MRI Radiomics for the Prediction of Fuhrman Grade in Clear Cell Renal Cell Carcinoma: a Machine Learning Exploratory Study
| Autor: | Arnaldo Stanzione, Pier Paolo Mainenti, Giovanni Improta, Valeria Romeo, Filippo De Rosa, Simone Maurea, Renato Cuocolo, Luigi Insabato, Michela Sarnataro, Carlo Ricciardi, Jessica Petrone, Arturo Brunetti |
|---|---|
| Přispěvatelé: | Stanzione, Arnaldo, Ricciardi, Carlo, Cuocolo, Renato, Romeo, Valeria, Petrone, Jessica, Sarnataro, Michela, Mainenti, Pier Paolo, Improta, Giovanni, De Rosa, Filippo, Insabato, Luigi, Brunetti, Arturo, Maurea, Simone |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Normalization (statistics)
Decision tree Machine learning computer.software_genre 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine C4.5 algorithm Renal cell carcinoma medicine Humans Radiology Nuclear Medicine and imaging Carcinoma Renal Cell Retrospective Studies Original Paper Radiomics Radiological and Ultrasound Technology business.industry Carcinoma Fuhrman grade MRI Machine Learning Magnetic Resonance Imaging Kidney Neoplasms Renal Cell medicine.disease Ensemble learning Computer Science Applications Random forest Clear cell renal cell carcinoma Feature (computer vision) Artificial intelligence Radiomic business computer 030217 neurology & neurosurgery |
| Zdroj: | J Digit Imaging |
| Popis: | The Fuhrman nuclear grade is a recognized prognostic factor for patients with clear cell renal cell carcinoma (CCRCC) and its pre-treatment evaluation significantly affects decision-making in terms of management. In this study, we aimed to assess the feasibility of a combined approach of radiomics and machine learning based on MR images for a non-invasive prediction of Fuhrman grade, specifically differentiation of high- from low-grade tumor and grade assessment. Images acquired on a 3-Tesla scanner (T2-weighted and post-contrast) from 32 patients (20 with low-grade and 12 with high-grade tumor) were annotated to generate volumes of interest enclosing CCRCC lesions. After image resampling, normalization, and filtering, 2438 features were extracted. A two-step feature reduction process was used to between 1 and 7 features depending on the algorithm employed. A J48 decision tree alone and in combination with ensemble learning methods were used. In the differentiation between high- and low-grade tumors, all the ensemble methods achieved an accuracy greater than 90%. On the other end, the best results in terms of accuracy (84.4%) in the assessment of tumor grade were achieved by the random forest. These evidences support the hypothesis that a combined radiomic and machine learning approach based on MR images could represent a feasible tool for the prediction of Fuhrman grade in patients affected by CCRCC. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|