Unsupervised Machine Learning in Pathology

AI-Enhanced evaluation of YouTube content on post-surgical incontinence following pelvic cancer treatment

Background

Several pelvic area cancers exhibit high incidence rates, and their surgical treatment can result in adverse effects such as urinary and fecal incontinence, significantly impacting patients' quality of life. Post-surgery incontinence is a significant concern, with prevalence rates ranging from 25 to 45% for urinary incontinence and 9-68% for fecal incontinence. Cancer survivors are increasingly turning to YouTube as a platform to connect with others, yet caution is warranted as misinformation is prevalent.

Objective

This study aims to evaluate the information quality in YouTube videos about post-surgical incontinence after pelvic area cancer surgery.

Methods

A YouTube search for "Incontinence after cancer surgery" yielded 108 videos, which were subsequently analyzed. To evaluate these videos, several quality assessment tools were utilized, including DISCERN, GQS, JAMA, PEMAT, and MQ-VET. Statistical analyses, such as descriptive statistics and intercorrelation tests, were employed to assess various video attributes, including characteristics, popularity, educational value, quality, and reliability. Also, artificial intelligence techniques like PCA, t-SNE, and UMAP were used for data analysis. HeatMap and Hierarchical Clustering Dendrogram techniques validated the Machine Learning results.

Results

The quality scales presented a high level of correlation one with each other (p < 0.01) and the Artificial Intelligence-based techniques presented clear clustering representations of the dataset samples, which were reinforced by the Heat Map and Hierarchical Clustering Dendrogram.

Conclusions

YouTube videos on "Incontinence after Cancer Surgery" present a "High" quality across multiple scales. The use of AI tools, like PCA, t-SNE, and UMAP, is highlighted for clustering large health datasets, improving data visualization, pattern recognition, and complex healthcare analysis.

Unlocking the Potential of Artificial Intelligence in Acute Myeloid Leukemia and Myelodysplastic Syndromes

PURPOSE OF THE REVIEW

This review aims to elucidate the transformative impact and potential of machine learning (ML) in the diagnosis, prognosis, and clinical management of myelodysplastic syndromes (MDS) and acute myeloid leukemia (AML). It further aims to bridge the gap between current advances of ML and their practical application in these diseases.

RECENT FINDINGS

Recent advances in ML have revolutionized prognostication, diagnosis, and treatment of MDS and AML. ML algorithms have proven effective in predicting disease progression, optimizing treatment responses, and in the stratification of patient groups. Particularly, the use of ML in genomic and epigenomic data analysis has unveiled novel insights into the molecular heterogeneity of MDS and AML, leading to better-informed therapeutic strategies. Furthermore, deep learning techniques have shown promise in analyzing complex patterns in bone marrow biopsy images, providing a potential pathway towards early and accurate diagnosis. While still in the nascent stages, ML applications in MDS and AML signify a paradigm shift towards precision medicine. The integration of ML with traditional clinical practices could potentially enhance diagnostic accuracy, refine risk stratification, and improve therapeutic approaches. However, challenges related to data privacy, standardization, and algorithm interpretability must be addressed to realize the full potential of ML in this field. Future research should focus on the development of robust, transparent ML models and their ethical implementation in clinical settings.

The State of Machine Learning in Outcomes Prediction of Transsphenoidal Surgery: A Systematic Review

The purpose of this analysis is to assess the use of machine learning (ML) algorithms in the prediction of postoperative outcomes, including complications, recurrence, and death in transsphenoidal surgery. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we systematically reviewed all papers that used at least one ML algorithm to predict outcomes after transsphenoidal surgery. We searched Scopus, PubMed, and Web of Science databases for studies published prior to May 12, 2021. We identified 13 studies enrolling 5,048 patients. We extracted the general characteristics of each study; the sensitivity, specificity, area under the curve (AUC) of the ML models developed as well as the features identified as important by the ML models. We identified 12 studies with 5,048 patients that included ML algorithms for adenomas, three with 1807 patients specifically for acromegaly, and five with 2105 patients specifically for Cushing's disease. Nearly all were single-institution studies. The studies used a heterogeneous mix of ML algorithms and features to build predictive models. All papers reported an AUC greater than 0.7, which indicates clinical utility. ML algorithms have the potential to predict postoperative outcomes of transsphenoidal surgery and can improve patient care. Ensemble algorithms and neural networks were often top performers when compared with other ML algorithms. Biochemical and preoperative features were most likely to be selected as important by ML models. Inexplicability remains a challenge, but algorithms such as local interpretable model-agnostic explanation or Shapley value can increase explainability of ML algorithms. Our analysis shows that ML algorithms have the potential to greatly assist surgeons in clinical decision making.

Artificial intelligence-assisted selection and efficacy prediction of antineoplastic strategies for precision cancer therapy

The rapid development of artificial intelligence (AI) technologies in the context of the vast amount of collectable data obtained from high-throughput sequencing has led to an unprecedented understanding of cancer and accelerated the advent of a new era of clinical oncology with a tone of precision treatment and personalized medicine. However, the gains achieved by a variety of AI models in clinical oncology practice are far from what one would expect, and in particular, there are still many uncertainties in the selection of clinical treatment options that pose significant challenges to the application of AI in clinical oncology. In this review, we summarize emerging approaches, relevant datasets and open-source software of AI and show how to integrate them to address problems from clinical oncology and cancer research. We focus on the principles and procedures for identifying different antitumor strategies with the assistance of AI, including targeted cancer therapy, conventional cancer therapy, and cancer immunotherapy. In addition, we also highlight the current challenges and directions of AI in clinical oncology translation. Overall, we hope this article will provide researchers and clinicians with a deeper understanding of the role and implications of AI in precision cancer therapy, and help AI move more quickly into accepted cancer guidelines.

The Brain Protein Atlas: A conglomerate of proteomics datasets of human neural tissue

The human brain represents one of the most complex biological structures with significant spatiotemporal molecular plasticity occurring through early development, learning, aging, and disease. While much progress has been made in mapping its transcriptional architecture, more downstream phenotypic readouts are relatively scarce due to limitations with tissue heterogeneity and accessibility, as well as an inability to amplify protein species prior to global -OMICS analysis. To address some of these barriers, our group has recently focused on using mass-spectrometry workflows compatible with small amounts of formalin-fixed paraffin-embedded tissue samples. This has enabled exploration into spatiotemporal proteomic signatures of the brain and disease across otherwise inaccessible neurodevelopmental timepoints and anatomical niches. Given the similar theme and approaches, we introduce an integrated online portal, "The Brain Protein Atlas (BPA)" (www.brainproteinatlas.org), representing a public resource that allows users to access and explore these amalgamated datasets. Specifically, this portal contains a growing set of peer-reviewed mass-spectrometry-based proteomic datasets, including spatiotemporal profiles of human cerebral development, diffuse gliomas, clinically aggressive meningiomas, and a detailed anatomic atlas of glioblastoma. One barrier to entry in mass spectrometry-based proteomics data analysis is the steep learning curve required to extract biologically relevant data. BPA, therefore, includes several built-in analytical tools to generate relevant plots (e.g., volcano plots, heatmaps, boxplots, and scatter plots) and evaluate the spatiotemporal patterns of proteins of interest. Future iterations aim to expand available datasets, including those generated by the community at large, and analytical tools for exploration. Ultimately, BPA aims to improve knowledge dissemination of proteomic information across the neuroscience community in hopes of accelerating the biological understanding of the brain and various maladies.

Application of Artificial Intelligence in Pathology: Trends and Challenges

Given the recent success of artificial intelligence (AI) in computer vision applications, many pathologists anticipate that AI will be able to assist them in a variety of digital pathology tasks. Simultaneously, tremendous advancements in deep learning have enabled a synergy with artificial intelligence (AI), allowing for image-based diagnosis on the background of digital pathology. There are efforts for developing AI-based tools to save pathologists time and eliminate errors. Here, we describe the elements in the development of computational pathology (CPATH), its applicability to AI development, and the challenges it faces, such as algorithm validation and interpretability, computing systems, reimbursement, ethics, and regulations. Furthermore, we present an overview of novel AI-based approaches that could be integrated into pathology laboratory workflows.

Applications of machine learning in routine laboratory medicine: Current state and future directions

Machine learning is able to leverage large amounts of data to infer complex patterns that are otherwise beyond the capabilities of rule-based systems and human experts. Its application to laboratory medicine is particularly exciting, as laboratory testing provides much of the foundation for clinical decision making. In this article, we provide a brief introduction to machine learning for the medical professional in addition to a comprehensive literature review outlining the current state of machine learning as it has been applied to routine laboratory medicine. Although still in its early stages, machine learning has been used to automate laboratory tasks, optimize utilization, and provide personalized reference ranges and test interpretation. The published literature leads us to believe that machine learning will be an area of increasing importance for the laboratory practitioner. We envision the laboratory of the future will utilize these methods to make significant improvements in efficiency and diagnostic precision.

Unsupervised Segmentation in NSCLC: How to Map the Output of Unsupervised Segmentation to Meaningful Histological Labels by Linear Combination?

Background: Segmentation is, in many Pathomics projects, an initial step. Usually, in supervised settings, well-annotated and large datasets are required. Regarding the rarity of such datasets, unsupervised learning concepts appear to be a potential solution. Against this background, we tested for a small dataset on lung cancer tissue microarrays (TMA) if a model (i) first can be in a previously published unsupervised setting and (ii) secondly can be modified and retrained to produce meaningful labels, and (iii) we finally compared this approach to standard segmentation models. Methods: (ad i) First, a convolutional neuronal network (CNN) segmentation model is trained in an unsupervised fashion, as recently described by Kanezaki et al. (ad ii) Second, the model is modified by adding a remapping block and is retrained on an annotated dataset in a supervised setting. (ad iii) Third, the segmentation results are compared to standard segmentation models trained on the same dataset. Results: (ad i–ii) By adding an additional mapping-block layer and by retraining, models previously trained in an unsupervised manner can produce meaningful labels. (ad iii) The segmentation quality is inferior to standard segmentation models trained on the same dataset. Conclusions: Unsupervised training in combination with subsequent supervised training offers for histological images here no benefit.

Biological Membrane-Penetrating Peptides: Computational Prediction and Applications

Peptides comprise a versatile class of biomolecules that present a unique chemical space with diverse physicochemical and structural properties. Some classes of peptides are able to naturally cross the biological membranes, such as cell membrane and blood-brain barrier (BBB). Cell-penetrating peptides (CPPs) and blood-brain barrier-penetrating peptides (B3PPs) have been explored by the biotechnological and pharmaceutical industries to develop new therapeutic molecules and carrier systems. The computational prediction of peptides’ penetration into biological membranes has been emerged as an interesting strategy due to their high throughput and low-cost screening of large chemical libraries. Structure- and sequence-based information of peptides, as well as atomistic biophysical models, have been explored in computer-assisted discovery strategies to classify and identify new structures with pharmacokinetic properties related to the translocation through biomembranes. Computational strategies to predict the permeability into biomembranes include cheminformatic filters, molecular dynamics simulations, artificial intelligence algorithms, and statistical models, and the choice of the most adequate method depends on the purposes of the computational investigation. Here, we exhibit and discuss some principles and applications of these computational methods widely used to predict the permeability of peptides into biomembranes, exhibiting some of their pharmaceutical and biotechnological applications.

The Utility of Unsupervised Machine Learning in Anatomic Pathology

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.

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.

The Use of Artificial Intelligence and Machine Learning in Surgery: A Comprehensive Literature Review

Interest in the use of artificial intelligence (AI) and machine learning (ML) in medicine has grown exponentially over the last few years. With its ability to enhance speed, precision, and efficiency, AI has immense potential, especially in the field of surgery. This article aims to provide a comprehensive literature review of artificial intelligence as it applies to surgery and discuss practical examples, current applications, and challenges to the adoption of this technology. Furthermore, we elaborate on the utility of natural language processing and computer vision in improving surgical outcomes, research, and patient care.

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.

Deep Learning of Histopathology Images at the Single Cell Level

The tumor immune microenvironment (TIME) encompasses many heterogeneous cell types that engage in extensive crosstalk among the cancer, immune, and stromal components. The spatial organization of these different cell types in TIME could be used as biomarkers for predicting drug responses, prognosis and metastasis. Recently, deep learning approaches have been widely used for digital histopathology images for cancer diagnoses and prognoses. Furthermore, some recent approaches have attempted to integrate spatial and molecular omics data to better characterize the TIME. In this review we focus on machine learning-based digital histopathology image analysis methods for characterizing tumor ecosystem. In this review, we will consider three different scales of histopathological analyses that machine learning can operate within: whole slide image (WSI)-level, region of interest (ROI)-level, and cell-level. We will systematically review the various machine learning methods in these three scales with a focus on cell-level analysis. We will provide a perspective of workflow on generating cell-level training data sets using immunohistochemistry markers to "weakly-label" the cell types. We will describe some common steps in the workflow of preparing the data, as well as some limitations of this approach. Finally, we will discuss future opportunities of integrating molecular omics data with digital histopathology images for characterizing tumor ecosystem.

Histopathological patterns in atypical teratoid/rhabdoid tumors are related to molecular subgroup

Atypical teratoid/rhabdoid tumor (AT/RT) is a highly malignant tumor that may not only contain rhabdoid tumor cells but also poorly differentiated small-round-blue cells as well as areas with mesenchymal or epithelial differentiation. Little is known on factors associated with histopathological diversity. Recent studies demonstrated three molecular subgroups of AT/RT, namely ATRT-TYR, ATRT-SHH, and ATRT-MYC. We thus aimed to investigate if morphological patterns might be related to molecular subgroup status. Hematoxylin-eosin stained sections of 114 AT/RT with known molecular subgroup status were digitalized and independently categorized by nine blinded observers into four morphological categories, that is, "rhabdoid," "small-round-blue," "epithelial," and "mesenchymal." The series comprised 48 ATRT-SHH, 40 ATRT-TYR, and 26 ATRT-MYC tumors. Inter-observer agreement was moderate but significant (Fleiss' kappa = 0.47; 95% C.I. 0.41-0.53; p < 0.001) and there was a highly significant overall association between morphological categories and molecular subgroups for each of the nine observers (p < 0.0001). Specifically, the category "epithelial" was found to be over-represented in ATRT-TYR (p < 0.000001) and the category "small-round-blue" to be over-represented in ATRT-SHH (p < 0.01). The majority of ATRT-MYC was categorized as "mesenchymal" or "rhabdoid," but this association was less compelling. The specificity of the category "epithelial" for ATRT-TYR was highest and accounted for 97% (range: 88-99%) whereas sensitivity was low [49% (range: 35%-63%)]. In line with these findings, cytokeratin-positivity was highly overrepresented in ATRT-TYR. In conclusion, morphological features of AT/RT might reflect molecular alterations and may also provide a first hint on molecular subgroup status, which will need to be confirmed by DNA methylation profiling.

Random forest regression analysis on combined role of meteorological indicators in disease dissemination in an Indian city: A case study of New Delhi

Meteorological parameters show a strong influence on disease transmission in urban localities. The combined influence of factors such as daily mean temperature, absolute humidity and average wind speed on the attack rate and mortality rate of COVID-19 rise in Delhi, India has been investigated in this case study. A Random forest regression algorithm has been utilized to compare the epidemiological and meteorological parameters. The performance of the model has been evaluated using statistical performance metrics. The random forest model shows a strong positive correlation between the predictor parameters on the attack rate (96.09%) and mortality rate (93.85%). On both the response variables, absolute humidity has been noted to be the variable of highest influence. In addition, both temperature and wind speed have shown moderate positive influence on the transmission and survival of coronavirus during the study period. The synergistic effect of absolute humidity with temperature and wind speed contributing towards the increase in the attack and mortality rate has been addressed. The inhibition to respiratory droplet evaporation, increment in droplet size due to hygroscopic effect and the enhanced duration of survival of coronavirus borne in respiratory droplets are attributed to the increase in coronavirus infection under the observed weather conditions.

Second-Generation Digital Health Platforms: Placing the Patient at the Center and Focusing on Clinical Outcomes

Artificial intelligence (AI) digital health systems have drawn much attention over the last decade. However, their implementation into medical practice occurs at a much slower pace than expected. This paper reviews some of the achievements of first-generation AI systems, and the barriers facing their implementation into medical practice. The development of second-generation AI systems is discussed with a focus on overcoming some of these obstacles. Second-generation systems are aimed at focusing on a single subject and on improving patients' clinical outcomes. A personalized closed-loop system designed to improve end-organ function and the patient's response to chronic therapies is presented. The system introduces a platform which implements a personalized therapeutic regimen and introduces quantifiable individualized-variability patterns into its algorithm. The platform is designed to achieve a clinically meaningful endpoint by ensuring that chronic therapies will have sustainable effect while overcoming compensatory mechanisms associated with disease progression and drug resistance. Second-generation systems are expected to assist patients and providers in adopting and implementing of these systems into everyday care.

Interrogating the microenvironmental landscape of tumors with computational image analysis approaches

The tumor microenvironment is an interacting heterogeneous collection of cancer cells, resident as well as infiltrating host cells, secreted factors, and extracellular matrix proteins. With the growing importance of immunotherapies, it has become crucial to be able to characterize the composition and the functional orientation of the microenvironment. The development of novel computational image analysis methodologies may enable the robust quantification and localization of immune and related biomarker-expressing cells within the microenvironment. The aim of the review is to concisely highlight a selection of current and significant contributions pertinent to methodological advances coupled with biomedical or translational applications. A further aim is to concisely present computational advances that, to our knowledge, have currently very limited use for the assessment of the microenvironment but have the potential to enhance image analysis pipelines; on this basis, an example is shown for the detection and segmentation of cells of the microenvironment using a published pipeline and a public dataset. Finally, a general proposal is presented on the conceptual design of automation-optimized computational image analysis workflows in the biomedical and clinical domain.