Deep Learning-Based Framework for In Vivo Identification of Glioblastoma Tumor using Hyperspectral Images of Human Brain.

Himar Fabelo,Mariano Márquez,David Carrera,Sara Bisshopp,María Hernández,Roberto Sarmiento,Aruma O’Shanahan,Jesús Morera,Carlos Espino,Baowei Fei,Samuel Ortega,Coralia Sosa,Gustavo Callico,Adam Szolna,Maysam Shahedi,Martin Halicek,Juan Piñeiro

doi:10.3390/s19040920

Abstract

The main goal of brain cancer surgery is to perform an accurate resection of the tumor, preserving as much normal brain tissue as possible for the patient. The development of a non-contact and label-free method to provide reliable support for tumor resection in real-time during neurosurgical procedures is a current clinical need. Hyperspectral imaging is a non-contact, non-ionizing, and label-free imaging modality that can assist surgeons during this challenging task without using any contrast agent. In this work, we present a deep learning-based framework for processing hyperspectral images of in vivo human brain tissue. The proposed framework was evaluated by our human image database, which includes 26 in vivo hyperspectral cubes from 16 different patients, among which 258,810 pixels were labeled. The proposed framework is able to generate a thematic map where the parenchymal area of the brain is delineated and the location of the tumor is identified, providing guidance to the operating surgeon for a successful and precise tumor resection. The deep learning pipeline achieves an overall accuracy of 80% for multiclass classification, improving the results obtained with traditional support vector machine (SVM)-based approaches. In addition, an aid visualization system is presented, where the final thematic map can be adjusted by the operating surgeon to find the optimal classification threshold for the current situation during the surgical procedure.

Highlights

Cancer is a leading cause of mortality worldwide [1]
We present the hyperspectral imaging imaging (HSI) instrumentation that is employed to obtain the in vivo HS brain cancer image database, the deep learning techniques and the proposed pipeline that is developed in this work, the support vector machine (SVM)-based approaches that have been used for the comparison of the results, and the validation metrics that have been employed for this comparison
The work presented in this paper employs deep learning techniques for the detection of in vivo brain tumors using intraoperative hyperspectral imaging

Summary

Introduction

Brain tumor is one of the most deadly forms of cancer, while high-grade malignant glioma is the most common form (~30%) of all brain and central nervous system tumors [2]. Within these malignant gliomas, glioblastoma (GBM) is the most aggressive and invasive type, accounting for 55% of these cases [3,4]. A 2D convolutional neural network (2D-CNN) classifier, which was selected because of its ability to incorporate both spectral and spatial components for machine learning, was implemented in a batch-based training approach using the TensorFlow open-source software library [46] on a. Gradient optimization was applied to the AdaDelta optimizer with a learning rate of 1.0 and with 200 and 50 epochs for the training data in the binary and multiclass classification, respectively

Objectives

Methods

Findings

Discussion

Conclusion