Recent advances in photoacoustic blind source spectral unmixing approaches and the enhanced detection of endogenous tissue chromophores

Abstract

Recently, the development of learning-based algorithms has shown a crucial role to extract features of vital importance from multi-spectral photoacoustic imaging. In particular, advances in spectral photoacoustic unmixing algorithms can identify tissue biomarkers without a priori information. This has the potential to enhance the diagnosis and treatment of a large number of diseases. Here, we investigated the latest progress within spectral photoacoustic unmixing approaches. We evaluated the sensitivity of different unsupervised Blind Source Separation (BSS) techniques such as Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Non-negative Matrix Factorization (NNMF) to distinguish absorbers from spectral photoacoustic imaging. Besides, the performance of a recently developed superpixel photoacoustic unmixing (SPAX) framework has been also examined in detail. Near-infrared spectroscopy (NIRS) has been used to validate the performance of the different unmixing algorithms. Although the NNMF has shown superior unmixing performance than PCA and ICA in terms of correlation and processing time, this is still prone to unmixing misinterpretation due to spectral coloring artifact. Thus, the SPAX framework, which also compensates for the spectral coloring effect, has shown improved sensitivity and specificity of the unmixed components. In addition, the SPAX also reveals the most and less prominent tissue components from sPAI at a volumetric scale in a data-driven way. Phantom experimental measurements and in vivo studies have been conducted to benchmark the performance of the BSS algorithms and the SPAX framework.

Multispectral optoacoustic tomography of the human intestine – temporal precision and the influence of postprandial gastrointestinal blood flow

“…The greater variation of spectrally unmixed HbT compared to single wavelength 800 nm might be attributed to corruption in spectral unmixing reasoned by wavelength-dependent fluence attenuation in deep tissue OAI [2] . In humans, tissue and disease-related spectral signatures are largely unknow and might interfere with supervised spectral unmixing [19] .…”

“…Furthermore, capturing of dedicated exogenous chromophores by spectral unmixing, such as indocyanine green, opens up completely new areas of applications [20] . However, for better understanding of spectral coloring in human deep tissue, larger clinical datasets are needed, to explore advanced depth correction or to apply blind source spectral unmixing methods [19] , [21] , [22] , [23] . To facilitate the latter analysis in research collaborations, studies should be performed according to guidelines in the field [24] , [25] and adhere to the recommendations of the International Photoacoustic Standardization Consortium (IPASC) [26] .…”

Near-Infrared Spectroscopy for the In Vivo Monitoring of Biodegradable Implants in Rats

“…NIR light is estimated to reach a 3–3.5 mm depth, and the diffuse light is detected by the optical fiber inside the probe [ 29 , 42 ]. The same optical probe was recently used to validate the spectral absorption curves obtained from USPA [ 43 ]. As shown in Figure 5 , we have used the molar extinction coefficient values to estimate the change in Hb and HbO 2 using an optical probe developed at Oslo Metropolitan University, Oslo, Norway [ 29 ].…”

Evaluation of multispectral unmixing algorithm for HbO2 and HbR

“…al. has presented a thorough survey of the algorithms used in sPAT [14,15]. The most used unmixing algorithm in sPAT which belong the supervised such as SF and unsupervised unmixing class like PCA, ICA and NNMF of algorithm.…”