No abstract

Background There is a lack of evidence in the literature regarding the learning outcomes of immersive technologies as educational tools for teaching university-level health care students. Objective The aim of this review is to assess the learning outcomes of immersive technologies compared with traditional learning modalities with regard to knowledge and the participants’ learning experience in medical, midwifery, and nursing preclinical university education. Methods A systematic review was conducted according to the Cochrane Collaboration guidelines. Randomized controlled trials comparing traditional learning methods with virtual, augmented, or mixed reality for the education of medicine, nursing, or midwifery students were evaluated. The identified studies were screened by 2 authors independently. Disagreements were discussed with a third reviewer. The quality of evidence was assessed using the Medical Education Research Study Quality Instrument (MERSQI). The review protocol was registered with PROSPERO (International Prospective Register of Systematic Reviews) in April 2020. Results Of 15,627 studies, 29 (0.19%) randomized controlled trials (N=2722 students) were included and evaluated using the MERSQI tool. Knowledge gain was found to be equal when immersive technologies were compared with traditional learning modalities; however, the learning experience increased with immersive technologies. The mean MERSQI score was 12.64 (SD 1.6), the median was 12.50, and the mode was 13.50. Immersive technology was predominantly used to teach clinical skills (15/29, 52%), and virtual reality (22/29, 76%) was the most commonly used form of immersive technology. Knowledge was the primary outcome in 97% (28/29) of studies. Approximately 66% (19/29) of studies used validated instruments and scales to assess secondary learning outcomes, including satisfaction, self-efficacy, engagement, and perceptions of the learning experience. Of the 29 studies, 19 (66%) included medical students (1706/2722, 62.67%), 8 (28%) included nursing students (727/2722, 26.71%), and 2 (7%) included both medical and nursing students (289/2722, 10.62%). There were no studies involving midwifery students. The studies were based on the following disciplines: anatomy, basic clinical skills and history-taking skills, neurology, respiratory medicine, acute medicine, dermatology, communication skills, internal medicine, and emergency medicine. Conclusions Virtual, augmented, and mixed reality play an important role in the education of preclinical medical and nursing university students. When compared with traditional educational modalities, the learning gain is equal with immersive technologies. Learning outcomes such as student satisfaction, self-efficacy, and engagement all increase with the use of immersive technology, suggesting that it is an optimal tool for education.

No abstract

Breast density estimation with visual evaluation is still challenging due to low contrast and significant fluctuations in the mammograms’ fatty tissue background. The primary key to breast density classification is to detect the dense tissues in the mammographic images correctly. Many methods have been proposed for breast density estimation; nevertheless, most of them are not fully automated. Besides, they have been badly affected by low signal-to-noise ratio and variability of density in appearance and texture. This study intends to develop a fully automated and digitalized breast tissue segmentation and classification using advanced deep learning techniques. The conditional Generative Adversarial Networks (cGAN) network is applied to segment the dense tissues in mammograms. To have a complete system for breast density classification, we propose a Convolutional Neural Network (CNN) to classify mammograms based on the standardization of Breast Imaging-Reporting and Data System (BI-RADS). The classification network is fed by the segmented masks of dense tissues generated by the cGAN network. For screening mammography, 410 images of 115 patients from the INbreast dataset were used. The proposed framework can segment the dense regions with an accuracy, Dice coefficient, Jaccard index of 98%, 88%, and 78%, respectively. Furthermore, we obtained precision, sensitivity, and specificity of 97.85%, 97.85%, and 99.28%, respectively, for breast density classification. This study’s findings are promising and show that the proposed deep learning-based techniques can produce a clinically useful computer-aided tool for breast density analysis by digital mammography.

Yield losses to waterlogging are expected to become an increasingly costly and frequent issue in some regions of the world. Despite the extensive work that has been carried out examining the molecular and physiological responses to waterlogging, phenotyping for waterlogging tolerance has proven difficult. This difficulty is largely due to the high variability of waterlogging conditions such as duration, temperature, soil type, and growth stage of the crop. In this review, we aim to highlight efforts utilising phenotyping to assess and improve waterlogging tolerance in temperate crop species. We start by outlining the experimental methods that have been utilised to impose waterlogging stress, ranging from highly controlled conditions of hydroponic systems to large-scale screenings in the field. We also describe the phenotyping traits used to assess tolerance ranging from survival rates and visual scoring to precise photosynthetic measurements. Finally, we present an overview of the challenges faced in attempting to improve waterlogging tolerance, the trade-offs associated with phenotyping in controlled conditions, limitations of classic phenotyping methods and future trends using plant-imaging methods. If effectively utilised to increase crop resilience to changing climates, crop phenotyping has a major role to play in global food security.