Rémy Vandaele

Collaborative analysis of multi-gigapixel imaging data using Cytomine

Motivation: Collaborative analysis of massive imaging datasets is essential to enable scientific discoveries. Results: We developed Cytomine to foster active and distributed collaboration of multidisciplinary teams for large-scale image-based studies. It uses web development methodologies and machine learning in order to readily organize, explore, share and analyze (semantically and quantitatively) multi-gigapixel imaging data over the internet. We illustrate how it has been used in several biomedical applications. Availability and implementation: Cytomine (http://www.cytomine.be/) is freely available under an open-source license from http://github.com/cytomine/. A documentation wiki (http://doc.cytomine.be) and a demo server (http://demo.cytomine.be) are also available. Contact: info@cytomine.be Supplementary information: Supplementary data are available at Bioinformatics online.

Evaluation and Comparison of Anatomical Landmark Detection Methods for Cephalometric X-Ray Images: A Grand Challenge

Cephalometric analysis is an essential clinical and research tool in orthodontics for the orthodontic analysis and treatment planning. This paper presents the evaluation of the methods submitted to the Automatic Cephalometric X-Ray Landmark Detection Challenge, held at the IEEE International Symposium on Biomedical Imaging 2014 with an on-site competition. The challenge was set to explore and compare automatic landmark detection methods in application to cephalometric X-ray images. Methods were evaluated on a common database including cephalograms of 300 patients aged six to 60 years, collected from the Dental Department, Tri-Service General Hospital, Taiwan, and manually marked anatomical landmarks as the ground truth data, generated by two experienced medical doctors. Quantitative evaluation was performed to compare the results of a representative selection of current methods submitted to the challenge. Experimental results show that three methods are able to achieve detection rates greater than 80% using the 4 mm precision range, but only one method achieves a detection rate greater than 70% using the 2 mm precision range, which is the acceptable precision range in clinical practice. The study provides insights into the performance of different landmark detection approaches under real-world conditions and highlights achievements and limitations of current image analysis techniques.

Automated multimodal volume registration based on supervised 3D anatomical landmark detection

We propose a new method for automatic 3D multimodal registration based on anatomical landmark detection. Landmark detectors are learned independantly in the two imaging modalities using Extremely Randomized Trees and multi-resolution voxel windows. A least-squares fitting algorithm is then used for rigid registration based on the landmark positions as predicted by these detectors in the two imaging modalities. Experiments are carried out with this method on a dataset of pelvis CT and CBCT scans related to 45 patients. On this dataset, our fully automatic approach yields results very competitive with respect to a manually assisted stateof-the-art rigid registration algorithm.

Landmark detection in 2D bioimages for geometric morphometrics: a multi-resolution tree-based approach.

The detection of anatomical landmarks in bioimages is a necessary but tedious step for geometric morphometrics studies in many research domains. We propose variants of a multi-resolution tree-based approach to speed-up the detection of landmarks in bioimages. We extensively evaluate our method variants on three different datasets (cephalometric, zebrafish, and drosophila images). We identify the key method parameters (notably the multi-resolution) and report results with respect to human ground truths and existing methods. Our method achieves recognition performances competitive with current existing approaches while being generic and fast. The algorithms are integrated in the open-source Cytomine software and we provide parameter configuration guidelines so that they can be easily exploited by end-users. Finally, datasets are readily available through a Cytomine server to foster future research.

Electronic Poster: Physics track: Imaging: focus on clinical applicationsEP-1529: Automated landmarks detection for rigid registration between the simulation-CT and the treatment CBCT

respiratory motion whilst using the device, but that interpretation of the visualization schemes can be quite literal. This can lead, for example, to ‘target driven’ pulsatile breath holding rather than quiescent, smooth motion patterns. Conclusions: This interim analysis shows that the visual feedback device is well tolerated in lung cancer patients. The optical surface measurement technology delivers fast and accurate skin surface measurements. However, great care must be taken with the psychology of visual feedback schema in order to encourage predictable patient response. 1. G.J. Price et al., doi: 10.1088/0031-9155/57/2/415 (2012). 2. J.M. Parkhurst et al., doi: 10.1016/j.ijrobp.2013.08.048 (2013).

Automated Landmark Detection For Rigid Registration Between The Simulation-CT and the Treatment CBCT

Introduction As a part of the RT process, CBCT-scans are acquired on a daily basis, so as to place the patient at the reference position of the computed treatment plan: This positioning is done through rigid image registration wrt. the simulation CT-scan. The golden standard of algorithms for the registration of 3D images are inherently iterative and based on the value of the voxels. In the context of 2D images, it is now well known that rigid registration can be dramatically improved and accelerated by detecting, then matching highly informative spots in the images that are known as “landmarks”. Our goal is to transpose this 2D approach to real-world 3D medical imaging by introducing novel, automated algorithms for landmark detection in 3D images.