A deep learning system for detection of early Barrett's neoplasia: a model development and validation study.

BACKGROUND: Computer-aided detection (CADe) systems could assist endoscopists in detecting early neoplasia in Barrett's oesophagus, which could be difficult to detect in endoscopic images. The aim of this study was to develop, test, and benchmark a CADe system for early neoplasia in Barrett's oesophagus. METHODS: The CADe system was first pretrained with ImageNet followed by domain-specific pretraining with GastroNet. We trained the CADe system on a dataset of 14 046 images (2506 patients) of confirmed Barrett's oesophagus neoplasia and non-dysplastic Barrett's oesophagus from 15 centres. Neoplasia was delineated by 14 Barrett's oesophagus experts for all datasets. We tested the performance of the CADe system on two independent test sets. The all-comers test set comprised 327 (73 patients) non-dysplastic Barrett's oesophagus images, 82 (46 patients) neoplastic images, 180 (66 of the same patients) non-dysplastic Barrett's oesophagus videos, and 71 (45 of the same patients) neoplastic videos. The benchmarking test set comprised 100 (50 patients) neoplastic images, 300 (125 patients) non-dysplastic images, 47 (47 of the same patients) neoplastic videos, and 141 (82 of the same patients) non-dysplastic videos, and was enriched with subtle neoplasia cases. The benchmarking test set was evaluated by 112 endoscopists from six countries (first without CADe and, after 6 weeks, with CADe) and by 28 external international Barrett's oesophagus experts. The primary outcome was the sensitivity of Barrett's neoplasia detection by general endoscopists without CADe assistance versus with CADe assistance on the benchmarking test set. We compared sensitivity using a mixed-effects logistic regression model with conditional odds ratios (ORs; likelihood profile 95% CIs). FINDINGS: Sensitivity for neoplasia detection among endoscopists increased from 74% to 88% with CADe assistance (OR 2·04; 95% CI 1·73-2·42; p<0·0001 for images and from 67% to 79% [2·35; 1·90-2·94; p<0·0001] for video) without compromising specificity (from 89% to 90% [1·07; 0·96-1·19; p=0·20] for images and from 96% to 94% [0·94; 0·79-1·11; ] for video; p=0·46). In the all-comers test set, CADe detected neoplastic lesions in 95% (88-98) of images and 97% (90-99) of videos. In the benchmarking test set, the CADe system was superior to endoscopists in detecting neoplasia (90% vs 74% [OR 3·75; 95% CI 1·93-8·05; p=0·0002] for images and 91% vs 67% [11·68; 3·85-47·53; p<0·0001] for video) and non-inferior to Barrett's oesophagus experts (90% vs 87% [OR 1·74; 95% CI 0·83-3·65] for images and 91% vs 86% [2·94; 0·99-11·40] for video). INTERPRETATION: CADe outperformed endoscopists in detecting Barrett's oesophagus neoplasia and, when used as an assistive tool, it improved their detection rate. CADe detected virtually all neoplasia in a test set of consecutive cases. FUNDING: Olympus.

Infant Facial Expression Analysis: Towards a Real-Time Video Monitoring System Using R-CNN and HMM.

The manual monitoring of young infants suffering from diseases like reflux is significant, since infants can hardly articulate their feelings. In this work, we propose a video-based infant monitoring system for the analysis of infant expressions and states, approaching real-time performance. The expressions of interest consist of discomfort, unhappy, joy and neutral, whereas states include sleep, pacifier and open mouth. Benefiting from the expression analysis, the discomfort moments can also be used and correlated with a symptom-related disease, such as a reflux measurement for the diagnosis of gastroesophageal reflux. The system consists of three components: infant expressions and states detection, object tracking and detection compensation. The proposed system is based on combining expression detection using Fast R-CNN with a compensated detection using analyzing information from the previous frame and utilizing a Hidden Markov Model. The experimental results show a mean average precision of 81.9% and 84.8% for 4 infant expressions and 3 states evaluated with both clinical and daily datasets. Meanwhile, the average precision for discomfort detection achieves up to 90%.

Improved Barrett's neoplasia detection using computer-assisted multiframe analysis of volumetric laser endomicroscopy.

Volumetric laser endomicroscopy (VLE) is a balloon-based technique, which provides a circumferential near-microscopic scan of the esophageal wall layers, and has potential to improve Barrett's neoplasia detection. Interpretation of VLE imagery in Barrett's esophagus (BE) however is time-consuming and complex, due to a large amount of visual information and numerous subtle gray-shaded VLE images. Computer-aided detection (CAD), analyzing multiple neighboring VLE frames, might improve BE neoplasia detection compared to automated single-frame analyses. This study is to evaluate feasibility of automatic data extraction followed by CAD using a multiframe approach for detection of BE neoplasia. Prospectively collected ex-vivo VLE images from 29 BE-patients with and without early neoplasia were retrospectively analyzed. Sixty histopathology-correlated regions of interest (30 nondysplastic vs. 30 neoplastic) were assessed using different CAD systems. Multiple neighboring VLE frames, corresponding to 1.25 millimeter proximal and distal to each region of interest, were evaluated. In total, 3060 VLE frames were analyzed via the CAD multiframe analysis. Multiframe analysis resulted in a significantly higher median AUC (median level = 0.91) compared to single-frame (median level = 0.83) with a median difference of 0.08 (95% CI, 0.06-0.10), P < 0.001. A maximum AUC of 0.94 was reached when including 22 frames on each side using a multiframe approach. In total, 3060 VLE frames were automatically extracted and analyzed by CAD in 3.9 seconds. Multiframe VLE image analysis shows improved BE neoplasia detection compared to single-frame analysis. CAD with multiframe analysis allows for fast and accurate VLE interpretation, thereby showing feasibility of automatic full scan assessment in a real-time setting during endoscopy.

Automatic Quality Assessment of Transperineal Ultrasound Images of the Male Pelvic Region, Using Deep Learning.

Ultrasound guidance is not in widespread use in prostate cancer radiotherapy workflows. This can be partially attributed to the need for image interpretation by a trained operator during ultrasound image acquisition. In this work, a one-class regressor, based on DenseNet and Gaussian processes, was implemented to automatically assess the quality of transperineal ultrasound images of the male pelvic region. The implemented deep learning approach was tested on 300 transperineal ultrasound images and it achieved a scoring accuracy of 94%, a specificity of 95% and a sensitivity of 92% with respect to the majority vote of 3 experts, which was comparable with the results of these experts. This is the first step toward a fully automatic workflow, which could potentially remove the need for ultrasound image interpretation and make real-time volumetric organ tracking in the radiotherapy environment using ultrasound more appealing.

Exploring the Parkinson patients' perspective on home-based video recording for movement analysis: a qualitative study.

BACKGROUND: Parkinson's disease is a complex neurological disorder characterized by a variety of motor- as well as non-motor symptoms. Video-based technology (using continuous home monitoring) may bridge the gap between the fragmented in-clinic observations and the need for a comprehensive understanding of the progression and fluctuation of disease symptoms. However, continuous monitoring can be intrusive, raising questions about feasibility as well as potential privacy violation. METHODS: We used a grounded theory approach in which we performed semi-structured interviews to explore the opinion of Parkinson's patients on home-based video recording used for vision-based movement analysis. RESULTS: Saturation was reached after sixteen interviews. Three first-level themes were identified that specify the conditions required to perform continuous video monitoring: Camera recording (e.g. being able to turn off the camera), privacy protection (e.g. patient's behaviour, patient's consent, camera location) and perceived motivation (e.g. contributing to science or clinical practice). CONCLUSION: Our findings show that Parkinson patients' perception of continuous, home-based video recording is positive, when a number of requirements are taken into account. This knowledge will enable us to start using this technology in future research and clinical practice in order to better understand the disease and to objectify outcomes in the patients' own homes.

Evaluation of a multidisciplinary epilepsy transition clinic for adolescents.

INTRODUCTION: The main goal of the transition clinic is to explore and optimize medical issues during transition from adolescence to adulthood, and to ease the transition into adult care. However, only limited data on the process and outcomes of transitional care in clinical practice are available. OBJECTIVE: To describe the process and outcomes of an Epilepsy Transition Clinic in a tertiary referral center in The Netherlands. METHODS: Data were collected from patients with epilepsy (aged 15-25 years), who visited the transition clinic between March 2012 and September 2014. RESULTS: The Epilepsy Transition Clinic is staffed with a multidisciplinary team including a neurologist/epileptologist, clinical neuropsychologist, a social worker and an educationalist/occupational counselor, all with knowledge of paediatric and adult medical and developmental issues. In total, 117 patients with epilepsy were included in the analysis. After consultation, 89 patients received a diagnostic work-up (76.1%), change in AED prescription (n = 64, 54.7%), or consultation/tailored advice (n = 73, 62.4%). In fourteen patients (12.0%) the epilepsy diagnosis was changed. Nineteen patients (16.2%) had complete epilepsy remission for over one year. Forty-three patients (36.8%) were referred to adult care. CONCLUSION: This study describes a multidisciplinary epilepsy transition clinic staffed by a neurologist/epileptologist, neuropsychologist, a social worker and an educationalist/occupational counselor. Diagnostic work-up and evaluation of psychosocial and educational/vocational status during adolescence are strongly recommended.

Developing from child to adult: Risk factors for poor psychosocial outcome in adolescents and young adults with epilepsy.

INTRODUCTION: Childhood-onset epilepsy during the years of transition to adulthood may affect normal social, physical, and mental development, frequently leading to psychosocial and health-related problems in the long term. OBJECTIVE: This study aimed to describe the main characteristics of patients in transition and to identify risk factors for poor psychosocial outcome in adolescents and young adults with epilepsy. METHODS: Patients with epilepsy, 15-25years of age, who visited the Kempenhaeghe Epilepsy Transition Clinic from March 2012 to December 2014 were included (n=138). Predefined risk scores for medical, educational/occupational status, and independence/separation/identity were obtained, along with individual risk profile scores for poor psychosocial outcome. Multivariate linear regression analysis and discriminant analysis were used to identify variables associated with an increased risk of poor long-term psychosocial outcome. RESULTS: Demographic, epilepsy-related, and psychosocial variables associated with a high risk of poor long-term outcome were lower intelligence, higher seizure frequency, ongoing seizures, and an unsupportive and unstable family environment. Using the aforementioned factors in combination, we were able to correctly classify the majority (55.1%) of the patients regarding their risk of poor psychosocial outcome. CONCLUSION: Our analysis may allow early identification of patients at high risk of prevention, preferably at pretransition age. The combination of a chronic refractory epilepsy and an unstable family environment constitutes a higher risk of transition problems and poor outcome in adulthood. As a consequence, early interventions should be put into place to protect youth at risk of poor transition outcome.

Transition to adult medical care for adolescents with epilepsy.

INTRODUCTION: During transition to adult medical care, the adolescent with epilepsy is especially prone to emotional, mental, physical, and social developmental difficulties, leading to stigma and poor psychosocial and socioeconomic outcome in the long term. OBJECTIVES: The aim of this review is twofold: to describe the psychosocial and medical transition from adolescence to adulthood and to evaluate the most effective model for transitional services in adolescents with epilepsy. METHODS: We searched PubMed for quantitative and qualitative data about transition from adolescence to adulthood in patients with epilepsy. RESULTS: A total of 49 articles were retrieved. We reviewed personal, psychosocial, and medical issues during transition and their long-term individual and societal consequences. Identifying risk factors for poor transition can lead to appropriate interventions for patients and their family. Although the concept of multidisciplinary transition care for adolescents with epilepsy is widely recognized, only a few transition clinics have been established. There is lack of evidence for their quality and cost-effectiveness. CONCLUSION: In addition to medical problems, more attention should be paid to the risk of psychosocial problems during transition from pediatric to adult care. The implementation of transition care for adolescents with epilepsy is considered beneficial; however, its effectiveness should be further investigated.