Automatic Liver Lesion Segmentation in Abdominal CT Scans: Exploring Cascaded 2D and 2.5D U-Net Approaches

Automatic segmentation of liver lesions could be an important advancement for patients and radiologists to further improve early diagnosis and treatment. To stimulate the development of such an automation, researchers are currently exploring deep learning approaches. In this paper we developed and experimented with two cascaded fully convolutionalneural network (FCN) approaches that work in 2D and 2.5D. The first U-Net focused on providing a liver prediction mask which was subsequent utilized as additional input for the second U-Nets. In these U-Nets, one received the liver prediction mask as an additional input channel, and the other utilized the same mask to discard the non-liver background. The networks were trained and tested on the Liver Tumor Segmentation Challenge (LiTS) dataset, consisting of 201 contrast-enhanced abdominal CT studies. Results of the rst FCN yielded 95% Dice score for the liver segmentation on the validation set. The U-Net with 3 slice input and masked-out non-liver background was the best performing network, and obtained 0.563 Dice score on the LiTS test set. Overall, both cascaded FCN approaches were found very promising performance-wise in comparison to a single slice input without information from the liver prediction mask. Further improvements can be made by addressing the qualitatively derived egmentation challenges as well as improving the networks by exploring the implementation of ResNet connections and additional post-processing steps.