Deep learning assisted classification of spectral photoacoustic imaging of carotid plaques

Camilo Cano; Nastaran Mohammadian Rad; Amir Gholampour; Marc van Sambeek; Josien Pluim; Richard Lopata; Min Wu

doi:10.1016/j.pacs.2023.100544

Deep learning assisted classification of spectral photoacoustic imaging of carotid plaques

Photoacoustics. 2023 Aug 16:33:100544. doi: 10.1016/j.pacs.2023.100544. eCollection 2023 Oct.

Authors

Camilo Cano¹, Nastaran Mohammadian Rad^{2

1}, Amir Gholampour¹, Marc van Sambeek^{3

1}, Josien Pluim¹, Richard Lopata¹, Min Wu¹

Affiliations

¹ Department of Biomedical Engineering, Eindhoven University of Technology, De Rondom 70, Eindhoven, the Netherlands.
² Department of Precision Medicine, Maastricht University, Minderbroedersberg 4-6, Maastricht, the Netherlands.
³ Department of Vascular Surgery, Catharina Ziekenhuis Eindhoven, Michelangelolaan 2, State Two, the Netherlands.

Abstract

Spectral photoacoustic imaging (sPAI) is an emerging modality that allows real-time, non-invasive, and radiation-free assessment of tissue, benefiting from their optical contrast. sPAI is ideal for morphology assessment in arterial plaques, where plaque composition provides relevant information on plaque progression and its vulnerability. However, since sPAI is affected by spectral coloring, general spectroscopy unmixing techniques cannot provide reliable identification of such complicated sample composition. In this study, we employ a convolutional neural network (CNN) for the classification of plaque composition using sPAI. For this study, nine carotid endarterectomy plaques were imaged and were then annotated and validated using multiple histological staining. Our results show that a CNN can effectively differentiate constituent regions within plaques without requiring fluence or spectra correction, with the potential to eventually support vulnerability assessment in plaques.

Keywords: Carotid plaque; Convolutional neural network; Spectral photoacoustic imaging.