Fully automated quantitative assessment of hepatic steatosis in liver transplants

Enhancing AI Research for Breast Cancer: A Comprehensive Review of Tumor-Infiltrating Lymphocyte Datasets

The field of immunology is fundamental to our understanding of the intricate dynamics of the tumor microenvironment. In particular, tumor-infiltrating lymphocyte (TIL) assessment emerges as essential aspect in breast cancer cases. To gain comprehensive insights, the quantification of TILs through computer-assisted pathology (CAP) tools has become a prominent approach, employing advanced artificial intelligence models based on deep learning techniques. The successful recognition of TILs requires the models to be trained, a process that demands access to annotated datasets. Unfortunately, this task is hampered not only by the scarcity of such datasets, but also by the time-consuming nature of the annotation phase required to create them. Our review endeavors to examine publicly accessible datasets pertaining to the TIL domain and thereby become a valuable resource for the TIL community. The overall aim of the present review is thus to make it easier to train and validate current and upcoming CAP tools for TIL assessment by inspecting and evaluating existing publicly available online datasets.

Improved assessment of donor liver steatosis using Banff consensus recommendations and deep learning algorithms

BACKGROUND & AIMS

The Banff Liver Working Group recently published consensus recommendations for steatosis assessment in donor liver biopsy, but few studies reported their use and no automated deep-learning algorithms based on the proposed criteria have been developed so far. We evaluated Banff recommendations on a large monocentric series of donor liver needle biopsies by comparing pathologists' scores with those generated by convolutional neural networks (CNNs) we specifically developed for automated steatosis assessment.

METHODS

We retrospectively retrieved 292 allograft liver needle biopsies collected between January 2016 and January 2020 and performed steatosis assessment using a former intra-institution method (pre-Banff method) and the newly introduced Banff recommendations. Scores provided by pathologists and CNN models were then compared, and the degree of agreement was measured with the intraclass correlation coefficient (ICC).

RESULTS

Regarding the pre-Banff method, poor agreement was observed between the pathologist and CNN models for small droplet macrovesicular steatosis (ICC: 0.38), large droplet macrovesicular steatosis (ICC: 0.08), and the final combined score (ICC: 0.16) evaluation, but none of these reached statistically significance. Interestingly, significantly improved agreement was observed using the Banff approach: ICC was 0.93 for the low-power score (p <0.001), 0.89 for the high-power score (p <0.001), and 0.93 for the final score (p <0.001). Comparing the pre-Banff method with the Banff approach on the same biopsy, pathologist and CNN model assessment showed a mean (±SD) percentage of discrepancy of 26.89 (±22.16) and 1.20 (±5.58), respectively.

CONCLUSIONS

Our findings support the use of Banff recommendations in daily practice and highlight the need for a granular analysis of their effect on liver transplantation outcomes.

IMPACT AND IMPLICATIONS

We developed and validated the first automated deep-learning algorithms for standardized steatosis assessment based on the Banff Liver Working Group consensus recommendations. Our algorithm provides an unbiased automated evaluation of steatosis, which will lay the groundwork for granular analysis of steatosis's short- and long-term effects on organ viability, enabling the identification of clinically relevant steatosis cut-offs for donor organ acceptance. Implementing our algorithm in daily clinical practice will allow for a more efficient and safe allocation of donor organs, improving the post-transplant outcomes of patients.

Deep Learning Neural Network-Guided Detection of Asbestos Bodies in Bronchoalveolar Lavage Samples

INTRODUCTION

Asbestos is a global occupational health hazard, and exposure to it by inhalation predisposes to interstitial as well as malignant pulmonary morbidity. Over time, asbestos fibers embedded in lung tissue can become coated with iron-rich proteins and mucopolysaccharides, after which they are called asbestos bodies (ABs) and can be detected in light microscopy (LM). Bronchoalveolar lavage, a cytological sample from the lower airways, is one of the methods for diagnosing lung asbestosis and related morbidity. Search for ABs in these samples is generally laborious and time-consuming. We describe a novel diagnostic method, which implements deep learning neural network technology for the detection of ABs in bronchoalveolar lavage samples (BALs).

METHODS

BALs with suspicion of asbestos exposure were scanned as whole slide images (WSIs) and uploaded to a cloud-based virtual microscopy platform with a neural network training interface. The images were used for training and testing a neural network model capable of recognizing ABs. To prioritize the model's sensitivity, we allowed it to also make false-positive suggestions. To test the model, we compared its performance to standard LM diagnostic data as well as the ground truth (GT) number of ABs, which we established by a thorough manual search of the WSIs.

RESULTS

We were able to reach overall sensitivity of 93.4% (95% CI: 90.3-95.7%) in the detection of ABs in comparison to their GT number. Compared to standard LM diagnostic data, our model showed equal to or higher sensitivity in most cases.

CONCLUSION

Our results indicate that deep learning neural network technology offers promising diagnostic tools for routine assessment of BALs. However, at this stage, a human expert is required to confirm the findings.

Artificial Intelligence-Based Opportunities in Liver Pathology-A Systematic Review

BACKGROUND

Artificial Intelligence (AI)-based Deep Neural Networks (DNNs) can handle a wide range of applications in image analysis, ranging from automated segmentation to diagnostic and prediction. As such, they have revolutionized healthcare, including in the liver pathology field.

OBJECTIVE

The present study aims to provide a systematic review of applications and performances provided by DNN algorithms in liver pathology throughout the Pubmed and Embase databases up to December 2022, for tumoral, metabolic and inflammatory fields.

RESULTS

42 articles were selected and fully reviewed. Each article was evaluated through the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool, highlighting their risks of bias.

CONCLUSIONS

DNN-based models are well represented in the field of liver pathology, and their applications are diverse. Most studies, however, presented at least one domain with a high risk of bias according to the QUADAS-2 tool. Hence, DNN models in liver pathology present future opportunities and persistent limitations. To our knowledge, this review is the first one solely focused on DNN-based applications in liver pathology, and to evaluate their bias through the lens of the QUADAS2 tool.

Comprehensive Approach to Assessment of Liver Viability During Normothermic Machine Perfusion

Liver transplantation is the most effective treatment of advanced liver disease, and the use of extended criteria donor organs has broadened the source of available livers. Although normothermic machine perfusion (NMP) has become a useful tool in liver transplantation, there are no consistent criteria that can be used to evaluate the viability of livers during NMP. This review summarizes the criteria, indicators, and methods used to evaluate liver viability during NMP. The shape, appearance, and hemodynamics of the liver can be analyzed at a macroscopic level, while markers of liver injury, indicators of liver and bile duct function, and other relevant indicators can be evaluated by biochemical analysis. The liver can also be assessed by tissue biopsy at the microscopic level. Novel methods for assessment of liver viability are introduced. The limitations of evaluating liver viability during NMP are discussed and suggestions for future clinical practice are provided.

How Can Machine Perfusion Change the Paradigm of Liver Transplantation for Patients with Perihilar Cholangiocarcinoma?

Perihilar cholangiocarcinomas (pCCA) are rare yet aggressive tumors originating from the bile ducts. While surgery remains the mainstay of treatment, only a minority of patients are amenable to curative resection, and the prognosis of unresectable patients is dismal. The introduction of liver transplantation (LT) after neoadjuvant chemoradiation for unresectable pCCA in 1993 represented a major breakthrough, and it has been associated with 5-year survival rates consistently >50%. Despite these encouraging results, pCCA has remained a niche indication for LT, which is most likely due to the need for stringent candidate selection and the challenges in preoperative and surgical management. Machine perfusion (MP) has recently been reintroduced as an alternative to static cold storage to improve liver preservation from extended criteria donors. Aside from being associated with superior graft preservation, MP technology allows for the safe extension of preservation time and the testing of liver viability prior to implantation, which are characteristics that may be especially useful in the setting of LT for pCCA. This review summarizes current surgical strategies for pCCA treatment, with a focus on unmet needs that have contributed to the limited spread of LT for pCCA and how MP could be used in this setting, with a particular emphasis on the possibility of expanding the donor pool and improving transplant logistics.

Accurate and generalizable quantitative scoring of liver steatosis from ultrasound images via scalable deep learning

BACKGROUND

Hepatic steatosis is a major cause of chronic liver disease. Two-dimensional (2D) ultrasound is the most widely used non-invasive tool for screening and monitoring, but associated diagnoses are highly subjective.

AIM

To develop a scalable deep learning (DL) algorithm for quantitative scoring of liver steatosis from 2D ultrasound images.

METHODS

Using multi-view ultrasound data from 3310 patients, 19513 studies, and 228075 images from a retrospective cohort of patients received elastography, we trained a DL algorithm to diagnose steatosis stages (healthy, mild, moderate, or severe) from clinical ultrasound diagnoses. Performance was validated on two multi-scanner unblinded and blinded (initially to DL developer) histology-proven cohorts (147 and 112 patients) with histopathology fatty cell percentage diagnoses and a subset with FibroScan diagnoses. We also quantified reliability across scanners and viewpoints. Results were evaluated using Bland-Altman and receiver operating characteristic (ROC) analysis.

RESULTS

The DL algorithm demonstrated repeatable measurements with a moderate number of images (three for each viewpoint) and high agreement across three premium ultrasound scanners. High diagnostic performance was observed across all viewpoints: Areas under the curve of the ROC to classify mild, moderate, and severe steatosis grades were 0.85, 0.91, and 0.93, respectively. The DL algorithm outperformed or performed at least comparably to FibroScan control attenuation parameter (CAP) with statistically significant improvements for all levels on the unblinded histology-proven cohort and for “= severe” steatosis on the blinded histology-proven cohort.

CONCLUSION

The DL algorithm provides a reliable quantitative steatosis assessment across view and scanners on two multi-scanner cohorts. Diagnostic performance was high with comparable or better performance than the CAP.

Hyperspectral imaging for quantitative assessment of hepatic steatosis in human liver allografts

INTRODUCTION

In liver transplantation (LT), steatosis is commonly judged to be a risk factor for graft dysfunction, and quantitative assessment of hepatic steatosis remains crucial. Liver biopsy as the gold standard for evaluation of hepatic steatosis has certain drawbacks, i.e. invasiveness, and intra- and inter-observer variability. A non-invasive, quantitative modality could replace liver biopsy and eliminate these disadvantages, but has not yet been evaluated in human LT.

METHODS

We performed a pilot study to evaluate the feasibility and accuracy of hyperspectral imaging (HSI) in the assessment of hepatic steatosis of human liver allografts for transplantation. Thirteen deceased donor liver allografts were included in the study. The degree of steatosis was assessed by means of conventional liver biopsy as well as HSI, performed at the end of backtable preparation, during normothermic machine perfusion (NMP), and after reperfusion in the recipient.

RESULTS

Organ donors were 51 [30-83] years old, and 61.5% were male. Donor body mass index was 24.2 [16.5-38.0] kg/m2. The tissue lipid index (TLI) generated by HSI at the end of back-table preparation correlated significantly with the histopathologically assessed degree of overall hepatic steatosis (R2 = 0.9085, p<0.0001); this was based on a correlation of TLI and microvesicular steatosis (R2 = 0.8120; p<0.0001). There is also a linear relationship between the histopathologically assessed degree of overall steatosis and TLI during NMP (R2 = 0.5646; p = 0.0031) as well as TLI after reperfusion (R2 = 0.6562; p = 0.0008).

CONCLUSION

HSI may safely be applied for accurate assessment of hepatic steatosis in human liver grafts. Certainly, TLI needs further assessment and validation in larger sample sizes. This article is protected by copyright. All rights reserved.

Integration of Deep Learning and Active Shape Models for More Accurate Prostate Segmentation in 3D MR Images

Magnetic resonance imaging (MRI) has a growing role in the clinical workup of prostate cancer. However, manual three-dimensional (3D) segmentation of the prostate is a laborious and time-consuming task. In this scenario, the use of automated algorithms for prostate segmentation allows us to bypass the huge workload of physicians. In this work, we propose a fully automated hybrid approach for prostate gland segmentation in MR images using an initial segmentation of prostate volumes using a custom-made 3D deep network (VNet-T2), followed by refinement using an Active Shape Model (ASM). While the deep network focuses on three-dimensional spatial coherence of the shape, the ASM relies on local image information and this joint effort allows for improved segmentation of the organ contours. Our method is developed and tested on a dataset composed of T2-weighted (T2w) MRI prostatic volumes of 60 male patients. In the test set, the proposed method shows excellent segmentation performance, achieving a mean dice score and Hausdorff distance of 0.851 and 7.55 mm, respectively. In the future, this algorithm could serve as an enabling technology for the development of computer-aided systems for prostate cancer characterization in MR imaging.

Automatic Liver Segmentation in CT Images with Enhanced GAN and Mask Region-Based CNN Architectures

Liver image segmentation has been increasingly employed for key medical purposes, including liver functional assessment, disease diagnosis, and treatment. In this work, we introduce a liver image segmentation method based on generative adversarial networks (GANs) and mask region-based convolutional neural networks (Mask R-CNN). Firstly, since most resulting images have noisy features, we further explored the combination of Mask R-CNN and GANs in order to enhance the pixel-wise classification. Secondly, k-means clustering was used to lock the image aspect ratio, in order to get more essential anchors which can help boost the segmentation performance. Finally, we proposed a GAN Mask R-CNN algorithm which achieved superior performance in comparison with the conventional Mask R-CNN, Mask-CNN, and k-means algorithms in terms of the Dice similarity coefficient (DSC) and the MICCAI metrics. The proposed algorithm also achieved superior performance in comparison with ten state-of-the-art algorithms in terms of six Boolean indicators. We hope that our work can be effectively used to optimize the segmentation and classification of liver anomalies.

State of machine and deep learning in histopathological applications in digestive diseases

Machine learning (ML)- and deep learning (DL)-based imaging modalities have exhibited the capacity to handle extremely high dimensional data for a number of computer vision tasks. While these approaches have been applied to numerous data types, this capacity can be especially leveraged by application on histopathological images, which capture cellular and structural features with their high-resolution, microscopic perspectives. Already, these methodologies have demonstrated promising performance in a variety of applications like disease classification, cancer grading, structure and cellular localizations, and prognostic predictions. A wide range of pathologies requiring histopathological evaluation exist in gastroenterology and hepatology, indicating these as disciplines highly targetable for integration of these technologies. Gastroenterologists have also already been primed to consider the impact of these algorithms, as development of real-time endoscopic video analysis software has been an active and popular field of research. This heightened clinical awareness will likely be important for future integration of these methods and to drive interdisciplinary collaborations on emerging studies. To provide an overview on the application of these methodologies for gastrointestinal and hepatological histopathological slides, this review will discuss general ML and DL concepts, introduce recent and emerging literature using these methods, and cover challenges moving forward to further advance the field.

Automated assessment of glomerulosclerosis and tubular atrophy using deep learning

In kidney transplantations, pathologists evaluate the architecture of both glomeruli, interstitium and tubules to assess the nephron status. An accurate assessment of glomerulosclerosis and tubular atrophy is crucial for determining kidney acceptance, which is currently based on the pathologists' histological evaluations on renal biopsies in addition to clinical data. In this work, we present an automated algorithm, called RENTAG (Robust EvaluatioN of Tubular Atrophy & Glomerulosclerosis), for the segmentation and classification of glomerular and tubular structures in histopathological images. The proposed novel strategy combines the accuracy of a level-set with the semantic segmentation of convolutional neural networks to detect the glomeruli and tubules contours. In the TEST set, our method exhibited excellent performance in both glomeruli (dice score: 0.9529) and tubule (dice score: 0.9174) detection and outperformed all the compared methods. To the best of our knowledge, the RENTAG algorithm is the first fully automated method capable of quantifying glomerulosclerosis and tubular atrophy in digital histological images. The developed software can be employed for the analysis of pre-transplantation biopsies to support the pathologists' diagnostic activity.

Karpinski Score under Digital Investigation: A Fully Automated Segmentation Algorithm to Identify Vascular and Stromal Injury of Donors’ Kidneys

In kidney transplantations, the evaluation of the vascular structures and stromal areas is crucial for determining kidney acceptance, which is currently based on the pathologist’s visual evaluation. In this context, an accurate assessment of the vascular and stromal injury is fundamental to assessing the nephron status. In the present paper, the authors present a fully automated algorithm, called RENFAST (Rapid EvaluatioN of Fibrosis And vesselS Thickness), for the segmentation of kidney blood vessels and fibrosis in histopathological images. The proposed method employs a novel strategy based on deep learning to accurately segment blood vessels, while interstitial fibrosis is assessed using an adaptive stain separation method. The RENFAST algorithm is developed and tested on 350 periodic acid–Schiff (PAS) images for blood vessel segmentation and on 300 Massone’s trichrome (TRIC) stained images for the detection of renal fibrosis. In the TEST set, the algorithm exhibits excellent segmentation performance in both blood vessels (accuracy: 0.8936) and fibrosis (accuracy: 0.9227) and outperforms all the compared methods. To the best of our knowledge, the RENFAST algorithm is the first fully automated method capable of detecting both blood vessels and fibrosis in digital histological images. Being very fast (average computational time 2.91 s), this algorithm paves the way for automated, quantitative, and real-time kidney graft assessments.

Computer-aided classification of hepatocellular ballooning in liver biopsies from patients with NASH using persistent homology

BACKGROUND AND OBJECTIVE

Hepatocellular ballooning is an important histological parameter in the diagnosis of nonalcoholic steatohepatitis (NASH), and it is considered to be a morphological pattern that indicates the severity and the progression to cirrhosis and liver-related deaths. There remains uncertainty about the pathological criteria for evaluating the spectrum of non-alcoholic fatty liver disease (NAFLD) in liver biopsies. We introduce persistence images as novel mathematical descriptors for the classification of ballooning degeneration in the pathological diagnosis.

METHODS

We implemented and tested a topological data analysis methodology combined with linear machine learning techniques and applied this to the classification of tissue images into NAFLD subtypes using Matteoni classification in liver biopsies.

RESULTS

Digital images of hematoxylin- and eosin-stained specimens with a pathologist's visual assessment were obtained from 79 patients who were clinically diagnosed with NAFLD. We obtained accuracy rates of more than 90% for the classification between NASH and non-NASH NAFLD groups. The highest area under the curve from the receiver operating characteristic analysis was 0.946 for the classification of NASH and NAFL2 (type 2 of Matteoni classification), when both 0- and 1-dimensional persistence images were used.

CONCLUSIONS

Our methodology using persistent homology provides quantitative measurements of the topological features in liver biopsies of NAFLD groups with considerable accuracy.