Share Email Print
cover

Proceedings Paper

Classification of tumor signatures from electrosurgical vapors using mass spectrometry and machine learning: a feasibility study
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

PURPOSE: The iKnife is a new surgical tool designed to aid in tumor resection procedures by providing enriched chemical feedback about the tumor resection cavity from electrosurgical vapors. We build and compare machine learning classifiers that are capable of distinguishing primary cancer from surrounding tissue at different stages of tumor progression. In developing our classification framework, we implement feature reduction and recognition tools that will assist in the translation of xenograft studies to clinical application and compare these tools to standard linear methods that have been previously demonstrated. METHODS: Two cohorts (n=6 each) of 12 week old female immunocompromised (Rag2−/−;Il2rg−/−) mice were injected with the same human breast adenocarcinoma (MDA-MB-231) cell line. At 4 and 6 weeks after cell injection, mice in each cohort were respectively euthanized, followed by iKnife burns performed on tumors and tissues prior to sample collection for future studies. A feature reduction technique that uses a neural network is compared to traditional linear analysis. For each method, we fit a classifier to distinguish primary cancer from surrounding tissue. RESULTS: Both classifiers can distinguish primary cancer from metastasis and surrounding tissue. The classifier that uses a neural network achieves an accuracy of 96.8% and the classifier without the neural network achieves an accuracy of 96%. CONCLUSIONS: The performance of these classifiers indicate that this device has the potential to offer real-time, intraoperative classification of tissue. This technology may be used to assist in intraoperative margin detection and inform surgical decisions to offer a better standard of care for cancer patients.

Paper Details

Date Published: 16 March 2020
PDF: 9 pages
Proc. SPIE 11315, Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling, 113150Q (16 March 2020); doi: 10.1117/12.2549343
Show Author Affiliations
Laura Connolly, Lab. for Percutaneous Surgery, Queen's Univ. (Canada)
Amoon Jamzad, Medical Informatics Lab., Queen's Univ. (Canada)
Martin Kaufmann, Lab. for Percutaneous Surgery, Queen's Univ. (Canada)
Rachel Rubino, Nicol Lab., Queen’s Univ. (Canada)
Alireza Sedghi, Medical Informatics Lab., Queen's Univ. (Canada)
Tamas Ungi, Lab. for Percutaneous Surgery, Queen's Univ. (Canada)
Mark Asselin, Lab. for Percutaneous Surgery, Queen's Univ. (Canada)
Scott Yam, Queen's Univ. (Canada)
John Rudan, Department of Surgery, Queen’s Univ. (Canada)
Christopher Nicol, Nicol Lab., Queen’s Univ. (Canada)
Gabor Fichtinger, Lab. for Percutaneous Surgery, Queen's Univ. (Canada)
Parvin Mousavi, Medical Informatics Lab., Queen's Univ. (Canada)


Published in SPIE Proceedings Vol. 11315:
Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling
Baowei Fei; Cristian A. Linte, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray