Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Nov 10;21(22):7481.
doi: 10.3390/s21227481.

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

Affiliations

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

Elżbieta Pociask et al. Sensors (Basel). .

Abstract

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.

Keywords: classification; cysts; granulomas; intraoral radiography; periapical lesions; tSNE; texture features.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Example of lossy compression artifacts on local binary pattern (LBP) feature maps (c,d) calculated for analyzed JPG images (a,b). Lesions are depicted with red lines.
Figure 2
Figure 2
Example of ROI outlines: for granulomas (a,c), for cysts (b,d). Legend: red for the lesion interior outline, green for the outline including the lesion edges.
Figure 3
Figure 3
Two-dimensional t-SNE (a) and 3D t-SNE (b) for model I for perplexity = 20. In (a), class 1 (red dots) represents cysts, and class 2 (blue dots) represents granulomas. In (b) red dots represent cysts, and green dots represent granulomas. The aggregation of red dots suggested that the chosen texture features could be used as a predictor to differentiate these two lesions.
Figure 4
Figure 4
Two-dimensional t-SNE (a) and 3D t-SNE (b) for model IV for perplexity = 20. In (a), class 1 (red dots) represents cysts, and class 2 (blue dots) represents granulomas. In (b), red dots represent cysts, and green dots represent granulomas. In both figures, the red dots tended to accumulate in a particular area of space.

References

    1. Nair P.R., Schroeder G.P.H.E. Types and incidence of human periapical lesions obtained with extracted teeth. Oral Surg. Oral Med. Oral Pathol. Oral Radiol. Endodontol. 1996;81:93–102. doi: 10.1016/S1079-2104(96)80156-9. - DOI - PubMed
    1. Bender I.B. Factors influencing the radiographic appearance of bony lesions. J. Endod. 1997;23:5–14. doi: 10.1016/S0099-2399(97)80199-9. - DOI - PubMed
    1. Bender I., Seltzer S. Roentgenographic and direct observation of experimental lesions in bone: I. J. Am. Dent. Assoc. 1961;62:152–160. doi: 10.14219/jada.archive.1961.0030. - DOI
    1. Friedman S., Abitbol S., Lawrence H.P. Treatment Outcome in Endodontics: The Toronto Study. Phase 1: Initial Treatment. J. Endod. 2003;29:787–793. doi: 10.1097/00004770-200312000-00001. - DOI - PubMed
    1. Natkin E., Oswald R.J., Carnes L.I. The relationship of lesion size to diagnosis, incidence, and treatment of periapical cysts and granulomas. Oral Surg. Oral Med. Oral Pathol. 1984;57:82–94. doi: 10.1016/0030-4220(84)90267-6. - DOI - PubMed

LinkOut - more resources