Automated classification of static ultrasound images of ovarian tumours based on decision level fusion

Ovarian cancer is the most deadly cancer of the female reproductive system. Early detection of ovarian carcinoma continues to be a challenging task. Manual classifications are generally based on subjective assessment by experts, which may result in different diagnoses. In this paper, we propose a new method for automatic ovarian tumour classification based on decision level fusion. The proposed method first extracts two different types of features (Histogram and Local Binary Pattern) from ultrasound images of the ovary. Support Vector Machine (SVM) is then used to classify ovarian tumour based on each type of features separately. The method then employs a novel decision fusion that categorizes SVM-based decision scores into a measure of confidence to assist the final diagnostic decision making. Experimental results on 187 ultrasound images of ovarian tumour show classification accuracy of 90%, 81% and 69% based on classification decisions of high, medium and low confidence respectively, whereas 18% of the cases were unclassified as inconclusive not sure cases. The paper argues that such confidence based prediction outcomes are more meaningful than other classical alternatives and closer to the reality in diagnosis of ovarian cancers.