Deep learning in healthcare organizations can support better patient care while reducing costs and improving efficiencies. One of the types, known as convolutional neural networks (CNNs) is particularly well-suited to analyzing images, such as MRI or x-rays. CNNs are designed with an assumption that they will be processing images, allowing the networks to operate more efficiently and handle larger images. One of the studies has shown that CNN trained to analyze dermatology images identified melanoma with ten percent more specificity than human clinicians. In addition to being highly accurate, deep learning tools are fast. Typical CNN model takes just 1.2 seconds to process the image, analyze its contents, and alert providers of a problematic clinical finding. The goal of this project is to use these effective deep learning techniques to classify chest x-ray images into normal, pneumonia, and tuberculosis.
Classifying these types of diseases are important because the risk of pneumonia and tuberculosis are immense for many, especially in developing nations where billions face energy poverty and rely on polluting forms of energy. The WHO estimates that over 4 million premature deaths occur annually from household air pollution-related diseases including pneumonia and tuberculosis. Over 150 million people get infected with pneumonia and tuberculosis on an annual basis especially children under 5 years old. In such regions, the problem can be further aggravated due to the dearth of medical resources and personnel. For these populations, accurate and fast diagnosis means everything. It can guarantee timely access to treatment and save much needed time and money for those already experiencing poverty.
The objective is to build an algorithm to automatically identify whether a patient is suffering from pneumonia/tuberculosis or not by looking at chest X-ray images. The algorithm must be extremely accurate because lives of people is at stake. Several different deep learning models are to be used to select models which give an optimal result.