BackgroundClear-cell renal cell carcinoma (ccRCC) is common and associated with substantial mortality. TNM stage and histopathological grading have been the sole determinants of a patient’s prognosis for decades and there are few prognostic biomarkers used in clinical routine. Management of ccRCC involves multiple disciplines such as urology, radiology, oncology, and pathology and each of these specialties generates highly complex medical data. Here, artificial intelligence (AI) could prove extremely powerful to extract meaningful information to benefit patients.ObjectiveIn the study, we developed and evaluated a multimodal deep learning model (MMDLM) for prognosis prediction in ccRCC.Design, Setting, and ParticipantsTwo mixed cohorts of non-metastatic and metastatic ccRCC patients were used: (1) The Cancer Genome Atlas cohort including 230 patients and (2) the Mainz cohort including 18 patients with ccRCC. For each of these patients, we trained the MMDLM on multiscale histopathological images, CT/MRI scans, and genomic data from whole exome sequencing.Outcome Measurements and Statistical AnalysisOutcome measurements included Harrell’s concordance index (C-index) and also various performance parameters for predicting the 5-year survival status (5YSS). Different visualization techniques were used to make our model more transparent.ResultsThe MMDLM showed great performance in predicting the prognosis of ccRCC patients with a mean C-index of 0.7791 and a mean accuracy of 83.43%. Training on a combination of data from different sources yielded significantly better results compared to when only one source was used. Furthermore, the MMDLM’s prediction was an independent prognostic factor outperforming other clinical parameters.InterpretationMultimodal deep learning can contribute to prognosis prediction in ccRCC and potentially help to improve the clinical management of this disease.Patient SummaryAn AI-based computer program can analyze various medical data (microscopic images, CT/MRI scans, and genomic data) simultaneously and thereby predict the survival time of patients with renal cancer.
Clear-cell renal cell carcinoma (ccRCC) is a von-Hippel-Lindau gene (
VHL
) associated tumor disease. In addition to activating the hypoxia inducible factor (HIF) dependent oxygen-sensing pathway,
VHL
loss also has an impact on a HIF-independent senescence program which functions as a tumorigenesis barrier. Lamin-B1 is a nuclear intermediate filament protein that exhibits effects on chromatin structure and gene expression and acts as a senescence effector. In the present study, the expression and prognostic relevance of Lamin-B1 in a large cohort of ccRCC patients was examined and the report presents initial functional data on possible therapeutic implications. The expression of Lamin-B1 was measured by immunohistochemistry using a tissue microarray containing tumor tissue samples from 763 ccRCC patients. Chi-squared tests, Kaplan-Meier curves and Cox regression models were used to investigate the possible association between Lamin-B1 expression, clinical and pathological characteristics and patient survival. High Lamin-B1 expression was associated with poor clinical outcomes and multivariate Cox regression analyses revealed that Lamin-B1 was an independent prognostic factor for cancer-specific survival. Furthermore
in vitro
data suggested that Lamin-B1 acted as a functional downstream senescence effector in RCC cell lines. In conclusion, patients affected by ccRCC with high Lamin-B1 expression exhibit poor prognosis. Lamin-B1 may serve as a tissue-based biomarker for new therapeutic agents targeting therapy-induced senescence.
Cyclin K plays a critical role in transcriptional regulation as well as cell development. However, the role of Cyclin K in prostate cancer is unknown. Here, we describe the impact of Cyclin K on prostate cancer cells and examine the clinical relevance of Cyclin K as a biomarker for patients with prostate cancer. We show that Cyclin K depletion in prostate cancer cells induces apoptosis and inhibits proliferation accompanied by an accumulation of cells in the G2/M phase. Moreover, knockdown of Cyclin K causes mitotic catastrophe displayed by multinucleation and spindle multipolarity. Furthermore, we demonstrate a Cyclin K dependent regulation of the mitotic kinase Aurora B and provide evidence for an Aurora B dependent induction of mitotic catastrophe. In addition, we show that Cyclin K expression is associated with poor biochemical recurrence-free survival in patients with prostate cancer treated with an adjuvant therapy. In conclusion, targeting Cyclin K represents a novel, promising anti-cancer strategy to induce cell cycle arrest and apoptotic cell death through induction of mitotic catastrophe in prostate cancer cells. Moreover, our results indicate that Cyclin K is a putative predictive biomarker for clinical outcome and therapy response for patients with prostate cancer.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.