RESUMEN

INTRODUCTION: The use of synthetic data in pathology has, to date, predominantly been augmenting existing pathology data to improve supervised machine learning algorithms. We present an alternative use case-using synthetic images to augment cytology training when the availability of real-world examples is limited. Moreover, we compare the assessment of real and synthetic urine cytology images by pathology personnel to explore the usefulness of this technology in a real-world setting. MATERIALS AND METHODS: Synthetic urine cytology images were generated using a custom-trained conditional StyleGAN3 model. A morphologically balanced 60-image data set of real and synthetic urine cytology images was created for an online image survey system to allow for the assessment of the differences in visual perception between real and synthetic urine cytology images by pathology personnel. RESULTS: A total of 12 participants were recruited to answer the 60-image survey. The study population had a median age of 36.5 years and a median of 5 years of pathology experience. There was no significant difference in diagnostic error rates between real and synthetic images, nor was there a significant difference between subjective image quality scores between real and synthetic images when assessed on an individual observer basis. CONCLUSIONS: The ability of Generative Adversarial Networks technology to generate highly realistic urine cytology images was demonstrated. Furthermore, there was no difference in how pathology personnel perceived the subjective quality of synthetic images, nor was there a difference in diagnostic error rates between real and synthetic urine cytology images. This has important implications for the application of Generative Adversarial Networks technology to cytology teaching and learning.

Asunto(s)

RESUMEN

INTRODUCTION: Urine cytology offers a rapid and relatively inexpensive method to diagnose urothelial neoplasia. In our setting of a public sector laboratory in South Africa, urothelial neoplasia is rare, compromising pathology training in this specific aspect of cytology. Artificial intelligence-based synthetic image generation-specifically the use of generative adversarial networks (GANs)-offers a solution to this problem. MATERIALS AND METHODS: A limited, but morphologically diverse, dataset of 1000 malignant urothelial cytology images was used to train a StyleGAN3 model to create completely novel, synthetic examples of malignant urine cytology using computer resources within reach of most pathology departments worldwide. RESULTS: We have presented the results of our trained GAN model, which was able to generate realistic, morphologically diverse examples of malignant urine cytology images when trained using a modest dataset. Although the trained model is capable of generating realistic images, we have also presented examples for which unrealistic and artifactual images were generated-illustrating the need for manual curation when using this technology in a training context. CONCLUSIONS: We have presented a proof-of-concept illustration of creating synthetic malignant urine cytology images using machine learning technology to augment cytology training when real-world examples are sparse. We have shown that despite significant morphologic diversity in terms of staining variations, slide background, variations in the diagnostic malignant cellular elements, the presence of other nondiagnostic cellular elements, and artifacts, visually acceptable and varied results are achievable using limited data and computing resources.

Asunto(s)

RESUMEN

INTRODUCTION: Dataset creation is one of the first tasks required for training AI algorithms but is underestimated in pathology. High-quality data are essential for training algorithms and data should be labelled accurately and include sufficient morphological diversity. The dynamics and challenges of labelling a urine cytology dataset using The Paris System (TPS) criteria are presented. METHODS: 2,454 images were labelled by pathologist consensus via video conferencing over a 14-day period. During the labelling sessions, the dynamics of the labelling process were recorded. Quality assurance images were randomly selected from images labelled in previous sessions within this study and randomly distributed throughout new labelling sessions. To assess the effect of time on the labelling process, the labelled set of images was split into 2 groups according to the median relative label time and the time taken to label images and intersession agreement were assessed. RESULTS: Labelling sessions ranged from 24 m 11 s to 41 m 06 s in length, with a median of 33 m 47 s. The majority of the 2,454 images were labelled as benign urothelial cells, with atypical and malignant urothelial cells more sparsely represented. The time taken to label individual images ranged from 1 s to 42 s with a median of 2.9 s. Labelling times differed significantly among categories, with the median label time for the atypical urothelial category being 7.2 s, followed by the malignant urothelial category at 3.8 s and the benign urothelial category at 2.9 s. The overall intersession agreement for quality assurance images was substantial. The level of agreement differed among classes of urothelial cells - benign and malignant urothelial cell classes showed almost perfect agreement and the atypical urothelial cell class showed moderate agreement. Image labelling times seemed to speed up, and there was no evidence of worsening of intersession agreement with session time. DISCUSSION/CONCLUSION: Important aspects of pathology dataset creation are presented, illustrating the significant resources required for labelling a large dataset. We present evidence that the time taken to categorise urine cytology images varies by diagnosis/class. The known challenges relating to the reproducibility of the AUC (atypical) category in TPS when compared to the NHGUC (benign) or HGUC (malignant) categories is also confirmed.

Asunto(s)

RESUMEN

OBJECTIVES: Developing accurate supervised machine learning algorithms is hampered by the lack of representative annotated datasets. Most data in anatomic pathology are unlabeled and creating large, annotated datasets is a time consuming and laborious process. Unsupervised learning, which does not require annotated data, possesses the potential to assist with this challenge. This review aims to introduce the concept of unsupervised learning and illustrate how clustering, generative adversarial networks (GANs) and autoencoders have the potential to address the lack of annotated data in anatomic pathology. METHODS: A review of unsupervised learning with examples from the literature was carried out. RESULTS: Clustering can be used as part of semisupervised learning where labels are propagated from a subset of annotated data points to remaining unlabeled data points in a dataset. GANs may assist by generating large amounts of synthetic data and performing color normalization. Autoencoders allow training of a network on a large, unlabeled dataset and transferring learned representations to a classifier using a smaller, labeled subset (unsupervised pretraining). CONCLUSIONS: Unsupervised machine learning techniques such as clustering, GANs, and autoencoders, used individually or in combination, may help address the lack of annotated data in pathology and improve the process of developing supervised learning models.

Asunto(s)

RESUMEN

BACKGROUND: The incorporation of digital pathology into routine pathology practice is becoming more widespread. Definite advantages exist with respect to the implementation of artificial intelligence (AI) and deep learning in pathology, including cytopathology. However, there are also unique challenges in this regard. SUMMARY: This review discusses cytology-specific challenges, including the need to implement digital cytology prior to AI; the large file sizes and increased acquisition times for whole slide images in cytology; the routine use of multiple stains, such as Papanicolaou and Romanowsky stains; the lack of high-quality annotated datasets on which to train algorithms; and the considerable computer resources required, in terms of both computer infrastructure and skilled personnel, for computing and storage of data. Global concerns regarding AI that are certainly applicable to cytology include the need for model validation and continued quality assurance, ethical issues such as the use of patient data in developing algorithms, the need to develop regulatory frameworks regarding what type of data can be utilized and ensuring cybersecurity during data collection and storage, and algorithm development. Key Messages: While AI will likely play a role in cytology practice in the future, applying this technology to cytology poses a unique set of challenges. A broad understanding of digital pathology and algorithm development is desirable to guide the development of algorithms, as well as the need to be cognizant of potential pitfalls to avoid when incorporating the technology in practice.

Asunto(s)

RESUMEN

The application of artificial intelligence technologies to anatomic pathology has the potential to transform the practice of pathology, but, despite this, many pathologists are unfamiliar with how these models are created, trained, and evaluated. In addition, many pathologists may feel that they do not possess the necessary skills to allow them to embark on research into this field. This article aims to act as an introductory tutorial to illustrate how to create, train, and evaluate simple artificial learning models (neural networks) on histopathology data sets in the programming language Python using the popular freely available, open-source libraries Keras, TensorFlow, PyTorch, and Detecto. Furthermore, it aims to introduce pathologists to commonly used terms and concepts used in artificial intelligence.

Asunto(s)

RESUMEN

BACKGROUND: The incidence of HIV-associated Hodgkin lymphoma (HIV-HL) has not dropped in the era of widespread antiretroviral therapy (ART), and there have reportedly been shifts in the most prevalent variants encountered. In this study, factors of interest in cases of HIV-HL diagnosed before and after the widespread availability of ART in Johannesburg, South Africa, were compared. METHODS: All cases of HIV-HL diagnosed in 2007 and 2017 were extracted from the laboratory information system, and pertinent factors compared. RESULTS: The number of cases of HL increased significantly over the period assessed, but without a clear increase in the incidence of HIV-HL. As has been reported previously, the proportion of HIV-HL subclassified as the Nodular Sclerosis and Mixed Cellularity subtypes increased and decreased respectively over the period. The number of unclassifiable cases also increased significantly largely because of more frequent diagnosis in bone marrow (BM). BM involvement was highly prevalent at both timepoints (51.7% in 2007 vs 66.2% in 2017; P = 0.18), but was more frequently associated with multiple cytopenias in 2017. Despite significant ART upscaling, the median CD4 count was significantly lower in 2017 (242.5 cells/µL in 2007 vs 85.5 in 2017; P = 0.002). This particularly affected patients with BM involvement, and the median survival time was significantly shorter among BM+ patients diagnosed in 2017 as compared to those diagnosed in 2007. Notably, 40.8% of the patients with BM involvement diagnosed in 2017 died before the diagnosis was established. CONCLUSION: HIV-HL with BM involvement identifies a very high-risk subpopulation in the post-ART era.

Asunto(s)

RESUMEN

Artificial intelligence (AI) technologies have the potential to transform cytopathology practice, and it is important for cytopathologists to embrace this and place themselves at the forefront of implementing these technologies in cytopathology. This review illustrates an archetypal AI workflow from project conception to implementation in a diagnostic setting and illustrates the cytopathologist's role and level of involvement at each stage of the process. Cytopathologists need to develop and maintain a basic understanding of AI, drive decisions regarding the development and implementation of AI in cytopathology, participate in the generation of datasets used to train and evaluate AI algorithms, understand how the performance of these algorithms is assessed, participate in the validation of these algorithms (either at a regulatory level or in the laboratory setting), and ensure continuous quality assurance of algorithms deployed in a diagnostic setting. In addition, cytopathologists should ensure that these algorithms are developed, trained, tested and deployed in an ethical manner. Cytopathologists need to become informed consumers of these AI algorithms by understanding their workings and limitations, how their performance is assessed and how to validate and verify their output in clinical practice.

Asunto(s)

RESUMEN

AIMS: Plasmablastic lymphoma (PBL) occurs mainly in immunocompromised individuals, usually secondary to human immunodeficiency virus (HIV) infection. It classically occurs intraorally, but has been described in extraoral locations. The aim of this study was to define the immunophenotype and Epstein-Barr virus (EBV) status in a large single-centre cohort of extraoral PBL (EPBL) in South Africa, a high-prevalence HIV setting. METHODS AND RESULTS: This retrospective study of 45 EPBLs included patients' age, gender, race, HIV status, and site. Cases were reviewed histologically, and classified morphologically as pure plasmablastic or plasmablastic with plasmacytic differentiation, and assessed immunohistochemically with antibodies against CD45, CD20, CD79a, PAX5, CD138, MUM1/IRF4, BLIMP1, VS38c, Ki67, bcl-6, CD10, cyclin D1, and human herpesvirus-8, by the use of standard automated procedures. EBV was assessed by the use of chromogenic in-situ hybridisation. Tumours were assessed with a fluorescence in-situ hybridisation (FISH) MYC break-apart probe. Twenty-seven PBLs showed pure plasmablastic morphology, and 18 showed plasmacytic differentiation. The male/female ratio was 1.5:1. The anus was the favoured extraoral site (31.1%), followed by lymph nodes (15.6%). All 29 patients with known HIV status were HIV-positive. The immunohistochemical profile recapitulated that reported for oral PBLs and EPBLs in HIV-positive and HIV-negative patients. EBV was positive in 92.5% of PBLs. FISH analysis showed MYC rearrangement in 48% of cases. CONCLUSION: This study showed a strong association of EPBLs with HIV and EBV infection, similarly to the previously described oral PBL. The strong EBV association together with other clinicopathological parameters and an immunohistochemical profile that includes CD45, CD20, MUM1/IRF4, CD138 and Ki67 may be used in distinguishing PBL from diffuse large B-cell lymphoma and plasma cell myeloma.

Asunto(s)

Asunto(s)