Automated detection of otosclerosis with interpretable deep learning using temporal bone computed tomography images

被引:0
作者
Wang, Zheng [1 ,3 ]
Song, Jian [2 ,4 ]
Lin, Kaibin [1 ,3 ]
Hong, Wei [1 ,3 ]
Mao, Shuang [2 ,4 ]
Wu, Xuewen [2 ,4 ]
Zhang, Jianglin [5 ,6 ,7 ]
机构
[1] Hunan First Normal Univ, Sch Comp Sci, Changsha 410205, Peoples R China
[2] Cent South Univ, Dept Otorhinolaryngol, Xiangya Hosp, Changsha, Hunan, Peoples R China
[3] Key Lab Hunan Prov Stat Learning & Intelligent Com, Changsha 410205, Peoples R China
[4] Prov Key Lab Otolaryngol Crit Dis, Changsha, Hunan, Peoples R China
[5] Southern Univ Sci & Technol, Jinan Univ, Shenzhen Peoples Hosp, Affiliated Hosp 1,Clin Med Coll 2,Dept Dermatol, Shenzhen 518020, Guangdong, Peoples R China
[6] Natl Clin Res Ctr Skin Dis, Candidate Branch, Shenzhen 518020, Guangdong, Peoples R China
[7] Southern Univ Sci & Technol, Jinan Univ, Shenzhen Peoples Hosp, Affiliated Hosp 1,Clin Med Coll 2,Dept Geriatr, Shenzhen 518020, Guangdong, Peoples R China
基金
中国国家自然科学基金;
关键词
Computed tomography; Deep learning; Area under the receiver operating; characteristic curve; Temporal bone computed tomography; Interpretability;
D O I
10.1016/j.heliyon.2024.e29670
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
Objective: This study aimed to develop an automated detection schema for otosclerosis with interpretable deep learning using temporal bone computed tomography images. Methods: With approval from the institutional review board, we retrospectively analyzed highresolution computed tomography scans of the temporal bone of 182 participants with otosclerosis (67 male subjects and 115 female subjects; average age, 36.42 years) and 157 participants without otosclerosis (52 male subjects and 102 female subjects; average age, 30.61 years) using deep learning. Transfer learning with the pretrained VGG19, Mask RCNN, and EfficientNet models was used. In addition, 3 clinical experts compared the system's performance by reading the same computed tomography images for a subset of 35 unseen subjects. An area under the receiver operating characteristic curve and a saliency map were used to further evaluate the diagnostic performance. Results: In prospective unseen test data, the diagnostic performance of the automatically interpretable otosclerosis detection system at the optimal threshold was 0.97 and 0.98 for sensitivity and specificity, respectively. In comparison with the clinical acumen of otolaryngologists at P < 0.05, the proposed system was not significantly different. Moreover, the area under the receiver operating characteristic curve for the proposed system was 0.99, indicating satisfactory diagnostic accuracy. Conclusion: Our research develops and evaluates a deep learning system that detects otosclerosis at a level comparable with clinical otolaryngologists. Our system is an effective schema for the differential diagnosis of otosclerosis in computed tomography examinations.
引用
收藏
页数:13
相关论文
共 50 条
  • [21] Lung Nodule Classification on Computed Tomography Images Using Deep Learning
    Amrita Naik
    Damodar Reddy Edla
    Wireless Personal Communications, 2021, 116 : 655 - 690
  • [22] Lung Nodule Classification on Computed Tomography Images Using Deep Learning
    Naik, Amrita
    Edla, Damodar Reddy
    WIRELESS PERSONAL COMMUNICATIONS, 2021, 116 (01) : 655 - 690
  • [23] Deep learning reconstruction for high-resolution computed tomography images of the temporal bone: comparison with hybrid iterative reconstruction
    Fujita, Nana
    Yasaka, Koichiro
    Hatano, Sosuke
    Sakamoto, Naoya
    Kurokawa, Ryo
    Abe, Osamu
    NEURORADIOLOGY, 2024, 66 (07) : 1105 - 1112
  • [24] Deep Learning for Detection of Intracranial Aneurysms from Computed Tomography Angiography Images
    Liu, Xiujuan
    Mao, Jun
    Sun, Ning
    Yu, Xiangrong
    Chai, Lei
    Tian, Ye
    Wang, Jianming
    Liang, Jianchao
    Tao, Haiquan
    Yuan, Lihua
    Lu, Jiaming
    Wang, Yang
    Zhang, Bing
    Wu, Kaihua
    Wang, Yiding
    Chen, Mengjiao
    Wang, Zhishun
    Lu, Ligong
    JOURNAL OF DIGITAL IMAGING, 2023, 36 (01) : 114 - 123
  • [25] Deep Learning for Detection of Intracranial Aneurysms from Computed Tomography Angiography Images
    Xiujuan Liu
    Jun Mao
    Ning Sun
    Xiangrong Yu
    Lei Chai
    Ye Tian
    Jianming Wang
    Jianchao Liang
    Haiquan Tao
    Lihua Yuan
    Jiaming Lu
    Yang Wang
    Bing Zhang
    Kaihua Wu
    Yiding Wang
    Mengjiao Chen
    Zhishun Wang
    Ligong Lu
    Journal of Digital Imaging, 2023, 36 : 114 - 123
  • [26] A Deep Learning Approach for Automated Bone Removal from Computed Tomography Angiography of the Brain
    Masis Isikbay
    M. Travis Caton
    Evan Calabrese
    Journal of Digital Imaging, 2023, 36 : 964 - 972
  • [27] A Deep Learning Approach for Automated Bone Removal from Computed Tomography Angiography of the Brain
    Isikbay, Masis
    Caton, M. Travis
    Calabrese, Evan
    JOURNAL OF DIGITAL IMAGING, 2023, 36 (03) : 964 - 972
  • [28] Deep Learning-enabled Detection of Acute Ischemic Stroke using Brain Computed Tomography Images
    Babutain, Khalid
    Hussain, Muhammad
    Aboalsamh, Hatim
    Al-Hameed, Majed
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2021, 12 (12) : 386 - 397
  • [29] Automated identification of myocardial perfusion defects in dynamic cardiac computed tomography using deep learning
    Kim, Yoon-Chul
    Choe, Yeon Hyeon
    PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS, 2023, 107
  • [30] Automatic multi-label temporal bone computed tomography segmentation with deep learning
    Zhou, Langtao
    Li, Zhenhua
    INTERNATIONAL JOURNAL OF MEDICAL ROBOTICS AND COMPUTER ASSISTED SURGERY, 2023, 19 (05)