Lung cancer is a leading cause of death worldwide. Currently, in differential diagnosis of lung cancer, accurate classification of cancer types (adenocarcinoma, squamous cell carcinoma, and small cell carcinoma) is required. However, improving the accuracy and stability of diagnosis is challenging. In this study, we developed an automated classification scheme for lung cancers presented in microscopic images using a deep convolutional neural network (DCNN), which is a major deep learning technique. The DCNN used for classification consists of three convolutional layers, three pooling layers, and two fully connected layers. In evaluation experiments conducted, the DCNN was trained using our original database with a graphics processing unit. Microscopic images were first cropped and resampled to obtain images with resolution of 256 × 256 pixels and, to prevent overfitting, collected images were augmented via rotation, flipping, and filtering. The probabilities of three types of cancers were estimated using the developed scheme and its classification accuracy was evaluated using threefold cross validation. In the results obtained, approximately 71% of the images were classified correctly, which is on par with the accuracy of cytotechnologists and pathologists. Thus, the developed scheme is useful for classification of lung cancers from microscopic images.

Although its prevalence is declining, gastric cancer remains a significant public health issue. The bacterium Helicobacter pylori is known to colonize the human stomach and induce chronic atrophic gastritis, intestinal metaplasia, and gastric cancer. Results using a Mongolian gerbil model revealed that H. pylori infection increased the incidence of carcinogen-induced adenocarcinoma, whereas curative treatment of H. pylori significantly lowered cancer incidence. Furthermore, some epidemiological studies have shown that eradication of H. pylori reduces the development of metachronous cancer in humans. However, other reports have warned that human cases of atrophic metaplastic gastritis are already at risk for gastric cancer development, even after eradication of these bacteria. In this article, we discuss the effectiveness of H. pylori eradication and the morphological changes that occur in gastric dysplasia/cancer lesions. We further assess the control of gastric cancer using various chemopreventive agents.

Cytology is the first pathological examination performed in the diagnosis of lung cancer. In our previous study, we introduced a deep convolutional neural network (DCNN) to automatically classify cytological images as images with benign or malignant features and achieved an accuracy of 81.0%. To further improve the DCNN's performance, it is necessary to train the network using more images. However, it is difficult to acquire cell images which contain a various cytological features with the use of many manual operations with a microscope. Therefore, in this study, we aim to improve the classification accuracy of a DCNN with the use of actual and synthesized cytological images with a generative adversarial network (GAN). Based on the proposed method, patch images were obtained from a microscopy image. Accordingly, these generated many additional similar images using a GAN. In this study, we introduce progressive growing of GANs (PGGAN), which enables the generation of high-resolution images. The use of these images allowed us to pretrain a DCNN. The DCNN was then fine-tuned using actual patch images. To confirm the effectiveness of the proposed method, we first evaluated the quality of the images which were generated by PGGAN and by a conventional deep convolutional GAN. We then evaluated the classification performance of benign and malignant cells, and confirmed that the generated images had characteristics similar to those of the actual images. Accordingly, we determined that the overall classification accuracy of lung cells was 85.3% which was improved by approximately 4.3% compared to a previously conducted study without pretraining using GAN-generated images. Based on these results, we confirmed that our proposed method will be effective for the classification of cytological images in cases at which only limited data are acquired.

Tall cell variant (TCV) of papillary thyroid carcinoma is a rare tumor, which is usually associated with poor outcome, and pathologists often face the dilemma of proper diagnosis of TCV, not only by cytology but also histology. To allow surgeons to determine aggressiveness of the tumor before operation, it is important for pathologists to detect tall cell features correctly by fine-needle aspiration cytology (FNAC). However, the current criteria and definition of TCV are still controversial and confounded by another problem, the differential diagnosis from poorly differentiated thyroid carcinoma (PDC).In this report, we describe two cases of TCV and present characteristic FNAC findings. The tumor cells had a peculiar shape, which included tall, columnar, and oxyphilic cytoplasm with ''eccentric,'' basally located nuclei. We propose new terms for these cells, such as ''tail-like cells'' or ''tadpole cells. '' In the surgically-resected specimens, both cases exhibited remarkable extrathyroidal invasion accompanying prominent vascular invasions. They showed high Ki-67 (MIB-1) labeling index by immunohistochemistry, which indicated a higher proliferation activity of TCV than conventional form of papillary thyroid carcinoma.Furthermore, we discuss in this report the problematic issue of differential diagnosis of TCV from PDC and oxyphilic papillary thyroid carcinoma. Diagn. Cytopathol. 2009;37:732-737. ' 2009 Wiley-Liss, Inc.Key Words: thyroid; papillary carcinoma; tall cell variant; cytology; immunohistochemistry The tall cell variant (TCV) of papillary thyroid carcinoma has been recognized as a high-grade malignancy, which is usually associated with extrathyroidal invasion, vessel invasion, and local recurrence.1 It is an uncommon tumor, accounting for 1.3-12% of papillary thyroid carcinoma.1-11 Its disease-free 10-year survival rate is believed to be 10-15% lower than conventional form of papillary carcinoma (CPC). 2,3,5,6,11,12 By fine-needle aspiration cytology (FNAC) of the thyroid tumors, it is important to detect tall cell features before operation to predict aggressive clinical behavior. However, it is not so simple to make an accurate diagnosis of TCV by FNAC, because sometimes typical nuclear grooves and/or intracytoplasmic inclusions are not observed, while abundant oxyphilic cytoplasms are often shown. In addition, it is not uncommon that some cases of CPC include tall cell components to varying degrees. 13 Thus, during diagnosis of TCV by FNAC, special attention should be paid to the other types of histological variants of thyroid tumor or metastatic carcinoma from other organs as differential diagnoses.We report here two cases of TCV by FNAC, and describe their characteristic cytological features and histopathological findings. We also undertook an immunohistochemical study of these cases in this article. Materials and MethodsAspirates from the thyroid tumor of case 1 and from the lymph node of case 2 were studied. Each sample of alcohol-fixed smear was stained with Papanicolaou stain and air-dried s...

No abstract