(Hyper)-graphical models in biomedical image analysis

Paragios, Nikos; Ferrante, Enzo; Glocker, Ben; Komodakis, Nikos; Parisot, Sarah; Zacharaki, Evangelia I.

doi:10.1016/j.media.2016.06.028

Cited by 16 publications

(18 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An enormous variety of tasks in computer vision and medical image analysis can be expressed as discrete labeling problems [35]. Low, mid and highlevel vision tasks can be addressed within this framework.…”

Section: Graph-based Slice-to-volume Deformable Registrationmentioning

confidence: 99%

Graph-Based Slice-to-Volume Deformable Registration

Ferrante

Paragios

2017

Int J Comput Vis

Self Cite

View full text Add to dashboard Cite

Deformable image registration is a fundamental problem in computer vision and medical image computing. In this paper we investigate the use of graphical models in the context of a particular type of image registration problem, known as slice-to-volume registration. We introduce a scalable, modular and flexible formulation that can accommodate low-rank and high order terms, that simultaneously selects the plane and estimates the in-plane deformation through a single shot optimization approach. The proposed framework is instantiated into different variants seeking either a compromise between computational efficiency (soft plane selection constraints and approximate definition of the data similarity terms through pair-wise components) or exact definition of the data terms and the constraints on the plane selection. Simulated and real-data in the context of ultrasound and magnetic resonance registration (where both framework instantiations as well as different optimization strategies are considered) demonstrate the potentials of our method.

show abstract

Section: Graph-based Slice-to-volume Deformable Registrationmentioning

confidence: 99%

Graph-Based Slice-to-Volume Deformable Registration

Ferrante

Paragios

2017

Int J Comput Vis

Self Cite

View full text Add to dashboard Cite

show abstract

“…Image segmentation is one of the most well studied problems in medical image analysis [8,6]. Segmentation seeks to group together voxels corresponding to the same organ, or to the same tissue type (healthy or pathological).…”

Section: Introductionmentioning

confidence: 99%

AtlasNet: Multi-atlas Non-linear Deep Networks for Medical Image Segmentation

Vakalopoulou

Chassagnon

Bus³

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Deep learning methods have gained increasing attention in addressing segmentation problems for medical images analysis despite challenges inherited from the medical domain, such as limited data availability, lack of consistent textural or salient patterns, and high dimensionality of the data. In this paper, we introduce a novel multi-network architecture that exploits domain knowledge to address those challenges. The proposed architecture consists of multiple deep neural networks that are trained after co-aligning multiple anatomies through multimetric deformable registration. This multi-network architecture can be trained with fewer examples and leads to better performance, robustness and generalization through consensus. Comparable to human accuracy, highly promising results on the challenging task of interstitial lung disease segmentation demonstrate the potential of our approach.

show abstract

“…For more than three decades, the research community has made major efforts towards developing more accurate and efficient registration methods. DIR has been modelled through different approaches, ranging from diffusion equations [15] to probabilistic graphical models [8]. During the last years, we have witnessed the birth of new image registration methods learned from data.…”

Section: Introductionmentioning

confidence: 99%

On the Adaptability of Unsupervised CNN-Based Deformable Image Registration to Unseen Image Domains

Ferrante

Oktay

Glocker

et al. 2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Deformable image registration is a fundamental problem in medical image analysis. During the last years, several methods based on deep convolutional neural networks (CNN) proved to be highly accurate to perform this task. These models achieved state-of-the-art accuracy while drastically reducing the required computational time, but mainly focusing on images of specific organs and modalities. To date, no work has reported on how these models adapt across different domains. In this work, we ask the question: can we use CNN-based registration models to spatially align images coming from a domain different than the one/s used at training time? We explore the adaptability of CNN-based image registration to different organs/modalities. We employ a fully convolutional architecture trained following an unsupervised approach. We consider a simple transfer learning strategy to study the generalisation of such model to unseen target domains, and devise a one-shot learning scheme taking advantage of the unsupervised nature of the proposed method. Evaluation on two publicly available datasets of X-Ray lung images and cardiac cine magnetic resonance sequences is provided. Our experiments suggest that models learned in different domains can be transferred at the expense of a decrease in performance, and that oneshot learning in the context of unsupervised CNN-based registration is a valid alternative to achieve consistent registration performance when only a pair of images from the target domain is available.

show abstract

(Hyper)-graphical models in biomedical image analysis

Cited by 16 publications

References 46 publications

Graph-Based Slice-to-Volume Deformable Registration

Graph-Based Slice-to-Volume Deformable Registration

AtlasNet: Multi-atlas Non-linear Deep Networks for Medical Image Segmentation

On the Adaptability of Unsupervised CNN-Based Deformable Image Registration to Unseen Image Domains

Contact Info

Product

Resources

About