Perioperative margin detection in basal cell carcinoma using a deep learning framework: a feasibility study
- PDF / 1,515,934 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 27 Downloads / 184 Views
ORIGINAL ARTICLE
Perioperative margin detection in basal cell carcinoma using a deep learning framework: a feasibility study Alice M. L. Santilli1 · Amoon Jamzad1 · Natasja N. Y. Janssen1 · Martin Kaufmann2 · Laura Connolly1 · Kaitlin Vanderbeck3 · Ami Wang3 · Doug McKay4 · John F. Rudan4 · Gabor Fichtinger1 · Parvin Mousavi1 Received: 18 November 2019 / Accepted: 31 March 2020 © CARS 2020
Abstract Purpose Basal cell carcinoma (BCC) is the most commonly diagnosed cancer and the number of diagnosis is growing worldwide due to increased exposure to solar radiation and the aging population. Reduction of positive margin rates when removing BCC leads to fewer revision surgeries and consequently lower health care costs, improved cosmetic outcomes and better patient care. In this study, we propose the first use of a perioperative mass spectrometry technology (iKnife) along with a deep learning framework for detection of BCC signatures from tissue burns. Methods Resected surgical specimen were collected and inspected by a pathologist. With their guidance, data were collected by burning regions of the specimen labeled as BCC or normal, with the iKnife. Data included 190 scans of which 127 were normal and 63 were BCC. A data augmentation approach was proposed by modifying the location and intensity of the peaks of the original spectra, through noise addition in the time and frequency domains. A symmetric autoencoder was built by simultaneously optimizing the spectral reconstruction error and the classification accuracy. Using t-SNE, the latent space was visualized. Results The autoencoder achieved an accuracy (standard deviation) of 96.62 (1.35%) when classifying BCC and normal scans, a statistically significant improvement over the baseline state-of-the-art approach used in the literature. The t-SNE plot of the latent space distinctly showed the separability between BCC and normal data, not visible with the original data. Augmented data resulted in significant improvements to the classification accuracy of the baseline model. Conclusion We demonstrate the utility of a deep learning framework applied to mass spectrometry data for surgical margin detection. We apply the proposed framework to an application with light surgical overhead and high incidence, the removal of BCC. The learnt models can accurately separate BCC from normal tissue. Keywords Surgical margin detection · Rapid evaporative ionization mass spectrometry · Intraoperative tissue characterization · Non-linear analysis · Autoencoder · Basal cell carcinoma
Introduction
B
Alice M. L. Santilli [email protected]
1
School of Computing, Queen’s University, Kingston, ON, Canada
2
Department of Medicine, Queen’s University, Kingston, ON, Canada
3
Department of Pathology, Queen’s University, Kingston, ON, Canada
4
Department of Surgery, Queen’s University, Kingston, ON, Canada
Basal cell carcinoma (BCC) is the most commonly diagnosed cancer, involving 60 000 Canadians in 2014 [1]. This number is increasing every year due to an increased exposure to solar ra
Data Loading...
