Improved detection of aortic dissection in non-contrast-enhanced chest CT using an attention-based deep learning model

被引:2
|
作者
Dong, Fenglei [1 ,2 ]
Song, Jiao [1 ,2 ]
Chen, Bo [1 ,2 ]
Xie, Xiaoxiao [1 ,2 ]
Cheng, Jianmin [1 ,2 ]
Song, Jiawen [1 ,2 ]
Huang, Qun [3 ]
机构
[1] Second Affiliated Hosp, Dept Radiol, East Sect Wenzhou Ave 1111, Wenzhou, Peoples R China
[2] Wenzhou Med Univ, Yuying Childrens Hosp, East Sect Wenzhou Ave 1111, Wenzhou, Peoples R China
[3] Wenzhou Med Univ, Affiliated Hosp 1, Dept Radiol, 1 Fanhai West Rd, Wenzhou, Peoples R China
关键词
Aortic dissection; Deep learning; Attention mechanism; Non -contrast -enhanced chest CT; COMPUTED-TOMOGRAPHY; DIAGNOSIS; IMAGES;
D O I
10.1016/j.heliyon.2024.e24547
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Rationale and objectives: This study investigated the effects of implementing an attention-based deep learning model for the detection of aortic dissection (AD) using non-contrast-enhanced chest computed tomography (CT). Materials and methods: We analysed the records of 1300 patients who underwent contrastenhanced chest CT at 2 medical centres between January 2015 and February 2023. We considered an internal cohort of 200 patients with AD and 200 patients without AD and an external test cohort of 40 patients with AD and 40 patients without AD. The internal cohort was divided into training and test sets, and a deep learning model was trained using 9600 CT images. A convolutional block attention module (CBAM) and a traditional deep learning architecture (namely, You Only Look Once version 5 [YOLOv5]) were combined into an attention-based model (i.e., YOLOv5-CBAM). Its performance was measured against the unmodified YOLOv5 model, and the accuracy, sensitivity, and specificity of the algorithm were evaluated by two independent radiologists. Results: The CBAM-based model outperformed the traditional deep learning model. In the external testing set, YOLOv5-CBAM achieved an area under the curve (AUC) of 0.938, accuracy of 91.5 %, sensitivity of 90.0 %, and specificity of 92.9 %, whereas the unmodified model achieved an AUC of 0.844, accuracy of 83.6 %, sensitivity of 71.2 %, and specificity of 96.0 %. The sensitivity results of the unmodified algorithms were not significantly different from those of the radiologists; however, the proposed YOLOv5-CBAM algorithm outperformed the unmodified algorithms in terms of detection. Conclusions: Incorporating the CBAM attention mechanism into a deep learning model can significantly improve AD detection in non-contrast-enhanced chest CT. This approach may aid radiologists in the timely and accurate diagnosis of AD, which is important for improving patient outcomes.
引用
收藏
页数:10
相关论文
共 50 条
  • [1] Deep learning algorithm for detection of aortic dissection on non-contrast-enhanced CT
    Hata, Akinori
    Yanagawa, Masahiro
    Yamagata, Kazuki
    Suzuki, Yuuki
    Kido, Shoji
    Kawata, Atsushi
    Doi, Shuhei
    Yoshida, Yuriko
    Miyata, Tomo
    Tsubamoto, Mitsuko
    Kikuchi, Noriko
    Tomiyama, Noriyuki
    EUROPEAN RADIOLOGY, 2021, 31 (02) : 1151 - 1159
  • [2] Deep learning algorithm for detection of aortic dissection on non-contrast-enhanced CT
    Akinori Hata
    Masahiro Yanagawa
    Kazuki Yamagata
    Yuuki Suzuki
    Shoji Kido
    Atsushi Kawata
    Shuhei Doi
    Yuriko Yoshida
    Tomo Miyata
    Mitsuko Tsubamoto
    Noriko Kikuchi
    Noriyuki Tomiyama
    European Radiology, 2021, 31 : 1151 - 1159
  • [3] Physical-Priors-Guided Aortic Dissection Detection Using Non-Contrast-Enhanced CT Images
    Ding, Zhengyao
    Hu, Yujian
    Zhang, Hongkun
    Wu, Fei
    Yang, Shifeng
    Du, Xiaolong
    Xiang, Yilang
    Li, Tian
    Chu, Xuesen
    Huang, Zhengxing
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2024, PT VII, 2024, 15007 : 551 - 561
  • [4] A deep learning algorithm for the detection of aortic dissection on non-contrast-enhanced computed tomography via the identification and segmentation of the true and false lumens of the aorta
    Cheng, Zhangbo
    Zhao, Lei
    Yan, Jun
    Zhang, Hongbo
    Lin, Shengmei
    Yin, Lei
    Peng, Changli
    Ma, Xiaohai
    Xie, Guoxi
    Sun, Lizhong
    QUANTITATIVE IMAGING IN MEDICINE AND SURGERY, 2024, 14 (10) : 7365 - 7378
  • [5] Detection of Aortic Dissection and Intramural Hematoma in Non-Contrast Chest Computed Tomography Using a You Only Look Once-Based Deep Learning Model
    Kim, Yu-Seop
    Kim, Jae Guk
    Choi, Hyun Young
    Lee, Dain
    Kong, Jin-Woo
    Kang, Gu Hyun
    Jang, Yong Soo
    Kim, Wonhee
    Lee, Yoonje
    Kim, Jihoon
    Shin, Dong Geum
    Park, Jae Keun
    Lee, Gayoung
    Kim, Bitnarae
    JOURNAL OF CLINICAL MEDICINE, 2024, 13 (22)
  • [6] Utility of non-contrast-enhanced CT for improved detection of arterial phase hyperenhancement in hepatocellular carcinoma
    Tiffany Hennedige
    Zhineng Jayson Yang
    Cheng Kang Ong
    Sudhakar Kundapur Venkatesh
    Abdominal Imaging, 2014, 39 : 1247 - 1254
  • [7] Utility of non-contrast-enhanced CT for improved detection of arterial phase hyperenhancement in hepatocellular carcinoma
    Hennedige, Tiffany
    Yang, Zhineng Jayson
    Ong, Cheng Kang
    Venkatesh, Sudhakar Kundapur
    ABDOMINAL IMAGING, 2014, 39 (06): : 1247 - 1254
  • [8] Study on screening and diagnosis of aortic dissection based on non-enhanced CT and deep learning
    Cheng, Z.
    Yan, J.
    Yin, L.
    Lin, S. M.
    Lin, J. Y.
    EUROPEAN HEART JOURNAL, 2024, 45
  • [9] A deep learning algorithm using contrast-enhanced computed tomography (CT) images for segmentation and rapid automatic detection of aortic dissection
    Cheng, Junlong
    Tian, Shengwei
    Yu, Long
    Ma, Xiang
    Xing, Yan
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2020, 62
  • [10] AUTOMATIC DETECTION OF AORTIC DISSECTION IN CONTRAST-ENHANCED CT
    Dehghan, Ehsan
    Wang, Hongzhi
    Syeda-Mahmood, Tanveer
    2017 IEEE 14TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2017), 2017, : 557 - 560