| Autor: |
Șerbănescu MS; Department of Medical Informatics and Biostatistics, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania., Bungărdean RM; Department of Pathology, Iuliu Haţieganu University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania., Georgiu C; Department of Pathology, Iuliu Haţieganu University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania., Crișan M; Department of Histology, Iuliu Haţieganu University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania. |
| Jazyk: |
angličtina |
| Zdroj: |
Diagnostics (Basel, Switzerland) [Diagnostics (Basel)] 2022 Jul 05; Vol. 12 (7). Date of Electronic Publication: 2022 Jul 05. |
| DOI: |
10.3390/diagnostics12071636 |
| Abstrakt: |
Basal cell carcinoma (BCC) is the most frequent cancer of the skin and comprises low-risk and high-risk subtypes. We selected a low-risk subtype, namely, nodular (N), and a high-risk subtype, namely, micronodular (MN), with the aim to identify differences between them using a classical morphometric approach through a gray-level co-occurrence matrix and histogram analysis, as well as an approach based on deep learning semantic segmentation. From whole-slide images, pathologists selected 216 N and 201 MN BCC images. The two groups were then manually segmented and compared based on four morphological areas: center of the BCC islands (tumor, T), peripheral palisading of the BCC islands (touching tumor, TT), peritumoral cleft (PC) and surrounding stroma (S). We found that the TT pattern varied the least, while the PC pattern varied the most between the two subtypes. The combination of two distinct analysis approaches yielded fresh insights into the characterization of BCC, and thus, we were able to describe two different morphological patterns for the T component of the two subtypes. |
| Databáze: |
MEDLINE |
| Externí odkaz: |
|
|
Nepřihlášeným uživatelům se plný text nezobrazuje |
K zobrazení výsledku je třeba se přihlásit.
|
