The early detection and accurate histopathological diagnosis of gastric cancer increase the chances of successful treatment. The worldwide shortage of pathologists offers a unique opportunity for the use of artificial intelligence assistance systems to alleviate the workload and increase diagnostic accuracy. Here, we report a clinically applicable system developed at the Chinese PLA General Hospital, China, using a deep convolutional neural network trained with 2,123 pixel-level annotated H&E-stained whole slide images. The model achieves a sensitivity near 100% and an average specificity of 80.6% on a real-world test dataset with 3,212 whole slide images digitalized by three scanners. We show that the system could aid pathologists in improving diagnostic accuracy and preventing misdiagnoses. Moreover, we demonstrate that our system performs robustly with 1,582 whole slide images from two other medical centres. Our study suggests the feasibility and benefits of using histopathological artificial intelligence assistance systems in routine practice scenarios.

Vignette is an interactive system that facilitates texture creation in pen-and-ink illustrations. Unlike existing systems, Vignette preserves illustrators' workflow and style: users draw a fraction of a texture and use gestures to automatically fill regions with the texture. We currently support both 1D and 2D synthesis with stitching. Our system also has interactive refinement and editing capabilities to provide a higher level texture control, which helps artists achieve their desired vision. A user study with professional artists shows that Vignette makes the process of illustration more enjoyable and that first time users can create rich textures from scratch within minutes.

Purpose: Recent advances in computational image analysis offer the opportunity to develop automatic quantification of histologic parameters as aid tools for practicing pathologists. We aim to develop deep learning (DL) models to quantify nonsclerotic and sclerotic glomeruli on frozen sections from donor kidney biopsies. Approach: A total of 258 whole slide images (WSI) from cadaveric donor kidney biopsies performed at our institution (n = 123) and at external institutions (n = 135) were used in this study. WSIs from our institution were divided at the patient level into training and validation datasets (ratio: 0.8:0.2), and external WSIs were used as an independent testing dataset. Nonsclerotic (n = 22767) and sclerotic (n = 1366) glomeruli were manually annotated by study pathologists on all WSIs. A nine-layer convolutional neural network based on the common U-Net architecture was developed and tested for the segmentation of nonsclerotic and sclerotic glomeruli. DL-derived, manual segmentation, and reported glomerular count (standard of care) were compared. Results: The average Dice similarity coefficient testing was 0.90 and 0.83. And the F1, recall, and precision scores were 0.93, 0.96, and 0.90, and 0.87, 0.93, and 0.81, for nonsclerotic and sclerotic glomeruli, respectively. DL-derived and manual segmentation-derived glomerular counts were comparable, but statistically different from reported glomerular count. Conclusions: DL segmentation is a feasible and robust approach for automatic quantification of glomeruli. We represent the first step toward new protocols for the evaluation of donor kidney biopsies.

Granular cell tumors are lesions of Schwannian phenotype that most frequently arise in the skin, breast, and tongue. Pulmonary granular cell tumors (pGCTs) are exceedingly rare and only a handful of cases worldwide have been reported as malignant. We report here a series of 4 pGCTs, including an extremely rare case of a malignant pGCT which underwent next-generation sequencing to identify a novel pathogenic mutation. We are the first to report any prognostic data and response to treatment. Consistent with granular cell tumors of other primary sites, the majority of pGCTs (75%) were deemed histologically and biological benign without metastasis or recurrence after resection (mean follow-up, 750 d). pGCTs occurred predominantly in women (75%) with a mean age of 57 years (range, 49 to 66 y) and variable smoking history. Notably, 2 women also developed an associated lung carcinoma (adenocarcinoma and small cell carcinoma). We also report here an exceedingly rare case of a 51-year-old nonsmoker woman diagnosed with a malignant pGCT. She presented with a 6.4×6.1×4.4 cm infrahilar left lower lobe mass with extrinsic compression and obstruction of the left mainstem on enhanced computed tomography. Pathology of the resection specimen confirmed a pGCT composed of sheets of tumor cells with pleural, pericardial, and diaphragmatic metastases. Molecular analysis by next-generation sequencing failed to yield any driver mutations common to primary lung adenocarcinomas. Only 2 previous malignant pGCTs have been reported; our case revealed a novel pathologic ATM mutation.