG) and our newly collected dataset (IGH_GIEndoLesion-SEG), which include various typical lesions of the gastrointestinal (GI) tract (reflux esophagitis, esophageal cancer, helicobacter pylori negative gastritis, helicobacter pylori positive gastritis, gastric cancer, duodenal ulcer, and colorectal polyps). Experimental results show that our proposed methods outperform the original FCOS by 4.2% and 7.2% on Kvasir-SEG and our collected dataset respectively in terms of the average <inline-formula> <tex-math notation="LaTeX">$AP_{50}$ </tex-math></inline-formula> score. On the Kvasir-SEG dataset, the GIFCOS-DT outperforms state-of-the-art detectors such as Faster R-CNN, DETR, YOLOv3, and YOLOv4. Our developed supporting system for lesion detection can run at 14.85 FPS on an embedded Jetson AGX Xavier or 31.92 FPS on an RTX 3090. The detection results of various types of lesions are promising, mostly on malignant lesions such as gastric cancers. The proposed system can be deployed as an assistant tool in endoscopy to reduce missed detection of lesions. Our code is available at <uri>https://github.com/hanhtran201/GIFCOS-DT</uri>.https://ieeexplore.ieee.org/document/10744010/Distance transformfully convolutional networksobject detectionendoscopygastrointestinal tractlesion detection |
| spellingShingle | Thanh-Hai Tran Danh Huy Vu Minh Hanh Tran Viet Hang Dao Hai Vu Thi Thuy Nguyen GIFCOS-DT: One Stage Detection of Gastrointestinal Tract Lesions From Endoscopic Images With Distance Transform IEEE Access Distance transform fully convolutional networks object detection endoscopy gastrointestinal tract lesion detection |
| title | GIFCOS-DT: One Stage Detection of Gastrointestinal Tract Lesions From Endoscopic Images With Distance Transform |
| title_full | GIFCOS-DT: One Stage Detection of Gastrointestinal Tract Lesions From Endoscopic Images With Distance Transform |
| title_fullStr | GIFCOS-DT: One Stage Detection of Gastrointestinal Tract Lesions From Endoscopic Images With Distance Transform |
| title_full_unstemmed | GIFCOS-DT: One Stage Detection of Gastrointestinal Tract Lesions From Endoscopic Images With Distance Transform |
| title_short | GIFCOS-DT: One Stage Detection of Gastrointestinal Tract Lesions From Endoscopic Images With Distance Transform |
| title_sort | gifcos dt one stage detection of gastrointestinal tract lesions from endoscopic images with distance transform |
| topic | Distance transform fully convolutional networks object detection endoscopy gastrointestinal tract lesion detection |
| url | https://ieeexplore.ieee.org/document/10744010/ |
| work_keys_str_mv | AT thanhhaitran gifcosdtonestagedetectionofgastrointestinaltractlesionsfromendoscopicimageswithdistancetransform AT danhhuyvu gifcosdtonestagedetectionofgastrointestinaltractlesionsfromendoscopicimageswithdistancetransform AT minhhanhtran gifcosdtonestagedetectionofgastrointestinaltractlesionsfromendoscopicimageswithdistancetransform AT viethangdao gifcosdtonestagedetectionofgastrointestinaltractlesionsfromendoscopicimageswithdistancetransform AT haivu gifcosdtonestagedetectionofgastrointestinaltractlesionsfromendoscopicimageswithdistancetransform AT thithuynguyen gifcosdtonestagedetectionofgastrointestinaltractlesionsfromendoscopicimageswithdistancetransform |