Diagnostics (Jun 2024)

Deep Learning-Based Prediction Model for the Cobb Angle in Adolescent Idiopathic Scoliosis Patients

  • Chun-Sing (Elvis) Chui,
  • Zhong He,
  • Tsz-Ping Lam,
  • Ka-Kwan (Kyle) Mak,
  • Hin-Ting (Randy) Ng,
  • Chun-Hai (Ericsson) Fung,
  • Mei-Shuen Chan,
  • Sheung-Wai Law,
  • Yuk-Wai (Wayne) Lee,
  • Lik-Hang (Alec) Hung,
  • Chiu-Wing (Winnie) Chu,
  • Sze-Yi (Sibyl) Mak,
  • Wing-Fung (Edmond) Yau,
  • Zhen Liu,
  • Wu-Jun Li,
  • Zezhang Zhu,
  • Man Yeung (Ronald) Wong,
  • Chun-Yiu (Jack) Cheng,
  • Yong Qiu,
  • Shu-Hang (Patrick) Yung

DOI
https://doi.org/10.3390/diagnostics14121263
Journal volume & issue
Vol. 14, no. 12
p. 1263

Abstract

Read online

Scoliosis, characterized by spine deformity, is most common in adolescent idiopathic scoliosis (AIS). Manual Cobb angle measurement limitations underscore the need for automated tools. This study employed a vertebral landmark extraction method and Feedforward Neural Network (FNN) to predict scoliosis progression in 79 AIS patients. The novel intervertebral angles matrix format showcased results. The mean absolute error for the intervertebral angle progression was 1.5 degrees, while the Pearson correlation of the predicted Cobb angles was 0.86. The accuracy in classifying Cobb angles (45°) was 0.85, with 0.65 sensitivity and 0.91 specificity. The FNN demonstrated superior accuracy, sensitivity, and specificity, aiding in tailored treatments for potential scoliosis progression. Addressing FNNs’ over-fitting issue through strategies like “dropout” or regularization could further enhance their performance. This study presents a promising step towards automated scoliosis diagnosis and prognosis.

Keywords