GAN augmentation for multiclass image classification using hemorrhage detection as a case-study.

In recent years, the development and exploration of deeper and more complex deep learning models has been on the rise. However, the availability of large heterogeneous datasets to support efficient training of deep learning models is lacking. While linear image transformations for augmentation have been used traditionally, the recent development of generative adversarial networks (GANs) could theoretically allow us to generate an infinite amount of data from the real distribution to support deep learning model training.

Clinico-microbiological study and antibiotic resistance profile of mecA and ESBL gene prevalence in patients with diabetic foot infections.

Diabetic foot infections (DFIs) constitute a major complication of diabetes mellitus. DFIs contribute to the development of gangrene and non-traumatic lower extremity amputations with a lifetime risk of up to 25%. The aim of the present study was to identify the presence of neuropathy and determine the ulcer grade, microbial profile and phenotypic and genotypic prevalence of the methicillin-resistance gene mecA and extended spectrum β-lactamase (ESBL)-encoding genes in bacterial isolates of DFI in patients registered at the Pakistan Institute of Medical Sciences (Islamabad, Pakistan).