Radiomics in bone pathology of the jaws
Dentomaxillofacial Radiology · 01.01.2023 · 52 (1)
DOI: 10.1259/dmfr.20220225 ↗Kurz gefasst
Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, erschienen am 01.01.2023. Verfasst von Glaucia Nize Martins Santos und 6 weiteren Autor:innen. Beteiligte Einrichtung: Dentistry Department, Faculty of Health Science, University of Brasília, Brasilia, Brazil. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Cysts. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Objective
To define which are and how the radiomics features of jawbone pathologies are extracted for diagnosis, predicting prognosis and therapeutic response.
Methods
A comprehensive literature search was conducted using eight databases and gray literature. Two independent observers rated these articles according to exclusion and inclusion criteria. 23 papers were included to assess the radiomics features related to jawbone pathologies. Included studies were evaluated by using JBI Critical Appraisal Checklist for Analytical Cross-Sectional Studies.
Results
Agnostic features were mined from periapical, dental panoramic radiographs, cone beam CT, CT and MRI images of six different jawbone alterations. The most frequent features mined were texture-, shape- and intensity-based features. Only 13 studies described the machine learning step, and the best results were obtained with Support Vector Machine and random forest classifier. For osteoporosis diagnosis and classification, filtering, shape-based and Tamura texture features showed the best performance. For temporomandibular joint pathology, gray-level co-occurrence matrix (GLCM), gray level run length matrix (GLRLM), Gray Level Size Zone Matrix (GLSZM), first-order statistics analysis and shape-based analysis showed the best results. Considering odontogenic and non-odontogenic cysts and tumors, contourlet and SPHARM features, first-order statistical features, GLRLM, GLCM had better indexes. For odontogenic cysts and granulomas, first-order statistical analysis showed better classification results.
Conclusions
GLCM was the most frequent feature, followed by first-order statistics, and GLRLM features. No study reported predicting response, prognosis or therapeutic response, but instead diseases diagnosis or classification. Although the lack of standardization in the radiomics workflow of the included studies, texture analysis showed potential to contribute to radiologists’ reports, decreasing the subjectivity and leading to personalized healthcare.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Dentistry Department, Faculty of Health Science, University of Brasília, Brasilia, Brazil.
- Mechanical Engineering Department, Faculty of Technology, University of Brasília, Brasília, Brazil.
Zitieren
APA
Santos, G. N. M., da Silva, H. E. C., Ossege, F. E. L., Figueiredo, P. T. S., Melo, N. S., Stefani, C. M., & Leite, A. F. (2023). Radiomics in bone pathology of the jaws. Dentomaxillofacial Radiology, 52(1). https://doi.org/10.1259/dmfr.20220225
Vancouver
Santos GNM, da Silva HEC, Ossege FEL, Figueiredo PTS, Melo NS, Stefani CM, et al. Radiomics in bone pathology of the jaws. Dentomaxillofacial Radiology. 2023;52(1). doi:10.1259/dmfr.20220225
BibTeX
@article{Santos2023,
author = {Santos, Glaucia Nize Martins and da Silva, Helbert Eustáquio Cardoso and Ossege, Filipe Eduard Leite and Figueiredo, Paulo Tadeu de Souza and Melo, Nilce de Santos and Stefani, Cristine Miron and Leite, André Ferreira},
title = {Radiomics in bone pathology of the jaws},
journal = {Dentomaxillofacial Radiology},
year = {2023},
volume = {52},
number = {1},
doi = {10.1259/dmfr.20220225}
}
EUVIMED