Deep learning based tumor-stroma ratio scoring in colon cancer correlates with microscopic assessment

Prognostic Significance of Tumor-associated Stroma in Nasopharyngeal Carcinoma: A Multicenter Study

Assessment of tumor-associated stroma has shown a reliable prognostic value in recent research. We evaluated the prognostic value of tumor-stroma ratio (TSR) in a large multicenter cohort of nasopharyngeal carcinoma (NPC). We used the conventional hematoxylin and eosin-stained slides of 115 cases of NPC to assess TSR as described in recent guidelines. The amount of tumor-associated stroma was assessed as a percentage and then tumors were classified as stroma-high (>50%) or stroma-low (≤50%). Kaplan-Meier curves, χ 2 test, and Cox regression univariable and multivariable analyses were carried out. A total of 48 (41.7%) tumors were stroma-high and 67 (58.3%) tumors were stroma-low. In the Cox regression multivariable analysis, the tumors categorized as stroma-high were associated with a worse overall survival with a hazard ratio of 2.30 (95% CI: 1.27-4.15, P =0.006) and with poor disease-specific survival (hazard ratio=1.87, 95% CI: 1.07-3.28, P =0.029). The assessment of TSR in NPC is simple and cost-effective, and it has a significant prognostic value. TSR can aid in risk stratification and clinical decision-making in NPC.

Deep learning for multi-class semantic segmentation enables colorectal cancer detection and classification in digital pathology images

In colorectal cancer (CRC), artificial intelligence (AI) can alleviate the laborious task of characterization and reporting on resected biopsies, including polyps, the numbers of which are increasing as a result of CRC population screening programs ongoing in many countries all around the globe. Here, we present an approach to address two major challenges in the automated assessment of CRC histopathology whole-slide images. We present an AI-based method to segment multiple ([Formula: see text]) tissue compartments in the H &E-stained whole-slide image, which provides a different, more perceptible picture of tissue morphology and composition. We test and compare a panel of state-of-the-art loss functions available for segmentation models, and provide indications about their use in histopathology image segmentation, based on the analysis of (a) a multi-centric cohort of CRC cases from five medical centers in the Netherlands and Germany, and (b) two publicly available datasets on segmentation in CRC. We used the best performing AI model as the basis for a computer-aided diagnosis system that classifies colon biopsies into four main categories that are relevant pathologically. We report the performance of this system on an independent cohort of more than 1000 patients. The results show that with a good segmentation network as a base, a tool can be developed which can support pathologists in the risk stratification of colorectal cancer patients, among other possible uses. We have made the segmentation model available for research use on https://grand-challenge.org/algorithms/colon-tissue-segmentation/ .

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.