Efficient machine learning frameworks For detection of diabetic foot in Infrared hermograms

Abstract

Diabetes Mellitus (DM) is a chronic disease that occurs when the pancreas is no longer able to make insulin, or when the body cannot make good use of the insulin it produces. People with diabetes have an increased risk of developing a number of serious life-threatening health problems resulting in higher medical care costs, reduced quality of life and increased mortality. One of the most important long-term sequelae of diabetes mellitus is the development of diabetic foot ulcers (DFU) and in high-risk patients could result in amputation. Early detection and appropriate treatment can prevent traumatic outcomes such as lower extremity amputation. newlineThe circulatory deviations play an important role in the pathogenesis of the diabetic foot. They are responsible for subtle skin temperature changes, which can be detected using infrared thermography. Thermography is a rapid, non-invasive and non-contact technique for detecting potential changes in temperature distribution in the foot region that may have complications in the future. The patients with diabetic neuropathy show a higher temperature in foot regions compared to patients without neuropathy. Infrared thermography plays a vital role in the health care sector, specifically for the detection of diabetic foot. In this thesis, different machine learning frameworks are explored for the detection of diabetic foot in infrared thermograms as an alternative to physical examination. newlineThe plantar foot regions are segmented using region growing algorithm in input infrared thermograms. The texture and temperature features are extracted from the ulcer prone regions newline