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.

Manual counting of mitotic tumor cells in tissue sections constitutes one of the strongest prognostic markers for breast cancer. This procedure, however, is time-consuming and error-prone. We developed a method to automatically detect mitotic figures in breast cancer tissue sections based on convolutional neural networks (CNNs). Application of CNNs to hematoxylin and eosin (H&E) stained histological tissue sections is hampered by: (1) noisy and expensive reference standards established by pathologists, (2) lack of generalization due to staining variation across laboratories, and (3) high computational requirements needed to process gigapixel whole-slide images (WSIs). In this paper, we present a method to train and evaluate CNNs to specifically solve these issues in the context of mitosis detection in breast cancer WSIs. First, by combining image analysis of mitotic activity in phosphohistone-H3 (PHH3) restained slides and registration, we built a reference standard for mitosis detection in entire H&E WSIs requiring minimal manual annotation effort. Second, we designed a data augmentation strategy that creates diverse and realistic H&E stain variations by modifying the hematoxylin and eosin color channels directly. Using it during training combined with network ensembling resulted in a stain invariant mitosis detector. Third, we applied knowledge distillation to reduce the computational requirements of the mitosis detection ensemble with a negligible loss of performance. The system was trained in a single-center cohort and evaluated in an independent multicenter cohort from The Cancer Genome Atlas on the three tasks of the Tumor Proliferation Assessment Challenge (TUPAC). We obtained a performance within the top-3 best methods for most of the tasks of the challenge.

Objective: The authors determined the prevalence of foreign body granulomas in intra-abdominal adhesions in patients with a history of abdominal surgery.Patients and Methods: In a cross-sectional, multicenter, multinational study, adult patients with a history of one or more previous abdominal operations and scheduled for laparotomy between 1991 and 1993 were examined during surgery.Patients in whom adhesions were present were selected for study. Quantity, distribution, and quality of adhesions were scored, and adhesion samples were taken for histologic examination.Results: In 448 studied patients, the adhesions were most frequently attached to the omentum (68%) and the small bowel (67%). The amount of adhesions was significantly smaller in patients with a history of only one minor operation or one major operation, compared with those with multiple laparotomies (p < 0.001).Significantly more adhesions were found in patients with a history of adhesions at previous laparotomy (p < 0.001), with presence of abdominal abscess, hematoma, and intestinal leakage as complications after former surgery (p = 0.01, p = 0.002, and p < 0.001, respectively), and with a history of an unoperated inflammatory process (p = 0.04).Granulomas were found in 26% of all patients. Suture granulomas were found in 25% of the patients. Starch granulomas were present in 5% of the operated patients whose surgeons wore starch-containing gloves. When suture granulomas were present, the median interval between the present and the most recent previous laparotomy was 13 months. When suture granulomas were absent, this interval was significantly longer-i.e., 30 months (p = 0.002). The percentage of patients with suture granulomas decreased gradually from 37% if the previous laparotomy had occurred up to 6 months before the present operation, to 18% if the previous laparotomy had occurred more than 2 years ago (p < 0.001).Conclusions: The number of adhesions found at laparotomy was significantly larger in patients with a history of multiple laparotomies, unoperated intraabdominal inflammatory disease, and previous postoperative intra-abdominal complications, and when adhesions were already present at previous laparotomy. In recent adhesions, suture granulomas occurred in a large percentage. This suggests that the intra-abdominal presence of foreign material is an important cause of adhesion formation. Therefore intra-abdominal contamination with foreign material should be minimized.

Lymphatic mapping using patent blue dye is feasible in colorectal cancer. The blue-stained nodes do not predict nodal status of the remaining lymph nodes in the resected specimen. The concept of lymphatic mapping and sentinel node identification is not valid for colorectal cancer.

No abstract