Tumor-Stroma Ratio in Colorectal Cancer-Comparison between Human Estimation and Automated Assessment.

The tumor-stroma ratio (TSR) has been repeatedly shown to be a prognostic factor for survival prediction of different cancer types. However, an objective and reliable determination of the tumor-stroma ratio remains challenging. We present an easily adaptable deep learning model for accurately segmenting tumor regions in hematoxylin and eosin (H&E)-stained whole slide images (WSIs) of colon cancer patients into five distinct classes (tumor, stroma, necrosis, mucus, and background). The tumor-stroma ratio can be determined in the presence of necrotic or mucinous areas. We employ a few-shot model, eventually aiming for the easy adaptability of our approach to related segmentation tasks or other primaries, and compare the results to a well-established state-of-the art approach (U-Net). Both models achieve similar results with an overall accuracy of 86.5% and 86.7%, respectively, indicating that the adaptability does not lead to a significant decrease in accuracy. Moreover, we comprehensively compare with TSR estimates of human observers and examine in detail discrepancies and inter-rater reliability. Adding a second survey for segmentation quality on top of a first survey for TSR estimation, we found that TSR estimations of human observers are not as reliable a ground truth as previously thought.

Fast whole-slide cartography in colon cancer histology using superpixels and CNN classification.

Purpose: Automatic outlining of different tissue types in digitized histological specimen provides a basis for follow-up analyses and can potentially guide subsequent medical decisions. The immense size of whole-slide-images (WSIs), however, poses a challenge in terms of computation time. In this regard, the analysis of nonoverlapping patches outperforms pixelwise segmentation approaches but still leaves room for optimization. Furthermore, the division into patches, regardless of the biological structures they contain, is a drawback due to the loss of local dependencies. Approach: We propose to subdivide the WSI into coherent regions prior to classification by grouping visually similar adjacent pixels into superpixels. Afterward, only a random subset of patches per superpixel is classified and patch labels are combined into a superpixel label. We propose a metric for identifying superpixels with an uncertain classification and evaluate two medical applications, namely tumor area and invasive margin estimation and tumor composition analysis. Results: The algorithm has been developed on 159 hand-annotated WSIs of colon resections and its performance is compared with an analysis without prior segmentation. The algorithm shows an average speed-up of 41% and an increase in accuracy from 93.8% to 95.7%. By assigning a rejection label to uncertain superpixels, we further increase the accuracy by 0.4%. While tumor area estimation shows high concordance to the annotated area, the analysis of tumor composition highlights limitations of our approach. Conclusion: By combining superpixel segmentation and patch classification, we designed a fast and accurate framework for whole-slide cartography that is AI-model agnostic and provides the basis for various medical endpoints.

Novel Criteria for Intratumoral Budding with Prognostic Relevance for Colon Cancer and Its Histological Subtypes.

Peritumoral budding and intratumoral budding (ITB) are important prognostic factors for colorectal cancer patients. Scientists worldwide have investigated the role of budding in tumor progression and its prognosis, but guidelines for reliably identifying tumor buds based on morphology are lacking. In this study, next-generation tissue microarray (ngTMA®) construction was used for tumor bud evaluation, and highly detailed rule-out annotation was used for tumor definition in pancytokeratin-stained tissue sections. Initially, tissues of 245 colon cancer patients were evaluated with high interobserver reliability, and a concordance of 96% was achieved. It was shown that high ITB scores were associated with poor distant metastasis-free survival (p = 0.006 with a cut-off of ≥10 buds). This cut-off was defined as the best maximum value from one of two/three ngTMA® cores (0.6 mm diameter). ITB in 30 cases of mucinous, medullary, and signet ring cell carcinoma was analyzed for the subsequent determination of differences in tumor bud analyses between those subtypes. In conclusion, blinded randomized punched cores in the tumor center can be useful for ITB detection. It can be assumed that this method is suitable for its adoption in clinical routines.