Search

Abstract Objective To conduct a systematic review of the computer vision applications that detect, diagnose, or analyse tuberculosis (TB) pathology or bacilli using digitised human lung tissue images either through automatic or semi-automatic methods. We categorised the computer vision platform into four technologies: image processing, object/pattern recognition, computer graphics, and deep learning. In this paper, the focus is on image processing and deep learning (DL) applications for either 2D or 3D digitised human lung tissue images. This review is useful for establishing a common practice in TB analysis using human lung tissue as well as identifying opportunities for further research in this space. The review brings attention to the state-of-art techniques for detecting TB, with emphasis on the challenges and limitations of the current techniques. The ultimate goal is to promote the development of more efficient and accurate algorithms for the detection or analysis of TB, and raise awareness about the importance of early detection. Design We searched five databases and Google Scholar for articles published between January 2017 and December 2022 that focus on Mycobacterium tuberculosis detection, or tuberculosis pathology using digitised human lung tissue images. Details regarding design, image processing and computer-aided techniques, deep learning models, and datasets were collected and summarised. Discussions, analysis, and comparisons of state-of-the-art methods are provided to help guide future research. Further, a brief update on the relevant techniques and their performance is provided. Results Several studies have been conducted to develop automated and AI-assisted methods for diagnosing Mtb and TB pathology from digitised human lung tissue images. Some studies presented a completely automated method of diagnosis, while other studies developed AI-assisted diagnostic methods. Low-level focus areas included the development of a novel $$\upmu$$ μ CT scanner for soft tissue image contract, and use of multiresolution computed tomography to analyse the 3D structure of the human lung. High-level focus areas included the investigation the effects of aging on the number and size of small airways in the lungs using CT and whole lung high-resolution $$\upmu$$ μ CT, and the 3D microanatomy characterisation of human tuberculosis lung using $$\upmu$$ μ CT in conjunction with histology and immunohistochemistry. Additionally, a novel method for acquiring high-resolution 3D images of human lung structure and topology is also presented. Conclusion The literature indicates that post 1950s, TB was predominantly studied using animal models even though no animal model reflects the full spectrum of human pulmonary TB disease and does not reproducibly transmit Mtb infection to other animals (Hunter, 2011). This explains why there are very few studies that used human lung tissue for detection or analysis of Mtb. Nonetheless, we found 10 studies that used human tissues (predominately lung) of which five studies proposed machine learning (ML) models for the detection of bacilli and the other five used CT on human lung tissue scanned ex-vivo.

Summary: Background: The ability to detect evidence of Mycobacterium tuberculosis (Mtb) infection within human tissues is critical to the study of Mtb physiology, tropism, and spatial distribution within TB lesions. The capacity of the widely-used Ziehl-Neelsen (ZN) staining method for identifying Mtb acid-fast bacilli (AFB) in tissue is highly variable, which can limit detection of Mtb bacilli for research and diagnostic purposes. Here, we sought to circumvent these limitations via detection of Mtb mRNA and secreted antigens in human tuberculous tissue. Methods: We adapted RNAscope, an RNA in situ hybridisation (RISH) technique, to detect Mtb mRNA in ante- and postmortem human TB tissues and developed a dual ZN/immunohistochemistry staining approach to identify AFB and bacilli producing antigen 85B (Ag85B). Findings: We identified Mtb mRNA within intact and disintegrating bacilli as well as extrabacillary mRNA. Mtb mRNA was distributed zonally within necrotic and non-necrotic granulomas. We also found Mtb mRNA within, and adjacent to, necrotic granulomas in ZN-negative lung tissue and in Ag85B-positive bronchiolar epithelium. Intriguingly, we observed accumulation of Mtb mRNA and Ag85B in the cytoplasm of host cells. Notably, many AFB were negative for Ag85B staining. Mtb mRNA was observed in ZN-negative antemortem lymph node biopsies. Interpretation: RNAscope and dual ZN/immunohistochemistry staining are well-suited for identifying subsets of intact Mtb and/or bacillary remnants in human tissue. RNAscope can identify Mtb mRNA in ZN-negative tissues from patients with TB and may have diagnostic potential in complex TB cases. Funding: Wellcome Leap Delta Tissue Program, Wellcome Strategic Core Award, the National Institutes of Health (NIH, USA), the Mary Heersink Institute for Global Health at UAB, the UAB Heersink School of Medicine.

Abstract Our current understanding of the spectrum of TB and COVID‐19 lesions in the human lung is limited by a reliance on low‐resolution imaging platforms that cannot provide accurate 3D representations of lesion types within the context of the whole lung. To characterize TB and COVID‐19 lesions in 3D, we applied micro/nanocomputed tomography to surgically resected, postmortem, and paraffin‐embedded human lung tissue. We define a spectrum of TB pathologies, including cavitary lesions, calcium deposits outside and inside necrotic granulomas and mycetomas, and vascular rearrangement. We identified an unusual spatial arrangement of vasculature within an entire COVID‐19 lobe, and 3D segmentation of blood vessels revealed microangiopathy associated with hemorrhage. Notably, segmentation of pathological anomalies reveals hidden pathological structures that might otherwise be disregarded, demonstrating a powerful method to visualize pathologies in 3D in TB lung tissue and whole COVID‐19 lobes. These findings provide unexpected new insight into the spatial organization of the spectrum of TB and COVID‐19 lesions within the framework of the entire lung.

Polygenic Risk Score (PRS) analysis is a method that predicts the genetic risk of an individual towards targeted traits. Even when there are no significant markers, it gives evidence of a genetic effect beyond the results of Genome-Wide Association Studies (GWAS). Moreover, it selects single nucleotide polymorphisms (SNPs) that contribute to the disease with low effect size making it more precise at individual level risk prediction. PRS analysis addresses the shortfall of GWAS by taking into account the SNPs/alleles with low effect size but play an indispensable role to the observed phenotypic/trait variance. PRS analysis has applications that investigate the genetic basis of several traits, which includes rare diseases. However, the accuracy of PRS analysis depends on the genomic data of the underlying population. For instance, several studies show that obtaining higher prediction power of PRS analysis is challenging for non-Europeans. In this manuscript, we review the conventional PRS methods and their application to sub-Saharan African communities. We conclude that lack of sufficient GWAS data and tools is the limiting factor of applying PRS analysis to sub-Saharan populations. We recommend developing Africa-specific PRS methods and tools for estimating and analyzing African population data for clinical evaluation of PRSs of interest and predicting rare diseases.

Polygenic Risk Score (PRS) analysis is a method that predicts the genetic risk of an individual towards targeted traits. Even when there are no significant markers, it gives evidence of a genetic effect beyond the results of Genome-Wide Association Studies (GWAS). Moreover, it selects single nucleotide polymorphisms (SNPs) that contribute to the disease with low effect size making it more precise at individual level risk prediction. PRS analysis addresses the shortfall of GWAS by taking into account the SNPs/alleles with low effect size but play an indispensable role to the observed phenotypic/trait variance. PRS analysis has applications that investigate the genetic basis of several traits, which includes rare diseases. However, the accuracy of PRS analysis depends on the genomic data of the underlying population. For instance, several studies show that obtaining higher prediction power of PRS analysis is challenging for non-Europeans. In this manuscript, we review the conventional PRS methods and their application to sub-Saharan African communities. We conclude that lack of sufficient GWAS data and tools is the limiting factor of applying PRS analysis to sub-Saharan populations. We recommend developing Africa-specific PRS methods and tools for estimating and analyzing African population data for clinical evaluation of PRSs of interest and predicting rare diseases.

Polygenic Risk Score (PRS) analysis is a method that predicts the genetic risk of an individual towards targeted traits. Even when there are no significant markers, it gives evidence of a genetic effect beyond the results of Genome-Wide Association Studies (GWAS). Moreover, it selects single nucleotide polymorphisms (SNPs) that contribute to the disease with low effect size making it more precise at individual level risk prediction. PRS analysis addresses the shortfall of GWAS by taking into account the SNPs/alleles with low effect size but play an indispensable role to the observed phenotypic/trait variance. PRS analysis has applications that investigate the genetic basis of several traits, which includes rare diseases. However, the accuracy of PRS analysis depends on the genomic data of the underlying population. For instance, several studies show that obtaining higher prediction power of PRS analysis is challenging for non-Europeans. In this manuscript, we review the conventional PRS methods and their application to sub-Saharan African communities. We conclude that lack of sufficient GWAS data and tools is the limiting factor of applying PRS analysis to sub-Saharan populations. We recommend developing Africa-specific PRS methods and tools for estimating and analyzing African population data for clinical evaluation of PRSs of interest and predicting rare diseases.