Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Clear Conversations: a mixed methods evaluation of a verbal health literacy initiative for health service providers.

BMC health services research·2026
Same author

Current validation practice undermines surgical AI development.

ArXiv·2026
Same author

Shift happens: a fairness-oriented framework for medical classification under hidden bias.

International journal of computer assisted radiology and surgery·2026
Same author

GUIDE-US: grade-informed unpaired distillation of encoder knowledge from histopathology to micro-ultrasound.

International journal of computer assisted radiology and surgery·2026
Same author

Explainable transfer learning ensemble AI model for lung ultrasound pneumothorax detection with expert benchmark.

Scandinavian journal of trauma, resuscitation and emergency medicine·2026
Same author

Extracellular vesicles from aged individuals trigger mitochondrial dysfunction in haematopoietic progenitor cells.

Haematologica·2026

Related Experiment Video

Updated: Dec 23, 2025

Author Spotlight: 3D Scanning and Augmented Reality for Enhanced Cancer Surgery Communication
07:47

Author Spotlight: 3D Scanning and Augmented Reality for Enhanced Cancer Surgery Communication

Published on: December 15, 2023

1.1K

Perioperative margin detection in basal cell carcinoma using a deep learning framework: a feasibility study.

Alice M L Santilli1, Amoon Jamzad2, Natasja N Y Janssen2

  • 1School of Computing, Queen's University, Kingston, ON, Canada. 14amls@queensu.ca.

International Journal of Computer Assisted Radiology and Surgery
|April 24, 2020
PubMed
Summary
This summary is machine-generated.

This study introduces a novel deep learning framework combined with perioperative mass spectrometry (iKnife) for basal cell carcinoma (BCC) detection. The technology accurately distinguishes BCC from normal tissue, potentially reducing revision surgeries and improving patient outcomes.

Keywords:
AutoencoderBasal cell carcinomaIntraoperative tissue characterizationNon-linear analysisRapid evaporative ionization mass spectrometrySurgical margin detection

More Related Videos

Intraoperative Assessment of Resection Margins in Oral Cavity Cancer: This is the Way
04:45

Intraoperative Assessment of Resection Margins in Oral Cavity Cancer: This is the Way

Published on: May 10, 2021

4.2K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K

Related Experiment Videos

Last Updated: Dec 23, 2025

Author Spotlight: 3D Scanning and Augmented Reality for Enhanced Cancer Surgery Communication
07:47

Author Spotlight: 3D Scanning and Augmented Reality for Enhanced Cancer Surgery Communication

Published on: December 15, 2023

1.1K
Intraoperative Assessment of Resection Margins in Oral Cavity Cancer: This is the Way
04:45

Intraoperative Assessment of Resection Margins in Oral Cavity Cancer: This is the Way

Published on: May 10, 2021

4.2K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K

Area of Science:

  • Oncology
  • Biotechnology
  • Data Science

Background:

  • Basal cell carcinoma (BCC) is the most common cancer globally, with increasing incidence due to factors like increased solar radiation exposure and an aging population.
  • Minimizing positive margin rates in BCC excisions is crucial for reducing repeat surgeries, healthcare costs, and improving cosmetic results and patient care.

Purpose of the Study:

  • To investigate the first-time application of perioperative mass spectrometry technology (iKnife) integrated with a deep learning framework for detecting basal cell carcinoma (BCC) signatures.
  • To assess the efficacy of this combined approach in differentiating BCC from normal tissue during surgical procedures.

Main Methods:

  • Surgical specimens were analyzed using the iKnife, with data collected from regions identified as BCC or normal by a pathologist.
  • A dataset of 190 spectral scans (63 BCC, 127 normal) was augmented using noise addition in time and frequency domains.
  • A symmetric autoencoder was developed to optimize spectral reconstruction error and classification accuracy, with results visualized using t-SNE.

Main Results:

  • The autoencoder achieved a classification accuracy of 96.62% (±1.35%) for BCC versus normal tissue, outperforming existing state-of-the-art methods.
  • t-SNE visualization revealed clear separation between BCC and normal tissue data in the latent space, which was not apparent in the original data.
  • Data augmentation significantly improved the classification accuracy of the baseline model.

Conclusions:

  • The study demonstrates the effectiveness of a deep learning framework applied to mass spectrometry data for precise surgical margin detection in BCC removal.
  • The developed models accurately differentiate between cancerous (BCC) and healthy tissue, offering a promising tool for intraoperative decision-making.
  • This technology has the potential to enhance surgical outcomes for BCC by providing real-time tissue analysis with minimal additional surgical burden.