Clinical workflows in oncology rely on predictive and prognostic molecular biomarkers. However, the growing number of these complex biomarkers tends to increase the cost and time for decision-making in routine daily oncology practice; furthermore, biomarkers often require tumour tissue on top of routine diagnostic material. Nevertheless, routinely available tumour tissue contains an abundance of clinically relevant information that is currently not fully exploited. Advances in deep learning (DL), an artificial intelligence (AI) technology, have enabled the extraction of previously hidden information directly from routine histology images of cancer, providing potentially clinically useful information. Here, we outline emerging concepts of how DL can extract biomarkers directly from histology images and summarise studies of basic and advanced image analysis for cancer histology. Basic image analysis tasks include detection, grading and subtyping of tumour tissue in histology images; they are aimed at automating pathology workflows and consequently do not immediately translate into clinical decisions. Exceeding such basic approaches, DL has also been used for advanced image analysis tasks, which have the potential of directly affecting clinical decision-making processes. These advanced approaches include inference of molecular features, prediction of survival and end-to-end prediction of therapy response. Predictions made by such DL systems could simplify and enrich clinical decision-making, but require rigorous external validation in clinical settings.

/pdf/deep-learning-in-cancer-pathology-a-new-generation-of-q9jahdg8as.pdf

Deep learning in cancer pathology: a new generation of clinical biomarkers.

Attempts to develop MET-targeted therapies have historically focused on MET-expressing cancers, with limited success. Thus, MET expression in the absence of a genomic marker of MET dependence is a poor predictor of benefit from MET-targeted therapy. However, owing to the development of more sensitive methods of detecting genomic alterations, high-level MET amplification and activating MET mutations or fusions are all now known to be drivers of oncogenesis. MET mutations include those affecting the kinase or extracellular domains and those that result in exon 14 skipping. The activity of MET tyrosine kinase inhibitors varies by MET alteration category. The likelihood of benefit from MET-targeted therapies increases with increasing levels of MET amplification, although no consensus exists on the optimal diagnostic cut-off point for MET copy number gains identified using fluorescence in situ hybridization and, in particular, next-generation sequencing. Several agents targeting exon 14 skipping alterations are currently in clinical development, with promising data available from early-phase trials. By contrast, the therapeutic implications of MET fusions remain underexplored. Here we summarize and evaluate the utility of various diagnostic techniques and the roles of different classes of MET-targeted therapies in cancers with MET amplification, mutation and fusion, and MET overexpression.

MET-dependent solid tumours - molecular diagnosis and targeted therapy

The proto-oncogene ROS1 encodes a receptor tyrosine kinase with an unknown physiological role in humans. Somatic chromosomal fusions involving ROS1 produce chimeric oncoproteins that drive a diverse range of cancers in adult and paediatric patients. ROS1-directed tyrosine kinase inhibitors (TKIs) are therapeutically active against these cancers, although only early-generation multikinase inhibitors have been granted regulatory approval, specifically for the treatment of ROS1 fusion-positive non-small-cell lung cancers; histology-agnostic approvals have yet to be granted. Intrinsic or extrinsic mechanisms of resistance to ROS1 TKIs can emerge in patients. Potential factors that influence resistance acquisition include the subcellular localization of the particular ROS1 oncoprotein and the TKI properties such as the preferential kinase conformation engaged and the spectrum of targets beyond ROS1. Importantly, the polyclonal nature of resistance remains underexplored. Higher-affinity next-generation ROS1 TKIs developed to have improved intracranial activity and to mitigate ROS1-intrinsic resistance mechanisms have demonstrated clinical efficacy in these regards, thus highlighting the utility of sequential ROS1 TKI therapy. Selective ROS1 inhibitors have yet to be developed, and thus the specific adverse effects of ROS1 inhibition cannot be deconvoluted from the toxicity profiles of the available multikinase inhibitors. Herein, we discuss the non-malignant and malignant biology of ROS1, the diagnostic challenges that ROS1 fusions present and the strategies to target ROS1 fusion proteins in both treatment-naive and acquired-resistance settings.

ROS1-dependent cancers - biology, diagnostics and therapeutics.

Immunotherapy for non-small cell lung cancer (NSCLC) is incorporated increasingly in first line treatments protocols. Multiple phase 3 studies have tested different medications targeting programmed death receptor 1 (PD-1), programmed death-ligand 1 (PD-L1), cytotoxic T-lymphocyte-associated protein 4 (CTLA-4), with or without chemotherapy. The inclusion criteria differ between the various clinical trials, including the cut-off levels of PD-L1 expression on tumor cells, and the tumor histology (squamous or non-squamous). Patients with tumor expression levels of PD-L1 ≥ 50% are candidates for treatment with single agent Pembrolizumab or Atezolizumab. Patients with PD-L1 1%; immunotherapy doublet, Nivolumab and Ipilimumab, or single agent immunotherapy combined with chemotherapy. Here we review phase 3 clinical trials utilizing immunotherapy in the first line for treatment of NSCLC, including Pembrolizumab in KEYNOTE-024, KEYNOTE-042, KEYNOTE-189 and KEYNOTE-407; Nivolumab and Ipilimumab in CHECKMATE-227 and CHECKMATE 9LA; and Atezolizumab in IMpower110, IMpower130 and IMpower150.

https://www.mdpi.com/1424-8247/13/11/373/pdf

First line Immunotherapy for Non-Small Cell Lung Cancer.

Lung cancer is the leading cause of cancer death worldwide. In the past decade EGFR, ALK and ROS1 TKIs lead to an unprecedented survival improvement of oncogene-addicted NSCLC patients, with better toxicity profile compared to chemotherapy. In recent years the implementation of high-throughput sequencing platforms led to the identification of uncommon molecular alterations in oncogenic drivers, such as BRAF, MET, RET, HER2 and NTRK. Moreover, newly developed drugs have been found to be active against hard to target drivers, such as KRAS. Specific TKIs targeting these genomic alterations are currently in clinical development and showed impressive activity and survival improvement, leading to FDA-accelerated approval for some of them. However, virtually all patients develop resistance to TKIs by on-target or off-target mechanisms. Here we review the clinicopathological features, the emerging targeted therapies and mechanisms of resistance and strategies to overcome them of KRAS, BRAF, MET, RET, HER2 and NTRK-addicted advanced NSCLCs.

S.D. Guibert

Papers

Crizotinib in c-MET- or ROS1-positive NSCLC: results of the AcSé phase II trial