Especially when trained on medical databases with sparseavailable annotation, these methods are prone to generate segmentation artifacts such as fragmentedstructures, topological inconsistencies and islands of pixel. Since the advent of U-Net, fully convolutional deep neural networks and its many variants havecompletely changed the modern landscape of deep learning based medical image segmentation.However, the over dependence of these methods on pixel level classification and regression hasbeen identified early on as a problem. For quick access, important details such as the underlying method, datasets and performance are tabulated.ĪA SURVEY ON SHAPE - CONSTRAINT DEEP LEARNING FORMEDICAL IMAGE SEGMENTATIONĭepartment of Computer ScienceTU DarmstadtDarmstadt, GermanyĬomputer Engineering DepartmentIstanbul Technical UniversityIstanbul, TurkeySchool of Biomedical Engineering Imaging SciencesKing's CollegeLondon, U.K.ĭepartment of Computer ScienceTU DarmstadtDarmstadt, GermanyJanuA BSTRACT We review the most relevant papers published until the submission date. In this review paper, a broad overview of recent literature on bringing anatomical constraints for medical image segmentation is given, the shortcomings and opportunities of the proposed methods are thoroughly discussed and potential future work is elaborated. ![]() To ensure the segmentation result is anatomically consistent, approaches based on Markov/ Conditional Random Fields, Statistical Shape Models are becoming increasingly popular over the past 5 years. However, one common thread across all these downstream tasks is the demand of anatomical consistency. The range of possible downstream evaluations is rather big, for example surgical planning, visualization, shape analysis, prognosis, treatment planning etc. These artefacts are especially problematic in medical imaging since segmentation is almost always a pre-processing step for some downstream evaluation. Especially when trained on medical databases with sparse available annotation, these methods are prone to generate segmentation artifacts such as fragmented structures, topological inconsistencies and islands of pixel. However, the over dependence of these methods on pixel level classification and regression has been identified early on as a problem. Since the advent of U-Net, fully convolutional deep neural networks and its many variants have completely changed the modern landscape of deep learning based medical image segmentation.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |