Detecting and characterizing cellular responses toMycobacterium tuberculosisfrom histology slides

The heme oxygenase-1 metalloporphyrin inhibitor stannsoporfin enhances the bactericidal activity of a novel regimen for multidrug-resistant tuberculosis in a murine model

Multidrug-resistant (MDR) Mycobacterium tuberculosis (Mtb) poses significant challenges to global tuberculosis (TB) control efforts. Host-directed therapies (HDTs) offer a novel approach to TB treatment by enhancing immune-mediated clearance of Mtb. Prior preclinical studies found that the inhibition of heme oxygenase-1 (HO-1), an enzyme involved in heme metabolism, with tin-protoporphyrin IX (SnPP) significantly reduced mouse lung bacillary burden when co-administered with the first-line antitubercular regimen. Here, we evaluated the adjunctive HDT activity of a novel HO-1 inhibitor, stannsoporfin (SnMP), in combination with a novel MDR-TB regimen comprising a next-generation diarylquinoline, TBAJ-876 (S), pretomanid (Pa), and a new oxazolidinone, TBI-223 (O) (collectively, SPaO), in Mtb-infected BALB/c mice. After 4 weeks of treatment, SPaO + SnMP 5mg/kg reduced mean lung bacillary burden by an additional 0.69 log10 (P = 0.01) relative to SPaO alone. As early as 2 weeks post-treatment initiation, SnMP adjunctive therapy differentially altered the expression of pro-inflammatory cytokine genes and CD38, a marker of M1 macrophages. Next, we evaluated the sterilizing potential of SnMP adjunctive therapy in a mouse model of microbiological relapse. After 6 weeks of treatment, SPaO + SnMP 10mg/kg reduced lung bacterial burdens to 0.71 ± 0.23 log10 colony-forming units (CFUs), a 0.78 log-fold greater decrease in lung CFU compared to SpaO alone (P = 0.005). However, adjunctive SnMP did not reduce microbiological relapse rates after 5 or 6 weeks of treatment. SnMP was well tolerated and did not significantly alter gross or histological lung pathology. SnMP is a promising HDT candidate requiring further study in combination with regimens for drug-resistant TB.

Prediction of Tuberculosis From Lung Tissue Images of Diversity Outbred Mice Using Jump Knowledge Based Cell Graph Neural Network

Tuberculosis (TB), primarily affecting the lungs, is caused by the bacterium Mycobacterium tuberculosis and poses a significant health risk. Detecting acid-fast bacilli (AFB) in stained samples is critical for TB diagnosis. Whole Slide (WS) Imaging allows for digitally examining these stained samples. However, current deep-learning approaches to analyzing large-sized whole slide images (WSIs) often employ patch-wise analysis, potentially missing the complex spatial patterns observed in the granuloma essential for accurate TB classification. To address this limitation, we propose an approach that models cell characteristics and interactions as a graph, capturing both cell-level information and the overall tissue micro-architecture. This method differs from the strategies in related cell graph-based works that rely on edge thresholds based on sparsity/density in cell graph construction, emphasizing a biologically informed threshold determination instead. We introduce a cell graph-based jumping knowledge neural network (CG-JKNN) that operates on the cell graphs where the edge thresholds are selected based on the length of the mycobacteria's cords and the activated macrophage nucleus's size to reflect the actual biological interactions observed in the tissue. The primary process involves training a Convolutional Neural Network (CNN) to segment AFBs and macrophage nuclei, followed by converting large (42831*41159 pixels) lung histology images into cell graphs where an activated macrophage nucleus/AFB represents each node within the graph and their interactions are denoted as edges. To enhance the interpretability of our model, we employ Integrated Gradients and Shapely Additive Explanations (SHAP). Our analysis incorporated a combination of 33 graph metrics and 20 cell morphology features. In terms of traditional machine learning models, Extreme Gradient Boosting (XGBoost) was the best performer, achieving an F1 score of 0.9813 and an Area under the Precision-Recall Curve (AUPRC) of 0.9848 on the test set. Among graph-based models, our CG-JKNN was the top performer, attaining an F1 score of 0.9549 and an AUPRC of 0.9846 on the held-out test set. The integration of graph-based and morphological features proved highly effective, with CG-JKNN and XGBoost showing promising results in classifying instances into AFB and activated macrophage nucleus. The features identified as significant by our models closely align with the criteria used by pathologists in practice, highlighting the clinical applicability of our approach. Future work will explore knowledge distillation techniques and graph-level classification into distinct TB progression categories.

Automatic discovery of clinically interpretable imaging biomarkers for Mycobacterium tuberculosis supersusceptibility using deep learning

BACKGROUND

Identifying which individuals will develop tuberculosis (TB) remains an unresolved problem due to few animal models and computational approaches that effectively address its heterogeneity. To meet these shortcomings, we show that Diversity Outbred (DO) mice reflect human-like genetic diversity and develop human-like lung granulomas when infected with Mycobacterium tuberculosis (M.tb) .

METHODS

Following M.tb infection, a "supersusceptible" phenotype develops in approximately one-third of DO mice characterized by rapid morbidity and mortality within 8 weeks. These supersusceptible DO mice develop lung granulomas patterns akin to humans. This led us to utilize deep learning to identify supersusceptibility from hematoxylin & eosin (H&E) lung tissue sections utilizing only clinical outcomes (supersusceptible or not-supersusceptible) as labels.

FINDINGS

The proposed machine learning model diagnosed supersusceptibility with high accuracy (91.50 ± 4.68%) compared to two expert pathologists using H&E stained lung sections (94.95% and 94.58%). Two non-experts used the imaging biomarker to diagnose supersusceptibility with high accuracy (88.25% and 87.95%) and agreement (96.00%). A board-certified veterinary pathologist (GB) examined the imaging biomarker and determined the model was making diagnostic decisions using a form of granuloma necrosis (karyorrhectic and pyknotic nuclear debris). This was corroborated by one other board-certified veterinary pathologist. Finally, the imaging biomarker was quantified, providing a novel means to convert visual patterns within granulomas to data suitable for statistical analyses.

IMPLICATIONS

Overall, our results have translatable implication to improve our understanding of TB and also to the broader field of computational pathology in which clinical outcomes alone can drive automatic identification of interpretable imaging biomarkers, knowledge discovery, and validation of existing clinical biomarkers.

FUNDING

National Institutes of Health and American Lung Association.

Gallium Porphyrin and Gallium Nitrate Synergistically Inhibit Mycobacterial Species by Targeting Different Aspects of Iron/Heme Metabolism

There is an urgent need for new effective and safe antibiotics active against pathogenic mycobacterial species. Gallium (Ga) nitrate (Ga(NO₃)₃) and Ga porphyrin (GaPP) have each been shown to inhibit the growth of a variety of mycobacterial species. The Ga(III) ion derived from Ga(NO₃)₃ has the potential to disrupt the mycobacterial Fe(III) uptake mechanisms and utilization, including replacing iron (Fe) in the active site of enzymes, resulting in the disruption of function. Similarly, noniron metalloporphyrins such as heme mimetics, which can be transported across the bacterial membrane via heme-uptake pathways, would potentially block the acquisition of iron-containing heme and bind to heme-utilizing proteins, making them nonfunctional. Given that they likely act on different aspects of mycobacterial Fe metabolism, the efficacy of combining Ga(NO₃)₃ and GaPP was studied in vitro against Mycobacterium avium, Mycobacterium abscessus, and Mycobacterium tuberculosis (M. tb). The combination was then assessed in vivo in a murine pulmonary infection model of M. abscessus. We observed that Ga(NO₃)₃ in combination with GaPP exhibited synergistic inhibitory activity against the growth of M. avium, M. tb, and M. abscessus, being most active against M. abscessus. Activity assays indicated that Ga(NO₃)₃ and GaPP inhibited both catalase and aconitase at high concentrations. However, the combination showed a synergistic effect on the aconitase activity of M. abscessus. The Ga(NO₃)₃/GaPP combination via intranasal administration showed significant antimicrobial activity in mice infected with M. abscessus. M. abscessus CFU from the lungs of the Ga(NO₃)₃/GaPP-treated mice was significantly less compared to that of nontreated or single Ga(III)-treated mice. These findings suggest that combinations of different Ga(III) compounds can synergistically target multiple iron/heme-utilizing mycobacterial enzymes. The results support the potential of combination Ga therapy for development against mycobacterial pathogens.

The Prognostic Relevance of the Proliferation Markers Ki-67 and Plk1 in Early-Stage Ovarian Cancer Patients With Serous, Low-Grade Carcinoma Based on mRNA and Protein Expression

Since type and duration of an appropriate adjuvant chemotherapy in early-stage ovarian cancer (OC) are still being debated, novel markers for a better stratification of these patients are of utmost importance for the design of an improved chemotherapeutical strategy. In contrast to numerous cancer studies on cellular proliferation based on the immunohistochemistry-driven evaluation of protein expression, we compared mRNA and protein expression of two independent markers of cellular proliferation, Ki-67 and Plk1, in a large cohort of 243 early-stage OC and their relationship with clinicopathological features and survival. Based on marker expression we demonstrate that early-stage OC patients (stages I/II, low-grade, serous) with high expression (Ki-67, Plk1) had a significantly shorter progression-free survival (PFS) and overall survival (OS) compared to patients with low expression (Ki-67, Plk1). Remarkably, based on mRNA expression this significant difference got lost in advanced stages (III/IV): At least for PFS, high levels of Ki-67 and Plk1 correlate with moderately better survival compared to patients with low expressing tumors. Our data suggest that in addition to Ki-67, Plk1 is a novel marker for the stratification of early-stage OC patients to maximize therapeutic efforts. Both, Ki-67 and Plk1, seem to be better suited in early-stages (I/II) as therapeutical targets compared to advanced-stages (III/IV) OC.

Automatic Detection of Granuloma Necrosis in Pulmonary Tuberculosis Using a Two-Phase Algorithm: 2D-TB

Granuloma necrosis occurs in hosts susceptible to pathogenic mycobacteria and is a diagnostic visual feature of pulmonary tuberculosis (TB) in humans and in super-susceptible Diversity Outbred (DO) mice infected with Mycobacterium tuberculosis. Currently, no published automated algorithms can detect granuloma necrosis in pulmonary TB. However, such a method could reduce variability, and transform visual patterns into quantitative data for statistical and machine learning analyses. Here, we used histopathological images from super-susceptible DO mice to train, validate, and performance test an algorithm to detect regions of cell-poor necrosis. The algorithm, named 2D-TB, works on 2-dimensional histopathological images in 2 phases. In phase 1, granulomas are detected following background elimination. In phase 2, 2D-TB searches within granulomas for regions of cell-poor necrosis. We used 8 lung sections from 8 different super-susceptible DO mice for training and 10-fold cross validation. We used 13 new lung sections from 10 different super-susceptible DO mice for performance testing. 2D-TB reached 100.0% sensitivity and 91.8% positive prediction value. Compared to an expert pathologist, agreement was 95.5% and there was a statistically significant positive correlation for area detected by 2D-TB and the pathologist. These results show the development, validation, and accurate performance of 2D-TB to detect granuloma necrosis.

Developing the Quantitative Histopathology Image Ontology (QHIO): A case study using the hot spot detection problem

Interoperability across data sets is a key challenge for quantitative histopathological imaging. There is a need for an ontology that can support effective merging of pathological image data with associated clinical and demographic data. To foster organized, cross-disciplinary, information-driven collaborations in the pathological imaging field, we propose to develop an ontology to represent imaging data and methods used in pathological imaging and analysis, and call it Quantitative Histopathological Imaging Ontology - QHIO. We apply QHIO to breast cancer hot-spot detection with the goal of enhancing reliability of detection by promoting the sharing of data between image analysts.

Visually Meaningful Histopathological Features for Automatic Grading of Prostate Cancer

Histopathologic features, particularly Gleason grading system, have contributed significantly to the diagnosis, treatment, and prognosis of prostate cancer for decades. However, prostate cancer demonstrates enormous heterogeneity in biological behavior, thus establishing improved prognostic and predictive markers is particularly important to personalize therapy of men with clinically localized and newly diagnosed malignancy. Many automated grading systems have been developed for Gleason grading but acceptance in the medical community has been lacking due to poor interpretability. To overcome this problem, we developed a set of visually meaningful features to differentiate between low- and high-grade prostate cancer. The visually meaningful feature set consists of luminal and architectural features. For luminal features, we compute: 1) the shortest path from the nuclei to their closest luminal spaces; 2) ratio of the epithelial nuclei to the total number of nuclei. A nucleus is considered an epithelial nucleus if the shortest path between it and the luminal space does not contain any other nucleus; 3) average shortest distance of all nuclei to their closest luminal spaces. For architectural features, we compute directional changes in stroma and nuclei using directional filter banks. These features are utilized to create two subspaces; one for prostate images histopathologically assessed as low grade and the other for high grade. The grade associated with a subspace, which results in the minimum reconstruction error is considered as the prediction for the test image. For training, we utilized 43 regions of interest (ROI) images, which were extracted from 25 prostate whole slide images of The Cancer Genome Atlas (TCGA) database. For testing, we utilized an independent dataset of 88 ROIs extracted from 30 prostate whole slide images. The method resulted in 93.0% and 97.6% training and testing accuracies, respectively, for the spectrum of cases considered. The application of visually meaningful features provided promising levels of accuracy and consistency for grading prostate cancer.

Mouse models of human TB pathology: roles in the analysis of necrosis and the development of host-directed therapies

A key aspect of TB pathogenesis that maintains Mycobacterium tuberculosis in the human population is the ability to cause necrosis in pulmonary lesions. As co-evolution shaped M. tuberculosis (M.tb) and human responses, the complete TB disease profile and lesion manifestation are not fully reproduced by any animal model. However, animal models are absolutely critical to understand how infection with virulent M.tb generates outcomes necessary for the pathogen transmission and evolutionary success. In humans, a wide spectrum of TB outcomes has been recognized based on clinical and epidemiological data. In mice, there is clear genetic basis for susceptibility. Although the spectra of human and mouse TB do not completely overlap, comparison of human TB with mouse lesions across genetically diverse strains firmly establishes points of convergence. By embracing the genetic heterogeneity of the mouse population, we gain tremendous advantage in the quest for suitable in vivo models. Below, we review genetically defined mouse models that recapitulate a key element of M.tb pathogenesis—induction of necrotic TB lesions in the lungs—and discuss how these models may reflect TB stratification and pathogenesis in humans. The approach ensures that roles that mouse models play in basic and translational TB research will continue to increase allowing researchers to address fundamental questions of TB pathogenesis and bacterial physiology in vivo using this well-defined, reproducible, and cost-efficient system. Combination of the new generation mouse models with advanced imaging technologies will also allow rapid and inexpensive assessment of experimental vaccines and therapies prior to testing in larger animals and clinical trials.

A multi-resolution textural approach to diagnostic neuropathology reporting

We present a computer aided diagnostic workflow focusing on two diagnostic branch points in neuropathology (intraoperative consultation and p53 status in tumor biopsy specimens) by means of texture analysis via discrete wavelet frames decomposition. For intraoperative consultation, our methodology is capable of classifying glioblastoma versus metastatic cancer by extracting textural features from the non-nuclei region of cytologic preparations based on the imaging characteristics of glial processes, which appear as anisotropic thin linear structures. For metastasis, these are homogeneous in appearance, thus suitable and extractable texture features distinguish the two tissue types. Experiments on 53 images (29 glioblastomas and 24 metastases) resulted in average accuracy as high as 89.7 % for glioblastoma, 87.5 % for metastasis and 88.7 % overall. For p53 interpretation, we detect and classify p53 status by classifying staining intensity into strong, moderate, weak and negative sub-classes. We achieved this by developing a novel adaptive thresholding for detection, a two-step rule based on weighted color and intensity for the classification of positively and negatively stained nuclei, followed by texture classification to classify the positively stained nuclei into the strong, moderate and weak intensity sub-classes. Our detection method is able to correctly locate and distinguish the four types of cells, at 85 % average precision and 88 % average sensitivity rate. These classification methods on the other hand recorded 81 % accuracy in classifying the positive and negative cells, and 60 % accuracy in further classifying the positive cells into the three intensity groups, which is comparable with neuropathologists' markings.

Lung necrosis and neutrophils reflect common pathways of susceptibility to Mycobacterium tuberculosis in genetically diverse, immune-competent mice

Pulmonary tuberculosis (TB) is caused by Mycobacterium tuberculosis in susceptible humans. Here, we infected Diversity Outbred (DO) mice with ∼100 bacilli by aerosol to model responses in a highly heterogeneous population. Following infection, ‘supersusceptible’, ‘susceptible’ and ‘resistant’ phenotypes emerged. TB disease (reduced survival, weight loss, high bacterial load) correlated strongly with neutrophils, neutrophil chemokines, tumor necrosis factor (TNF) and cell death. By contrast, immune cytokines were weak correlates of disease. We next applied statistical and machine learning approaches to our dataset of cytokines and chemokines from lungs and blood. Six molecules from the lung: TNF, CXCL1, CXCL2, CXCL5, interferon-γ (IFN-γ), interleukin 12 (IL-12); and two molecules from blood – IL-2 and TNF – were identified as being important by applying both statistical and machine learning methods. Using molecular features to generate tree classifiers, CXCL1, CXCL2 and CXCL5 distinguished four classes (supersusceptible, susceptible, resistant and non-infected) from each other with approximately 77% accuracy using completely independent experimental data. By contrast, models based on other molecules were less accurate. Low to no IFN-γ, IL-12, IL-2 and IL-10 successfully discriminated non-infected mice from infected mice but failed to discriminate disease status amongst supersusceptible, susceptible and resistant M.-tuberculosis-infected DO mice. Additional analyses identified CXCL1 as a promising peripheral biomarker of disease and of CXCL1 production in the lungs. From these results, we conclude that: (1) DO mice respond variably to M. tuberculosis infection and will be useful to identify pathways involving necrosis and neutrophils; (2) data from DO mice is suited for machine learning methods to build, validate and test models with independent data based solely on molecular biomarkers; (3) low levels of immunological cytokines best indicate a lack of exposure to M. tuberculosis but cannot distinguish infection from disease.

Summary: Molecular biomarkers of tuberculosis are identified and used to classify disease status of Diversity Outbred mice that have been infected with Mycobacterium tuberculosis.

Perceptual clustering for automatic hotspot detection from Ki-67-stained neuroendocrine tumour images

Hotspot detection plays a crucial role in grading of neuroendocrine tumours of the digestive system. Hotspots are often detected manually from Ki-67-stained images, a practice which is tedious, irreproducible and error prone. We report a new method to segment Ki-67-positive nuclei from Ki-67-stained slides of neuroendocrine tumours. The method combines minimal graph cuts along with the multistate difference of Gaussians to detect the individual cells from images of Ki-67-stained slides. It, then, automatically defines the composite function, which is used to determine hotspots in neuroendocrine tumour slide images. We combine modified particle swarm optimization with message passing clustering to mimic the thought process of the pathologist during hotspot detection in neuroendocrine tumour slide images. The proposed method was tested on 55 images of size 10 × 5 K and resulted in an accuracy of 94.60%. The developed methodology can also be part of the workflow for other diseases such as breast cancer and glioblastomas.