3DTINC: Time-Equivariant Non-Contrastive Learning for Predicting Disease Progression from Longitudinal OCTs.

Self-supervised learning (SSL) has emerged as a powerful technique for improving the efficiency and effectiveness of deep learning models. Contrastive methods are a prominent family of SSL that extract similar representations of two augmented views of an image while pushing away others in the representation space as negatives. However, the state-of-the-art contrastive methods require large batch sizes and augmentations designed for natural images that are impractical for 3D medical images. To address these limitations, we propose a new longitudinal SSL method, 3DTINC, based on non-contrastive learning. It is designed to learn perturbation-invariant features for 3D optical coherence tomography (OCT) volumes, using augmentations specifically designed for OCT. We introduce a new non-contrastive similarity loss term that learns temporal information implicitly from intra-patient scans acquired at different times. Our experiments show that this temporal information is crucial for predicting progression of retinal diseases, such as age-related macular degeneration (AMD). After pretraining with 3DTINC, we evaluated the learned representations and the prognostic models on two large-scale longitudinal datasets of retinal OCTs where we predict the conversion to wet-AMD within a six-month interval. Our results demonstrate that each component of our contributions is crucial for learning meaningful representations useful in predicting disease progression from longitudinal volumetric scans.

Morph-SSL: Self-Supervision with Longitudinal Morphing for Forecasting AMD Progression from OCT Volumes.

The lack of reliable biomarkers makes predicting the conversion from intermediate to neovascular age-related macular degeneration (iAMD, nAMD) a challenging task. We develop a Deep Learning (DL) model to predict the future risk of conversion of an eye from iAMD to nAMD from its current OCT scan. Although eye clinics generate vast amounts of longitudinal OCT scans to monitor AMD progression, only a small subset can be manually labeled for supervised DL. To address this issue, we propose Morph-SSL, a novel Self-supervised Learning (SSL) method for longitudinal data. It uses pairs of unlabelled OCT scans from different visits and involves morphing the scan from the previous visit to the next. The Decoder predicts the transformation for morphing and ensures a smooth feature manifold that can generate intermediate scans between visits through linear interpolation. Next, the Morph-SSL trained features are input to a Classifier which is trained in a supervised manner to model the cumulative probability distribution of the time to conversion with a sigmoidal function. Morph-SSL was trained on unlabelled scans of 399 eyes (3570 visits). The Classifier was evaluated with a five-fold cross-validation on 2418 scans from 343 eyes with clinical labels of the conversion date. The Morph-SSL features achieved an AUC of 0.779 in predicting the conversion to nAMD within the next 6 months, outperforming the same network when trained end-to-end from scratch or pre-trained with popular SSL methods. Automated prediction of the future risk of nAMD onset can enable timely treatment and individualized AMD management.

Comparison of the clinical efficacy of concentrated growth factor and advanced platelet-rich fibrin in the treatment of type I multiple gingival recessions: a controlled randomized clinical trial.

OBJECTIVES: The purpose of this randomized controlled clinical trial was to compare and evaluate the clinical effects of concentrated growth factor (CGF) and advanced platelet-rich fibrin (A-PRF) applied together with coronally advanced flap (CAF) technique using a microsurgical approach in the treatment of type I multiple gingival recessions (GR). MATERIALS AND METHODS: Sixteen patients with multiple recession defects (Cairo type I) were included in this randomized and controlled study. Forty-five gingival recession defects were randomly equally divided into three groups (n = 15): CAF + CGF (test site); CAF + A-PRF (test site), and CAF alone (control site). Clinical attachment level (CAL), vertical gingival recession (VGR), horizontal gingival recession (HGR), gingival thickness (GT), width of keratinized gingiva (KGW), percentages of the mean (MRC), and complete root coverage (CRC), patient esthetic score (PES), and hypersensitivity score (HS) were recorded at baseline and 6 months after surgery. Patient comfort score (PCS) was evaluated at the day of surgery. RESULTS: Significant improvements were determined in CAL, VGR, HGR, KGW, and GT at 6 months when compared to baseline levels in intra-group comparisons for all groups, and also GT was increased in CAF + A-PRF and CAF + CGF compared to CAF alone at 6 months in intergroup comparisons (p < 0.05). At 6 months, MRC was detected 85.66 ± 22.68% in the CAF + CGF, 90.88 ± 20.87% in the CAF + A-PRF, and 75.10 ± 32,37% in the CAF alone, and a significant increase was detected in the CAF + A-PRF group compared to CAF alone (p < 0.05). CRC in CAF + CGF was 66.66%, in CAF + A-PRF 80% and in CAF alone was 53.33% (p > 0.05). PES and HS values showed significant improvement from baseline to 6 months for all groups and also in CAF + CGF and CAF + A-PRF compared to CAF alone at 6 months in intergroup comparisons (p < 0.05). CONCLUSIONS: The present study showed that the use of A-PRF and CGF membranes in GR therapy may have an additional benefit in GT increase and also A-PRF may increase the percentages of MRC. The use of A-PRF and CGF membranes may be beneficial in terms of improving patient-related parameters. CLINICAL RELEVANCE: A-PRF and CGF may be superior to CAF alone in terms of patient-related parameters and GT increase in multiple recession defects. TRIAL REGISTRATION NUMBER: 17578e02-00a9-4a41-8c8d-42a637143531.

Artificial Intelligence for Surgical Safety: Automatic Assessment of the Critical View of Safety in Laparoscopic Cholecystectomy Using Deep Learning.

OBJECTIVE: To develop a deep learning model to automatically segment hepatocystic anatomy and assess the criteria defining the critical view of safety (CVS) in laparoscopic cholecystectomy (LC). BACKGROUND: Poor implementation and subjective interpretation of CVS contributes to the stable rates of bile duct injuries in LC. As CVS is assessed visually, this task can be automated by using computer vision, an area of artificial intelligence aimed at interpreting images. METHODS: Still images from LC videos were annotated with CVS criteria and hepatocystic anatomy segmentation. A deep neural network comprising a segmentation model to highlight hepatocystic anatomy and a classification model to predict CVS criteria achievement was trained and tested using 5-fold cross validation. Intersection over union, average precision, and balanced accuracy were computed to evaluate the model performance versus the annotated ground truth. RESULTS: A total of 2854 images from 201 LC videos were annotated and 402 images were further segmented. Mean intersection over union for segmentation was 66.6%. The model assessed the achievement of CVS criteria with a mean average precision and balanced accuracy of 71.9% and 71.4%, respectively. CONCLUSIONS: Deep learning algorithms can be trained to reliably segment hepatocystic anatomy and assess CVS criteria in still laparoscopic images. Surgical-technical partnerships should be encouraged to develop and evaluate deep learning models to improve surgical safety.

Increased levels of interleukin-32 isoforms alpha, beta, gamma, and delta in the gingival crevicular fluid and plasma of the patients with periodontitis.

BACKGROUND AND OBJECTIVE: Interleukin (IL)-32, which has been recently reported to be associated with periodontitis, has been suggested to have pleiotropic effect due to its 9 different isoforms. The aim of this study was to investigate the levels of IL-32α, IL-32ß, IL-32γ, IL-32δ isoforms in gingival crevicular fluid (GCF) and plasma before and after non-surgical periodontal treatment in patients with periodontitis (P). MATERIALS AND METHODS: Twenty-seven P and 27 periodontally healthy controls (C) were recruited in this study. Non-surgical periodontal treatment was performed to periodontitis patients. GCF and plasma sampling and clinical periodontal parameters were evaluated before and 1 month after treatment. Enzyme-linked immunosorbent assay was used to analyze the levels of IL-32α, IL-32ß, IL-32γ, IL-32δ isoforms in GCF and plasma samples. RESULTS: The levels of IL-32α, IL-32ß, IL-32γ, and IL-32δ in plasma and GCF were significantly higher in patients with periodontitis than healthy controls (P < .001). In P group, plasma and GCF IL-32α, IL-32ß, IL-32γ, and IL-32δ levels after non-surgical periodontal treatment were lower when compared to baseline (P < .001). Moreover, there was a positive correlation between GCF and plasma IL-32α, IL-32ß, IL-32γ, and IL-32δ levels in all groups at baseline and after treatment (P < .05). CONCLUSION: The study supported that there was a relationship between elevated levels of IL-32 isoforms and periodontitis. Also, our novel findings suggest that the pro-inflammatory role of IL-32 in the periodontitis may be originated from IL-32α, IL-32ß, IL-32γ, and IL-32δ isoforms.

Formalizing video documentation of the Critical View of Safety in laparoscopic cholecystectomy: a step towards artificial intelligence assistance to improve surgical safety.

BACKGROUND: In laparoscopic cholecystectomy (LC), achievement of the Critical View of Safety (CVS) is commonly advocated to prevent bile duct injuries (BDI). However, BDI rates remain stable, probably due to inconsistent application or a poor understanding of CVS as well as unreliable reporting. Objective video reporting could serve for quality auditing and help generate consistent datasets for deep learning models aimed at intraoperative assistance. In this study, we develop and test a method to report CVS using videos. METHOD: LC videos performed at our institution were retrieved and the video segments starting 60 s prior to the division of cystic structures were edited. Two independent reviewers assessed CVS using an adaptation of the doublet view 6-point scale and a novel binary method in which each criterion is considered either achieved or not. Feasibility to assess CVS in the edited video clips and inter-rater agreements were evaluated. RESULTS: CVS was attempted in 78 out of the 100 LC videos retrieved. CVS was assessable in 100% of the 60-s video clips. After mediation, CVS was achieved in 32/78(41.03%). Kappa scores of inter-rater agreements using the doublet view versus the binary assessment were as follows: 0.54 versus 0.75 for CVS achievement, 0.45 versus 0.62 for the dissection of the hepatocystic triangle, 0.36 versus 0.77 for the exposure of the lower part of the cystic plate, and 0.48 versus 0.79 for the 2 structures connected to the gallbladder. CONCLUSIONS: The present study is the first to formalize a reproducible method for objective video reporting of CVS in LC. Minute-long video clips provide information on CVS and binary assessment yields a higher inter-rater agreement than previously used methods. These results offer an easy-to-implement strategy for objective video reporting of CVS, which could be used for quality auditing, scientific communication, and development of deep learning models for intraoperative guidance.