Enhanced diagnosis of pes planus and pes cavus using deep learning-based segmentation of weight-bearing lateral foot radiographs: a comparative observer study

被引:0
作者
Ryu, Seung Min [1 ,6 ]
Shin, Keewon [2 ]
Shin, Soo Wung [3 ]
Lee, Sun Ho [4 ]
Seo, Su Min [5 ]
Koh, Seung Hong [5 ]
Ryu, Seung-Ah [5 ]
Kim, Ki-Hong [1 ]
Ko, Jeong Hwan [6 ]
Doh, Chang Hyun [7 ]
Choi, Young Rak [7 ]
Kim, Namkug [6 ,8 ,9 ]
机构
[1] Seoul Med Ctr, Dept Orthoped Surg, Seoul, South Korea
[2] Korea Univ, Coll Med, Dept Artificial Intelligence, Res Ctr, Seoul, South Korea
[3] Seoul Natl Univ, Dept Comp Sci & Engn, Seoul, South Korea
[4] Chonnam Natl Univ Hosp, Dept Orthoped Surg, Gwangju, South Korea
[5] Seoul Med Ctr, Dept Anesthesiol & Pain Med, Seoul, South Korea
[6] Univ Ulsan, Asan Med Inst Convergence Sci & Technol, Asan Med Ctr, Dept Biomed Engn,Coll Med, Seoul, South Korea
[7] Univ Ulsan, Coll Med, Asan Med Ctr, Dept Orthoped Surg, Seoul, South Korea
[8] Univ Ulsan, Asan Med Inst Convergence Sci & Technol, Asan Med Ctr, Dept Convergence Med,Coll Med, Seoul, South Korea
[9] Univ Ulsan, Res Inst Radiol, Asan Med Ctr, Dept Radiol,Coll Med, 26 Olymp Ro 43 Gil, Seoul 05505, South Korea
基金
新加坡国家研究基金会;
关键词
Deep learning; Artificial intelligence; Segmentation; Orthopaedics; X-rays; Computer-assisted diagnosis; ACQUIRED FLATFOOT DEFORMITY; ADULT; ALIGNMENT;
D O I
10.1007/s13534-024-00439-3
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
A weight-bearing lateral radiograph (WBLR) of the foot is a gold standard for diagnosing adult-acquired flatfoot deformity. However, it is difficult to measure the major axis of bones in WBLR without using auxiliary lines. Herein, we develop semantic segmentation with a deep learning model (DLm) on the WBLR of the foot for enhanced diagnosis of pes planus and pes cavus. We used 300 consecutive WBLRs from young Korean males. The semantic segmentation model was developed based on U2-Net. An expert orthopedic surgeon manually labeled ground truths. We used 200 radiographs for training, 100 for internal validation, and two external datasets for external validation. The model was trained using a hybrid loss function, combining Dice Loss and boundary-based loss, to enhance both overall segmentation accuracy and precise delineation of boundary regions between pes planus and pes cavus. Angle measurement errors with minimum moment of inertia (MMI) and ellipsoidal fitting (EF) based on the segmentation results were evaluated. The DLm exhibited better results than human observers. For internal validation, the absolute angle errors of the DLm using MMI and EF were 0.92 +/- 1.32 degrees and 1.34 +/- 2.07 degrees, respectively. In external validation, these errors were 1.17 +/- 1.60 degrees and 1.60 +/- 2.42 degrees for AMC's dataset, and 1.23 +/- 1.39 degrees and 1.68 +/- 1.98 degrees for the LERA dataset, respectively. The DLm showed higher overall diagnostic accuracy than human observers in identifying flatfoot angles, regardless of the measurement methods. The absolute angle errors and diagnostic accuracy of the developed DLm are superior to those of the three human observers. Furthermore, when comparing the angle measurement methods within the DLm, the MMI method proves to be more accurate than EF. Finally, the proposed deep learning model, particularly with the implementation of the U2-Net demonstrates enhanced boundary segmentation and achieves sufficient external validation results, affirming its applicability in the real clinical setting.
引用
收藏
页码:203 / 215
页数:13
相关论文
共 40 条
  • [1] Abousayed MM, 2017, JBJS REV, V5, DOI 10.2106/JBJS.RVW.16.00116
  • [2] Geometric 3D analyses of the foot and ankle using weight-bearing and non weight-bearing cone-beam CT images: The new standard?
    Broos, M.
    Berardo, S.
    Dobbe, J. G. G.
    Maas, M.
    Streekstra, G. J.
    Wellenberg, R. H. H.
    [J]. EUROPEAN JOURNAL OF RADIOLOGY, 2021, 138
  • [3] Reliability and correlation analysis of computed methods to convert conventional 2D radiological hindfoot measurements to a 3D setting using weightbearing CT
    Burssens, A.
    Peeters, J.
    Peiffer, M.
    Marien, R.
    Lenaerts, T.
    Vandeputte, G.
    Victor, J.
    [J]. INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2018, 13 (12) : 1999 - 2008
  • [4] Albumentations: Fast and Flexible Image Augmentations
    Buslaev, Alexander
    Iglovikov, Vladimir I.
    Khvedchenya, Eugene
    Parinov, Alex
    Druzhinin, Mikhail
    Kalinin, Alexandr A.
    [J]. INFORMATION, 2020, 11 (02)
  • [5] Cardoso MJ, 2022, MONAI OPEN SOURCE FR
  • [6] Techniques for 3D foot bone orientation angles in weight-bearing from cone-beam computed tomography
    Carrara, Claudio
    Belvedere, Claudio
    Caravaggi, Paolo
    Durante, Stefano
    Leardini, Alberto
    [J]. FOOT AND ANKLE SURGERY, 2021, 27 (02) : 168 - 174
  • [7] Weightbearing CT Scan Assessment of Foot Alignment in Patients With Hallux Rigidus
    Cheung, Zoe B.
    Myerson, Mark S.
    Tracey, Joseph
    Vulcano, Ettore
    [J]. FOOT & ANKLE INTERNATIONAL, 2018, 39 (01) : 67 - 74
  • [8] Chi TD, 1999, CLIN ORTHOP RELAT R, P81
  • [9] TIME-SERIES SEGMENTATION - A SLIDING WINDOW APPROACH
    CHU, CSJ
    [J]. INFORMATION SCIENCES, 1995, 85 (1-3) : 147 - 173
  • [10] Davidovits P., 2018, Physics in biology and medicine