ItemArticle

A novel wide slice kronecker forward fractional network for osteoporosis detection using knee X-ray image

Title
A novel wide slice kronecker forward fractional network for osteoporosis detection using knee X-ray image
Creator
Narayanan, Pughazendi; Jeevan Nagendra Kumar, Y.; Chandrasekhar, Rohith Bhat; Kumaresan, Praghash
Description
Osteoporosis is an asymptomatic and progressive skeletal disorder that maximizes the risk of fractures in people aged 50 to 60. Early and accurate detection is critical, yet challenging, due to the fine structural changes in bone that are often difficult to identify in routine medical images. Knee X-rays are commonly used diagnostic tools, but interpreting them for osteoporosis detection remains complex because of variations in bone geometry and trabecular patterns. To solve these challenges, the novel Wide Slice Kronecker Forward Fractional Network (WKFF-Net) is developed to detect osteoporosis efficiently. Initially, the input image is taken from the database for detection. Here, the denoising process is done using the Non-Local Means (NLM) filter, and the Otsu thresholding method is considered for the segmentation process. Further, a template search method is used for analyzing the femur geometry. Next, features, like spatial, adaptive Local Binary Patterns (aLBP), Convolutional Neural Networks (CNN), and medical-level features, are extracted, and osteoporosis detection is accomplished by the hybrid WKFF-Net model that integrates Deep Kronecker Network (DKN), Wide Slice Residual Network (WISeR), and fractional calculus. The experimental results obtained by the WKFF-Net are 90.868% accuracy, 92.876% True Positive Rate (TPR), 87.766% True Negative Rate (TNR), 89.888% precision, and 91.357% F1-score, for 90% of the training samples. 2026 Elsevier B.V.
Source
Knowledge-Based Systems;Volume;342;Issue;;Article No.;115806;
Date
01-01-2026
Publisher
Elsevier B.V.
Subject
Deep learning; Knee X-ray images; Non-local means filter; Ostu thresholding; Wide slice kronecker forward fractional network
Coverage
Narayanan P., Faculty of Science and Humanities, SRM Institute of Science and Technology (Ramapuram Campus), Chennai, 600 089, India; Jeevan Nagendra Kumar Y., Department of Information Technology, Gokaraju Rangaraju Institute of Engineering and Technology, Bachupally, Hyderabad, India; Chandrasekhar R.B., Department of Computer Science and Engineering Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences (SIMATS), Saveetha University, Tamil Nadu, Chennai, India; Kumaresan P., Department of Electronics and Communication Engineering, Christ University, Bengaluru, India
Rights
Restricted Access; Hardcopy may be available in the library
Relation
ISSN: 9507051; CODEN: KNSYE
Format
online
Language
English
Type
Article

Citation

Narayanan, Pughazendi; Jeevan Nagendra Kumar, Y.; Chandrasekhar, Rohith Bhat; Kumaresan, Praghash, “A novel wide slice kronecker forward fractional network for osteoporosis detection using knee X-ray image,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/22378.

Output Formats