The kidney biopsy based diagnosis of Lupus Nephritis (LN) is characterized by low inter-observer agreement, with misdiagnosis being associated with increased patient morbidity and mortality. Although various Computer Aided Diagnosis (CAD) systems have been developed for other nephrohistopathological applications, little has been done to accurately classify kidneys based on their kidney level Lupus Glomerulonephritis (LGN) scores. The successful implementation of CAD systems has also been hindered by the diagnosing physician's perceived classifier strengths and weaknesses, which has been shown to have a negative effect on patient outcomes. We propose an Uncertainty-Guided Bayesian Classification (UGBC) scheme that is designed to accurately classify control, class I/II, and class III/IV LGN (3 class) at both the glomerular-level classification task (26,634 segmented glomerulus images) and the kidney-level classification task (87 MRL/lpr mouse kidney sections). Data annotation was performed using a high throughput, bulk labeling scheme that is designed to take advantage of Deep Neural Network's (or DNNs) resistance to label noise. Our augmented UGBC scheme achieved a 94.5% weighted glomerular-level accuracy while achieving a weighted kidney-level accuracy of 96.6%, improving upon the standard Convolutional Neural Network (CNN) architecture by 11.8% and 3.5% respectively.
Although inverse linear programming (LP) has received increasing attention as a technique to identify an LP that can reproduce observed decisions that are originally from a complex system, the performance of the linear objective function inferred by existing inverse LP methods is often highly sensitive to noise, errors, and uncertainty in the underlying decision data. Inspired by robust regression techniques that mitigate the impact of noisy data on the model fitting, in “Quantile Inverse Optimization: Improving Stability in Inverse Linear Programming,” Shahmoradi and Lee propose a notion of stability in inverse LP and develop an inverse optimization model that identities objective functions that are stable against data imperfection. Although such a stability consideration renders the inverse model a large-scale mixed-integer program, the authors analyze the connection between the model and well-known biclique problems and propose an efficient exact algorithm as well as heuristics.
Inverse linear programming (LP) has received increasing attention due to its potential to generate efficient optimization formulations that can closely replicate the behavior of a complex system. However, inversely inferred parameters and corresponding forward solutions from the existing inverse LP method can be highly sensitive to noise, errors, and uncertainty in the input data, limiting its applicability in data-driven settings. We introduce the notion of inverse and forward stability in inverse LP and propose a novel inverse LP method that determines a set of objective functions that are stable under data imperfection and generate solutions close to the relevant subset of the data. We formulate the inverse model as a mixed-integer program and elucidate its connection to bi-clique problems, which we exploit to develop efficient heuristics. We also show how this method can be used for online learning. We numerically evaluate the stability of the proposed method and demonstrate its practical use in the diet recommendation and transshipment applications.