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
  • [41] DeepDR:An image guideddiabetic retinopathy detection technique using attention-based deep learning scheme
    Islam, Noman
    Saeed, Umair
    Naz, Rubina
    Tanveer, Jaweria
    Kumar, Kamlesh
    Shaikh, Aftab Ahmed
    2019 2ND INTERNATIONAL CONFERENCE ON NEW TRENDS IN COMPUTING SCIENCES (ICTCS), 2019, : 130 - 135
  • [42] Using contrast-enhanced CT and non-contrast-enhanced CT to predict EGFR mutation status in NSCLC patients—a radiomics nomogram analysis
    Xiaoyan Yang
    Min Liu
    Yanhong Ren
    Huang Chen
    Pengxin Yu
    Siyi Wang
    Rongguo Zhang
    Huaping Dai
    Chen Wang
    European Radiology, 2022, 32 : 2693 - 2703
  • [43] Attention-Based Deep Learning Model for Image Desaturation of SDO/AIA
    Zhang, Xinze
    Xu, Long
    Ren, Zhixiang
    Yu, Xuexin
    Li, Jia
    RESEARCH IN ASTRONOMY AND ASTROPHYSICS, 2023, 23 (08)
  • [44] An attention-based deep learning model for citywide traffic flow forecasting
    Zhou, Tao
    Huang, Bo
    Li, Rongrong
    Liu, Xiaoqian
    Huang, Zhihui
    INTERNATIONAL JOURNAL OF DIGITAL EARTH, 2022, 15 (01) : 323 - 344
  • [45] An attention-based hybrid deep learning model for EEG emotion recognition
    Yong Zhang
    Yidie Zhang
    Shuai Wang
    Signal, Image and Video Processing, 2023, 17 : 2305 - 2313
  • [46] An attention-based hybrid deep learning model for EEG emotion recognition
    Zhang, Yong
    Zhang, Yidie
    Wang, Shuai
    SIGNAL IMAGE AND VIDEO PROCESSING, 2023, 17 (05) : 2305 - 2313
  • [47] An attention-based deep learning model for multiple pedestrian attributes recognition
    Yaghoubi, Ehsan
    Borza, Diana
    Neves, Joao
    Kumar, Aruna
    Proenca, Hugo
    IMAGE AND VISION COMPUTING, 2020, 102 (102)
  • [48] Attention-Based Distributed Deep Learning Model for Air Quality Forecasting
    Mengara, Axel Gedeon Mengara
    Park, Eunyoung
    Jang, Jinho
    Yoo, Younghwan
    SUSTAINABILITY, 2022, 14 (06)
  • [49] Attention-Based Deep Learning Model for Arabic Handwritten Text Recognition
    Gader T.B.A.
    Echi A.K.
    Machine Graphics and Vision, 2022, 31 (1-4): : 49 - 73
  • [50] Learning to Drive at Unsignalized Intersections using Attention-based Deep Reinforcement Learning
    Seong, Hyunki
    Jung, Chanyoung
    Lee, Seungwook
    Shim, David Hyunchul
    2021 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC), 2021, : 559 - 566