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.

Evaluation of Synthetc Derived Wheat Lines for Heat Stress Using Physiological and Agronomic Traits

Wheat production is decreasing continuously due to heat stress in the developing countries especially Pakistan. Every 1 ?C rise in temperature is resulting in 10% reduction in the yield of wheat worldwide. Therefore in order to overcome shortage of food in the near future better analysis of the wheat crops as well as improved research mechanisms are needed to enhance heat resistance in the existing wheat varieties. Present study was conducted to assess heat tolerance variation among thirty synthetic-derived wheat lines in order to identify new sources of diversity that could accelerate the development of improved wheat genotypes better suited to meet the challenges posed by changing climate in Pakistan. Plants were grown in plastic pots and heat stress was applied after post anthesis stage to determine the effect of heat stress on various morphological, agronomic and physiological traits. Heat stress significantly affected leaf area (LA), plant height (PH), number of fertile tillers (FT), Spike length (SL), Spikelet/spike (Sp/S), No. of seeds/Spike (NOS/S), 1000 seed weight (TSW), chlorophyll a and bcontent of leaves, membrane stability index (MSI) and also affected levels of proline. Statistical analysis of all the traits showed significant reduction in the particular trait as compared to their control data sets. Higher percentage reduction under heat stress reduced yields in (SDL1, 31.00), (SDL6, 32.00), (SDL29, 30.00) while minimum reduction under heat stress and maximum yield was observed for (SDL4, 45.00), (SDL5, 48), (SDL9, 44), (SDL12, 45.00), (SDL15, 49.00), (SDL19, 51.00), (SDL22, 45.00), (SDL23, 45.00) and (SDL27, 46.00) respectively. Reduction in physiological traits was recorded as 24.46% reduction in chlorophyll a (Chl-a), 28.19% chlorophyll b (Chl-b), 29.17% proline (Pro) content of leaf, 16.36% membrane stability index (MSI). In the same way in morphological trait a relative decrease in plant height (PH) 12%, days to physiological maturity (DM) 7.59%, fertile tillers (F/T) 21.43%, leaf area (LA) 25.58%, , spike length (SL) 25%, number of seeds per spike (NOS/S) 15.38%,and 1000 seed weight (TSW) 19.23%was observed. As a result it was observed that relative decrease in the yield contents in (SDL4), (SDL5), (SDL9), (SDL12), (SDL15), (SDL19), (SDL22), (SDL23) and (SDL27) was lesser as compared to all other genotypes so they can be considered as heat tolerant genotypes with potential to enrich genetic background of local wheat cultivars and can be used in breeding programs for the improvement of wheat production and can overcome food shortage in future.