Treatment of Nocturnal Enuresis Using Miniaturised Smart Mechatronics With Artificial Intelligence.

Our study was designed to develop a customisable, wearable, and comfortable medical device - the text so-called "MyPAD" that monitors the fullness of the bladder, triggering an alarm indicating the need to void, in order to prevent badwetting - i.e., treating Nocturnal Enuresis (NE) at the text pre-void stage using miniaturised mechatronics with Artificial Intelligence (AI). The developed features include: multiple bespoke ultrasound (US) probes for sensing, a bespoke electronic device housing custom US electronics for signal processing, a bedside alarm box for processing the echoed pulses and generating alarms, and a phantom to mimic the human body. The validation of the system is conducted on the text tissue-mimicking phantom and volunteers using Bidirectional Long Short-Term Memory Recurrent Neural Networks (Bi-LSTM-RNN) and Reinforcement Learning (RL). A Se value of 99% and a Sp value of 99.5% with an overall accuracy rate of 99.3% are observed. The obtained results demonstrate successful empirical evidence for the viability of the device, both in monitoring bladder expansion to determine voiding need and in reinforcing the continuous learning and customisation of the device for bladder control through consecutive uses. Clinical impact: MyPAD will treat the NE better and efficiently against other techniques currently used (e.g., post-void alarms) and will i) replace those techniques quickly considering sufferers' condition while being treated by other approaches, and ii) enable children to gain control of incontinence over time and consistently have dry nights. Category: Early/Pre-Clinical Research.

Pupil Localisation and Eye Centre Estimation Using Machine Learning and Computer Vision.

Various methods have been used to estimate the pupil location within an image or a real-time video frame in many fields. However, these methods lack the performance specifically in low-resolution images and varying background conditions. We propose a coarse-to-fine pupil localisation method using a composite of machine learning and image processing algorithms. First, a pre-trained model is employed for the facial landmark identification to extract the desired eye frames within the input image. Then, we use multi-stage convolution to find the optimal horizontal and vertical coordinates of the pupil within the identified eye frames. For this purpose, we define an adaptive kernel to deal with the varying resolution and size of input images. Furthermore, a dynamic threshold is calculated recursively for reliable identification of the best-matched candidate. We evaluated our method using various statistical and standard metrics along with a standardised distance metric that we introduce for the first time in this study. The proposed method outperforms previous works in terms of accuracy and reliability when benchmarked on multiple standard datasets. The work has diverse artificial intelligence and industrial applications including human computer interfaces, emotion recognition, psychological profiling, healthcare, and automated deception detection.

Intelligent autonomous treatment of bedwetting using non-invasive wearable advanced mechatronics systems and MEMS sensors : Intelligent autonomous bladder monitoring to treat NE.

Post-void alarm systems to monitor bedwetting in nocturnal enuresis (NE) have been deemed unsatisfactory. The aim of this study is to develop a safe, comfortable and non-invasive pre-void wearable alarm and associated technologies using advanced mechatronics. Each stage of development includes patient and public involvement and engagement (PPI). The early stages of the development involved children with and without NE (and parents) who were tested at a hospital under the supervision of physicians, radiologists, psychologists, and nurses. The readings of the wearable device were simultaneously compared with B-mode images and measurements, acquired from a conventional ultrasound device, and were found to correlate highly. The results showed that determining imminent voiding need is viable using non-invasive sensors. Following on from "proof of concept," a bespoke advanced mechatronics device has been developed. The device houses custom electronics, an ultrasound system, intelligent software, a user-friendly smartphone application, bedside alarm box, and a dedicated undergarment, along with a self-adhesive gel pad-designed to keep the MEMS sensors aligned with the abdomen. Testing of the device with phantoms and volunteers has been successful in determining bladder volume and associated voiding need. Five miniaturised, and therefore more ergonomic, versions of the device are being developed, with an enabled connection to the cloud platform for location independent control and monitoring. Thereafter, the enhanced device will be tested with children with NE at their homes for 14 weeks, to gain feedback relating to wearability and data collection involving the cloud platform. Graphical Abstract Design of the MyPAD advanced mechatronics system.

Patient Engagement in Medical Device Design: Refining the Essential Attributes of a Wearable, Pre-Void, Ultrasound Alarm for Nocturnal Enuresis.

BACKGROUND: To date, no pre-void wearable alarm exists to treat nocturnal enuresis (NE)-night-time bedwetting, and children with NE and their families are disappointed in relation to the post-void moisture alarms and medicine currently available. Development of a safe, comfortable and non-invasive wearable pre-void alarm and associated technology, using advanced mechatronics, is underway (the MyPAD device). Each stage of development includes patient and public involvement (PPI), particularly with respect to human factors, in collaboration with physicians, radiologists, psychologists, nurses, engineers and designers. OBJECTIVES: The aim of this study was to help us understand the families' experience of the condition of enuresis, and to provide opinion relating to existing NE alarms, designed to detect moisture, and most importantly, the initial design of the MyPAD wearable technology. METHODS: A PPI workshop in the form of a focus group, made up of children with enuresis and their parents, was conducted during the early stage of the MyPAD product development. The key research questions (RQs) were: (RQ1) What were the families' experiences of using existing post-void enuresis alarms? (RQ2) What do families like about the MyPAD prototype? and (RQ3) What do families not like about the MyPAD prototype? A nurse specialised in terms of NE treatment, including post-void alarms, from the Lancashire Teaching Hospitals NHS Foundation Trust, and two MyPAD design engineers were also present, to explain the MyPAD design concept. Braun and Clarke's six-phase approach to thematic analysis was implemented, which included familiarisation with the data, initial descriptive coding, identifying themes, reviewing themes, defining and labelling themes and producing a report. RESULTS: Four common themes were identified from the focus group discussions: the importance of sleep; children do not want to feel different; parents feel frustrated and concerned; resilience and perseverance. These themes applied across the research questions; for example, sleep disruption was highlighted as an issue with existing post-void alarms and as an important requirement for the design of MyPAD. The evaluation of the early version of the MyPAD device has prompted the consideration of changes to some existing facets of the device, including providing multiple alarm types, more options for the design of the garment that houses the device, and the need for clear, age-appropriate and informative instructions relating to how the device should be used, in order to maximise its performance/efficiency and acceptance. CONCLUSIONS: The qualitative data derived from the focus group discussion was incredibly valuable as it enabled the research and design team to experience the perspectives of the families in terms of the challenges and conflicts of managing the condition and the limited utility of existing post-void alarms. This has improved our understanding of the social and environmental challenges that will need to be considered during the design process.

Feasibility study of intelligent autonomous determination of the bladder voiding need to treat bedwetting using ultrasound and smartphone ML techniques : Intelligent autonomous treatment of bedwetting.

Unsatisfactory cure rates for the treatment of nocturnal enuresis (NE), i.e. bed-wetting, have led to the need to explore alternative modalities. New treatment methods that focus on preventing enuretic episodes by means of a pre-void alerting system could improve outcomes for children with NE in many aspects. No such technology exists currently to monitor the bladder to alarm before bed-wetting. The aim of this study is to carry out the feasibility of building, refining and evaluating a new, safe, comfortable and non-invasive wearable autonomous intelligent electronic device to monitor the bladder using a single-element low-powered low-frequency ultrasound with the help of Machine Learning techniques and to treat NE by warning the patient at the pre-void stage, enhancing quality of life for these children starting from the first use. The sensitivity and specificity values are 0.89 and 0.93 respectively for determining imminent voiding need. The results indicate that customised imminent voiding need based on the expansion of the bladder can be determined by applying a single-element transducer on a bladder in intermittent manner. The acquired results can be improved further with a comfortable non-invasive device by adding several more features to the current features employed in this pilot study. Graphical Abstract Ultrasound device design: echoed US pulses reflected from the bladder and related tissues around the bladder is detected. These pulses are analysed, and an alarm is triggered when needed to treat nocturnal enuresis.

Biomedical visual data analysis to build an intelligent diagnostic decision support system in medical genetics.

BACKGROUND: In general, medical geneticists aim to pre-diagnose underlying syndromes based on facial features before performing cytological or molecular analyses where a genotype-phenotype interrelation is possible. However, determining correct genotype-phenotype interrelationships among many syndromes is tedious and labor-intensive, especially for extremely rare syndromes. Thus, a computer-aided system for pre-diagnosis can facilitate effective and efficient decision support, particularly when few similar cases are available, or in remote rural districts where diagnostic knowledge of syndromes is not readily available. METHODS: The proposed methodology, visual diagnostic decision support system (visual diagnostic DSS), employs machine learning (ML) algorithms and digital image processing techniques in a hybrid approach for automated diagnosis in medical genetics. This approach uses facial features in reference images of disorders to identify visual genotype-phenotype interrelationships. Our statistical method describes facial image data as principal component features and diagnoses syndromes using these features. RESULTS: The proposed system was trained using a real dataset of previously published face images of subjects with syndromes, which provided accurate diagnostic information. The method was tested using a leave-one-out cross-validation scheme with 15 different syndromes, each of comprised 5-9 cases, i.e., 92 cases in total. An accuracy rate of 83% was achieved using this automated diagnosis technique, which was statistically significant (p<0.01). Furthermore, the sensitivity and specificity values were 0.857 and 0.870, respectively. CONCLUSION: Our results show that the accurate classification of syndromes is feasible using ML techniques. Thus, a large number of syndromes with characteristic facial anomaly patterns could be diagnosed with similar diagnostic DSSs to that described in the present study, i.e., visual diagnostic DSS, thereby demonstrating the benefits of using hybrid image processing and ML-based computer-aided diagnostics for identifying facial phenotypes.

Optimization and enhancement of H&E stained microscopical images by applying bilinear interpolation method on lab color mode.

BACKGROUND: Hematoxylin & Eosin (H&E) is a widely employed technique in pathology and histology to distinguish nuclei and cytoplasm in tissues by staining them in different colors. This procedure helps to ease the diagnosis by enhancing contrast through digital microscopes. However, microscopic digital images obtained from this technique usually suffer from uneven lighting, i.e. poor Koehler illumination. Several off-the-shelf methods particularly established to correct this problem along with some popular general commercial tools have been examined to find out a robust solution. METHODS: First, the characteristics of uneven lighting in pathological images obtained from the H&E technique are revealed, and then how the quality of these images can be improved by employing bilinear interpolation based approach applied on the channels of Lab color mode is explored without losing any essential detail, especially for the color information of nuclei (hematoxylin stained sections). Second, an approach to enhance the nuclei details that are a fundamental part of diagnosis and crucially needed by the pathologists who work with digital images is demonstrated. RESULTS: Merits of the proposed methodology are substantiated on sample microscopic images. The results show that the proposed methodology not only remedies the deficiencies of H&E microscopical images, but also enhances delicate details. CONCLUSIONS: Non-uniform illumination problems in H&E microscopical images can be corrected without compromising crucial details that are essential for revealing the features of tissue samples.