Related Experiment Video
Updated: Sep 13, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
6.9K
Metastatic Melanoma Prognosis Prediction Using a TC Radiomic-Based Machine Learning Model: A Preliminary Study
Antonino Guerrisi1, Maria Teresa Maccallini2, Italia Falcone3
1Radiology and Diagnostic Imaging Unit, Department of Clinical and Dermatological Research, San Gallicano Dermatological Institute IRCCS, 00144 Rome, Italy.
Cancers
|July 29, 2025
Summary
This study developed an Artificial Intelligence (AI) model using computed tomography (CT) radiomics to predict prognosis in metastatic melanoma (MM) patients. The AI model demonstrated good predictive ability, offering personalized prognostic insights.
Area of Science:
- Radiology
- Oncology
- Artificial Intelligence
Background:
- Metastatic melanoma (MM) management is evolving with AI applications.
- Medical imaging data fuels AI for revolutionizing patient surveillance and care.
Purpose of the Study:
- Develop and validate a machine-learning model using CT radiomics for MM prognosis.
- Identify key prognostic factors and predict patient outcomes accurately.
Main Methods:
- Extracted quantitative radiomic features (texture, morphology, intensity) from CT scans.
- Trained a model on 60 CT series and validated on 70 independent series from 58 MM patients.
- Evaluated performance using sensitivity, specificity, and AUC.
Main Results:
- The AI-enhanced model achieved an 82% ROC-AUC in internal testing.
- Demonstrated favorable predictive ability for lesion outcomes compared to traditional methods.
Conclusions:
- The AI-driven radiomic approach shows promise for personalized prognostic prediction in MM.
- Further validation in larger, diverse populations is warranted to support clinical decision-making.
