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.

Supplemental Digital Content is available in the text.

These authors contributed equally to this work.The brightfield microscope is instrumental in the visual examination of both biological and physical samples at sub-millimeter scales. One key clinical application has been in cancer histopathology, where the microscopic assessment of the tissue samples is used for the diagnosis and staging of cancer and thus guides clinical therapy 1 . However, the interpretation of these samples is inherently subjective, resulting in significant diagnostic variability 2,3 . Moreover, in many regions of the world, access to pathologists is severely limited due to lack of trained personnel 4 . In this regard, Artificial Intelligence (AI) based tools promise to improve the access and quality of healthcare 5-7 . However, despite significant advances in AI research, integration of these tools into real-world cancer diagnosis workflows remains challenging because of the costs of image digitization and difficulties in deploying AI solutions 8 , 9 . Here we propose a cost-effective solution to the integration of AI: the Augmented Reality Microscope (ARM). The ARM overlays AI-based information onto the current view of the sample through the optical pathway in real-time, enabling seamless integration of AI into the regular microscopy workflow. We demonstrate the utility of ARM in the detection of lymph node metastases in breast cancer and the identification of prostate cancer with a latency that supports real-time workflows. We anticipate that ARM will remove barriers towards the use of AI in microscopic analysis and thus improve the accuracy and efficiency of cancer diagnosis. This approach is applicable to other microscopy tasks and AI algorithms in the life sciences 10 and beyond 11,12 .Microscopic examination of samples is the gold standard for the diagnosis of cancer, autoimmune diseases, infectious diseases, and more. In cancer, the microscopic examination of stained tissue sections is critical for diagnosing and staging the patient's tumor, which informs treatment decisions and prognosis. In cancer, microscopy analysis faces three major challenges. As a form of image interpretation, these examinations are inherently subjective, exhibiting considerable inter-observer and intra-observer variability 2,3 . Moreover, clinical guidelines 1 and studies 13 have begun to require quantitative assessments as part of the effort towards better patient risk stratification 1 . For example, breast cancer staging requires counting mitotic cells and quantification of the tumor burden in lymph nodes by measuring the largest tumor focus. However, despite being helpful in treatment planning, quantification is laborious and error-prone. Lastly, access to disease experts can be limited in both developed and developing countries 4 , exacerbating the problem.

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.

This article examines whether the player draft used since 1986 in the Australian Football League has caused clubs to tank; that is, to seek to lose matches to obtain improved draft choices. A comparison of clubs’ performances in regular season matches played before and after introduction of the draft provides no evidence that clubs have engaged in tanking. The main potential explanations for the absence of tanking in the Australian Football League are the relatively low benefits to clubs from tanking and limited opportunities for them to engage in this behavior.