A Joint Deep Learning Approach for Automated Liver and Tumor\n Segmentation

2019/02/21 by Nadja Gruber, Stephan Antholzer, Gruber, Nadja +7 · 1 citation
Computer Science · Medicine · #AI in cancer detection #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Mathematics #Hepatocellular Carcinoma Treatment and Prognosis #Numerical Analysis (math.NA) #Radiomics and Machine Learning in Medical Imaging

paper · pdf · doi:10.48550/arxiv.1902.07971

openalex publication_date 2019/02/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Hepatocellular carcinoma (HCC) is the most common type of primary liver\ncancer in adults, and the most common cause of death of people suffering from\ncirrhosis. The segmentation of liver lesions in CT images allows assessment of\ntumor load, treatment planning, prognosis and monitoring of treatment response.\nManual segmentation is a very time-consuming task and in many cases, prone to\ninaccuracies and automatic tools for tumor detection and segmentation are\ndesirable. In this paper, we compare two network architectures, one that is\ncomposed of one neural network and manages the segmentation task in one step\nand one that consists of two consecutive fully convolutional neural networks.\nThe first network segments the liver whereas the second network segments the\nactual tumor inside the liver. Our networks are trained on a subset of the LiTS\n(Liver Tumor Segmentation) Challenge and evaluated on data.\n

Cited by

• Iterative pseudo-labeling based adaptive copy-paste supervision for semi-supervised tumor segmentation

Related

• Hierarchical Convolutional-Deconvolutional Neural Networks for Automatic Liver and Tumor Segmentation
• Neural Network-Based Automatic Liver Tumor Segmentation With Random Forest-Based Candidate Filtering
• A New Three-stage Curriculum Learning Approach to Deep Network Based Liver Tumor Segmentation
• 2D-Densely Connected Convolution Neural Networks for automatic Liver and Tumor Segmentation
• Joint Liver and Hepatic Lesion Segmentation in MRI using a Hybrid CNN with Transformer Layers