Segment-based and patient-based segmentation of CTPA Image in pulmonary embolism using CBAM ResU-Net

Name: Theeraphat Trongmetheerat

Organization : Kamnoetvidya Science Academy

Email : theeraphat_t@kvis.ac.th

Name: Kanjanajak Sukprasert

Organization : Kamnoetvidya Science Academy

Email : kanjanajak_s@kvis.ac.th

Name: Kontee Netiwongsanon

Organization : Kamnoetvidya Science Academy

Email : kontee_n@kvis.ac.th

Name: Tanawan Leeboonngam

Organization : Kamnoetvidya Science Academy. Department of Biology and Environmental Science

Email : tanawan.l@kvis.ac.th

Name: Kanes Sumetpipat

Organization : Kamnoetvidya Science Academy. Department of Mathematics and Computer Science

Email : kanes.s@kvis.ac.th

keyword: Pulmonary embolism

LCSH: Tomography

; Convolutional neural networks

LCSH: Image segmentation

LCSH: Neural networks (Computer science)

LCSH: Diagnostic imaging

LCSH: Pattern recognition systems

Abstract: An accurate pulmonary embolism segmentation from computed tomography pulmonary angiography (CTPA) images is very important in pulmonary embolism diagnosis. However, the segmentation process nowadays is done manually by physicians, making the process time-consuming and the accuracy dependent on the physician’s ability. Hence, we focused on improving the accuracy of an automatic segmentation method by employing image preprocessing techniques and modifying U-Net architecture in many ways. This paper introduced ResU-Net (residual U-Net) and CBAM ResU-Net (ResU-Net with the addition of CBAM attention modules in the skip connections) models to this framework. Furthermore, we explored two training approaches: segment-based and patient-based. Our experimental results showed that segment-based models performed substantially better than patient-based models. Regardless of training approaches, the most accurate model was CBAM ResU-Net, which achieved up to 0.8719 in Dice score for the segment-based approach and 0.6751 for the patient-based approach

King Mongkut's University of Technology North Bangkok. Central Library

Address: BANGKOK

Email: library@kmutnb.ac.th

Created: 2023

Modified: 2025-03-04

Issued: 2025-03-04

บทความ/Article

application/pdf

BibliograpyCitation : In King Mongkut's University of Technology Thonburi. The 13th International Conference on Advances in Information Technology (IAIT 2023) (Article 21). Bangkok : King Mongkut's University of Technology Thonburi

eng

©copyrights King Mongkut's University of Technology North Bangkok

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	IAIT 2023 Article 21.pdf	769.95 KB

ใช้เวลา

0.050224 วินาที