Differential diagnosis of thyroid nodule capsules using random forest guided selection of image features.

Autor: Eftimie LG; Center for Microscopy-Microanalysis and Information Processing, University Politehnica of Bucharest, 313 Splaiul Independentei, 060042, Bucharest, Romania.; Pathology Department, Central University Emergency Military Hospital, 134 Calea Plevnei, 010825, Bucharest, Romania., Glogojeanu RR; Department of Special Motricity and Medical Recovery, The National University of Physical Education and Sports, 140 Constantin Noica, 060057, Bucharest, Romania., Tejaswee A; Department of Computer Science and Engineering, Indian Institute of Technology Jodhpur, Jodhpur, India., Gheorghita P; Faculty of Energetics, University Politehnica of Bucharest, 313 Splaiul Independentei, 060042, Bucharest, Romania., Stanciu SG; Center for Microscopy-Microanalysis and Information Processing, University Politehnica of Bucharest, 313 Splaiul Independentei, 060042, Bucharest, Romania., Chirila A; Pathology Department, Central University Emergency Military Hospital, 134 Calea Plevnei, 010825, Bucharest, Romania., Stanciu GA; Center for Microscopy-Microanalysis and Information Processing, University Politehnica of Bucharest, 313 Splaiul Independentei, 060042, Bucharest, Romania., Paul A; Department of Computer Science and Engineering, Indian Institute of Technology Jodhpur, Jodhpur, India., Hristu R; Center for Microscopy-Microanalysis and Information Processing, University Politehnica of Bucharest, 313 Splaiul Independentei, 060042, Bucharest, Romania. radu.hristu@upb.ro.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2022 Dec 14; Vol. 12 (1), pp. 21636. Date of Electronic Publication: 2022 Dec 14.
DOI: 10.1038/s41598-022-25788-w
Abstrakt: Microscopic evaluation of tissue sections stained with hematoxylin and eosin is the current gold standard for diagnosing thyroid pathology. Digital pathology is gaining momentum providing the pathologist with additional cues to traditional routes when placing a diagnosis, therefore it is extremely important to develop new image analysis methods that can extract image features with diagnostic potential. In this work, we use histogram and texture analysis to extract features from microscopic images acquired on thin thyroid nodule capsules sections and demonstrate how they enable the differential diagnosis of thyroid nodules. Targeted thyroid nodules are benign (i.e., follicular adenoma) and malignant (i.e., papillary thyroid carcinoma and its sub-type arising within a follicular adenoma). Our results show that the considered image features can enable the quantitative characterization of the collagen capsule surrounding thyroid nodules and provide an accurate classification of the latter's type using random forest.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje