Open-source deep learning-based automatic segmentation of mouse Schlemm's canal in optical coherence tomography images.

The purpose of this study was to develop an automatic deep learning-based approach and corresponding free, open-source software to perform segmentation of the Schlemm's canal (SC) lumen in optical coherence tomography (OCT) scans of living mouse eyes. A novel convolutional neural network (CNN) for semantic segmentation grounded in a U-Net architecture was developed by incorporating a late fusion scheme, multi-scale input image pyramid, dilated residual convolution blocks, and attention-gating. 163 pairs of intensity and speckle variance (SV) OCT B-scans acquired from 32 living mouse eyes were used for training, validation, and testing of this CNN model for segmentation of the SC lumen. The proposed model achieved a mean Dice Similarity Coefficient (DSC) of 0.694 ± 0.256 and median DSC of 0.791, while manual segmentation performed by a second expert grader achieved a mean and median DSC of 0.713 ± 0.209 and 0.763, respectively. This work presents the first automatic method for segmentation of the SC lumen in OCT images of living mouse eyes. The performance of the proposed model is comparable to the performance of a second human grader. Open-source automatic software for segmentation of the SC lumen is expected to accelerate experiments for studying treatment efficacy of new drugs affecting intraocular pressure and related diseases such as glaucoma, which present as changes in the SC area.

Risk stratification of parotid neoplasms based on intraoperative frozen section and preoperative fine needle aspiration cytology.

PURPOSE: This study aims to determine the relationship of frozen section (FS) to final histology and determine how incorporating FS may change preoperative malignancy risk estimates based on preoperative fine needle aspiration cytology (FNAC). The secondary aim is to determine if FS is useful in influencing intraoperative decision-making. METHODS: Retrospective review of 426 intraoperative FS for parotidectomies performed for primary parotid lesions. RESULTS: Risk of malignancy with a benign FS was 2.5%, with indeterminate 36.1%, and with malignant 100%. Incorporating FS to fine needle aspiration for cytology helped to stratify malignancy risk especially in the Milan categories of atypia of undetermined significance, neoplasm of uncertain malignant potential and non-diagnostic categories, where a malignant FS increased malignancy risk significantly. FS was only able to identify 11% of high-risk histological subtypes for which a neck dissection would be recommended. CONCLUSIONS: FS may be used to stratify malignancy risk intraoperatively but has limited utility in clinical decision-making to perform a neck dissection and more extensive parotid resection in high-risk histological subtypes.

Cognitive outcome after on- and off-pump coronary artery bypass grafting surgery: a systematic review and meta-analysis.

OBJECTIVE: The aim of this study was to compare cognition following coronary artery bypass grafting (CABG) surgery with or without cardiopulmonary bypass (CPB) (on- or off-pump). DESIGN: Systematic review and meta-analysis of randomized control trials comparing cognitive outcome in patients undergoing CABG surgery on- or off-pump as assessed by continuous measures from a battery of 7 psychometric tests. SETTING: Multi-institutional centers performing CABG surgery. PARTICIPANTS: Patients with coronary artery disease requiring CABG surgery. INTERVENTIONS: CABG surgery with or without CPB. MEASUREMENTS AND MAIN RESULTS: A structured literature search identified 13 randomized control trials that included a total of 2,405 patients. Results from 7 psychometric tests were grouped into early (≤3 months) and late (6-12 months) postoperative periods. No significant differences were found between on- and off-pump groups in any of the 7 psychometric tests in either the early (p range 0.21-0.78) or late (p range 0.09-0.93) postoperative period. CONCLUSION: The results suggested that CPB may not be associated with cognitive decline that is associated with CABG surgery.

Risk stratification of fine-needle aspiration cytology of parotid neoplasms based on the Milan system-Experience from a tertiary center in Asia.

BACKGROUND: The recently described Milan system provides a unified way of categorizing salivary gland fine-needle aspiration (FNA) cytology. We aim to use this system to stratify risk of malignancy in parotid FNAs. METHODS: In this retrospective case series, 376 FNAs were preoperatively performed for 573 parotidectomies over 14 years. RESULTS: Risk of malignancy on FNA is as follows: nondiagnostic 14.5%, non-neoplastic 26.7%, atypia of undetermined significance 29.3%, benign neoplasm 2.7%, neoplasm of uncertain malignant potential 19.1%, suspicious for malignancy 87.5%, and malignant 100%. The specific diagnoses of pleomorphic adenoma and Warthin tumor on FNA have high positive predictive value of 97.5% and 96.6%, respectively. Multivariate regression associates smaller size of lesion with a nondiagnostic or indeterminate result. Seniority of operator is associated with a lower likelihood of a nondiagnostic result. CONCLUSIONS: This large Asian series validates the Milan system as a valuable tool in stratifying malignancy risk of parotid FNAs.