Isabelle Bloch

On some associations between mathematical morphology and artificial intelligence

Abstract

This paper aims at providing an overview of the use of mathematical morphology, in its algebraic setting, in several fields of artificial intelligence (AI). Three domains of AI will be covered. In the first domain, mathematical morphology operators will be expressed in some logics (propositional, modal, description logics) to answer typical questions in knowledge representation and reasoning, such as revision, fusion, explanatory relations, satisfying usual postulates. In the second domain, spatial reasoning will benefit from spatial relations modeled using fuzzy sets and morphological operators, with applications in model-based image understanding. In the third domain, interactions between mathematical morphology and deep learning will be detailed. Morphological neural networks were introduced as an alternative to classical architectures, yielding a new geometry in decision surfaces. Deep networks were also trained to learn morphological operators and pipelines, and morphological algorithms were used as companion tools to machine learning, for pre/post processing or even regularization purposes. These ideas have known a large resurgence in the last few years and new ones are emerging.

Continue reading

Segmentation des hyperintensités de la matière blanche en quelques secondes à l’aide d’un réseau de neurones convolutif et de transfert d’apprentissage

Abstract

Dans cet article, nous proposons une méthode automatique et rapide pour segmenter les hyper-intensités de la matière blanche (WMH) dans des images IRM cérébrales 3D, en utilisant un réseau de neurones entièrement convolutif (FCN) et du transfert d’apprentissage. Ce FCN est le réseau neuronal du Visual Geometry Group (VGG) pré-entraîné sur la base ImageNet pour la classification des images naturelles, et affiné avec l’ensemble des données d’entraînement du concours MICCAI WMH. Nous considérons trois images pour chaque coupe du volume à segmenter, provenant des acquisitions en T1, en FLAIR, et le résultat d’un opérateur morphologique appliqué sur le FLAIR, le top-hat, qui met en évidence les petites structures de forte intensité. Ces trois images 2D sont assemblées pour former une image 2D-3 canaux interprétée comme une image en couleurs, ensuite passée au FCN pour obtenir la segmentation 2D de la coupe correspondante. Nous traitons ainsi toutes les coupes pour former la segmentation de sortie 3D. Avec une telle technique, la segmentation de WMH sur un volume cérébral 3D prend environ 10 secondes, pré-traitement compris. Notre technique a été classée 6e sur 20 participants au concours MICCAI WMH.

Continue reading

The challenge of cerebral magnetic resonance imaging in neonates: A new method using mathematical morphology for the segmentation of structures including diffuse excessive high signal intensities

Abstract

Preterm birth is a multifactorial condition associated with increased morbidity and mortality. Diffuse excessive high signal intensity (DEHSI) has been recently described on T2-weighted MR sequences in this population and thought to be associated with neuropathologies. To date, no robust and reproducible method to assess the presence of white matter hyperintensities has been developed, perhaps explaining the current controversy over their prognostic value. The aim of this paper is to propose a new semi-automated framework to detect DEHSI on neonatal brain MR images having a particular pattern due to the physiological lack of complete myelination of the white matter. A novel method for semi- automatic segmentation of neonatal brain structures and DEHSI, based on mathematical morphology and on max-tree representations of the images is thus described. It is a mandatory first step to identify and clinically assess homogeneous cohorts of neonates for DEHSI and/or volume of any other segmented structures. Implemented in a user-friendly interface, the method makes it straightforward to select relevant markers of structures to be segmented, and if needed, apply eventually manual corrections. This method responds to the increasing need for providing medical experts with semi-automatic tools for image analysis, and overcomes the limitations of visual analysis alone, prone to subjectivity and variability. Experimental results demonstrate that the method is accurate, with excellent reproducibility and with very few manual corrections needed. Although the method was intended initially for images acquired at 1.5T, which corresponds to usual clinical practice, preliminary results on images acquired at 3T suggest that the proposed approach can be generalized.

Continue reading

White matter hyperintensities segmentation in a few seconds using fully convolutional network and transfer learning

Abstract

Continue reading

Segmentation d’IRM de cerveaux de nouveau-nés en quelques secondes à l’aide d’un réseau de neurones convolutif <i>pseudo-3D</i> et de transfert d’apprentissage

Abstract

L’imagerie par résonance magnétique (IRM) du cerveau est utilisée sur les nouveau-nés pour évaluer l’évolution du cerveau et diagnostiquer des maladies neurologiques. Ces examens nécessitent souvent une analyse quantitative des différents tissus du cerveau, de sorte qu’avoir une segmentation précise est essentiel. Dans cet article, nous proposons une méthode automatique rapide de segmentation en différents tissus des images IRM 3D de cerveaux de nouveau-nés ; elle utilise un réseau de neurones totalement convolutif (FCN) et du transfert d’apprentissage. Par rapport aux approches similaires qui reposent soit sur des patchs 2D ou 3D, soit sur des FCN totalement 3D, notre méthode est beaucoup plus rapide : elle ne prend que quelques secondes, et une seule modalité (T2) est nécessaire. Afin de prendre les informations 3D en compte, trois coupes 2D successives sont empilées pour former une image 2D en couleurs, dont l’ensemble sur tout le volume sert d’entrée à un FCN, pré-entraîné sur ImageNet pour la classification d’images naturelles. Nos expériences sur un ensemble de données de référence montrent que notre méthode obtient des résultats du niveau de ceux de l’état de l’art.

Continue reading

From neonatal to adult brain MR image segmentation in a few seconds using 3D-like fully convolutional network and transfer learning

Abstract

Brain magnetic resonance imaging (MRI) is widely used to assess brain developments in neonates and to diagnose a wide range of neurological diseases in adults. Such studies are usually based on quantitative analysis of different brain tissues, so it is essential to be able to classify them accurately. In this paper, we propose a fast automatic method that segments 3D brain MR images into different tissues using fully convolutional network (FCN) and transfer learning. As compared to existing deep learning-based approaches that rely either on 2D patches or on fully 3D FCN, our method is way much faster: it only takes a few seconds, and only a single modality (T1 or T2) is required. In order to take the 3D information into account, all 3 successive 2D slices are stacked to form a set of 2D color images, which serve as input for the FCN pre-trained on ImageNet for natural image classification. To the best of our knowledge, this is the first method that applies transfer learning to segment both neonatal and adult brain 3D MR images. Our experiments on two public datasets show that our method achieves state-of-the-art results.

Continue reading

A challenging issue: Detection of white matter hyperintensities in neonatal brain MRI

Abstract

The progress of magnetic resonance imaging (MRI) allows for a precise exploration of the brain of premature infants at term equivalent age. The so-called DEHSI (diffuse excessive high signal intensity) of the white matter of premature brains remains a challenging issue in terms of definition, and thus of interpretation. We propose a semi-automatic detection and quantification method of white matter hyperintensities in MRI relying on morphological operators and max-tree representations, which constitutes a powerful tool to help radiologists to improve their interpretation. Results show better reproducibility and robustness than interactive segmentation.

Continue reading

Local reasoning in fuzzy attribute graphs for optimizing sequential segmentation

Abstract

Spatial relations play a crucial role in model-based image recognition and interpretation due to their stability compared to many other image appearance characteristics. Graphs are well adapted to represent such information. Sequential methods for knowledge-based recognition of structures require to define in which order the structures have to be recognized. We propose to address this problem of order definition by developing algorithms that automatically deduce sequential segmentation paths from fuzzy spatial attribute graphs. As an illustration, these algorithms are applied on brain image understanding.

Continue reading

Spatial reasoning with relative incomplete information on relative positioning

Abstract

This paper describes a probabilistic method of inferring the position of a point with respect to a reference point knowing their relative spatial position to a third point. We address this problem in the case of incomplete information where only the angular spatial relationships are known. The use of probabilistic representations allows us to model prior knowledge. We derive exact formulae expressing the conditional probability of the position given the two known angles, in typical cases: uniform or Gaussian random prior distributions within rectangular or circular regions. This result is illustrated with respect to two different simulations: The first is devoted to the localization of a mobile phone using only angular relationships, the second, to geopositioning within a city. This last example uses angular relationships and some additional knowledge about the position.

Continue reading

Fusion of spatial relationships for guiding recognition, example of brain structure recognition in 3D MRI

Abstract

Spatial relations play an important role in recognition of structures embedded in a complex environment and for reasoning under imprecision. Several types of relationships can be modeled in a unified way using fuzzy mathematical morphology. Their combination benefits from the powerful framework of fuzzy set theory for fusion tasks and decision making. This paper presents several methods of fusion of information about spatial relationships and illustrates them on the example of model-based recognition of brain structures in 3D magnetic resonance imaging.

Continue reading