Cargando…

Adaptive IoU Thresholding for Improving Small Object Detection: A Proof-of-Concept Study of Hand Erosions Classification of Patients with Rheumatic Arthritis on X-ray Images

In recent years, much research evaluating the radiographic destruction of finger joints in patients with rheumatoid arthritis (RA) using deep learning models was conducted. Unfortunately, most previous models were not clinically applicable due to the small object regions as well as the close spatial...

Descripción completa

Detalles Bibliográficos
Autores principales: Radke, Karl Ludger, Kors, Matthias, Müller-Lutz, Anja, Frenken, Miriam, Wilms, Lena Marie, Baraliakos, Xenofon, Wittsack, Hans-Jörg, Distler, Jörg H. W., Abrar, Daniel B., Antoch, Gerald, Sewerin, Philipp
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9818241/
https://www.ncbi.nlm.nih.gov/pubmed/36611395
http://dx.doi.org/10.3390/diagnostics13010104
_version_ 1784864936896233472
author Radke, Karl Ludger
Kors, Matthias
Müller-Lutz, Anja
Frenken, Miriam
Wilms, Lena Marie
Baraliakos, Xenofon
Wittsack, Hans-Jörg
Distler, Jörg H. W.
Abrar, Daniel B.
Antoch, Gerald
Sewerin, Philipp
author_facet Radke, Karl Ludger
Kors, Matthias
Müller-Lutz, Anja
Frenken, Miriam
Wilms, Lena Marie
Baraliakos, Xenofon
Wittsack, Hans-Jörg
Distler, Jörg H. W.
Abrar, Daniel B.
Antoch, Gerald
Sewerin, Philipp
author_sort Radke, Karl Ludger
collection PubMed
description In recent years, much research evaluating the radiographic destruction of finger joints in patients with rheumatoid arthritis (RA) using deep learning models was conducted. Unfortunately, most previous models were not clinically applicable due to the small object regions as well as the close spatial relationship. In recent years, a new network structure called RetinaNets, in combination with the focal loss function, proved reliable for detecting even small objects. Therefore, the study aimed to increase the recognition performance to a clinically valuable level by proposing an innovative approach with adaptive changes in intersection over union (IoU) values during training of Retina Networks using the focal loss error function. To this end, the erosion score was determined using the Sharp van der Heijde (SvH) metric on 300 conventional radiographs from 119 patients with RA. Subsequently, a standard RetinaNet with different IoU values as well as adaptively modified IoU values were trained and compared in terms of accuracy, mean average accuracy (mAP), and IoU. With the proposed approach of adaptive IoU values during training, erosion detection accuracy could be improved to 94% and an mAP of 0.81 ± 0.18. In contrast Retina networks with static IoU values achieved only an accuracy of 80% and an mAP of 0.43 ± 0.24. Thus, adaptive adjustment of IoU values during training is a simple and effective method to increase the recognition accuracy of small objects such as finger and wrist joints.
format Online
Article
Text
id pubmed-9818241
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-98182412023-01-07 Adaptive IoU Thresholding for Improving Small Object Detection: A Proof-of-Concept Study of Hand Erosions Classification of Patients with Rheumatic Arthritis on X-ray Images Radke, Karl Ludger Kors, Matthias Müller-Lutz, Anja Frenken, Miriam Wilms, Lena Marie Baraliakos, Xenofon Wittsack, Hans-Jörg Distler, Jörg H. W. Abrar, Daniel B. Antoch, Gerald Sewerin, Philipp Diagnostics (Basel) Article In recent years, much research evaluating the radiographic destruction of finger joints in patients with rheumatoid arthritis (RA) using deep learning models was conducted. Unfortunately, most previous models were not clinically applicable due to the small object regions as well as the close spatial relationship. In recent years, a new network structure called RetinaNets, in combination with the focal loss function, proved reliable for detecting even small objects. Therefore, the study aimed to increase the recognition performance to a clinically valuable level by proposing an innovative approach with adaptive changes in intersection over union (IoU) values during training of Retina Networks using the focal loss error function. To this end, the erosion score was determined using the Sharp van der Heijde (SvH) metric on 300 conventional radiographs from 119 patients with RA. Subsequently, a standard RetinaNet with different IoU values as well as adaptively modified IoU values were trained and compared in terms of accuracy, mean average accuracy (mAP), and IoU. With the proposed approach of adaptive IoU values during training, erosion detection accuracy could be improved to 94% and an mAP of 0.81 ± 0.18. In contrast Retina networks with static IoU values achieved only an accuracy of 80% and an mAP of 0.43 ± 0.24. Thus, adaptive adjustment of IoU values during training is a simple and effective method to increase the recognition accuracy of small objects such as finger and wrist joints. MDPI 2022-12-29 /pmc/articles/PMC9818241/ /pubmed/36611395 http://dx.doi.org/10.3390/diagnostics13010104 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Radke, Karl Ludger
Kors, Matthias
Müller-Lutz, Anja
Frenken, Miriam
Wilms, Lena Marie
Baraliakos, Xenofon
Wittsack, Hans-Jörg
Distler, Jörg H. W.
Abrar, Daniel B.
Antoch, Gerald
Sewerin, Philipp
Adaptive IoU Thresholding for Improving Small Object Detection: A Proof-of-Concept Study of Hand Erosions Classification of Patients with Rheumatic Arthritis on X-ray Images
title Adaptive IoU Thresholding for Improving Small Object Detection: A Proof-of-Concept Study of Hand Erosions Classification of Patients with Rheumatic Arthritis on X-ray Images
title_full Adaptive IoU Thresholding for Improving Small Object Detection: A Proof-of-Concept Study of Hand Erosions Classification of Patients with Rheumatic Arthritis on X-ray Images
title_fullStr Adaptive IoU Thresholding for Improving Small Object Detection: A Proof-of-Concept Study of Hand Erosions Classification of Patients with Rheumatic Arthritis on X-ray Images
title_full_unstemmed Adaptive IoU Thresholding for Improving Small Object Detection: A Proof-of-Concept Study of Hand Erosions Classification of Patients with Rheumatic Arthritis on X-ray Images
title_short Adaptive IoU Thresholding for Improving Small Object Detection: A Proof-of-Concept Study of Hand Erosions Classification of Patients with Rheumatic Arthritis on X-ray Images
title_sort adaptive iou thresholding for improving small object detection: a proof-of-concept study of hand erosions classification of patients with rheumatic arthritis on x-ray images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9818241/
https://www.ncbi.nlm.nih.gov/pubmed/36611395
http://dx.doi.org/10.3390/diagnostics13010104
work_keys_str_mv AT radkekarlludger adaptiveiouthresholdingforimprovingsmallobjectdetectionaproofofconceptstudyofhanderosionsclassificationofpatientswithrheumaticarthritisonxrayimages
AT korsmatthias adaptiveiouthresholdingforimprovingsmallobjectdetectionaproofofconceptstudyofhanderosionsclassificationofpatientswithrheumaticarthritisonxrayimages
AT mullerlutzanja adaptiveiouthresholdingforimprovingsmallobjectdetectionaproofofconceptstudyofhanderosionsclassificationofpatientswithrheumaticarthritisonxrayimages
AT frenkenmiriam adaptiveiouthresholdingforimprovingsmallobjectdetectionaproofofconceptstudyofhanderosionsclassificationofpatientswithrheumaticarthritisonxrayimages
AT wilmslenamarie adaptiveiouthresholdingforimprovingsmallobjectdetectionaproofofconceptstudyofhanderosionsclassificationofpatientswithrheumaticarthritisonxrayimages
AT baraliakosxenofon adaptiveiouthresholdingforimprovingsmallobjectdetectionaproofofconceptstudyofhanderosionsclassificationofpatientswithrheumaticarthritisonxrayimages
AT wittsackhansjorg adaptiveiouthresholdingforimprovingsmallobjectdetectionaproofofconceptstudyofhanderosionsclassificationofpatientswithrheumaticarthritisonxrayimages
AT distlerjorghw adaptiveiouthresholdingforimprovingsmallobjectdetectionaproofofconceptstudyofhanderosionsclassificationofpatientswithrheumaticarthritisonxrayimages
AT abrardanielb adaptiveiouthresholdingforimprovingsmallobjectdetectionaproofofconceptstudyofhanderosionsclassificationofpatientswithrheumaticarthritisonxrayimages
AT antochgerald adaptiveiouthresholdingforimprovingsmallobjectdetectionaproofofconceptstudyofhanderosionsclassificationofpatientswithrheumaticarthritisonxrayimages
AT sewerinphilipp adaptiveiouthresholdingforimprovingsmallobjectdetectionaproofofconceptstudyofhanderosionsclassificationofpatientswithrheumaticarthritisonxrayimages