Liver tumor segmentation CT data based on Alexnet-like convolution neural nets

Abstract

Abstract. Anatomical structure segmentation on computed tomography (CT) is the key stage in medical visualization and computer diagnosis. Tumors are one of types of internal structures, for which the problem of automatic segmentation today has no solution fully satisfying by quality. The reason is high variance of tumor's density and inability of using a priori anatomical information about shape. In this paper we propose automatic method of liver tumors segmentation based on convolution neural nets (CNN). Studying and validation have been performed on set of CT with liver and tumors segmentation ground truth. Average error (VOE) by cross-validation is 17.3%. Also there were considered algorithms of pre-and post-processing which increase accuracy and performance of segmentation procedure. Particularly the acceleration of the segmentation procedure with negligible decrease of quality has been reached 6 times.

Automated Deep System for Joint Liver and Tumor Segmentation Using Majority Voting (Dept.E)

“…One stage deep learning approach attempt to segment the liver and its lesions using one deep CNN stage. For example, Korabelnikov et.al [10] used a segmentation framework which is consisting of a pre-processing step, a pixel-wise classification using pre-trained CNN (Alexnet) and smoothing and thresholding as post-processing of the obtained binary segmented image. Badrinarayanan et al [11] used the VGG-Segnet model directly for joint liver and tumor segmentation.…”