[Feasibility multi-center study of artificial intelligence assistance in cervical fluid-based cytology diagnosis].

Objective: To propose a method of cervical cytology screening based on deep convolutional neural network and compare it with the diagnosis of cytologists. Method: The deep segmentation network was used to extract 618 333 regions of interest (ROI) from 5, 516 cytological pathological images. Combined with the experience of physicians, the deep classification network with the ability to analyze ROI was trained. The classification results were used to construct features, and the decision model was used to complete the classification of cytopathological images. Results: The sensitivity and specificity were 89.72%, 58.48%, 33.95% and 95.94% respectively. Among the smears derived from four different preparation methods, this algorithm had the best effect on natural fallout with a sensitivity of 91.10%, specificity of 69.32%, positive predictive rate of 41.41%, and negative predictive rate of 97.03%. Conclusion: Deep convolutional neural network image recognition technology can be applied to cervical cytology screening.

Comparisons of MR Findings Between Supratentorial and Infratentorial Gangliogliomas.

PURPOSE: Ganglioglioma is an uncommon intracranial disorder. The purpose of our study was to describe the different MR characteristics between supratentorial and infratentorial gangliogliomas and to evaluate the diagnostic value of MR imaging for the disorder. METHODS: The MR images of 33 patients with intracranial gangliogliomas from July 2007 to November 2012 were retrospectively reviewed. We evaluated the images in relation to the following variables: location, size, cystic changes, cortical changes, and enhancement pattern. RESULTS: Histological diagnosis was achieved in all cases by surgery. Tumors were divided into a supratentorial group (n = 24) and an infratentorial group (n = 9) according to their location. In the supratentorial group, tumor dimensions varied from 0.5 to 5 cm (mean dimension, 2.7 cm). Cystic (n = 2), cystic-solid (n = 10), and solid (n = 12) tumors without cortical changes had variable enhancement in this group. In the infratentorial group, tumor dimensions varied from 4 to 7 cm (mean dimension, 5.2 cm). Solid (n = 7) tumors with ipsilateral cerebellar cortical atrophy (n = 7) had remarkable heterogeneous enhancement in this group. CONCLUSIONS: MR imaging features of supratentorial gangliogliomas are non-specific. Relatively larger solid masses with remarkable heterogeneous enhancement and ipsilateral cerebellar cortical atrophy in the infratentorial region are suggestive of ganglioglioma. As such, cerebellar cortical atrophy may be a specific finding that is well demonstrated with MR imaging. Although MR findings can provide some evidence for this rare entity, a differential diagnosis is still needed.