Coronavirus (COVID-19) detection from chest radiology images using convolutional neural networks.

Coronavirus disease (Covid-19) has been spreading all over the world and its diagnosis is attracting more research every moment. It is need of the hour to develop automated methods, which could detect this disease at its early stage, in a non-invasive way and within lesser time. Currently, medical specialists are analyzing Computed Tomography (CT), X-Ray, and Ultrasound (US) images or conducting Polymerase Chain Reaction (PCR) for its confirmation on manual basis. In Pakistan, CT scanners are available in most hospitals at district level, while X-Ray machines are available in all tehsil (large urban towns) level hospitals. Being widely used imaging modalities to analyze chest related diseases, produce large volume of medical data each moment clinical environments. Since automatic, time efficient and reliable methods for Covid-19 detection are required as alternate methods, therefore an automatic method of Covid-19 detection using Convolutional Neural Networks (CNN) has been proposed. Three publically available and a locally developed dataset, obtained from Department of Radiology (Diagnostics), Bahawal Victoria Hospital, Bahawalpur (BVHB), Pakistan have been used. The proposed method achieved on average accuracy (96.68 %), specificity (95.65 %), and sensitivity (96.24 %). Proposed model is trained on a large dataset and is being used at the Radiology Department, (BVHB), Pakistan.

Paclitaxel loaded magnetic nanocomposites with folate modified chitosan/carboxymethyl surface; a vehicle for imaging and targeted drug delivery.

In this study, Paclitaxel (PTX) containing, bovine serum albumin (BSA) nanoparticles were fabricated via a simple approach. Folic acid (FA) was conjugated to chitosan (CS)/carboxymethyl cellulose (CMC) through an esterification reaction to produce BSA-CS-FA or BSA-CMC-FA conjugates. NiFe2O4 noncore (NFs) and PTX were loaded through a heat treatment and by a diffusion process. NFs-BSA-CS and NFs-BSA-CMC-FA with size of about 80nm, showed superior transversal R2 relaxation rate of 349 (mM)-1s-1 along with folate receptor-targeted and magnetically directed functions. NFs-BSA-CS-FA or NFs-BSA-CS-FA were found stable and biocompatible. Application of an external magnetic field effectively enhanced the PTX release from PTX-NFs-BSA-CS-FA or PTX-NFs-BSA-CS-FA and hence tumor inhibition rate. This study validate that NFs-BSA-CS-FA or NFs-BSA-CMC-FA and PTX-NFs-BSA-CS-FA or PTX-NFs-BSA-CS-FA are suitable systems for tumor diagnosis and therapy.

Diagnostic value of apparent diffusion coefficient for the accurate assessment and differentiation of intracranial meningiomas.

BACKGROUND: Diffusion-weighted imaging (DWI) along with the calculation of apparent diffusion coefficient (ADC), is a novel, non-invasive, and reliable technique of choice for accurate assessment and for the treatment planning of different types of brain tumors. It is more advantageous in the distinction and differentiation of benign from malignant meningiomas on the basis of ADC values. PURPOSE: To investigate the utility of DW magnetic resonance imaging (MRI), and to compare the apparent diffusion coefficient (ADC) obtained at two b-values for an authentic and preoperative characterization of meningiomas. MATERIAL AND METHODS: Twenty-six patients with clinically diagnosed or histologically verified meningioma (18 benign and 8 malignant) underwent imaging including DWI at 1.5 T. DW images were obtained at b = 1000 s/mm(2) and b = 2000 s/mm(2), ADC maps were generated at both the b-values. Signal intensities (SIs) and ADCs for solid tumorous tissues, contralateral normal tissues, and peritumoral edema were calculated and normalized ADC (NADC) ratio were determined for tumorous tissues. SI scores, ADC maps, and ADC values were analyzed visually and quantitatively, and were compared at both the b-values. RESULTS: DW images at b = 2000 s/mm(2) were more conspicuity (either hyperintense or hypointense) with improved contrast. The mean ADC of malignant meningiomas (0.64 ± 0.05 and 0.42 ± 0.03) was significantly lower (P < 0.05) as compared with benign meningiomas (1.04 ± 0.12 and 0.80 ± 0.07) at both the b-values. Mean NADC ratio in the malignant type was also significantly lower (P < 0.05) than the benign type at both the b-values. Mean ADC values for peritumoral edema do not differ between benign and malignant meningiomas. CONCLUSION: 1.5-T DWI using high b-values improved our ability to differentiate benign from malignant meningiomas. DWI may play an important role in the preoperative radiological evaluation and the recognition of these types for proper surgical treatment.