Deep neural network to locate and segment brain tumors outperformed the expert technicians who created the training data

Purpose: Deep learning (DL) algorithms have shown promising results for brain tumor segmentation in MRI. However, validation is required prior to routine clinical use. We report the first randomized and blinded comparison of DL and trained technician segmentations. Approach: We compiled a multi-inst...

Descripción completa

Detalles Bibliográficos
Autores principales: Mitchell, Joseph Ross, Kamnitsas, Konstantinos, Singleton, Kyle W., Whitmire, Scott A., Clark-Swanson, Kamala R., Ranjbar, Sara, Rickertsen, Cassandra R., Johnston, Sandra K., Egan, Kathleen M., Rollison, Dana E., Arrington, John, Krecke, Karl N., Passe, Theodore J., Verdoorn, Jared T., Nagelschneider, Alex A., Carr, Carrie M., Port, John D., Patton, Alice, Campeau, Norbert G., Liebo, Greta B., Eckel, Laurence J., Wood, Christopher P., Hunt, Christopher H., Vibhute, Prasanna, Nelson, Kent D., Hoxworth, Joseph M., Patel, Ameet C., Chong, Brian W., Ross, Jeffrey S., Boxerman, Jerrold L., Vogelbaum, Michael A., Hu, Leland S., Glocker, Ben, Swanson, Kristin R.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Society of Photo-Optical Instrumentation Engineers 2020
Materias:
Image Perception, Observer Performance, and Technology Assessment
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7567400/
https://www.ncbi.nlm.nih.gov/pubmed/33102623
http://dx.doi.org/10.1117/1.JMI.7.5.055501

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7567400/
https://www.ncbi.nlm.nih.gov/pubmed/33102623
http://dx.doi.org/10.1117/1.JMI.7.5.055501

Ejemplares similares