Macular edema (ME) and central serous retinopathy (CSR) are two macular diseases that affect the central vision of a person if they are left untreated. Optical coherence tomography (OCT) imaging is the latest eye examination technique that shows a cross-sectional region of the retinal layers and that can be used to detect many retinal disorders in an early stage. Many researchers have done clinical studies on ME and CSR and reported significant findings in macular OCT scans. However, this paper proposes an automated method for the classification of ME and CSR from OCT images using a support vector machine (SVM) classifier. Five distinct features (three based on the thickness profiles of the sub-retinal layers and two based on cyst fluids within the sub-retinal layers) are extracted from 30 labeled images (10 ME, 10 CSR, and 10 healthy), and SVM is trained on these. We applied our proposed algorithm on 90 time-domain OCT (TD-OCT) images (30 ME, 30 CSR, 30 healthy) of 73 patients. Our algorithm correctly classified 88 out of 90 subjects with accuracy, sensitivity, and specificity of 97.77%, 100%, and 93.33%, respectively.

Purpose The aim of this study was to develop a novel technique for lung nodule detection using an optimized feature set. This feature set has been achieved after rigorous experimentation, which has helped in reducing the false positives significantly. Method The proposed method starts with preprocessing, removing any present noise from input images, followed by lung segmentation using optimal thresholding. Then the image is enhanced using multiscale dot enhancement filtering prior to nodule detection and feature extraction. Finally, classification of lung nodules is achieved using Support Vector Machine (SVM) classifier. The feature set consists of intensity, shape (2D and 3D) and texture features, which have been selected to optimize the sensitivity and reduce false positives. In addition to SVM, some other supervised classifiers like K‐Nearest‐Neighbor (KNN), Decision Tree and Linear Discriminant Analysis (LDA) have also been used for performance comparison. The extracted features have also been compared class‐wise to determine the most relevant features for lung nodule detection. The proposed system has been evaluated using 850 scans from Lung Image Database Consortium (LIDC) dataset and k‐fold cross‐validation scheme. Results The overall sensitivity has been improved compared to the previous methods and false positives per scan have been reduced significantly. The achieved sensitivities at detection and classification stages are 94.20% and 98.15%, respectively, with only 2.19 false positives per scan. Conclusions It is very difficult to achieve high performance metrics using only a single feature class therefore hybrid approach in feature selection remains a better choice. Choosing right set of features can improve the overall accuracy of the system by improving the sensitivity and reducing false positives.

Tuberculosis (TB) remains one of the major health problems in modern times with a high mortality rate. While efforts are being made to make early diagnosis accessible and more reliable in high burden TB countries, digital chest radiography has become a popular source for this purpose. However, the screening process requires expert radiologists which may be a potential barrier in developing countries. A fully automatic computer-aided diagnosis system can reduce the need of trained personnel for early diagnosis of TB using chest X-ray images. In this paper, we have proposed a novel TB detection technique that combines hand-crafted features with deep features (convolutional neural network-based) through Ensemble Learning. Handcrafted features were extracted via Gabor Filter and deep features were extracted via pre-trained deep learning models. Two publicly available datasets namely (i) Montgomery and (ii) Shenzhen were used to evaluate the proposed system. The proposed methodology was validated with a k-fold cross-validation scheme. The area under receiver operating characteristics curves of 0.99 and 0.97 were achieved for Shenzhen and Montgomery datasets respectively which shows the superiority of the proposed scheme.

No abstract

Self-mixing (SM) or optical feedback interferometry has been extensively used for high precision displacement and vibration sensing. However, presence of speckle can significantly degrade the SM interferometric signal and cause changes in signal amplitude as well as in the operating optical feedback regime, resulting in reduction in measurement precision. Previously, different advanced digital signal processing techniques have been proposed to undo the effects caused by speckle. However, their complex and computationally heavy nature inhibits their use for real-time, high bandwidth sensing applications. In this regard, an all analog signal processing algorithm has been presented in this paper which allows realtime processing of speckle affected SM signal while using standard analog circuits. Various simulations indicated that it is able to correctly process speckle affected SM signals having amplitude variation of at least one order and optical feedback parameter C reduction till 0.5. This proposed algorithm has been tested on experimentally acquired speckle affected SM signals and found capable of dealing with variations in optical feedback regime and amplitude modulation of SM signals, in accordance with simulation results. The developed hardware prototype circuit measures maximum displacement amplitude of 0.4 mm at maximum target velocity of 8 mm/s for an SM sensor with laser wavelength of 785 nm as long as C > 0.5. The proposed all analog processing could be a significant step towards a robust, low-cost, integrated, real-time SM displacement sensor.

No abstract

We present an in-depth review and analysis of salient methods for computer-aided detection of lung nodules. We evaluate the current methods for detecting lung nodules using literature searches with selection criteria based on validation dataset types, nodule sizes, numbers of cases, types of nodules, extracted features in traditional feature-based classifiers, sensitivity, and false positives (FP)/scans. Our review shows that current detection systems are often optimized for particular datasets and can detect only one or two types of nodules. We conclude that, in addition to achieving high sensitivity and reduced FP/scans, strategies for detecting lung nodules must detect a variety of nodules with high precision to improve the performances of the radiologists. To the best of our knowledge, ours is the first review of the effectiveness of feature extraction using traditional feature-based classifiers. Moreover, we discuss deep-learning methods in detail and conclude that features must be appropriately selected to improve the overall accuracy of the system. We present an analysis of current schemes and highlight constraints and future research areas.

No abstract