A Radiogenomics Ensemble to Predict EGFR and KRAS Mutations in NSCLC
| Autor: | Eduardo E. Zurek, Mario Bonfante, Lawrence O. Hall, Dmitry Cherezov, Matthew B. Schabath, Silvia Moreno, Dmitry B. Goldgof |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
0301 basic medicine
Lung Neoplasms Computer science EGFR radiogenomics Computer applications to medicine. Medical informatics education R858-859.7 Radiogenomics ensembles NSCLC Machine learning computer.software_genre medicine.disease_cause Article Proto-Oncogene Proteins p21(ras) 03 medical and health sciences 0302 clinical medicine Carcinoma Non-Small-Cell Lung KRAS medicine Humans Radiology Nuclear Medicine and imaging business.industry Deep learning ErbB Receptors machine learning 030104 developmental biology Egfr mutation 030220 oncology & carcinogenesis Mutation Artificial intelligence business computer CNN Kras mutation |
| Zdroj: | Tomography, Vol 7, Iss 14, Pp 154-168 (2021) Tomography Volume 7 Issue 2 Pages 14-168 |
| ISSN: | 2379-139X |
| DOI: | 10.3390/tomography7020014 |
| Popis: | Lung cancer causes more deaths globally than any other type of cancer. To determine the best treatment, detecting EGFR and KRAS mutations is of interest. However, non-invasive ways to obtain this information are not available. Furthermore, many times there is a lack of big enough relevant public datasets, so the performance of single classifiers is not outstanding. In this paper, an ensemble approach is applied to increase the performance of EGFR and KRAS mutation prediction using a small dataset. A new voting scheme, Selective Class Average Voting (SCAV), is proposed and its performance is assessed both for machine learning models and CNNs. For the EGFR mutation, in the machine learning approach, there was an increase in the sensitivity from 0.66 to 0.75, and an increase in AUC from 0.68 to 0.70. With the deep learning approach, an AUC of 0.846 was obtained, and with SCAV, the accuracy of the model was increased from 0.80 to 0.857. For the KRAS mutation, both in the machine learning models (0.65 to 0.71 AUC) and the deep learning models (0.739 to 0.778 AUC), a significant increase in performance was found. The results obtained in this work show how to effectively learn from small image datasets to predict EGFR and KRAS mutations, and that using ensembles with SCAV increases the performance of machine learning classifiers and CNNs. The results provide confidence that as large datasets become available, tools to augment clinical capabilities can be fielded. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|