Lina Jansen

BACKGROUND: For virtually every patient with colorectal cancer (CRC), hematoxylin-eosin (HE)-stained tissue slides are available. These images contain quantitative information, which is not routinely used to objectively extract prognostic biomarkers. In the present study, we investigated whether deep convolutional neural networks (CNNs) can extract prognosticators directly from these widely available images. METHODS AND FINDINGS: We hand-delineated single-tissue regions in 86 CRC tissue slides, yielding more than 100,000 HE image patches, and used these to train a CNN by transfer learning, reaching a nine-class accuracy of >94% in an independent data set of 7,180 images from 25 CRC patients. With this tool, we performed automated tissue decomposition of representative multitissue HE images from 862 HE slides in 500 stage I-IV CRC patients in the The Cancer Genome Atlas (TCGA) cohort, a large international multicenter collection of CRC tissue. Based on the output neuron activations in the CNN, we calculated a "deep stroma score," which was an independent prognostic factor for overall survival (OS) in a multivariable Cox proportional hazard model (hazard ratio [HR] with 95% confidence interval [CI]: 1.99 [1.27-3.12], p = 0.0028), while in the same cohort, manual quantification of stromal areas and a gene expression signature of cancer-associated fibroblasts (CAFs) were only prognostic in specific tumor stages. We validated these findings in an independent cohort of 409 stage I-IV CRC patients from the "Darmkrebs: Chancen der Verhütung durch Screening" (DACHS) study who were recruited between 2003 and 2007 in multiple institutions in Germany. Again, the score was an independent prognostic factor for OS (HR 1.63 [1.14-2.33], p = 0.008), CRC-specific OS (HR 2.29 [1.5-3.48], p = 0.0004), and relapse-free survival (RFS; HR 1.92 [1.34-2.76], p = 0.0004). A prospective validation is required before this biomarker can be implemented in clinical workflows. CONCLUSIONS: In our retrospective study, we show that a CNN can assess the human tumor microenvironment and predict prognosis directly from histopathological images.

BACKGROUND: Increasing proportions of patients diagnosed with cancer will become long-term survivors (≥ 5 years post-diagnosis). However, survivors may continue to experience negative effects of cancer and/or treatment, including fear of recurrence (FoR). This review aims to provide an overview of current knowledge on FoR, including determinants and consequences in long-term cancer survivors, and to outline methodological and conceptual challenges that should be addressed in future research. METHODS: Multiple databases including PUBMED, EMBASE, and PsycINFO were searched to identify relevant articles. Seventeen articles were included. Data were extracted by two reviewers and summarized following a systematic scheme. RESULTS: Even years after initial diagnosis, cancer survivors suffer from FoR. Most studies report low or moderate mean FoR scores, suggesting that FoR is experienced in modest intensity by most survivors. Studies including long-term and short-term survivors indicate no significant change of FoR over time. Lower level of education, lower level of optimism, and being Hispanic or White/Caucasian were found to be associated with higher levels of FoR. Significant negative associations were reported between FoR and quality of life as well as psychosocial well-being. All but three studies were conducted in the USA. General cut-offs for severity/clinical significance have not been defined yet. CONCLUSIONS: FoR at modest intensity is experienced by most long-term cancer survivors. Future studies should address determinants and consequences of FoR in more detail. Validated instruments providing cut-offs for severity/clinical significance of FoR should be developed and utilized. Efficient interventions should be implemented to reduce detrimental effects of FoR.