Multi-class brain tumor segmentation and volumetric measurements
The text based on materials by Bartosz Machura
An end-to-end pipeline for automating multi-class brain tumor segmentation and volumetric measurements. This is the title of poster which was displayed by Bartosz Machura during the BioTechX congress.
The largest european conference on diagnostics, precision medicine, and digital revolution in drug development and healthcare was organized last week in Basel.
If you have questions about
Bartosz Machura’s poster,
please contact us
Multi-class segmentation of brain tumors – our solution
Tumor burden assessment by magnetic resonance imaging (MRI) is crucial to the evaluation of glioblastoma treatment response. This assessment is complex to perform and associated with high variability due to the heterogeneity and complexity of the disease.
The introduction of a new drug requires laborious and strenuous testing in clinical settings. During a clinical study, lesions from multiple visits are being analyzed to track and assess the progression of the disease. The lesion sub-regions are usually contoured manually or semi-automatically by multiple radiologists in a time-consuming process which is hardly reproducible.
Our deep learning-powered solution tackles this issue through offering full reproducibility of an AI tool for delineating and analyzing the brain tumor lesions which also accelerates the analysis process.
“It is worth mentioning that we established the state of the art in multi-class segmentation of brain tumors – our solution was among the top performing methods evaluated in this year’s Brain Tumor Segmentation Challenge (BraTS) and Federated Tumor Segmentation Challenge (FeTS) held during the Medical Image Computing and Computer Assisted Intervention conference (MICCAI).”