Jose Dolz
Telephone: 514-396-8800 ext. 8907
Currently working as Assistant Professor at the ETS Montreal. My current research interests focus on medical image analysis and deep learning techniques with special interest on learning with limited supervision (e.g., weak supervision, few-shot learning).
Before that, I was post-doctoral researcher at the LIVIA department of the ETS in Montreal, under the supervision of Prof. Ismail Ben Ayed and Prof. Christian Desrosiers. My research as post-doc focused on bringing the power and strengths of deep learning to the problem of automatizing medical image segmentation. In addition to deep learning I explored some regularization techniques and optimization techniques to improve segmentation performance.
Previously, I worked as research engineer at AQUILAB at the same time that I was enrolled as PhD student at the scientific unit INSERM Onco-Thai U1189 “Interventional Therapies Assisted by Image and Simulation”.
Working mostly on medical image analysis. Research interests include image segmentation, feature extraction, and machine and deep learning techniques.
‘+ Original articles in refereed journals and books chapters
«Attention-based dynamic subspace learners for medical image analysis»Sukesh Adiga V, Jose Dolz, Herve Lombaert” |
«Deep interpretable classification and weakly-supervised segmentation of histology images via max-min uncertainty»Soufiane Belharbi, Jérôme Rony, Jose Dolz, Ismail Ben Ayed, Luke McCaffrey, Eric Granger” |
«State-of-the-art retinal vessel segmentation with minimalistic models»Adrian Galdran, André Anjos, José Dolz, Hadi Chakor, Hervé Lombaert, Ismail Ben Ayed” |
«Incremental multi-target domain adaptation for object detection with efficient domain transfer»Le Thanh Nguyen-Meidine, Madhu Kiran, Marco Pedersoli, Jose Dolz, Louis-Antoine Blais-Morin, Eric Granger” |
«Weakly supervised segmentation with cross-modality equivariant constraints»Gaurav Patel, Jose Dolz” |
Read More >
+ Papers in refereed conference proceedings
«On the texture bias for few-shot CNN segmentation»Reza Azad, Abdur R.Fayjie, Claude Kauffmann, Ismail Ben Ayed, Marco Pedersoli, Jose Dolz” |
«Few-shot segmentation without meta-learning: A good transductive inference is all you need?»Malik Boudiaf, Hoel Kervadec, Ziko Imtiaz Masud, Pablo Piantanida, Ismail Ben Ayed, Jose Dolz” |
«Teach me to segment with mixed supervision: Confident students become masters»Jose Dolz, Christian Desrosiers, Ismail Ben Ayed” |
«A self-training framework for glaucoma grading in OCT B-scans»Gabriel Garcia, Adrian Colomer, Rafael Verdu-Monedero, Jose Dolz, Valery Naranjo” |
«Beyond pixel-wise supervision: semantic segmentation with higher-order shape descriptors»Hoel Kervadec, Houda Bahig, Laurent Letourneau-Guillon, Jose Dolz, Ismail Ben Ayed” |
‘
[2019] Kervadec H, Bouchtiba J, Desrosiers C, Granger É, Dolz J, Ben Ayed I. Boundary loss for highly unbalanced segmentation. MIDL 2019. [Code]
[2019] Kervadec H, Dolz J, Tang M, Granger E, Boykov Y, Ben Ayed I. Constrained-CNN losses for weakly supervised segmentation. Medical Image Analysis. 2019 Feb 13. [Code]
[2018] J. Dolz, K. Gopinath, J. Yuan, H. Lombaert, C. Desrosiers, I. Ben Ayed. “HyperDenseNet: a hyper-densely connected CNN for multi-modal semantic segmentation”. IEEE TMI.[Code]
[2018] Dolz J, Ben Ayed I, Desrosiers C. Dense multi-path U-Net for ischemic stroke lesion segmentation in multiple image modalities. In International MICCAI Brainlesion Workshop 2018 Sep 16 (pp. 271-282). Springer, Cham.
[2018] Mondal AK, Dolz J, Desrosiers C. Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning. arXiv preprint arXiv:1810.12241. 2018 Oct 29. [Code]
[2018] Dolz J, Xu X, Rony J, Yuan J, Liu Y, Granger E, Desrosiers C, Zhang X, Ben Ayed I, Lu H. Multiregion segmentation of bladder cancer structures in MRI with progressive dilated convolutional networks. Medical physics. 2018 Dec;45(12):5482-93.
[2017] Dolz J, Desrosiers C, Wang L, Yuan J, Shen D, Ben Ayed I. Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation. arXiv preprint arXiv:1712.05319. 2017 Dec 14. [Code]
[2017] J. Dolz, I. Ben Ayed, C. Desrosiers. “Unbiased Shape Compactness for Segmentation“. In Medical Image Computing and Computer Assisted Interventions (MICCAI) 2017. [Code]
[2017] T. Fechter, S. Adebahr, D. Baltas, I. Ben Ayed, C. Desrosiers, J. Dolz. “Esophagus segmentation in CT via 3D fully convolutional neural network and random walk”.Medical Physics, 44 (12), 6341-6352.
[2017] J. Dolz, I Ben Ayed, C. Desrosiers. “DOPE: Distributed Optimization for Pairwise Energies”. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawai, 2017.
[2017] J. Dolz, C. Desrosiers, I. Ben Ayed. “3D fully convolutional networks for subcortical segmentation: A large-scale study”. NeuroImage, 170, 456-470. [Code]
[2016] J. Dolz, H.A. Kirisli, T. Fechter, S. Karnitzki, O. Oehlke, U. Nestle, M. Vermandel, L. Massoptier. “Interactive contour delineation of organs at risk in radiotherapy: Clinical evaluation on NSCLC patients”. Medical Physics, 2016 May 1;43(5): 2569-80.
[2016] J. Dolz, N. Betrouni, M. Quiet, D. Kharroubi, H.A. Leroy, N. Reyns, L. Massoptier, M. Vermandel. “Stacking denoising auto-encoders in a deep network to segment the brainstem on MRI in brain cancer patients: a clinical study“. International Journal of Computerized Medical Imaging and Graphics, 52 (2016): 8-18.
[2015] J. Dolz, A. Laprie, S. Ken, HA Leroy, N Reyns, L Massoptier, M Vermandel. “Supervised machine learning-based classification scheme to segment the brainstem on MRI in multicenter brain tumor treatment context”. International Journal of Computer Assisted Radiology and Surgery (IJCARS), 2015, 1-9.
- [2016] A. Laruelo*, J. Dolz*, S. Ken, L. Chaari, M. Vermandel, L. Massoptier, A. Laprie. “Probability map prediction of relapse areas in glioblastoma patients using multi-parametric MR”, ESTRO 35th Meeting, April-May 2016, Turin. Nominated to the ESTRO Best Poster Award in the category of “Physics Poster Award”.
-
[2016] J. Dolz, H.A. Kirisli, T. Fechter, S. Karnitzki, U.Nestle, M. Vermandel, L. Massoptier. “Preliminary clinical study to evaluate an interactive system to segment OARs in thoracic oncology”, ESTRO 35th Meeting, April-May 2016, Turin. Nominated to the ESTRO Best Poster Award in the category of “Physics Poster Award”.
-
[2015] Jose Dolz, Soléakhéna Ken, Henri Arthur Leroy, Nicolas Reyns, Anne Laprie, Laurent Massoptier; Maximilien Vermandel.“Supervised machine learning method to segment the brainstem on MRI in multicenter brain tumor treatment context”, International Conference of Computer Assisted Radiology and Surgery (CARS), June 2015, Barcelone.
- [2015] Dolz J, Leroy HA, Reyns N, Massoptier L, Vermandel M. “A fast and fully automated approach to segment optic nerves on MRI and its application to radiosurgery”, IEEE International Symposium on Biomedical Imaging (ISBI), April 2015, New York (pp. 1102-1105).
Tab Content goes here
+ ACADEMIC PROFILE
2013 – 2016
I was enrolled as PhD student at Universite Lille 2. Under the supervision of Maximilien Vermandel (INSERM U703) and Laurent Massoptier (AQUILAB), I develop my PhD. thesis which is entitled “Towards automatic segmentation of organs at risk on brain cancer on MRI through deep learning techniques and its application to clinical routine”. This thesis is integrated inside the european SUMMER Project, where AQUILAB is the coordinator. I obtained my PhD diploma the 15th, June, 2016, with the highest distinction (Summa cum laude).
-
Visiting Researcher during one month(January 2014) at the University Medical Center Freiburg in the Radiation Oncology department.
-
Visiting Researcher during one month(October 2014) at the Medical University of Vienna (MUW) in the Digital Image Processing Laboratory Center of Medical Physics and Biomedical Engineering
2010/06
Bachelor and MSc Degree in Telecommunications & Electrical Engineering in Polytechnic University of Valencia, majoring in signal processing and developing the Master ́s Thesis in Högskolan I Gävle (Sweden), with an Erasmus grant.
+ WORK EXPERIENCE
2016/07 – Present
Post-doctoral researcher
at the LIVIA department of the ETS, in Montreal. Following my research during the obtention of my PhD degree, I keep on working on bringing the power of deep learning to the problem of automatizing segmentation in medical images.
2012/11 – 2016/05
Marie Curie Early Stage Researcher
at Aquilab, on the SUMMER Project. “SUMMER” was devised to produce a unique software solution using all imaging techniques for biological target volume delineation, based on spatial co-registration of multi-modal morphologic and functional images. My main tasks regarding this project focused on finding novel automatic or semi-automatic segmentation methods to delineate Organs at Risk in radiotherapy. As quantity of information at medical images are becoming larger really fast, efficient processing of these kind of images is a must in order to the algorithms may be be used in clinical routine. This fact made me combine CPU and GPU programming when implementing the solutions found in the research step. Apart of the programming knowledge and skills already present before starting this stage, I improved and learned new ones, like OpenCL, ITK or MITK.
2011/10 – 2012/11
Team Leader and Researcher at Computer Vision Department at ARLab.
In this stage I was mainly involved in these topics: Image Matching, 3D image Tracking, 3D face Tracking and Detection and Motion, all markerless-based. This work included from the research to the implementation of the methods. As other tasks, I also had to rewrite some functions in assembler, in order to speed up some processes. However, this is still an early stage for me. I was the responsible of developing all the core code for the Image Matching and 3D Image Tracking Engines that the company used as SDK for developers. I also actively participated in the SDK creation of these engines, with which I strongly improved my C++ skills. Regarding the communication and team-work skills, at the spanish office we had people from several countries, and the company also had an office in Haifa (Israel), which allowed me to improve these skills due to the daily co-operation between both offices and also the co-operation between members of different teams (Computer Vision, Real-time and Mobile Development).
2010/10 – 2011/09
Scholarship in Research at Applications Area and Technological Services at Biomechanical Institute of Valencia. Image and Video processing, Pattern Recognition and 3D Modelling tasks focused in biomechanical applications. These tasks were carried out using different programming languages, such as Matlab or C++, and using some libraries like Qt or OpenCV for interfaces and Image Processing, respectively. Specifically I was involded in two main projects, a footprint laser Scanner in which I develop and improve all the Image Processing algorihtms(MATLAB and C++) and a 3D Face Scanner where I participated developing some parts of that project, like auto- camera calibration software (C++) or some pre-processing parts (MATLAB and C++).
2009/12 – 2010/06
“Laboratory assistant” in Radio Center for Technology Gävle. Laboratory support functions such as taking measurements, systems´s calibration or implementation of several applications with the GUI of MATLAB for processing the measurements taken. Apart from that, here I worked in an international environment, where I was able to develop my personal skills.
Jose
Dolz
Research & Innovation
Contact Us
Pavillon Principal (A)
1100, rue Notre-Dame Ouest
Montréal, QC, H3C 1K3
Room A-3600
Tel.: +1 (514) 396-8650
E-Mail: eric.granger@etsmtl.ca