Exploring Deep Registration Latent Spaces
원문 초록
Explainability of deep neural networks is one of the most challenging and interesting problems in the field. In this study, we investigate the topic focusing on the interpretability of deep learning-based registration methods. In particular, with the appropriate model architecture and using a simple linear projection, we decompose the encoding space, generating a new basis, and we empirically show that this basis captures various decomposed anatomically aware geometrical transformations. We perform experiments using two different datasets focusing on lungs and hippocampus MRI. We show that such an approach can decompose the highly convoluted latent spaces of registration pipelines in an orthogonal space with several interesting properties. We hope that this work could shed some light on a better understanding of deep learning-based registration methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ROIsGAN: A Region Guided Generative Adversarial Framework for Murine Hippocampal Subregion Segmentation
Towards a Vision-Language Episodic Memory Framework: Large-scale Pretrained Model-Augmented Hippocampal Attractor Dynamics
Conditional diffusion model with spatial attention and latent embedding for medical image segmentation
Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation
Segment Anything for Dendrites from Electron Microscopy
NCAdapt: Dynamic adaptation with domain-specific Neural Cellular Automata for continual hippocampus segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.