Generalizable and accurate stereo depth estimation is vital for 3D reconstruction, especially in surgery. Supervised learning methods obtain best performance however, limited ground truth data for surgical scenes limits generalizability. Self-supervised methods don't need ground truth, but suffer from scale ambiguity and incorrect disparity prediction due to inconsistency of photometric loss. This work proposes a two-phase training procedure that is generalizable and retains the high performance of supervised methods. It entails: (1) performing self-supervised representation learning of left and right views via masked image modelling (MIM) to learn generalizable semantic stereo features (2) utilizing the MIM pre-trained model to learn robust depth representation via supervised learning for disparity estimation on synthetic data only. To improve stereo representations learnt via MIM, perceptual loss terms are introduced, which improve the model's stereo representations learnt by explicitly encouraging the learning of higher scene-level features. Qualitative and quantitative performance evaluation on surgical and natural scenes shows that the approach achieves sub-millimetre accuracy and lowest errors respectively, setting a new state-of-the-art. Despite not training on surgical nor natural scene data for disparityestimation.

Real-time detection of surgical tools in laparoscopic data plays a vital role in understanding surgical procedures, evaluating the performance of trainees, facilitating learning, and ultimately supporting the autonomy of robotic systems. Existing detection methods for surgical data need to improve processing speed and high prediction accuracy. Most methods rely on anchors or region proposals, limiting their adaptability to variations in tool appearance and leading to sub-optimal detection results. Moreover, using non-anchor-based detectors to alleviate this problem has been partially explored without remarkable results. An anchor-free architecture based on a transformer that allows real-time tool detection is introduced. The proposal is to utilize multi-scale features within the feature extraction layer and at the transformer-based detection architecture through positional encoding that can refine and capture context-aware and structural information of different-sized tools. Furthermore, a supervised contrastive loss is introduced to optimize representations of object embeddings, resulting in improved feed-forward network performances for classifying localized bounding boxes. The strategy demonstrates superiority to state-of-the-art (SOTA) methods. Compared to the most accurate existing SOTA (DSSS) method, the approach has an improvement of nearly 4% on mAP and a reduction in the inference time by 113%. It also showed a 7% higher mAP than the baselinemodel.

Recent research studies reported that the employment of wearable augmented reality (AR) systems such as head-mounted displays for the in situ visualisation of ultrasound (US) images can improve the outcomes of US-guided biopsies through reduced procedure completion times and improved accuracy. Here, the authors continue in the direction of recent developments and present the first AR system for guiding an in-depth tumour enucleation procedure under US guidance. The system features an innovative visualisation modality with cutting trajectories that 'sink' into the tissue according to the depth reached by the electric scalpel, tracked in real-time, and a virtual-to-virtual alignment between the scalpel's tip and the trajectory. The system has high accuracy in estimating the scalpel's tip position (mean depth error of 0.4 mm and mean radial error of 1.34 mm). Furthermore, we demonstrated with a preliminary user study that our system allowed us to successfully guide an in-depth tumour enucleation procedure (i.e. preserving the safety margin around the lesion).

Post-traumatic stress disorder (PTSD) is an anxiety condition caused by exposure to severe trauma. It is characterised by nightmares, flashbacks, hyper-vigilance and avoidance behaviour. These all lead to impaired functioning reducing quality of life. PTSD affects 2-5% of the population globally. Most sufferers cannot access effective treatment, leading to impaired psychological functioning reducing quality of life. Eye movement desensitisation and reprocessing (EMDR) is a non-invasive brain stimulation treatment that has shown significant clinical effectiveness in PTSD. Another treatment modality, that is, trauma-focused cognitive behavioural therapy is also an effective intervention. However, both evidence-based treatments are significantly resource intensive as they need trained therapists to deliver them. A concept of a neuro-digital tool for development is proposed to put to clinical practice of delivering EMDR to improve availability, efficiency and effectiveness of treatment. The evidence in using new technologies to measure sleep, geolocation and conversational analysis of social media to report objective outcome measures is explored. If achieved, this can be fed back to users with data anonymously collated to evaluate and improve the tool. Coproduction would be at the heart of product development so that the tool is acceptable and accessible to people with the condition.

The aim of this work is to assess the performance of various inkjet printing techniques. These techniques are aimed at optimizing the volume of conductive ink used in the fabrication of inkjet printed Radio Frequency Identification tags. It is also possible that they can be used in fabricating other electronic and electromagnetic devices and structures. Three ink optimization approaches were examined viz. gridded (meshed) designs, conductive area trimming and selective ink deposition. The volume of conductive ink utilized in tag fabrication and the measured on-body (forearm) read range of the tag were used to develop a figure of merit which determined the best printing approach. Although the longest read range was obtained from the tag with 48% conductive area trimming (Trim 1), the best figure of merit, that is, the tag with the best balance between measured read range and utilized conductive ink, was obtained from the tag that had its surface area trimmed by 65% (Trim 2). It is however suggested that optimum use of conductive ink would be achieved with a combination of 65% surface area trimming and selective ink deposition technique.

Today, the elderly population is increasing, and there are many drawbacks for them, especially defects in their knee joints which lead to improper gait. To solve this problem, their knee joint can be replaced with knee arthroplasty. In this letter, level of improvement in the human gait before and after total knee arthroplasty (TKA) surgery is investigated using the dynamic time warping (DTW) algorithm. For this purpose, several volunteers who have problems with their knees are incorporated in a test before and after TKA surgery. Then, the data of gait analysis is collected and the data is compared with a reference using the DTW algorithm. The outcome results illustrate an improvement of 89%-97% by the proposed algorithm after TKA surgery. Therefore, patients can see improvement with high accuracy and very fast that result in more use this technique in TKR surgery.

Preterm birth is a global epidemic affecting millions of mothers across different ethnicities. The cause of the condition remains unknown but has recognised health‐based implications, in addition to financial and economic ones. Machine Learning methods have enabled researchers to combine datasets using uterine contraction signals with various forms of prediction machines to improve awareness of the likelihood of premature births. This work investigates the feasibility of enhancing these prediction methods using physiological signals including uterine contractions, and foetal and maternal heart rate signals, for a population of south American women in active labour. As part of this work, the use of the Linear Series Decomposition Learner (LSDL) was seen to lead to an improvement in the prediction accuracies of all models, which included supervised and unsupervised learning models. The results from the supervised learning models showed high prediction metrics upon the physiological signals being pre‐processed by the LSDL for all variations of the physiological signals. The unsupervised learning models showed good metrics for the partitioning of Preterm/Term labour patients from their uterine contraction signals but produced a comparatively lower set of results for the various kinds of heart rate signals investigated.

Diabetes is a metabolic disease that affects millions of people each year. It is associated with an increased likelihood of vital organ failures and decreased quality of life. Early detection and regular monitoring are crucial for managing diabetes. Remote patient monitoring can facilitate effective intervention and treatment paradigms using current technology. This work proposes an end‐to‐end remote monitoring framework for automated diabetes risk prediction and management, using personal health devices, smart wearables and smartphones. A support vector machine was developed for diabetes risk prediction using the Pima Indian Diabetes Database, after feature scaling, imputation, selection and augmentation. This work achieved the performance metrics of accuracy, sensitivity and specificity scores at 83.20%, 87.20% and 79% respectively through the tenfold stratified cross validation method, which is competitive with existing methods. Patients can use multiple healthcare devices, smartphones and smartwatches to measure vital parameters, curb the progression of diabetes and close the communication loop with medical professionals. The proposed framework enables medical professionals to make informed decisions based on the latest diabetes risk predictions and lifestyle insights while attaining unobtrusiveness, reduced cost, and vendor interoperability.

This paper examines the impact of daily activities on the performance of a body-mounted radio frequency identification (RFID) tag inkjet printed onto tattoo transfer paper. This paper aims to assess how robust RFID tags of this nature are when mounted on the skin while the user undergoes various daily activities. The factors considered for these robustness tests are the effect of sweat and wear and tear on these tags during everyday use and also how it stands up to being exposed to water and soap during showering. Performance assessment was carried out using parameters such as point-to-point surface DC resistance as well as read range. Results show marginal effects on the tag performance and the tag continued to function during a normal day's activities, which lasted for 8 h, and rigorous activities like exercising but stopped functioning when there was severe damage to tag.