Molecular imaging of pulmonary diseases

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.

From Pixels to Pathology: Employing Computer Vision to Decode Chest Diseases in Medical Images

Radiology has been a pioneer in the healthcare industry's digital transformation, incorporating digital imaging systems like picture archiving and communication system (PACS) and teleradiology over the past thirty years. This shift has reshaped radiology services, positioning the field at a crucial junction for potential evolution into an integrated diagnostic service through artificial intelligence and machine learning. These technologies offer advanced tools for radiology's transformation. The radiology community has advanced computer-aided diagnosis (CAD) tools using machine learning techniques, notably deep learning convolutional neural networks (CNNs), for medical image pattern recognition. However, the integration of CAD tools into clinical practice has been hindered by challenges in workflow integration, unclear business models, and limited clinical benefits, despite development dating back to the 1990s. This comprehensive review focuses on detecting chest-related diseases through techniques like chest X-rays (CXRs), magnetic resonance imaging (MRI), nuclear medicine, and computed tomography (CT) scans. It examines the utilization of computer-aided programs by researchers for disease detection, addressing key areas: the role of computer-aided programs in disease detection advancement, recent developments in MRI, CXR, radioactive tracers, and CT scans for chest disease identification, research gaps for more effective development, and the incorporation of machine learning programs into diagnostic tools.

Artificial intelligence in functional imaging of the lung

Artificial intelligence (AI) is transforming the way we perform advanced imaging. From high-resolution image reconstruction to predicting functional response from clinically acquired data, AI is promising to revolutionize clinical evaluation of lung performance, pushing the boundary in pulmonary functional imaging for patients suffering from respiratory conditions. In this review, we overview the current developments and expound on some of the encouraging new frontiers. We focus on the recent advances in machine learning and deep learning that enable reconstructing images, quantitating, and predicting functional responses of the lung. Finally, we shed light on the potential opportunities and challenges ahead in adopting AI for functional lung imaging in clinical settings.

COVID-Classifier: an automated machine learning model to assist in the diagnosis of COVID-19 infection in chest X-ray images

Chest-X ray (CXR) radiography can be used as a first-line triage process for non-COVID-19 patients with pneumonia. However, the similarity between features of CXR images of COVID-19 and pneumonia caused by other infections makes the differential diagnosis by radiologists challenging. We hypothesized that machine learning-based classifiers can reliably distinguish the CXR images of COVID-19 patients from other forms of pneumonia. We used a dimensionality reduction method to generate a set of optimal features of CXR images to build an efficient machine learning classifier that can distinguish COVID-19 cases from non-COVID-19 cases with high accuracy and sensitivity. By using global features of the whole CXR images, we successfully implemented our classifier using a relatively small dataset of CXR images. We propose that our COVID-Classifier can be used in conjunction with other tests for optimal allocation of hospital resources by rapid triage of non-COVID-19 cases.

Optical Biosensors for Virus Detection: Prospects for SARS-CoV-2/COVID-19

The recent pandemic of the novel coronavirus disease 2019 (COVID-19) has caused huge worldwide disruption due to the lack of available testing locations and equipment. The use of optical techniques for viral detection has flourished in the past 15 years, providing more reliable, inexpensive, and accurate detection methods. In the current minireview, optical phenomena including fluorescence, surface plasmons, surface-enhanced Raman scattering (SERS), and colorimetry are discussed in the context of detecting virus pathogens. The sensitivity of a viral detection method can be dramatically improved by using materials that exhibit surface plasmons or SERS, but often this requires advanced instrumentation for detection. Although fluorescence and colorimetry lack high sensitivity, they show promise as point-of-care diagnostics because of their relatively less complicated instrumentation, ease of use, lower costs, and the fact that they do not require nucleic acid amplification. The advantages and disadvantages of each optical detection method are presented, and prospects for applying optical biosensors in COVID-19 detection are discussed.

Imaging of dopamine transporters in Parkinson disease: a meta-analysis of 18 F/123 I-FP-CIT studies

OBJECTIVE

¹⁸ F-FP-CIT and ¹²³ I-FP-CIT are widely used radiotracers in molecular imaging for Parkinson's disease (PD) diagnosis. Compared with ¹²³ I-FP-CIT, ¹⁸ F-FP-CIT has superior tracer kinetics. We aimed to conduct a meta-analysis to assess the efficacy of using ¹⁸ F-FP-CIT positron emission tomography (PET) and ¹²³ I-FP-CIT single-photon emission computed tomography (SPECT) of dopamine transporters in patients with PD in order to provide evidence for clinical decision-making.

METHODS

We searched the PubMed, Embase, Wanfang Data, and China National Knowledge Infrastructure databases to identify the relevant studies from the time of inception of the databases to 30 April 2020. We identified six PET studies, including 779 patients with PD and 124 healthy controls, which met the inclusion criteria. Twenty-seven SPECT studies with 1244 PD patients and 859 controls were also included in this meta-analysis.

RESULTS

Overall effect-size analysis indicated that patients with PD showed significantly reduced ¹⁸ F-FP-CIT uptake in three brain regions [caudate nucleus: standardized mean difference (SMD) = -1.71, Z = -3.31, P = 0.0009; anterior putamen: SMD = -3.71, Z = -6.26, P < 0.0001; and posterior putamen: SMD = -5.49, Z = -5.97, P < 0.0001]. Significant decreases of ¹²³ I-FP-CIT uptake were also observed in the caudate (SMD = -2.31, Z = -11.49, P < 0.0001) and putamen (SMD = -3.25, Z = -14.79, P < 0.0001).

INTERPRETATION

In conclusion, our findings indicate that both ¹⁸ F-FP-CIT PET and ¹²³ I-FP-CIT SPECT imaging of dopamine transporters can provide viable biomarkers for early PD diagnosis.

Current Applications for Nuclear Medicine Imaging in Pulmonary Disease

Purpose of Review

The main goal of the article is to familiarize the reader with commonly and uncommonly used nuclear medicine procedures that can significantly contribute to improved patient care. The article presents examples of specific modality utilization in the chest including assessment of lung ventilation and perfusion, imaging options for broad range of infectious and inflammatory processes, and selected aspects of oncologic imaging. In addition, rapidly developing new techniques utilizing molecular imaging are discussed.

Recent Findings

The article describes nuclear medicine imaging modalities including gamma camera, SPECT, PET, and hybrid imaging (SPECT/CT, PET/CT, and PET/MR) in the context of established and emerging clinical applications. Areas of potential future development in nuclear medicine are discussed with emphasis on molecular imaging and implementation of new targeted tracers used in diagnostics and therapeutics (theranostics).

Summary

Nuclear medicine and molecular imaging provide many unique and novel options for the diagnosis and treatment of pulmonary diseases. This article reviews current applications for nuclear medicine and molecular imaging and selected future applications for radiopharmaceuticals and targeted molecular imaging techniques.

COVID-Classifier: An automated machine learning model to assist in the diagnosis of COVID-19 infection in chest x-ray images

Chest-X ray (CXR) radiography can be used as a first-line triage process for non-COVID-19 patients with pneumonia. However, the similarity between features of CXR images of COVID-19 and pneumonia caused by other infections make the differential diagnosis by radiologists challenging. We hypothesized that machine learning-based classifiers can reliably distinguish the CXR images of COVID-19 patients from other forms of pneumonia. We used a dimensionality reduction method to generate a set of optimal features of CXR images to build an efficient machine learning classifier that can distinguish COVID-19 cases from non-COVID-19 cases with high accuracy and sensitivity. By using global features of the whole CXR images, we were able to successfully implement our classifier using a relatively small dataset of CXR images. We propose that our COVID-Classifier can be used in conjunction with other tests for optimal allocation of hospital resources by rapid triage of non-COVID-19 cases.

Molecular Imaging of Pulmonary Inflammation and Infection

Infectious and inflammatory pulmonary diseases are a leading cause of morbidity and mortality worldwide. Although infrequently used in this setting, molecular imaging may significantly contribute to their diagnosis using techniques like single photon emission tomography (SPET), positron emission tomography (PET) with computed tomography (CT) or magnetic resonance imaging (MRI) with the support of specific or unspecific radiopharmaceutical agents. ¹⁸F-Fluorodeoxyglucose (¹⁸F-FDG), mostly applied in oncological imaging, can also detect cells actively involved in infectious and inflammatory conditions, even if with a low specificity. SPET with nonspecific (e.g., ⁶⁷Gallium-citrate (⁶⁷Ga citrate)) and specific tracers (e.g., white blood cells radiolabeled with ¹¹¹Indium-oxine (¹¹¹In) or ^99mTechnetium (^99mTc)) showed interesting results for many inflammatory lung diseases. However, ⁶⁷Ga citrate is unfavorable by a radioprotection point of view while radiolabeled white blood cells scan implies complex laboratory settings and labeling procedures. Radiolabeled antibiotics (e.g., ciprofloxacin) have been recently tested, although they seem to be quite unspecific and cause antibiotic resistance. New radiolabeled agents like antimicrobic peptides, binding to bacterial cell membranes, seem very promising. Thus, the aim of this narrative review is to provide a comprehensive overview about techniques, including PET/MRI, and tracers that can guide the clinicians in the appropriate diagnostic pathway of infectious and inflammatory pulmonary diseases.

Imaging the Injured Lung: Mechanisms of Action and Clinical Use

Acute respiratory distress syndrome (ARDS) consists of acute hypoxemic respiratory failure characterized by massive and heterogeneously distributed loss of lung aeration caused by diffuse inflammation and edema present in interstitial and alveolar spaces. It is defined by consensus criteria, which include diffuse infiltrates on chest imaging-either plain radiography or computed tomography. This review will summarize how imaging sciences can inform modern respiratory management of ARDS and continue to increase the understanding of the acutely injured lung. This review also describes newer imaging methodologies that are likely to inform future clinical decision-making and potentially improve outcome. For each imaging modality, this review systematically describes the underlying principles, technology involved, measurements obtained, insights gained by the technique, emerging approaches, limitations, and future developments. Finally, integrated approaches are considered whereby multimodal imaging may impact management of ARDS.

Role of medical and molecular imaging in COPD

Chronic obstructive pulmonary disease (COPD) is expected to climb on the podium of the leading causes of mortality worldwide in the upcoming decade. Clinical diagnosis of COPD has classically relied upon detecting irreversible airflow obstruction on pulmonary function testing as a global assessment of pulmonary physiology. However, the outcome is still not favorable to decrease mortality due to COPD. Progress made in both medical and molecular imaging fields are beginning to offer additional tools to address this clinical problem. This review aims to describe medical and molecular imaging modalities used to diagnose COPD and to select patients for appropriate treatments and to monitor response to therapy.