Fingerprinting Heterogeneity of Glioma using PET-MR Information

شروع رویداد
سه‌شنبه ۲۷ مهر ۹۵ ۱۵:۰۰
پایان رویداد
سه‌شنبه ۲۷ مهر ۹۵ ۱۷:۰۰
مکان رویدادتهران
موضوع رویدادپزشکی / غیره
اضافه به تقویم
Fingerprinting Heterogeneity of Glioma using PET-MR Information
برگزارکننده‌ی رویداد
تماس با برگزارکننده
-۰۲۱-۸۸۶۲۸۹۴۰- ۰۲۱-۸۸۶۲۸۹۳۶- ۰۲۱-۸۸۶۲۸۹۴۵
مهلت ثبت‌نام برای این رویداد به پایان رسیده است.
مهلت ثبت‌نام
قیمت (تومان)

توضیحات بیشتر

مؤسسه بین المللی توسعه دانش فردای ایرانیان با همکاری دانشکده مهندسی دانشگاه امیرکبیر برگزار می کند:


سمینار Fingerprinting Heterogeneity of Glioma using PET-MR Information


با حضور خانم فاطمه نجات بخش 

دستیار تحقیق در دانشکاه لودویگ ماکسیمیلیان مونیخ

چکیده موضوعات مورد بحث:

The era of PET/MRI provides the opportunity to capture different anatomical and molecular perspective of glioma. However, it is still very challenging to properly identifying individual parts of glioma from multi-parametric images acquired in PET/MRI. This project is proposing a novel machine learning algorithm based on Generative Method to characterize intra-tumor heterogeneity of glioma. The algorithm was applied on dynamic [18F] FET-PET, [18F] Fmiso PET, rOEF, MRI T1, T2, T1W, T2W, FLAIR, DCE MRI and so on. This probabilistic model allows for different tumor boundaries in each channel, reflecting difference in tumor appearance across modalities. Classification result shows partly distributed feature maps in order to be able to select relevant features amongst wide patient data. The identified parts with different malignancy were discussed and validated according to first, the manual segmentations by clinical experts to investigate the performance on the tumor borders and second, graph maps to investigate the performance on the intra tumor regions

The main aim of the project is focused on the extraction of the additive information from PET and combining it with the MRI images information for each patient and relating them to the grade of malignancy. Magnetic resonance imaging (MRI), as the gold standard diagnostic tool for brain tumors, offers high spatial resolution and is widely available. In high-grade gliomas (HGG) the area of contrast enhancement on MRI T1-weighted sequences is generally assumed to reflect the main tumor burden. In neuropathologic studies, however, invasive glioma cells can be found far beyond contrast enhancing areas. Recently, molecular imaging studies using the [18F]-FET tracer revealed that in HGG patients the “metabolic tumor volumes” are subject and instrument dependent which brought us about this conclusion into four classes

 Case1: Metabolic tumor volumes are frequently larger on PET compared to the corresponding “morphologic contrast enhancing tumor volumes” on MRI

 Case2: Active region of metabolic tumor volumes are visualized on PET while there is less chance to have such a segmentation on MRI

 Case3: Due to the weak and not adequate PET signal, no useful information could be extracted for some certain cases

Based on the morphologic contrast enhancing tumor volumes achieved from MRI information and clinical data, such a patients suffers from a first or second grade glioma

 Case4: According to some certain subjects studied, there are some spots and regions in only the PET signal having similar kinetic parameters as a grade or Glioma. These regions are isointense looking into MRI. [18F]-FET PET was able to identify LGG even in the absence of contrast enhancement on MRI

مدت و زمان بندی: سه شنبه 27 مهر ماه 1395 از ساعت 15:00 الی 17:00

 لینک ثبت نام:

 آدرس محل برگزاری:

تهران، خیابان حافظ، شماره ۴۲۴، دانشگاه صنعتی امیرکبیر، دانشکده مهندسی پزشکی


آدرس:تهران خيابان شريعتي، خيابان یخچال، بعد از پارک موزه آب، دانشکده مدیریت دانشگاه آزاد تهران جنوب، سالن همایش

موقعیت جغرافیایی رویداد