Fully Automated Detection and Classification of White Blood Cells.

The measure of White Blood Cells (WBC) in the blood is an important indicator of pathological conditions. Computer vision based methods for differential counting of WBC are increasing due to their advantages over traditional methods. However, most of these methods are proposed for single WBC images which are pre-processed, and do not generalize for raw microscopic images with multiple WBC. Moreover, they do not have the capability to detect the absence of WBC in the images. This paper proposes an image processing algorithm based on K-Means clustering to detect the presence of WBC in raw microscopic images and to localize them, and a VGG-16 classifier to classify those cells with a classification accuracy of 95.89%.

Clinico-epidemiology and management of Russell's viper (Daboia russelii) envenoming in dogs in Sri Lanka.

INTRODUCTION: Russell's viper envenoming in dogs is a significant problem in Sri Lanka. The current study focused on investigating clinical profile, laboratory findings of three selected tests and to develop a treatment strategy with Indian polyvalent Anti-Venom Serum (AVS). It was also intended to report adverse effects and complications caused by both Russell's viper venom (RVV) and AVS in Russell's Viper (RV) envenomed dogs. OBJECTIVE: To evaluate and report the clinical manifestations, to find out the minimum effective vials of AVS and to record AVS induced adverse reactions of RV envenoming in dogs. MATERIALS AND METHODS: A prospective study was conducted on Russell's viper bitten dogs (n = 65) admitted to the Veterinary Teaching Hospital (VTH) in Sri Lanka. Indian polyvalent AVS was used to treat all the envenomed dogs. The number of vials of AVS that was administered to a patient was decided upon by a second degree polynomial model with a number of vials of AVS in the X axis verses Prothrombine Time (PT), Activated Partial Thromboplastine Time (aPTT) and Clotting Time (CT) in the Y axis respectively. RESULTS: Varying degrees of pain were exhibited by all the victim dogs. Mild swelling and necrosis at the site of bite was seen in 54% (n = 35) and 37% (n = 24) of dogs respectively. Prolonged values of, PT, aPTT and CT were seen from all the RV envenomed dogs. The mean leukocyte count in these dogs was 39.79 × 103/µL (normal range; 4-20 × 103/µL) (IQR:29.05 × 103/µL-45.92 × 103/µL). Statistical analysis showed that the initial vials of 7 AVS would be the minimum required vials. Therefore, a range of 6-15 AVS vials in total were administered to these dogs and in 7.6% (n = 5) of dogs, the results of PT, aPTT and CT became normal with 6 AVS vials at 32-97 minutes. Acute Renal Failure (ARF) was detected from 29% (n = 19) of dogs as a complication. CONCLUSIONS: Systemic clinical signs of haemorrhagic lesions, cardio respiratory toxicities were common in Russell's viper envenomed dogs. Initially 6 vials of AVS must be administered. AVS induced reactions were reported commonly. Russell's viper envenoming was found to be lethal in dogs.