Rapid detection of non-normal teeth on dental X-ray images using improved Mask R-CNN with attention mechanism.

PURPOSE: Dental health has been getting increased attention. Timely detection of non-normal teeth (caries, residual root, retainer, teeth filling, etc.) is of great importance for people's health, well-being, and quality of life. This work proposes a rapid detection of non-normal teeth based on improved Mask R-CNN, aiming to achieve comprehensive screening of non-normal teeth on dental X-ray images. METHODS: An improved Mask R-CNN based on attention mechanism was used to develop a non-normal teeth detection method trained on a high-quality annotated dataset, which can segment the whole mask of each non-normal tooth on the dental X-ray image immediately. RESULTS: The average precision (AP) of the proposed non-normal teeth detection was 0.795 with an intersection-over-union of 0.5 and max detections (maxDets) of 32, which was higher than that of the typical Mask R-CNN method (AP = 0.750). In addition, validation experiments showed that the evaluation metrics (AP, recall, precision-recall (P-R) curve) of the proposed method were superior to those of the Mask R-CNN method. Furthermore, the experimental results indicated that proposed method exhibited a high sensitivity (95.65%) in detecting secondary caries. The proposed method took about 0.12 s to segment non-normal teeth on one dental X-ray image using the laptop (8G memory, NVIDIA RTX 3060 graphics processing unit), which was much faster than conventional manual methods. CONCLUSION: The proposed method enhances the accuracy and efficiency of abnormal tooth diagnosis for practitioners, while also facilitating early detection and treatment of dental caries to substantially lower patient costs. Additionally, it can enable rapid and objective evaluation of student performance in dental examinations.

TestFit: A plug-and-play one-pass test time method for medical image segmentation.

Deep learning (DL) based methods have been extensively studied for medical image segmentation, mostly emphasizing the design and training of DL networks. Only few attempts were made on developing methods for applying DL models in test time. In this paper, we study whether a given off-the-shelf segmentation network can be stably improved on-the-fly during test time in an online processing-and-learning fashion. We propose a new online test-time method, called TestFit, to improve results of a given off-the-shelf DL segmentation model in test time by actively fitting the test data distribution. TestFit first creates a supplementary network (SuppNet) from the given trained off-the-shelf segmentation network (this original network is referred to as OGNet) and applies SuppNet together with OGNet for test time inference. OGNet keeps its hypothesis derived from the original training set to prevent the model from collapsing, while SuppNet seeks to fit the test data distribution. Segmentation results and supervision signals (for updating SuppNet) are generated by combining the outputs of OGNet and SuppNet on the fly. TestFit needs only one pass on each test sample - the same as the traditional test model pipeline - and requires no training time preparation. Since it is challenging to look at only one test sample and no manual annotation for model update each time, we develop a series of technical treatments for improving the stability and effectiveness of our proposed online test-time training method. TestFit works in a plug-and-play fashion, requires minimal hyper-parameter tuning, and is easy to use in practice. Experiments on a large collection of 2D and 3D datasets demonstrate the capability of our TestFit method.

Study on the effective measurement area of an open-ended coaxial probe for the dielectric measurement of biological tissues.

BACKGROUND: The dielectric properties of tissues are very important physical factors for the investigation and application of bio-electromagnetism. However, the size of the active sample tissue is usually limited in actual measurement, making it difficult to meet the requirements of the existing high-frequency measurement methods, thus influencing the measurement results. OBJECTIVE: The present study aimed to systematically investigate the various factors influencing the effective measurement area of the open-ended coaxial probe, including the design size of the probe and the dielectric properties of the object to be measured. METHODS: The simplified material mixing model, in which several types of materials were set as the material under test (MUT) and the perfect conductor (PEC) was set as the specific material, was used in the simulation to study the effective measurement area of eight types of probes with different sizes for the dielectric measurement of different MUTs. Different concentrations of NaCl solutions and three types of coaxial probes were used in the actual measurement to verify the simulation results. RESULTS: According to the simulation results, the effective measurement area, especially the effective measurement radius, was closely related to the outer conductor radius of the probe. The effective measurement area of the probe decreased when the outer conductor radius of the probe reduced. Moreover, the change in the effective measurement area of the probe was independent of the MUT when the cross-sectional size of the probe was smaller than a certain threshold value. The experimental results also confirmed this conclusion. CONCLUSION: According to the research results, the independent variable dimension could be effectively reduced and the modeling difficulty was reduced when the analysis model of the effective measurement area of the probe was established.

Temperature dependence of dielectric properties of blood at 10 Hz-100 MHz.

The temperature dependence of the dielectric properties of blood is important for studying the biological effects of electromagnetic fields, electromagnetic protection, disease diagnosis, and treatment. However, owing to the limitations of measurement methods, there are still some uncertainties regarding the temperature characteristics of the dielectric properties of blood at low and medium frequencies. In this study, we designed a composite impedance measurement box with high heat transfer efficiency that allowed for a four/two-electrode measurement method. Four-electrode measurements were carried out at 10 Hz-1 MHz to overcome the influence of electrode polarization, and two-electrode measurements were carried out at 100 Hz-100 MHz to avoid the influence of distribution parameters, and the data was integrated to achieve dielectric measurements at 10 Hz-100 MHz. At the same time, the temperature of fresh blood from rabbits was controlled at 17-39°C in combination with a temperature-controlled water sink. The results showed that the temperature coefficient for the real part of the resistivity of blood remained constant from 10 Hz to 100 kHz (-2.42%/°C) and then gradually decreased to -0.26%/°C. The temperature coefficient of the imaginary part was positive and bimodal from 6.31 kHz to 100 MHz, with peaks of 5.22%/°C and 4.14%/°C at 126 kHz and 39.8 MHz, respectively. Finally, a third-order function model was developed to describe the dielectric spectra at these temperatures, in which the resistivity parameter in each dispersion zone decreased linearly with temperature and each characteristic frequency increased linearly with temperature. The model could estimate the dielectric properties at any frequency and temperature in this range, and the maximum error was less than 1.39%, thus laying the foundation for subsequent studies.

A Machine Learning-Based System for Real-Time Polyp Detection (DeFrame): A Retrospective Study.

Background and Aims: Recent studies have shown that artificial intelligence-based computer-aided detection systems possess great potential in reducing the heterogeneous performance of doctors during endoscopy. However, most existing studies are based on high-quality static images available in open-source databases with relatively small data volumes, and, hence, are not applicable for routine clinical practice. This research aims to integrate multiple deep learning algorithms and develop a system (DeFrame) that can be used to accurately detect intestinal polyps in real time during clinical endoscopy. Methods: A total of 681 colonoscopy videos were collected for retrospective analysis at Xiangya Hospital of Central South University from June 2019 to June 2020. To train the machine learning (ML)-based system, 6,833 images were extracted from 48 collected videos, and 1,544 images were collected from public datasets. The DeFrame system was further validated with two datasets, consisting of 24,486 images extracted from 176 collected videos and 12,283 images extracted from 259 collected videos. The remaining 198 collected full-length videos were used for the final test of the system. The measurement metrics were sensitivity and specificity in validation dataset 1, precision, recall and F1 score in validation dataset 2, and the overall performance when tested in the complete video perspective. Results: A sensitivity and specificity of 79.54 and 95.83%, respectively, was obtained for the DeFrame system for detecting intestinal polyps. The recall and precision of the system for polyp detection were determined to be 95.43 and 92.12%, respectively. When tested using full colonoscopy videos, the system achieved a recall of 100% and precision of 80.80%. Conclusion: We have developed a fast, accurate, and reliable DeFrame system for detecting polyps, which, to some extent, is feasible for use in routine clinical practice.

Automated Disease Detection in Gastroscopy Videos Using Convolutional Neural Networks.

A large percentage of the world's population is affected by gastric diseases ranging from erosion and ulcer to serious ailments such as gastric cancer, which is mainly caused by Helicobacter pylori(H.pylori) infection. While most erosions and ulcers are benign, severe cases of gastric diseases can still develop into cancer. Thus, early screening and treatment of all gastric diseases are of great importance. Upper gastroscopy is one such common screening procedure that visualizes the patient's upper digestive system by inserting a camera attached to a rubber tube down the patient's digestive tracts, but since the procedure requires manual inspection of the video feed, it is prone to human errors. To improve the sensitivity and specificity of gastroscopies, we applied deep learning methods to develop an automated gastric disease detection system that detects frames of the video feed showing signs of gastric diseases. To this end, we collected data from images in anonymous patient case reports and gastroscopy videos to train and evaluate a convolutional neural network (CNN), and we used sliding window to improve the stability of our model's video performance. Our CNN model achieved 84.92% sensitivity, 88.26% specificity, and 85.2% F1-score on the test set, as well as 97% true positive rate and 16.2% false positive rate on a separate video test set.

AFP-Mask: Anchor-Free Polyp Instance Segmentation in Colonoscopy.

Colorectal cancer (CRC) is a common and lethal disease. Globally, CRC is the third most commonly diagnosed cancer in males and the second in females. The most effective way to prevent CRC is through using colonoscopy to identify and remove precancerous growths at an early stage. The detection and removal of colorectal polyps have been found to be associated with a reduction in mortality from colorectal cancer. However, the false negative rate of polyp detection during colonoscopy is often high even for experienced physicians. With recent advances in deep learning based object detection techniques, automated polyp detection shows great potential in helping physicians reduce false positive rate during colonoscopy. In this paper, we propose a novel anchor-free instance segmentation framework that can localize polyps and produce the corresponding instance level masks without using predefined anchor boxes. Our framework consists of two branches: (a) an object detection branch that performs classification and localization, (b) a mask generation branch that produces instance level masks. Instead of predicting a two-dimensional mask directly, we encode it into a compact representation vector, which allows us to incorporate instance segmentation with one-stage bounding-box detectors in a simple yet effective way. Moreover, our proposed encoding method can be trained jointly with object detector. Our experiment results show that our framework achieves a precision of 99.36% and a recall of 96.44% on public datasets, outperforming existing anchor-free instance segmentation methods by at least 2.8% in mIoU on our private dataset.

Monitoring deterioration of knee osteoarthritis using vibration arthrography in daily activities.

BACKGROUND AND OBJECTIVE: Pathological recognition of knee joint using vibration arthrography (VAG) is increasingly becoming prevailed, due to the non-invasive and non-radiative benefits. However, knee joint health monitoring using VAG signals is a difficult problem, since VAG signals are contaminated by strong motion artifacts (MA) caused by knee movements during daily activities, such as squatting. So far few works have investigated this problem. Existing studies mainly focused on clinical diagnosis of knee disorders for 2-class (normal/abnormal) classification using VAG signals, which are less contaminated by MA in the scene when subjects perform knee extension and flexion movements in seated position. The purpose of this study is to propose a framework to monitor knee joint health during daily activities. METHODS: In this paper, a general framework is designed to monitor knee joint health, which consists of VAG enhancement, feature extraction and fusion, and classification. VAG enhancement aims to remove MA and irrelevant components of knee joint pathologies in raw VAG signals. Distinctive features from enhanced VAG signals are obtained in feature extraction and fusion. Classification can not only distinguish whether the knee joint is normal or abnormal, but also distinguish the grade of deterioration of knee osteoarthritis. RESULTS: 813 VAG signals from VAG-OA dataset, which is currently the largest VAG dataset, have been collected from medical cases in Xijing Hospital of the Fourth Military Medical University during daily activities. Experimental results on VAG-OA dataset showed that the accuracy of 2-class (normal/abnormal) classification was 95.9% with sensitivity 98.1% and specificity 93.3%. For 5-class classification based on deterioration grades of osteoarthritis (OA), we obtained accuracy 74.4%, sensitivity 52.6% and specificity 78.3%. CONCLUSION: The VAG-OA dataset can be used not only for knee joint health monitoring but also for clinical diagnosis. The designed framework on VAG-OA dataset has high classification accuracy, which is of great value to monitor knee joint health using VAG signals during daily activities. The results also demonstrate that the designed framework significantly outperforms the baselines and several state-of-the-art methods.

Nursing Perspectives on the Impacts of COVID-19: Social Media Content Analysis.

BACKGROUND: Nurses are at the forefront of the COVID-19 pandemic. During the pandemic, nurses have faced an elevated risk of exposure and have experienced the hazards related to a novel virus. While being heralded as lifesaving heroes on the front lines of the pandemic, nurses have experienced more physical, mental, and psychosocial problems as a consequence of the COVID-19 outbreak. Social media discussions by nursing professionals participating in publicly formed Facebook groups constitute a valuable resource that offers longitudinal insights. OBJECTIVE: This study aimed to explore how COVID-19 impacted nurses through capturing public sentiments expressed by nurses on a social media discussion platform and how these sentiments changed over time. METHODS: We collected over 110,993 Facebook discussion posts and comments in an open COVID-19 group for nurses from March 2020 until the end of November 2020. Scraping of deidentified offline HTML tags on social media posts and comments was performed. Using subject-matter expert opinions and social media analytics (ie, topic modeling, information retrieval, and sentiment analysis), we performed a human-in-a-loop analysis of nursing professionals' key perspectives to identify trends of the COVID-19 impact among at-risk nursing communities. We further investigated the key insights of the trends of the nursing professionals' perspectives by detecting temporal changes of comments related to emotional effects, feelings of frustration, impacts of isolation, shortage of safety equipment, and frequency of safety equipment uses. Anonymous quotes were highlighted to add context to the data. RESULTS: We determined that COVID-19 impacted nurses' physical, mental, and psychosocial health as expressed in the form of emotional distress, anger, anxiety, frustration, loneliness, and isolation. Major topics discussed by nurses were related to work during a pandemic, misinformation spread by the media, improper personal protective equipment (PPE), PPE side effects, the effects of testing positive for COVID-19, and lost days of work related to illness. CONCLUSIONS: Public Facebook nursing groups are venues for nurses to express their experiences, opinions, and concerns and can offer researchers an important insight into understanding the COVID-19 impact on health care workers.

Implementing a socio-technical system for computer-aided tuberculosis diagnosis in Peru: A field trial among health professionals in resource-constraint settings.

A major challenge of tuberculosis diagnosis is the lack of universal accessibility to bacteriological confirmation. Computer-aided diagnostic interventions have been developed to address this gap and their successful implementation depends on many health systems factors. A socio-technical system to implement a computer-aided diagnostic tuberculosis diagnosis was preliminary tested in five primary health centers located in Lima, Peru. We recruited nurses (n = 7) and tuberculosis physicians (n = 5) from these health centers to participate in a field trial of an mHealth tool (eRx X-ray diagnostic app). From September 2018 to February 2019, the nurses uploaded images of chest X-rays using smartphones and the physicians reviewed those images on web-based platforms using tablets. Both completed weekly written feedback about their experience. Each nurse participated for a median duration of 12 weeks (interquartile range = 7.5-15.5), but image upload was only possible at a median of 58 percent (interquartile range = 35.1%-84.4%) of those weeks. Each physician participated for a median duration of 17 weeks (interquartile range = 12-17), but X-ray image review was only possible at a median of 52 percent (interquartile range = 49.7%-57.4%) of those weeks. Heavy workload was most frequently provided as the reason for missing data. Several infrastructural and technological challenges impaired the effective implementation of the mHealth tool, irrespective of its diagnostic accuracy.

Real-Time Detection of Hemothorax and Monitoring its Progression in a Piglet Model by Electrical Impedance Tomography: A Feasibility Study.

Hemothorax is a serious medical condition that can be life-threatening if left untreated. Early diagnosis and timely treatment are of great importance to produce favorable outcome. Although currently available diagnostic techniques, e.g., chest radiography, ultrasonography, and CT, can accurately detect hemothorax, delayed hemothorax cannot be identified early because these examinations are often performed on patients until noticeable symptoms manifest. Therefore, for early detection of delayed hemothorax, real-time monitoring by means of a portable and noninvasive imaging technique is needed. In this study, we employed electrical impedance tomography (EIT) to detect the onset of hemothorax in real time on eight piglet hemothorax models. The models were established by injection of 60 ml fresh autologous blood into the pleural cavity, and the subsequent development of hemothorax was monitored continuously. The results showed that EIT was able to sensitively detect hemothorax as small as 10 ml in volume, as well as its location. Also, the development of hemothorax over a range of 10 ml up to 60 ml was well monitored in real time, with a favorable linear relationship between the impedance change in EIT images and the volume of blood injected. These findings demonstrated that EIT has a unique potential for early diagnosis and continuous monitoring of hemothorax in clinical practice, providing medical staff valuable information for prompt identification and treatment of delayed hemothorax.

[A multifrequency time-difference electrical impedance tomography algorithm using spectral constraints].

This study aims to propose a multifrequency time-difference algorithm using spectral constraints. Based on the knowledge of tissue spectrum in the imaging domain, the fraction model was used in conjunction with the finite element method (FEM) to approximate a conductivity distribution. Then a frequency independent parameter (volume or area fraction change) was reconstructed which made it possible to simultaneously employ multifrequency time-difference boundary voltage data and then reduce the degrees of freedom of the reconstruction problem. Furthermore, this will alleviate the illness of the EIT inverse problem and lead to a better reconstruction result. The numerical validation results suggested that the proposed time-difference fraction reconstruction algorithm behaved better than traditional damped least squares algorithm (DLS) especially in the noise suppression capability. Moreover, under the condition of low signal-to-noise ratio, the proposed algorithm had a more obvious advantage in reconstructions of targets shape and position. This algorithm provides an efficient way to simultaneously utilize multifrequency measurement data for time-difference EIT, and leads to a more accurate reconstruction result. It may show us a new direction for the development of time-difference EIT algorithms in the case that the tissue spectrums are known.

Combing signal processing methods with algorithm priori information to produce synergetic improvements on continuous imaging of brain electrical impedance tomography.

Dynamic electrical impedance tomography (EIT) promises to be a valuable technique for monitoring the development of brain injury. But in practical long-term monitoring, noise and interferences may cause insufficient image quality. To help unveil intracranial conductivity changes, signal processing methods were introduced to improve EIT data quality and algorithms were optimized to be more robust. However, gains for EIT image reconstruction can be significantly increased if we combine the two techniques properly. The basic idea is to apply the priori information in algorithm to help de-noise EIT data and use signal processing to optimize algorithm. First, we process EIT data with principal component analysis (PCA) and reconstruct an initial CT-EIT image. Then, as the priori that changes in scalp and skull domains are unwanted, we eliminate their corresponding boundary voltages from data sets. After the two-step denoising process, we finally re-select a local optimal regularization parameter and accomplish the reconstruction. To evaluate performances of the signal processing-priori information based reconstruction (SPR) method, we conducted simulation and in-vivo experiments. The results showed SPR could improve brain EIT image quality and recover the intracranial perturbations from certain bad measurements, while for some measurement data the generic reconstruction method failed.

Noninvasive Cerebral Imaging and Monitoring Using Electrical Impedance Tomography During Total Aortic Arch Replacement.

OBJECTIVE: To explore the feasibility of using electrical impedance tomography (EIT) to provide noninvasive cerebral imaging and monitoring in total aortic arch replacement (TAAR). DESIGN: A prospective, observational study. SETTING: Department of cardiovascular surgery in a university hospital. PARTICIPANTS: Forty-two patients undergoing TAAR using hypothermic circulatory arrest and unilateral antegrade cerebral perfusion. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Cerebral impedances of the patients were monitored intraoperatively by an EIT system. The prognostic information of the patients, including postoperative neurological dysfunction, was collected during their hospitalizations. Eight (19.0%) subjects had at least 1 postoperative neurological dysfunction complication. The results show that cerebral impedance was related negatively to perfusion flow, and the gradual increase in cerebral resistivity might reflect the evolving process of brain tissue caused by hypoxia. Maximum resistivity asymmetry index was extracted from the reconstructed images to quantify the pathological changes of the brain. The area under the receiver operating characteristic curve of maximum resistivity asymmetry index for postoperative neurological dysfunction was 0.864. In multivariate logistic regression, maximum resistivity asymmetry index was the strongest independent predictor of neurological dysfunction with an odds ratio of 24.3. CONCLUSION: EIT is a promising technique to provide noninvasive cerebral imaging and monitoring in TAAR.

Unveiling the development of intracranial injury using dynamic brain EIT: an evaluation of current reconstruction algorithms.

OBJECTIVE: Dynamic brain electrical impedance tomography (EIT) is a promising technique for continuously monitoring the development of cerebral injury. While there are many reconstruction algorithms available for brain EIT, there is still a lack of study to compare their performance in the context of dynamic brain monitoring. APPROACH: To address this problem, we develop a framework for evaluating different current algorithms with their ability to correctly identify small intracranial conductivity changes. Firstly, a simulation 3D head phantom with realistic layered structure and impedance distribution is developed. Next several reconstructing algorithms, such as back projection (BP), damped least-square (DLS), Bayesian, split Bregman (SB) and GREIT are introduced. We investigate their temporal response, noise performance, location and shape error with respect to different noise levels on the simulation phantom. The results show that the SB algorithm demonstrates superior performance in reducing image error. To further improve the location accuracy, we optimize SB by incorporating the brain structure-based conductivity distribution priors, in which differences of the conductivities between different brain tissues and the inhomogeneous conductivity distribution of the skull are considered. We compare this novel algorithm (called SB-IBCD) with SB and DLS using anatomically correct head shaped phantoms with spatial varying skull conductivity. Main results and Significance: The results showed that SB-IBCD is the most effective in unveiling small intracranial conductivity changes, where it can reduce the image error by an average of 30.0% compared to DLS.

For You and Your Baby (4YYB): Adapting the Centers for Disease Control and Prevention's Text4Baby Program for Saudi Arabia.

BACKGROUND: Poor birth outcomes in the Kingdom of Saudi Arabia (KSA) have been found to be partially due to missed prenatal appointments as well as lack of knowledge of healthy pregnancy behaviors. OBJECTIVE: The objectives are to summarize birth outcomes and the antenatal care system in KSA, summarize research related to the US Text4Baby mobile health program, and outline the development of an Arabic version of the Text4baby app, For You and Your Baby (4YYB). METHODS: First, birth outcomes, health care access, and smartphone usage among Saudi Arabian women are reviewed. Next, the current evidence behind Text4Baby is described. Finally, a plan to develop and test 4YYB is proposed. In the plan, studies will need to be conducted to determine the effectiveness of 4YYB in educating pregnant Saudi women on healthy knowledge and behaviors. This will create an evidence base behind 4YYB before it is launched as a full-scale public health effort in KSA. RESULTS: The KSA offers public medical services but remaining challenges include poor birth outcomes and health care access barriers. An estimated 73% to 84% of Saudi women of child-bearing age use smartphone social media apps. A total of 13 published articles on Text4Baby were identified and reviewed. Due to design limitations, the studies provide only limited evidence about the effectiveness of the program in increasing healthy pregnancy knowledge and behaviors. To be useful for Saudi women, the educational messages in 4YYB will need to be translated from English to Arabic and tailored for cultural norms. CONCLUSIONS: Developing the 4YYB Arabic-language app for use by pregnant Saudi Arabian women based on Text4Baby is a viable approach, but a rigorous study design is needed to determine its effectiveness in improving healthy pregnancy knowledge and behaviors.

Towards research-tested smartphone applications for preventing breast cancer.

Efforts to prevent breast cancer and other chronic illnesses have focused on promoting physical activity, healthy diet and nutrition, and avoidance of excessive alcohol consumption. Smartphone applications (apps) offer a low-cost, effective strategy for breast cancer prevention in women through behavioral change. However, there are currently no research-tested smartphone apps for breast cancer prevention that are suitable for women with varying levels of health literacy and eHealth literacy. In this perspective, we consider modifiable risk factors for breast cancer in women in relation to the development of smartphone apps to promote healthy behaviors associated with breast cancer-risk reduction. First, we provide a summary of breast cancer risk factors that are modifiable through behavioral change including their corresponding relative risk. Second, we discuss scientific issues related to the development of smartphone apps for the primary prevention of breast cancer and offer suggestions for further research. Smartphone apps for preventing breast cancer should be tailored for women at different life stages (e.g., young women, women who are post-menopausal, and older women). Topics such as breastfeeding and oral contraceptives are appropriate for younger women. Weight management, physical activity, avoiding cigarette smoking, and dispelling breast cancer myths are appropriate for women of all ages. As women age, topics such as hormone replacement therapy or comorbid health conditions become more important to address. Apps for breast cancer prevention should be grounded in a behavioral theory or framework and should be suitable for people with varying levels of health literacy. Future developments in smartphone apps for breast cancer prevention should include apps that are tailored for specific cultural, racial, and ethnic groups.

Mobile Phone Apps for Preventing Cancer Through Educational and Behavioral Interventions: State of the Art and Remaining Challenges.

BACKGROUND: Rapid developments in technology have encouraged the use of mobile phones in smoking cessation, promoting healthy diet, nutrition, and physical activity, sun safety, and cancer screening. Although many apps relating to the prevention of cancer and other chronic diseases are available from major mobile phone platforms, relatively few have been tested in research studies to determine their efficacy. OBJECTIVE: In this paper, we discuss issues related to the development and testing of new apps for preventing cancer through smoking cessation, sun safety, and other healthy behaviors, including key methodologic issues and outstanding challenges. METHODS: An exploratory literature review was conducted using bibliographic searches in PubMed and CINAHL with relevant search terms (eg, smartphones, smoking cessation, cancer prevention, cancer screening, and carcinogens) to identify papers published in English through October 2015. RESULTS: Only 4 randomized controlled trials of the use of mobile phone apps for smoking cessation and 2 trials of apps for sun safety were identified, indicating that it is premature to conduct a systematic search and meta-analysis of the published literature on this topic. CONCLUSIONS: Future studies should utilize randomized controlled trial research designs, larger sample sizes, and longer study periods to better establish the cancer prevention and control capabilities of mobile phone apps. In developing new and refined apps for cancer prevention and control, both health literacy and eHealth literacy should be taken into account. There is a need for culturally appropriate, tailored health messages to increase knowledge and awareness of health behaviors such as smoking cessation, cancer screening, and sun safety. Mobile phone apps are likely to be a useful and low-cost intervention for preventing cancer through behavioral changes.

TROIKA: a general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise.

Heart rate monitoring using wrist-type photoplethysmographic signals during subjects' intensive exercise is a difficult problem, since the signals are contaminated by extremely strong motion artifacts caused by subjects' hand movements. So far few works have studied this problem. In this study, a general framework, termed TROIKA, is proposed, which consists of signal decomposiTion for denoising, sparse signal RecOnstructIon for high-resolution spectrum estimation, and spectral peaK trAcking with verification. The TROIKA framework has high estimation accuracy and is robust to strong motion artifacts. Many variants can be straightforwardly derived from this framework. Experimental results on datasets recorded from 12 subjects during fast running at the peak speed of 15 km/h showed that the average absolute error of heart rate estimation was 2.34 beat per minute, and the Pearson correlation between the estimates and the ground truth of heart rate was 0.992. This framework is of great values to wearable devices such as smartwatches which use PPG signals to monitor heart rate for fitness.