BioTechX – our brain tumor segmentation algorithm

The largest european conference on diagnostics, precision medicine, and digital revolution in drug development and healthcare – BioTechX – is starting tomorrow in Basel. The congress runs 8-10th November.
This is the place where you can meet specialists form different healthcare areas – IT, genomics, translational medicine. There are experts from pharma and healthcare companies, data scientists, bioinformaticians, cheminformaticians and clinicians from over the world.
Let’s talk during BioTechX
about brain image
segmentation solutions
BioTechX – our footprint
We will be there, because it is great opportunity to exchange experiences, meet many interesting people and gain new knowledge.
There will be displayed the poster by Bartosz Machura, Graylight Imaging expert focused on medical image processing, computer vision and 3D visualization. The poster entitled “An end-to-end pipeline for automating multi-class brain tumor segmentation and volumetric measurements”. During the intractive poster session (9-10th November) you will have the opportunity to ask questions about our solutions based on artificial intelligence we have been working on. Meet Bartosz Machura!
Brain tumor segmentation challenge
We have been working on brain tumor segmentation and analysis algorithm for several years. In this year we submitted our solution to two competitions: The Federated Tumor Segmentation Challenge 2022 (FeTS) and again to the Brain Tumor Segmentation Challenge (BraTS).
Our algorithm was ranked 2nd in FeTS 2022, 2nd in BraTS 2022 on a pediatric dataset, and 3rd in BraTS 2022 on a Sub-Saharan Africa dataset.
“We designed a fully automated deep learning tool for the analysis of 3D MRI data acquired for glioma patients. We proposed an end-to-end system that uses MR sequences (pre-contrast T1, post-contrast T1-weighted T1Gd, T2-weighted T2, and T2 fluid-attenuated inversion recovery T2-FLAIR) to identify different tumor sub-regions (enhancing tumor ET, peritumoral edema ED and necrosis NEC), compute their respective volumes, alongside the bidimensional diameters according to the Response Assessment in Neuro-Oncology (RANO) for the active parts of the tumor.”