Shaping for PET image analysis

Abstract Component-trees constitute an efficient data structure for hierarchical image modeling. In particular they are relevant for processing and analyzing images where the structures of interest correspond either to local maxima or local minima of intensity. This is indeed the case of functional data in medical imaging. This motivates the use of component-tree-based approaches for analyzing Positron Emission Tomography (PET) images in the context of oncology. In this article, we present a simple, yet efficient, methodological framework for PET image analysis based on component-trees. More precisely, we show that the second-order paradigm of shaping, that broadly consists of computing the component-tree of a component-tree, provides a relevant way of generalizing the threshold-based strategies classically used by medical practitioners for handling PET images. In addition, it also allows to embed relevant priors regarding the sought cancer lesions.

[1]  Barbara Romaniuk,et al.  Multicriteria 3D PET image segmentation , 2015, 2015 International Conference on Image Processing Theory, Tools and Applications (IPTA).

[2]  Bruce D Cheson,et al.  Recommendations for initial evaluation, staging, and response assessment of Hodgkin and non-Hodgkin lymphoma: the Lugano classification. , 2014, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[3]  Philippe Salembier,et al.  Antiextensive connected operators for image and sequence processing , 1998, IEEE Trans. Image Process..

[4]  Isabelle Bloch,et al.  Brain Lesion Detection in 3D PET Images Using Max-Trees and a New Spatial Context Criterion , 2017, ISMM.

[5]  Hervé Le Men,et al.  Scale-Sets Image Analysis , 2005, International Journal of Computer Vision.

[6]  Thierry Géraud,et al.  A Comparative Review of Component Tree Computation Algorithms , 2014, IEEE Transactions on Image Processing.

[7]  Nicolas Passat,et al.  Attribute-Filtering and Knowledge Extraction for Vessel Segmentation , 2010, ISVC.

[8]  Alexandre Cochet,et al.  Beth Israel Plugin for FIJI : logiciel gratuit et open source pour la recherche scientifique , 2016 .

[9]  Hugues Talbot,et al.  Filtering and segmentation of 3D angiographic data: Advances based on mathematical morphology , 2013, Medical Image Anal..

[10]  Michael H. F. Wilkinson,et al.  Shape Preserving Filament Enhancement Filtering , 2001, MICCAI.

[11]  Yongchao Xu,et al.  Connected Filtering on Tree-Based Shape-Spaces , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Barbara Romaniuk,et al.  Matching Filtering by Region-Based Attributes on Hierachical Structures for Image Co-Segmentation , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[13]  Hugues Talbot,et al.  Shape-Based Analysis on Component-Graphs for Multivalued Image Processing , 2015, ISMM.

[14]  Martin Hutchings,et al.  Prognostic value of baseline metabolic tumor volume in early-stage Hodgkin lymphoma in the standard arm of the H10 trial. , 2018, Blood.

[15]  Hugues Talbot,et al.  Hierarchies and shape-space for pet image segmentation , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[16]  Barbara Romaniuk,et al.  Hierarchical forest attributes for multimodal tumor segmentation on FDG-PET/contrast-enhanced CT , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[17]  Hugues Talbot,et al.  Automated 3D lymphoma lesion segmentation from PET/CT characteristics , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[18]  Ronald Jones,et al.  Connected Filtering and Segmentation Using Component Trees , 1999, Comput. Vis. Image Underst..

[19]  Alexandre Cochet,et al.  Baseline metabolic tumour volume is an independent prognostic factor in Hodgkin lymphoma , 2014, European Journal of Nuclear Medicine and Molecular Imaging.

[20]  Federica Fioroni,et al.  Metabolic tumour volumes measured at staging in lymphoma: methodological evaluation on phantom experiments and patients , 2014, European Journal of Nuclear Medicine and Molecular Imaging.

[21]  G. Salles,et al.  HIGH TOTAL METABOLIC TUMOR VOLUME AT BASELINE ALLOWS TO DISCRIMINATE FOR SURVIVAL PATIENTS IN RESPONSE AFTER R‐CHOP: AN ANCILLARY ANALYSIS OF THE REMARC STUDY , 2019, Hematological Oncology.