Towards an Efficient Computational Framework for Guiding Surgical Resection through Intra-operative Endo-microscopic Pat
Precise detection and surgical resection of the tumors during an operation greatly increases the chance of the overall procedure efficacy. Emerging experimental in-vivo imaging technologies such as Confocal Laser Endomicroscopy (CLE), could potentially as
- PDF / 1,132,132 Bytes
- 9 Pages / 439.363 x 666.131 pts Page_size
- 13 Downloads / 179 Views
3
Siemens Corporation, Corporate Technology, Princeton, NJ, USA 2 Siemens AG, Corporate Technology, Munich, Germany Department of Neurosurgery, Hospital Merheim, Cologne Medical Center, Germany
Abstract. Precise detection and surgical resection of the tumors during an operation greatly increases the chance of the overall procedure efficacy. Emerging experimental in-vivo imaging technologies such as Confocal Laser Endomicroscopy (CLE), could potentially assist surgeons to examine brain tissues on histological scale in real-time during the operation. However, it is a challenging task for neurosurgeons to interpret these images in real-time, primarily due to the low signal to noise ratio and variability in the patterns expressed within these images by various examined tissue types. In this paper, we present a comprehensive computational framework capable of automatic brain tumor classification in real-time. Specifically, our contributions include: (a) an end-to-end computational pipeline where a variety of the feature extraction methods, encoding schemes, and classification algorithms can be readily deployed, (b) thorough evaluation of state-ofthe-art low-level image features and popular encoding techniques in context of CLE imagery, and finally, (c) A highly optimized feature pooling method based on codeword proximity. The proposed system can effectively classify two types of commonly diagnosed brain tumors in CLE sequences captured in real-time with close to 90% accuracy. Extensive experiments on a dataset of 117 videos demonstrate the efficacy of our system.
1 Introduction Glioblastoma is the most predominant and most aggressive malignant brain tumor in humans that accounts for 52% of all brain tumor cases and 20% of all intracranial tumors [1]. Meningioma, on the other hand, although benign, accounts for more than 35% of primary brain tumors in the US, and occurs in approximately 7 of every 100, 000 people [2, 3], with an approximate 5 year survival time-line of the diagnosed patient. Optimal surgical resection is primarily based on accurate detection of tumor tissue during the surgical resection. Recently, Confocal Laser Endomicroscopy (CLE) [4] has emerged as a promising invivo imaging technology that allows real-time examination of body tissues on a scale
Shaohua Wan (from University of Texas at Austin, Austin, TX, US) contributed to this work during his internship at Siemens Corporation, Corporate Technology, Princeton, NJ, USA.
c Springer International Publishing Switzerland 2015 N. Navab et al. (Eds.): MICCAI 2015, Part I, LNCS 9349, pp. 421–429, 2015. DOI: 10.1007/978-3-319-24553-9_52
422
S. Wan et al.
that was previously only possible on histologic slices. Neurosurgeons could now use CLE as a surgical guidance tool for brain tumors. However, as a manual examination task, this can be highly time-consuming and error-prone. Thus, there has been an increasing demand in employing computer vision techniques for brain tumor tissue typing and pathology in the CLE probing process.
(a) Glioblastoma, th
Data Loading...
