E2E-FS: An End-to-End Feature Selection Method for Neural Networks.

Classic embedded feature selection algorithms are often divided in two large groups: tree-based algorithms and LASSO variants. Both approaches are focused in different aspects: while the tree-based algorithms provide a clear explanation about which variables are being used to trigger a certain output, LASSO-like approaches sacrifice a detailed explanation in favor of increasing its accuracy. In this paper, we present a novel embedded feature selection algorithm, called End-to-End Feature Selection (E2E-FS), that aims to provide both accuracy and explainability in a clever way.

Ocular and systemic toxicity of high-dose intravitreal topotecan in rabbits: Implications for retinoblastoma treatment.

Although many more eyes of children with retinoblastoma are salvaged now compared to just 10 years ago, the control of vitreous seeding remains a challenge. The introduction of intravitreal injection of melphalan has enabled more eyes to be salvaged safely but with definite retinal toxicity. Intensive treatment with high-dose intravitreal topotecan may be a strategy to control tumor burden because of its cell cycle-dependent cytotoxicity and the proven safety in humans.

Wavefront Marching Methods: A Unified Algorithm to Solve Eikonal and Static Hamilton-Jacobi Equations.

This paper presents a unified propagation method for dealing with both the classic Eikonal equation, where the motion direction does not affect the propagation, and the more general static Hamilton-Jacobi equations, where it does. While classic Fast Marching Method (FMM) techniques achieve the solution to the Eikonal equation with a O(M log M) (or O(M) assuming some modifications), solving the more general static Hamilton-Jacobi equation requires a higher complexity. The proposed framework maintains the O(M log M) complexity for both problems, while achieving higher accuracy than available state-of-the-art.

Immunotherapy eradicates metastases with reversible defects in MHC class I expression.

Tumor or metastatic cells lose MHC class I (MHC-I) expression during cancer progression as an escape mechanism from immune surveillance. These defects in MHC-I may be reversible by cytokines or different agents (soft lesions) or irreversible due to structural defects (hard lesions). The nature of these MHC-I alterations might determine the success or failure of immunotherapy treatments.