An Automatic Classification Method for Adolescent Idiopathic Scoliosis Based on U-net and Support Vector Machine

Abstract The traditional manual method for adolescent idiopathic scoliosis diagnosis suffers from observer variability. Doctors need an objective, accurate and fast detection method which would help to overcome the problem encountered by the traditional classification. This study introduces new techniques, including automatic radiograph segmentation, scoliosis measurement and classification, based on artificial intelligence. Firstly, the vertebral region in the radiograph was segmented by U-net and the scoliosis measurement was performed on the segmented image. Secondly, SVM classification was conducted by extracting the curve features in posteroanterior images and supplementary parameters in lateral and bending images. Finally, the results of automatic scoliosis measurement were compared with the one made by surgeons and the accuracy of the proposed automatic classification method was verified by a test set. The U-net segmentation model was successfully established to segment the vertebrae and the differences between the measurement results obtained by the automatic and manual measurement method were less than one degree and the accuracy of the automatic curve identification approach was found to be 100%.

Download Full-text

THE ETIOLOGIC RELEVANCE OF 3-D PATHOANATOMY OF ADOLESCENT IDIOPATHIC SCOLIOSIS

Coluna/Columna ◽

10.1590/s1808-185120171604183510 ◽

2017 ◽

Vol 16 (4) ◽

pp. 302-307

Author(s):

Tom Schlösser ◽

Rob Brink ◽

René Castelein

Keyword(s):

Adolescent Idiopathic Scoliosis ◽

Idiopathic Scoliosis ◽

Three Dimensional ◽

Imaging Studies ◽

Cross Sectional ◽

Ongoing Research ◽

Biomechanical Loading ◽

Cross Sectional Imaging ◽

Sectional Imaging ◽

The One

ABSTRACT Despite many years of dedicated research into the etiopathogenesis of adolescent idiopathic scoliosis, there is still no single distinct cause for this puzzling condition. In this overview, we attempt to link knowledge on the complex three-dimensional pathoanatomy of AIS, based on our ongoing research in this field, with etiopathogenic questions. Evidence from multiple recent cross-sectional imaging studies is provided that supports the hypothesis that AIS has an intrinsic biomechanical basis: an imbalance between the biomechanical loading of the upright human spine due to its unique sagittal configuration on the one hand, and the body’s compensating mechanisms on the other. The question that remains in the etiology of AIS, and the focus of our ongoing research, is to determine what causes or induces this imbalance.

Download Full-text

A Novel Classification Method for Mild Adolescent Idiopathic Scoliosis Using 3D Ultrasound Imaging

Medicine in Novel Technology and Devices ◽

10.1016/j.medntd.2021.100075 ◽

2021 ◽

pp. 100075

Author(s):

D. Yang ◽

T.T.Y. Lee ◽

K.K.L. Lai ◽

Y.S. Wong ◽

L.N. Wong ◽

...

Keyword(s):

Adolescent Idiopathic Scoliosis ◽

Idiopathic Scoliosis ◽

Ultrasound Imaging ◽

3D Ultrasound ◽

Classification Method

Download Full-text

The effect of brace treatment on pulmonary functions in adolescent idiopathic scoliosis: An 8-month follow-up study

Journal of Back and Musculoskeletal Rehabilitation ◽

10.3233/bmr-200195 ◽

2021 ◽

pp. 1-7

Author(s):

Yasin Yurt ◽

İlker Yatar ◽

Mehtap Malkoç ◽

Yavuz Yakut ◽

Serpil Mıhçıoğlu ◽

...

Keyword(s):

Adolescent Idiopathic Scoliosis ◽

Idiopathic Scoliosis ◽

Vital Capacity ◽

Forced Expiratory Volume ◽

Pulmonary Functions ◽

Measurement Results ◽

Forced Expiratory Flow ◽

Permanent Effect ◽

Expiratory Flow

BACKGROUND: The instant effect of a brace on pulmonary functions of patients with adolescent idiopathic scoliosis (AIS) is known. However, the permanent effects of its regular use are still unclear. OBJECTIVE: This study aimed to determine whether a brace in patients with AIS had a permanent effect on respiratory functions. METHODS: Fifteen patients with a mean age of 13.2 ± 1.6 years, and a major Cobb angle of 25.8∘± 7.7∘ participated in this study. Lung volumes and respiratory muscle strength were measured with and without thoracolumbosacral brace, at the end of first month and follow-up period after the patients started using the brace for 23 hours daily. RESULTS: When the brace was on, the forced vital capacity (FVC), forced expiratory volume in 1 second (FEV1), ratio of FEV1/FVC, peak expiratory flow, and forced expiratory flow between 25% and 75% of vital capacity values were found to be lower at both first month and follow-up. After the follow-up, the measurement results did not differ from the results of the first month. CONCLUSIONS: The brace had a momentary restrictive effect on patients with AIS. However, it did not cause a permanent change in pulmonary functions after the 8-month follow-up.

Download Full-text

A Fast Classification Method of Faults in Power Electronic Circuits Based on Support Vector Machines

Metrology and Measurement Systems ◽

10.1515/mms-2017-0056 ◽

2017 ◽

Vol 24 (4) ◽

pp. 701-720 ◽

Cited By ~ 2

Author(s):

Jiang Cui ◽

Ge Shi ◽

Chunying Gong

Keyword(s):

Classification Problem ◽

Classification Performance ◽

Classification Method ◽

Fault Classification ◽

Support Vector ◽

Power Electronic ◽

Electronic Circuits ◽

Power Electronic Circuits ◽

The One ◽

Fast Classification

AbstractFault detection and location are important and front-end tasks in assuring the reliability of power electronic circuits. In essence, both tasks can be considered as the classification problem. This paper presents a fast fault classification method for power electronic circuits by using the support vector machine (SVM) as a classifier and the wavelet transform as a feature extraction technique. Using one-against-rest SVM and one-against-one SVM are two general approaches to fault classification in power electronic circuits. However, these methods have a high computational complexity, therefore in this design we employ a directed acyclic graph (DAG) SVM to implement the fault classification. The DAG SVM is close to the one-against-one SVM regarding its classification performance, but it is much faster. Moreover, in the presented approach, the DAG SVM is improved by introducing the method of Knearest neighbours to reduce some computations, so that the classification time can be further reduced. A rectifier and an inverter are demonstrated to prove effectiveness of the presented design.

Download Full-text