Development and validation of a deep learning-based microsatellite instability predictor from prostate cancer whole-slide images.

Microsatellite instability-high (MSI-H) is a tumor-agnostic biomarker for immune checkpoint inhibitor therapy. However, MSI status is not routinely tested in prostate cancer, in part due to low prevalence and assay cost. As such, prediction of MSI status from hematoxylin and eosin (H&E) stained whole-slide images (WSIs) could identify prostate cancer patients most likely to benefit from confirmatory testing to evaluate their eligibility for immunotherapy and need for Lynch syndrome testing. Prostate biopsies and surgical resections from prostate cancer patients referred to our institution were analyzed. MSI status was determined by next-generation sequencing. Patients sequenced before a cutoff date formed an algorithm development set (n = 4015, MSI-H 1.8%) and a paired validation set (n = 173, MSI-H 19.7%) that consisted of two serial sections from each sample, one stained and scanned internally and the other at an external site. Patients sequenced after the cutoff date formed a temporally independent validation set (n = 1350, MSI-H 2.3%). Attention-based multiple instance learning models were trained to predict MSI-H from H&E WSIs. The predictor achieved area under the receiver operating characteristic curve values of 0.78 (95% CI [0.69-0.86]), 0.72 (95% CI [0.63-0.81]), and 0.72 (95% CI [0.62-0.82]) on the internally prepared, externally prepared, and temporal validation sets, respectively, showing effective predictability and generalization to both external staining/scanning processes and temporally independent samples. While MSI-H status is significantly correlated with Gleason score, the model remained predictive within each Gleason score subgroup.

Prediction of MET Overexpression in Lung Adenocarcinoma from Hematoxylin and Eosin Images.

Mesenchymal epithelial transition (MET) protein overexpression is a targetable event in non-small cell lung cancer and is the subject of active drug development. Challenges in identifying patients for these therapies include lack of access to validated testing, such as standardized immunohistochemistry assessment, and consumption of valuable tissue for a single gene/protein assay. Development of prescreening algorithms using routinely available digitized hematoxylin and eosin (H&E)-stained slides to predict MET overexpression could promote testing for those who will benefit most. Recent literature reports a positive correlation between MET protein overexpression and RNA expression. In this work, a large database of matched H&E slides and RNA expression data were leveraged to train a weakly supervised model to predict MET RNA overexpression directly from H&E images. This model was evaluated on an independent holdout test set of 300 overexpressed and 289 normal patients, demonstrating a receiver operating characteristic area under curve of 0.70 (95th percentile interval: 0.66 to 0.74) with stable performance characteristics across different patient clinical variables and robust to synthetic noise on the test set. These results suggest that H&E-based predictive models could be useful to prioritize patients for confirmatory testing of MET protein or MET gene expression status.

Assessing the utility of molecular diagnostic classification for cancers of unknown primary.

BACKGROUND: Roughly 5% of metastatic cancers present with uncertain origin, for which molecular classification could influence subsequent management; however, prior studies of molecular diagnostic classifiers have reported mixed results with regard to clinical impact. In this retrospective study, we evaluated the utility of a novel molecular diagnostic classifier by assessing theoretical changes in treatment and additional testing recommendations from oncologists before and after the review of classifier predictions. METHODS: We retrospectively analyzed de-identified records from 289 patients with a consensus diagnosis of cancer of uncertain/unknown primary (CUP). Two (or three, if adjudication was required) independent oncologists separately reviewed patient clinical information to determine the course of treatment before they reviewed results from the molecular diagnostic classifier and subsequently evaluated whether the predicted diagnosis would alter their treatment plan. RESULTS: Results from the molecular diagnostic classifier changed the consensus oncologist-reported treatment recommendations for 235 out of 289 patients (81.3%). At the level of individual oncologist reviews (n = 414), 64.7% (n = 268) of treatment recommendations were based on CUP guidelines prior to review of results from the molecular diagnostic classifier. After seeing classifier results, 98.1% (n = 207) of the reviews, where treatment was specified (n = 211), were guided by the tissue of origin-specific guidelines. Overall, 89.9% of the 414 total reviews either expressed strong agreement (n = 242) or agreement (n = 130) that the molecular diagnostic classifier result increased confidence in selecting the most appropriate treatment regimen. CONCLUSIONS: A retrospective review of CUP cases demonstrates that a novel molecular diagnostic classifier could affect treatment in the majority of patients, supporting its clinical utility. Further studies are needed to prospectively evaluate whether the use of molecular diagnostic classifiers improves clinical outcomes in CUP patients.

Validation of a Transcriptome-Based Assay for Classifying Cancers of Unknown Primary Origin.

INTRODUCTION: Cancers assume a variety of distinct histologies, and may originate from a myriad of sites including solid organs, hematopoietic cells, and connective tissue. Clinical decision-making based on consensus guidelines such as the National Comprehensive Cancer Network (NCCN) is often predicated on a specific histologic and anatomic diagnosis, supported by clinical features and pathologist interpretation of morphology and immunohistochemical (IHC) staining patterns. However, in patients with nonspecific morphologic and IHC findings-in addition to ambiguous clinical presentations such as recurrence versus new primary-a definitive diagnosis may not be possible, resulting in the patient being categorized as having a cancer of unknown primary (CUP). Therapeutic options and clinical outcomes are poor for patients with CUP, with a median survival of 8-11 months. METHODS: Here, we describe and validate the Tempus Tumor Origin (Tempus TO) assay, an RNA-sequencing-based machine learning classifier capable of discriminating between 68 clinically relevant cancer subtypes. Model accuracy was assessed using primary and/or metastatic samples with known subtype. RESULTS: We show that the Tempus TO model is 91% accurate when assessed on both a retrospectively held out cohort and a set of samples sequenced after model freeze that collectively contained 9210 total samples with known diagnoses. When evaluated on a cohort of CUPs, the model recapitulated established associations between genomic alterations and cancer subtype. DISCUSSION: Combining diagnostic prediction tests (e.g., Tempus TO) with sequencing-based variant reporting (e.g., Tempus xT) may expand therapeutic options for patients with cancers of unknown primary or uncertain histology.

Artificial intelligence-augmented histopathologic review using image analysis to optimize DNA yield from formalin-fixed paraffin-embedded slides.

To achieve minimum DNA input requirements for next-generation sequencing (NGS), pathologists visually estimate macrodissection and slide count decisions. Unfortunately, misestimation may cause tissue waste and increased laboratory costs. We developed an artificial intelligence (AI)-augmented smart pathology review system (SmartPath) to empower pathologists with quantitative metrics for accurately determining tissue extraction parameters. SmartPath uses two deep learning architectures, a U-Net based network for cell segmentation and a multi-field-of-view convolutional network for tumor area segmentation, to extract features from digitized H&E-stained formalin-fixed paraffin-embedded slides. From the segmented tumor area, SmartPath suggests a macrodissection area. To predict DNA yield per slide, the extracted features from within the macrodissection area are correlated with known DNA yields to fit a regularized linear model (R = 0.85). Then, a pathologist-defined target yield divided by the predicted DNA yield per slide gives the number of slides to scrape. Following model development, an internal validation trial was conducted within the Tempus Labs molecular sequencing laboratory. We evaluated our system on 501 clinical colorectal cancer slides, where half received SmartPath-augmented review and half traditional pathologist review. The SmartPath cohort had 25% more DNA yields within a desired target range of 100-2000 ng. The number of extraction attempts was statistically unchanged between cohorts. The SmartPath system recommended fewer slides to scrape for large tissue sections, saving tissue in these cases. Conversely, SmartPath recommended more slides to scrape for samples with scant tissue sections, especially those with degraded DNA, helping prevent costly re-extraction due to insufficient extraction yield. A statistical analysis was performed to measure the impact of covariates on the results, offering insights on how to improve future applications of SmartPath. With these improvements, AI-augmented histopathologic review has the potential to decrease tissue waste, sequencing time, and laboratory costs by optimizing DNA yields, especially for samples with scant tissue and/or degraded DNA.

Privacy preserving validation for multiomic prediction models.

Reproducibility of results obtained using ribonucleic acid (RNA) data across labs remains a major hurdle in cancer research. Often, molecular predictors trained on one dataset cannot be applied to another due to differences in RNA library preparation and quantification, which inhibits the validation of predictors across labs. While current RNA correction algorithms reduce these differences, they require simultaneous access to patient-level data from all datasets, which necessitates the sharing of training data for predictors when sharing predictors. Here, we describe SpinAdapt, an unsupervised RNA correction algorithm that enables the transfer of molecular models without requiring access to patient-level data. It computes data corrections only via aggregate statistics of each dataset, thereby maintaining patient data privacy. Despite an inherent trade-off between privacy and performance, SpinAdapt outperforms current correction methods, like Seurat and ComBat, on publicly available cancer studies, including TCGA and ICGC. Furthermore, SpinAdapt can correct new samples, thereby enabling unbiased evaluation on validation cohorts. We expect this novel correction paradigm to enhance research reproducibility and to preserve patient privacy.

A pan-cancer organoid platform for precision medicine.

Patient-derived tumor organoids (TOs) are emerging as high-fidelity models to study cancer biology and develop novel precision medicine therapeutics. However, utilizing TOs for systems-biology-based approaches has been limited by a lack of scalable and reproducible methods to develop and profile these models. We describe a robust pan-cancer TO platform with chemically defined media optimized on cultures acquired from over 1,000 patients. Crucially, we demonstrate tumor genetic and transcriptomic concordance utilizing this approach and further optimize defined minimal media for organoid initiation and propagation. Additionally, we demonstrate a neural-network-based high-throughput approach for label-free, light-microscopy-based drug assays capable of predicting patient-specific heterogeneity in drug responses with applicability across solid cancers. The pan-cancer platform, molecular data, and neural-network-based drug assay serve as resources to accelerate the broad implementation of organoid models in precision medicine research and personalized therapeutic profiling programs.

Interpretable survival prediction for colorectal cancer using deep learning.

Deriving interpretable prognostic features from deep-learning-based prognostic histopathology models remains a challenge. In this study, we developed a deep learning system (DLS) for predicting disease-specific survival for stage II and III colorectal cancer using 3652 cases (27,300 slides). When evaluated on two validation datasets containing 1239 cases (9340 slides) and 738 cases (7140 slides), respectively, the DLS achieved a 5-year disease-specific survival AUC of 0.70 (95% CI: 0.66-0.73) and 0.69 (95% CI: 0.64-0.72), and added significant predictive value to a set of nine clinicopathologic features. To interpret the DLS, we explored the ability of different human-interpretable features to explain the variance in DLS scores. We observed that clinicopathologic features such as T-category, N-category, and grade explained a small fraction of the variance in DLS scores (R2 = 18% in both validation sets). Next, we generated human-interpretable histologic features by clustering embeddings from a deep-learning-based image-similarity model and showed that they explained the majority of the variance (R2 of 73-80%). Furthermore, the clustering-derived feature most strongly associated with high DLS scores was also highly prognostic in isolation. With a distinct visual appearance (poorly differentiated tumor cell clusters adjacent to adipose tissue), this feature was identified by annotators with 87.0-95.5% accuracy. Our approach can be used to explain predictions from a prognostic deep learning model and uncover potentially-novel prognostic features that can be reliably identified by people for future validation studies.

Real-world Evidence of Diagnostic Testing and Treatment Patterns in US Patients With Breast Cancer With Implications for Treatment Biomarkers From RNA Sequencing Data.

OBJECTIVE/BACKGROUND: We performed a retrospective analysis of longitudinal real-world data (RWD) from patients with breast cancer to replicate results from clinical studies and demonstrate the feasibility of generating real-world evidence. We also assessed the value of transcriptome profiling as a complementary tool for determining molecular subtypes. METHODS: De-identified, longitudinal data were analyzed after abstraction from records of patients with breast cancer in the United States (US) structured and stored in the Tempus database. Demographics, clinical characteristics, molecular subtype, treatment history, and survival outcomes were assessed according to strict qualitative criteria. RNA sequencing and clinical data were used to predict molecular subtypes and signaling pathway enrichment. RESULTS: The clinical abstraction cohort (n = 4000) mirrored the demographics and clinical characteristics of patients with breast cancer in the US, indicating feasibility for RWE generation. Among patients who were human epidermal growth factor receptor 2-positive (HER2+), 74.2% received anti-HER2 therapy, with ∼70% starting within 3 months of a positive test result. Most non-treated patients were early stage. In this RWD set, 31.7% of patients with HER2+ immunohistochemistry (IHC) had discordant fluorescence in situ hybridization results recorded. Among patients with multiple HER2 IHC results at diagnosis, 18.6% exhibited intra-test discordance. Through development of a whole-transcriptome model to predict IHC receptor status in the molecular sequenced cohort (n = 400), molecular subtypes were resolved for all patients (n = 36) with equivocal HER2 statuses from abstracted test results. Receptor-related signaling pathways were differentially enriched between clinical molecular subtypes. CONCLUSIONS: RWD in the Tempus database mirrors the overall population of patients with breast cancer in the US. These results suggest that real-time, RWD analyses are feasible in a large, highly heterogeneous database. Furthermore, molecular data may aid deficiencies and discrepancies observed from breast cancer RWD.

Predicting prostate cancer specific-mortality with artificial intelligence-based Gleason grading.

Background: Gleason grading of prostate cancer is an important prognostic factor, but suffers from poor reproducibility, particularly among non-subspecialist pathologists. Although artificial intelligence (A.I.) tools have demonstrated Gleason grading on-par with expert pathologists, it remains an open question whether and to what extent A.I. grading translates to better prognostication. Methods: In this study, we developed a system to predict prostate cancer-specific mortality via A.I.-based Gleason grading and subsequently evaluated its ability to risk-stratify patients on an independent retrospective cohort of 2807 prostatectomy cases from a single European center with 5-25 years of follow-up (median: 13, interquartile range 9-17). Results: Here, we show that the A.I.'s risk scores produced a C-index of 0.84 (95% CI 0.80-0.87) for prostate cancer-specific mortality. Upon discretizing these risk scores into risk groups analogous to pathologist Grade Groups (GG), the A.I. has a C-index of 0.82 (95% CI 0.78-0.85). On the subset of cases with a GG provided in the original pathology report (n = 1517), the A.I.'s C-indices are 0.87 and 0.85 for continuous and discrete grading, respectively, compared to 0.79 (95% CI 0.71-0.86) for GG obtained from the reports. These represent improvements of 0.08 (95% CI 0.01-0.15) and 0.07 (95% CI 0.00-0.14), respectively. Conclusions: Our results suggest that A.I.-based Gleason grading can lead to effective risk stratification, and warrants further evaluation for improving disease management.

Evaluation of the Use of Combined Artificial Intelligence and Pathologist Assessment to Review and Grade Prostate Biopsies.

Importance: Expert-level artificial intelligence (AI) algorithms for prostate biopsy grading have recently been developed. However, the potential impact of integrating such algorithms into pathologist workflows remains largely unexplored. Objective: To evaluate an expert-level AI-based assistive tool when used by pathologists for the grading of prostate biopsies. Design, Setting, and Participants: This diagnostic study used a fully crossed multiple-reader, multiple-case design to evaluate an AI-based assistive tool for prostate biopsy grading. Retrospective grading of prostate core needle biopsies from 2 independent medical laboratories in the US was performed between October 2019 and January 2020. A total of 20 general pathologists reviewed 240 prostate core needle biopsies from 240 patients. Each pathologist was randomized to 1 of 2 study cohorts. The 2 cohorts reviewed every case in the opposite modality (with AI assistance vs without AI assistance) to each other, with the modality switching after every 10 cases. After a minimum 4-week washout period for each batch, the pathologists reviewed the cases for a second time using the opposite modality. The pathologist-provided grade group for each biopsy was compared with the majority opinion of urologic pathology subspecialists. Exposure: An AI-based assistive tool for Gleason grading of prostate biopsies. Main Outcomes and Measures: Agreement between pathologists and subspecialists with and without the use of an AI-based assistive tool for the grading of all prostate biopsies and Gleason grade group 1 biopsies. Results: Biopsies from 240 patients (median age, 67 years; range, 39-91 years) with a median prostate-specific antigen level of 6.5 ng/mL (range, 0.6-97.0 ng/mL) were included in the analyses. Artificial intelligence-assisted review by pathologists was associated with a 5.6% increase (95% CI, 3.2%-7.9%; P < .001) in agreement with subspecialists (from 69.7% for unassisted reviews to 75.3% for assisted reviews) across all biopsies and a 6.2% increase (95% CI, 2.7%-9.8%; P = .001) in agreement with subspecialists (from 72.3% for unassisted reviews to 78.5% for assisted reviews) for grade group 1 biopsies. A secondary analysis indicated that AI assistance was also associated with improvements in tumor detection, mean review time, mean self-reported confidence, and interpathologist agreement. Conclusions and Relevance: In this study, the use of an AI-based assistive tool for the review of prostate biopsies was associated with improvements in the quality, efficiency, and consistency of cancer detection and grading.

Development and Validation of a Deep Learning Algorithm for Gleason Grading of Prostate Cancer From Biopsy Specimens.

Importance: For prostate cancer, Gleason grading of the biopsy specimen plays a pivotal role in determining case management. However, Gleason grading is associated with substantial interobserver variability, resulting in a need for decision support tools to improve the reproducibility of Gleason grading in routine clinical practice. Objective: To evaluate the ability of a deep learning system (DLS) to grade diagnostic prostate biopsy specimens. Design, Setting, and Participants: The DLS was evaluated using 752 deidentified digitized images of formalin-fixed paraffin-embedded prostate needle core biopsy specimens obtained from 3 institutions in the United States, including 1 institution not used for DLS development. To obtain the Gleason grade group (GG), each specimen was first reviewed by 2 expert urologic subspecialists from a multi-institutional panel of 6 individuals (years of experience: mean, 25 years; range, 18-34 years). A third subspecialist reviewed discordant cases to arrive at a majority opinion. To reduce diagnostic uncertainty, all subspecialists had access to an immunohistochemical-stained section and 3 histologic sections for every biopsied specimen. Their review was conducted from December 2018 to June 2019. Main Outcomes and Measures: The frequency of the exact agreement of the DLS with the majority opinion of the subspecialists in categorizing each tumor-containing specimen as 1 of 5 categories: nontumor, GG1, GG2, GG3, or GG4-5. For comparison, the rate of agreement of 19 general pathologists' opinions with the subspecialists' majority opinions was also evaluated. Results: For grading tumor-containing biopsy specimens in the validation set (n = 498), the rate of agreement with subspecialists was significantly higher for the DLS (71.7%; 95% CI, 67.9%-75.3%) than for general pathologists (58.0%; 95% CI, 54.5%-61.4%) (P < .001). In subanalyses of biopsy specimens from an external validation set (n = 322), the Gleason grading performance of the DLS remained similar. For distinguishing nontumor from tumor-containing biopsy specimens (n = 752), the rate of agreement with subspecialists was 94.3% (95% CI, 92.4%-95.9%) for the DLS and similar at 94.7% (95% CI, 92.8%-96.3%) for general pathologists (P = .58). Conclusions and Relevance: In this study, the DLS showed higher proficiency than general pathologists at Gleason grading prostate needle core biopsy specimens and generalized to an independent institution. Future research is necessary to evaluate the potential utility of using the DLS as a decision support tool in clinical workflows and to improve the quality of prostate cancer grading for therapy decisions.

Deep learning-based survival prediction for multiple cancer types using histopathology images.

Providing prognostic information at the time of cancer diagnosis has important implications for treatment and monitoring. Although cancer staging, histopathological assessment, molecular features, and clinical variables can provide useful prognostic insights, improving risk stratification remains an active research area. We developed a deep learning system (DLS) to predict disease specific survival across 10 cancer types from The Cancer Genome Atlas (TCGA). We used a weakly-supervised approach without pixel-level annotations, and tested three different survival loss functions. The DLS was developed using 9,086 slides from 3,664 cases and evaluated using 3,009 slides from 1,216 cases. In multivariable Cox regression analysis of the combined cohort including all 10 cancers, the DLS was significantly associated with disease specific survival (hazard ratio of 1.58, 95% CI 1.28-1.70, p<0.0001) after adjusting for cancer type, stage, age, and sex. In a per-cancer adjusted subanalysis, the DLS remained a significant predictor of survival in 5 of 10 cancer types. Compared to a baseline model including stage, age, and sex, the c-index of the model demonstrated an absolute 3.7% improvement (95% CI 1.0-6.5) in the combined cohort. Additionally, our models stratified patients within individual cancer stages, particularly stage II (p = 0.025) and stage III (p<0.001). By developing and evaluating prognostic models across multiple cancer types, this work represents one of the most comprehensive studies exploring the direct prediction of clinical outcomes using deep learning and histopathology images. Our analysis demonstrates the potential for this approach to provide significant prognostic information in multiple cancer types, and even within specific pathologic stages. However, given the relatively small number of cases and observed clinical events for a deep learning task of this type, we observed wide confidence intervals for model performance, thus highlighting that future work will benefit from larger datasets assembled for the purposes for survival modeling.

Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network.

The electrocardiogram (ECG) is a widely used medical test, consisting of voltage versus time traces collected from surface recordings over the heart1. Here we hypothesized that a deep neural network (DNN) can predict an important future clinical event, 1-year all-cause mortality, from ECG voltage-time traces. By using ECGs collected over a 34-year period in a large regional health system, we trained a DNN with 1,169,662 12-lead resting ECGs obtained from 253,397 patients, in which 99,371 events occurred. The model achieved an area under the curve (AUC) of 0.88 on a held-out test set of 168,914 patients, in which 14,207 events occurred. Even within the large subset of patients (n = 45,285) with ECGs interpreted as 'normal' by a physician, the performance of the model in predicting 1-year mortality remained high (AUC = 0.85). A blinded survey of cardiologists demonstrated that many of the discriminating features of these normal ECGs were not apparent to expert reviewers. Finally, a Cox proportional-hazard model revealed a hazard ratio of 9.5 (P < 0.005) for the two predicted groups (dead versus alive 1 year after ECG) over a 25-year follow-up period. These results show that deep learning can add substantial prognostic information to the interpretation of 12-lead resting ECGs, even in cases that are interpreted as normal by physicians.

Erratum: Publisher Correction: Development and validation of a deep learning algorithm for improving Gleason scoring of prostate cancer.

[This corrects the article DOI: 10.1038/s41746-019-0112-2.].

An augmented reality microscope with real-time artificial intelligence integration for cancer diagnosis.

The microscopic assessment of tissue samples is instrumental for the diagnosis and staging of cancer, and thus guides therapy. However, these assessments demonstrate considerable variability and many regions of the world lack access to trained pathologists. Though artificial intelligence (AI) promises to improve the access and quality of healthcare, the costs of image digitization in pathology and difficulties in deploying AI solutions remain as barriers to real-world use. Here we propose a cost-effective solution: the augmented reality microscope (ARM). The ARM overlays AI-based information onto the current view of the sample in real time, enabling seamless integration of AI into routine workflows. We demonstrate the utility of ARM in the detection of metastatic breast cancer and the identification of prostate cancer, with latency compatible with real-time use. We anticipate that the ARM will remove barriers towards the use of AI designed to improve the accuracy and efficiency of cancer diagnosis.

Development and validation of a deep learning algorithm for improving Gleason scoring of prostate cancer.

For prostate cancer patients, the Gleason score is one of the most important prognostic factors, potentially determining treatment independent of the stage. However, Gleason scoring is based on subjective microscopic examination of tumor morphology and suffers from poor reproducibility. Here we present a deep learning system (DLS) for Gleason scoring whole-slide images of prostatectomies. Our system was developed using 112 million pathologist-annotated image patches from 1226 slides, and evaluated on an independent validation dataset of 331 slides. Compared to a reference standard provided by genitourinary pathology experts, the mean accuracy among 29 general pathologists was 0.61 on the validation set. The DLS achieved a significantly higher diagnostic accuracy of 0.70 (p = 0.002) and trended towards better patient risk stratification in correlations to clinical follow-up data. Our approach could improve the accuracy of Gleason scoring and subsequent therapy decisions, particularly where specialist expertise is unavailable. The DLS also goes beyond the current Gleason system to more finely characterize and quantitate tumor morphology, providing opportunities for refinement of the Gleason system itself.

Similar image search for histopathology: SMILY.

The increasing availability of large institutional and public histopathology image datasets is enabling the searching of these datasets for diagnosis, research, and education. Although these datasets typically have associated metadata such as diagnosis or clinical notes, even carefully curated datasets rarely contain annotations of the location of regions of interest on each image. As pathology images are extremely large (up to 100,000 pixels in each dimension), further laborious visual search of each image may be needed to find the feature of interest. In this paper, we introduce a deep-learning-based reverse image search tool for histopathology images: Similar Medical Images Like Yours (SMILY). We assessed SMILY's ability to retrieve search results in two ways: using pathologist-provided annotations, and via prospective studies where pathologists evaluated the quality of SMILY search results. As a negative control in the second evaluation, pathologists were blinded to whether search results were retrieved by SMILY or randomly. In both types of assessments, SMILY was able to retrieve search results with similar histologic features, organ site, and prostate cancer Gleason grade compared with the original query. SMILY may be a useful general-purpose tool in the pathologist's arsenal, to improve the efficiency of searching large archives of histopathology images, without the need to develop and implement specific tools for each application.