Non-linear Logistic Regression applied to Radiomics
This work proposes to improve the performance of the Logistic Regression (LR) which is the most used ML model in radiomics, and proposes to represent the radiomics features with one-hot encoding, showing that the resulting LR is non-linear and almost equivalent to the Naive Bayes classifier (NBC).
Abstract
In the past decade, radiomics has gained huge popularity. This method has a significant potential in cancer detection, diagnostic or prediction of response to a treatment due to its capacity of reflecting tumor-phenotypic characteristics. Despite its qualities and the interest shown in it by the scientific community, radiomics is still not used for clinical care. Reliable Machine Learning (ML) approaches could promote the usage of radiomics by showing relevant results. In this context, we propose to improve the performance of the Logistic Regression (LR) which is the most used ML model in radiomics. We propose to represent the radiomics features with one-hot encoding. Then, we show that the resulting LR is non-linear and almost equivalent to the Naive Bayes classifier (NBC). Since our LR score function remains additive, the contribution of each feature to the decision can be easily measured. We illustrate the performance of the proposed non-linear LR with two radiomics datasets.