Basal Cell Carcinoma
Conditions
Keywords
Basal Cell Carcinoma, Artificial Intelligence, Convolutional Neural Network, Dermoscopy, Skin Cancer, Histopathological Subtypes, Risk Classification
Brief summary
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.
Detailed description
Basal cell carcinoma (BCC) is the most common skin malignancy and comprises histopathological subtypes with different biological behaviors, recurrence risks, and treatment implications. Accurate identification of high-risk and low-risk subtypes is important for clinical decision-making. Dermoscopy improves diagnostic accuracy in BCC; however, prediction of histopathological risk categories based solely on dermoscopic findings remains challenging. This retrospective observational study will use archived clinical and dermoscopic images, histopathology reports, and clinical records of patients with histopathologically confirmed BCC. All data will be anonymized before analysis. Images containing identifiable patient information will be excluded. A convolutional neural network (CNN)-based artificial intelligence model will be developed using clinical and dermoscopic images. Images will undergo preprocessing, including standardization of image size, normalization procedures, and removal of potentially identifiable information. The dataset will be divided into training, validation, and test sets while maintaining separation at the patient level to avoid data leakage. The primary outcome is the diagnostic performance of the CNN model for classification of BCC into low-risk and high-risk histopathological groups. Secondary outcomes include prediction of histopathological subtypes and comparison of model performance with dermatologist assessments. Histopathological diagnosis will serve as the reference standard. Model performance will be evaluated using accuracy, sensitivity, specificity, precision, recall, F1 score, and area under the receiver operating characteristic curve (ROC-AUC). Comparisons between the artificial intelligence model and physician assessments will be performed using appropriate statistical methods. Interobserver agreement may also be assessed when applicable.
Interventions
None listed
Sponsors
Study design
Eligibility
Inclusion criteria
* 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.
Exclusion criteria
* 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.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Accuracy of artificial intelligence-based classification of basal cell carcinoma risk groups | Baseline | 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. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| 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 | baseline | 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 | baseline | 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. |
Countries
Turkey (Türkiye)
Contacts
Istanbul Training and Research Hospital