Molecular Risk Stratification for Anal Cancer Prevention

Analytical validation and diagnostic performance of the ASCL1/ZNF582 methylation test for detection of high-grade anal intraepithelial neoplasia and anal cancer

DNA methylation testing on biopsies can detect high-grade anal intraepithelial neoplasia (HGAIN) in need of treatment and anal cancer. This study aimed to analytically validate and determine the diagnostic performance of a newly developed multiplex quantitative methylation-specific PCR, PreCursor-M AnoGYN (RUO), combining ASCL1, ZNF582 and a reference (ACTB) in one assay. Analytical validation was performed on two qPCR devices using predefined quality criteria. Diagnostic performance was determined on a cross-sectional series of 111 anal biopsies covering all stages of anal disease. Differences in methylation levels were assessed using the Kruskal-Wallis test. Area under the curve was determined using logistic regression analysis. Detection rates were calculated at predefined specificities for the cross-sectional and an additional longitudinal series of 23 HGAIN biopsies preceding anal cancer (i.e., progressive HGAIN). For both devices analytical quality criteria were met. ASCL1 and ZNF582 methylation levels increased with increasing severity of disease (p < 6*10-8). Diagnostic performance for AIN3+ was 0.81. All cancers and virtually all progressive HGAIN were detected at 70% and 80% specificity. In conclusion, the ASCL1/ZNF582 methylation test (PreCursor-M AnoGYN (RUO)) was demonstrated to be highly robust and reproducible. Moreover, it had excellent diagnostic accuracy to detect AIN3+ and can potentially be used to guide HGAIN management.

Image-Based Subtype Classification for Glioblastoma Using Deep Learning: Prognostic Significance and Biologic Relevance

PURPOSE

To apply deep learning algorithms to histopathology images, construct image-based subtypes independent of known clinical and molecular classifications for glioblastoma, and produce novel insights into molecular and immune characteristics of the glioblastoma tumor microenvironment.

MATERIALS AND METHODS

Using whole-slide hematoxylin and eosin images from 214 patients with glioblastoma in The Cancer Genome Atlas (TCGA), a fine-tuned convolutional neural network model extracted deep learning features. Biclustering was used to identify subtypes and image feature modules. Prognostic value of image subtypes was assessed via Cox regression on survival outcomes and validated with 189 samples from the Clinical Proteomic Tumor Analysis Consortium (CPTAC) data set. Morphological, molecular, and immune characteristics of glioblastoma image subtypes were analyzed.

RESULTS

Four distinct subtypes and modules (imClust1-4) were identified for the TCGA patients with glioblastoma on the basis of the image feature data. The glioblastoma image subtypes were significantly associated with overall survival (OS; P = .028) and progression-free survival (P = .003). Apparent association was also observed for disease-specific survival (P = .096). imClust2 had the best prognosis for all three survival end points (eg, after 25 months, imClust2 had >7% surviving patients than the other subtypes). Examination of OS in the external validation using the unseen CPTAC data set showed consistent patterns. Multivariable Cox analyses confirmed that the image subtypes carry unique prognostic information independent of known clinical and molecular predictors. Molecular and immune profiling revealed distinct immune compositions of the tumor microenvironment in different image subtypes and may provide biologic explanations for the patterns in patients' outcomes.

CONCLUSION

Our image-based subtype classification on the basis of deep learning models is a novel tool to refine risk stratification in cancers. The image subtypes detected for glioblastoma represent a promising prognostic biomarker with distinct molecular and immune characteristics and may facilitate developing novel, individualized immunotherapies for glioblastoma.

Colorectal Cancer Survival Prediction Using Deep Distribution Based Multiple-Instance Learning

Most deep-learning algorithms that use Hematoxylin- and Eosin-stained whole slide images (WSIs) to predict cancer survival incorporate image patches either with the highest scores or a combination of both the highest and lowest scores. In this study, we hypothesize that incorporating wholistic patch information can predict colorectal cancer (CRC) cancer survival more accurately. As such, we developed a distribution-based multiple-instance survival learning algorithm (DeepDisMISL) to validate this hypothesis on two large international CRC WSIs datasets called MCO CRC and TCGA COAD-READ. Our results suggest that combining patches that are scored based on percentile distributions together with the patches that are scored as highest and lowest drastically improves the performance of CRC survival prediction. Including multiple neighborhood instances around each selected distribution location (e.g., percentiles) could further improve the prediction. DeepDisMISL demonstrated superior predictive ability compared to other recently published, state-of-the-art algorithms. Furthermore, DeepDisMISL is interpretable and can assist clinicians in understanding the relationship between cancer morphological phenotypes and a patient's cancer survival risk.