Boundary Finding with Prior Shape and Smoothness Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Model-Based Initialisation for Segmentation
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
The Use of Active Shape Models for Locating Structures in Medical Images
IPMI '93 Proceedings of the 13th International Conference on Information Processing in Medical Imaging
Predictive K-PLSR myocardial contractility modeling with phase contrast MR velocity mapping
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
Dynamic shape instantiation for intra-operative guidance
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I
Reinforcement learning for context aware segmentation
MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part III
Snakes, shapes, and gradient vector flow
IEEE Transactions on Image Processing
IEEE Transactions on Image Processing
Hi-index | 0.00 |
Subject-specific segmentation for medical images plays a critical role in translating medical image computing techniques to routine clinical practice. Many current segmentation methods, however, are still focused on building general models, and thus lack the generalizability for unseen, particularly pathological data. In this paper, a reinforcement learning algorithm is proposed to integrate specific human expert behavior for segmenting subject-specific data. The algorithm uses a generic two-layer reinforcement learning framework and incorporates shape instantiation to constrain the target shape geometrically. The learning occurs in the background when the user segments the image in realtime, thus eliminating the need to prepare subject-specific training data. Detailed validation of the algorithm on hypertrophic cardiomyopathy (HCM) datasets demonstrates improved segmentation accuracy, reduced user-input, and thus the potential clinical value of the proposed algorithm.