Digital Pathology Research Articles

A Study on Resolving Dynamic analysis using deep learning Framework Logical Methods

Deep learning technologies have gained a great deal of interest in recent months for demonstrating material removal capabilities in a variety of separation, categorization, as well as other machine vision activities. The majority of these deep networks are built employing convolution or completely convolution structures. Our suggested Dynamic and Static gestures System guided by a hand gesture high dimensional data methodology We use a snapshot of a human's thoracic spine to determine the person's depth and the size of the space around his or her hands. In this research, we provide a novel object-based deep-learning framework for semantic segmentation of extremely high-resolution satellite data. In specifically, we leverage object-based prior record by augmenting a fully convolutional neural network's training strategy with an anisotropic diffusion data pre-processing phase and an additional loss term. The goal of this restricted framework is to ensure that similar visual data is assigned to the same semantic class. Here, we employ intermediate steps based on traditional image processing techniques to aid in the resolution of the subsequent problem of classification, detection, or segmentation. Research shows that adding pre- and post-processing steps to a deep learning pipeline can boost model performance over using only the network. Recent advances in UQ algorithms used for deep learning are analysed, and their potential for use in relevance feedback is addressed. It also emphasizes basic research difficulties and directions linked with UQ. Quantifiably, man-made classes with more precise geometry, such as buildings, benefited the most from our strategy, particularly along object borders, indicating the developed approach's enormous potential. The purpose of this paper is to offer an overview of the approaches used inside deep learning frameworks to either appropriately prepare the input (pre-processing) or enhance the outcomes of the network output (post-processing), with an emphasis on digital pathology image analysis.

Mounting agents with low toxicity and with fast curing time for digital pathology in the intraoperative frozen section laboratory

AimsIn intraoperative frozen tissue section laboratories (FS laboratories) conventional practice for mounting coverslips on tissue slides involves the use of xylene-based mounting agents, such as Pertex. However, toxic vapours pose...

AI Digital Pathology Using qFibrosis Shows Heterogeneity of Fibrosis Regression in Patients with Chronic Hepatitis B and C with Viral Response.

This study aimed to understand the dynamic changes in fibrosis and its relationship with the evaluation of post-treatment viral hepatitis using qFibrosis. A total of 158 paired pre- and post-treatment liver samples from patients with chronic hepatitis B (CHB; n = 100) and C (CHC; n = 58) were examined. qFibrosis was employed with artificial intelligence (AI) to analyze the fibrosis dynamics in the portal tract (PT), periportal (PP), midzonal, pericentral, and central vein (CV) regions. All patients with CHB achieved a virological response after 78 weeks of treatment, whereas patients with CHC achieved a sustained viral response after 24 weeks. For patients initially staged as F5/6 (Ishak system) at baseline, the post-treatment cases exhibited a significant reduction in the collagen proportionate area (CPA) (25-69%) and number of collagen strings (#string) (9-72%) across all regions. In contrast, those initially staged as F3/4 at baseline showed a similar CPA and #string trend at 24 weeks. For regression patients, 27 parameters (25 in the CV region) in patients staged as F3/4 and 15 parameters (three in the PT and 12 in the PP regions) in those staged as F5/6 showed significant differences between the CHB and CHC groups at baseline. Following successful antiviral treatment, the pre- and post-treatment liver samples provided quantitative evidence of the heterogeneity of fibrotic features. qFibrosis has the potential to provide new insights into the characteristics of fibrosis regression in both patients with CHB and CHC as early as 24 weeks after antiviral therapy.

FR-MIL: Distribution Re-calibration based Multiple Instance Learning with Transformer for Whole Slide Image Classification.

In digital pathology, whole slide images (WSI) are crucial for cancer prognostication and treatment planning. WSI classification is generally addressed using multiple instance learning (MIL), alleviating the challenge of processing billions of pixels and curating rich annotations. Though recent MIL approaches leverage variants of the attention mechanism to learn better representations, they scarcely study the properties of the data distribution itself i.e., different staining and acquisition protocols resulting in intra-patch and inter-slide variations. In this work, we first introduce a distribution re-calibration strategy to shift the feature distribution of a WSI bag (instances) using the statistics of the max-instance (critical) feature. Second, we enforce class (bag) separation via a metric loss assuming that positive bags exhibit larger magnitudes than negatives. We also introduce a generative process leveraging Vector Quantization (VQ) for improved instance discrimination i.e., VQ helps model bag latent factors for improved classification. To model spatial and context information, a position encoding module (PEM) is employed with transformer-based pooling by multi-head self-attention (PMSA). Evaluation of popular WSI benchmark datasets reveals our approach improves over state-of-the-art MIL methods. Further, we validate the general applicability of our method on classic MIL benchmark tasks and for point cloud classification with limited points https://github.com/PhilipChicco/FRMIL.

Towards Digital Quantification of Ploidy from Pan-Cancer Digital Pathology Slides using Deep Learning.

Abnormal DNA ploidy, found in numerous cancers, is increasingly being recognized as a contributor in driving chromosomal instability, genome evolution, and the heterogeneity that fuels cancer cell progression. Furthermore, it has been linked with poor prognosis of cancer patients. While next-generation sequencing can be used to approximate tumor ploidy, it has a high error rate for near-euploid states, a high cost and is time consuming, motivating alternative rapid quantification methods. We introduce PloiViT, a transformer-based model for tumor ploidy quantification that outperforms traditional machine learning models, enabling rapid and cost-effective quantification directly from pathology slides. We trained PloiViT on a dataset of fifteen cancer types from The Cancer Genome Atlas and validated its performance in multiple independent cohorts. Additionally, we explored the impact of self-supervised feature extraction on performance. PloiViT, using self-supervised features, achieved the lowest prediction error in multiple independent cohorts, exhibiting better generalization capabilities. Our findings demonstrate that PloiViT predicts higher ploidy values in aggressive cancer groups and patients with specific mutations, validating PloiViT potential as complementary for ploidy assessment to next-generation sequencing data. To further promote its use, we release our models as a user-friendly inference application and a Python package for easy adoption and use.

Globalization of a telepathology network with artificial intelligence applications in Colombia: The GLORIA program study protocol

In Colombia, cancer is recognized as a high-cost pathology by the national government and the Colombian High-Cost Disease Fund. As of 2020, the situation is most critical for adult cancer patients, particularly those under public healthcare and residing in remote regions of the country. The highest lag time for a diagnosis was observed for cervical cancer (79.13 days), followed by prostate (77.30 days), and breast cancer (70.25 days). Timely and accurate histopathological reporting plays a vital role in the diagnosis of cancer. In recent years, digital pathology has been globally implemented as a technological tool in two main areas: telepathology (TP) and computational pathology. TP has been shown to improve rapid and timely diagnosis in anatomic pathology by facilitating interaction between general laboratories and specialized pathologists worldwide through information and telecommunication technologies. Computational pathology provides diagnostic and prognostic assistance based on histopathological patterns, molecular, and clinical information, aiding pathologists in making more accurate diagnoses. We present the study protocol of the GLORIA digital pathology network, a pioneering initiative, and national grant-approved program aiming to design and pilot a Colombian digital pathology transformation focused on TP and computational pathology, in response to the general needs of pathology laboratories for diagnosing complex malignant tumors. The study protocol describes the design of a TP network to expand oncopathology services across all Colombian regions. It also describes an artificial intelligence proposal for lung cancer, one of Colombia's most prevalent cancers, and a freely accessible national histopathological image database to facilitate image analysis studies.

Artificial Intelligence for the Automatic Diagnosis of Gastritis: A Systematic Review.

Background and Objective: Gastritis represents one of the most prevalent gastrointestinal diseases and has a multifactorial etiology, many forms of manifestation, and various symptoms. Diagnosis of gastritis is made based on clinical, endoscopic, and histological criteria, and although it is a thorough process, many cases are misdiagnosed or overlooked. This systematic review aims to provide an extensive overview of current artificial intelligence (AI) applications in gastritis diagnosis and evaluate the precision of these systems. This evaluation could highlight the role of AI as a helpful and useful tool in facilitating timely and accurate diagnoses, which in turn could improve patient outcomes. Methods: We have conducted an extensive and comprehensive literature search of PubMed, Scopus, and Web of Science, including studies published until July 2024. Results: Despite variations in study design, participant numbers and characteristics, and outcome measures, our observations suggest that implementing an AI automatic diagnostic tool into clinical practice is currently feasible, with the current systems achieving high levels of accuracy, sensitivity, and specificity. Our findings indicate that AI outperformed human experts in most studies, with multiple studies exhibiting an accuracy of over 90% for AI compared to human experts. These results highlight the significant potential of AI to enhance diagnostic accuracy and efficiency in gastroenterology. Conclusions: AI-based technologies can now automatically diagnose using images provided by gastroscopy, digital pathology, and radiology imaging. Deep learning models exhibited high levels of accuracy, sensitivity, and specificity while assessing the diagnosis, staging, and risk of neoplasia for different types of gastritis, results that are superior to those of human experts in most studies.

Gastric Cancer Detection with Ensemble Learning on Digital Pathology: Use Case of Gastric Cancer on GasHisSDB Dataset.

Gastric cancer has become a serious worldwide health concern, emphasizing the crucial importance of early diagnosis measures to improve patient outcomes. While traditional histological image analysis is regarded as the clinical gold standard, it is labour intensive and manual. In recognition of this problem, there has been a rise in interest in the use of computer-aided diagnostic tools to help pathologists with their diagnostic efforts. In particular, deep learning (DL) has emerged as a promising solution in this sector. However, current DL models are still restricted in their ability to extract extensive visual characteristics for correct categorization. To address this limitation, this study proposes the use of ensemble models, which incorporate the capabilities of several deep-learning architectures and use aggregate knowledge of many models to improve classification performance, allowing for more accurate and efficient gastric cancer detection. To determine how well these proposed models performed, this study compared them with other works, all of which were based on the Gastric Histopathology Sub-Size Images Database, a publicly available dataset for gastric cancer. This research demonstrates that the ensemble models achieved a high detection accuracy across all sub-databases, with an average accuracy exceeding 99%. Specifically, ResNet50, VGGNet, and ResNet34 performed better than EfficientNet and VitNet. For the 80 × 80-pixel sub-database, ResNet34 exhibited an accuracy of approximately 93%, VGGNet achieved 94%, and the ensemble model excelled with 99%. In the 120 × 120-pixel sub-database, the ensemble model showed 99% accuracy, VGGNet 97%, and ResNet50 approximately 97%. For the 160 × 160-pixel sub-database, the ensemble model again achieved 99% accuracy, VGGNet 98%, ResNet50 98%, and EfficientNet 92%, highlighting the ensemble model's superior performance across all resolutions. Overall, the ensemble model consistently provided an accuracy of 99% across the three sub-pixel categories. These findings show that ensemble models may successfully detect critical characteristics from smaller patches and achieve high performance. The findings will help pathologists diagnose gastric cancer using histopathological images, leading to earlier identification and higher patient survival rates.

CellRegNet: Point Annotation-Based Cell Detection in Histopathological Images via Density Map Regression.

Recent advances in deep learning have shown significant potential for accurate cell detection via density map regression using point annotations. However, existing deep learning models often struggle with multi-scale feature extraction and integration in complex histopathological images. Moreover, in multi-class cell detection scenarios, current density map regression methods typically predict each cell type independently, failing to consider the spatial distribution priors of different cell types. To address these challenges, we propose CellRegNet, a novel deep learning model for cell detection using point annotations. CellRegNet integrates a hybrid CNN/Transformer architecture with innovative feature refinement and selection mechanisms, addressing the need for effective multi-scale feature extraction and integration. Additionally, we introduce a contrastive regularization loss that models the mutual exclusiveness prior in multi-class cell detection cases. Extensive experiments on three histopathological image datasets demonstrate that CellRegNet outperforms existing state-of-the-art methods for cell detection using point annotations, with F1-scores of 86.38% on BCData (breast cancer), 85.56% on EndoNuke (endometrial tissue) and 93.90% on MBM (bone marrow cells), respectively. These results highlight CellRegNet's potential to enhance the accuracy and reliability of cell detection in digital pathology.

AnNoBrainer, An Automated Annotation of Mouse Brain Images using Deep Learning.

Annotation of multiple regions of interest across the whole mouse brain is an indispensable process for quantitative evaluation of a multitude of study endpointsin neuroscience digital pathology. Prior experience and domain expert knowledge are the key aspects for image annotation quality and consistency. At present, image annotation is often achieved manually by certified pathologists or trained technicians, limiting the total throughput of studies performed at neuroscience digital pathology labs. It may also mean that simpler and quicker methods of examining tissue samples are used by non-pathologists, especially in the early stages of research and preclinical studies. To address these limitations and to meet the growing demand for image analysis in a pharmaceutical setting, we developed AnNoBrainer, an open-source software tool that leverages deep learning, image registration, and standard cortical brain templates to automatically annotate individual brain regions on 2D pathology slides. Application of AnNoBrainer to a published set of pathology slides from transgenic mice models of synucleinopathy revealed comparable accuracy, increased reproducibility, and a significant reduction (~ 50%) in time spent on brain annotation, quality control and labelling compared to trained scientists in pathology. Taken together, AnNoBrainer offers a rapid, accurate, and reproducible automated annotation of mouse brain images that largely meets the experts' histopathological assessment standards (> 85% of cases) and enables high-throughput image analysis workflows in digital pathology labs.

Artificial Intelligence Applications in Oral Cancer and Oral Dysplasia.

Oral squamous cell carcinoma (OSCC) is a highly unpredictable disease with devastating mortality rates that have not changed over the past decades, in the face of advancements in treatments and biomarkers, which have improved survival for other cancers. Delays in diagnosis are frequent, leading to more disfiguring treatments and poor outcomes for patients. The clinical challenge lies in identifying those patients at the highest risk of developing OSCC. Oral epithelial dysplasia (OED) is a precursor of OSCC with highly variable behavior across patients. There is no reliable clinical, pathological, histological, or molecular biomarker to determine individual risk in OED patients. Similarly, there are no robust biomarkers to predict treatment outcomes or mortality in OSCC patients. This review aims to highlight advancements in artificial intelligence (AI)-based methods to develop predictive biomarkers of OED transformation to OSCC or predictive biomarkers of OSCC mortality and treatment response. Biomarkers such as S100A7 demonstrate promising appraisal for the risk of malignant transformation of OED. Machine learning-enhanced multiplex immunohistochemistry workflows examine immune cell patterns and organization within the tumor immune microenvironment to generate outcome predictions in immunotherapy. Deep learning (DL) is an AI-based method using an extended neural network or related architecture with multiple "hidden" layers of simulated neurons to combine simple visual features into complex patterns. DL-based digital pathology is currently being developed to assess OED and OSCC outcomes. The integration of machine learning in epigenomics aims to examine the epigenetic modification of diseases and improve our ability to detect, classify, and predict outcomes associated with epigenetic marks. Collectively, these tools showcase promising advancements in discovery and technology, which may provide a potential solution to addressing the current limitations in predicting OED transformation and OSCC behavior, both of which are clinical challenges that must be addressed in order to improve OSCC survival.

CINNAMON-GUI: Revolutionizing Pap Smear Analysis with CNN-Based Digital Pathology Image Classification

Background Medical imaging has seen significant advancements through machine learning, particularly convolutional neural networks (CNNs). These technologies have transformed the analysis of pathological images, enhancing the accuracy of diagnosing and classifying cellular anomalies. Digital pathology methodologies, including image analysis, have improved cervical cancer diagnostics. However, existing commercial platforms are often costly and restrictive, limiting customization and scalability. Methods CINNAMON-GUI is an open-source digital pathology tool based on CNNs for classifying Pap smear images. Transitioning to a Shiny app in Python, it offers enhanced user interface and interactivity. The application supports dynamic web interactions, advanced features for image analysis, and state-of-the-art CNN models tailored for digital pathology. Key features include intuitive UI components, real-time image and plot generation, memory-efficient data handling, and robust training capabilities with customizable CNN architectures. The tool also integrates with Labelme for defining regions of interest and allows testing on external biospecimens. Results Model A (seed 42, 100 epochs) and Model B (same architecture with adjusted augmentation parameters) were compared. Model A stabilized with training accuracy around 0.88 and validation accuracy around 0.913. Model B showed improved performance with training accuracy around 0.91 and validation accuracy around 0.95. Feature mapping highlighted critical morphological aspects, improving classification accuracy. Model B reduced misclassification errors significantly compared to Model A. Conclusions CINNAMON-GUI demonstrates the potential of an open-source platform in digital pathology, providing transparency and collaborative opportunities. The tool enhances diagnostic accuracy through feature map analysis and optimized CNN training. Future development aims to extend its application to other cancer types, leveraging its dynamic and user-friendly interface for broader use in diagnostics.

Exploring the link between dystrophic microglia and the spread of Alzheimer's neuropathology.

Genetics and other data modalities indicate that microglia play a critical role in Alzheimer's disease (AD) progression, but details of microglia's disease-driving influence are poorly understood. Microglial cells can be parsed into subtypes based on their histologic appearance. One microglia subtype, termed dystrophic microglia, is characterised structurally by fragmented processes and cytoplasmic decay, and their presence has been associated with ageing and neurodegeneration. Recent studies suggest that the interaction between tau proteins and amyloid-β might induce dystrophic changes in microglia, potentially linking amyloid-β and tau pathologies to their effects on these microglia. We developed a study of human brains to test the hypothesis that dystrophic microglia are involved in AD progression. We speculated that if their presence is unique to AD neuropathologic change (ADNC), they would be substantially more common in ADNC than in neurodegenerative diseases characterised by other proteinopathies, e.g., α-synuclein or TDP-43 pathology. Our analyses used histologically stained sections from five human brain regions of 64 individuals across six disease states, from healthy controls to advanced AD stages, including comparative conditions such as Lewy Body Disease (LBD) and limbic-predominant age-related TDP-43 encephalopathy neuropathologic change (LATE-NC). Using stereological sampling and digital pathology, we assessed ramified, hypertrophic, and dystrophic microglia populations. We found a significant increase in dystrophic microglia in areas early affected by ADNC, suggesting a disease-specific role in neuropathology. Mediation analysis and structural equation modelling suggest dystrophic microglia may impact the regional spread of ADNC. In the mediation model, tau was found to be the initiating factor leading to the development of dystrophic microglia, which then was associated with the spread of amyloid-β and tau. These results suggest that a loss of microglia's protective role could contribute to the spread of ADNC and indicate that further research into preserving microglial function may be warranted.

A dynamic uncertainty-aware ensemble model: Application to lung cancer segmentation in digital pathology

Ensemble models have emerged as a powerful technique for improving robustness in medical image segmentation. However, traditional ensembles suffer from limitations such as under-confidence and over-reliance on poor performing models. In this work, we introduce an Adaptive Uncertainty-based Ensemble (AUE) model for tumor segmentation in histopathological slides. Our approach leverages uncertainty estimates from Monte Carlo dropout during testing to dynamically select the optimal pair of models for each whole slide image. The AUE model combines predictions from the two most reliable models (K-Net, ResNeSt, Segformer, Twins), identified through uncertainty quantification, to enhance segmentation performance. We validate the AUE model on the ACDC@LungHP challenge dataset, systematically comparing it against state-of-the-art approaches. Results demonstrate that our uncertainty-guided ensemble achieves a mean Dice score of 0.8653 and outperforms traditional ensemble techniques and top-ranked methods from the challenge by over 3 %. Our adaptive ensemble approach provides accurate and reliable lung tumor delineation in histopathology images by managing model uncertainty.

Second harmonic generation digital pathology with artificial intelligence: breakthroughs in studying fibrosis dynamics and treatment response

Fibrosis represents a highly conserved response to tissue injury. Assessing fibrosis is central in diagnostic pathology, evaluating treatment response and prognosis. Second harmonic generation digital pathology with artificial intelligence analyses provides unparalleled precision and granularity in quantifying tissue collagen in its natural, unstained environment.. This technology reveals new insights into the balance between fibrogenesis and fibrolysis, crucial in tracking disease evolution and treatment outcomes. This review describes applications of second harmonic generation digital pathology with artificial intelligence for detailed characterization of liver fibrosis, assessing treatment response in clinical trials, analyzing collagen features in other chronic diseases and cancers. Additionally, it offers a perspective on future developments in integrating various technologies into a comprehensive diagnostic workflow for more effective evaluation of therapy and disease prognosis.

Decoding pathology: the role of computational pathology in research and diagnostics.

Traditional histopathology, characterized by manual quantifications and assessments, faces challenges such as low-throughput and inter-observer variability that hinder the introduction of precision medicine in pathology diagnostics and research. The advent of digital pathology allowed the introduction of computational pathology, a discipline that leverages computational methods, especially based on deep learning (DL) techniques, to analyze histopathology specimens. A growing body of research shows impressive performances of DL-based models in pathology for a multitude of tasks, such as mutation prediction, large-scale pathomics analyses, or prognosis prediction. New approaches integrate multimodal data sources and increasingly rely on multi-purpose foundation models. This review provides an introductory overview of advancements in computational pathology and discusses their implications for the future of histopathology in research and diagnostics.

Integrating telepathology and digital pathology with artificial intelligence: An inevitable future

Telepathology and digital pathology, enhanced with artificial intelligence (AI), represent groundbreaking technology advancements. These entities offer information exchange, enhanced teaching and research, and automated diagnosis with high precision through a computerized approach. Machine learning in pathology shows promise for both human and veterinary medicine, yielding favorable results and in some cases, surpassing the accuracy of human pathologists. This study aimed to highlight the significance of integrated AI with telepathology and digital pathology, outlining both its advantages and limitations while emphasizing the crucial role of pathologists in its implementation. A literature review was conducted to uncover publications and data on telepathology and AI, and their implementation in human and veterinary medicine. This approach has facilitated information exchange, enhancing both teaching and research. In addition, it facilitates the creation of innovative methods and offers more precise patient diagnoses, adhering to ethical and legal standards. This study delivers valuable and comparable data on telepathology, digital pathology, and AI integration. Given the continually emerging nature of these technologies, further studies are essential for their application to human and veterinary medicine. Keywords: artificial intelligence, diagnosis, telepathology.

A hierarchical algorithm with randomized learning for robust tissue segmentation and classification in digital pathology

Highly detailed and accurate segmentation and classification of images constitutes an important class of tasks in computer vision. Typical “universal” domain-agnostic methods are known to suffer from instabilities and are prone to adversarial perturbations. Natural heterogeneity inherent in biological tissue structures complicates the interpretation of images even by trained physicians. Yet, algorithms in the medical domain require a high level of stability and interpretability to ensure their adoption by clinical experts and acceptance in clinical decision-making. In this work, we propose a novel method for segmentation and classification to address these challenges. The method is based on a hierarchical approach and biologically-informed feature extraction. The method's technical pipeline includes the automatic extraction of key biologically-informed features typically considered by physicians. This is followed by image classification using these features. Both stages rely on randomized ML techniques. The proposed hierarchical biomedically-informed approach significantly improved the image classification quality compared to the baseline solution of image classification in the task of colorectal cancer (CRC) analysis. The average F1-score for the four tissue types increased from 0.737 to 0.956. Using tumor tissue classification task as an example, we showed that the proposed algorithm offers an effective and practical avenue to solve these challenging issues.

Spatial distribution of tumour immune infiltrate predicts outcomes of patients with high-risk soft tissue sarcomas after neoadjuvant chemotherapy

BackgroundAnthracycline-based neoadjuvant chemotherapy (NAC) may modify tumour immune infiltrate. This study characterized immune infiltrate spatial distribution after NAC in primary high-risk soft tissue sarcomas (STS) and investigate association with prognosis. MethodsThe ISG-STS 1001 trial randomized STS patients to anthracycline plus ifosfamide (AI) or a histology-tailored (HT) NAC. Four areas of tumour specimens were sampled: the area showing the highest lymphocyte infiltrate (HI) at H&E; the area with lack of post-treatment changes (highest grade, HG); the area with post-treatment changes (lowest grade, LG); and the tumour edge (TE). CD3, CD8, PD-1, CD20, FOXP3, and CD163 were analyzed at immunohistochemistry and digital pathology. A machine learning method was used to generate sarcoma immune index scores (SIS) that predict patient disease-free and overall survival (DFS and OS). FindingsTumour infiltrating lymphocytes and PD-1+ cells together with CD163+ cells were more represented in STS histologies with complex compared to simple karyotype, while CD20+ B-cells were detected in both these histology groups. PD-1+ cells exerted a negative prognostic value irrespectively of their spatial distribution. Enrichment in CD20+ B-cells at HI and TE areas was associated with better patient outcomes. We generated a prognostic SIS for each tumour area, having the HI-SIS the best performance. Such prognostic value was driven by treatment with AI. InterpretationThe different spatial distribution of immune populations and their different association with prognosis support NAC as a modifier of tumour immune infiltrate in STS.Funding: Pharmamar; Italian Ministry of Health [RF-2019-12370923; GR-2016-02362609]; 5x1000 Funds—2016, Italian Ministry of Health; AIRC Grant [ID#28546].

Trends in Active Surveillance for Men With Intermediate-Risk Prostate Cancer

Initial management of intermediate-risk prostate cancer is evolving, with no clear recommendation for treatment. Data on utilization of active surveillance for patients with newly diagnosed intermediate-risk prostate cancer may help clarify emerging trends. To further characterize US national trends of initial management of intermediate-risk prostate cancer. This cohort study included patients with intermediate-risk prostate cancer diagnosed from January 1, 2010, to December 31, 2020. Eligible patients were diagnosed in US hospitals included in the National Cancer Database; National Comprehensive Cancer Network risk stratification guidelines were used to characterize as favorable vs unfavorable intermediate risk. Analysis was performed in September 2023. Active surveillance vs intervention with surgery and/or radiation or no treatment. Temporal trends in demographic, clinical, and socioeconomic factors among men with intermediate-risk prostate cancer and their association with the use of active surveillance; further subgroup analysis was conducted for those with favorable vs unfavorable intermediate risk classification. In total, 289 584 men diagnosed with intermediate-risk prostate cancer were identified from 2010 to 2020 (46 147 Black [15.9%], 230 071 White [79.5%]). Among patients, 153 726 (53.1%) underwent prostatectomy, 107 152 (37.0%) underwent radiotherapy, and 15 847 (5.5%) underwent active surveillance as initial treatment strategy. Overall, active surveillance quadrupled from 418 of 21 457 patients (2.0%) in 2010 to 2428 of 28 192 patients (8.6%) in 2020 for the entire cohort (P < .001). Active surveillance increased from 317 of 12 858 patients (2.4%) in 2010 to 2020 of 12 902 patients (13.5%) in 2020 in men with favorable intermediate-risk prostate cancer (P < .001). In the unfavorable intermediate-risk cohort, active surveillance increased from 101 of 8181 patients (1.2%) in 2010 to 408 of 12 861 patients (3.1%) in 2020 (P < .001). On multivariable analysis, use of active surveillance was associated with increased age (age 70-80 years vs <50 years: odds ratio [OR], 3.09; 95% CI, 2.66-3.59), lower Gleason score (3 + 3 vs 3 + 4: OR, 3.45; 95% CI, 3.25-3.66), early T stage (T2c vs T1a through T2a: OR, 0.35; 95% CI, 0.32-0.38), treatment at an academic center (community vs academic center: OR, 0.72; 95% CI, 0.67-0.78), higher level of education (communities with 21% or higher population without high school vs less than 7%: OR, 0.73; 95% CI, 0.67-0.79), insurance type (Medicare or other governmental service vs private: OR, 1.11; 95% CI, 1.07-1.16), proximity to treatment facility (greater than 120 miles vs less than 60 miles: OR, 0.75; 95% CI, 0.68-0.84), facility location (South Atlantic vs New England: OR, 0.54; 95% CI, 0.46-0.53), and lower income (less than $38 000 vs $63 000 or greater: OR, 1.22; 95% CI, 1.14-1.31). These findings highlight increasing implementation of active surveillance in the initial management of intermediate risk prostate cancer. Prospective data with improved risk stratification incorporating genomics and digital pathology artificial intelligence as well as novel surveillance strategies may continue to better delineate optimal treatment recommendations in this patient population.