A computational pipeline for quantification of pulmonary infections in small animal models using serial PET-CT imaging

An exploratory deep learning approach to investigate tuberculosis pathogenesis in nonhuman primate model: Combining automated radiological analysis with clinical and biomarkers data

BACKGROUND

Tuberculosis (TB) kills approximately 1.6 million people yearly despite the fact anti-TB drugs are generally curative. Therefore, TB-case detection and monitoring of therapy, need a comprehensive approach. Automated radiological analysis, combined with clinical, microbiological, and immunological data, by machine learning (ML), can help achieve it.

METHODS

Six rhesus macaques were experimentally inoculated with pathogenic Mycobacterium tuberculosis in the lung. Data, including Computed Tomography (CT), were collected at 0, 2, 4, 8, 12, 16, and 20 weeks.

RESULTS

Our ML-based CT analysis (TB-Net) efficiently and accurately analyzed disease progression, performing better than standard deep learning model (LLM OpenAI's CLIP Vi4). TB-Net based results were more consistent than, and confirmed independently by, blinded manual disease scoring by two radiologists and exhibited strong correlations with blood biomarkers, TB-lesion volumes, and disease-signs during disease pathogenesis.

CONCLUSION

The proposed approach is valuable in early disease detection, monitoring efficacy of therapy, and clinical decision making.

Standardised lesion segmentation for imaging biomarker quantitation: a consensus recommendation from ESR and EORTC

BACKGROUND

Lesion/tissue segmentation on digital medical images enables biomarker extraction, image-guided therapy delivery, treatment response measurement, and training/validation for developing artificial intelligence algorithms and workflows. To ensure data reproducibility, criteria for standardised segmentation are critical but currently unavailable.

METHODS

A modified Delphi process initiated by the European Imaging Biomarker Alliance (EIBALL) of the European Society of Radiology (ESR) and the European Organisation for Research and Treatment of Cancer (EORTC) Imaging Group was undertaken. Three multidisciplinary task forces addressed modality and image acquisition, segmentation methodology itself, and standards and logistics. Devised survey questions were fed via a facilitator to expert participants. The 58 respondents to Round 1 were invited to participate in Rounds 2-4. Subsequent rounds were informed by responses of previous rounds.

RESULTS/CONCLUSIONS

Items with ≥ 75% consensus are considered a recommendation. These include system performance certification, thresholds for image signal-to-noise, contrast-to-noise and tumour-to-background ratios, spatial resolution, and artefact levels. Direct, iterative, and machine or deep learning reconstruction methods, use of a mixture of CE marked and verified research tools were agreed and use of specified reference standards and validation processes considered essential. Operator training and refreshment were considered mandatory for clinical trials and clinical research. Items with a 60-74% agreement require reporting (site-specific accreditation for clinical research, minimal pixel number within lesion segmented, use of post-reconstruction algorithms, operator training refreshment for clinical practice). Items with ≤ 60% agreement are outside current recommendations for segmentation (frequency of system performance tests, use of only CE-marked tools, board certification of operators, frequency of operator refresher training). Recommendations by anatomical area are also specified.

Information Bottleneck Attribution for Visual Explanations of Diagnosis and Prognosis

Visual explanation methods have an important role in the prognosis of the patients where the annotated data is limited or unavailable. There have been several attempts to use gradient-based attribution methods to localize pathology from medical scans without using segmentation labels. This research direction has been impeded by the lack of robustness and reliability. These methods are highly sensitive to the network parameters. In this study, we introduce a robust visual explanation method to address this problem for medical applications. We provide an innovative visual explanation algorithm for general purpose and as an example application we demonstrate its effectiveness for quantifying lesions in the lungs caused by the Covid-19 with high accuracy and robustness without using dense segmentation labels. This approach overcomes the drawbacks of commonly used Grad-CAM and its extended versions. The premise behind our proposed strategy is that the information flow is minimized while ensuring the classifier prediction stays similar. Our findings indicate that the bottleneck condition provides a more stable severity estimation than the similar attribution methods. The source code will be publicly available upon publication.

A physics-guided modular deep-learning based automated framework for tumor segmentation in PET

An important need exists for reliable positron emission tomography (PET) tumor-segmentation methods for tasks such as PET-based radiation-therapy planning and reliable quantification of volumetric and radiomic features. To address this need, we propose an automated physics-guided deep-learning-based three-module framework to segment PET images on a per-slice basis. The framework is designed to help address the challenges of limited spatial resolution and lack of clinical training data with known ground-truth tumor boundaries in PET. The first module generates PET images containing highly realistic tumors with known ground-truth using a new stochastic and physics-based approach, addressing lack of training data. The second module trains a modified U-net using these images, helping it learn the tumor-segmentation task. The third module fine-tunes this network using a small-sized clinical dataset with radiologist-defined delineations as surrogate ground-truth, helping the framework learn features potentially missed in simulated tumors. The framework was evaluated in the context of segmenting primary tumors in 18F-fluorodeoxyglucose (FDG)-PET images of patients with lung cancer. The framework's accuracy, generalizability to different scanners, sensitivity to partial volume effects (PVEs) and efficacy in reducing the number of training images were quantitatively evaluated using Dice similarity coefficient (DSC) and several other metrics. The framework yielded reliable performance in both simulated (DSC: 0.87 (95% confidence interval (CI): 0.86, 0.88)) and patient images (DSC: 0.73 (95% CI: 0.71, 0.76)), outperformed several widely used semi-automated approaches, accurately segmented relatively small tumors (smallest segmented cross-section was 1.83 cm2), generalized across five PET scanners (DSC: 0.74 (95% CI: 0.71, 0.76)), was relatively unaffected by PVEs, and required low training data (training with data from even 30 patients yielded DSC of 0.70 (95% CI: 0.68, 0.71)). In conclusion, the proposed automated physics-guided deep-learning-based PET-segmentation framework yielded reliable performance in delineating tumors in FDG-PET images of patients with lung cancer.

Can Laws Be a Potential PET Image Texture Analysis Approach for Evaluation of Tumor Heterogeneity and Histopathological Characteristics in NSCLC?

We investigated the association between the textural features obtained from ¹⁸F-FDG images, metabolic parameters (SUVmax_, SUVmean, MTV, TLG), and tumor histopathological characteristics (stage and Ki-67 proliferation index) in non-small cell lung cancer (NSCLC). The FDG-PET images of 67 patients with NSCLC were evaluated. MATLAB technical computing language was employed in the extraction of 137 features by using first order statistics (FOS), gray-level co-occurrence matrix (GLCM), gray-level run length matrix (GLRLM), and Laws' texture filters. Textural features and metabolic parameters were statistically analyzed in terms of good discrimination power between tumor stages, and selected features/parameters were used in the automatic classification by k-nearest neighbors (k-NN) and support vector machines (SVM). We showed that one textural feature (gray-level nonuniformity, GLN) obtained using GLRLM approach and nine textural features using Laws' approach were successful in discriminating all tumor stages, unlike metabolic parameters. There were significant correlations between Ki-67 index and some of the textural features computed using Laws' method (r = 0.6, p = 0.013). In terms of automatic classification of tumor stage, the accuracy was approximately 84% with k-NN classifier (k = 3) and SVM, using selected five features. Texture analysis of FDG-PET images has a potential to be an objective tool to assess tumor histopathological characteristics. The textural features obtained using Laws' approach could be useful in the discrimination of tumor stage.

Replacement, Refinement, and Reduction in Animal Studies With Biohazardous Agents

Animal models are critical to the advancement of our knowledge of infectious disease pathogenesis, diagnostics, therapeutics, and prevention strategies. The use of animal models requires thoughtful consideration for their well-being, as infections can significantly impact the general health of an animal and impair their welfare. Application of the 3Rs—replacement, refinement, and reduction—to animal models using biohazardous agents can improve the scientific merit and animal welfare. Replacement of animal models can use in vitro techniques such as cell culture systems, mathematical models, and engineered tissues or invertebrate animal hosts such as amoeba, worms, fruit flies, and cockroaches. Refinements can use a variety of techniques to more closely monitor the course of disease. These include the use of biomarkers, body temperature, behavioral observations, and clinical scoring systems. Reduction is possible using advanced technologies such as in vivo telemetry and imaging, allowing longitudinal assessment of animals during the course of disease. While there is no single method to universally replace, refine, or reduce animal models, the alternatives and techniques discussed are broadly applicable and they should be considered when infectious disease animal models are developed.

Radiomics in Oncological PET/CT: a Methodological Overview

Radiomics is a medical imaging analysis approach based on computer-vision. Metabolic radiomics in particular analyses the spatial distribution patterns of molecular metabolism on PET images. Measuring intratumoral heterogeneity via image is one of the main targets of radiomics research, and it aims to build a image-based model for better patient management. The workflow of radiomics using texture analysis follows these steps: 1) imaging (image acquisition and reconstruction); 2) preprocessing (segmentation & quantization); 3) quantification (texture matrix design & texture feature extraction); and 4) analysis (statistics and/or machine learning). The parameters or conditions at each of these steps are effect on the results. In statistical testing or modeling, problems such as multiple comparisons, dependence on other variables, and high dimensionality of small sample size data should be considered. Standardization of methodology and harmonization of image quality are one of the most important challenges with radiomics methodology. Even though there are current issues in radiomics methodology, it is expected that radiomics will be clinically useful in personalized medicine for oncology.

A semi-automatic technique to quantify complex tuberculous lung lesions on 18F-fluorodeoxyglucose positron emission tomography/computerised tomography images

BACKGROUND

There is a growing interest in the use of 18F-FDG PET-CT to monitor tuberculosis (TB) treatment response. However, TB causes complex and widespread pathology, which is challenging to segment and quantify in a reproducible manner. To address this, we developed a technique to standardise uptake (Z-score), segment and quantify tuberculous lung lesions on PET and CT concurrently, in order to track changes over time. We used open source tools and created a MATLAB script. The technique was optimised on a training set of five pulmonary tuberculosis (PTB) cases after standard TB therapy and 15 control patients with lesion-free lungs.

RESULTS

We compared the proposed method to a fixed threshold (SUV > 1) and manual segmentation by two readers and piloted the technique successfully on scans of five control patients and five PTB cases (four cured and one failed treatment case), at diagnosis and after 1 and 6 months of treatment. There was a better correlation between the Z-score-based segmentation and manual segmentation than SUV > 1 and manual segmentation in terms of overall spatial overlap (measured in Dice similarity coefficient) and specificity (1 minus false positive volume fraction). However, SUV > 1 segmentation appeared more sensitive. Both the Z-score and SUV > 1 showed very low variability when measuring change over time. In addition, total glycolytic activity, calculated using segmentation by Z-score and lesion-to-background ratio, correlated well with traditional total glycolytic activity calculations. The technique quantified various PET and CT parameters, including the total glycolytic activity index, metabolic lesion volume, lesion volumes at different CT densities and combined PET and CT parameters. The quantified metrics showed a marked decrease in the cured cases, with changes already apparent at month one, but remained largely unchanged in the failed treatment case.

CONCLUSIONS

Our technique is promising to segment and quantify the lung scans of pulmonary tuberculosis patients in a semi-automatic manner, appropriate for measuring treatment response. Further validation is required in larger cohorts.

Phenotypic Heterogeneity in Mycobacterium tuberculosis

The interaction between the host and the pathogen is extremely complex and is affected by anatomical, physiological, and immunological diversity in the microenvironments, leading to phenotypic diversity of the pathogen. Phenotypic heterogeneity, defined as nongenetic variation observed in individual members of a clonal population, can have beneficial consequences especially in fluctuating stressful environmental conditions. This is all the more relevant in infections caused by Mycobacterium tuberculosis wherein the pathogen is able to survive and often establish a lifelong persistent infection in the host. Recent studies in tuberculosis patients and in animal models have documented the heterogeneous and diverging trajectories of individual lesions within a single host. Since the fate of the individual lesions appears to be determined by the local tissue environment rather than systemic response of the host, studying this heterogeneity is very relevant to ensure better control and complete eradication of the pathogen from individual lesions. The heterogeneous microenvironments greatly enhance M. tuberculosis heterogeneity influencing the growth rates, metabolic potential, stress responses, drug susceptibility, and eventual lesion resolution. Single-cell approaches such as time-lapse microscopy using microfluidic devices allow us to address cell-to-cell variations that are often lost in population-average measurements. In this review, we focus on some of the factors that could be considered as drivers of phenotypic heterogeneity in M. tuberculosis as well as highlight some of the techniques that are useful in addressing this issue.

Positron Emission Tomography Imaging of Macaques with Tuberculosis Identifies Temporal Changes in Granuloma Glucose Metabolism and Integrin α4β1-Expressing Immune Cells

Positron emission tomography and computed tomography imaging (PET/CT) is an increasingly valuable tool for diagnosing tuberculosis (TB). The glucose analog [¹⁸F]fluoro-2-deoxy-2-d-glucose ([¹⁸F]-FDG) is commonly used in PET/CT that is retained by metabolically active inflammatory cells in granulomas, but lacks specificity for particular cell types. A PET probe that could identify recruitment and differentiation of different cell populations in granulomas would be a useful research tool and could improve TB diagnosis and treatment. We used the Mycobacterium-antigen murine inflammation model and macaques with TB to identify [⁶⁴Cu]-labeled CB-TE1A1P-PEG₄-LLP2A ([⁶⁴Cu]-LLP2A), a high affinity peptidomimetic ligand for very late Ag-4 (VLA-4; also called integrin α4β1) binding cells in granulomas, and compared [⁶⁴Cu]-LLP2A with [¹⁸F]-FDG over the course of infection. We found that [⁶⁴Cu]-LLP2A retention was driven by macrophages and T cells, with less contribution from neutrophils and B cells. In macaques, granulomas had higher [⁶⁴Cu]-LLP2A uptake than uninfected tissues, and immunohistochemical analysis of granulomas with known [⁶⁴Cu]-LLP2A uptake identified significant correlations between LLP2A signal and macrophage and T cell numbers. The same cells coexpressed integrin α4 and β1, further supporting that macrophages and T cells drive [⁶⁴Cu]-LLP2A avidity in granulomas. Over the course of infection, granulomas and thoracic lymph nodes experienced dynamic changes in affinity for both probes, suggesting metabolic changes and cell differentiation or recruitment occurs throughout granuloma development. These results indicate [⁶⁴Cu]-LLP2A is a PET probe for VLA-4, which when used in conjunction with [¹⁸F]-FDG, may be a useful tool for understanding granuloma biology in TB.

Imaging Chronic Tuberculous Lesions Using Sodium [(18)F]Fluoride Positron Emission Tomography in Mice

PURPOSE

Calcification is a hallmark of chronic tuberculosis (TB) in humans, often noted years to decades (after the initial infection) on chest radiography, but not visualized well with traditional positron emission tomography (PET). We hypothesized that sodium [(18)F]fluoride (Na[(18)F]F) PET could be used to detect microcalcifications in a chronically Mycobacterium tuberculosis-infected murine model.

PROCEDURES

C3HeB/FeJ mice, which develop necrotic and hypoxic TB lesions, were aerosol-infected with M. tuberculosis and imaged with Na[(18)F]F PET.

RESULTS

Pulmonary TB lesions from chronically infected mice demonstrated significantly higher Na[(18)F]F uptake compared with acutely infected or uninfected animals (P < 0.01), while no differences were noted in the blood or bone compartments (P > 0.08). Ex vivo biodistribution studies confirmed the imaging findings, and tissue histology demonstrated microcalcifications in TB lesions from chronically infected mice, which has not been demonstrated previously in a murine model.

CONCLUSION

Na[(18)F]F PET can be used for the detection of chronic TB lesions and could prove to be a useful noninvasive biomarker for TB studies.

Segmentation and Image Analysis of Abnormal Lungs at CT: Current Approaches, Challenges, and Future Trends

The computer-based process of identifying the boundaries of lung from surrounding thoracic tissue on computed tomographic (CT) images, which is called segmentation, is a vital first step in radiologic pulmonary image analysis. Many algorithms and software platforms provide image segmentation routines for quantification of lung abnormalities; however, nearly all of the current image segmentation approaches apply well only if the lungs exhibit minimal or no pathologic conditions. When moderate to high amounts of disease or abnormalities with a challenging shape or appearance exist in the lungs, computer-aided detection systems may be highly likely to fail to depict those abnormal regions because of inaccurate segmentation methods. In particular, abnormalities such as pleural effusions, consolidations, and masses often cause inaccurate lung segmentation, which greatly limits the use of image processing methods in clinical and research contexts. In this review, a critical summary of the current methods for lung segmentation on CT images is provided, with special emphasis on the accuracy and performance of the methods in cases with abnormalities and cases with exemplary pathologic findings. The currently available segmentation methods can be divided into five major classes: (a) thresholding-based, (b) region-based, (c) shape-based, (d) neighboring anatomy-guided, and (e) machine learning-based methods. The feasibility of each class and its shortcomings are explained and illustrated with the most common lung abnormalities observed on CT images. In an overview, practical applications and evolving technologies combining the presented approaches for the practicing radiologist are detailed.

Computer-aided pulmonary image analysis in small animal models

PURPOSE

To develop an automated pulmonary image analysis framework for infectious lung diseases in small animal models.

METHODS

The authors describe a novel pathological lung and airway segmentation method for small animals. The proposed framework includes identification of abnormal imaging patterns pertaining to infectious lung diseases. First, the authors' system estimates an expected lung volume by utilizing a regression function between total lung capacity and approximated rib cage volume. A significant difference between the expected lung volume and the initial lung segmentation indicates the presence of severe pathology, and invokes a machine learning based abnormal imaging pattern detection system next. The final stage of the proposed framework is the automatic extraction of airway tree for which new affinity relationships within the fuzzy connectedness image segmentation framework are proposed by combining Hessian and gray-scale morphological reconstruction filters.

RESULTS

133 CT scans were collected from four different studies encompassing a wide spectrum of pulmonary abnormalities pertaining to two commonly used small animal models (ferret and rabbit). Sensitivity and specificity were greater than 90% for pathological lung segmentation (average dice similarity coefficient > 0.9). While qualitative visual assessments of airway tree extraction were performed by the participating expert radiologists, for quantitative evaluation the authors validated the proposed airway extraction method by using publicly available EXACT'09 data set.

CONCLUSIONS

The authors developed a comprehensive computer-aided pulmonary image analysis framework for preclinical research applications. The proposed framework consists of automatic pathological lung segmentation and accurate airway tree extraction. The framework has high sensitivity and specificity; therefore, it can contribute advances in preclinical research in pulmonary diseases.

Heterogeneity in tuberculosis pathology, microenvironments and therapeutic responses

Tuberculosis (TB) lesions are extremely complex and dynamic. Here, we review the multiple types and fates of pulmonary lesions that form following infection by Mycobacterium tuberculosis and the impact of this spatial and temporal heterogeneity on the bacteria they harbor. The diverse immunopathology of granulomas and cavities generates a plethora of microenvironments to which M. tuberculosis bacilli must adapt. This in turn affects the replication, metabolism, and relative density of bacterial subpopulations, and consequently their respective susceptibility to chemotherapy. We outline recent developments that support a paradigm shift in our understanding of lesion progression. The simple model according to which lesions within a single individual react similarly to the systemic immune response no longer prevails. Host-pathogen interactions within lesions are a dynamic process, driven by subtle and local differences in signaling pathways, resulting in diverging trajectories of lesions within a single host. The spectrum of TB lesions is a continuum with a large overlap in the lesion types found in latently infected and active TB patients. We hope this overview will guide TB researchers in the design, choice of read-outs, and interpretation of future studies in the search for predictive biomarkers and novel therapies.

Accurate and efficient separation of left and right lungs from 3D CT scans: A generic hysteresis approach

Separation of left and right lungs from binary segmentation is often necessary for quantitative image-based pulmonary disease evaluation. In this article, we present a new fully automated approach for accurate, robust, and efficient lung separation using 3-D CT scans. Our method follows a hysteresis setting that utilizes information from both lung regions and background gaps. First, original segmentation is separated by subtracting the gaps between left and right lungs, which are enhanced with Hessian filtering. Second, the 2-D separation manifold in 3-D image space is estimated based on the distance information from the two subsets. Finally, the separation manifold is projected back to the original segmentation in order to produce the separated lungs through optimization for addressing minor local variations. An evaluation on over 400 human and 100 small animal 3-D CT images with various abnormalities is performed. The proposed scheme successfully separated all connections on the candidate CT images. Using hysteresis mechanism, each phase is performed robustly and 3-D information is utilized to achieve a generic, efficient, and accurate solution.

Lower Respiratory Tract Infection of the Ferret by 2009 H1N1 Pandemic Influenza A Virus Triggers Biphasic, Systemic, and Local Recruitment of Neutrophils

Infection of the lower respiratory tract by influenza A viruses results in increases in inflammation and immune cell infiltration in the lung. The dynamic relationships among the lung microenvironments, the lung, and systemic host responses during infection remain poorly understood. Here we used extensive systematic histological analysis coupled with live imaging to gain access to these relationships in ferrets infected with the 2009 H1N1 pandemic influenza A virus (H1N1pdm virus). Neutrophil levels rose in the lungs of H1N1pdm virus-infected ferrets 6 h postinfection and became concentrated at areas of the H1N1pdm virus-infected bronchiolar epithelium by 1 day postinfection (dpi). In addition, neutrophil levels were increased throughout the alveolar spaces during the first 3 dpi and returned to baseline by 6 dpi. Histochemical staining revealed that neutrophil infiltration in the lungs occurred in two waves, at 1 and 3 dpi, and gene expression within microenvironments suggested two types of neutrophils. Specifically, CCL3 levels, but not CXCL8/interleukin 8 (IL-8) levels, were higher within discrete lung microenvironments and coincided with increased infiltration of neutrophils into the lung. We used live imaging of ferrets to monitor host responses within the lung over time with [(18)F]fluorodeoxyglucose (FDG). Sites in the H1N1pdm virus-infected ferret lung with high FDG uptake had high levels of proliferative epithelium. In summary, neutrophils invaded the H1N1pdm virus-infected ferret lung globally and focally at sites of infection. Increased neutrophil levels in microenvironments did not correlate with increased FDG uptake; hence, FDG uptake may reflect prior infection and inflammation of lungs that have experienced damage, as evidenced by bronchial regeneration of tissues in the lungs at sites with high FDG levels.

IMPORTANCE

Severe influenza disease is characterized by an acute infection of the lower airways that may progress rapidly to organ failure and death. Well-developed animal models that mimic human disease are essential to understanding the complex relationships of the microenvironment, organ, and system in controlling virus replication, inflammation, and disease progression. Employing the ferret model of H1N1pdm virus infection, we used live imaging and comprehensive histological analyses to address specific hypotheses regarding spatial and temporal relationships that occur during the progression of infection and inflammation. We show the general invasion of neutrophils at the organ level (lung) but also a distinct pattern of localized accumulation within the microenvironment at the site of infection. Moreover, we show that these responses were biphasic within the lung. Finally, live imaging revealed an early and sustained host metabolic response at sites of infection that may reflect damage and repair of tissues in the lungs.

A hybrid method for airway segmentation and automated measurement of bronchial wall thickness on CT

Inflammatory and infectious lung diseases commonly involve bronchial airway structures and morphology, and these abnormalities are often analyzed non-invasively through high resolution computed tomography (CT) scans. Assessing airway wall surfaces and the lumen are of great importance for diagnosing pulmonary diseases. However, obtaining high accuracy from a complete 3-D airway tree structure can be quite challenging. The airway tree structure has spiculated shapes with multiple branches and bifurcation points as opposed to solid single organ or tumor segmentation tasks in other applications, hence, it is complex for manual segmentation as compared with other tasks. For computerized methods, a fundamental challenge in airway tree segmentation is the highly variable intensity levels in the lumen area, which often causes a segmentation method to leak into adjacent lung parenchyma through blurred airway walls or soft boundaries. Moreover, outer wall definition can be difficult due to similar intensities of the airway walls and nearby structures such as vessels. In this paper, we propose a computational framework to accurately quantify airways through (i) a novel hybrid approach for precise segmentation of the lumen, and (ii) two novel methods (a spatially constrained Markov random walk method (pseudo 3-D) and a relative fuzzy connectedness method (3-D)) to estimate the airway wall thickness. We evaluate the performance of our proposed methods in comparison with mostly used algorithms using human chest CT images. Our results demonstrate that, on publicly available data sets and using standard evaluation criteria, the proposed airway segmentation method is accurate and efficient as compared with the state-of-the-art methods, and the airway wall estimation algorithms identified the inner and outer airway surfaces more accurately than the most widely applied methods, namely full width at half maximum and phase congruency.

Improving the tuberculosis drug development pipeline

Mycobacterium tuberculosis is considered one of the most successful pathogens and multidrug-resistant tuberculosis, a disease that urgently requires new chemical entities to be developed for treatment. There are currently several new molecules under clinical investigation in the tuberculosis (TB) drug development pipeline. However, the complex lifestyle of M. tuberculosis within the host presents a barrier to the development of new drugs. In this review, we highlight the reasons that make TB drug discovery and development challenging as well as providing solutions, future directions and alternative approaches to new therapeutics for TB.

A generic approach to pathological lung segmentation

In this study, we propose a novel pathological lung segmentation method that takes into account neighbor prior constraints and a novel pathology recognition system. Our proposed framework has two stages; during stage one, we adapted the fuzzy connectedness (FC) image segmentation algorithm to perform initial lung parenchyma extraction. In parallel, we estimate the lung volume using rib-cage information without explicitly delineating lungs. This rudimentary, but intelligent lung volume estimation system allows comparison of volume differences between rib cage and FC based lung volume measurements. Significant volume difference indicates the presence of pathology, which invokes the second stage of the proposed framework for the refinement of segmented lung. In stage two, texture-based features are utilized to detect abnormal imaging patterns (consolidations, ground glass, interstitial thickening, tree-inbud, honeycombing, nodules, and micro-nodules) that might have been missed during the first stage of the algorithm. This refinement stage is further completed by a novel neighboring anatomy-guided segmentation approach to include abnormalities with weak textures, and pleura regions. We evaluated the accuracy and efficiency of the proposed method on more than 400 CT scans with the presence of a wide spectrum of abnormalities. To our best of knowledge, this is the first study to evaluate all abnormal imaging patterns in a single segmentation framework. The quantitative results show that our pathological lung segmentation method improves on current standards because of its high sensitivity and specificity and may have considerable potential to enhance the performance of routine clinical tasks.

Nuclear imaging: a powerful novel approach for tuberculosis

Nearly 20 years after the World Health Organization declared tuberculosis (TB) a global public health emergency, TB still remains a major global threat with 8.6 million new cases and 1.3 million deaths annually. Mycobacterium tuberculosis adapts to a quiescent physiological state, and is notable for complex interaction with the host, producing poorly-understood disease states ranging from latent infection to fully active disease. Of the approximately 2.5 billion people latently infected with M. tuberculosis, many will develop reactivation disease (relapse), years after the initial infection. While progress has been made on some fronts, the alarming spread of multidrug-resistant, extensively drug-resistant, and more recently totally-drug resistant strains is of grave concern. New tools are urgently needed for rapidly diagnosing TB, monitoring TB treatments and to allow unique insights into disease pathogenesis. Nuclear bioimaging is a powerful, noninvasive tool that can rapidly provide three-dimensional views of disease processes deep within the body and conduct noninvasive longitudinal assessments of the same patient. In this review, we discuss the application of nuclear bioimaging to TB, including the current state of the field, considerations for radioprobe development, study of TB drug pharmacokinetics in infected tissues, and areas of research and clinical needs that could be addressed by nuclear bioimaging. These technologies are an emerging field of research, overcome several fundamental limitations of current tools, and will have a broad impact on both basic research and patient care. Beyond diagnosis and monitoring disease, these technologies will also allow unique insights into understanding disease pathogenesis; and expedite bench-to-bedside translation of new therapeutics. Finally, since molecular imaging is readily available for humans, validated tracers will become valuable tools for clinical applications.

Imaging the evolution of reactivation pulmonary tuberculosis in mice using 18F-FDG PET

Latent tuberculosis infection affects one third of the world's population and can reactivate (relapse) decades later. However, current technologies, dependent on postmortem analyses, cannot follow the temporal evolution of disease.

METHODS

C3HeB/FeJ mice, which develop necrotic and hypoxic tuberculosis lesions, were aerosol-infected with Mycobacterium tuberculosis. PET and CT were used to serially image the same cohort of infected mice through pretreatment, tuberculosis treatment, and subsequent development of relapse.

RESULTS

A novel diffeomorphic registration was successfully used to monitor the spatial evolution of individual pulmonary lesions. Although most lesions during relapse developed in the same regions as those noted during pretreatment, several lesions also arose de novo within regions with no prior lesions.

CONCLUSION

This study presents a novel model that simulates infection and reactivation disease as seen in humans and could prove valuable to study tuberculosis pathogenesis and evaluate novel therapeutics.

In vivo imaging in an ABSL-3 regional biocontainment laboratory

The Regional Biocontainment Laboratory (RBL) at the University of Pittsburgh is a state-of-the-art ABSL-3 facility that supports research on highly pathogenic viruses and bacteria. Recent advances in radiologic imaging provide several noninvasive, in vivo imaging modalities that can be used to longitudinally monitor animals following experimental infection or vaccination. The University of Pittsburgh RBL provides digital radiography, bioluminescence imaging, and PET/CT. Operating these platforms in an ABSL-3 poses unique challenges. This review will discuss the development and refinement of these imaging platforms in high containment, emphasizing specific challenges and how they were overcome.

A review on segmentation of positron emission tomography images

Positron Emission Tomography (PET), a non-invasive functional imaging method at the molecular level, images the distribution of biologically targeted radiotracers with high sensitivity. PET imaging provides detailed quantitative information about many diseases and is often used to evaluate inflammation, infection, and cancer by detecting emitted photons from a radiotracer localized to abnormal cells. In order to differentiate abnormal tissue from surrounding areas in PET images, image segmentation methods play a vital role; therefore, accurate image segmentation is often necessary for proper disease detection, diagnosis, treatment planning, and follow-ups. In this review paper, we present state-of-the-art PET image segmentation methods, as well as the recent advances in image segmentation techniques. In order to make this manuscript self-contained, we also briefly explain the fundamentals of PET imaging, the challenges of diagnostic PET image analysis, and the effects of these challenges on the segmentation results.

Efficient ribcage segmentation from CT scans using shape features

Rib cage structure and morphology is important for anatomical analysis of chest CT scans. A fundamental challenge in rib cage extraction is varying intensity levels and connection with adjacent bone structures including shoulder blade and sternum. In this study, we present a fully automated 3-D algorithm to segment the rib cage by detection and separation of other bone structures. The proposed approach consists of four steps. First, all high-intensity bone structures are segmented. Second, multi-scale Hessian analysis is performed to capture plateness and vesselness information. Third, with the plate/vessel features, bone structures other than rib cage are detected. Last, the detected bones are separated from rib cage with iterative relative fuzzy connectedness method. The algorithm was evaluated using 400 human CT scans and 100 small animal images with various resolution. The results suggested that the percent accuracy of rib cage extraction is over 95% with the proposed algorithm.

Segmentation of PET images for computer-aided functional quantification of tuberculosis in small animal models

Pulmonary infections often cause spatially diffuse and multi-focal radiotracer uptake in positron emission tomography (PET) images, which makes accurate quantification of the disease extent challenging. Image segmentation plays a vital role in quantifying uptake due to the distributed nature of immuno-pathology and associated metabolic activities in pulmonary infection, specifically tuberculosis (TB). For this task, thresholding-based segmentation methods may be better suited over other methods; however, performance of the thresholding-based methods depend on the selection of thresholding parameters, which are often suboptimal. Several optimal thresholding techniques have been proposed in the literature, but there is currently no consensus on how to determine the optimal threshold for precise identification of spatially diffuse and multi-focal radiotracer uptake. In this study, we propose a method to select optimal thresholding levels by utilizing a novel intensity affinity metric within the affinity propagation clustering framework. We tested the proposed method against 70 longitudinal PET images of rabbits infected with TB. The overall dice similarity coefficient between the segmentation from the proposed method and two expert segmentations was found to be 91.25 ±8.01% with a sensitivity of 88.80 ±12.59% and a specificity of 96.01 ±9.20%. High accuracy and heightened efficiency of our proposed method, as compared to other PET image segmentation methods, were reported with various quantification metrics.