The Utility of Unsupervised Machine Learning in Anatomic Pathology

A Comparison of Diagnostic and Immunohistochemical Workup and Literature Review Capabilities of Online Artificial Intelligence Assistance Models in Pathology

Artificial intelligence (AI) is a suite of technologies that enables computers to learn and interpret information like human cognition. It has found applications across various fields, including healthcare, agriculture, astronomy, navigation, and robotics. Within healthcare, AI has the potential to enhance diagnostic accuracy, facilitate drug research, and automate patient experiences. This comparative study focuses on the proficiency of AI in generating accurate differential diagnoses in the field of pathology. Six medical vignettes were crafted, and each scenario was then input into three different AI platforms. The pathologist reviewed and determined the most accurate AI model.

Computational pathology: an evolving concept

The initial enthusiasm about computational pathology (CP) and artificial intelligence (AI) was that they will replace pathologists entirely on the way to fully automated diagnostics. It is becoming clear that currently this is not the immediate model to pursue. On top of the legal and regulatory complexities surrounding its implementation, the majority of tested machine learning (ML)-based predictive algorithms do not display the exquisite performance needed to render them unequivocal, standalone decision makers for matters with direct implications to human health. We are thus moving into a different model of "computer-assisted diagnostics", where AI is there to provide support, rather than replacing, the pathologist. Herein we focus on the practical aspects of CP, from a pathologist perspective. There is a wide range of potential applications where CP can enhance precision of pathology diagnosis, tailor prognostic and predictive information, as well as save time. There are, however, a number of potential limitations for CP that currently hinder their wider adoption in the clinical setting. We address the key necessary steps towards clinical implementation of computational pathology, discuss the significant obstacles that hinders its adoption in the clinical context and summarize some proposed solutions. We conclude that the advancement of CP in the clinic is a promising resource-intensive endeavour that requires broad and inclusive collaborations between academia, industry, and regulatory bodies.

Explainability and causability in digital pathology

The current move towards digital pathology enables pathologists to use artificial intelligence (AI)-based computer programmes for the advanced analysis of whole slide images. However, currently, the best-performing AI algorithms for image analysis are deemed black boxes since it remains - even to their developers - often unclear why the algorithm delivered a particular result. Especially in medicine, a better understanding of algorithmic decisions is essential to avoid mistakes and adverse effects on patients. This review article aims to provide medical experts with insights on the issue of explainability in digital pathology. A short introduction to the relevant underlying core concepts of machine learning shall nurture the reader's understanding of why explainability is a specific issue in this field. Addressing this issue of explainability, the rapidly evolving research field of explainable AI (XAI) has developed many techniques and methods to make black-box machine-learning systems more transparent. These XAI methods are a first step towards making black-box AI systems understandable by humans. However, we argue that an explanation interface must complement these explainable models to make their results useful to human stakeholders and achieve a high level of causability, i.e. a high level of causal understanding by the user. This is especially relevant in the medical field since explainability and causability play a crucial role also for compliance with regulatory requirements. We conclude by promoting the need for novel user interfaces for AI applications in pathology, which enable contextual understanding and allow the medical expert to ask interactive 'what-if'-questions. In pathology, such user interfaces will not only be important to achieve a high level of causability. They will also be crucial for keeping the human-in-the-loop and bringing medical experts' experience and conceptual knowledge to AI processes.

Investigation of semi- and self-supervised learning methods in the histopathological domain

Training models with semi- or self-supervised learning methods is one way to reduce annotation effort since they rely on unlabeled or sparsely labeled datasets. Such approaches are particularly promising for domains with a time-consuming annotation process requiring specialized expertise and where high-quality labeled machine learning datasets are scarce, like in computational pathology. Even though some of these methods have been used in the histopathological domain, there is, so far, no comprehensive study comparing different approaches. Therefore, this work compares feature extractors models trained with state-of-the-art semi- or self-supervised learning methods PAWS, SimCLR, and SimSiam within a unified framework. We show that such models, across different architectures and network configurations, have a positive performance impact on histopathological classification tasks, even in low data regimes. Moreover, our observations suggest that features learned from a particular dataset, i.e., tissue type, are only in-domain transferable to a certain extent. Finally, we share our experience using each method in computational pathology and provide recommendations for its use.

Are synthetic cytology images ready for prime time? A comparative assessment of real and synthetic urine cytology images

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.

Chronic Lymphocytic Leukemia Progression Diagnosis with Intrinsic Cellular Patterns via Unsupervised Clustering

Simple Summary

Distinguishing between chronic lymphocytic leukemia (CLL), accelerated CLL (aCLL), and full-blown transformation to diffuse large B-cell lymphoma (Richter transformation; RT) has significant clinical implications. Identifying cellular phenotypes via unsupervised clustering provides the most robust analytic performance in analyzing digitized pathology slides. This study serves as a proof of concept that using an unsupervised machine learning scheme can enhance diagnostic accuracy.

Abstract

Identifying the progression of chronic lymphocytic leukemia (CLL) to accelerated CLL (aCLL) or transformation to diffuse large B-cell lymphoma (Richter transformation; RT) has significant clinical implications as it prompts a major change in patient management. However, the differentiation between these disease phases may be challenging in routine practice. Unsupervised learning has gained increased attention because of its substantial potential in data intrinsic pattern discovery. Here, we demonstrate that cellular feature engineering, identifying cellular phenotypes via unsupervised clustering, provides the most robust analytic performance in analyzing digitized pathology slides (accuracy = 0.925, AUC = 0.978) when compared to alternative approaches, such as mixed features, supervised features, unsupervised/mixed/supervised feature fusion and selection, as well as patch-based convolutional neural network (CNN) feature extraction. We further validate the reproducibility and robustness of unsupervised feature extraction via stability and repeated splitting analysis, supporting its utility as a diagnostic aid in identifying CLL patients with histologic evidence of disease progression. The outcome of this study serves as proof of principle using an unsupervised machine learning scheme to enhance the diagnostic accuracy of the heterogeneous histology patterns that pathologists might not easily see.

Is it real or not? Toward artificial intelligence-based realistic synthetic cytology image generation to augment teaching and quality assurance in pathology

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.

Artificial intelligence, machine learning, and deep learning for clinical outcome prediction

AI is a broad concept, grouping initiatives that use a computer to perform tasks that would usually require a human to complete. AI methods are well suited to predict clinical outcomes. In practice, AI methods can be thought of as functions that learn the outcomes accompanying standardized input data to produce accurate outcome predictions when trialed with new data. Current methods for cleaning, creating, accessing, extracting, augmenting, and representing data for training AI clinical prediction models are well defined. The use of AI to predict clinical outcomes is a dynamic and rapidly evolving arena, with new methods and applications emerging. Extraction or accession of electronic health care records and combining these with patient genetic data is an area of present attention, with tremendous potential for future growth. Machine learning approaches, including decision tree methods of Random Forest and XGBoost, and deep learning techniques including deep multi-layer and recurrent neural networks, afford unique capabilities to accurately create predictions from high dimensional, multimodal data. Furthermore, AI methods are increasing our ability to accurately predict clinical outcomes that previously were difficult to model, including time-dependent and multi-class outcomes. Barriers to robust AI-based clinical outcome model deployment include changing AI product development interfaces, the specificity of regulation requirements, and limitations in ensuring model interpretability, generalizability, and adaptability over time.