Hybrid Deep Learning Approach for Automatic Detection in Musculoskeletal Radiographs
The practice of Deep Convolution neural networks in the field of medicine has congregated immense success and significance in present situations. Previously, researchers have developed numerous models for detecting abnormalities in musculoskeletal radiographs of upper extremities, but did not succee...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-04-01
|
Series: | Biology |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-7737/11/5/665 |
_version_ | 1797501535636160512 |
---|---|
author | Gurpreet Singh Darpan Anand Woong Cho Gyanendra Prasad Joshi Kwang Chul Son |
author_facet | Gurpreet Singh Darpan Anand Woong Cho Gyanendra Prasad Joshi Kwang Chul Son |
author_sort | Gurpreet Singh |
collection | DOAJ |
description | The practice of Deep Convolution neural networks in the field of medicine has congregated immense success and significance in present situations. Previously, researchers have developed numerous models for detecting abnormalities in musculoskeletal radiographs of upper extremities, but did not succeed in achieving respectable accuracy in the case of finger radiographs. A novel deep neural network-based hybrid architecture named ComDNet-512 is proposed in this paper to efficiently detect the bone abnormalities in the musculoskeletal radiograph of a patient. ComDNet-512 comprises a three-phase pipeline structure: compression, training of the dense neural network, and progressive resizing. The ComDNet-512 hybrid model is trained with finger radiographs samples to make a binary prediction, i.e., normal or abnormal bones. The proposed model showed phenomenon outcomes when cross-validated on the testing samples of arthritis patients and gives many superior results when compared with state-of-the-art practices. The model is able to achieve an area under the ROC curve (AUC) equal to 0.894 (sensitivity = 0.941 and specificity = 0.847). The Precision, Recall, F1 Score, and Kappa values, recorded as 0.86, 0.94, 0.89, and 0.78, respectively, are better than any of the previous models’. With an increasing appearance of enormous cases of musculoskeletal conditions in people, deep learning-based computational solutions can play a big role in performing automated detections in the future. |
first_indexed | 2024-03-10T03:19:50Z |
format | Article |
id | doaj.art-d2a4982387414b42aa7fff7cafc94f58 |
institution | Directory Open Access Journal |
issn | 2079-7737 |
language | English |
last_indexed | 2024-03-10T03:19:50Z |
publishDate | 2022-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Biology |
spelling | doaj.art-d2a4982387414b42aa7fff7cafc94f582023-11-23T10:06:43ZengMDPI AGBiology2079-77372022-04-0111566510.3390/biology11050665Hybrid Deep Learning Approach for Automatic Detection in Musculoskeletal RadiographsGurpreet Singh0Darpan Anand1Woong Cho2Gyanendra Prasad Joshi3Kwang Chul Son4Department of Computer Science and Engineering, Chandigarh University, Mohali 140413, IndiaDepartment of Computer Science and Engineering, Chandigarh University, Mohali 140413, IndiaDepartment of Software Convergence, Daegu Catholic University, Gyeongsan 38430, KoreaDepartment of Computer Science and Engineering, Sejong University, Seoul 05006, KoreaDepartment of Information Contents, Kwangwoon University, Seoul 01897, KoreaThe practice of Deep Convolution neural networks in the field of medicine has congregated immense success and significance in present situations. Previously, researchers have developed numerous models for detecting abnormalities in musculoskeletal radiographs of upper extremities, but did not succeed in achieving respectable accuracy in the case of finger radiographs. A novel deep neural network-based hybrid architecture named ComDNet-512 is proposed in this paper to efficiently detect the bone abnormalities in the musculoskeletal radiograph of a patient. ComDNet-512 comprises a three-phase pipeline structure: compression, training of the dense neural network, and progressive resizing. The ComDNet-512 hybrid model is trained with finger radiographs samples to make a binary prediction, i.e., normal or abnormal bones. The proposed model showed phenomenon outcomes when cross-validated on the testing samples of arthritis patients and gives many superior results when compared with state-of-the-art practices. The model is able to achieve an area under the ROC curve (AUC) equal to 0.894 (sensitivity = 0.941 and specificity = 0.847). The Precision, Recall, F1 Score, and Kappa values, recorded as 0.86, 0.94, 0.89, and 0.78, respectively, are better than any of the previous models’. With an increasing appearance of enormous cases of musculoskeletal conditions in people, deep learning-based computational solutions can play a big role in performing automated detections in the future.https://www.mdpi.com/2079-7737/11/5/665deep learningmusculoskeletal abnormalitiespredictionconvolutional neural networkmachine learningartificial intelligence |
spellingShingle | Gurpreet Singh Darpan Anand Woong Cho Gyanendra Prasad Joshi Kwang Chul Son Hybrid Deep Learning Approach for Automatic Detection in Musculoskeletal Radiographs Biology deep learning musculoskeletal abnormalities prediction convolutional neural network machine learning artificial intelligence |
title | Hybrid Deep Learning Approach for Automatic Detection in Musculoskeletal Radiographs |
title_full | Hybrid Deep Learning Approach for Automatic Detection in Musculoskeletal Radiographs |
title_fullStr | Hybrid Deep Learning Approach for Automatic Detection in Musculoskeletal Radiographs |
title_full_unstemmed | Hybrid Deep Learning Approach for Automatic Detection in Musculoskeletal Radiographs |
title_short | Hybrid Deep Learning Approach for Automatic Detection in Musculoskeletal Radiographs |
title_sort | hybrid deep learning approach for automatic detection in musculoskeletal radiographs |
topic | deep learning musculoskeletal abnormalities prediction convolutional neural network machine learning artificial intelligence |
url | https://www.mdpi.com/2079-7737/11/5/665 |
work_keys_str_mv | AT gurpreetsingh hybriddeeplearningapproachforautomaticdetectioninmusculoskeletalradiographs AT darpananand hybriddeeplearningapproachforautomaticdetectioninmusculoskeletalradiographs AT woongcho hybriddeeplearningapproachforautomaticdetectioninmusculoskeletalradiographs AT gyanendraprasadjoshi hybriddeeplearningapproachforautomaticdetectioninmusculoskeletalradiographs AT kwangchulson hybriddeeplearningapproachforautomaticdetectioninmusculoskeletalradiographs |