Find the Flame: Predictive Biomarkers for Immunotherapy in Melanoma

Reproducible Reporting of the Collection and Evaluation of Annotations for Artificial Intelligence Models

This work puts forth and demonstrates the utility of a reporting framework for collecting and evaluating annotations of medical images used for training and testing artificial intelligence (AI) models in assisting detection and diagnosis. AI has unique reporting requirements, as shown by the AI extensions to the Consolidated Standards of Reporting Trials (CONSORT) and Standard Protocol Items: Recommendations for Interventional Trials (SPIRIT) checklists and the proposed AI extensions to the Standards for Reporting Diagnostic Accuracy (STARD) and Transparent Reporting of a Multivariable Prediction model for Individual Prognosis or Diagnosis (TRIPOD) checklists. AI for detection and/or diagnostic image analysis requires complete, reproducible, and transparent reporting of the annotations and metadata used in training and testing data sets. In an earlier work by other researchers, an annotation workflow and quality checklist for computational pathology annotations were proposed. In this manuscript, we operationalize this workflow into an evaluable quality checklist that applies to any reader-interpreted medical images, and we demonstrate its use for an annotation effort in digital pathology. We refer to this quality framework as the Collection and Evaluation of Annotations for Reproducible Reporting of Artificial Intelligence (CLEARR-AI).

Peripheral B-cell levels predict efficacy and overall survival in advanced melanoma patients under PD-1 immunotherapy

Aims: Programmed death-1 (PD-1) blockade is a vital therapy for solid tumors, but not all patients benefit. Identifying which patients will benefit from immunotherapy is a key focus in oncology research. Patients & Methods: This study analyzed the correlation between the number of peripheral lymphocytes and the efficacy and prognosis of immunotherapy in advanced malignant melanoma. Results: Patients with a partial response had significantly lower peripheral B cell levels, and patients with a lower number of B lymphocytes had a longer survival time. Conclusion: These results suggest that peripheral B cells are correlated with the efficacy of PD-1 antibody and prognosis and are thus potential biomarkers for the efficacy and prognosis of PD-1 antibody immunotherapy in malignant melanoma.

Can we yet use tertiary lymphoid structures as predictive biomarkers for immunotherapy response in melanoma?

PURPOSE OF REVIEW

In this review, we explore the potential of tertiary lymphoid structures (TLS) as predictive biomarkers in the response to immunotherapy for melanoma patients.

RECENT FINDINGS

The significance of TLS as indicators predicting immunotherapy response becomes particularly pronounced. Melanoma, renowned for its aggressive characteristics, has undergone revolutionary transformations in treatment through immunotherapeutic interventions. Investigations have unveiled a compelling correlation between the presence of TLS in the melanoma tumor microenvironment and favorable responses to immunotherapy. These responses, characterized by heightened survival rates and improved clinical outcomes, imply that TLS might be pivotal in tailoring more efficient and personalized treatments for individuals with melanoma. The ongoing discourse regarding TLS as a predictive biomarker underscores the need for a meticulous examination of its potential in guiding clinical decisions and optimizing therapeutic strategies.

SUMMARY

TLS show great promises as potential biomarkers to melanoma patient's outcomes in ICI treatment; however, more studies are needed to understand their mechanisms of actions and the long-term impact of their functionality.

A Narrative Review of Current Knowledge on Cutaneous Melanoma

Cutaneous melanoma is a public health problem. Efforts to reduce its incidence have failed, as it continues to increase. In recent years, many risk factors have been identified. Numerous diagnostic systems exist that greatly assist in early clinical diagnosis. The histopathological aspect illustrates the grim nature of these cancers. Currently, pathogenic pathways and the tumor microclimate are key to the development of therapeutic methods. Revolutionary therapies like targeted therapy and immune checkpoint inhibitors are starting to replace traditional therapeutic methods. Targeted therapy aims at a specific molecule in the pathogenic chain to block it, stopping cell growth and dissemination. The main function of immune checkpoint inhibitors is to boost cellular immunity in order to combat cancer cells. Unfortunately, these therapies have different rates of effectiveness and side effects, and cannot be applied to all patients. These shortcomings are the basis of increased incidence and mortality rates. This study covers all stages of the evolutionary sequence of melanoma. With all these data in front of us, we see the need for new research efforts directed at therapies that will bring greater benefits in terms of patient survival and prognosis, with fewer adverse effects.

A Dramatic Response to Second-Line Nivolumab and Ipilimumab in BRAF-V600-Mutated Metastatic Melanoma

Introduction

Current treatment options for BRAF V600-mutated unresectable stage III/IV melanoma include anti-PD-1 monotherapy or combination with anti-CTLA-4 or anti-LAG-3 agents, BRAF/MEK inhibitors, and clinical trials. The strategy of combination immunotherapy with nivolumab and ipilimumab has shown promising results, achieving higher response rates, longer duration of response, improved progression-free survival, and enhanced overall survival. The optimal sequence of treatments remains a topic of interest, with preliminary data suggesting a greater effectiveness of immunotherapy as the first-line approach. Preclinical trials have indicated that the efficacy of this sequence may be due to the modification of the immune environment by BRAF kinase inhibitors, leading to immune escape by tumor cells and resistance to immune checkpoint inhibitors.

Case Presentation

We present a case of a 72-year-old woman with high-burden metastatic melanoma who failed to respond to prior targeted therapy with BRAF/MEK inhibitors and exhibited a successful response to the second-line treatment with ipilimumab and nivolumab. We discuss the potential reasons for this positive outcome contributing to the current debate concerning treatment sequences, resistance mechanisms, and biomarkers predictive of response to immune checkpoint inhibitors in metastatic melanoma.

Conclusion

We believe that in few years the therapeutic algorithms in BRAF V600-mutated unresectable stage III/IV melanoma will be more complex since they will define clearly the correct therapeutic sequences with the inclusion of new immune checkpoint inhibitor drugs and multiple predictive biomarkers of response to better select patients eligible to immunotherapy.

Classification of the tumor immune microenvironment and associations with outcomes in patients with metastatic melanoma treated with immunotherapies

BACKGROUND

Tumor microenvironment (TME) characteristics are potential biomarkers of response to immune checkpoint inhibitors in metastatic melanoma. This study developed a method to perform unsupervised classification of TME of metastatic melanoma.

METHODS

We used multiplex immunohistochemical and quantitative pathology-derived assessment of immune cell compositions of intratumoral and peritumoral regions of metastatic melanoma baseline biopsies to classify TME in relation to response to anti-programmed cell death protein 1 (PD-1) monotherapy or in combination with anti-cytotoxic T-cell lymphocyte-4 (ipilimumab (IPI)+PD-1).

RESULTS

Spatial profiling of CD8+T cells, macrophages, and melanoma cells, as well as phenotypic PD-1 receptor ligand (PD-L1) and CD16 proportions, were used to identify and classify patients into one of three mutually exclusive TME classes: immune-scarce, immune-intermediate, and immune-rich tumors. Patients with immune-rich tumors were characterized by a lower proportion of melanoma cells and higher proportions of immune cells, including higher PD-L1 expression. These patients had higher response rates and longer progression-free survival (PFS) than those with immune-intermediate and immune-scarce tumors. At a median follow-up of 18 months (95% CI: 6.7 to 49 months), the 1-year PFS was 76% (95% CI: 64% to 90%) for patients with an immune-rich tumor, 56% (95% CI: 44% to 72%) for those with an immune-intermediate tumor, and 33% (95% CI: 23% to 47%) for patients with an immune-scarce tumor. A higher response rate was observed in patients with an immune-scarce or immune-intermediate tumor when treated with IPI+PD-1 compared with those treated with PD-1 alone.

CONCLUSIONS

Our study provides an automatic TME classification method that may predict the clinical efficacy of immunotherapy for patients with metastatic melanoma.

Deep learning in computational dermatopathology of melanoma: A technical systematic literature review

Deep learning (DL) has become one of the major approaches in computational dermatopathology, evidenced by a significant increase in this topic in the current literature. We aim to provide a structured and comprehensive overview of peer-reviewed publications on DL applied to dermatopathology focused on melanoma. In comparison to well-published DL methods on non-medical images (e.g., classification on ImageNet), this field of application comprises a specific set of challenges, such as staining artifacts, large gigapixel images, and various magnification levels. Thus, we are particularly interested in the pathology-specific technical state-of-the-art. We also aim to summarize the best performances achieved thus far with respect to accuracy, along with an overview of self-reported limitations. Accordingly, we conducted a systematic literature review of peer-reviewed journal and conference articles published between 2012 and 2022 in the databases ACM Digital Library, Embase, IEEE Xplore, PubMed, and Scopus, expanded by forward and backward searches to identify 495 potentially eligible studies. After screening for relevance and quality, a total of 54 studies were included. We qualitatively summarized and analyzed these studies from technical, problem-oriented, and task-oriented perspectives. Our findings suggest that the technical aspects of DL for histopathology in melanoma can be further improved. The DL methodology was adopted later in this field, and still lacks the wider adoption of DL methods already shown to be effective for other applications. We also discuss upcoming trends toward ImageNet-based feature extraction and larger models. While DL has achieved human-competitive accuracy in routine pathological tasks, its performance on advanced tasks is still inferior to wet-lab testing (for example). Finally, we discuss the challenges impeding the translation of DL methods to clinical practice and provide insight into future research directions.

Melanoma patients with immune-related adverse events after immune checkpoint inhibitors are characterized by a distinct immunological phenotype of circulating T cells and M-MDSCs

Treatment with immune checkpoint inhibitors (ICIs) has improved the prognosis of melanoma patients. However, ICIs can cause an overactivation of the immune system followed by diverse immunological side effects known as immune-related adverse events (irAE). Currently, the toxicity of irAE is limiting the usage of ICIs. Here, we studied circulating monocytic myeloid-derived suppressor cells (M-MDSCs) and T cells in course of irAE after the ICI therapy. Our longitudinal study involved 31 melanoma patients with and without adverse events during anti-PD-1 monotherapy or anti-CTLA-4/PD-1 combination therapy. Peripheral blood samples were analyzed before ICI start, during ICI treatment, at the time point of irAE and during immunosuppressive treatment to cure irAE. We observed an enhanced progression-free survival among patients with irAE. In patients with irAE, we found an upregulation of CD69 on CD8+ T cells and a decreased frequency of regulatory T cells (Tregs). Moreover, lower frequencies of Tregs correlated with more severe side effects. Patients treated with immunomodulatory drugs after irAE manifestation tend to show an elevated number of M-MDSCs during an immunosuppressive therapy. We suggest that an activation of CD8+ T cells and the reduction of Treg frequencies could be responsible for the development of irAE.

Plasma glycoproteomic biomarkers identify metastatic melanoma patients with reduced clinical benefit from immune checkpoint inhibitor therapy

The clinical success of immune-checkpoint inhibitors (ICI) in both resected and metastatic melanoma has confirmed the validity of therapeutic strategies that boost the immune system to counteract cancer. However, half of patients with metastatic disease treated with even the most aggressive regimen do not derive durable clinical benefit. Thus, there is a critical need for predictive biomarkers that can identify individuals who are unlikely to benefit with high accuracy so that these patients may be spared the toxicity of treatment without the likely benefit of response. Ideally, such an assay would have a fast turnaround time and minimal invasiveness. Here, we utilize a novel platform that combines mass spectrometry with an artificial intelligence-based data processing engine to interrogate the blood glycoproteome in melanoma patients before receiving ICI therapy. We identify 143 biomarkers that demonstrate a difference in expression between the patients who died within six months of starting ICI treatment and those who remained progression-free for three years. We then develop a glycoproteomic classifier that predicts benefit of immunotherapy (HR=2.7; p=0.026) and achieves a significant separation of patients in an independent cohort (HR=5.6; p=0.027). To understand how circulating glycoproteins may affect efficacy of treatment, we analyze the differences in glycosylation structure and discover a fucosylation signature in patients with shorter overall survival (OS). We then develop a fucosylation-based model that effectively stratifies patients (HR=3.5; p=0.0066). Together, our data demonstrate the utility of plasma glycoproteomics for biomarker discovery and prediction of ICI benefit in patients with metastatic melanoma and suggest that protein fucosylation may be a determinant of anti-tumor immunity.

Machine Learning Improves the Prediction of Responses to Immune Checkpoint Inhibitors in Metastatic Melanoma

Pretreatment LDH is a standard prognostic biomarker for advanced melanoma and is associated with response to ICI. We assessed the role of machine learning-based radiomics in predicting responses to ICI and in complementing LDH for prognostication of metastatic melanoma. From 2008-2022, 79 patients with 168 metastatic hepatic lesions were identified. All patients had arterial phase CT images 1-month prior to initiation of ICI. Response to ICI was assessed on follow-up CT at 3 months using RECIST criteria. A machine learning algorithm was developed using radiomics. Maximum relevance minimum redundancy (mRMR) was used to select features. ROC analysis and logistic regression analyses evaluated performance. Shapley additive explanations were used to identify the variables that are the most important in predicting a response. mRMR selection revealed 15 features that are associated with a response to ICI. The machine learning model combining both radiomics features and pretreatment LDH resulted in better performance for response prediction compared to models that included radiomics or LDH alone (AUC of 0.89 (95% CI: [0.76-0.99]) vs. 0.81 (95% CI: [0.65-0.94]) and 0.81 (95% CI: [0.72-0.91]), respectively). Using SHAP analysis, LDH and two GLSZM were the most predictive of the outcome. Pre-treatment CT radiomic features performed equally well to serum LDH in predicting treatment response.

Gut Microbiota and Therapy in Metastatic Melanoma: Focus on MAPK Pathway Inhibition

Gut microbiome (GM) and its either pro-tumorigenic or anti-tumorigenic role is intriguing and constitutes an evolving landscape in translational oncology. It has been suggested that these microorganisms may be involved in carcinogenesis, cancer treatment response and resistance, as well as predisposition to adverse effects. In melanoma patients, one of the most immunogenic cancers, immune checkpoint inhibitors (ICI) and MAPK-targeted therapy—BRAF/MEK inhibitors—have revolutionized prognosis, and the study of the microbiome as a modulating factor is thus appealing. Although BRAF/MEK inhibitors constitute one of the main backbones of treatment in melanoma, little is known about their impact on GM and how this might correlate with immune re-induction. On the contrary, ICI and their relationship to GM has become an interesting field of research due to the already-known impact of immunotherapy in modulating the immune system. Immune reprogramming in the tumor microenvironment has been established as one of the main targets of microbiome, since it can induce immunosuppressive phenotypes, promote inflammatory responses or conduct anti-tumor responses. As a result, ongoing clinical trials are evaluating the role of fecal microbiota transplant (FMT), as well as the impact of using dietary supplements, antibiotics and probiotics in the prediction of response to therapy. In this review, we provide an overview of GM’s link to cancer, its relationship with the immune system and how this may impact response to treatments in melanoma patients. We also discuss insights about novel therapeutic approaches including FMT, changes in diet and use of probiotics, prebiotics and symbiotics. Finally, we hypothesize on the possible pathways through which GM may impact anti-tumor efficacy in melanoma patients treated with targeted therapy, an appealing subject of which little is known.

Disease Recurrence during Adjuvant Immune Checkpoint Inhibitor Treatment in Metastatic Melanoma: Clinical, Laboratory, and Radiological Characteristics in Patients from a Single Tertiary Referral Center

Despite the dramatic improvements in recurrence-free survival in patients with metastatic melanoma treated with immune checkpoint inhibitors (ICI), a number of patients develop metastases during adjuvant therapy. It is not currently possible to predict which patients are most likely to develop disease recurrence due to a lack of reliable biomarkers. Thus, we retrospectively analyzed the case records of all patients who commenced adjuvant ICI therapy between January 2018 and December 2021 in a single university skin cancer center (n = 46) (i) to determine the rates of disease recurrence, (ii) to examine the utility of established markers, and (iii) to examine whether re-challenge with immunotherapy resulted in clinical response. Twelve out of forty-six (26%) patients developed a relapse on adjuvant immunotherapy in our cohort, and the median time to relapse was 139 days. Adjuvant immunotherapy was continued in three patients. Of the twelve patients who developed recurrence during adjuvant immunotherapy, seven had further disease recurrence within the observation period, with a median time of 112 days after the first progress. There was no significant difference comparing early recurrence (<180 days after initiation) on adjuvant immunotherapy to late recurrence (>180 days after initiation) on adjuvant immunotherapy. Classical tumor markers, including serum lactate dehydrogenase (LDH) and S-100, were unreliable for the detection of disease recurrence. Baseline lymphocyte and eosinophil counts and those during immunotherapy were not associated with disease recurrence. Interestingly, patients with NRAS mutations were disproportionately represented (60%) in the patients who developed disease recurrence, suggesting that these patients should be closely monitored during adjuvant therapy.

Pilot study to evaluate tools to collect pathologist annotations for validating machine learning algorithms

Purpose: Validation of artificial intelligence (AI) algorithms in digital pathology with a reference standard is necessary before widespread clinical use, but few examples focus on creating a reference standard based on pathologist annotations. This work assesses the results of a pilot study that collects density estimates of stromal tumor-infiltrating lymphocytes (sTILs) in breast cancer biopsy specimens. This work will inform the creation of a validation dataset for the evaluation of AI algorithms fit for a regulatory purpose. Approach: Collaborators and crowdsourced pathologists contributed glass slides, digital images, and annotations. Here, "annotations" refer to any marks, segmentations, measurements, or labels a pathologist adds to a report, image, region of interest (ROI), or biological feature. Pathologists estimated sTILs density in 640 ROIs from hematoxylin and eosin stained slides of 64 patients via two modalities: an optical light microscope and two digital image viewing platforms. Results: The pilot study generated 7373 sTILs density estimates from 29 pathologists. Analysis of annotations found the variability of density estimates per ROI increases with the mean; the root mean square differences were 4.46, 14.25, and 26.25 as the mean density ranged from 0% to 10%, 11% to 40%, and 41% to 100%, respectively. The pilot study informs three areas of improvement for future work: technical workflows, annotation platforms, and agreement analysis methods. Upgrades to the workflows and platforms will improve operability and increase annotation speed and consistency. Conclusions: Exploratory data analysis demonstrates the need to develop new statistical approaches for agreement. The pilot study dataset and analysis methods are publicly available to allow community feedback. The development and results of the validation dataset will be publicly available to serve as an instructive tool that can be replicated by developers and researchers.

Harmonization of PD-L1 immunohistochemistry and mRNA expression scoring in metastatic melanoma: a multicenter analysis

AIMS

This multicenter study sought to harmonize programmed death ligand 1 (PD-L1) immunohistochemistry (IHC) data and melanoma scoring. To provide a reference for PD-L1 expression independent of the IHC protocol, PD-L1 mRNA expression was determined then compared to IHC.

METHODS

Standardized PD-L1 assays (22C3, 28-8, SP142, and SP263) and laboratory-developed tests (QR1 and 22C3) were evaluated on three IHC platforms using a training set of 7 cases. mRNA expression was determined via RNAscope (CD274/PD-L1 probe) and analyzed by image analysis. PD-L1 IHC findings were scored by seven blinded pathologists using the tumor proportion score (TPS), combined positive score (CPS), and MELscore. This method was validated by three blinded pathologists on 40 metastatic melanomas.

RESULTS

Concordances among various antibody/platforms were high across antibodies (ICC > 0.80 for CPS), except for SP142. Two levels of immunostaining intensities were observed: high (QR1 and SP263) and low (28-8, 22C3, and SP142). Reproducibilities across pathologists were higher for QR1 and SP263 (ICC ≥ 0.87 and ≥ 0.85 for TPS and CPS, respectively). QR1, SP263, and 28-8 showed the highest concordance with mRNA expression (ICC ≥ 0.81 for CPS). We developed a standardized method for PD-L1 immunodetection and scoring, tested on 40 metastatic melanomas. Concordances among antibodies were excellent for all criteria, and concordances among pathologists were better for the MELscore than for other scores.

CONCLUSION

Harmonization of PD-L1 staining and scoring in melanomas with good concordance is achievable using the PD-L1 IHC protocols applied to other cancers; this reproducible approach can simplify daily practice.

Identification of MicroRNA-mRNA Networks in Melanoma and Their Association with PD-1 Checkpoint Blockade Outcomes

Metastatic melanoma is a deadly malignancy with poor outcomes historically. Immuno-oncology (IO) agents, targeting immune checkpoint molecules such as cytotoxic T-lymphocyte associated protein-4 (CTLA-4) and programmed cell death-1 (PD-1), have revolutionized melanoma treatment and outcomes, achieving significant response rates and remarkable long-term survival. Despite these vast improvements, roughly half of melanoma patients do not achieve long-term clinical benefit from IO therapies and there is an urgent need to understand and mitigate mechanisms of resistance. MicroRNAs are key post-transcriptional regulators of gene expression that regulate many aspects of cancer biology, including immune evasion. We used network analysis to define two core microRNA-mRNA networks in melanoma tissues and cell lines corresponding to 'MITF-low' and 'Keratin' transcriptomic subsets of melanoma. We then evaluated expression of these core microRNAs in pre-PD-1-inhibitor-treated melanoma patients and observed that higher expression of miR-100-5p and miR-125b-5p were associated with significantly improved overall survival. These findings suggest that miR-100-5p and 125b-5p are potential markers of response to PD-1 inhibitors, and further evaluation of these microRNA-mRNA interactions may yield further insight into melanoma resistance to PD-1 inhibitors.

LRP1B: A Giant Lost in Cancer Translation

Low-density lipoprotein receptor-related protein 1B (LRP1B) is a giant member of the LDLR protein family, which includes several structurally homologous cell surface receptors with a wide range of biological functions from cargo transport to cell signaling. LRP1B is among the most altered genes in human cancer overall. Found frequently inactivated by several genetic and epigenetic mechanisms, it has mostly been regarded as a putative tumor suppressor. Still, limitations in LRP1B studies exist, in particular associated with its huge size. Therefore, LRP1B expression and function in cancer remains to be fully unveiled. This review addresses the current understanding of LRP1B and the studies that shed a light on the LRP1B structure and ligands. It goes further in presenting increasing knowledge brought by technical and methodological advances that allow to better manipulate LRP1B expression in cells and to more thoroughly explore its expression and mutation status. New evidence is pushing towards the increased relevance of LRP1B in cancer as a potential target or translational prognosis and response to therapy biomarker.