Automated quantification of steatosis: agreement with stereological point counting

Modelling the Tumour Microenvironment, but What Exactly Do We Mean by "Model"?

The Oxford English Dictionary includes 17 definitions for the word "model" as a noun and another 11 as a verb. Therefore, context is necessary to understand the meaning of the word model. For instance, "model railways" refer to replicas of railways and trains at a smaller scale and a "model student" refers to an exemplary individual. In some cases, a specific context, like cancer research, may not be sufficient to provide one specific meaning for model. Even if the context is narrowed, specifically, to research related to the tumour microenvironment, "model" can be understood in a wide variety of ways, from an animal model to a mathematical expression. This paper presents a review of different "models" of the tumour microenvironment, as grouped by different definitions of the word into four categories: model organisms, in vitro models, mathematical models and computational models. Then, the frequencies of different meanings of the word "model" related to the tumour microenvironment are measured from numbers of entries in the MEDLINE database of the United States National Library of Medicine at the National Institutes of Health. The frequencies of the main components of the microenvironment and the organ-related cancers modelled are also assessed quantitatively with specific keywords. Whilst animal models, particularly xenografts and mouse models, are the most commonly used "models", the number of these entries has been slowly decreasing. Mathematical models, as well as prognostic and risk models, follow in frequency, and these have been growing in use.

ZFP36L1 Regulates Fgf21 mRNA Turnover and Modulates Alcoholic Hepatic Steatosis and Inflammation in Mice

Zinc finger protein 36 like 1 (ZFP36L1) enhances the turnover of mRNAs containing AU-rich elements (AREs) in their 3'-untranslated regions (3'UTR). The physiological and pathological functions of ZFP36L1 in liver, however, remain largely unknown. Liver-specific ZFP36L1-deficient (Zfp36l1^flox/flox/Cre⁺; L1^LKO) mice were generated to investigate the role of ZFP36L1 in liver physiology and pathology. Under normal conditions, the L1^LKO mice and their littermate controls (Zfp36l1^flox/flox/Cre^-; L1^FLX) appeared normal. When fed a Lieber-DeCarli liquid diet containing alcohol, L1^LKO mice were significantly protected from developing alcohol-induced hepatic steatosis, injury, and inflammation compared with L1^FLX mice. Most importantly, fibroblast growth factor 21 (Fgf21) mRNA was significantly increased in the livers of alcohol diet-fed L1^LKO mice compared with the alcohol diet-fed L1^FLX group. The Fgf21 mRNA contains three AREs in its 3'UTR, and Fgf21 3'UTR was directly regulated by ZFP36L1 in luciferase reporter assays. Steady-state levels of Fgf21 mRNA were significantly decreased by wild-type ZFP36L1, but not by a non-binding zinc finger ZFP36L1 mutant. Finally, wild-type ZFP36L1, but not the ZFP36L1 mutant, bound to the Fgf21 3'UTR ARE RNA probe. These results demonstrate that ZFP36L1 inactivation protects against alcohol-induced hepatic steatosis and liver injury and inflammation, possibly by stabilizing Fgf21 mRNA. These findings suggest that the modulation of ZFP36L1 may be beneficial in the prevention or treatment of human alcoholic liver disease.

Recommendations on compiling test datasets for evaluating artificial intelligence solutions in pathology

Artificial intelligence (AI) solutions that automatically extract information from digital histology images have shown great promise for improving pathological diagnosis. Prior to routine use, it is important to evaluate their predictive performance and obtain regulatory approval. This assessment requires appropriate test datasets. However, compiling such datasets is challenging and specific recommendations are missing. A committee of various stakeholders, including commercial AI developers, pathologists, and researchers, discussed key aspects and conducted extensive literature reviews on test datasets in pathology. Here, we summarize the results and derive general recommendations on compiling test datasets. We address several questions: Which and how many images are needed? How to deal with low-prevalence subsets? How can potential bias be detected? How should datasets be reported? What are the regulatory requirements in different countries? The recommendations are intended to help AI developers demonstrate the utility of their products and to help pathologists and regulatory agencies verify reported performance measures. Further research is needed to formulate criteria for sufficiently representative test datasets so that AI solutions can operate with less user intervention and better support diagnostic workflows in the future.

Quantitative magnetic resonance imaging for chronic liver disease

Chronic liver disease (CLD) has rapidly increased in prevalence over the past two decades, resulting in significant morbidity and mortality worldwide. Historically, the clinical gold standard for diagnosis, assessment of severity, and longitudinal monitoring of CLD has been liver biopsy with histological analysis, but this approach has limitations that may make it suboptimal for clinical and research settings. Magnetic resonance (MR)-based biomarkers can overcome the limitations by allowing accurate, precise, and quantitative assessment of key components of CLD without the risk of invasive procedures. This review briefly describes the limitations associated with liver biopsy and the need for non-invasive biomarkers. It then discusses the current state-of-the-art for MRI-based biomarkers of liver iron, fat, and fibrosis, and inflammation.

Systematic Evaluation of the Safety Threshold for Allograft Macrovesicular Steatosis in Cadaveric Liver Transplantation

Background: Currently, 30% macrovesicular steatosis (MaS) content is usually assigned empirically as the boundary between “use” and “refuse” a donor liver for liver transplantation (LT); however, this cut-off is questionable due to the lack of systemic evidence of the efficiency relative to prognosis prediction. Clinicians have tried to identify the threshold for optimized utilization of marginal steatotic allografts, but controversy exists among different studies.

Aim: Our study aimed to systematically determine an acceptable donor MaS content cut-off without incurring extra risk in liver transplantation, using meta-analysis.

Methods: The relevant literature reporting the relationship between MaS content and post-transplant mortality/morbidity was searched and retrieved in Pubmed, Embase, and ISI Web of Science.

Results: Nine studies were enrolled into the final analysis. A categorical comparison revealed that patients who received allografts with moderate steatosis (MaS content >30%) had significantly higher risks of graft failure/dysfunction, but not of mortality. Dose-response analysis showed that donor MaS content affected the graft failure/dysfunction in a non-linear relationship. Risks associated with MaS content in terms of poorer outcomes were independent of other risk covariates for liver transplantation. A non-significant increase in risk of inferior post-transplant outcomes was observed in patients who received allografts with a MaS content <35%. The risks of post-transplant graft failure and dysfunction increased with severe donor MaS content infiltration, without a consistent relationship.

Conclusions: The threshold of allograft MaS content can be safely extended to 35% without additional risk burden on post-transplant inferior outcomes. Clarification on “the effects of stratification” for MaS content can provide theoretical evidence for further optimal utilization of marginal steatotic allografts in liver transplantation.

LIVER STEATOSIS SEGMENTATION WITH DEEP LEARNING METHODS

Liver steatosis is known as the abnormal accumulation of lipids within cells. An accurate quantification of steatosis area within the liver histopathological microscopy images plays an important role in liver disease diagnosis and transplantation assessment. Such a quantification analysis often requires a precise steatosis segmentation that is challenging due to abundant presence of highly overlapped steatosis droplets. In this paper, a deep learning model Mask-RCNN is used to segment the steatosis droplets in clumps. Extended from Faster R-CNN, Mask-RCNN can predict object masks in addition to bounding box detection. With transfer learning, the resulting model is able to segment overlapped steatosis regions at 75.87% by Average Precision, 60.66% by Recall,65.88% by F1-score, and 76.97% by Jaccard index, promising to support liver disease diagnosis and allograft rejection prediction in future clinical practice.

Automatic stereology of mean nuclear size of neurons using an active contour framework

The use of unbiased stereology to quantify structural parameters such as mean cell and nuclear size (area and volume) can be useful for a wide variety of biological studies. Here we propose a novel segmentation framework using an Active Contour Model to automate the collection of stereology from stained cells and other objects in tissue sections. This approach is demonstrated for stained brain sections from young adult Fischer 344 rats. Animals were perfused in-vivo with 4% paraformaldehyde and sectioned by frozen microtomy at an instrument setting of 40 μm. For each rat brain, a systematic-random set of sections through the entire substantia nigra pars compacta (SN) were immunostained to reveal tyrosine hydroxylase (TH)-immunopositive neurons. The novel framework applied an active contour (modified balloon snake) model with non-constant balloon force to automatically segment and quantify neuronal cell bodies by stereological point counting (SPC). Several contours were initialized in the image and based on the contour fit after 200 iterations classified as immunopositive (signal) or background contours in a sequential manner. Cell contours were determined in four steps based on several criteria, e.g., area of contour, dispersion measure, and degree of overlap. The image was automatically segmented according to the final contours. Using a point grid automatically generated at systematic-random orientations over the images, points hitting the segmented neural cell bodies were automatically counted. The final values from the automatic framework were compared with findings for ground truth (manual SPC). The results of this study show a strong agreement between data collected by the automatic framework and the ground truth (R² ≥ 0.95) with a 5× gain in time efficiency for the automatic SPC. These findings give strong support for future applications of pattern recognition for assessing stereological parameters of biological objects identified by high signal:noise stains.

Quantification of hepatic steatosis in histologic images by deep learning method

OBJECTIVE

To develop and test a novel method for automatic quantification of hepatic steatosis in histologic images based on the deep learning scheme designed to predict the fat ratio directly, which aims to improve accuracy in diagnosis of non-alcoholic fatty liver disease (NAFLD) with objective assessment of the severity of hepatic steatosis instead of subjective visual estimation.

MATERIALS AND METHODS

Thirty-six 8-week old New Zealand white rabbits of both sexes were fed with high-cholesterol, high-fat diet and sacrificed under deep anesthesia at various time points to obtain the pathological specimen. All rabbits were performed by multislice computed tomography for surveillance to measure density changes of liver parenchyma. A deep learning scheme using a convolutional neural network was developed to directly predict the liver fat ratio based on the pathological images. The average error value, standard deviation, and accuracy (error <5%) were evaluated and compared between the deep learning scheme and manual segmentation results. The Pearson's correlation coefficient was also calculated in this study.

RESULTS

The deep learning scheme performs successfully on rabbit liver histologic data, showing a high degree of accuracy and stability. The average error value, standard deviation, and accuracy (error <5%) were 3.21%, 4.02%, and 79.10% for the cropped images, 2.22%, 1.92%, and 88.34% for the original images, respectively. The strong positive correlation was also observed for cropped images (R = 0.9227) and original images (R = 0.9255) in comparison to labeled fat ratio.

CONCLUSIONS

This new deep learning scheme may aid in the quantification of steatosis in the liver and facilitate its treatment by providing an earlier clinical diagnosis.

Focused scores enable reliable discrimination of small differences in steatosis

Background

Automated image analysis enables quantitative measurement of steatosis in histological images. However, spatial heterogeneity of steatosis can make quantitative steatosis scores unreliable. To improve the reliability, we have developed novel scores that are “focused” on steatotic tissue areas.

Methods

Focused scores use concepts of tile-based hotspot analysis in order to compute statistics about steatotic tissue areas in an objective way. We evaluated focused scores on three data sets of images of rodent liver sections exhibiting different amounts of dietary-induced steatosis. The same evaluation was conducted with the standard steatosis score computed by most image analysis methods.

Results

The standard score reliably discriminated large differences in steatosis (intraclass correlation coefficient ICC = 0.86), but failed to discriminate small (ICC = 0.54) and very small (ICC = 0.14) differences. With an appropriate tile size, mean-based focused scores reliably discriminated large (ICC = 0.92), small (ICC = 0.86) and very small (ICC = 0.83) differences. Focused scores based on high percentiles showed promise in further improving the discrimination of very small differences (ICC = 0.93).

Conclusions

Focused scores enable reliable discrimination of small differences in steatosis in histological images. They are conceptually simple and straightforward to use in research studies.