A combined feature set for automatic diaphyseal Tibial fracture classification from X-Ray images. (January 2022)

• Record Type: Journal Article
• Authors: V., Kumar Swamy; Anami, Basavaraj S.; Latte, Mrityunjaya V.
• Is Part Of: Biomedical signal processing and control. Volume 71(2022)Part A
• Publication Date: 2022-01
• Subjects: Diaphyseal fracture classification -- X-ray images -- Artificial neural network; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.103119
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Combined feature set for Diaphyseal Tibial fracture detection using X-Ray images is defined. Knowledge gained by Orthopaedic doctors are deployed on image processing algorithms. The work is useful to give second opinion to practicing Orthopaedic doctors. The proposed method is compared with state-of-the-art methods in the related study. Abstract: In Orthopaedics, fracture detection is considered one of the challenging tasks with x-ray images. The proposed methodology uses a novel feature-set to classify diaphyseal Tibial fractures using an Artificial Neural Network. The task of classification is carried out in two levels. The first level involves the classification of images into normal and fractured. The second level comprises of classification into three types of fractures, namely, simple, wedge and complex type. Around 12, 000 X-Ray images are used as a dataset, collected from local hospitals and publicly available musculoskeletal radiographs. The local features such as Hough lines, texture values, number of intersection points, number of fragments and local binary patterns are deployed in the work. Performance-based feature reduction is carried out. The experimentation performed with individuals, a combination of two, three, four and five features, has revealed an average classification accuracy of 98.59%. Along with BPNN, other classifiers, namely, k-NN and DT are used. Results show that the method outperforms the state-of-the-art works and are found encouraging. The work is useful for Orthopaedic practitioners and extendable to other types of bones.