Jonathan Kobold soutient sa thèse de doctorat le lundi 2 décembre 2019.
Titre: Deep Learning for lesion and thrombus segmentation from cerebral MRI
Résumé:
Deep learning, the world’s best set of methods for identifying ob-jects on images. Stroke, a deadly disease whose treatment requiresidentifying objects on medical imaging. Sounds like an obvious com-bination yet it is not trivial to marry the two. Segmenting the lesionfrom stroke MRI has had some attention in literature but thrombussegmentation is still uncharted area. This work shows that contem-porary convolutional neural network architectures cannot reliablyidentify the thrombus on stroke MRI. Also it is demonstrated whythese models don’t work on this problem. With this knowledge arecurrent neural network architecture, the logic LSTM, is developedthat takes into account the way medical doctors identify the throm-bus. Not only this architecture provides the first reliable thrombusidentification, it also provides new insights to neural network design.Especially the methods for increasing the receptive field are enrichedwith a new parameter free option. And last but not least the logicLSTM also improves the results of lesion segmentation by providinga lesion segmentation with human level performance.
Mots-clés: AVC ischémique, Automatic segmentation, Lstm, Imbalanced data
- Date : lundi 02/12/2019
- Lieu : IBISC site Pelvoux
- Doctorant : Jonathan KOBOLD, IBISC équipe SIAM
- Direction de thèse coté IBISC: Hichem MAAREF (PR IUT Évry, IBISC équipe SIAM) et Vincent VIGNERON (MCF HDR Univ. Évry, IBISC équipe SIAM)
- Le document de thèse est dans HAL
