Neural network combining with clinical ultrasonography: A new approach for classification of salivary gland tumors.

OBJECTIVE: Little information is available about deep learning methods used in ultrasound images of salivary gland tumors. We aimed to compare the accuracy of the ultrasound-trained model to computed tomography or magnetic resonance imaging trained model. MATERIALS AND METHODS: Six hundred and thirty-eight patients were included in this retrospective study. There were 558 benign and 80 malignant salivary gland tumors. A total of 500 images (250 benign and 250 malignant) were acquired in the training and validation set, then 62 images (31 benign and 31 malignant) in the test set. Both machine learning and deep learning were used in our model. RESULTS: The test accuracy, sensitivity, and specificity of our final model were 93.5%, 100%, and 87%, respectively. There were no over fitting in our model as the validation accuracy was similar with the test accuracy. CONCLUSIONS: The sensitivity and specificity were comparable with current MRI and CT images using artificial intelligence.

An Open Dataset of Annotated Metaphase Cell Images for Chromosome Identification.

Chromosomes are a principal target of clinical cytogenetic studies. While chromosomal analysis is an integral part of prenatal care, the conventional manual identification of chromosomes in images is time-consuming and costly. This study developed a chromosome detector that uses deep learning and that achieved an accuracy of 98.88% in chromosomal identification. Specifically, we compiled and made available a large and publicly accessible database containing chromosome images and annotations for training chromosome detectors. The database contains five thousand 24 chromosome class annotations and 2,000 single chromosome annotations. This database also contains examples of chromosome variations. Our database provides a reference for researchers in this field and may help expedite the development of clinical applications.

Automatic ovarian tumors recognition system based on ensemble convolutional neural network with ultrasound imaging.

BACKGROUND: Upon the discovery of ovarian cysts, obstetricians, gynecologists, and ultrasound examiners must address the common clinical challenge of distinguishing between benign and malignant ovarian tumors. Numerous types of ovarian tumors exist, many of which exhibit similar characteristics that increase the ambiguity in clinical diagnosis. Using deep learning technology, we aimed to develop a method that rapidly and accurately assists the different diagnosis of ovarian tumors in ultrasound images. METHODS: Based on deep learning method, we used ten well-known convolutional neural network models (e.g., Alexnet, GoogleNet, and ResNet) for training of transfer learning. To ensure method stability and robustness, we repeated the random sampling of the training and validation data ten times. The mean of the ten test results was set as the final assessment data. After the training process was completed, the three models with the highest ratio of calculation accuracy to time required for classification were used for ensemble learning pertaining. Finally, the interpretation results of the ensemble classifier were used as the final results. We also applied ensemble gradient-weighted class activation mapping (Grad-CAM) technology to visualize the decision-making results of the models. RESULTS: The highest mean accuracy, mean sensitivity, and mean specificity of ten single CNN models were 90.51 ± 4.36%, 89.77 ± 4.16%, and 92.00 ± 5.95%, respectively. The mean accuracy, mean sensitivity, and mean specificity of the ensemble classifier method were 92.15 ± 2.84%, 91.37 ± 3.60%, and 92.92 ± 4.00%, respectively. The performance of the ensemble classifier is better than that of a single classifier in three evaluation metrics. Moreover, the standard deviation is also better which means the ensemble classifier is more stable and robust. CONCLUSION: From the comprehensive perspective of data quantity, data diversity, robustness of validation strategy, and overall accuracy, the proposed method outperformed the methods used in previous studies. In future studies, we will continue to increase the number of authenticated images and apply our proposed method in clinical settings to increase its robustness and reliability.

Towards precision sleep medicine: Self-attention GAN as an innovative data augmentation technique for developing personalized automatic sleep scoring classification.

It is very important to have good quality sleep, which can affect aspects such as memory consolidation, emotional regulation, learning, physical development, and quality of life. Diagnosing human sleep quality and problems quickly and accurately is an important issue for human well-being. Therefore, many automatic sleep scoring methods have been proposed. However, the methods have been developed using sleep data from different individuals or groups. The accuracies of these proposed methods might decrease, due to existing individual differences. In this study, the self-attention generative adversarial network (SAGAN) was applied as an advanced data augmentation technique to propose an improved personalized automatic sleep scoring classification. First, the spectrograms were converted from electroencephalography (EEG). Then, SAGAN was used to generate synthesized spectrograms for each subject. Finally, the real and synthesized spectrograms of each subject were utilized to train a personalized classifier. The averaged accuracy and standard deviation of the proposed method are 95.74% and 3.78%, respectively. Compared to the classifier trained with all subjects' training data, the average accuracy increased by 8.08%. The results proved that the generated spectrograms significantly improved the performance of the personalized automatic sleep scoring classification. The contributions of the proposed method were that made the medical staff and subjects save massive medical resources and time for manual recording and scoring.

Comparisons of the Nonlinear Relationship of Cerebral Blood Flow Response and Cerebral Vasomotor Reactivity to Carbon Dioxide under Hyperventilation between Postural Orthostatic Tachycardia Syndrome Patients and Healthy Subjects.

Postural orthostatic tachycardia syndrome (POTS) typically occurs in youths, and early accurate POTS diagnosis is challenging. A recent hypothesis suggests that upright cognitive impairment in POTS occurs because reduced cerebral blood flow velocity (CBFV) and cerebrovascular response to carbon dioxide (CO2) are nonlinear during transient changes in end-tidal CO2 (PETCO2). This novel study aimed to reveal the interaction between cerebral autoregulation and ventilatory control in POTS patients by using tilt table and hyperventilation to alter the CO2 tension between 10 and 30 mmHg. The cerebral blood flow velocity (CBFV), partial pressure of end-tidal carbon dioxide (PETCO2), and other cardiopulmonary signals were recorded for POTS patients and two healthy groups including those aged >45 years (Healthy-Elder) and aged <45 years (Healthy-Youth) throughout the experiment. Two nonlinear regression functions, Models I and II, were applied to evaluate their CBFV-PETCO2 relationship and cerebral vasomotor reactivity (CVMR). Among the estimated parameters, the curve-fitting Model I for CBFV and CVMR responses to CO2 for POTS patients demonstrated an observable dissimilarity in CBFVmax (p = 0.011), mid-PETCO2 (p = 0.013), and PETCO2 range (p = 0.023) compared with those of Healthy-Youth and in CBFVmax (p = 0.015) and CVMRmax compared with those of Healthy-Elder. With curve-fitting Model II for POTS patients, the fit parameters of curvilinear (p = 0.036) and PETCO2 level (p = 0.033) displayed significant difference in comparison with Healthy-Youth parameters; range of change (p = 0.042), PETCO2 level, and CBFVmax also displayed a significant difference in comparison with Healthy-Elder parameters. The results of this study contribute toward developing an early accurate diagnosis of impaired CBFV responses to CO2 for POTS patients.

Development of a human-computer collaborative sleep scoring system for polysomnography recordings.

The overnight polysomnographic (PSG) recordings of patients were scored by an expert to diagnose sleep disorders. Visual sleep scoring is a time-consuming and subjective process. Automatic sleep staging methods can help; however, the mechanism and reliability of these methods are not fully understood. Therefore, experts often need to rescore the recordings to obtain reliable results. Here, we propose a human-computer collaborative sleep scoring system. It is a rule-based automatic sleep scoring method that follows the American Academy of Sleep Medicine (AASM) guidelines to perform an initial scoring. Then, the reliability level of each epoch is analyzed based on physiological patterns during sleep and the characteristics of various stage changes. Finally, experts would only need to rescore epochs with a low-reliability level. The experimental results show that the average agreement rate between our system and fully manual scorings can reach 90.42% with a kappa coefficient of 0.85. Over 50% of the manual scoring time can be reduced. Due to the demonstrated robustness and applicability, the proposed approach can be integrated with various PSG systems or automatic sleep scoring methods for sleep monitoring in clinical or homecare applications in the future.

Development and Evaluation of a Wearable Device for Sleep Quality Assessment.

OBJECTIVE: In this study, a wearable actigraphy recording device with low sampling rate (1 Hz) for power saving and data reduction and a high accuracy wake-sleep scoring method for the assessment of sleep were developed. METHODS: The developed actigraphy recorder was successfully applied to overnight recordings of 81 subjects with simultaneous polysomnography (PSG) measurements. The total length of recording reached 639.8 h. A wake-sleep scoring method based on the concept of movement density evaluation and adaptive windowing was proposed. Data from subjects with good (N = 43) and poor (N = 16) sleep efficiency (SE) in the range of 52.7-97.42% were used for testing. The Bland-Altman technique was used to evaluate the concordance of various sleep measurements between the manual PSG scoring and the proposed actigraphy method. RESULTS: For wake-sleep staging, the average accuracy, sensitivity, specificity, and kappa coefficient of the proposed system were 92.16%, 95.02%, 71.30%, and 0.64, respectively. For the assessment of SE, the accuracy of classifying the subject with good or poor SE reached 91.53%. The mean biases of SE, sleep onset time, wake after sleep onset, and total sleep time were -0.95%, 0.74 min, 2.84 min, and -4.3 min, respectively. CONCLUSION: These experimental results demonstrate the robustness and reliability of our method using limited activity information to estimate wake-sleep stages during overnight recordings. SIGNIFICANCE: The results suggest that the proposed wearable actigraphy system is practical for the in-home screening of objective sleep measurements and objective evaluation of sleep improvement after treatment.

Combination of Expert Knowledge and a Genetic Fuzzy Inference System for Automatic Sleep Staging.

OBJECTIVE: In this paper, the genetic fuzzy inference system based on expert knowledge for automatic sleep staging was developed. METHODS: Eight features, including temporal and spectrum analyses of the EEG and EMG signals, were utilized as the input variables. The fuzzy rules and the fuzzy sets were constructed based on expert knowledge and the distributions of feature values at different sleep stages. Three experiments were designed to develop and evaluate the proposed system. PSGs of 32 healthy subjects and 16 subjects with insomnia were included in the experiment to develop and evaluate the proposed method. Finally, a complete sleep scoring system integrating two fuzzy inference models with robust performance on various subject groups is developed. RESULTS: The overall agreement and kappa coefficient of this integrated system applied to PSG data from 8 subjects with good sleep efficiency, 8 subjects with poor sleep efficiency and 8 subjects with insomnia were 86.44 % and 0.81, respectively. CONCLUSION: Due to the high performance of the proposed system, it is expected to integrate the proposed method with various PSG systems for sleep monitoring in clinical or homecare applications in the future. SIGNIFICANCE: An automatic sleep staging system integrating knowledge of the experts in scoring of PSG data and the elasticity of fuzzy systems in reasoning and decision making is proposed and the robustness and clinical applicability of the proposed method is demonstrated on data from healthy subjects and subjects with insomnia.

Using off-the-shelf lossy compression for wireless home sleep staging.

BACKGROUND: Recently, there has been increasing interest in the development of wireless home sleep staging systems that allow the patient to be monitored remotely while remaining in the comfort of their home. However, transmitting large amount of Polysomnography (PSG) data over the Internet is an important issue needed to be considered. In this work, we aim to reduce the amount of PSG data which has to be transmitted or stored, while having as little impact as possible on the information in the signal relevant to classify sleep stages. NEW METHOD: We examine the effects of off-the-shelf lossy compression on an all-night PSG dataset from 20 healthy subjects, in the context of automated sleep staging. The popular compression method Set Partitioning in Hierarchical Trees (SPIHT) was used, and a range of compression levels was selected in order to compress the signals with various degrees of loss. In addition, a rule-based automatic sleep staging method was used to automatically classify the sleep stages. RESULTS: Considering the criteria of clinical usefulness, the experimental results show that the system can achieve more than 60% energy saving with a high accuracy (>84%) in classifying sleep stages by using a lossy compression algorithm like SPIHT. COMPARISON WITH EXISTING METHOD(S): As far as we know, our study is the first that focuses how much loss can be tolerated in compressing complex multi-channel PSG data for sleep analysis. CONCLUSIONS: We demonstrate the feasibility of using lossy SPIHT compression for wireless home sleep staging.

A transition-constrained discrete hidden Markov model for automatic sleep staging.

BACKGROUND: Approximately one-third of the human lifespan is spent sleeping. To diagnose sleep problems, all-night polysomnographic (PSG) recordings including electroencephalograms (EEGs), electrooculograms (EOGs) and electromyograms (EMGs), are usually acquired from the patient and scored by a well-trained expert according to Rechtschaffen & Kales (R&K) rules. Visual sleep scoring is a time-consuming and subjective process. Therefore, the development of an automatic sleep scoring method is desirable. METHOD: The EEG, EOG and EMG signals from twenty subjects were measured. In addition to selecting sleep characteristics based on the 1968 R&K rules, features utilized in other research were collected. Thirteen features were utilized including temporal and spectrum analyses of the EEG, EOG and EMG signals, and a total of 158 hours of sleep data were recorded. Ten subjects were used to train the Discrete Hidden Markov Model (DHMM), and the remaining ten were tested by the trained DHMM for recognition. Furthermore, the 2-fold cross validation was performed during this experiment. RESULTS: Overall agreement between the expert and the results presented is 85.29%. With the exception of S1, the sensitivities of each stage were more than 81%. The most accurate stage was SWS (94.9%), and the least-accurately classified stage was S1 (<34%). In the majority of cases, S1 was classified as Wake (21%), S2 (33%) or REM sleep (12%), consistent with previous studies. However, the total time of S1 in the 20 all-night sleep recordings was less than 4%. CONCLUSION: The results of the experiments demonstrate that the proposed method significantly enhances the recognition rate when compared with prior studies.

A rule-based automatic sleep staging method.

In this paper, a rule-based automatic sleep staging method was proposed. Twelve features, including temporal and spectrum analyses of the EEG, EOG, and EMG signals, were utilized. Normalization was applied to each feature to reduce the effect of individual variability. A hierarchical decision tree, with fourteen rules, was constructed for sleep stage classification. Finally, a smoothing process considering the temporal contextual information was applied for the continuity. The average accuracy and kappa coefficient of the proposed method applied to the all night polysomnography (PSG) of twenty subjects compared with the manual scorings reached 86.5% and 0.78, respectively. This method can assist the clinical staff reduce the time required for sleep scoring in the future.