Deep Transfer Learning Based Unified Framework for COVID19 Classification and Infection Detection from Chest X-Ray Images.

The presentation of the COVID19 has endangered several million lives worldwide causing thousands of deaths every day. Evolution of COVID19 as a pandemic calls for automated solutions for initial screening and treatment management. In addition to the thermal scanning mechanisms, findings from chest X-ray imaging examinations are reliable predictors in COVID19 detection, long-term monitoring and severity evaluation. This paper presents a novel deep transfer learning based framework for COVID19 detection and segmentation of infections from chest X-ray images. It is realized as a two-stage cascaded framework with classifier and segmentation subnetwork models. The classifier is modeled as a fine-tuned residual SqueezeNet network, and the segmentation network is implemented as a fine-tuned SegNet semantic segmentation network. The segmentation task is enhanced with a bioinspired Gaussian Mixture Model-based super pixel segmentation. This framework is trained and tested with two public datasets for binary and multiclass classifications and infection segmentation. It achieves accuracies of 99.69% and 99.48% for binary and three class classifications, and a mean accuracy of 83.437% for segmentation. Experimental results and comparative evaluations demonstrate the superiority of this unified model and signify potential extensions for biomarker definition and severity quantization.

In-vitro assessment of first-line antifungal drugs against Aspergillus spp. caused human keratomycoses.

BACKGROUND AND OBJECTIVES: Aspergillus keratitis are in the increasing trend and reported as the second most common cause of mycotic keratitis in developing countries. The present study was designed to isolate, identify Aspergillus spp. from the keratits/corneal ulcer patients attending a tertiary care eye hospital, Coimbatore, South India and to assess the minimum inhibitory concentrations (MICs) against ten clinically used first-line antifungal drugs. METHODS: A total of seventy-three Aspergillus strains isolated from corneal scrapings were included and assessed for a period of one year. All isolates were identified up to the species level by morphological observations. Antifungal drug susceptibilities were determined against a standard panel of antifungal agents. CONCLUSIONS: Five different species of aspergilli, A. flavus (n=53), A. fumigatus (n=14), A. terreus (n=9), A. tamarii (n=6) and A. niger (n=3) were identified based on morphological features. Minimum inhibitory concentration analyses indicated that, voriconazole, natamycin, itraconazole, clotrimazole, econazole followed by ketoconazole shall be the order of choices for the effective treatment for Aspergillus keratitis.