Differential Diagnosis of Cysts and Granulomas Supported by Texture Analysis of Intraoral Radiographs

The aim of this study was to evaluate whether textural analysis could differentiate between the two common types of lytic lesions imaged with use of radiography. Sixty-two patients were enrolled in the study with intraoral radiograph images and a histological reference study. Full textural analysis...

Full description

Bibliographic Details
Main Authors: Elżbieta Pociask, Karolina Nurzynska, Rafał Obuchowicz, Paulina Bałon, Daniel Uryga, Michał Strzelecki, Andrzej Izworski, Adam Piórkowski
Format: Article
Language:English
Published: MDPI AG 2021-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/21/22/7481
_version_ 1827675425872019456
author Elżbieta Pociask
Karolina Nurzynska
Rafał Obuchowicz
Paulina Bałon
Daniel Uryga
Michał Strzelecki
Andrzej Izworski
Adam Piórkowski
author_facet Elżbieta Pociask
Karolina Nurzynska
Rafał Obuchowicz
Paulina Bałon
Daniel Uryga
Michał Strzelecki
Andrzej Izworski
Adam Piórkowski
author_sort Elżbieta Pociask
collection DOAJ
description The aim of this study was to evaluate whether textural analysis could differentiate between the two common types of lytic lesions imaged with use of radiography. Sixty-two patients were enrolled in the study with intraoral radiograph images and a histological reference study. Full textural analysis was performed using MaZda software. For over 10,000 features, logistic regression models were applied. Fragments containing lesion edges were characterized by significant correlation of structural information. Although the input images were stored using lossy compression and their scale was not preserved, the obtained results confirmed the possibility of distinguishing between cysts and granulomas with use of textural analysis of intraoral radiographs. It was shown that the important information distinguishing the aforementioned types of lesions is located at the edges and not within the lesion.
first_indexed 2024-03-10T05:04:52Z
format Article
id doaj.art-38b6a419283f4af6ab805bc7d67e2c1e
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-10T05:04:52Z
publishDate 2021-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-38b6a419283f4af6ab805bc7d67e2c1e2023-11-23T01:24:02ZengMDPI AGSensors1424-82202021-11-012122748110.3390/s21227481Differential Diagnosis of Cysts and Granulomas Supported by Texture Analysis of Intraoral RadiographsElżbieta Pociask0Karolina Nurzynska1Rafał Obuchowicz2Paulina Bałon3Daniel Uryga4Michał Strzelecki5Andrzej Izworski6Adam Piórkowski7Department of Biocybernetics and Biomedical Engineering, AGH University of Science and Technology, 30-059 Krakow, PolandDepartment of Algorithmics and Software, Silesian University of Technology, 44-100 Gliwice, PolandDepartment of Diagnostic Imaging, Medical College, Jagiellonian University, 31-501 Krakow, PolandDepartment of Biocybernetics and Biomedical Engineering, AGH University of Science and Technology, 30-059 Krakow, PolandDepartment of Oral Surgery, Medical College, Jagiellonian University, 31-155 Krakow, PolandInstitute of Electronics, Lodz University of Technology, 93-590 Lodz, PolandDepartment of Biocybernetics and Biomedical Engineering, AGH University of Science and Technology, 30-059 Krakow, PolandDepartment of Biocybernetics and Biomedical Engineering, AGH University of Science and Technology, 30-059 Krakow, PolandThe aim of this study was to evaluate whether textural analysis could differentiate between the two common types of lytic lesions imaged with use of radiography. Sixty-two patients were enrolled in the study with intraoral radiograph images and a histological reference study. Full textural analysis was performed using MaZda software. For over 10,000 features, logistic regression models were applied. Fragments containing lesion edges were characterized by significant correlation of structural information. Although the input images were stored using lossy compression and their scale was not preserved, the obtained results confirmed the possibility of distinguishing between cysts and granulomas with use of textural analysis of intraoral radiographs. It was shown that the important information distinguishing the aforementioned types of lesions is located at the edges and not within the lesion.https://www.mdpi.com/1424-8220/21/22/7481texture featuresclassificationperiapical lesionsintraoral radiographytSNEgranulomas
spellingShingle Elżbieta Pociask
Karolina Nurzynska
Rafał Obuchowicz
Paulina Bałon
Daniel Uryga
Michał Strzelecki
Andrzej Izworski
Adam Piórkowski
Differential Diagnosis of Cysts and Granulomas Supported by Texture Analysis of Intraoral Radiographs
Sensors
texture features
classification
periapical lesions
intraoral radiography
tSNE
granulomas
title Differential Diagnosis of Cysts and Granulomas Supported by Texture Analysis of Intraoral Radiographs
title_full Differential Diagnosis of Cysts and Granulomas Supported by Texture Analysis of Intraoral Radiographs
title_fullStr Differential Diagnosis of Cysts and Granulomas Supported by Texture Analysis of Intraoral Radiographs
title_full_unstemmed Differential Diagnosis of Cysts and Granulomas Supported by Texture Analysis of Intraoral Radiographs
title_short Differential Diagnosis of Cysts and Granulomas Supported by Texture Analysis of Intraoral Radiographs
title_sort differential diagnosis of cysts and granulomas supported by texture analysis of intraoral radiographs
topic texture features
classification
periapical lesions
intraoral radiography
tSNE
granulomas
url https://www.mdpi.com/1424-8220/21/22/7481
work_keys_str_mv AT elzbietapociask differentialdiagnosisofcystsandgranulomassupportedbytextureanalysisofintraoralradiographs
AT karolinanurzynska differentialdiagnosisofcystsandgranulomassupportedbytextureanalysisofintraoralradiographs
AT rafałobuchowicz differentialdiagnosisofcystsandgranulomassupportedbytextureanalysisofintraoralradiographs
AT paulinabałon differentialdiagnosisofcystsandgranulomassupportedbytextureanalysisofintraoralradiographs
AT danieluryga differentialdiagnosisofcystsandgranulomassupportedbytextureanalysisofintraoralradiographs
AT michałstrzelecki differentialdiagnosisofcystsandgranulomassupportedbytextureanalysisofintraoralradiographs
AT andrzejizworski differentialdiagnosisofcystsandgranulomassupportedbytextureanalysisofintraoralradiographs
AT adampiorkowski differentialdiagnosisofcystsandgranulomassupportedbytextureanalysisofintraoralradiographs