Maximilien Vermandel
Lille, Hauts-de-France, France
2 k abonnés
+ de 500 relations
Articles de Maximilien
Activité
-
🌟 [𝐋𝐄𝐕𝐄𝐄 𝐃𝐄 𝐅𝐎𝐍𝐃𝐒] 𝐋𝐀𝐓𝐓𝐈𝐂𝐄 𝐌𝐄𝐃𝐈𝐂𝐀𝐋 𝐥𝐞̀𝐯𝐞 𝟒𝟑 𝐌€ 𝐩𝐨𝐮𝐫 𝐫𝐞́𝐯𝐨𝐥𝐮𝐭𝐢𝐨𝐧𝐧𝐞𝐫 𝐥𝐚…
🌟 [𝐋𝐄𝐕𝐄𝐄 𝐃𝐄 𝐅𝐎𝐍𝐃𝐒] 𝐋𝐀𝐓𝐓𝐈𝐂𝐄 𝐌𝐄𝐃𝐈𝐂𝐀𝐋 𝐥𝐞̀𝐯𝐞 𝟒𝟑 𝐌€ 𝐩𝐨𝐮𝐫 𝐫𝐞́𝐯𝐨𝐥𝐮𝐭𝐢𝐨𝐧𝐧𝐞𝐫 𝐥𝐚…
Aimé par Maximilien Vermandel
-
Hemerion participated for the first time this year in the Annual Meeting of the Congress of Neurological Surgeons (CNS) of Neurosurgeons, the…
Hemerion participated for the first time this year in the Annual Meeting of the Congress of Neurological Surgeons (CNS) of Neurosurgeons, the…
Aimé par Maximilien Vermandel
-
One week already since we are back from Los Angeles after an intense week at the Congress of Neurological Surgeons (CNS) Annual Meeting. 👉 Read…
One week already since we are back from Los Angeles after an intense week at the Congress of Neurological Surgeons (CNS) Annual Meeting. 👉 Read…
Partagé par Maximilien Vermandel
Expérience
Formation
-
Institut national des Sciences et Techniques nucléaires
-
-
-
-
-
-
-
-
Mise en correspondance tridimensionnelle d'images multimodales : applications aux systèmes d'imagerie projective et tomographique d'angiographie cérébrale, Dir. Rech. : Jean Rousseau / Christian Vasseur
-
-
-
-
-
-
-
-
-
-
-
-
Stage à l'Université de Charlotte en Caroline du Nord (UNCC, Charlotte, North Carolina) et chez Johnson Controls (Charlotte, North Carolina)
Publications
-
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
To constrain the risk of severe toxicity in radiotherapy and radiosurgery, precise volume delineation of organs at risk is required. This task is still manually performed, which is time-consuming and prone to observer variability. To address these issues, and as alternative to atlas-based segmentation methods, machine learning techniques, such as support vector machines (SVM), have been recently presented to segment subcortical structures on magnetic resonance images (MRI).
SVM is proposed…To constrain the risk of severe toxicity in radiotherapy and radiosurgery, precise volume delineation of organs at risk is required. This task is still manually performed, which is time-consuming and prone to observer variability. To address these issues, and as alternative to atlas-based segmentation methods, machine learning techniques, such as support vector machines (SVM), have been recently presented to segment subcortical structures on magnetic resonance images (MRI).
SVM is proposed to segment the brainstem on MRI in multicenter brain cancer context. A dataset composed by 14 adult brain MRI scans is used to evaluate its performance. In addition to spatial and probabilistic information, five different image intensity values (IIVs) configurations are evaluated as features to train the SVM classifier. Segmentation accuracy is evaluated by computing the Dice similarity coefficient (DSC), absolute volumes difference (AVD) and percentage volume difference between automatic and manual contours.
Mean DSC for all proposed IIVs configurations ranged from 0.89 to 0.90. Mean AVD values were below 1.5cm3, where the value for best performing IIVs configuration was 0.85cm3, representing an absolute mean difference of 3.99% with respect to the manual segmented volumes.
Results suggest consistent volume estimation and high spatial similarity with respect to expert delineations. The proposed approach outperformed presented methods to segment the brainstem, not only in volume similarity metrics, but also in segmentation time. Preliminary results showed that the approach might be promising for adoption in clinical use.Autres auteursVoir la publication
Brevets
-
Calibration phantom and method for measuring and correcting geometric distorsions in an image of a body part of a patient.
Émis le EU EP09305842.8
The invention relates to a calibration phantom and to a method for measuring and correcting geometric distortions in an image of a body part of a patient.
In the medical field, an image of a body part obtained by a medical imaging system, such as a magnetic resonance imaging system, is known to be prone to geometric distortions. The image of the body part is therefore not necessarily an exact representation of the actual body part.
Sources of geometric distortions are various. For a…
The invention relates to a calibration phantom and to a method for measuring and correcting geometric distortions in an image of a body part of a patient.
In the medical field, an image of a body part obtained by a medical imaging system, such as a magnetic resonance imaging system, is known to be prone to geometric distortions. The image of the body part is therefore not necessarily an exact representation of the actual body part.
Sources of geometric distortions are various. For a magnetic resonance imaging system, among the possible sources, one can cite the geometric distortions induced by the imaging system itself, especially due to inhomogeneity of main magnetic field and nonlinearities of gradients, and the geometric distortions induced by the imaged body part, especially due to chemical shift and susceptibility variations within the imagined body part and at the air and tissue interfaces.
Images acquired for a purpose that requires an accurate spatial localisation, such as images for diagnosis or operation of the brain as well as abdomen, limb or others, need to be corrected as to such geometric distortions to reach the required accuracy.
A known method for measuring and correcting geometric distortions induced by the imaging system itself in an image obtained by the medical imaging system implements a calibration phantom that comprises a plurality of detection elements arranged in a determined pattern. To calibrate the imaging system, a correspondence between the positions of the detection elements on the image and their actual positions in the determined pattern is established.
Autres inventeurs -
-
FANTÔME POUR LE CONTRÔLE DE QUALITE EN IMAGERIE TOMOGRAPHIQUE, ET NOTAMMENT EN IMAGERIE TEP
Émis le EU 1 923 000
La présente invention concerne le domaine du contrôle de qualité en imagerie tomographique 3D, et trouve préférentiellement, mais pas exclusivement son application au contrôle de qualité en imagerie TEP (Tomographie par Emission de Positons). Dans ce domaine, l’invention a pour objet un nouveau fantôme qui permet, par tomographie au moyen d’un appareil d’imagerie, et en association avec un programme de calcul, de déterminer un ou plusieurs paramètres caractérisant la qualité des images…
La présente invention concerne le domaine du contrôle de qualité en imagerie tomographique 3D, et trouve préférentiellement, mais pas exclusivement son application au contrôle de qualité en imagerie TEP (Tomographie par Emission de Positons). Dans ce domaine, l’invention a pour objet un nouveau fantôme qui permet, par tomographie au moyen d’un appareil d’imagerie, et en association avec un programme de calcul, de déterminer un ou plusieurs paramètres caractérisant la qualité des images tomographiques acquises au moyen dudit appareil d’imagerie, tels que notamment la résolution spatiale selon différentes direction, le rapport signal/bruit, le profil de coupe ou l'uniformité. L’invention trouve principalement son application dans le domaine du contrôle de qualité d’un appareil d’imagerie médicale.
Autres inventeurs -
Langues
-
Anglais
-
Plus d’activités de Maximilien
-
Dans cette vidéo, retrouvez Camille et Thomas qui détaillent le rôle de la sortiline dans le cancer du poumon, la protéine "gardienne" à l'origine du…
Dans cette vidéo, retrouvez Camille et Thomas qui détaillent le rôle de la sortiline dans le cancer du poumon, la protéine "gardienne" à l'origine du…
Aimé par Maximilien Vermandel
-
Venez découvrir nos dernières innovations pour la chirurgie du rachis sur le congrès #EUROSPINE à Copenhague.
Venez découvrir nos dernières innovations pour la chirurgie du rachis sur le congrès #EUROSPINE à Copenhague.
Aimé par Maximilien Vermandel
-
Große Ehre für Prof. Walter Stummer 🏅 Univ.-Prof. Dr. Walter Stummer, Direktor der Klinik für Neurochirurgie am UKM , wurde Mitte Oktober beim CNS…
Große Ehre für Prof. Walter Stummer 🏅 Univ.-Prof. Dr. Walter Stummer, Direktor der Klinik für Neurochirurgie am UKM , wurde Mitte Oktober beim CNS…
Aimé par Maximilien Vermandel
-
🚀 Il s'agirait de l'une des plus grosses ventes franco-françaises de l'histoire de la French Tech ! ➡️ https://lnkd.in/ebvYsn4t 💰 Le laboratoire…
🚀 Il s'agirait de l'une des plus grosses ventes franco-françaises de l'histoire de la French Tech ! ➡️ https://lnkd.in/ebvYsn4t 💰 Le laboratoire…
Aimé par Maximilien Vermandel