A convolutional neural network to detect scoliosis treatment in radiographs
TypeArticles dans des revues avec comité de lecture
Purpose The aim of this work is to propose a classiﬁcation algorithm to automatically detect treatment for scoliosis (brace, implant or no treatment) in postero-anterior radiographs. Such automatic labelling of radiographs could represent a step towards global automatic radiological analysis. Methods Seven hundred and ninety-six frontal radiographies of adolescents were collected (84 patients wearing a brace, 325 with a spinal implant and 387 reference images with no treatment). The dataset was augmented to a total of 2096 images. A classiﬁcation model was built, composed by a forward convolutional neural network (CNN) followed by a discriminant analysis; the output was a probability for a given image to contain a brace, a spinal implant or none. The model was validated with a stratiﬁed tenfold cross-validation procedure. Performance was estimated by calculating the average accuracy. Results 98.3% of the radiographs were correctly classiﬁed as either reference, brace or implant, excluding 2.0% unclassiﬁed images. 99.7% of brace radiographs were correctly detected, while most of the errors occurred in the reference group (i.e. 2.1% of reference images were wrongly classiﬁed). Conclusion The proposed classiﬁcation model, the originality of which is the coupling of a CNN with discriminant analysis, can be used to automatically label radiographs for the presence of scoliosis treatment. This information is usually missing from DICOM metadata, so such method could facilitate the use of large databases. Furthermore, the same model architecture could potentially be applied for other radiograph classiﬁcations, such as sex and presence of scoliotic deformity.
Files in this item
Showing items related by title, author, creator and subject.
Vertebral rotation estimation from frontal X-rays using a quasi-automated pedicle detection method EBRAHIMI, Shahin; GAJNY, Laurent; VERGARI, Claudio; ANGELINI, Elsa D; SKALLI, Wafa (Springer, 2019)Purpose Measurement of vertebral axial rotation (VAR) is relevant for the assessment of scoliosis. Stokes method allows estimating VAR in frontal X-rays from the relative position of the pedicles and the vertebral body. ...
YANG, Zixin; SKALLI, Wafa; VERGARI, Claudio; ANGELINI, Elsa; GAJNY, Laurent (Springer International Publishing, 2019)Manually annotating medical images with few landmarks to initialize 3D shape models is a common practice. For instance, when reconstructing the 3D spine from biplanar X-rays, the spinal midline, passing through vertebrae ...
Quasi-automatic 3D reconstruction of the full spine from low-dose biplanar X-rays based on statistical inferences and image analysis GAJNY, Laurent; EBRAHIMI, Shahin; VERGARI, Claudio; ANGELINI, Elsa; SKALLI, Wafa (Springer Nature, 2018)Purpose: To design a quasi-automated three-dimensional reconstruction method of the spine from biplanar X-rays as the daily used method in clinical routine is based on manual adjustments of a trained operator and the ...
Quasi-automatic early detection of progressive idiopathic scoliosis from biplanar radiography: a preliminary validation VERGARI, Claudio; GAJNY, Laurent; COURTOIS, Isabelle; EBERMEYER, Eric; ABELIN-GENEVOIS, Kariman; KIM, Youngwoo; LANGLAIS, Tristan; VIALLE, Raphaël; ASSI, Ayman; GHANEM, Ismat; DUBOUSSET, Jean; SKALLI, Wafa (2019)Purpose To validate the predictive power and reliability of a novel quasi-automatic method to calculate the severity index of adolescent idiopathic scoliosis (AIS). Methods Fifty-five AIS patients were prospectively ...
VERGARI, Claudio; VERGARI, Claudio; ROUCH, Philippe; DUBOIS, Guillaume; BONNEAU, Dominique; DUBOUSSET, Jean; TANTER, Mickael; GENNISSON, Jean-Luc; SKALLI, Wafa (SAGE, 2014)Patient-specific numerical simulation of the spine is a useful tool both in clinic and research. While geometrical personalization of the spine is no more an issue, thanks to recent technological advances, non-invasive ...