Neural Style Transfer Improves 3D Cardiovascular MR Image Segmentation on Inconsistent Data

September 20, 2019 ยท Entered Twilight ยท ๐Ÿ› International Conference on Medical Image Computing and Computer-Assisted Intervention

๐ŸŒ… TWILIGHT: Old Age
Predates the code-sharing era โ€” a pioneer of its time

"Last commit was 5.0 years ago (โ‰ฅ5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: Label_Analysis.py, README.md, RW_analysis_branch_gaussian.py, Refine_Analysis.py, StyleSegor_Analysis.py, Style_Analysis.py, generate_one_pair.py, generate_one_to_all_test.py, generate_styled_image.py, generate_styled_label.py, helper.py, img, miccai_Analysis.py, models.py, nii2img_SemiSegor.py, nii2img_StyleSegor.py, test.py, test.sh, toposeg_train.sh, train.py, utils.py

Authors Chunwei Ma, Zhanghexuan Ji, Mingchen Gao arXiv ID 1909.09716 Category cs.CV: Computer Vision Citations 52 Venue International Conference on Medical Image Computing and Computer-Assisted Intervention Repository https://github.com/horsepurve/StyleSegor โญ 8 Last Checked 1 month ago
Abstract
Three-dimensional medical image segmentation is one of the most important problems in medical image analysis and plays a key role in downstream diagnosis and treatment. Recent years, deep neural networks have made groundbreaking success in medical image segmentation problem. However, due to the high variance in instrumental parameters, experimental protocols, and subject appearances, the generalization of deep learning models is often hindered by the inconsistency in medical images generated by different machines and hospitals. In this work, we present StyleSegor, an efficient and easy-to-use strategy to alleviate this inconsistency issue. Specifically, neural style transfer algorithm is applied to unlabeled data in order to minimize the differences in image properties including brightness, contrast, texture, etc. between the labeled and unlabeled data. We also apply probabilistic adjustment on the network output and integrate multiple predictions through ensemble learning. On a publicly available whole heart segmentation benchmarking dataset from MICCAI HVSMR 2016 challenge, we have demonstrated an elevated dice accuracy surpassing current state-of-the-art method and notably, an improvement of the total score by 29.91\%. StyleSegor is thus corroborated to be an accurate tool for 3D whole heart segmentation especially on highly inconsistent data, and is available at https://github.com/horsepurve/StyleSegor.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computer Vision