{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/adversarial-synthesis-learning-enables","title":"Adversarial Synthesis Learning Enables Segmentation Without Target Modality Ground Truth","arxiv_id":"1712.07695","date":"2017-12-20","proceeding":null,"authors":["Yuankai Huo","Zhoubing Xu","Shunxing Bao","Albert Assad","Richard G. Abramson","Bennett A. Landman"],"abstract":"A lack of generalizability is one key limitation of deep learning based\nsegmentation. Typically, one manually labels new training images when\nsegmenting organs in different imaging modalities or segmenting abnormal organs\nfrom distinct disease cohorts. The manual efforts can be alleviated if one is\nable to reuse manual labels from one modality (e.g., MRI) to train a\nsegmentation network for a new modality (e.g., CT). Previously, two stage\nmethods have been proposed to use cycle generative adversarial networks\n(CycleGAN) to synthesize training images for a target modality. Then, these\nefforts trained a segmentation network independently using synthetic images.\nHowever, these two independent stages did not use the complementary information\nbetween synthesis and segmentation. Herein, we proposed a novel end-to-end\nsynthesis and segmentation network (EssNet) to achieve the unpaired MRI to CT\nimage synthesis and CT splenomegaly segmentation simultaneously without using\nmanual labels on CT. The end-to-end EssNet achieved significantly higher median\nDice similarity coefficient (0.9188) than the two stages strategy (0.8801), and\neven higher than canonical multi-atlas segmentation (0.9125) and ResNet method\n(0.9107), which used the CT manual labels.","url_abs":"http://arxiv.org/abs/1712.07695v1","url_pdf":"http://arxiv.org/pdf/1712.07695v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"adversarial-synthesis-learning-enables","repo_url":"https://github.com/MASILab/SynSeg-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"splenomegaly-segmentation-on-multi-modal-mri","task_name":"Splenomegaly Segmentation On Multi-Modal Mri"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}