Quantification of histopathological findings using a novel image analysis platform

CCL2/CCR2 Expression in Locally Advanced Prostate Cancer and Patient Long-Term Outcome: 10-Year Results from the TROG 03.04 RADAR Trial

This study investigated the prognostic value of the chemokine C-C motif ligand 2 (CCL2) and its receptor C-C motif chemokine receptor 2 (CCR2) expression in locally advanced prostate cancer treated with radiotherapy and androgen deprivation using the 10-year outcome data from the TROG 03.04 RADAR clinical trial. CCL2 and CCR2 protein expression in prostate cancer biopsies at the time of diagnosis were quantified by immunohistochemistry and digital quantification. CCR2 protein expression was detected in prostate cancer cells and was associated with prostate-specific antigen serum concentration (p = 0.045). However, neither CCL2 nor CCR2 tissue expression could predict prostate cancer progression, or other clinicopathological parameters including perineural invasion and patient outcome. In serum samples, CCL2 concentration at the time of diagnosis, as assayed by enzyme-linked immunosorbent assay, was significantly higher in patients with prostate cancer compared with benign prostatic hyperplasia (median difference 0.22 ng/mL, 95% CI, 0.17-0.30) (p < 0.0001) and normal controls (median difference 0.13 ng/mL, 95% CI, 0.13-0.17) (p < 0.0001). However, circulating CCL2 was not statistically significant as a predictor of disease progression and patient outcome. In conclusion, this study shows that although CCL2 and CCR2 are expressed in prostate cancer, with an increased level of CCL2 in the serum, neither CCL2 nor CCR2 expression has a clinical prognostic value in locally advanced prostate cancer.

Combination of pathological, biochemical and behavioral evaluations for peripheral neurotoxicity assessment in isoniazid-treated rats

In drug development, assessment of non-clinical peripheral neurotoxicity is important to ensure human safety. Clarifying the pathological features and mechanisms of toxicity enables the management of safety risks in humans by estimating the degree of risk and proposing monitoring strategies. Published guidelines for peripheral neurotoxicity assessment do not provide detailed information on which endpoints should be monitored preferentially and how the results should be integrated and discussed. To identify an optimal assessment method for the characterization of peripheral neurotoxicity, we conducted pathological, biochemical (biomaterials contributing to mechanistic considerations and biomarkers), and behavioral evaluations of isoniazid-treated rats. We found a discrepancy between the days on which marked pathological changes were noted and those on which biochemical and behavioral changes were noted, suggesting the importance of combining these evaluations. Although pathological evaluation is essential for pathological characterization, the results of biochemical and behavioral assessments at the same time points as the pathological evaluation are also important for discussion. In this study, since the measurement of serum neurofilament light chain could detect changes earlier than pathological examination, it could be useful as a biomarker for peripheral neurotoxicity. Moreover, examination of semi-thin specimens and choline acetyltransferase immunostaining were useful for characterizing morphological neurotoxicity, and image analysis of semi-thin specimens enabled us to objectively show the pathological features.

Inhibition of repulsive guidance molecule-a ameliorates compromised blood-spinal cord barrier integrity associated with neuromyelitis optica in rats

The influx of pathogenic aquaporin-4 antibodies (AQP4-Abs) across the blood-spinal cord barrier (BSCB) is crucial for the development and exacerbation of neuromyelitis optica (NMO). We examined whether prophylactic intravenous administration of anti-repulsive guidance molecule-a antibodies (RGMa-Abs) has disease-modifying effects on BSCB dysfunction using an NMO model elicited by peripheral administration of AQP4-Abs to rats. RGMa-Ab treatment attenuated the acute exacerbation of perivascular astrocytopathy in the spinal cord and clinical symptoms, which were highly correlated with neurofilament light chain levels in both the cerebrospinal fluid (CSF) and serum. Additionally, RGMa-Ab treatment suppressed the expression of proinflammatory cytokines/chemokines and the infiltration of inflammatory cells into the spinal cord. CSF analysis of NMO rats revealed that RGMa-Ab treatment improved the CSF/serum albumin ratio and suppressed AQP4-Abs influx. RGMa inhibition using RGMa-Abs is suggested as a potential therapeutic option for BSCB dysfunction associated with NMO.

CD64 plays a key role in diabetic wound healing

Introduction

Wound healing poses a clinical challenge in diabetes mellitus (DM) due to compromised host immunity. CD64, an IgG-binding Fcgr1 receptor, acts as a pro-inflammatory mediator. While its presence has been identified in various inflammatory diseases, its specific role in wound healing, especially in DM, remains unclear.

Objectives

We aimed to investigate the involvement of CD64 in diabetic wound healing using a DM animal model with CD64 KO mice.

Methods

First, we compared CD64 expression in chronic skin ulcers from human DM and non-DM skin. Then, we monitored wound healing in a DM mouse model over 10 days, with or without CD64 KO, using macroscopic and microscopic observations, as well as immunohistochemistry.

Results

CD64 expression was significantly upregulated (1.25-fold) in chronic ulcerative skin from DM patients compared to non-DM individuals. Clinical observations were consistent with animal model findings, showing a significant delay in wound healing, particularly by day 7, in CD64 KO mice compared to WT mice. Additionally, infiltrating CD163+ M2 macrophages in the wounds of DM mice decreased significantly compared to non-DM mice over time. Delayed wound healing in DM CD64 KO mice correlated with the presence of inflammatory mediators.

Conclusion

CD64 seems to play a crucial role in wound healing, especially in DM conditions, where it is associated with CD163+ M2 macrophage infiltration. These data suggest that CD64 relies on host immunity during the wound healing process. Such data may provide useful information for both basic scientists and clinicians to deal with diabetic chronic wound healing.

Electrocardiographic Markers of Adverse Left Ventricular Remodeling and Myocardial Fibrosis in Severe Aortic Stenosis

The optimal timing for aortic valve replacement (AVR) in aortic stenosis (AS) is still controversial and may be guided by markers of adverse left ventricular (LV) remodeling. We aim to assess electrocardiographic (ECG) strain in relation to LV remodeling and myocardial fibrosis. 83 severe AS patients underwent surgical AVR, with preoperative 12-lead ECG, cardiovascular magnetic resonance with T1 mapping and echocardiography with global longitudinal strain analysis. Collagen volume fraction (CVF) was measured in myocardial biopsies sampled during AVR. Patients with ECG strain had more severe AS, more advanced LV remodeling and evidence of heart failure. Patients with ECG strain had more diffuse fibrosis, as evident by higher mean native T1 values (974.8 ± 34 ms vs. 946.5 ± 28 ms, p < 0.001). ECG strain was the only predictor of increased LV mass index on multivariate regression analysis (OR = 7.10, 95% CI 1.46-34.48, p = 0.02). Patients with persistent ECG strain at 1 year following AVR had more advanced LV remodeling and more histological fibrosis (CVF 12.5% vs. 7.3%, p = 0.009) at baseline assessment. Therefore, ECG strain is a marker of adverse LV remodeling and interstitial myocardial fibrosis. Lack of improvement in ECG strain following AVR indicates more advanced baseline LV injury and higher levels of myocardial fibrosis.

A comparative study on the implementation of deep learning algorithms for detection of hepatic necrosis in toxicity studies

Deep learning has recently become one of the most popular methods of image analysis. In non-clinical studies, several tissue slides are generated to investigate the toxicity of a test compound. These are converted into digital image data using a slide scanner, which is then studied by researchers to investigate abnormalities, and the deep learning method has been started to adopt in this study. However, comparative studies evaluating different deep learning algorithms for analyzing abnormal lesions are scarce. In this study, we applied three algorithms, SSD, Mask R-CNN, and DeepLabV3+, to detect hepatic necrosis in slide images and determine the best deep learning algorithm for analyzing abnormal lesions. We trained each algorithm on 5750 images and 5835 annotations of hepatic necrosis including validation and test, augmented with 500 image tiles of 448 × 448 pixels. Precision, recall, and accuracy were calculated for each algorithm based on the prediction results of 60 test images of 2688 × 2688 pixels. The two segmentation algorithms, DeepLabV3+ and Mask R-CNN, showed over 90% of accuracy (0.94 and 0.92, respectively), whereas SSD, an object detection algorithm, showed lower accuracy. The trained DeepLabV3+ outperformed all others in recall while also successfully separating hepatic necrosis from other features in the test images. It is important to localize and separate the abnormal lesion of interest from other features to investigate it on a slide level. Therefore, we suggest that segmentation algorithms are more appropriate than object detection algorithms for use in the pathological analysis of images in non-clinical studies.

Supplementary Information

The online version contains supplementary material available at 10.1007/s43188-023-00173-5.

Age-related morphometrics of normal adrenal glands based on deep learning-aided segmentation

OBJECTIVE

This study aims to evaluate the morphometrics of normal adrenal glands in adult patients semiautomatically using a deep learning-based segmentation model.

MATERIALS AND METHODS

A total of 520 abdominal CT image series with normal findings, from January 1, 2016, to March 14, 2019, were retrospectively collected for the training of the adrenal segmentation model. Then, 1043 portal venous phase image series of inpatient contrast-enhanced abdominal CT examinations with normal adrenal glands were included for analysis and grouped by every 10-year gap. A 3D U-Net-based segmentation model was used to predict bilateral adrenal labels followed by manual modification of labels as appropriate. Quantitative parameters (volume, CT value, and diameters) of the bilateral adrenal glands were then analyzed.

RESULTS

In the study cohort aged 18-77 years old (554 males and 489 females), the left adrenal gland was significantly larger than the right adrenal gland [all patients, 2867.79 (2317.11-3499.89) mm³ vs. 2452.84 (1983.50-2935.18) mm³, P < 0.001]. Male patients showed a greater volume of bilateral adrenal glands than females in all age groups (all patients, left: 3237.83 ± 930.21 mm³ vs. 2646.49 ± 766.42 mm³, P < 0.001; right: 2731.69 ± 789.19 mm³ vs. 2266.18 ± 632.97 mm³, P = 0.001). Bilateral adrenal volume in male patients showed an increasing then decreasing trend as age increased that peaked at 38-47 years old (left: 3416.01 ± 886.21 mm³, right: 2855.04 ± 774.57 mm³).

CONCLUSIONS

The semiautomated measurement revealed that the adrenal volume differs as age increases. Male patients aged 38-47 years old have a peaked adrenal volume.

Targeting XBP1 mRNA splicing sensitizes glioblastoma to chemotherapy

Glioblastoma (GBM) is the most frequent and deadly primary brain tumor in adults. Temozolomide (TMZ) is the standard systemic therapy in GBM but has limited and restricted efficacy. Better treatments are urgently needed. The role of endoplasmic reticulum stress (ER stress) is increasingly described in GBM pathophysiology. A key molecular mediator of ER stress, the spliced form of the transcription factor x-box binding protein 1 (XBP1s) may constitute a novel therapeutic target; here we report XBP1s expression and biological activity in GBM. Tumor samples from patients with GBM (n = 85) and low-grade glioma (n = 20) were analyzed by immunohistochemistry for XBP1s with digital quantification. XBP1s expression was significantly increased in GBM compared to low-grade gliomas. XBP1s mRNA showed upregulation by qPCR analysis in a panel of patient-derived GBM cell lines. Inhibition of XBP1 splicing using the small molecular inhibitor MKC-3946 significantly reduced GBM cell viability and potentiated the effect of TMZ in GBM cells, particularly in those with methylated O6-methylguanine-DNA methyl transferase gene promoter. GBM cells resistant to TMZ were also responsive to MKC-3946 and the long-term inhibitory effect of MKC-3946 was confirmed by colony formation assay. In conclusion, this data reveals that XBP1s is overexpressed in GBM and contributes to cancer cell growth. XBP1s warrants further investigation as a clinical biomarker and therapeutic target in GBM.

ProNGF Expression and Targeting in Glioblastoma Multiforme

Glioblastoma multiforme (GBM) is the most lethal adult brain cancer. Temozolomide (TMZ), the standard chemotherapeutic drug used in GBM, has limited benefit and alternate therapies are needed to improve GBM treatment. Nerve growth factor (NGF) and its precursor proNGF are increasingly recognized as stimulators of human tumor progression. The expression and stimulatory effect of NGF on GBM cell growth has previously been reported, but the status of proNGF in GBM is unreported. In this study, we have investigated proNGF expression and biological activity in GBM. A clinical cohort of GBM (n = 72) and low-grade glioma (n = 20) was analyzed by immunohistochemistry for proNGF and digital quantification. ProNGF expression was significantly increased in GBM compared to low grade gliomas and proNGF was also detected in patient plasma samples. ProNGF was also detected in most GBM cell lines by Western blotting. Although anti-proNGF blocking antibodies inhibited cell growth in GBM cells with methylated MGMT gene promoter, targeting proNGF could not potentiate the efficacy of TMZ. In subcutaneous xenograft of human GBM cells, anti-proNGF antibodies slightly reduced tumor volume but had no impact on TMZ efficacy. In conclusion, this data reveals that proNGF is overexpressed in GBM and can stimulate cancer cell growth. The potential of proNGF as a clinical biomarker and therapeutic target warrants further investigations.

A semi-supervised learning approach with consistency regularization for tumor histopathological images analysis

Introduction

Manual inspection of histopathological images is important in clinical cancer diagnosis. Pathologists implement pathological diagnosis and prognostic evaluation through the microscopic examination of histopathological slices. This entire process is time-consuming, laborious, and challenging for pathologists. The modern use of whole-slide imaging, which scans histopathology slides to digital slices, and analysis using computer-aided diagnosis is an essential problem.

Methods

To solve the problem of difficult labeling of histopathological data, and improve the flexibility of histopathological analysis in clinical applications, we herein propose a semi-supervised learning algorithm coupled with consistency regularization strategy, called"Semi- supervised Histopathology Analysis Network"(Semi-His-Net), for automated normal-versus-tumor and subtype classifications. Specifically, when inputted disturbing versions of the same image, the model should predict similar outputs. Based on this, the model itself can assign artificial labels to unlabeled data for subsequent model training, thereby effectively reducing the labeled data required for training.

Results

Our Semi-His-Net is able to classify patches from breast cancer histopathological images into normal tissue and three other different tumor subtypes, achieving an accuracy was 90%. The average AUC of cross-classification between tumors reached 0.893.

Discussion

To overcome the limitations of visual inspection by pathologists for histopathology images, such as long time and low repeatability, we have developed a deep learning-based framework (Semi-His-Net) for automatic classification subdivision of the subtypes contained in the whole pathological images. This learning-based framework has great potential to improve the efficiency and repeatability of histopathological image diagnosis.

Methods for assessment of the tumour microenvironment and immune interactions in non-small cell lung cancer. A narrative review

Non-small cell lung cancer (NSCLC) is one of the leading causes of cancer death worldwide. Immunotherapy with immune checkpoint inhibitors (ICI) has significantly improved outcomes in some patients, however 80-85% of patients receiving immunotherapy develop primary resistance, manifesting as a lack of response to therapy. Of those that do have an initial response, disease progression may occur due to acquired resistance. The make-up of the tumour microenvironment (TME) and the interaction between tumour infiltrating immune cells and cancer cells can have a large impact on the response to immunotherapy. Robust assessment of the TME with accurate and reproducible methods is vital to understanding mechanisms of immunotherapy resistance. In this paper we will review the evidence of several methodologies to assess the TME, including multiplex immunohistochemistry, imaging mass cytometry, flow cytometry, mass cytometry and RNA sequencing.

Automated recognition of glomerular lesions in the kidneys of mice by using deep learning

Background

In recent years, digital pathology has been rapidly developing and applied throughout the world. Especially in clinical settings, it has been utilized in a variety of situations, including automated cancer diagnosis. Conversely, in non-clinical research, it has not yet been utilized as much as in clinical settings. We have been performing automated recognition of various pathological animal tissues and quantitative analysis of pathological findings, including liver and lung. In this study, we attempted to construct an artificial intelligence (AI)-based trained model that can automatedly recognize glomerular lesions in mouse kidneys that are characterized by complex structures.

Materials and methods

By using hematoxylin and eosin (HE)-stained whole slide images (WSI) from Col4a3 KO mice as variation data, normal glomeruli and glomerular lesions were annotated, and deep learning (DL) was performed with the use of the neural network classifier DenseNet system in HALO AI. The trained model was refined by correcting the annotation of misrecognized tissue area and reperforming DL. The accuracy of the trained model was confirmed by comparing the AI-obtained results with the pathological grades evaluated by pathologists. The generality of the trained model was also confirmed by analyzing the WSI of adriamycin (ADR)-induced nephropathy mice, which is a different disease model.

Results

Glomerular lesions (including mesangial proliferation, crescent formation, and sclerosis) observed in Col4a3 KO mice and ADR mice were detected by our trained model. The number of glomerular lesions detected by our trained model were also highly correlated with that of counted by pathologists.

Conclusion

In this study, we constructed a trained model allowing us to automatedly recognize glomerular lesions in the mouse kidney with the use of the HALO AI system. The findings and insights of this study will facilitate the development of digital pathology in non-clinical research and improve the probability of success in drug discovery research.

Approaches to spatially resolving the tumour immune microenvironment of hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is a common and deadly cancer worldwide. Many factors contribute to mortality and place an individual at high risk of developing HCC, including viral infection, alcohol intake, metabolic-associated disease, autoimmunity and genetic liver disorders. Although there are many therapeutics available, much about this disease remains to be understood. This is most evident when investigating the tumour microenvironment (TME). Both innate and adaptive immune cells have been associated with carcinogenesis within the TME of HCC patients. The ability to interrogate the TME more thoroughly with spatial technologies continues to improve, both at the experimental and analytical stages. This review provides insight into technologies available to investigate the TME, and how such technologies are beneficial for improving our understanding of HCC carcinogenesis.

Reduced SARS-CoV-2 disease outcomes in Syrian hamsters receiving immune sera: Quantitative image analysis in pathologic assessments

There is a need to standardize pathologic endpoints in animal models of SARS-CoV-2 infection to help benchmark study quality, improve cross-institutional comparison of data, and assess therapeutic efficacy so that potential drugs and vaccines for SARS-CoV-2 can rapidly advance. The Syrian hamster model is a tractable small animal model for COVID-19 that models clinical disease in humans. Using the hamster model, the authors used traditional pathologic assessment with quantitative image analysis to assess disease outcomes in hamsters administered polyclonal immune sera from previously challenged rhesus macaques. The authors then used quantitative image analysis to assess pathologic endpoints across studies performed at different institutions using different tissue processing protocols. The authors detail pathological features of SARS-CoV-2 infection longitudinally and use immunohistochemistry to quantify myeloid cells and T lymphocyte infiltrates during SARS-CoV-2 infection. High-dose immune sera protected hamsters from weight loss and diminished viral replication in tissues and reduced lung lesions. Cumulative pathology scoring correlated with weight loss and was robust in distinguishing IgG efficacy. In formalin-infused lungs, quantitative measurement of percent area affected also correlated with weight loss but was less robust in non-formalin-infused lungs. Longitudinal immunohistochemical assessment of interstitial macrophage infiltrates showed that peak infiltration corresponded to weight loss, yet quantitative assessment of macrophage, neutrophil, and CD3+ T lymphocyte numbers did not distinguish IgG treatment effects. Here, the authors show that quantitative image analysis was a useful adjunct tool for assessing SARS-CoV-2 treatment outcomes in the hamster model.

Exploring myocardial fibrosis in severe aortic stenosis: echo, CMR and histology data from FIB-AS study

Myocardial fibrosis in aortic stenosis is associated with worse survival following aortic valve replacement. We assessed myocardial fibrosis in severe AS patients, integrating echocardiographic, cardiovascular magnetic resonance (CMR) and histological data. A total of 83 severe AS patients (age 66.4 ± 8.3, 42% male) who were scheduled for surgical AVR underwent CMR with late gadolinium enhancement and T1 mapping and global longitudinal strain analysis. Collagen volume fraction was measured in myocardial biopsies (71) that were sampled at the time of AVR. Results. CVF correlated with imaging and serum biomarkers of LV systolic dysfunction and left side chamber enlargement and was higher in the sub-endocardium compared with midmyocardium (p<0.001). CVF median values were higher in LGE-positive versus LGE-negative patients [28.7% (19-33) vs 20.7% (15-30), respectively, p=0.040]. GLS was associated with invasively (CVF; r=-0.303, p=0.013) and non-invasively (native T1; r=-0.321, p<0.05) measured myocardial fibrosis. GLS and native T1 correlated with parameters of adverse LV remodelling, systolic and diastolic dysfunction and serum biomarkers of heart failure and myocardial injury. Conclusion. Our data highlight the role of myocardial fibrosis in adverse cardiac remodelling in AS. GLS has potential as a surrogate marker of myocardial fibrosis, and high native T1 and low GLS values differentiated patients with more advanced cardiac remodelling.

Techniques for digital histological morphometry of the pineal gland

INTRODUCTION

The pineal gland is a small photo-neuro-endocrine organ. This study used human post-mortem pineal glands to microscopically assess immunohistochemical marker intensity and percentage of positivity using known and novel digital techniques.

MATERIALS AND METHODS

An experimental non-inferiority study has been performed on 72 pineal glands harvested from post-mortem examinations. The glands have been stained with glial fibrillary acidic protein (GFAP), synaptophysin (SYN), neuron-specific enolase (NSE), and neurofilament (NF). Slides were digitally scanned. Morphometric data were obtained using optical analysis, CaseViewer, ImageJ, and MorphoRGB RESULTS: Strong and statistically significant correlations were found and plotted using Bland-Altman diagrams between the two image analysis software in the case of mean percentage and intensity of GFAP, NSE, NF, and SYN.

DISCUSSIONS

Software such as SlideViewer and ImageJ, with our novel software MorphoRGB were used to perform histological morphometry of the pineal gland. Digital morphometry of a small organ such as the pineal gland is easy to do by using whole slide imaging (WSI) and digital image analysis software, with potential use in clinical settings. MorphoRGB provides slightly more accurate data than ImageJ and is more user-friendly regarding measurements of parenchyma percentage stained by immunohistochemistry. The results show that MorphoRGB is not inferior in functionality.

CONCLUSIONS

The described morphometric techniques have potential value in current practice, experimental small animal models and human pineal glands, or other small endocrine organs that can be fully included in a whole slide image. The software we used has applications in quantifying immunohistochemical stains.

Expression of NGF/proNGF and Their Receptors TrkA, p75NTR and Sortilin in Melanoma

There is increasing evidence that nerve growth factor (NGF) and its receptors, the neurotrophic receptor tyrosine kinase 1 (NTRK1/TrkA), the common neurotrophin receptor (NGFR/p75NTR) and the membrane receptor sortilin, participate in cancer growth. In melanoma, there have been some reports suggesting that NGF, TrkA and p75NTR are dysregulated, but the expression of the NGF precursor (proNGF) and its membrane receptor sortilin is unknown. In this study, we investigated the expression of NGF, proNGF, TrkA, p75NTR and sortilin by immunohistochemistry in a series of human tissue samples (n = 100), including non-cancerous nevi (n = 20), primary melanomas (n = 40), lymph node metastases (n = 20) and distant metastases (n = 20). Immunostaining was digitally quantified and revealed NGF and proNGF were expressed in all nevi and primary melanomas, and that the level of expression decreased from primary tumors to melanoma metastases (p = 0.0179 and p < 0.0001, respectively). Interestingly, TrkA protein expression was high in nevi and thin primary tumors but was strongly downregulated in thick primary tumors (p < 0.0001) and metastases (p < 0.0001). While p75NTR and sortilin were both expressed in most nevi and melanomas, there was no significant difference in expression between them. Together, these results pointed to a downregulation of NGF/ProNGF and TrkA in melanoma, and thus did not provide evidence to support the use of anti-proNGF/NGF or anti-TrkA therapies in advanced and metastatic forms of melanoma.

Multiparameter immunohistochemistry analysis of HIV DNA, RNA and immune checkpoints in lymph node tissue

The main barrier to a cure for HIV is the persistence of long-lived and proliferating latently infected CD4+ T-cells despite antiretroviral therapy (ART). Latency is well characterized in multiple CD4+ T-cell subsets, however, the contribution of regulatory T-cells (Tregs) expressing FoxP3 as well as immune checkpoints (ICs) PD-1 and CTLA-4 as targets for productive and latent HIV infection in people living with HIV on suppressive ART is less well defined. We used multiplex detection of HIV DNA and RNA with immunohistochemistry (mIHC) on formalin-fixed paraffin embedded (FFPE) cells to simultaneously detect HIV RNA and DNA and cellular markers. HIV DNA and RNA were detected by in situ hybridization (ISH) (RNA/DNAscope) and IHC was used to detect cellular markers (CD4, PD-1, FoxP3, and CTLA-4) by incorporating the tyramide system amplification (TSA) system. We evaluated latently infected cell lines, a primary cell model of HIV latency and excisional lymph node (LN) biopsies collected from people living with HIV (PLWH) on and off ART. We clearly detected infected cells that coexpressed HIV RNA and DNA (active replication) and DNA only (latently infected cells) in combination with IHC markers in the in vitro infection model as well as LN tissue from PLWH both on and off ART. Combining ISH targeting HIV RNA and DNA with IHC provides a platform to detect and quantify HIV persistence within cells identified by multiple markers in tissue samples from PLWH on ART or to study HIV latency.

Deep Learning-Based Model Significantly Improves Diagnostic Performance for Assessing Renal Histopathology in Lupus Glomerulonephritis

<b><i>Background:</i></b> Assessment of glomerular lesions and structures plays an essential role in understanding the pathological diagnosis of glomerulonephritis and prognostic evaluation of many kidney diseases. Renal pathophysiological assessment requires novel high-throughput tools to conduct quantitative, unbiased, and reproducible analyses representing a central readout. Deep learning may be an effective tool for glomerulonephritis pathological analysis. <b><i>Methods:</i></b> We developed a murine renal pathological system (MRPS) model to objectify the pathological evaluation via the deep learning method on whole-slide image (WSI) segmentation and feature extraction. A convolutional neural network model was used for accurate segmentation of glomeruli and glomerular cells of periodic acid-Schiff-stained kidney tissue from healthy and lupus nephritis mice. To achieve a quantitative evaluation, we subsequently filtered five independent predictors as image biomarkers from all features and developed a formula for the scoring model. <b><i>Results:</i></b> Perimeter, shape factor, minimum internal diameter, minimum caliper diameter, and number of objects were identified as independent predictors and were included in the establishment of the MRPS. The MRPS showed a positive correlation with renal score (<i>r</i> = 0.480, <i>p</i> &#x3c; 0.001) and obtained great diagnostic performance in discriminating different score bands (Obuchowski index, 0.842 [95% confidence interval: 0.759, 0.925]), with an area under the curve of 0.78–0.98, sensitivity of 58–93%, specificity of 72–100%, and accuracy of 74–94%. <b><i>Conclusion:</i></b> Our MRPS for quantitative assessment of renal WSIs from MRL/lpr lupus nephritis mice enables accurate histopathological analyses with high reproducibility, which may serve as a useful tool for glomerulonephritis diagnosis and prognosis evaluation.

Deep Learning Approaches and Applications in Toxicologic Histopathology: Current Status and Future Perspectives

Whole slide imaging enables the use of a wide array of digital image analysis tools that are revolutionizing pathology. Recent advances in digital pathology and deep convolutional neural networks have created an enormous opportunity to improve workflow efficiency, provide more quantitative, objective, and consistent assessments of pathology datasets, and develop decision support systems. Such innovations are already making their way into clinical practice. However, the progress of machine learning - in particular, deep learning (DL) - has been rather slower in nonclinical toxicology studies. Histopathology data from toxicology studies are critical during the drug development process that is required by regulatory bodies to assess drug-related toxicity in laboratory animals and its impact on human safety in clinical trials. Due to the high volume of slides routinely evaluated, low-throughput, or narrowly performing DL methods that may work well in small-scale diagnostic studies or for the identification of a single abnormality are tedious and impractical for toxicologic pathology. Furthermore, regulatory requirements around good laboratory practice are a major hurdle for the adoption of DL in toxicologic pathology. This paper reviews the major DL concepts, emerging applications, and examples of DL in toxicologic pathology image analysis. We end with a discussion of specific challenges and directions for future research.

spatialTIME and iTIME: R package and Shiny application for visualization and analysis of immunofluorescence data

Summary

Multiplex immunofluorescence (mIF) staining combined with quantitative digital image analysis is a novel and increasingly used technique that allows for the characterization of the tumor immune microenvironment (TIME). Generally, mIF data is used to examine the abundance of immune cells in the TIME; however, this does not capture spatial patterns of immune cells throughout the TIME, a metric increasingly recognized as important for prognosis. To address this gap, we developed an R package spatialTIME that enables spatial analysis of mIF data, as well as the iTIME web application that provides a robust but simplified user interface for describing both abundance and spatial architecture of the TIME. The spatialTIME package calculates univariate and bivariate spatial statistics (e.g. Ripley’s K, Besag’s L, Macron’s M and G or nearest neighbor distance) and creates publication quality plots for spatial organization of the cells in each tissue sample. The iTIME web application allows users to statistically compare the abundance measures with patient clinical features along with visualization of the TIME for one tissue sample at a time.

Availability and implementation

spatialTIME is implemented in R and can be downloaded from GitHub (https://github.com/FridleyLab/spatialTIME) or CRAN. An extensive vignette for using spatialTIME can also be found at https://cran.r-project.org/web/packages/spatialTIME/index.html. iTIME is implemented within a R Shiny application and can be accessed online (http://itime.moffitt.org/), with code available on GitHub (https://github.com/FridleyLab/iTIME).

Supplementary information

Supplementary data are available at Bioinformatics online.

Challenges and Opportunities in the Statistical Analysis of Multiplex Immunofluorescence Data

Simple Summary

Immune modulation is considered a hallmark of cancer initiation and progression, and has offered promising opportunities for therapeutic manipulation. Multiplex immunofluorescence (mIF) technology has enabled the tumor immune microenvironment (TIME) to be studied at an increased scale, in terms of both the number of markers and the number of samples. Another benefit of mIF technology is the ability to measure not only the abundance but also the spatial location of multiple cells types within a tissue sample simultaneously, allowing for assessment of the co-localization of different types of immune markers. Thus, the use of mIF technologies have enable researchers to characterize patient, clinical, and tumor characteristics in the hope of identifying patients whom might benefit from immunotherapy treatments. In this review we outline some of the challenges and opportunities in the statistical analyses of mIF data to study the TIME.

Abstract

Immune modulation is considered a hallmark of cancer initiation and progression. The recent development of immunotherapies has ushered in a new era of cancer treatment. These therapeutics have led to revolutionary breakthroughs; however, the efficacy of immunotherapy has been modest and is often restricted to a subset of patients. Hence, identification of which cancer patients will benefit from immunotherapy is essential. Multiplex immunofluorescence (mIF) microscopy allows for the assessment and visualization of the tumor immune microenvironment (TIME). The data output following image and machine learning analyses for cell segmenting and phenotyping consists of the following information for each tumor sample: the number of positive cells for each marker and phenotype(s) of interest, number of total cells, percent of positive cells for each marker, and spatial locations for all measured cells. There are many challenges in the analysis of mIF data, including many tissue samples with zero positive cells or “zero-inflated” data, repeated measurements from multiple TMA cores or tissue slides per subject, and spatial analyses to determine the level of clustering and co-localization between the cell types in the TIME. In this review paper, we will discuss the challenges in the statistical analysis of mIF data and opportunities for further research.

Conventional and semi-automatic histopathological analysis of tumor cell content for multigene sequencing of lung adenocarcinoma

Background

Targeted genetic profiling of tissue samples is paramount to detect druggable genetic aberrations in patients with non-squamous non-small cell lung cancer (NSCLC). Accurate upfront estimation of tumor cell content (TCC) is a crucial pre-analytical step for reliable testing and to avoid false-negative results. As of now, TCC is usually estimated on hematoxylin-eosin (H&E) stained tissue sections by a pathologist, a methodology that may be prone to substantial intra- and interobserver variability. Here we the investigate suitability of digital pathology for TCC estimation in a clinical setting by evaluating the concordance between semi-automatic and conventional TCC quantification.

Methods

TCC was analyzed in 120 H&E and thyroid transcription factor 1 (TTF-1) stained high-resolution images by 19 participants with different levels of pathological expertise as well as by applying two semi-automatic digital pathology image analysis tools (HALO and QuPath).

Results

Agreement of TCC estimations [intra-class correlation coefficients (ICC)] between the two software tools (H&E: 0.87; TTF-1: 0.93) was higher compared to that between conventional observers (0.48; 0.47). Digital TCC estimations were in good agreement with the average of human TCC estimations (0.78; 0.96). Conventional TCC estimators tended to overestimate TCC, especially in H&E stainings, in tumors with solid patterns and in tumors with an actual TCC close to 50%.

Conclusions

Our results determine factors that influence TCC estimation. Computer-assisted analysis can improve the accuracy of TCC estimates prior to molecular diagnostic workflows. In addition, we provide a free web application to support self-training and quality improvement initiatives at other institutions.

Deep Learning in Toxicologic Pathology: A New Approach to Evaluate Rodent Retinal Atrophy

Quantification of retinal atrophy, caused by therapeutics and/or light, by manual measurement of retinal layers is labor intensive and time-consuming. In this study, we explored the role of deep learning (DL) in automating the assessment of retinal atrophy, particularly of the outer and inner nuclear layers, in rats. Herein, we report our experience creating and employing a hybrid approach, which combines conventional image processing and DL to quantify rodent retinal atrophy. Utilizing a DL approach based upon the VGG16 model architecture, models were trained, tested, and validated using 10,746 image patches scanned from whole slide images (WSIs) of hematoxylin-eosin stained rodent retina. The accuracy of this computational method was validated using pathologist annotated WSIs throughout and used to separately quantify the thickness of the outer and inner nuclear layers of the retina. Our results show that DL can facilitate the evaluation of therapeutic and/or light-induced atrophy, particularly of the outer retina, efficiently in rodents. In addition, this study provides a template which can be used to train, validate, and analyze the results of toxicologic pathology DL models across different animal species used in preclinical efficacy and safety studies.

Quantitative neurotoxicology: Potential role of artificial intelligence/deep learning approach

Neurotoxicity studies are important in the preclinical stages of drug development process, because exposure to certain compounds that may enter the brain across a permeable blood brain barrier damages neurons and other supporting cells such as astrocytes. This could, in turn, lead to various neurological disorders such as Parkinson's or Huntington's disease as well as various dementias. Toxicity assessment is often done by pathologists after these exposures by qualitatively or semiquantitatively grading the severity of neurotoxicity in histopathology slides. Quantification of the extent of neurotoxicity supports qualitative histopathological analysis and provides a better understanding of the global extent of brain damage. Stereological techniques such as the utilization of an optical fractionator provide an unbiased quantification of the neuronal damage; however, the process is time-consuming. Advent of whole slide imaging (WSI) introduced digital image analysis which made quantification of neurotoxicity automated, faster and with reduced bias, making statistical comparisons possible. Although automated to a certain level, simple digital image analysis requires manual efforts of experts which is time-consuming and limits analysis of large datasets. Digital image analysis coupled with a deep learning artificial intelligence model provides a good alternative solution to time-consuming stereological and simple digital analysis. Deep learning models could be trained to identify damaged or dead neurons in an automated fashion. This review has focused on and discusses studies demonstrating the role of deep learning in segmentation of brain regions, toxicity detection and quantification of degenerated neurons as well as the estimation of area/volume of degeneration.