Niehues, J. M. | bioRxiv Science

bioRxiv2022

Self-supervised deep learning for pan-cancer mutation prediction from histopathology

The histopathological phenotype of tumors reflects the underlying genetic makeup. Deep learning can predict genetic alterations from tissue morphology, but it is unclear how well these predictions generalize to external datasets. Here, we present a deep learning pipeline based on self-supervised feature extraction which achieves a robust predictability of genetic alterations in two large multicentric datasets of seven tumor types.

cancer biology↗

bioRxiv2020

Nerve fibers in the Tumor Microenvironment are co-localized with Tertiary Lymphoid Structures

BackgroundB cells and tertiary lymphoid structures (TLS) are reported to be important in the improvement of survival of cancer patients. These secondary lymphoid organs have been associated with the generation of an anti-tumor response. Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancer types and the stromal architecture shapes the intratumoral heterogeneity. The stroma of PDAC is a complex system in which crosstalk takes place between cancer-associated fibroblasts, immune cells, endothelial cells and the cancer cells. Besides immune cells and fibroblasts, there is some limited data about the influence of nerve fibers on cancer progression. Patients and methodsNerve Fiber Density (NFD) was analysed in our cohort of 188 patients with Pancreatic Ductal Adenocarcinoma who underwent pancreatic surgery. We used immunohistochemistry and multiplex imaging to phenotype the immune cell infiltrate. The cell detection classifier measured distance from immune cell to cancer gland and with a heat map we could count TLS. By using Machine learning we were able to define the spatial distribution and counting Tertiary Lymphoid Structures. ResultsHigh NFD is significantly associated with prolonged overall survival (HR 1.676 (95%CI 1.126,2.495) for low vs. high NFD, p-value 0.0109). The immune cells surrounding the nerve fibers were phenotyped in B cells, T cells and dendritic follicular cells, matching a TLS. Here we show that small nerve fibers are located at the TLS in Pancreatic Cancer and a high Nerve Fiber Density combined with more than 5 TLS is associated with a better survival (HR 0.388 (95%CI 0.218, 0.689). ConclusionThe co-localization of small nerve fibers with TLS is a new finding which has not been described before. However the precise roles of these TLS and nerve fibers remains unknown. These findings unravel future pathways and has the potential to reach new directions into already existing targeted therapy.

cancer biology↗

bioRxiv2019

Pan-cancer image-based detection of clinically actionable genetic alterations

Precision treatment of cancer relies on genetic alterations which are diagnosed by molecular biology assays.1 These tests can be a bottleneck in oncology workflows because of high turnaround time, tissue usage and costs.2 Here, we show that deep learning can predict point mutations, molecular tumor subtypes and immune-related gene expression signatures3,4 directly from routine histological images of tumor tissue. We developed and systematically optimized a one-stop-shop workflow and applied it to more than 4000 patients with breast5, colon and rectal6, head and neck7, lung8,9, pancreatic10, prostate11 cancer, melanoma12 and gastric13 cancer. Together, our findings show that a single deep learning algorithm can predict clinically actionable alterations from routine histology data. Our method can be implemented on mobile hardware14, potentially enabling point-of-care diagnostics for personalized cancer treatment in individual patients.

genetics↗