Segmenting pediatric optic pathway glioma from MRI using deep learning
Challenge: segmenting pediatric optic pathway glioma
The challenge was to verify if an ML model based on brain MRI that automatically segments glioblastoma (GBM) in adults is useful in automated segmentation of pediatric optic pathway gliomas (OPG), although OPGs have vastly different locations and characteristics than GBMs. In summary, the goal of the project was to improve the specificity of the diagnostic process and therapy planning.
What we did: experimental study
In that case, our role was to conduct the whole experimental study related to segmenting optic pathway glioma. The study was performed over two clinical datasets and involved quantitative, qualitative and statistical analysis. We have also set up and coordinated the cooperation between medical facilities. In effect, we leveraged our medical imaging analysis technology and delivered results in 3 months.
Medical image analysis – our technology
Graylight Imaging specialises in creating AI technologies for medical image analysis. Moreover, we have extensive experience in developing AI medical solutions and algorithms tailored to specific needs. Our advanced algorithms automate the manual segmentation process.
In this project, we used a model that automatically segments glioblastoma (GBM) in adults. What’s more the model features automated tumor identification with subregions from MRI, including edemas, necroses, and enhancing tumors. Additionally, it can calculate the volume of each subregion.
Results of the experiment
The experiment indicated high agreement between automatically calculated and ground-truth volumetric measurements of the tumors and very fast operation of the proposed approach. Surely both of which can increase the clinical utility of the suggested software tool. This rigorous experimental study was published in ‘Computers in Biology and Medicine’.
Your content goes here. Edit or remove this text inline or in the module Content settings. You can also style every aspect of this content in the module Design settings and even apply custom CSS to this text in the module Advanced settings.
Our team of scientists
Our team has documented the detailed results in the “Segmenting pediatric optic pathway gliomas from MRI using deep learning” paper.
References:
Image comes from: J. Nalepa, S. Adamski, K. Kotowski, S. Chelstowska, M. Machnikowska-Sokolowska, O. Bozek, A. Wisz, E. Jurkiewicz: Segmenting pediatric optic pathway gliomas from MRI using deep learning. Computers in Biology and Medicine, Volume 142, 2022, 105237, ISSN 0010-4825, https://doi.org/10.1016/j.compbiomed.2022.105237.