AbstractReal-world large-scale medical image analysis (MIA) datasets have three challenges: 1) they contain noisy-labelled samples that affect training convergence and generalisation, 2) usually an imbalanced distribution of per class, 3) normally comprise a multi-label problem, where can multiple diagnoses. Current approaches are commonly trained to solve subset those problems, but we unaware ...

Abstract A number of large technology companies have created code-free cloud-based platforms that allow researchers and clinicians without coding experience to create deep learning algorithms. In this study, we comprehensively analyse the performance featureset six platforms, using four representative cross-sectional en-face medical imaging datasets image classification models. The mean (s.d.) ...

The amount of medical images for training deep classification models is typically very scarce, making these prone to overfit the data. Studies showed that knowledge distillation (KD), especially mean-teacher framework which more robust perturbations, can help mitigate over-fitting effect. However, directly transferring KD from computer vision image yields inferior performance as suffer higher i...

Gait refers to a person’s particular movements and stance while moving around. Although each gait is unique made up of variety tiny limb orientations body positions, they all have common characteristics that help define normalcy. Swiftly identifying such are difficult spot by the naked eye, can in monitoring elderly who require constant care support. Analyzing silhouettes easiest way assess mak...

Large, annotated datasets are not widely available in medical image analysis due to the prohibitive time, costs, and challenges associated with labelling large datasets. Unlabelled easier obtain, many contexts, it would be feasible for an expert provide labels a small subset of images. This work presents information-theoretic active learning framework that guides optimal selection images from u...