An Efficient Liver Tumor Detection using Machine Learning

Liver Cancer is among the most commonly diagnosed diseases in today’s modern era. Liver tumor segmentation is a fundamental task to perform early diagnosis and recommend a treatment. Manual segmentation is the traditional approach to achieve the required results but it has always been a time-consuming process. There are some anomalies like ambiguous gray level color ranges similar to other neighboring organs, irregular tumor shapes, and various uneven tumor sizes which are overlooked. Due to these reasons, some semi-automated and even fully automated techniques have been put forward. However, the advancement of machine learning has been very accommodating for addressing this issue. In this paper, we propose an unsupervised machine learning technique combined with a supervised mechanism that accurately performs liver tumor segmentation. We perform clustering on our collected dataset and extract LBP features as well as HOG features from these clusters. Furthermore, we perform classification which is based on these extracted features using KNN. Furthermore, we have compared our results with two classifiers namely SVM and Ensemble to achieve a better understanding. Our proposed technique outperformed existing techniques and showed encouraging results when compared to other methods.