Experience with CellaVision DM96 for peripheral blood differentials in a large multi-center academic hospital system

Performance of the automated digital cell image analyzer UIMD PBIA in white blood cell classification: a comparative study with sysmex DI-60

OBJECTIVES

This study aimed to evaluate the performance of PBIA (UIMD, Seoul, Republic of Korea), an automated digital morphology analyzer using deep learning, for white blood cell (WBC) classification in peripheral blood smears and compare it with the widely used DI-60 (Sysmex, Kobe, Japan).

METHODS

A total of 461 slides were analyzed using PBIA and DI-60. For each instrument, pre-classification performance was evaluated on the basis of post-classification results verified by users. Pre- and post-classification results were compared with manual WBC differentials, and the ability to identify abnormal cells was assessed.

RESULTS

The pre-classification performance of PBIA was better than that of DI-60 for most cell classes. PBIA had an accuracy of 90.0 % and Cohen's kappa of 0.934, higher than DI-60 (45.5 % accuracy and 0.629 kappa) across all cell classes. The pre-classification performance of both instruments decreased when abnormal cells were observed in manual counts, but PBIA still performed better. PBIA also appeared to show better correlation with manual WBC differential counts, particularly in pre-classification (Pearson's correlation coefficient: 0.696-0.944 vs. 0.230-0.882 for neutrophils, lymphocytes, monocytes, eosinophils, basophils, and blasts), although the mean differences varied by cell class. For abnormal cells identified in manual counts, PBIA exhibited more false positives for blasts (30.5 vs. 2.3 %), while DI-60 had a higher rate of false negatives (42.1 vs. 6.1 %). Both instruments exhibited high false negative rates for atypical lymphocytes.

CONCLUSIONS

PBIA demonstrated better performance than DI-60, highlighting its clinical utility. Further multicenter studies are required for full validation.

Deep Learning in Hematology: From Molecules to Patients

Deep learning (DL), a subfield of machine learning, has made remarkable strides across various aspects of medicine. This review examines DL's applications in hematology, spanning from molecular insights to patient care. The review begins by providing a straightforward introduction to the basics of DL tailored for those without prior knowledge, touching on essential concepts, principal architectures, and prevalent training methods. It then discusses the applications of DL in hematology, concentrating on elucidating the models' architecture, their applications, performance metrics, and inherent limitations. For example, at the molecular level, DL has improved the analysis of multi-omics data and protein structure prediction. For cells and tissues, DL enables the automation of cytomorphology analysis, interpretation of flow cytometry data, and diagnosis from whole slide images. At the patient level, DL's utility extends to analyzing curated clinical data, electronic health records, and clinical notes through large language models. While DL has shown promising results in various hematology applications, challenges remain in model generalizability and explainability. Moreover, the integration of novel DL architectures into hematology has been relatively slow in comparison to that in other medical fields.

Digital Imaging and AI Pre-classification in Hematology

A leukocyte differential of peripheral blood can be performed using digital imaging coupled with cellular pre-classification by artificial neural networks. Platelet and erythrocyte morphology can be assessed and counts estimated. Systems from a single vendor have been used in clinical practice for several years, with other vendors' systems, in a development. These systems perform comparably to traditional manual optical microscopy, however, it is important to note that they are designed and intended to be operated by a trained morphologist. These systems have several benefits including increased standardization, efficiency, and remote-review capability.

Diagnostic performance of the CellaVision preclassification neutrophil count - time to bypass the reclassification?

OBJECTIVES

The objective of this study was to perform a method comparison between the CellaVision preclassification neutrophil count and the reclassification neutrophil count performed by trained laboratory technicians, and to evaluate the diagnostic performance of the preclassification neutrophil count at clinical decision levels.

METHODS

We retrospectively identified patient samples through 2019-2022 in which the differential count was performed on Cellavision (n = 4,354). Data on sample characteristics and leukocyte- and differential counts was extracted from the electronic medical journal. For each sample, data containing the pre- and reclassification leukocyte classification, respectively, was extracted from the Cellavision software. Method comparison between the pre-and reclassification neutrophil count was performed using Bland Altman analysis. Diagnostic performance of the preclassification neutrophil count was evaluated according to four pre-specified categories of results with the reclassification as reference method.

RESULTS

The median difference between the pre- and reclassification neutrophil count was 0.044 x 109/L. The preclassification neutrophil count categorised 95.6% of all samples correctly according to the four categories. The sensitivity, specificity, positive predictive value and negative predictive value for detecting neutrophilia > 7.00 x 109/L was 98.8%, 97.2%, 95.8%, and 99.2%, respectively. In samples with leukopenia (n = 543), the sensitivity, specificity, positive predictive value and negative predictive value for detecting severe neutropenia (< 0.50 x 109/L) was 97.7%, 99.1%, 98.6%, and 98.5%, respectively.

CONCLUSION

The diagnostic performance of the CellaVision preclassification neutrophil count was satisfactory. The preclassification neutrophil count may be released to the electronic medical journal to improve turnaround time and benefit laboratory management.

Performance comparison of two automated digital morphology analyzers for leukocyte differential in patients with malignant hematological diseases: Mindray MC-80 and Sysmex DI-60

BACKGROUND

The MC-80 (Mindray, Shenzhen, China), a newly available artificial intelligence (AI)-based digital morphology analyzer, is the focus of this study. We aim to compare the leukocyte differential performance of the Mindray MC-80 with that of the Sysmex DI-60 and the gold standard, manual microscopy.

METHODS

A total of 100 abnormal peripheral blood (PB) smears were compared across the MC-80, DI-60, and manual microscopy. Sensitivity, specificity, predictive value, and efficiency were calculated according to the Clinical and Laboratory Standards Institute (CLSI) EP12-A2 guidelines. Comparisons were made using Bland-Altman analysis and Passing-Bablok regression analysis. Additionally, within-run imprecision was evaluated using five samples, each with varying percentages of mature leukocytes and blasts, in accordance with CLSI EP05-A3 guidelines.

RESULTS

The within-run coefficient of variation (%CV) of the MC-80 for most cell classes in the five samples was lower than that of the DI-60. Sensitivities for the MC-80 ranged from 98.2% for nucleated red blood cells (NRBC) to 28.6% for reactive lymphocytes. The DI-60's sensitivities varied between 100% for basophils and reactive lymphocytes, and 11.1% for metamyelocytes. Both analyzers demonstrated high specificity, negative predictive value, and efficiency, with over 90% for most cell classes. However, the DI-60 showed relatively lower specificity for lymphocytes (73.2%) and lower efficiency for blasts and lymphocytes (80.1% and 78.6%, respectively) compared with the MC-80. Bland-Altman analysis indicated that the absolute mean differences (%) ranged from 0.01 to 4.57 in MC-80 versus manual differential and 0.01 to 3.39 in DI-60 versus manual differential. After verification by technicians, both analyzers exhibited a very high correlation (r = 0.90-1.00) with the manual differential results in neutrophils, lymphocytes, and blasts.

CONCLUSIONS

The Mindray MC-80 demonstrated good performance for leukocyte differential in PB smears, notably exhibiting higher sensitivity for blasts identification than the DI-60.

A comparative evaluation of three consecutive artificial intelligence algorithms released by Techcyte for identification of blasts and white blood cells in abnormal peripheral blood films

INTRODUCTION

Digital pathology artificial intelligence (AI) platforms have the capacity to improve over time through "deep machine learning." We have previously reported on the accuracy of peripheral white blood cell (WBC) differential and blast identification by Techcyte (Techcyte, Inc., Orem, UT, USA), a digital scanner-agnostic web-based system for blood film reporting. The aim of the current study was to compare AI protocols released over time to assess improvement in cell identification.

METHODS

WBC differentials were performed using Techcyte's online AI software on the same 124 digitized abnormal peripheral blood films (including 64 acute and 22 chronic leukaemias) in 2019 (AI1), 2020 (AI2), and 2022 (AI3), with no reassignment by a morphologist at any time point. AI results were correlated to the "gold standard" of manual microscopy, and comparison of Lin's concordance coefficients (LCC) and sensitivity and specificity of blast identification were used to determine the superior AI version.

RESULTS

AI correlations (r) with manual microscopy for individual cell types ranged from 0.50-0.90 (AI1), 0.66-0.86 (AI2) and 0.71-0.91 (AI3). AI3 concordance with manual microscopy was significantly improved compared to AI1 for identification of neutrophils (LCC AI3 = 0.86 vs. AI1 = 0.77, p = 0.03), total granulocytes (LCC AI3 = 0.92 vs. AI1 = 0.82, p = 0.0008), immature granulocytes (LCC AI3 = 0.67 vs. AI1 = 0.38, p = 0.0014), and promyelocytes (LCC AI3 = 0.53 vs. AI1 = 0.16, p = 0.0008). Sensitivity for blast identification (n = 65 slides) improved from 97% (AI1), to 98% (AI2), to 100% (AI3), while blast specificity decreased from 24% (AI1), to 14% (AI2) to 12% (AI3).

CONCLUSION

Techcyte AI has shown significant improvement in cell identification over time and maintains high sensitivity for blast identification in malignant films.

Digital assessment of peripheral blood and bone marrow aspirate smears

The diagnosis of benign and neoplastic hematologic disorders relies on analysis of peripheral blood and bone marrow aspirate smears. As demonstrated by the widespread laboratory adoption of hematology analyzers for automated assessment of peripheral blood, digital analysis of these samples provides many significant benefits compared to relying solely on manual review. Nonetheless, analogous instruments for digital bone marrow aspirate smear assessment have yet to be clinically implemented. In this review, we first provide a historical overview detailing the implementation of hematology analyzers for digital peripheral blood assessment in the clinical laboratory, including the improvements in accuracy, scope, and throughput of current instruments over prior generations. We also describe recent research in digital peripheral blood assessment, particularly in the development of advanced machine learning models that may soon be incorporated into commercial instruments. Next, we provide an overview of recent research in digital assessment of bone marrow aspirate smears and how these approaches could soon lead to development and clinical adoption of instrumentation for automated bone marrow aspirate smear analysis. Finally, we describe the relative advantages and provide our vision for the future of digital assessment of peripheral blood and bone marrow aspirate smears, including what improvements we can soon expect in the hematology laboratory.

A deep learning model for detection of leukocytes under various interference factors

The accurate detection of leukocytes is the basis for the diagnosis of blood system diseases. However, diagnosing leukocyte disorders by doctors is time-consuming and requires extensive experience. Automated detection methods with high accuracy can improve detection efficiency and provide recommendations to inexperienced doctors. Current methods and instruments either fail to automate the identification process fully or have low performance and need suitable leukocyte data sets for further study. To improve the current status, we need to develop more intelligent strategies. This paper investigates fulfilling high-performance automatic detection for leukocytes using a deep learning-based method. We established a new dataset more suitable for leukocyte detection, containing 6273 images (8595 leukocytes) and considering nine common clinical interference factors. Based on the dataset, the performance evaluation of six mainstream detection models is carried out, and a more robust ensemble model is proposed. The mean of average precision (mAP) @IoU = 0.50:0.95 and mean of average recall (mAR)@IoU = 0.50:0.95 of the ensemble model on the test set are 0.853 and 0.922, respectively. The detection performance of poor-quality images is robust. For the first time, it is found that the ensemble model yields an accuracy of 98.84% for detecting incomplete leukocytes. In addition, we also compared the test results of different models and found multiple identical false detections of the models, then provided correct suggestions for the clinic.

Hematology and Machine Learning

BACKGROUND

Substantial improvements in computational power and machine learning (ML) algorithm development have vastly increased the limits of what autonomous machines are capable of. Since its beginnings in the 19th century, laboratory hematology has absorbed waves of progress yielding improvements in both of accuracy and efficiency. The next wave of change in laboratory hematology will be the result of the ML revolution that has already touched many corners of healthcare and society at large.

CONTENT

This review will describe the manifestations of ML and artificial intelligence (AI) already utilized in the clinical hematology laboratory. This will be followed by a topical summary of the innovative and investigational applications of this technology in each of the major subdomains within laboratory hematology.

SUMMARY

Application of this technology to laboratory hematology will increase standardization and efficiency by reducing laboratory staff involvement in automatable activities. This will unleash time and resources for focus on more meaningful activities such as the complexities of patient care, research and development, and process improvement.

Multicentric evaluation of the variability of digital morphology performances also respect to the reference methods by optical microscopy

INTRODUCTION

Despite the important diagnostic role of peripheral blood morphology, cell classification is subjective. Automated image-processing systems (AIS) provide more accurate and objective morphological evaluation. The aims of this multicenter study were the evaluation of the intra and inter-laboratory variation between different AIS in cell pre-classification and after reclassification, compared with manual optical microscopy, the reference method.

METHODS

Six peripheral blood samples were included in this study, for each sample, 70 May-Grunwald and Giemsa stained PB smears were prepared from each specimen and 10 slides were delivered to the seven laboratories involved. Smears were processed by both optical microscopy (OM) and AIS. In addition, the assessment times of both methods were recorded.

RESULTS

Within-laboratory Reproducibility ranged between 4.76% and 153.78%; between-laboratory Precision ranged between 2.10% and 82.2%, while Total Imprecision ranged between 5.21% and 20.60%. The relative Bland Altman bias ranged between -0.01% and 20.60%. The mean of assessment times were 326 ± 110 s and 191 ± 68 s for AIS post reclassification and OM, respectively.

CONCLUSIONS

AIS can be helpful when the number of cell counted are low and can give advantages in terms of efficiency, objectivity and time saving in the morphological analysis of blood cells. They can also help in the interpretation of some morphological features and can serve as learning and investigation tools.

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.

Accurate white blood cell differential by Alinity hq: A comparison with flow cytometry and manual differential

INTRODUCTION

White blood cell (WBC) differential by flow cytometry can report a six-part WBC differential and enumerate blasts. Some modern hematology analyzers are also able to provide a six-part WBC differential (including immature granulocytes). Our goal was to compare the WBC differential obtained by the Abbott Alinity hq hematology analyzer to an 8-color single-tube flow cytometry method and to manual WBC differential.

METHODS

Samples from 144 patients were tested with Alinity hq, flow cytometry, and microscopic WBC differential. The WBC count ranged from 1.22 to 359 × 10⁹ /L, and 34 samples were flagged by the analyzer for abnormal WBC morphology.

RESULTS

Strong concordance was demonstrated between Alinity hq and flow cytometry for all six components of the differential, with correlation coefficients ranging from 0.86 (basophils) to 1.00 (lymphocytes). Small, clinically insignificant positive difference was observed between Alinity hq and flow cytometry for mature and total neutrophils (2.51% and 1.85%) and eosinophils (0.14%), and small negative difference for immature granulocytes (-0.65%), lymphocytes (-0.61%), and basophils (-0.21%). No bias was detected between the Alinity hq and flow cytometry monocyte counts. Alinity hq and flow cytometry results agreed with the manual differential, apart from small, clinically insignificant differences. Alinity hq nucleated red blood cell concentrations were equivalent with the manual results (r = 0.95, slope = 1.16). The percentage of blasts by flow cytometry demonstrated good correlation and agreement with the manual count (r = 0.99, slope = 1.35).

CONCLUSION

Alinity hq has produced accurate six-part WBC differential in this three-way comparison, equivalent to flow cytometry and morphological classification.

Diagnosis of Leukaemia in Blood Slides Based on a Fine-Tuned and Highly Generalisable Deep Learning Model

Leukaemia is a dysfunction that affects the production of white blood cells in the bone marrow. Young cells are abnormally produced, replacing normal blood cells. Consequently, the person suffers problems in transporting oxygen and in fighting infections. This article proposes a convolutional neural network (CNN) named LeukNet that was inspired on convolutional blocks of VGG-16, but with smaller dense layers. To define the LeukNet parameters, we evaluated different CNNs models and fine-tuning methods using 18 image datasets, with different resolution, contrast, colour and texture characteristics. We applied data augmentation operations to expand the training dataset, and the 5-fold cross-validation led to an accuracy of 98.61%. To evaluate the CNNs generalisation ability, we applied a cross-dataset validation technique. The obtained accuracies using cross-dataset experiments on three datasets were 97.04, 82.46 and 70.24%, which overcome the accuracies obtained by current state-of-the-art methods. We conclude that using the most common and deepest CNNs may not be the best choice for applications where the images to be classified differ from those used in pre-training. Additionally, the adopted cross-dataset validation approach proved to be an excellent choice to evaluate the generalisation capability of a model, as it considers the model performance on unseen data, which is paramount for CAD systems.

Learn from one data set to classify all - A multi-target domain adaptation approach for white blood cell classification

BACKGROUND AND OBJECTIVE

Traditional machine learning methods assume that both training and test data come from the same distribution. In this way, it becomes possible to achieve high successes when modelling on the same domain. Unfortunately, in real-world problems, direct transfer between domains is adversely affected due to differences in the data collection process and the internal dynamics of the data. In order to cope with such drawbacks, researchers use a method called "domain adaptation", which enables the successful transfer of information learned in one domain to other domains. In this study, a model that can be used in the classification of white blood cells (WBC) and is not affected by domain differences was proposed.

METHODS

Only one data set was used as source domain, and an adaptation process was created that made possible the learned knowledge to be used effectively in other domains (multi-target domain adaptation). While constructing the model, we employed data augmentation, data generation and fine-tuning processes, respectively.

RESULTS

The proposed model has been able to extract "domain-invariant" features and achieved high success rates in the tests performed on nine different data sets. Multi-target domain adaptation accuracy was measured as %98.09.

CONCLUSIONS

At the end of the study, it has been observed that the proposed model ignores the domain differences and it can adapt in a successful way to target domains. In this way, it becomes possible to classify unlabeled samples rapidly by using only a few number of labeled ones.

Pilot Study on the Performance of a New System for Image Based Analysis of Peripheral Blood Smears on Normal Samples

Image analysis based automated systems aiming to automate the manual microscopic review of peripheral blood smears have gained popularity in recent times. In this paper, we evaluate a new blood smear analysis system based on artificial intelligence, Shonit™ by SigTuple Technologies Private Limited. One hundred normal samples with no flags from an automated haematology analyser were taken. Peripheral blood smear slides were prepared using the autostainer integrated with an automated haematology analyser and stained using May-Grunwald-Giemsa stain. These slides were analysed with Shonit™. The metrics for evaluation included (1) accuracy of white blood cell classification for the five normal white blood cell types, and (2) comparison of white blood cell differential count with the automated haematology analyser. In addition, we also explored the possibility of estimating the value of red blood cell and platelet indices via image analysis. Overall white blood cell classification specificity was greater than 97.90% and the precision was greater than 93.90% for all the five white blood cell classes. The correlation of the white blood cell differential count between the automated haematology analyser and Shonit™ was found to be within the known inter cell-counter variability. Shonit™ was found to show promise in terms of its ability to analyse peripheral blood smear images to derive quantifiable metrics useful for clinicians. Future enhancement should include the ability to analyse abnormal blood samples.

Evaluation of the accuracy of the CellaVision™ DM96 in a high HIV-prevalence population in South Africa

INTRODUCTION

The CellaVision™ DM96 (DM96) is a digital microscopy system which performs well in developed countries. However, to date it has not been evaluated in Africa, where the pathology spectrum encountered is very different. In particular, its utility in a setting with high HIV prevalence has not been assessed, which is of interest because of the morphological aberrations often seen in HIV-positive patients.

OBJECTIVES

This study aimed to evaluate the accuracy of the DM96 in a South African laboratory, with emphasis on its performance in samples collected from HIV-positive patients.

METHODS

A total of 149 samples submitted for a routine differential white cell count in 2012 and 2013 at the Chris Hani Baragwanath Academic Hospital in Johannesburg, South Africa were included, of which 79 (53.0%) were collected from HIV-positive patients. Results of DM96 analysis pre- and post-classification were compared with a manual differential white cell count and the impact of HIV infection and other variables of interest were assessed.

RESULTS

Pre- and post-classification accuracies were similar to those reported in developed countries. Reclassification was required in 16% of cells, with particularly high misclassification rates for eosinophils (31.7%), blasts (33.7%) and basophils (93.5%). Multivariate analysis revealed a significant relationship between the number of misclassified cells and both the white cell count (p = 0.035) and the presence of malignant cells in the blood (p = 0.049), but not with any other variables analysed, including HIV status.

CONCLUSION

The DM96 exhibited acceptable accuracy in this South African laboratory, which was not impacted by HIV infection. However, as it does not eliminate the need for experienced morphologists, its cost may be unjustifiable in a resource-constrained setting.

Accuracy of the CellaVision DM96 platform for reticulocyte counting

CONTEXT

Many hematology laboratories have adopted semi-automated digital platforms for routine use and the evidence supporting their use is increasing.

AIMS

The CellaVision platforms are among the most thoroughly studied digital hematology platforms; we wished to determine the accuracy of CellaVision for reticulocyte counting.

DESIGN MATERIALS AND METHODS

We compared reticulocyte counts performed manually, using the Beckman Coulter LH750 automated analyzer and with the CellaVision DM96 platform. We analyzed the results for pair-wise correlation and bias, and precision.

STATISTICAL ANALYSES USED

Analyses were performed using Statistical Package for the Social Sciences software (SPSS), including Spearman's rho correlation coefficient, Friedman's two-way Analysis Of Variance (ANOVA) for comparison of distributions; bias was compared by way of mean and standard deviation.

RESULTS

The CellaVision reticulocyte counts correlated most strongly with those of the analyzer (often considered the benchmark test); the reticulocyte count distributions were noted not to be significantly different from each other across all three methods. The mean and standard deviation of bias were lowest in the comparison of CellaVision and LH750 counts.

CONCLUSIONS

Our data provide additional support for the accuracy of digital hematology applications using the CellaVision DM96 platform.

Performance of CellaVision DM96 in leukocyte classification

Background:

Leukocyte differentials are an important component of clinical care. Morphologic assessment of peripheral blood smears (PBS) may be required to accurately classify leukocytes. However, manual microscopy is labor intensive. The CellaVision DM96 is an automated system that acquires digital images of leukocytes on PBS, pre-classifies the cell type, and displays them on screen for a Technologist or Pathologist to approve or reclassify. Our study compares the results of the DM96 with manual microscopy.

Methods:

Three hundred and fifty-nine PBS were selected and assessed by manual microscopy with a 200 leukocyte cell count. They were then reassessed using the CellaVision DM96 with a 115 leukocyte cell count including reclassification when necessary. Correlation between the manual microscopy results and the CellaVision DM96 results was calculated for each cell type.

Results:

The correlation coefficients (r²) range from a high of 0.99 for blasts to a low of 0.72 for metamyelocytes.

Conclusions:

The correlation between the CellaVision DM96 and manual microscopy was as good or better than the previously published data. The accuracy of leukocyte classification depended on the cell type, and in general, there was lower correlation for rare cell types. However, the correlation is similar to previous studies on the correlation of manual microscopy with an established reference result. Therefore, the CellaVision DM96 is appropriate for clinical implementation.

Experience with multimodality telepathology at the University of Pittsburgh Medical Center

Several modes of telepathology exist including static (store-and-forward), dynamic (live video streaming or robotic microscopy), and hybrid technology involving whole slide imaging (WSI). Telepathology has been employed at the University of Pittsburgh Medical Center (UPMC) for over a decade at local, national, and international sites. All modes of telepathology have been successfully utilized to exploit our institutions subspecialty expertise and to compete for pathology services. This article discusses the experience garnered at UPMC with each of these teleconsultation methods. Static and WSI telepathology systems have been utilized for many years in transplant pathology using a private network and client-server architecture. Only minor clinically significant differences of opinion were documented. In hematopathology, the CellaVision^® system is used to transmit, via email, static images of blood cells in peripheral blood smears for remote interpretation. While live video streaming has remained the mode of choice for providing immediate adequacy assessment of cytology specimens by telecytology, other methods such as robotic microscopy have been validated and shown to be effective. Robotic telepathology has been extensively used to remotely interpret intra-operative neuropathology consultations (frozen sections). Adoption of newer technology and increased pathologist experience has improved accuracy and deferral rates in teleneuropathology. A digital pathology consultation portal (https://pathconsult.upmc.com/) was recently created at our institution to facilitate digital pathology second opinion consults, especially for WSI. The success of this web-based tool is the ability to handle vendor agnostic, large image files of digitized slides, and ongoing user-friendly customization for clients and teleconsultants. It is evident that the practice of telepathology at our institution has evolved in concert with advances in technology and user experience. Early and continued adoption of telepathology has promoted additional digital pathology resources that are now being leveraged for other clinical, educational, and research purposes.