BackgroundThe presence of lymph node metastases is one of the most important factors in breast cancer prognosis. The most common way to assess regional lymph node status is the sentinel lymph node procedure. The sentinel lymph node is the most likely lymph node to contain metastasized cancer cells and is excised, histopathologically processed, and examined by a pathologist. This tedious examination process is time-consuming and can lead to small metastases being missed. However, recent advances in whole-slide imaging and machine learning have opened an avenue for analysis of digitized lymph node sections with computer algorithms. For example, convolutional neural networks, a type of machine-learning algorithm, can be used to automatically detect cancer metastases in lymph nodes with high accuracy. To train machine-learning models, large, well-curated datasets are needed.ResultsWe released a dataset of 1,399 annotated whole-slide images (WSIs) of lymph nodes, both with and without metastases, in 3 terabytes of data in the context of the CAMELYON16 and CAMELYON17 Grand Challenges. Slides were collected from five medical centers to cover a broad range of image appearance and staining variations. Each WSI has a slide-level label indicating whether it contains no metastases, macro-metastases, micro-metastases, or isolated tumor cells. Furthermore, for 209 WSIs, detailed hand-drawn contours for all metastases are provided. Last, open-source software tools to visualize and interact with the data have been made available.ConclusionsA unique dataset of annotated, whole-slide digital histopathology images has been provided with high potential for re-use.

The development of reliable imaging biomarkers for the analysis of colorectal cancer (CRC) in hematoxylin and eosin (H&E) stained histopathology images requires an accurate and reproducible classification of the main tissue components in the image. In this paper, we propose a system for CRC tissue classification based on convolutional networks (ConvNets). We investigate the importance of stain normalization in tissue classification of CRC tissue samples in H&E-stained images. Furthermore, we report the performance of ConvNets on a cohort of rectal cancer samples and on an independent publicly available dataset of colorectal H&E images.

No abstract

Purpose Tumor-stroma ratio (TSR) serves as an independent prognostic factor in colorectal cancer and other solid malignancies. The recent introduction of digital pathology in routine tissue diagnostics holds opportunities for automated TSR analysis. We investigated the potential of computer-aided quantification of intratumoral stroma in rectal cancer whole-slide images. Methods Histological slides from 129 rectal adenocarcinoma patients were analyzed by two experts who selected a suitable stroma hot-spot and visually assessed TSR. A semi-automatic method based on deep learning was trained to segment all relevant tissue types in rectal cancer histology and subsequently applied to the hot-spots provided by the experts. Patients were assigned to a 'stroma-high' or 'stroma-low' group by both TSR methods (visual and automated). This allowed for prognostic comparison between the two methods in terms of disease-specific and disease-free survival times.Results With stroma-low as baseline, automated TSR was found to be prognostic independent of age, gender, pT-stage, lymph node status, tumor grade, and whether adjuvant therapy was given, both for disease-specific survival (hazard ratio = 2.48 (95% confidence interval 1.29-4.78)) and for disease-free survival (hazard ratio = 2.05 (95% confidence interval 1.11-3.78)). Visually assessed TSR did not serve as an independent prognostic factor in multivariate analysis. Conclusions This work shows that TSR is an independent prognosticator in rectal cancer when assessed automatically in userprovided stroma hot-spots. The deep learning-based technology presented here may be a significant aid to pathologists in routine diagnostics.

By working digitally, a significant amount of time could be saved in a large regional pathology laboratory with a typical case mix. We also present the data in each workflow per task and concrete logistic steps to allow extrapolation to the context and case mix of other laboratories.

Objective-Advanced glycation end products (AGEs), such as N -(carboxymethyl)lysine (CML), are implicated in vascular disease. We previously reported increased CML accumulation in small intramyocardial blood vessels in diabetes patients. Diabetes patients have an increased risk for acute myocardial infarction (AMI). Here, we examined a putative relationship between CML and AMI. Methods and Results-Heart tissue was stained for CML, myeloperoxidase, and E-selectin in AMI patients (nϭ26), myocarditis patients (nϭ17), and control patients (nϭ15). In AMI patients, CML depositions were 3-fold increased compared with controls in the small intramyocardial blood vessels and predominantly colocalized with activated endothelium (E-selectin-positive) both in infarction and noninfarction areas. A trend of increased CML positivity of the intima of epicardial coronary arteries did not reach significance in AMI patients. In the rat heart AMI model, CML depositions were undetectable after 24 hours of reperfusion, but became clearly visible after 5 days of reperfusion. In line with an inflammatory contribution, human myocarditis was also accompanied by accumulation of CML on the endothelium of intramyocardial blood vessels. Conclusions-CML, present predominantly on activated endothelium in small intramyocardial blood vessels in patients with AMI, might reflect an increased risk for AMI rather than being a result of AMI.

AIMTo evaluate the prognostic value of the tumor-stroma ratio (TSR) in rectal cancer.METHODSTSR was determined on hematoxylin and eosin stained histological sections of 154 patients treated for rectal adenocarcinoma without prior neoadjuvant treatment in the period 1996-2006 by two observers to assess reproducibility. Patients were categorized into three categories: TSR-high [carcinoma percentage (CP) ≥ 70%], TSR-intermediate (CP 40%, 50% and 60%) and TSR-low (CP ≤ 30%). The relation between categorized TSR and survival was analyzed using Cox proportional hazards model.RESULTSThirty-six (23.4%) patients were scored as TSR-low, 70 (45.4%) as TSR-intermediate and 48 (31.2%) as TSR-high. TSR had a good interobserver agreement (κ = 0.724, concordance 82.5%). Overall survival (OS) and disease free survival (DFS) were significantly better for patients with a high TSR (P = 0.01 and P = 0.02, respectively). A similar association existed for disease specific survival (P = 0.06). In multivariate analysis, patients without lymph node metastasis and an intermediate TSR had a higher risk of dying from rectal cancer (HR = 5.27, 95%CI: 1.54-18.10), compared to lymph node metastasis negative patients with a high TSR. This group also had a worse DFS (HR = 6.41, 95%CI: 1.84-22.28). An identical association was seen for OS. These relations were not seen in lymph node metastasis positive patients.CONCLUSIONThe TSR has potential as a prognostic factor for survival in surgically treated rectal cancer patients, especially in lymph node negative cases.

In our in vitro closed-loop model, reproducible vessel wall changes were observed in all human vein graft specimens studied. The beneficial effect of perivenous support could also be established for the human greater saphenous vein, providing a basis for clinical application.