Deep learning-based quantitative optoacoustic tomography of deep tissues in the absence of labeled experimental data

Jiao Li, Cong Wang, Tingting Chen, Tong Lu, Shuai Li, Biao Sun, Feng Gao, Vasilis Ntziachristos

Research output: Contribution to journalArticlepeer-review

26 Scopus citations

Abstract

Deep learning (DL) shows promise for quantitating anatomical features and functional parameters of tissues in quantitative optoacoustic tomography (QOAT), but its application to deep tissue is hindered by a lack of ground truth data. We propose DL-based "QOAT-Net,"which functions without labeled experimental data: A dual-path convolutional network estimates absorption coefficients after training with data-label pairs generated via unsupervised "simulation-to-experiment"data translation. In simulations, phantoms, and ex vivo and in vivo tissues, QOAT-Net affords quantitative absorption images with high spatial resolution. This approach makes DL-based QOAT and other imaging applications feasible in the absence of ground truth data.

Original languageEnglish
Pages (from-to)32-41
Number of pages10
JournalOptica
Volume9
Issue number1
DOIs
StatePublished - 20 Jan 2022

Fingerprint

Dive into the research topics of 'Deep learning-based quantitative optoacoustic tomography of deep tissues in the absence of labeled experimental data'. Together they form a unique fingerprint.

Cite this