Health equity assessment of machine learning performance (HEAL): a framework and dermatology AI model case study.

Background: Artificial intelligence (AI) has repeatedly been shown to encode historical inequities in healthcare. We aimed to develop a framework to quantitatively assess the performance equity of health AI technologies and to illustrate its utility via a case study. Methods: Here, we propose a methodology to assess whether health AI technologies prioritise performance for patient populations experiencing worse outcomes, that is complementary to existing fairness metrics. We developed the Health Equity Assessment of machine Learning performance (HEAL) framework designed to quantitatively assess the performance equity of health AI technologies via a four-step interdisciplinary process to understand and quantify domain-specific criteria, and the resulting HEAL metric. As an illustrative case study (analysis conducted between October 2022 and January 2023), we applied the HEAL framework to a dermatology AI model. A set of 5420 teledermatology cases (store-and-forward cases from patients of 20 years or older, submitted from primary care providers in the USA and skin cancer clinics in Australia), enriched for diversity in age, sex and race/ethnicity, was used to retrospectively evaluate the AI model's HEAL metric, defined as the likelihood that the AI model performs better for subpopulations with worse average health outcomes as compared to others. The likelihood that AI performance was anticorrelated to pre-existing health outcomes was estimated using bootstrap methods as the probability that the negated Spearman's rank correlation coefficient (i.e., "R") was greater than zero. Positive values of R suggest that subpopulations with poorer health outcomes have better AI model performance. Thus, the HEAL metric, defined as p (R >0), measures how likely the AI technology is to prioritise performance for subpopulations with worse average health outcomes as compared to others (presented as a percentage below). Health outcomes were quantified as disability-adjusted life years (DALYs) when grouping by sex and age, and years of life lost (YLLs) when grouping by race/ethnicity. AI performance was measured as top-3 agreement with the reference diagnosis from a panel of 3 dermatologists per case. Findings: Across all dermatologic conditions, the HEAL metric was 80.5% for prioritizing AI performance of racial/ethnic subpopulations based on YLLs, and 92.1% and 0.0% respectively for prioritizing AI performance of sex and age subpopulations based on DALYs. Certain dermatologic conditions were significantly associated with greater AI model performance compared to a reference category of less common conditions. For skin cancer conditions, the HEAL metric was 73.8% for prioritizing AI performance of age subpopulations based on DALYs. Interpretation: Analysis using the proposed HEAL framework showed that the dermatology AI model prioritised performance for race/ethnicity, sex (all conditions) and age (cancer conditions) subpopulations with respect to pre-existing health disparities. More work is needed to investigate ways of promoting equitable AI performance across age for non-cancer conditions and to better understand how AI models can contribute towards improving equity in health outcomes. Funding: Google LLC.

Predicting lymph node metastasis from primary tumor histology and clinicopathologic factors in colorectal cancer using deep learning.

BACKGROUND: Presence of lymph node metastasis (LNM) influences prognosis and clinical decision-making in colorectal cancer. However, detection of LNM is variable and depends on a number of external factors. Deep learning has shown success in computational pathology, but has struggled to boost performance when combined with known predictors. METHODS: Machine-learned features are created by clustering deep learning embeddings of small patches of tumor in colorectal cancer via k-means, and then selecting the top clusters that add predictive value to a logistic regression model when combined with known baseline clinicopathological variables. We then analyze performance of logistic regression models trained with and without these machine-learned features in combination with the baseline variables. RESULTS: The machine-learned extracted features provide independent signal for the presence of LNM (AUROC: 0.638, 95% CI: [0.590, 0.683]). Furthermore, the machine-learned features add predictive value to the set of 6 clinicopathologic variables in an external validation set (likelihood ratio test, p < 0.00032; AUROC: 0.740, 95% CI: [0.701, 0.780]). A model incorporating these features can also further risk-stratify patients with and without identified metastasis (p < 0.001 for both stage II and stage III). CONCLUSION: This work demonstrates an effective approach to combine deep learning with established clinicopathologic factors in order to identify independently informative features associated with LNM. Further work building on these specific results may have important impact in prognostication and therapeutic decision making for LNM. Additionally, this general computational approach may prove useful in other contexts.

When colorectal cancers spread to the lymph nodes, it can indicate a poorer prognosis. However, detecting lymph node metastasis (spread) can be difficult and depends on a number of factors such as how samples are taken and processed. Here, we show that machine learning, which involves computer software learning from patterns in data, can predict lymph node metastasis in patients with colorectal cancer from the microscopic appearance of their primary tumor and the clinical characteristics of the patients. We also show that the same approach can predict patient survival. With further work, our approach may help clinicians to inform patients about their prognosis and decide on appropriate treatments.

Deep learning models for histologic grading of breast cancer and association with disease prognosis.

Histologic grading of breast cancer involves review and scoring of three well-established morphologic features: mitotic count, nuclear pleomorphism, and tubule formation. Taken together, these features form the basis of the Nottingham Grading System which is used to inform breast cancer characterization and prognosis. In this study, we develop deep learning models to perform histologic scoring of all three components using digitized hematoxylin and eosin-stained slides containing invasive breast carcinoma. We first evaluate model performance using pathologist-based reference standards for each component. To complement this typical approach to evaluation, we further evaluate the deep learning models via prognostic analyses. The individual component models perform at or above published benchmarks for algorithm-based grading approaches, achieving high concordance rates with pathologist grading. Further, prognostic performance using deep learning-based grading is on par with that of pathologists performing review of matched slides. By providing scores for each component feature, the deep-learning based approach also provides the potential to identify the grading components contributing most to prognostic value. This may enable optimized prognostic models, opportunities to improve access to consistent grading, and approaches to better understand the links between histologic features and clinical outcomes in breast cancer.

Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge.

Artificial intelligence (AI) has shown promise for diagnosing prostate cancer in biopsies. However, results have been limited to individual studies, lacking validation in multinational settings. Competitions have been shown to be accelerators for medical imaging innovations, but their impact is hindered by lack of reproducibility and independent validation. With this in mind, we organized the PANDA challenge-the largest histopathology competition to date, joined by 1,290 developers-to catalyze development of reproducible AI algorithms for Gleason grading using 10,616 digitized prostate biopsies. We validated that a diverse set of submitted algorithms reached pathologist-level performance on independent cross-continental cohorts, fully blinded to the algorithm developers. On United States and European external validation sets, the algorithms achieved agreements of 0.862 (quadratically weighted κ, 95% confidence interval (CI), 0.840-0.884) and 0.868 (95% CI, 0.835-0.900) with expert uropathologists. Successful generalization across different patient populations, laboratories and reference standards, achieved by a variety of algorithmic approaches, warrants evaluating AI-based Gleason grading in prospective clinical trials.

Comparative analysis of machine learning approaches to classify tumor mutation burden in lung adenocarcinoma using histopathology images.

Both histologic subtypes and tumor mutation burden (TMB) represent important biomarkers in lung cancer, with implications for patient prognosis and treatment decisions. Typically, TMB is evaluated by comprehensive genomic profiling but this requires use of finite tissue specimens and costly, time-consuming laboratory processes. Histologic subtype classification represents an established component of lung adenocarcinoma histopathology, but can be challenging and is associated with substantial inter-pathologist variability. Here we developed a deep learning system to both classify histologic patterns in lung adenocarcinoma and predict TMB status using de-identified Hematoxylin and Eosin (H&E) stained whole slide images. We first trained a convolutional neural network to map histologic features across whole slide images of lung cancer resection specimens. On evaluation using an external data source, this model achieved patch-level area under the receiver operating characteristic curve (AUC) of 0.78-0.98 across nine histologic features. We then integrated the output of this model with clinico-demographic data to develop an interpretable model for TMB classification. The resulting end-to-end system was evaluated on 172 held out cases from TCGA, achieving an AUC of 0.71 (95% CI 0.63-0.80). The benefit of using histologic features in predicting TMB is highlighted by the significant improvement this approach offers over using the clinical features alone (AUC of 0.63 [95% CI 0.53-0.72], p = 0.002). Furthermore, we found that our histologic subtype-based approach achieved performance similar to that of a weakly supervised approach (AUC of 0.72 [95% CI 0.64-0.80]). Together these results underscore that incorporating histologic patterns in biomarker prediction for lung cancer provides informative signals, and that interpretable approaches utilizing these patterns perform comparably with less interpretable, weakly supervised approaches.

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.

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.

Determining breast cancer biomarker status and associated morphological features using deep learning.

Background: Breast cancer management depends on biomarkers including estrogen receptor, progesterone receptor, and human epidermal growth factor receptor 2 (ER/PR/HER2). Though existing scoring systems are widely used and well-validated, they can involve costly preparation and variable interpretation. Additionally, discordances between histology and expected biomarker findings can prompt repeat testing to address biological, interpretative, or technical reasons for unexpected results. Methods: We developed three independent deep learning systems (DLS) to directly predict ER/PR/HER2 status for both focal tissue regions (patches) and slides using hematoxylin-and-eosin-stained (H&E) images as input. Models were trained and evaluated using pathologist annotated slides from three data sources. Areas under the receiver operator characteristic curve (AUCs) were calculated for test sets at both a patch-level (>135 million patches, 181 slides) and slide-level (n = 3274 slides, 1249 cases, 37 sites). Interpretability analyses were performed using Testing with Concept Activation Vectors (TCAV), saliency analysis, and pathologist review of clustered patches. Results: The patch-level AUCs are 0.939 (95%CI 0.936-0.941), 0.938 (0.936-0.940), and 0.808 (0.802-0.813) for ER/PR/HER2, respectively. At the slide level, AUCs are 0.86 (95%CI 0.84-0.87), 0.75 (0.73-0.77), and 0.60 (0.56-0.64) for ER/PR/HER2, respectively. Interpretability analyses show known biomarker-histomorphology associations including associations of low-grade and lobular histology with ER/PR positivity, and increased inflammatory infiltrates with triple-negative staining. Conclusions: This study presents rapid breast cancer biomarker estimation from routine H&E slides and builds on prior advances by prioritizing interpretability of computationally learned features in the context of existing pathological knowledge.

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.

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.].

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.

Registered report: the androgen receptor induces a distinct transcriptional program in castration-resistant prostate cancer in man.

The Prostate Cancer Foundation-Movember Foundation Reproducibility Initiative (PCFMFRI) seeks to address growing concerns about reproducibility in scientific research by conducting replications of recent papers in the field of prostate cancer. This Registered Report describes the proposed replication plan of key experiments from "The Androgen Receptor Induces a Distinct Transcriptional Program in Castration-Resistant Prostate Cancer in Man" by Sharma and colleagues (2013), published in Cancer Cell in 2013. Of thousands of targets for the androgen receptor (AR), the authors elucidated a subset of 16 core genes that were consistently downregulated with castration and re-emerged with castration resistance. These 16 AR binding sites were distinct from those observed in cells in culture. The authors suggested that cellular context can have dramatic effects on downstream transcriptional regulation of AR binding sites. The present study will attempt to replicate Fig. 7C by comparing gene expression of the 16 core genes identified by Sharma and colleagues in xenograft tumor tissue compared to androgen treated LNCaP cells in vitro. The Prostate Cancer Foundation-Movember Foundation Reproducibility Initiative is a collaboration between the Prostate Cancer Foundation, the Movember Initiative, and Science Exchange, and the results of the replications will be published by PeerJ.

Registered report: androgen receptor splice variants determine taxane sensitivity in prostate cancer.

The Prostate Cancer Foundation-Movember Foundation Reproducibility Initiative seeks to address growing concerns about reproducibility in scientific research by conducting replications of recent papers in the field of prostate cancer. This Registered Report describes the proposed replication plan of key experiments from "Androgen Receptor Splice Variants Determine Taxane Sensitivity in Prostate Cancer" by Thadani-Mulero and colleagues (2014) published in Cancer Research in 2014. The experiment that will be replicated is reported in Fig. 6A. Thadani-Mulero and colleagues generated xenografts from two prostate cancer cell lines; LuCaP 86.2, which expresses predominantly the ARv567 splice variant of the androgen receptor (AR), and LuCaP 23.1, which expresses the full length AR as well as the ARv7 variant. Treatment of the tumors with the taxane docetaxel showed that the drug inhibited tumor growth of the LuCaP 86.2 cells but not of the LuCaP 23.1 cells, indicating that expression of splice variants of the AR can affect sensitivity to docetaxel. The Prostate Cancer Foundation-Movember Foundation Reproducibility Initiative is a collaboration between the Prostate Cancer Foundation, the Movember Foundation and Science Exchange, and the results of the replications will be published by PeerJ.

An open investigation of the reproducibility of cancer biology research.

It is widely believed that research that builds upon previously published findings has reproduced the original work. However, it is rare for researchers to perform or publish direct replications of existing results. The Reproducibility Project: Cancer Biology is an open investigation of reproducibility in preclinical cancer biology research. We have identified 50 high impact cancer biology articles published in the period 2010-2012, and plan to replicate a subset of experimental results from each article. A Registered Report detailing the proposed experimental designs and protocols for each subset of experiments will be peer reviewed and published prior to data collection. The results of these experiments will then be published in a Replication Study. The resulting open methodology and dataset will provide evidence about the reproducibility of high-impact results, and an opportunity to identify predictors of reproducibility.

Myb promotes centriole amplification and later steps of the multiciliogenesis program.

The transcriptional control of primary cilium formation and ciliary motility are beginning to be understood, but little is known about the transcriptional programs that control cilium number and other structural and functional specializations. One of the most intriguing ciliary specializations occurs in multiciliated cells (MCCs), which amplify their centrioles to nucleate hundreds of cilia per cell, instead of the usual monocilium. Here we report that the transcription factor MYB, which promotes S phase and drives cycling of a variety of progenitor cells, is expressed in postmitotic epithelial cells of the mouse airways and ependyma destined to become MCCs. MYB is expressed early in multiciliogenesis, as progenitors exit the cell cycle and amplify their centrioles, then switches off as MCCs mature. Conditional inactivation of Myb in the developing airways blocks or delays centriole amplification and expression of FOXJ1, a transcription factor that controls centriole docking and ciliary motility, and airways fail to become fully ciliated. We provide evidence that MYB acts in a conserved pathway downstream of Notch signaling and multicilin, a protein related to the S-phase regulator geminin, and upstream of FOXJ1. MYB can activate endogenous Foxj1 expression and stimulate a cotransfected Foxj1 reporter in heterologous cells, and it can drive the complete multiciliogenesis program in Xenopus embryonic epidermis. We conclude that MYB has an early, crucial and conserved role in multiciliogenesis, and propose that it promotes a novel S-like phase in which centriole amplification occurs uncoupled from DNA synthesis, and then drives later steps of multiciliogenesis through induction of Foxj1.

How the turtle forms its shell: a paracrine hypothesis of carapace formation.

We propose a two-step model for the evolutionary origin of the turtle shell. We show here that the carapacial ridge (CR) is critical for the entry of the ribs into the dorsal dermis. Moreover, we demonstrate that the maintenance of the CR and its ability to attract the migrating rib precursor cells depend upon fibroblast growth factor (FGF) signaling. Inhibitors of FGF allow the CR to degenerate, with the consequent migration of ribs along the ventral body wall. Beads containing FGF10 can rearrange rib migration in the chick, suggesting that the CR FGF10 plays an important role in attracting the rib rudiments. The co-ordinated growth of the carapacial plate and the ribs may be a positive feedback loop (similar to that of the limbs) caused by the induction of Fgf8 in the distal tips of the ribs by the FGF10-secreting mesenchyme of the CR. Once in the dermis, the ribs undergo endochrondral ossification. We provide evidence that the ribs act as signaling centers for the dermal ossification and that this ossification is due to bone morphogenetic proteins secreted by the rib. Thus, once the ribs are within the dermis, the ossification of the dermis is not difficult to achieve. This relatively rapid means of carapace formation would allow for the appearance of turtles in the fossil record without obvious intermediates.