Weakly supervised detection and classification of basal cell carcinoma using graph-transformer on whole slide images

The high incidence rates of basal cell carcinoma (BCC) cause a significant burden at pathology laboratories. The standard diagnostic process is time-consuming and prone to inter-pathologist variability. Despite the application of deep learning approaches in grading of other cancer types, there is li...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2023-05, Vol.13 (1), p.7555-7555, Article 7555
Main Authors: Yacob, Filmon, Siarov, Jan, Villiamsson, Kajsa, Suvilehto, Juulia T., Sjöblom, Lisa, Kjellberg, Magnus, Neittaanmäki, Noora
Format: Article
Language:English
Subjects:
631/114
631/67
692/308
692/699
692/700
Accuracy
Automation
Basal cell carcinoma
Biomedical Laboratory Science/Technology
Biomedicinsk laboratorievetenskap/teknologi
Cancer
Carcinoma, Basal Cell - diagnostic imaging
Classification
Deep learning
Electric Power Supplies
Humanities and Social Sciences
Humans
Image processing
Laboratories
Medical prognosis
multidisciplinary
Natural language processing
Neural networks
Neural Networks, Computer
Pathology
Science
Science (multidisciplinary)
Skin cancer
Skin Neoplasms - diagnosis
Tumors
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The high incidence rates of basal cell carcinoma (BCC) cause a significant burden at pathology laboratories. The standard diagnostic process is time-consuming and prone to inter-pathologist variability. Despite the application of deep learning approaches in grading of other cancer types, there is limited literature on the application of vision transformers to BCC on whole slide images (WSIs). A total of 1832 WSIs from 479 BCCs, divided into training and validation (1435 WSIs from 369 BCCs) and testing (397 WSIs from 110 BCCs) sets, were weakly annotated into four aggressivity subtypes. We used a combination of a graph neural network and vision transformer to (1) detect the presence of tumor (two classes), (2) classify the tumor into low and high-risk subtypes (three classes), and (3) classify four aggressivity subtypes (five classes). Using an ensemble model comprised of the models from cross-validation, accuracies of 93.5%, 86.4%, and 72% were achieved on two, three, and five class classifications, respectively. These results show high accuracy in both tumor detection and grading of BCCs. The use of automated WSI analysis could increase workflow efficiency.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-023-33863-z