Image Quality Improvement Techniques and Assessment Adequacy in Clinical Optoacoustic Imaging: A Systematic Review

A methodical exploration of imaging modalities from dataset to detection through machine learning paradigms in prominent lung disease diagnosis: a review

BACKGROUND

Lung diseases, both infectious and non-infectious, are the most prevalent cause of mortality overall in the world. Medical research has identified pneumonia, lung cancer, and Corona Virus Disease 2019 (COVID-19) as prominent lung diseases prioritized over others. Imaging modalities, including X-rays, computer tomography (CT) scans, magnetic resonance imaging (MRIs), positron emission tomography (PET) scans, and others, are primarily employed in medical assessments because they provide computed data that can be utilized as input datasets for computer-assisted diagnostic systems. Imaging datasets are used to develop and evaluate machine learning (ML) methods to analyze and predict prominent lung diseases.

OBJECTIVE

This review analyzes ML paradigms, imaging modalities' utilization, and recent developments for prominent lung diseases. Furthermore, the research also explores various datasets available publically that are being used for prominent lung diseases.

METHODS

The well-known databases of academic studies that have been subjected to peer review, namely ScienceDirect, arXiv, IEEE Xplore, MDPI, and many more, were used for the search of relevant articles. Applied keywords and combinations used to search procedures with primary considerations for review, such as pneumonia, lung cancer, COVID-19, various imaging modalities, ML, convolutional neural networks (CNNs), transfer learning, and ensemble learning.

RESULTS

This research finding indicates that X-ray datasets are preferred for detecting pneumonia, while CT scan datasets are predominantly favored for detecting lung cancer. Furthermore, in COVID-19 detection, X-ray datasets are prioritized over CT scan datasets. The analysis reveals that X-rays and CT scans have surpassed all other imaging techniques. It has been observed that using CNNs yields a high degree of accuracy and practicability in identifying prominent lung diseases. Transfer learning and ensemble learning are complementary techniques to CNNs to facilitate analysis. Furthermore, accuracy is the most favored metric for assessment.

Optoacoustic biomarkers of lipids, hemorrhage and inflammation in carotid atherosclerosis

Imaging plays a critical role in exploring the pathophysiology and enabling the diagnostics and therapy assessment in carotid artery disease. Ultrasonography, computed tomography, magnetic resonance imaging and nuclear medicine techniques have been used to extract of known characteristics of plaque vulnerability, such as inflammation, intraplaque hemorrhage and high lipid content. Despite the plethora of available techniques, there is still a need for new modalities to better characterize the plaque and provide novel biomarkers that might help to detect the vulnerable plaque early enough and before a stroke occurs. Optoacoustics, by providing a multiscale characterization of the morphology and pathophysiology of the plaque could offer such an option. By visualizing endogenous (e.g., hemoglobin, lipids) and exogenous (e.g., injected dyes) chromophores, optoacoustic technologies have shown great capability in imaging lipids, hemoglobin and inflammation in different applications and settings. Herein, we provide an overview of the main optoacoustic systems and scales of detail that enable imaging of carotid plaques in vitro, in small animals and humans. Finally, we discuss the limitations of this novel set of techniques while investigating their potential to enable a deeper understanding of carotid plaque pathophysiology and possibly improve the diagnostics in future patients with carotid artery disease.

Development and implementation of optimized endogenous contrast sequences for delineation in adaptive radiotherapy on a 1.5T MR-linear-accelerator: a prospective R-IDEAL stage 0-2a quantitative/qualitative evaluation of in vivo site-specific quality-assurance using a 3D T2 fat-suppressed platform for head and neck cancer

Purpose

To improve segmentation accuracy in head and neck cancer (HNC) radiotherapy treatment planning for the 1.5T hybrid magnetic resonance imaging/linear accelerator (MR-Linac), three-dimensional (3D), T2-weighted, fat-suppressed magnetic resonance imaging sequences were developed and optimized.

Approach

After initial testing, spectral attenuated inversion recovery (SPAIR) was chosen as the fat suppression technique. Five candidate SPAIR sequences and a nonsuppressed, T2-weighted sequence were acquired for five HNC patients using a 1.5T MR-Linac. MR physicists identified persistent artifacts in two of the SPAIR sequences, so the remaining three SPAIR sequences were further analyzed. The gross primary tumor volume, metastatic lymph nodes, parotid glands, and pterygoid muscles were delineated using five segmentors. A robust image quality analysis platform was developed to objectively score the SPAIR sequences on the basis of qualitative and quantitative metrics.

Results

Sequences were analyzed for the signal-to-noise ratio and the contrast-to-noise ratio and compared with fat and muscle, conspicuity, pairwise distance metrics, and segmentor assessments. In this analysis, the nonsuppressed sequence was inferior to each of the SPAIR sequences for the primary tumor, lymph nodes, and parotid glands, but it was superior for the pterygoid muscles. The SPAIR sequence that received the highest combined score among the analysis categories was recommended to Unity MR-Linac users for HNC radiotherapy treatment planning.

Conclusions

Our study led to two developments: an optimized, 3D, T2-weighted, fat-suppressed sequence that can be disseminated to Unity MR-Linac users and a robust image quality analysis pathway that can be used to objectively score SPAIR sequences and can be customized and generalized to any image quality optimization protocol. Improved segmentation accuracy with the proposed SPAIR sequence will potentially lead to improved treatment outcomes and reduced toxicity for patients by maximizing the target coverage and minimizing the radiation exposure of organs at risk.

Skeletal muscle optoacoustics reveals patterns of circulatory function and oxygen metabolism during exercise

Imaging skeletal muscle function and metabolism, as reported by local hemodynamics and oxygen kinetics, can elucidate muscle performance, severity of an underlying disease or outcome of a treatment. Herein, we used multispectral optoacoustic tomography (MSOT) to image hemodynamics and oxygen kinetics within muscle during exercise. Four healthy volunteers underwent three different hand-grip exercise challenges (60s isometric, 120s intermittent isometric and 60s isotonic). During isometric contraction, MSOT showed a decrease of HbO₂, Hb and total blood volume (TBV), followed by a prominent increase after the end of contraction. Corresponding hemodynamic behaviors were recorded during the intermittent isometric and isotonic exercises. A more detailed analysis of MSOT readouts revealed insights into arteriovenous oxygen differences and muscle oxygen consumption during all exercise schemes. These results demonstrate an excellent capability of visualizing both circulatory function and oxygen metabolism within skeletal muscle under exercise, with great potential implications for muscle research, including relevant disease diagnostics.

Non-invasive multispectral optoacoustic tomography resolves intrahepatic lipids in patients with hepatic steatosis

Hepatic steatosis is characterized by intrahepatic lipid accumulation and may lead to irreversible liver damage if untreated. Here, we investigate whether multispectral optoacoustic tomography (MSOT) can offer label-free detection of liver lipid content to enable non-invasive characterization of hepatic steatosis by analyzing the spectral region around 930 nm, where lipids characteristically absorb. In a pilot study, we apply MSOT to measure liver and surrounding tissues in five patients with liver steatosis and five healthy volunteers, revealing significantly higher absorptions at 930 nm in the patients, while no significant difference was observed in the subcutaneous adipose tissue of the two groups. We further corroborated the human observations with corresponding MSOT measurements in high fat diet (HFD) - and regular chow diet (CD)-fed mice. This study introduces MSOT as a potential non-invasive and portable technique for detecting/monitoring hepatic steatosis in clinical settings, providing justification for larger studies.