Machine Vision based Computer-Aided Detection of Pulmonary Tuberculosis using Chest X-Ray Images

Tuberculosis (TB) is a lethal disease and developing countries are struggling to overcome this health hazard especially in rural areas and faced globally. Therefore, serious measures are required to reduce this global health hazard. Millary and pulmonary are the most common types of tuberculosis occurring globally. X-ray is the preliminary method to detect tuberculosis; however, the diagnosis is quite often subject to human error. In contrast, the chances of curing Tuberculosis depend on its timely and accurate diagnosis. Therefore, an intelligent machine learning algorithm is developed in this study to assist the clinician in an accurate TB identification in x-ray images. The proposed method pre-processes the X-ray image, enhances its quality and extracts the features of each class which are further passed on to a Deep Convolutional Neural Network-based design for the X-ray image classification, followed by the identification of the tuberculosis type i.e. Millary, Cavitary, Healthy. The classification accuracy for the developed method resulted in 88% and 89% for millary and cavitary TB diseases in x ray images.

Expression Profiling of Huanglongbing Disease in Citrus Though Molecular Techniques

Huanglongbing (HLB), also called greening, is a fatal disease of citrus. Candidatus Liberibacter, a Gram negative and non culturable bacterium, is the pathogen of huanglongbing. It becomes difficult to detect this bacterium because it is unevenly distributed in its citrus hosts.The bacteria are transmitted naturally to citrus by an insect vector called citrus psyllid. Hussain and Nath documented the occurrence of HLB and its related vector Diaphorina citri Kuwayama in Pakistan in 1927.In this study, 97 accessions of citrus germplasm were raised in greenhouse. of 97 accessions, 51 were survived. The seed of citrus germplasm was obtained from National Clonal Germplasm Repository for Citrus and Dates, Riverside, California, USA and University of Agriculture Faisalabad (UAF), Pakistan. For HLB diagnosis in the leaf samples of sweet orange (Citrus sinensis) cultivar Succari from field, conventional polymerase chain reaction technique was employed. Asian citrus psyllid (ACP) was captured from HLB positive sweet orange field trees and released on healthy plants of sweet orange and kinnow for rearing and infestation in the controlled conditions of growth room. Those plants were also tested for their HLB positivity by using 16s rDNA primers OI1/OI2c and Candidatus Liberibacter asiaticus specific primer A2/J5. After confirmation of HLB, sweet orange plants infested by ACP in growth room, were usedfor the inoculation of fifty one genotypes of citrus and citrus relatives. Candidatus Liberibacter asiaticus was detected in 96.07% of the inoculated citrus germplasm by Taqman based real time PCR using primers set HLBasfpr.SYBR green based real time qPCR was performed to differentiate expression of genes in HLB infected and healthy leaf samples of forty five genotypes of citrus and its relatives. Seven genes, includingsulfate transferase (CsSULF), glucose-1-phosphate adenyl transferase (CsSB1), granule bound starch synthase (CsSB2), alpha amylase (CsSD1), alpha amylase 3 (CsSD2), beta amylase9 (CsSD3) and cytochrome P450 mono oxygenase 83B1(CsSUR2) were tested for expression profiling. Gene expression data analysis for relative quantity represented the down regulation ofcarbohydrate metabolism related genes (CsSB1and CsSD3) in Clausena harmandiana while transporter gene CsSULF expressed at equal level in healthy and diseased Glycosmis pentaphylla. Remaining genes did not express in both of the varieties. These two genotypes may be placed in tolerant category against HLB as the causal bacterium was not detected in them. In Tahitian and Schuab, no gene was amplified except CsSULF gene that was down regulated indicating strong root system for plant survival.