醫學圖像分割的主流方法之一是基于水平集（Level Set）的分割方法。目前針對主流的分割方法，我們主體研究思路如下圖

在模型凸化以及形狀先驗兩個方面，未開展相關工作。

參考文獻（部分演示代碼-參數隨圖像需要調整）:

[7] Xiaomeng Xin, Lingfeng Wang, Chunhong Pan, Shigang Liu:Adaptive regularization level set ?evolution for medical image segmentation and bias field correction. International Conference on Image Processing 2015: 1006-1010

[6] Lingfeng Wang, Chunhong Pan, Explicit Order Model for Region-based Level Set Segmentation, International Conference on Acoustics,Speech, and Signal Processing, 2015

[5] Lingfeng Wang?(Corresponding Author), Chunhong Pan, Robust Level Set Image Segmentation via a Local Correntropy-based K-means Clustering, PatternRecognition, 2014

PR_Code.rar

[4] Lingfeng Wang?(Corresponding Author), Chunhong Pan, Image Guided Regularization Level Set Evolution for MR Image Segmentation and Bias Field Correction,Magnetic Resonance Imaging, 2013

[3] Lingfeng Wang?(Corresponding Author), Huaiyu Wu,Chunhong Pan, Region-based Image Segmentation with Local Signed Difference Energy, Pattern RecognitionLetters, 2013

PRLetters_Code.zip

[2] Lingfeng Wang?(Corresponding Author), Zeyun Yu, Chunhong Pan, A Unified Level Set Framework Utilizing Parameter Priors for Medical Image Segmentation, Science China (Series F), 1-14, 2012 (This is the extension version of ACCV 2010) ?

ACCV_CHINA_Science_Segmentation.zip

[1] Ying Wang, Lingfeng Wang, Shiming Xiang, Chunhong Pan, Level Set Evolution with Locally ?Linear Classification for Image Segmentation,International Conference on Image Processing, 2011 (The entension version is accepted by Pattern Recognition)

from:?http://www.escience.cn/people/LingfengWang/medical_image_segmentation.html

總結

以上是生活随笔為你收集整理的医学图像分割研究思路的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。