Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology.

Deep learning using convolutional neural networks is an actively emerging field in histological image analysis. This study explores deep learning methods for computer-aided classification in H&E stained histopathological whole slide images of gastric carcinoma. An introductory convolutional neural network architecture is proposed for two computerized applications, namely, cancer classification based on immunohistochemical response and necrosis detection based on the existence of tumor necrosis in the tissue. Classification performance of the developed deep learning approach is quantitatively compared with traditional image analysis methods in digital histopathology requiring prior computation of handcrafted features, such as statistical measures using gray level co-occurrence matrix, Gabor filter-bank responses, LBP histograms, gray histograms, HSV histograms and RGB histograms, followed by random forest machine learning. Additionally, the widely known AlexNet deep convolutional framework is comparatively analyzed for the corresponding classification problems. The proposed convolutional neural network architecture reports favorable results, with an overall classification accuracy of 0.6990 for cancer classification and 0.8144 for necrosis detection.

A rare case of ovarian cancer in pregnancy complicated by pulmonary embolus and myocardial infarction: management dilemmas.

Malignant ovarian neoplasms diagnosed during pregnancy at advanced stages are very rare. The clinical course and prognosis of pregnant patients diagnosed with epithelial ovarian cancer is similar to that of non-pregnant patients. We describe our management of a woman diagnosed with FIGO IIIc ovarian cancer at Caesarean section. Immediately after surgery she suffered a pulmonary embolus and a myocardial infarction. She showed signs of a severe pulmonary hypertension (59 mmHg). Four weeks later the pulmonary hypertension was still moderate but, despite her critical status, she underwent primary debulking surgery (PDS). This was performed under extensive anaesthesiological monitoring. Through this rare case, we show that despite the complex initial status of a critically ill patient, PDS can still remain the mainstay of treatment in patients with advanced ovarian cancer as most patients are able to tolerate even extensive debulking surgery without the need for neoadjuvant chemotherapy.