Ph.D. student @ Technische Universiteit Eindhoven (TU/e)
since 4/1/2014 for 3 years.
under the supervision of Prof. Bart ter Haar Romeny
PhD Thesis public defence “Contextual and Deep Learning Approaches in Retinal Image Analysis” on December 4, 2017
The main aim of the study is to apply sub-Riemannian geometric methods to the analysis of retinal images, in order to facilitate computer-aided diagnosis for screening purposes. Several ocular and systemic diseases such as hypertension and arteriosclerosis cause geometrical and functional changes to the blood vasculature in retinal images, including the change of vessel widths and angles at bifurcations and crossings. These diagnostic biomarkers are investigated using the vessel segmentation, junction detections or vessel trackings. We have proposed a fully automatic supervised segmentation method (called Brain-Inspired Multi-Scales and multi-Orientation: BIMSO) for not only the color RGB images, but also the ones taken with laser ophthalmoscope (SLO) imaging cameras. Moreover, we introduced a novel BIfurcation and CRossing detection method using Orientations Scores (BICROS). BIMSO and BICROS are inspired by the pinwheel structure of receptive fields in primary visual cortex. By lifting the 2D image to a joint space of positions and orientations (SE(2)) the vessels disentangle based on their orientations. After using the non-linear enhancement in this space, the blood vessels and junctions are discriminated based on their geometric properties in a supervised manner. Tracking the vessels faces difficulties when the vessel paths are interrupted or junctions are disconnected. We analysed the specific problems at junctions with a connectivity kernel obtained as the fundamental solution of the Fokker-Planck equation, which is usually used to represent the geometrical structure of multi-orientation cortical connectivity. By using the spectral clustering on a large local affinity matrix constructed by both the connectivity kernel and the feature of intensity, the vessels are identified successfully in a hierarchical topology each representing an individual perceptual unit.
Complementary training activities:
- Programming with Mathematica - June 24, 2014 Amsterdam, Netherlands
Local training activities:
- Advanced Pattern Recognition (lecturers V. Cheplygina, J.H. Krijthe, M. Loog, J. Mooij, D.M.J.Tax) - April 13-17, 2015 TU Delft, Netherlands
- Designing algorithms for Biologically-Inspired Computer Vision - April 22-25, 2014 Eindhoven, Netherlands
- NVPHBV, Spring meeting - May 20, 2016 Amsterdam, Netherlands
Network-wide training activities:
- Scientific collaboration IDIAP research institute, EPFL - October 2016 to March 2017 Martigny, Switzerland
- Swiss Machine Learning Day 2016 - November 23, 2016 Lausanne, Switzerland
- Third Biomedical Image Analysis Summer School - July 6-10, 2015 Paris, France
- Deep learning in Medical Imaging - October 7, 2016 Rotterdam, Netherlands
Talks and Poster Presentations:
- Automated Analysis of Retinal Images for Early Diabetes Detection with Sub-Riemannian Methods at International ICIAR Conference - July 22-24, 2015 Niagara Falls, Canada
- Poster: Automatic Detection of Vascular Bifurcations and Crossings in Retinal Images Using Orientation Scores at IEEE International Symposium on Biomedical Imaging (ISBI) - April 13-16, 2016 Prague, Czeh Republic
- Talk: Automated Analysis of Retinal Images for Early Diabetes Detection with Sub-Riemannian Methods at Sub-Riemannian Analysis, PDE and Applications - January 26-30, 2015 Berna, Swiss
- Poster: Analysis of Vessel Connectivities in Retinal Images by Cortically Inspired Spectral Clustering at BME research day - August 8, 2016 Eindhoven, Netherlands
- Talk: Automated Analysis of Retinal Images for Early Diabetes Detection with Sub-Riemannian Methods at Mid-term Review Meeting - December 9, 2015 Helsinki, Finland
- Talk: Geometric connectivity analysis in curvilinear images based on the data-driven edge co-occurrence at NVPHBV, Spring meeting - May 20, 2016 Rotterdam, Netherlands
- Talk: Geometric connectivity analysis based on edge co-occurrences in retinal images at MICCAI 2016 Conference, Workshop on Machine Learning in Medical Imaging, Workshop on Ophthalmic Medical Image Analysis - October 10, 2016 Athens, Greece
- CNRS Paris - April 7 to June 10, 2015 Paris, France
- I-optics - January to March, 2015 Paris, France
Publications and Preprints
- S. Abbasi-Sureshjani, M. Favali, G. Citti, A. Sarti, B. ter Haar Romeny Cortically-inspired spectral clustering for connectivity anal- ysis in retinal images: Curvature integration preprint
- S. Abbasi-Sureshjani, J. Zhang, R. Duits, B.ter Haar Romeny Retrieving challenging vessel connections in retinal images by line co-occurrence statistics preprint
- S. Abbasi-Sureshjani, I. Smit-Ockeloen, J. Zhang, B. Ter Haar Romeny Biologically-Inspired Supervised Vasculature Segmentation in SLO Retinal Fundus Images on Lecture Notes in Computer Science Vol. 9164 Springer Verlag 2015 pp. 325-334
- J. Zhang, E. Bekkers, S. Abbas-Sureshaji, B. Dashtbozorg, B. Ter Haar Romeny Robust and Fast Vessel Segmentation via Gaussian Derivatives in Orientation Scores on Lecture Notes in Computer Science Vol 9279 Springer Verlag 2015 pp. 537-547 open access version
- F. Huang, B. Dashtbozorg, J.Zhang, E. Bekkers, S. Abbasi-Sureshjani, T. TJM Berendschot, B.M ter Haar Romeny Reliability of Using Retinal Vascular Fractal Dimension as a Biomarker in the Diabetic Retinopathy Detection on British Journal of Ophthalmology Vol 2016 2016 pp. 1-13
- B. M. ter Haar Romeny, E. J. Bekkers, J. Zhang, S. Abbasi-Sureshjani, F. Huang, R. Duits, B. Dashtbozorg, T. T. J. M. Berendschot , I. Smit-Ockeloen, K. A. J. Eppenhof, J. Feng, J. Hannink, J. Schouten, M. Tong, H. Wu, H. W. Van Triest, S. Zhu, D. Chen, W. He, L.Xu, P. Han, Y. Kang Brain-inspired algorithms for retinal image analysis on Machine Vision and Applications Vol 27 2016 pp. 1117-1135
- S. Abbasi-Sureshjani, I. Smit-Ockeloen, E. Bekkers, B. Dashtbozorg, B. ter Haar Romeny Automatic detection of vascular bifurcations and crossings in retinal images using orientation scores on IEEE Xplore Digital Library 2016 pp.
- J. Zhang, E. Bekkers, S. Abbasi-Sureshjani, B. Dashtbozorg, B. ter Haar Romeny Bridging Disconnected Curvilinear Structures via Numerical Evolutions of Completion Process in Ophthalmologic Images on 2016 pp.
- B. Dashtbozorg, S. Abbasi-Sureshjani, J. Zhang, F. Huang, E. Bekkers, B. ter Haar Romeny Infrastructure for Retinal Image Analysis on 2016 pp.
- Z. Li, F. Huang, J. Zhang, B. Dashtbozorg, S. Abbasi-Sureshjani, Y. Sun, X. Long, Q. Yu, B. Ter Haar Romeny, T. Tan Multi-modal and multi-vendor retina image registration on Vol 9 2018 pp. 410-422
- M. Favali, S. Abbasi, A. Sarti, B. H. ter Romeny Analysis of Vessel Connectivities in Retinal Images by Cortically Inspired Spectral Clustering on Journal of Mathematical Imaging and Vision Vol 56 Springer Netherlands 2016 pp. 158-172 open access version
- S. Abbasi Automated Analysis of Retinal Images for Early Diabetes Detection report
- S. Abbasi Automated Analysis of Retinal Images for Early Diabetes Detection with Sub-Riemannian Methods report
← Fellows' list