Neural Network-Based Automatic Liver Tumor Segmentation With Random Forest-Based Candidate Filtering

TL;DR

This paper introduces an automatic liver tumor segmentation method combining CNNs and random forest filtering, achieving competitive accuracy on the ISBI 2017 LiTS challenge dataset.

Contribution

It presents a novel pipeline integrating CNN-based liver segmentation with CNN and random forest-based tumor candidate filtering.

Findings

Achieved a mean Dice coefficient of 0.65 on test data

Ranked second in the ISBI 2017 LiTS challenge

Demonstrated effective combination of CNNs and random forests for segmentation

Abstract

We present a fully automatic method employing convolutional neural networks based on the 2D U-net architecture and random forest classifier to solve the automatic liver lesion segmentation problem of the ISBI 2017 Liver Tumor Segmentation Challenge (LiTS). In order to constrain the ROI in which the tumors could be located, a liver segmentation is performed first. For the organ segmentation, an ensemble of convolutional networks is trained to segment a liver using a set of 179 liver CT datasets from liver surgery planning. Inside of the liver ROI a neural network, trained using 127 challenge training datasets, identifies tumor candidates, which are subsequently filtered with a random forest classifier yielding the final tumor segmentation. The evaluation on the 70 challenge test cases resulted in a mean Dice coefficient of 0.65, ranking our method in the second place.