Vous êtes ici : Accueil » Kiosque » Annonce


Mot de passe : 

Mot de passe oublié ?
Détails d'identification oubliés ?


5 juin 2020

Smart image segmentation applied to stroke diagnosis and survival prediction -- Segmentation d’image intelligente par réseau récurrent appliquée à la prédiction de survie de patients AVC

Catégorie : Doctorant

Thématique / Domaine / Contexte
Basic AI and Data Science: statistical learning theory for high dimensional data
Specialized ML and AI: signal, image, vision
Application domain: Health and well-being
Mots-clés réseau récurrent, médecine de précision, AVC, apprentissage profond, réseau de neurones convolutionnel

Contact: Vincent Vigneron, Hichem Maaref
Phone: +33 6 635 687 60


Description of the research problem It is teatime. Marie, 62, lifts her cup of black tea to her lips when her arm goes suddenly numb. She manages to set down the cup but she has trouble moving her arm. She is afraid, not knowing what is happening to her. But her friend has the presence of mind to call an ambulance immediately. Thirty minutes later at the hospital an MRI reveals the cause: stroke. Luckily Marie arrived quickly at the hospital and can be treated with thrombolysis. She can leave the hospital a few days later and she doesn’t retain any permanent damage.
According to the World Health Organization (WHO), in 2017, stroke is the second cause of death and the leading cause of chronic functional disability in adults, with 17 million victims, 31% of whom were under the age of 65. More than 6 million people die from stroke worldwide each year.

In France, each year around 150,000 people are hospitalized for a stroke, one every 4 minutes with an average cost of 19 k€. It is estimated that 750,000 people have survived a stroke, two thirds of which will have disabling consequences, which represents a financial burden for the state of around 2.8 billion €/year. . . in reality 10 billion over 5 years due to the car of handicap. The ischemic attack is caused by a blood clot (thrombus) that blocks a brain artery causing the brain tissue supplied by that artery to lack of oxygen . There is an urgent need to diagnose and determine if treatment with thrombolytic drugs (anti-coagulants) can “reverse” the stroke. The response time is limited and should not exceed 3 to 4 hours after the onset of symptoms. Confronted with the management of a stroke, the doctor then asks 3 questions to which the imagery provides particularly relevant answers: is it really a stroke? Is the stroke ischemic or hemorrhagic in nature? If thrombolysis is considered, are there any radiological contraindications to this treatment? There is consensus that magnetic resonance imaging (MRI) is the gold standard for eliminating non-vascular diagnoses because of its sensitivity and specificity in acute ischemia.
Hospital reception therefore favors the speed of access to the neurovascular unit (NVU) and MRI to confirm the diagnosis of cerebral infarction or cerebral hemorrhage: early management (<3h) to limit the severity sequelae.
If MRI makes it possible to search for the cause of the lesion, it raises many methodological difficulties linked to the very progressive pathophysiology of stroke in the very first hours:
1. a sequence of complex multifactorial images from which the doctor must decide on a treatment in a few minutes
2. the operator character depending on the technique considered.
3. the reduced definition of images due to the urgency of the diagnosis.
The early diagnosis of stroke by MRI represents a big data challenge. An automatic method to segment the lesion would improve MRI interpretation and productivity, by quantifying the relevant parameters instead of the current approximations.
However, there has not been a complete automatic tool for the simultaneous segmentation of lesions to date.

Objectives The objectives are to validate the results on multicenter patient databases. The challenge of this work is the redefinition of the choice of the therapeutic option in front of a hyperacute ischemic stroke (<3h) in a UNV thanks to the results of segmentation.

Expected results The expected solution will better characterize stroke by associating multiple weak signals with the definition of pathology, which can therefore lead to replacing complex clinical scales (CPSSS, NIHSS, LAMS, VAN, etc.), which are tedious to calculate in current practice. It will improve the quality of reading of current images, for example, by performing analyzes which are not currently carried out because they take too long to execute manually such as the volumetric measurement of the lesion, the extraction of textures, etc.

it will be able to determine what information in the image implies certain treatments leading to better results for patients. Artificial intelligence (AI) can help also the radiologist prioritize urgent cases by determining in advance which imaging tests to assess first. AI can do an initial assessment and escalate cases if necessary.

Ultimately, the technique should give more information than the expert’s eye on the texture of the lesion and its accessibility for recanalization treatments [1, 6]. The MRI interpretation is really only a quick overview of the images by the doctor, without the possibility of an in-depth evaluation. An automatic method of segmenting the lesion would improve MRI interpretation and productivity, by providing numerical values of the relevant parameters instead of the approximations currently used.

Expected performance criteria: Evaluating the new procedure against a referenced procedure raises many methodological difficulties. The expected performance indicators are
1. the repeatability of the (deterministic) segmentation process in a degraded situation or not,
2. the efficiency of the tool to be tested on a ground truth basis and quantified by a DICE [3] to measure performance in segmentation,
3. a speed of execution of a few minutes,
4. the prediction on several patches dividing the brain
5. the success rate of revascularization according to the time of arrival in the NVU.

Profil and searched skills: The person recruited must have an engineering degree or a Masters degree, solid knowledge in artificial intelligence, for example in deep learning (DL), in deep neural networks and in coding (Python, Cuda, C++). Experiences with graphics processor development (GPU) will be highly appreciated.
His English will be fluent.
The work will be carried out at the IBISC Laboratory, a SIAM team on the premises of the UFR ST located on the Evry campus of the UPSaclay. IBISC develops multidisciplinary, theoretical and applied research in the field of information sciences and automatic learning, with a strong orientation towards health applications. The selected candidate will have the chance to work in an interdisciplinary team and with a consortium of data scientists and clinicians from the CHSF.

Contact: Vincent Vigneron, Hichem Maaref
Phone: +33 6 635 687 60

For application: CV+curriculum+marks/GPA, motivation letter are required

Details on the supervision: The doctoral student will be co-supervised by Vincent Vigneron, and Hichem Maaref from the IT department of the Evry campus of the University of Paris-
Saclay, France. Vincent Vigneronis specialized in machine learning and statistical signal and image processing. Hichem Maaref is an expert in neuro-fuzzy models and their hardware
implementation. The student will stay in second year 3 months at UNICAMP to develop multi-criteria decision algorithms and supervise data collection at the UNICAMP hospital, partner of the project.

Material and financial scientific conditions of the research project The consortium, assisted by the SATT and the DISI of the University of Evry, will undertake all the steps necessary for the conservation and security of the data and the results obtained. The methods of data collection and analysis, the results and the details of the data, will be accessible, if necessary, at the request of the supervisors of the hospitals involved in the consortium.

The SATT will finance about 20 ke for the purchase of equipment (server with GPU cards, management of clinical databases) and travel expenses for the activity of the consortium.

International outlet: Several international NVUs participate in this collection of MRIs, including those from the university hospitals of UNICAMP (Bre), Melbourne (Aus), Regensburg (All).

[1] Ikram Brahim, Dominique Fourer, Vincent Vigneron, and Hichem Maaref. Deep Learning Methods for MRI Brain Tumor Segmentation: a comparative study. In 9th IEEE International Conference on Image Processing Theory, Tools and Applications (IPTA 2019), Istanbul, Turkey, November 2019.
[2] Liang Chen, Paul Bentley, and Daniel Rueckert. Fully automatic acute ischemic lesion segmentation in dwi using convolutional neural networks. NeuroImage: Clinical, 15:633 – 643, 2017.
[3] Lee R. Dice. Measures of the amount of ecologic association between species. Ecology, 26(3):297–302, 1945.
[4] J. Egger, Thomas O’Donnell, C. Hopfgartner, and B. Freisleben. Graph-based tracking method for aortic thrombus segmentation. In Jos Vander Sloten, Pascal Verdonck, Marc Nyssen, and Jens Haueisen, editors, 4th European Conference of the International Federation for Medical and Biological Engineering, pages 584–587, Berlin, Heidelberg, 2009. Springer Berlin Heidelberg.
[5] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural Comput., 9(8):1735–1780, November 1997.
[6] J. Kobold, V. Vigneron, H. Maaref, M. Aghasaryan, C. Alecu, N. Chausson, Y. L’hermitte, D. Smadja, and E. Läng. Stroke Thrombus Segmentation on SWAN with Multi-Directional U-Nets. In 9th IEEE International Conference on Image Processing Theory, Tools and Applications (IPTA 2019), Istanbul, Turkey, November 2019.
[7] J. Kobold, V. Vigneron, H. Maaref, E. Lang, and A. Tome. Extending the receptive field. an alternative to feature extraction pyramids. IEEE Trans on Neural Networks, 2019. under review.
[8] Oskar Maier, Bjoern Menze, Janina Gablentz, Levin Häni, Mattias Heinrich, Matthias Liebrand, Stefan Winzeck, Abdul Basit, Paul Bentley, Liang Chen, Daan Christiaens, Francis Dutil, Karl Egger, Chaolu Feng, Ben Glocker, Michael Götz, Tom Haeck, Hanna-Leena Halme, Mohammad Havaei, and Mauricio Reyes. Isles 2015 - a public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI. Medical Image Analysis, 35, 07 2016.

[9] Sı́lvia Delgado Olabarriaga, Jean-Michel Rouet, Maxim Fradkin, Marcel Breeuwer, and Wiro J. Niessen. Segmentation of thrombus in abdominal aortic aneurysms from cta with nonparametric statistical grey level appearance modeling. IEEE Transactions on Medical Imaging, 24:477–485, 2005.
[10] C. Parmar, P. Grossmann, J. Bussink, P. Lambin, and H. Aerts. Machine learning methods for quantitative radiomic biomarkers. Scientific reports, 5(13087), 2015.
[11] H. Branch Coslett Peter E. Turkeltaub Nicholas Tustison Myrna F. Schwartz Pustina, Dorian and Brian Avants. Automated segmentation of chronic stroke lesions using linda : Lesion identification with neighborhood data analysis. Human Brain Mapping, 37(4):1405–1421, 2016.
[12] Emmad Qazi, Alexis T Wilson, Connor McDougall, Mari Boesen, Fahad S Al-Ajlan, Pooneh Pordeli, Connor Batchelor, Khayam Khan, Tolulope T Sajobi, Ting-Yim Lee, Michael D Hill, Andrew M Demchuk, Mayank Goyal, Christopher D d’Esterre, Bijoy K Menon, and Nils D Forkert. Abstract tp45: One threshold does not fit all: Hounsfield unit thresholds to segment clot on ncct are patient specific. Stroke, 47(suppl 1):ATP45–ATP45, 2016.
[13] Christian H. Riedel, Ulf Jensen, Axel Rohr, Marc Tietke, Karsten Alfke, Stephan Ulmer, and Olav Jansen. Assessment of thrombus in acute middle cerebral artery occlusion using thin-slice nonenhanced computed tomography reconstructions. Stroke, 41(8):1659–1664, 2010.
[14] Emilie M. M. Santos, Henk A. Marquering, Olvert A. Berkhemer, Wim H. van Zwam, Aad van der Lugt, Charles B. Majoie, Wiro J. Niessen, and on behalf of the MR CLEAN investigators. Development and validation of intracranial thrombus segmentation on ct angiography in patients with acute ischemic stroke. PLOS ONE, 9(7):1–8, 07 2014.
[15] Xingjian Shi, Zhourong Chen, Hao Wang, Dit-Yan Yeung, Wai kin Wong, and Wang chun Woo. Convolutional LSTM network: A machine learning approach for precipitation nowcasting, 2015.



Dans cette rubrique

(c) GdR 720 ISIS - CNRS - 2011-2020.