Visual Contrast Enhancement Algorithm Based on Histogram Equalization.

Image enhancement techniques primarily improve the contrast of an image to lend it a better appearance. One of the popular enhancement methods is histogram equalization (HE) because of its simplicity and effectiveness. However, it is rarely applied to consumer electronics products because it can cause excessive contrast enhancement and feature loss problems. These problems make the images processed by HE look unnatural and introduce unwanted artifacts in them. In this study, a visual contrast enhancement algorithm (VCEA) based on HE is proposed. VCEA considers the requirements of the human visual perception in order to address the drawbacks of HE. It effectively solves the excessive contrast enhancement problem by adjusting the spaces between two adjacent gray values of the HE histogram. In addition, VCEA reduces the effects of the feature loss problem by using the obtained spaces. Furthermore, VCEA enhances the detailed textures of an image to generate an enhanced image with better visual quality. Experimental results show that images obtained by applying VCEA have higher contrast and are more suited to human visual perception than those processed by HE and other HE-based methods.

A Real-Time Contact-Free Atrial Fibrillation Detection System for Mobile Devices.

As the global population ages, the death and prevalence of atrial fibrillation (AF) continue to rise, posing significant concerns due to its strong association with stroke-related disabilities. Detecting AF early before a stroke occurs has become paramount. However, existing methods face challenges in achieving quick, easy, and affordable detection in complex environments characterized by motion interference and varying light conditions. To address these challenges, we propose a system that is employable for edge computing devices like smartphones, tablets, or laptops. Meanwhile, to ensure that the dataset reflects real-world scenarios, we collect 7,216 30-second segments from 452 subjects, categorized into Atrial Fibrillation (AF), Normal Sinus Rhythm (NSR), and Other Arrhythmias (Others), with a subject ratio of 105:116:231. Our lightweight non-contact facial rPPG atrial fibrillation detection system utilizes a Convolution Neural Network (CNN) with a large receptive field and a bidirectional spatial mapping augmented attention module (BiSME-ATT) coupled with a bidirectional feature pyramid network layer (BiFPN), optimized for deployment on mobile devices by reducing model parameters and floating-point operations per second (FLOPs). Our approach significantly improves AF detection accuracy, sensitivity, specificity, positive predictive value, and negative predictive value to 94.39%, 91.57%, 95.44%, 88.06%, and 96.93%, respectively, in AF vs. Non-AF scenarios. Furthermore, the results demonstrate notable enhancements in AF detection across various motion and light intensity levels.

Contactless Blood Pressure Measurement Via Remote Photoplethysmography With Synthetic Data Generation Using Generative Adversarial Networks.

Remote photoplethysmography (rPPG) has been used to measure vital signs such as heart rate, heart rate variability, blood pressure (BP), and blood oxygen. Recent studies adopt features developed with photoplethysmography (PPG) to achieve contactless BP measurement via rPPG. These features can be classified into two groups: time or phase differences from multiple signals, or waveform feature analysis from a single signal. Here we devise a solution to extract the time difference information from the rPPG signal captured at 30 FPS. We also propose a deep learning model architecture to estimate BP from the extracted features. To prevent overfitting and compensate for the lack of data, we leverage a multi-model design and generate synthetic data. We also use subject information related to BP to assist in model learning. For real-world usage, the subject information is replaced with values estimated from face images, with performance that is still better than the state-of-the-art. To our best knowledge, the improvements can be achieved because of: 1) the model selection with estimated subject information, 2) replacing the estimated subject information with the real one, 3) the InfoGAN assistance training (synthetic data generation), and 4) the time difference features as model input. To evaluate the performance of the proposed method, we conduct a series of experiments, including dynamic BP measurement for many single subjects and nighttime BP measurement with infrared lighting. Our approach reduces the MAE from 15.49 to 8.78 mmHg for systolic blood pressure (SBP) and 10.56 to 6.16 mmHg for diastolic blood pressure(DBP) on a self-constructed rPPG dataset. On the Taipei Veterans General Hospital(TVGH) dataset for nighttime applications, the MAE is reduced from 21.58 to 11.12 mmHg for SBP and 9.74 to 7.59 mmHg for DBP, with improvement ratios of 48.47% and 22.07% respectively.

Contact-Free Atrial Fibrillation Screening With Attention Network.

Atrial Fibrillation (AF) screening from face videos has become popular with the trend of telemedicine and telehealth in recent years. In this study, the largest facial image database for camera-based AF detection is proposed. There are 657 participants from two clinical sites and each of them is recorded for about 10 minutes of video data, which can be further processed as over 10 000 segments around 30 seconds, where the duration setting is referred to the guideline of AF diagnosis. It is also worth noting that, 2 979 segments are segment-wise labeled, that is, every rhythm is independently labeled with AF or not. Besides, all labels are confirmed by the cardiologist manually. Various environments, talking, facial expressions, and head movements are involved in data collection, which meets the situations in practical usage. Specific to camera-based AF screening, a novel CNN-based architecture equipped with an attention mechanism is proposed. It is capable of fusing heartbeat consistency, heart rate variability derived from remote photoplethysmography, and motion features simultaneously to reliable outputs. With the proposed model, the performance of intra-database evaluation comes up to 96.62% of sensitivity, 90.61% of specificity, and 0.96 of AUC. Furthermore, to check the capability of adaptation of the proposed method thoroughly, the cross-database evaluation is also conducted, and the performance also reaches about 90% on average with the AUCs being over 0.94 in both clinical sites.

Motion-Robust Atrial Fibrillation Detection Based on Remote-Photoplethysmography.

Atrial fibrillation (AF) has been proven highly correlated to stroke; more than 43 million people suffer from AF worldwide. However, most of these patients are unaware of their disease. There is no convenient tool by which to conduct a comprehensive screening to identify asymptomatic AF patients. Hence, we provide a non-contact AF detection approach based on remote photoplethysmography (rPPG). We address motion disturbance, the most challenging issue in rPPG technology, with the NR-Net, ATT-Net, and SQ-Mask modules. NR-Net is designed to eliminate motion noise with a CNN model, and ATT-Net and SQ-Mask utilize channel-wise and temporal attention to reduce the influence of poor signal segments. Moreover, we present an AF dataset collected from hospital wards which contains 452 subjects (mean age, 69.3 ±13.0 years; women, 46%) and 7,306 30-second segments to verify the proposed algorithm. To our best knowledge, this dataset has the most participants and covers the full age range of possible AF patients. The proposed method yields accuracy, sensitivity, and specificity of 95.69%, 96.76%, and 94.33%, respectively, when discriminating AF from normal sinus rhythm. More than previous studies, other arrhythmias are also taken into consideration, leading to a further investigation of AF vs. Non-AF and AF vs. Other scenarios. For the three scenarios, the proposed approach outperforms the benchmark algorithms. Additionally, the accuracy of the slight motion data improves to 95.82%, 92.39%, and 89.18% for the three scenarios, respectively, while that of full motion data increases by over 3%.

Identification of tophi in ultrasound imaging based on transfer learning and clinical practice.

Gout is a common metabolic disorder characterized by deposits of monosodium urate monohydrate crystals (tophi) in soft tissue, triggering intense and acute arthritis with intolerable pain as well as articular and periarticular inflammation. Tophi can also promote chronic inflammatory and erosive arthritis. 2015 ACR/EULAR Gout Classification criteria include clinical, laboratory, and imaging findings, where cases of gout are indicated by a threshold score of ≥ 8. Some imaging-related findings, such as a double contour sign in ultrasound, urate in dual-energy computed tomography, or radiographic gout-related erosion, generate a score of up to 4. Clearly, the diagnosis of gout is largely assisted by imaging findings; however, dual-energy computed tomography is expensive and exposes the patient to high levels of radiation. Although musculoskeletal ultrasound is non-invasive and inexpensive, the reliability of the results depends on expert experience. In the current study, we applied transfer learning to train a convolutional neural network for the identification of tophi in ultrasound images. The accuracy of predictions varied with the convolutional neural network model, as follows: InceptionV3 (0.871 ± 0.020), ResNet101 (0.913 ± 0.015), and VGG19 (0.918 ± 0.020). The sensitivity was as follows: InceptionV3 (0.507 ± 0.060), ResNet101 (0.680 ± 0.056), and VGG19 (0.747 ± 0.056). The precision was as follows: InceptionV3 (0.767 ± 0.091), ResNet101 (0.863 ± 0.098), and VGG19 (0.825 ± 0.062). Our results demonstrate that it is possible to retrain deep convolutional neural networks to identify the patterns of tophi in ultrasound images with a high degree of accuracy.

Contactless facial video recording with deep learning models for the detection of atrial fibrillation.

Atrial fibrillation (AF) is often asymptomatic and paroxysmal. Screening and monitoring are needed especially for people at high risk. This study sought to use camera-based remote photoplethysmography (rPPG) with a deep convolutional neural network (DCNN) learning model for AF detection. All participants were classified into groups of AF, normal sinus rhythm (NSR) and other abnormality based on 12-lead ECG. They then underwent facial video recording for 10 min with rPPG signals extracted and segmented into 30-s clips as inputs of the training of DCNN models. Using voting algorithm, the participant would be predicted as AF if > 50% of their rPPG segments were determined as AF rhythm by the model. Of the 453 participants (mean age, 69.3 ± 13.0 years, women, 46%), a total of 7320 segments (1969 AF, 1604 NSR & 3747others) were analyzed by DCNN models. The accuracy rate of rPPG with deep learning model for discriminating AF from NSR and other abnormalities was 90.0% and 97.1% in 30-s and 10-min recording, respectively. This contactless, camera-based rPPG technique with a deep-learning model achieved significantly high accuracy to discriminate AF from non-AF and may enable a feasible way for a large-scale screening or monitoring in the future.

A Heart Rate Monitoring Framework for Real-World Drivers Using Remote Photoplethysmography.

Remote photoplethysmography (rPPG) is an unobtrusive solution to heart rate monitoring in drivers. However, disturbances that occur during driving such as driver behavior, motion artifacts, and illuminance variation complicate the monitoring of heart rate. Faced with disturbance, one commonly used assumption is heart rate periodicity (or spectrum sparsity). Several methods improve stability at the expense of tracking sensitivity for heart rate variation. Based on statistical signal processing (SSP) and Monte Carlo simulations, the outlier probability is derived and ADaptive spectral filter banks (AD) is proposed as a new algorithm which provides an explicable tuning option for spectral filter banks to strike a balance between robustness and sensitivity in remote monitoring for driving scenarios. Moreover, we construct a driving database containing over 23 hours of data to verify the proposed algorithm. The influence on rPPG from driver habits (both amateurs and professionals), vehicle types (compact cars and buses), and routes are also evaluated. In comparison to state-of-the-art rPPG for driving scenarios, the mean absolute error in the Passengers, Compact Cars, and Buses scenarios is 3.43, 7.85, and 5.02 beats per minute, respectively. Moreover, AD also won the top third place in the first challenge on remote physiological signal sensing (RePSS) with relative low computational complexity.

A low memory zerotree coding for arbitrarily shaped objects.

The set partitioning in hierarchical trees (SPIHT) algorithm is a computationally simple and efficient zerotree coding technique for image compression. However, the high working memory requirement is its main drawback for hardware realization. We present a low memory zerotree coder (LMZC), which requires much less working memory than SPIHT. The LMZC coding algorithm abandons the use of lists, defines a different tree structure, and merges the sorting pass and the refinement pass together. The main techniques of LMZC are the recursive programming and a top-bit scheme (TBS). In TBS, the top bits of transformed coefficients are used to store the coding status of coefficients instead of the lists used in SPIHT. In order to achieve high coding efficiency, shape-adaptive discrete wavelet transforms are used to transformation arbitrarily shaped objects. A compact emplacement of the transformed coefficients is also proposed to further reduce working memory. The LMZC carefully treats "don't care" nodes in the wavelet tree and does not use bits to code such nodes. Comparison of LMZC with SPIHT shows that for coding a 768 /spl times/ 512 color image, LMZC saves at least 5.3 MBytes of memory but only increases a little execution time and reduces minor peak signal-to noise ratio (PSNR) values, thereby making it highly promising for some memory limited applications.

Gain-phase margin analysis of dynamic fuzzy control systems.

In this paper, we apply some effective methods, including the gain-phase margin tester, describing function and parameter plane, to predict the limit cycles of dynamic fuzzy control systems with adjustable parameters. Both continuous-time and sampled-data fuzzy control systems are considered. In general, fuzzy control systems are nonlinear. By use of the classical method of describing functions, the dynamic fuzzy controller may be linearized first. According to the stability equations and parameter plane methods, the stability of the equivalent linearized system with adjustable parameters is then analyzed. In addition, a simple approach is also proposed to determine the gain margin and phase margin which limit cycles can occur for robustness. Two examples of continuous-time fuzzy control systems with and without nonlinearity are presented to demonstrate the design procedure. Finally, this approach is also extended to a sampled-data fuzzy control system.