A Dual-Branch Network for Diagnosis of Thorax Diseases From Chest X-Rays.

Automated chest X-ray analysis has a great potential for diagnosing thorax diseases since errors in diagnosis have always been a concern among radiologists. Being a multi-label classification problem, achieving accurate classification remains challenging. Several studies have focused on accurately segmenting the lung regions from the chest X-rays to deal with the challenges involved. The features extracted from the lung regions typically provide precise clues for diseases like nodules. However, such methods ignore the features outside the lung regions, which have been shown to be crucial for diagnosing conditions like cardiomegaly. Therefore, in this work, we explore a dual-branch network-based framework that relies on features extracted from the lung regions as well as the entire chest X-rays. The proposed framework uses a novel network named R-I UNet for segmenting the lung regions. The dual-branch network in the proposed framework employs two pre-trained AlexNet models to extract discriminative features, forming two feature vectors. Each feature vector is fed into a recurrent neural network consisting of a stack of gated recurrent units with skip connections. Finally, the resulting feature vectors are concatenated for classification. The proposed models achieve state-of-the-art performance for both segmentation and classification tasks on the benchmark datasets. Specifically, our lung segmentation model achieves a 5-fold cross-validation accuracy of 98.18 % and 99.14 % on Montgomery (MC) and JSRT datasets. For classification, the proposed approach achieves state-of-the-art AUC for 9 out of 14 diseases with a mean AUC of 0.842 on the NIH ChestXray14 dataset.

Automated glaucoma diagnosis using bit-plane slicing and local binary pattern techniques.

BACKGROUND AND OBJECTIVE: Glaucoma is a ocular disorder which causes irreversible damage to the retinal nerve fibers. The diagnosis of glaucoma is important as it may help to slow down the progression. The available clinical methods and imaging techniques are manual and require skilled supervision. For the purpose of mass screening, an automated system is needed for glaucoma diagnosis which is fast, accurate, and helps in reducing the burden on experts. METHODS: In this work, we present a bit-plane slicing (BPS) and local binary pattern (LBP) based novel approach for glaucoma diagnosis. Firstly, our approach separates the red (R), green (G), and blue (B) channels from the input color fundus image and splits the channels into bit planes. Secondly, we extract LBP based statistical features from each of the bit planes of the individual channels. Thirdly, these features from the individual channels are fed separately to three different support vector machines (SVMs) for classification. Finally, the decisions from the individual SVMs are fused at the decision level to classify the input fundus image into normal or glaucoma class. RESULTS: Our experimental results suggest that the proposed approach is effective in discriminating normal and glaucoma cases with an accuracy of 99.30% using 10-fold cross validation. CONCLUSIONS: The developed system is ready to be tested on large and diverse databases and can assist the ophthalmologists in their daily screening to confirm their diagnosis, thereby increasing accuracy of diagnosis.

Detection of electrocardiographic changes in partial epileptic patients using local binary pattern based composite feature.

In this paper, we propose a novel method for detecting electrocardiographic (ECG) changes in partial epileptic patients using a composite feature set. At the core of our approach is a local binary pattern (LBP) based feature representation containing a set of statistical features derived from the distribution of LBPs of the ECG signal. In order to enhance the discriminating power, a set of statistical features are also extracted from the original ECG signal. The composite feature is then generated by combining the two homogeneous feature sets. The discriminating ability of the proposed composite feature is investigated using two different classifiers namely, support vector machine and a bagged ensemble of decision trees. Results from the experimental evaluation on the publicly available MIT-BIH ECG dataset demonstrate the superiority of the proposed features over conventional histogram based LBP features. Our results also show that the proposed approach provides better classification accuracy than methods existing in the literature for classification of normal and partial epileptic beats in ECG.

Iterative variational mode decomposition based automated detection of glaucoma using fundus images.

Glaucoma is one of the leading causes of permanent vision loss. It is an ocular disorder caused by increased fluid pressure within the eye. The clinical methods available for the diagnosis of glaucoma require skilled supervision. They are manual, time consuming, and out of reach of common people. Hence, there is a need for an automated glaucoma diagnosis system for mass screening. In this paper, we present a novel method for an automated diagnosis of glaucoma using digital fundus images. Variational mode decomposition (VMD) method is used in an iterative manner for image decomposition. Various features namely, Kapoor entropy, Renyi entropy, Yager entropy, and fractal dimensions are extracted from VMD components. ReliefF algorithm is used to select the discriminatory features and these features are then fed to the least squares support vector machine (LS-SVM) for classification. Our proposed method achieved classification accuracies of 95.19% and 94.79% using three-fold and ten-fold cross-validation strategies, respectively. This system can aid the ophthalmologists in confirming their manual reading of classes (glaucoma or normal) using fundus images.

Automated Diagnosis of Epilepsy Using Key-Point-Based Local Binary Pattern of EEG Signals.

The electroencephalogram (EEG) signals are commonly used for diagnosis of epilepsy. In this paper, we present a new methodology for EEG-based automated diagnosis of epilepsy. Our method involves detection of key points at multiple scales in EEG signals using a pyramid of difference of Gaussian filtered signals. Local binary patterns (LBPs) are computed at these key points and the histogram of these patterns are considered as the feature set, which is fed to the support vector machine (SVM) for the classification of EEG signals. The proposed methodology has been investigated for the four well-known classification problems namely, 1) normal and epileptic seizure, 2) epileptic seizure and seizure free, 3) normal, epileptic seizure, and seizure free, and 4) epileptic seizure and nonseizure EEG signals using publically available university of Bonn EEG database. Our experimental results in terms of classification accuracies have been compared with existing methods for the classification of the aforementioned problems. Further, performance evaluation on another EEG dataset shows that our approach is effective for classification of seizure and seizure-free EEG signals. The proposed methodology based on the LBP computed at key points is simple and easy to implement for real-time epileptic seizure detection.

Contactless and pose invariant biometric identification using hand surface.

This paper presents a novel approach for hand matching that achieves significantly improved performance even in the presence of large hand pose variations. The proposed method utilizes a 3-D digitizer to simultaneously acquire intensity and range images of the user's hand presented to the system in an arbitrary pose. The approach involves determination of the orientation of the hand in 3-D space followed by pose normalization of the acquired 3-D and 2-D hand images. Multimodal (2-D as well as 3-D) palmprint and hand geometry features, which are simultaneously extracted from the user's pose normalized textured 3-D hand, are used for matching. Individual matching scores are then combined using a new dynamic fusion strategy. Our experimental results on the database of 114 subjects with significant pose variations yielded encouraging results. Consistent (across various hand features considered) performance improvement achieved with the pose correction demonstrates the usefulness of the proposed approach for hand based biometric systems with unconstrained and contact-free imaging. The experimental results also suggest that the dynamic fusion approach employed in this work helps to achieve performance improvement of 60% (in terms of EER) over the case when matching scores are combined using the weighted sum rule.