Computed tomography (CT) has been widely used to diagnose Graves’ orbitopathy, and the utility is gradually increasing. To develop a neural network (NN)-based method for diagnosis and severity assessment of Graves’ orbitopathy (GO) using orbital CT, a specific type of NN optimized for diagnosing GO was developed and trained using 288 orbital CT scans obtained from patients with mild and moderate-to-severe GO and normal controls. The developed NN was compared with three conventional NNs [GoogleNet Inception v1 (GoogLeNet), 50-layer Deep Residual Learning (ResNet-50), and 16-layer Very Deep Convolutional Network from Visual Geometry group (VGG-16)]. The diagnostic performance was also compared with that of three oculoplastic specialists. The developed NN had an area under receiver operating curve (AUC) of 0.979 for diagnosing patients with moderate-to-severe GO. Receiver operating curve (ROC) analysis yielded AUCs of 0.827 for GoogLeNet, 0.611 for ResNet-50, 0.540 for VGG-16, and 0.975 for the oculoplastic specialists for diagnosing moderate-to-severe GO. For the diagnosis of mild GO, the developed NN yielded an AUC of 0.895, which is better than the performances of the other NNs and oculoplastic specialists. This study may contribute to NN-based interpretation of orbital CTs for diagnosing various orbital diseases

Multilabel feature selection involves the selection of relevant features from multilabeled datasets, resulting in improved multilabel learning accuracy. Evolutionary search-based multilabel feature selection methods have proved useful for identifying a compact feature subset by successfully improving the accuracy of multilabel classification. However, conventional methods frequently violate budget constraints or result in inefficient searches due to ineffective exploration of important features. In this paper, we present an effective evolutionary search-based feature selection method for multilabel classification with a budget constraint. The proposed method employs a novel exploration operation to enhance the search capabilities of a traditional genetic search, resulting in improved multilabel classification. Empirical studies using 20 real-world datasets demonstrate that the proposed method outperforms conventional multilabel feature selection methods.

No abstract

Multi-label feature selection that identifies important features from the original feature set of multi-labeled datasets has been attracting considerable attention owing to its generality compared to conventional single-label feature selection. The unimportant features are filtered by scoring the dependency of features to labels. In conventional multi-label feature filter studies, the score function is obtained by approximating a dependency measure such as joint entropy because direct calculation is often impractical due to the presence of multiple labels with limited training patterns. Although the efficacy of approximation can differ depending on the characteristics of the multi-label dataset, conventional methods presume a certain approximation method, leading to a degenerated feature subset if the presumed approximation is inappropriate for the given dataset. In this study, we propose a strategy for selecting an approximation among a series of approximations depending on the number of involved variables and consequently instantiate a score function based on the chosen approximation. The experimental results demonstrate that the proposed strategy and score function outperform conventional multi-label feature selection methods.

The method proposed in this Letter selects a feature subset that preserves the data quality in the viewpoint of information theory. Using an efficient information-theoretic evaluation, the proposed method identifies the final feature subset significantly faster than conventional methods.