Visual representation learning for brain tumor classification

Abstract

Independent subspace analysis (ISA) is used to learn (42) filter kernels for CLE images in brain tumor classification. Convolution (46) and stacking are used for unsupervised learning (44, 48) with ISA to derive the filter kernels. A classifier is trained (56) to classify CLE brain images based on features extracted using the filter kernels. The resulting filter kernels and trained classifier areused (60, 64) to assist in diagnosis of occurrence of brain tumors during or as part of neurosurgical resection. The classification may assist a physician in detecting whether CLE examined brain tissue is healthy or not and/or a type of tumor.

Description

[0001] related application [0002] Pursuant to 35 U.S.C. §119(e), this patent document claims the benefit of Provisional U.S. Patent Application Serial No. 62 / 200,678, filed on the filing date of August 4, 2015, which is hereby incorporated by reference middle. Background technique [0003] This embodiment relates to classification of images of brain tumors. Confocal laser endoscopy (CLE) is an alternative to in vivo imaging techniques for examining tumors in brain tissue. CLE allows real-time examination of body tissue on a scale previously only possible on tissue slices. Neurosurgical resection was one of the early adopters of this technique, where the task is to manually identify tumors within the human brain (eg, in the dura mater, occipital cortex, parietal cortex, or other locations) using probes or endoscopy. However, given the current nascent state of the technology, this task can be very time-consuming and error-prone. [0004] In addition, there is an increasing...

AI Technical Summary

Problems solved by technology

However, the classification accuracy was lower than expected

Images