Interrogating the microenvironmental landscape of tumors with computational image analysis approaches

New target DDR1: A "double-edged sword" in solid tumors

Globally, cancer is a major catastrophic disease that seriously threatens human health. Thus, there is an urgent need to find new strategies to treat cancer. Among them, identifying new targets is one of the best ways to treat cancer at present. Especially in recent years, scientists have discovered many new targets and made breakthroughs in the treatment of cancer, bringing new hope to cancer patients. As one of the novel targets for cancer treatment, DDR1 has attracted much attention due to its unique role in cancer. Hence, here, we focus on a new target, DDR1, which may be a "double-edged sword" of human solid tumors. In this review, we provide a comprehensive overview of how DDR1 acts as a "double-edged sword" in cancer. First, we briefly introduce the structure and normal physiological function of DDR1; Second, we delineate the DDR1 expression pattern in single cells; Next, we sorte out the relationship between DDR1 and cancer, including the abnormal expression of DDR1 in cancer, the mechanism of DDR1 and cancer occurrence, and the value of DDR1 on cancer prognosis. In addition, we introduced the current status of global drug and antibody research and development targeting DDR1 and its future design prospects; Finally, we summarize and look forward to designing more DDR1-targeting drugs in the future to make further progress in the treatment of solid tumors.

Deep learning-based tumor microenvironment segmentation is predictive of tumor mutations and patient survival in non-small-cell lung cancer

BACKGROUND

Despite the fact that tumor microenvironment (TME) and gene mutations are the main determinants of progression of the deadliest cancer in the world - lung cancer, their interrelations are not well understood. Digital pathology data provides a unique insight into the spatial composition of the TME. Various spatial metrics and machine learning approaches were proposed for prediction of either patient survival or gene mutations from this data. Still, these approaches are limited in the scope of analyzed features and in their explainability, and as such fail to transfer to clinical practice.

METHODS

Here, we generated 23,199 image patches from 26 hematoxylin-and-eosin (H&E)-stained lung cancer tissue sections and annotated them into 9 different tissue classes. Using this dataset, we trained a deep neural network ARA-CNN. Next, we applied the trained network to segment 467 lung cancer H&E images from The Cancer Genome Atlas (TCGA) database. We used the segmented images to compute human-interpretable features reflecting the heterogeneous composition of the TME, and successfully utilized them to predict patient survival and cancer gene mutations.

RESULTS

We achieved per-class AUC ranging from 0.72 to 0.99 for classifying tissue types in lung cancer with ARA-CNN. Machine learning models trained on the proposed human-interpretable features achieved a c-index of 0.723 in the task of survival prediction and AUC up to 73.5% for PDGFRB in the task of mutation classification.

CONCLUSIONS

We presented a framework that accurately predicted survival and gene mutations in lung adenocarcinoma patients based on human-interpretable features extracted from H&E slides. Our approach can provide important insights for designing novel cancer treatments, by linking the spatial structure of the TME in lung adenocarcinoma to gene mutations and patient survival. It can also expand our understanding of the effects that the TME has on tumor evolutionary processes. Our approach can be generalized to different cancer types to inform precision medicine strategies.