Surgical Aid Visualization System for Glioblastoma Identification based on Deep Learning and I
Sala de Juntas, Edificio Politécnico
Wednesday January 30, 2019

"Surgical Aid Visualization System for Glioblastoma Tumor Identification based on Deep Learning and In-Vivo Hyperspectral Images of Human Patients"

 

Himar A. Fabelo, BEng, MSc

Research Fellow

Universidad de Las Palmas de Gran Canaria (ULPGC)

Research Institute for Applied Microelectronics

 30 de enero, 12:30h. 

Cancer is a leading cause of mortality worldwide. In particular, brain tumor is one of the most deadly forms of cancer, while high-grade malignant glioma being the most common form of all brain and central nervous system tumors. Within these malignant gliomas, glioblastoma (GBM) is the most aggressive and invasive type. Traditional diagnoses of brain tumors are based on excisional biopsy followed by histology. They are invasive with potential side effects and complications. In addition, the diagnostic information is not available in real-time during the surgical procedure since the tissue needs to be processed in a pathological laboratory. The importance of complete resection for low-grade tumors has been reported and it has proven to be beneficial, especially in pediatric cases. Although other techniques, such as computed tomography (CT), may be able to image the brain, they cannot be used in real time during surgical operation without significantly affecting the course of the procedure. In this sense, hyperspectral imaging arises as a non-invasive, non-ionizing and real-time potential solution that allows precise detection of malignant tissue boundaries, while assisting guidance for diagnosis during surgical interventions and treatment.

 

Several works have investigated the classification and delineation of the tumor boundaries using hyperspectral imaging and traditional machine learning algorithms. In particular, head and neck cancer were extensively investigated using quantitative HSI to detect and delineate the tumor boundaries in in-vivo animal samples using machine learning techniques and in ex-vivo human samples using deep learning techniques. In case of brain tumors, quantitative and qualitative hyperspectral imaging analyses were accomplished with the goal of delineate the tumor boundaries by employing both the spatial and spectral features of hyperspectral images during the execution of the European project HELICoiD. In addition, qualitative results were also obtained intraoperatively by performing an inter-patient validation using ML algorithms.

 

The latest research performed in this field involves the use of deep learning architectures and the creation of a surgical aid visualization system capable of identifying and detecting the boundaries of brain tumors during surgical procedures using in-vivo human brain hyperspectral images. This tool could assist neurosurgeons in the future in the critical task of identifying cancer tissue during brain surgeries.