SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth

Abstract

A key limitation of deep convolutional neural networks (DCNN) based image segmentation methods is the lack of generalizability. Manually traced training images are typically required when segmenting organs in a new imaging modality or from distinct disease cohort. The manual efforts can be alleviated if the manually traced images in one imaging modality (e.g., MRI) are able to train a segmentation network for another imaging modality (e.g., CT). In this paper, we propose an end-to-end synthetic segmentation network (SynSeg-Net) to train a segmentation network for a target imaging modality without having manual labels. SynSeg-Net is trained by using (1) unpaired intensity images from source and target modalities, and (2) manual labels only from source modality. SynSeg-Net is enabled by the recent advances of cycle generative adversarial networks (CycleGAN) and DCNN. We evaluate the performance of the SynSeg-Net on two experiments: (1) MRI to CT splenomegaly synthetic segmentation for abdominal images, and (2) CT to MRI total intracranial volume synthetic segmentation (TICV) for brain images. The proposed end-to-end approach achieved superior performance to two stage methods. Moreover, the SynSeg-Net achieved comparable performance to the traditional segmentation network using target modality labels in certain scenarios. The source code of SynSeg-Net is publicly available (https://github.com/MASILab/SynSeg-Net).

IEEE Transactions on Medical Imaging (TMI)

References in corpus (2)

• A Survey on Deep Learning in Medical Image Analysis
• Distribution Matching Losses Can Hallucinate Features in Medical Image Translation

Cited by in corpus (15)

• SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining
• Causality matters in medical imaging
• Efficient Medical Image Segmentation Based on Knowledge Distillation
• Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation
• LE-UDA: Label-efficient unsupervised domain adaptation for medical image segmentation
• Disentangle, align and fuse for multimodal and semi-supervised image segmentation
• PSIGAN: Joint probabilistic segmentation and image distribution matching for unpaired cross-modality adaptation based MRI segmentation
• Can segmentation models be trained with fully synthetically generated data?
• A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images using a GAN
• Conditional Generation of Medical Images via Disentangled Adversarial Inference
• MouseGAN++: Unsupervised Disentanglement and Contrastive Representation for Multiple MRI Modalities Synthesis and Structural Segmentation of Mouse Brain
• Unpaired cross-modality educed distillation (CMEDL) for medical image segmentation
• A Unified Multi-Phase CT Synthesis and Classification Framework for Kidney Cancer Diagnosis with Incomplete Data
• An Attentive-based Generative Model for Medical Image Synthesis
• Deep Learning-based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Bi-parametric MRI Datasets