Tumor Segmentation Based on Hybrid MR-Images for Radiation Treatment Planning

Résumé fourni par la source

The development of tumor segmentation method using only MRI hybrid images is considered. Proposed original tumor segmentation algorithms based on different brain MRI methods and use of U-Net convolutional neural network allow evaluate the effectiveness and accuracy of tumor segmentation algorithms using only MRI images and select the most adequate combination of them for specific clinical conditions.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.