This retrospective observational study aims to develop and evaluate a convolutional neural network (CNN)-based artificial intelligence model for risk classification and histopathological subtype prediction of basal cell carcinoma (BCC) using clinical and dermoscopic images. Histopathologically confirmed BCC cases from a dermatology archive will be included. The primary objective is to assess the diagnostic performance of the CNN model in classifying BCC as low-risk or high-risk. Secondary objectives include predicting histopathological subtypes and comparing the model's performance with that of dermatology physicians. Histopathological diagnosis will serve as the reference standard. All archived data will be anonymized before analysis.
Patients with histopathologically confirmed basal cell carcinoma.
Cases with a specified histopathological subtype.
Availability of dermoscopic images with sufficient image quality and resolution for artificial intelligence analysis.
Cases without histopathological confirmation of basal cell carcinoma.
Cases with unspecified histopathological subtype.
Images with insufficient quality or resolution for artificial intelligence analysis.
Cases without available dermoscopic images.
The study population consists of patients with histopathologically confirmed basal cell carcinoma who have dermoscopic images of sufficient quality for artificial intelligence analysis and documented histopathological subtype information. Archived clinical and dermoscopic images collected at Istanbul Training and Research Hospital will be retrospectively analyzed.
Case-only
Retrospective
Not listed
Accuracy of artificial intelligence-based classification of basal cell carcinoma risk groups
Diagnostic accuracy of the convolutional neural network model in distinguishing low-risk and high-risk basal cell carcinoma using dermoscopic images, compared with histopathological diagnosis as the reference standard.
Diagnostic accuracy (accuracy, sensitivity, specificity, F1-score and ROC-AUC) of convolutional neural network for histopathological subtype prediction of basal cell carcinoma using dermoscopic images
Diagnostic performance of the convolutional neural network in predicting histopathological subtypes of basal cell carcinoma from dermoscopic images compared with histopathological diagnosis (reference standard). Diagnostic accuracy will be assessed using accuracy, sensitivity, specificity, precision, F1-score and ROC-AUC.
Diagnostic accuracy (accuracy, sensitivity, specificity, F1-score and ROC-AUC) of artificial intelligence compared with dermatologists for basal cell carcinoma risk classification
Comparison of diagnostic performance between the artificial intelligence model and dermatologists in risk classification of basal cell carcinoma. Performance will be assessed using accuracy, sensitivity, specificity, precision, F1-score and ROC-AUC.
Click on the lead sponsor to view all of their trials.
