loading page

Deep learning analysis of mid-infrared microscopic imaging data for the diagnosis and classification of human lymphomas
  • +6
  • Philipp Zelger,
  • Andrea Brunner,
  • Bettina Zelger,
  • Ella Willenbacher,
  • Seraphin Unterberger,
  • Roland Stalder,
  • Christian Huck,
  • Wolfgang Willenbacher,
  • Johannes Pallua
Philipp Zelger
Medical University of Innsbruck
Author Profile
Andrea Brunner
Medical University of Innsbruck
Author Profile
Bettina Zelger
Medical University of Innsbruck
Author Profile
Ella Willenbacher
Medizinische Universität Innsbruck
Author Profile
Seraphin Unterberger
Leopold Franzens Universität für Innsbruck
Author Profile
Roland Stalder
Leopold Franzens Universität für Innsbruck
Author Profile
Christian Huck
Author Profile
Wolfgang Willenbacher
Medizinische Universität Innsbruck
Author Profile
Johannes Pallua
Medical University of Innsbruck

Corresponding Author:johannes.pallua@i-med.ac.at

Author Profile

Abstract

The present study presents an alternative analytical workflow that combines mid-infrared (MIR) microscopic imaging and deep learning to diagnose human lymphoma and differentiate between small and large cell lymphoma. We could show that using a deep learning approach to analyze MIR hyperspectral data obtained from benign and malignant lymph node pathology results in high accuracy for correct classification, learning the distinct region of 3900 cm-1 to 850 cm-1. The accuracy is above 95% for every pair of malignant lymphoid tissue and still above 90% for the distinction between benign and malignant lymphoid tissue for binary classification. These results demonstrate that a preliminary diagnosis and subtyping of human lymphoma could be streamlined by applying a deep learning approach to analyze MIR spectroscopic data.
18 Jan 2023Submitted to Journal of Biophotonics
18 Jan 2023Submission Checks Completed
18 Jan 2023Assigned to Editor
18 Jan 2023Review(s) Completed, Editorial Evaluation Pending
18 Jan 2023Reviewer(s) Assigned
04 Mar 2023Editorial Decision: Revise Major
30 May 20231st Revision Received
30 May 2023Reviewer(s) Assigned
30 May 2023Submission Checks Completed
30 May 2023Assigned to Editor
30 May 2023Review(s) Completed, Editorial Evaluation Pending
03 Jul 2023Editorial Decision: Revise Major
19 Jul 20232nd Revision Received
19 Jul 2023Submission Checks Completed
19 Jul 2023Assigned to Editor
19 Jul 2023Reviewer(s) Assigned
19 Jul 2023Review(s) Completed, Editorial Evaluation Pending
09 Aug 2023Editorial Decision: Accept