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.

Relationship Between the School Resource Inputs and Academic Achievement of Students at Secondary Level in Pakistan

The study was conducted to investigate the relationship between school resource inputs and academic achievement at secondary level in Pakistan. School resource inputs have a vital role in the education process. The provision and availability of school resource inputs in schools is not important and beneficial until they are actually used efficiently. The focus of the provision and availability, and the use of school resource inputs, is to maximize the academic achievement of students within the limited funds available. School resource inputs include prior achievement, prior academic environment, leadership style, per pupil expenditures, pupil teacher ratio, class size, school facilities, instructional material and teacher quality. . The population of the study comprised all the secondary and higher secondary schools, secondary teachers and secondary students in Punjab. Overall, a total of 288 schools, 5760 students and 2880 teachers were the sample of the study. The study identified the availability and the use of school resource inputs through the ―School profile Proforma‖ and the ―Questionnaire‖. The longitudinal data of academic achievement of the same students from class VI to X were collected through ―Result Sheet‖. The study identified the extent of the use of school resource inputs i.e. leadership style, practical laboratories and instructional material. However, it was assumed that the basic school facilities and teacher quality are used where provided. The data were analyzed at school level and then collectively for the final analysis through Statistical package for social sciences (SPSS). Pearson Correlation Coefficient was used to find out the simple relationship (association) and Stepwise Regression analysis was used to find out the differential impact of school resource inputs on academic achievement. The results of the study show that school resource inputs are, overall, the predictors of academic achievement in their collective function. However, they have the mixed effects on academic achievement in their individual function. The findings of the study show that prior achievement of students is the most important predictor of academic achievement and prior academic environment has some positive impact. Democratic leadership style is the best leadership style; however, it is not properly used. Per student expenditure, most of the basic school facilities and most of the items of instructional material have the mixed effects on academic achievement. Student teacher ratio has positive but larger class size has negative impact. Additionally, the five indicators of teacher quality i.e. academic and professional qualifications, in-service refresher courses/ trainings, teacher experience and teacher salary are not effective. The study also identified that school resource inputs are least provided, misallocated, and inefficiently and deficiently used. These are the main causes of the negative, insignificant and minor impact of some school resource inputs on academic achievement. It is also concluded that fairly allocation and efficient use of school resource inputs leads to the significant impact of school resource inputs on academic achievement. One of the policy implications of this study is that education standards for the provision, allocation and use of school resource inputs may be developed and implemented in Pakistan. This study also guides the policy makers and the educationists by formulating the lines of action how and to what extent the school resource inputs may be provided and used in schools.