Deep-learning-based separation of shallow and deep layer blood flow rates in diffuse correlation spectroscopy

Mikie Nakabayashi; Siwei Liu; Nawara Mahmood Broti; Masashi Ichinose; Yumie Ono

doi:10.1364/BOE.498693

Deep-learning-based separation of shallow and deep layer blood flow rates in diffuse correlation spectroscopy

Biomed Opt Express. 2023 Sep 21;14(10):5358-5375. doi: 10.1364/BOE.498693. eCollection 2023 Oct 1.

Authors

Mikie Nakabayashi¹, Siwei Liu¹, Nawara Mahmood Broti¹, Masashi Ichinose², Yumie Ono³

Affiliations

¹ Electrical Engineering Program, Graduate School of Science and Technology, Meiji University, 1-1-1 Higashi-Mita, Tama-ku, Kawasaki, Kanagawa, 2148571, Japan.
² Human Integrative Physiology Laboratory, School of Business Administration, Meiji University,1-1 Surugadai, Kanda, Chiyoda-ku, Tokyo,1018301, Japan.
³ Department of Electronics and Bioinformatics, School of Science and Technology, Meiji University, 1-1-1 Higashi-Mita, Tama-ku, Kawasaki, Kanagawa, 2148571, Japan.

Abstract

Diffuse correlation spectroscopy faces challenges concerning the contamination of cutaneous and deep tissue blood flow. We propose a long short-term memory network to directly quantify the flow rates of shallow and deep-layer tissues. By exploiting the different contributions of shallow and deep-layer flow rates to auto-correlation functions, we accurately predict the shallow and deep-layer flow rates (RMSE = 0.047 and 0.034 ml/min/100 g of simulated tissue, R² = 0.99 and 0.99, respectively) in a two-layer flow phantom experiment. This approach is useful in evaluating the blood flow responses of active muscles, where both cutaneous and deep-muscle blood flow increase with exercise.