Digital pathology poses unique computational challenges, as a standard gigapixel slide may comprise tens of thousands of image tiles^1–3. Prior models have often resorted to subsampling a small portion of tiles for each slide, thus missing the important slide-level context⁴. Here we present Prov-GigaPath, a whole-slide pathology foundation model pretrained on 1.3 billion 256 × 256 pathology image tiles in 171,189 whole slides from Providence, a large US health network comprising 28 cancer centres. The slides originated from more than 30,000 patients covering 31 major tissue types. To pretrain Prov-GigaPath, we propose GigaPath, a novel vision transformer architecture for pretraining gigapixel pathology slides. To scale GigaPath for slide-level learning with tens of thousands of image tiles, GigaPath adapts the newly developed LongNet⁵ method to digital pathology. To evaluate Prov-GigaPath, we construct a digital pathology benchmark comprising 9 cancer subtyping tasks and 17 pathomics tasks, using both Providence and TCGA data⁶. With large-scale pretraining and ultra-large-context modelling, Prov-GigaPath attains state-of-the-art performance on 25 out of 26 tasks, with significant improvement over the second-best method on 18 tasks. We further demonstrate the potential of Prov-GigaPath on vision–language pretraining for pathology^7,8 by incorporating the pathology reports. In sum, Prov-GigaPath is an open-weight foundation model that achieves state-of-the-art performance on various digital pathology tasks, demonstrating the importance of real-world data and whole-slide modelling.

Prediction of clinical outcome in cancer is usually achieved by histopathological evaluation of tissue samples obtained during surgical resection of the primary tumor. Traditional tumor staging (AJCC/UICC-TNM classification) summarizes data on tumor burden (T), presence of cancer cells in draining and regional lymph nodes (N) and evidence for metastases (M). However, it is now recognized that clinical outcome can significantly vary among patients within the same stage. The current classification provides limited prognostic information, and does not predict response to therapy. Recent literature has alluded to the importance of the host immune system in controlling tumor progression. Thus, evidence supports the notion to include immunological biomarkers, implemented as a tool for the prediction of prognosis and response to therapy. Accumulating data, collected from large cohorts of human cancers, has demonstrated the impact of immune-classification, which has a prognostic value that may add to the significance of the AJCC/UICC TNM-classification. It is therefore imperative to begin to incorporate the ‘Immunoscore’ into traditional classification, thus providing an essential prognostic and potentially predictive tool. Introduction of this parameter as a biomarker to classify cancers, as part of routine diagnostic and prognostic assessment of tumors, will facilitate clinical decision-making including rational stratification of patient treatment. Equally, the inherent complexity of quantitative immunohistochemistry, in conjunction with protocol variation across laboratories, analysis of different immune cell types, inconsistent region selection criteria, and variable ways to quantify immune infiltration, all underline the urgent requirement to reach assay harmonization. In an effort to promote the Immunoscore in routine clinical settings, an international task force was initiated. This review represents a follow-up of the announcement of this initiative, and of the J Transl Med. editorial from January 2012. Immunophenotyping of tumors may provide crucial novel prognostic information. The results of this international validation may result in the implementation of the Immunoscore as a new component for the classification of cancer, designated TNM-I (TNM-Immune).

Evaluation of T lymphocyte frequency provides prognostic information for patients with oral squamous cell cancer (OSCC). However, the effect of simultaneously evaluating T cell frequency and assessing suppressive elements and defects in antigen-processing machinery (APM) has not been clarified. Simultaneous characterization of CD3 ⁺ , CD8 ⁺ , FoxP3 ⁺ , CD163 ⁺ , and PD-L1 ⁺ cells using multispectral imaging was performed on sections from 119 patients with HPV ^– OSCC. Expression of β ₂ -microglobulin, MHC class I heavy chain, and large multifunctional peptidase 10 was quantified, and all data were correlated with patient outcome. We found that, consistent with previous reports, high numbers of CD8 ⁺ T cells at the invasive margin correlated significantly with prolonged overall survival (OS), while the number of FoxP3 ⁺ or PD-L1 ⁺ cells did not. Compiling the number of FoxP3 ⁺ or PD-L1 ⁺ cells within 30 μm of CD8 ⁺ T cells identified a significant association with a high number of suppressive elements close to CD8 ⁺ T cells and reduced OS. Integrating this information into a cumulative suppression index (CSI) increased correlation with OS. Incorporating tumor expression levels of APM components with CSI further improved prognostic power. This multiparametric immune profiling may be useful for stratifying patients with OSCC for clinical trials.

The fifth “Melanoma Bridge Meeting” took place in Naples, December 1–5th, 2015. The main topics discussed at this meeting were: Molecular and Immuno advances, Immunotherapies and Combination Therapies, Tumor Microenvironment and Biomarkers and Immunoscore. The natural history of cancer involves interactions between the tumor and the immune system of the host. The immune infiltration at the tumor site may be indicative of host response. Significant correlations were shown between the levels of immune cell infiltration in tumors and patient’s clinical outcome. Moreover, incredible progress comes from the discovery of mutation-encoded tumor neoantigens. In fact, as tumors grow, they acquire mutations that are able to influence the response of patients to immune checkpoint inhibitors. It has been demonstrated that sensitivity to PD-1 and CTLA-4 blockade in patients with advanced NSCLC and melanoma was enhanced in tumors enriched for clonal neoantigens. The road ahead is still very long, but the knowledge of the mechanisms of immune escape, the study of tumor neo-antigens as well as of tumor microenvironment and the development of new immunotherapy strategies, will make cancer a more and more treatable disease.

Background Basal cell carcinoma (BCC) and cutaneous squamous cell carcinoma (CSCC) share exposure to UV light as the dominant risk factor, and these tumors therefore harbor high mutation burdens. In other malignancies, high mutation burden has been associated with clinical benefit from therapy with antibodies directed against the Programmed Death 1 (PD-1) immune checkpoint receptor. Highly mutated tumors are more likely to express immunogenic tumor neoantigens that attract effector T cells, which can be unleashed by blockade of the PD-1 immune checkpoint. Case presentations This report describes a patient with metastatic BCC and a patient with metastatic CSCC who were treated with REGN2810, a fully human anti-PD-1 monoclonal antibody, in an ongoing phase 1 trial (NCT02383212). The CSCC patient has experienced an ongoing complete response (16+ months), and the BCC patient has experienced an ongoing partial response (12+ months). Conclusions These case reports suggest that UV-associated skin cancers, beyond melanoma, are sensitive to PD-1 blockade. Trial registration Clinicaltrials.gov NCT02383212. Registered 2 February 2015.