Integrating machine learning with region-based active contour models in medical image segmentation

详细信息    查看全文

• 作者：Agus Pratondo^a ; ^b ; ^{pratondo@gmail.com} ; Chee-Kong Chui^c ; Sim-Heng Ong^b
• 关键词：Machine learning ; Active contour ; Medical images ; Segmentation
• 刊名：Journal of Visual Communication and Image Representation
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：43
• 期：Complete
• 页码：1-9
• 全文大小：2572 K
• 卷排序：43

文摘

Machine learning is integrated with region-based active contour models. A map of classification probability scores from machine learning algorithm is used. Two family of regularization functions are proposed and used to regularize the map. The region-based active contour model is applied on the regularized map. The accuracy, speed, and sensitivity to parameter tuning are improved.