Validity and Reliability of Active Shape Models for the Estimation of Cobb Angle in Patients with Adolescent Idiopathic Scoliosis

Abstract

Choosing the most suitable treatment for scoliosis relies heavily on accurate and reproducible Cobb angle measurement from successive radiographs. The objective is to reduce variability of Cobb angle measurement by reducing user intervention and bias. Custom software to increase automation of the Cobb angle measurement from posteroanterior radiographs was developed using active shape models. Validity and reliability of the automated system against a manual and semiautomated measurement method was conducted by two examiners each performing measurements on three occasions from a test set (N = 22). A training set (N = 47) of radiographs representative of curves seen in a scoliosis clinic was used to train the software to recognize vertebrae from T4 to L4. Images with a maximum Cobb angle between 20 degrees and 50 degrees , excluding surgical cases, were selected for training and test sets. Automated Cobb angles were calculated using best-fit slopes of the detected vertebrae endplates. Intraclass correlation coefficient (ICC) and standard error of measurement (SEM) showed high intraexaminer (ICC > 0.90, SEM 2 degrees -3 degrees ) and interexaminer (ICC > 0.82, SEM 2 degrees -4 degrees ), but poor intermethod reliability (ICC = 0.30, SEM 8 degrees -9 degrees ). The automated method underestimated large curves. The reliability improved (ICC = 0.70, SEM 4 degrees -5 degrees ) with exclusion of the four largest curves (>40 degrees ) in the test set. The automated method was reliable for moderate-sized curves, and did detect vertebrae in larger curves with a modified training set of larger curves.

Measuring procedures to determine the Cobb angle in idiopathic scoliosis: a systematic review

“…Because the study by Allen et al [13] examined three different measuring procedures, we divided the reference column into two parts. The manual and digital procedures were then used as the reference test.…”

“…''fuzzy hough transform procedure [14]'', or initial points, i.e. the ''active shape procedure [13]'', to be imputed on a radiograph by the observer. The computer itself recognises the exact profile of the vertebrae or the landmarks, and will calculate the angle automatically.…”

“…Aside from the manual procedure, there are so-called digital computer-assisted (semi-automatic) [6][7][8][9][10][11][12], automatic [13,14] and smartphone app procedures [15,16].…”

Automatic Cobb Measurement of Scoliosis Based on Fuzzy Hough Transform with Vertebral Shape Prior

“…Compared with another computerized method proposed by Allen et al 8 , the proposed method did not require the training set. As long as each individual vertebra tilted less than 45°, the accuracy of the proposed method had no relations with the severity of the spinal curve.…”

“…Allen et al 8 developed an automatic Cobb measurement method based on active shape models, where the training set was required, and the measurement results heavily relied on the training data. Chockalingam et al 9 proposed a method to measure the Cobb angle automatically.…”