Dual Energy CT for Deep Learning-Based Segmentation and Volumetric Estimation of Early Ischemic Infarcts.

Ischemic changes are not visible on non-contrast head CT until several hours after infarction, though deep convolutional neural networks have shown promise in the detection of subtle imaging findings. This study aims to assess if dual-energy CT (DECT) acquisition can improve early infarct visibility for machine learning. The retrospective dataset consisted of 330 DECTs acquired up to 48 h prior to confirmation of a DWI positive infarct on MRI between 2016 and 2022. Infarct segmentation maps were generated from the MRI and co-registered to the CT to serve as ground truth for segmentation. A self-configuring 3D nnU-Net was trained for segmentation on (1) standard 120 kV mixed-images (2) 190 keV virtual monochromatic images and (3) 120 kV + 190 keV images as dual channel inputs. Algorithm performance was assessed with Dice scores with paired t-tests on a test set. Global aggregate Dice scores were 0.616, 0.645, and 0.665 for standard 120 kV images, 190 keV, and combined channel inputs respectively. Differences in overall Dice scores were statistically significant with highest performance for combined channel inputs (p < 0.01). Small but statistically significant differences were observed for infarcts between 6 and 12 h from last-known-well with higher performance for larger infarcts. Volumetric accuracy trended higher with combined inputs but differences were not statistically significant (p = 0.07). Supplementation of standard head CT images with dual-energy data provides earlier and more accurate segmentation of infarcts for machine learning particularly between 6 and 12 h after last-known-well.

Optimizing Acute Stroke Segmentation on MRI Using Deep Learning: Self-Configuring Neural Networks Provide High Performance Using Only DWI Sequences.

Segmentation of infarcts is clinically important in ischemic stroke management and prognostication. It is unclear what role the combination of DWI, ADC, and FLAIR MRI sequences provide for deep learning in infarct segmentation. Recent technologies in model self-configuration have promised greater performance and generalizability through automated optimization. We assessed the utility of DWI, ADC, and FLAIR sequences on ischemic stroke segmentation, compared self-configuring nnU-Net models to conventional U-Net models without manual optimization, and evaluated the generalizability of results on an external clinical dataset. 3D self-configuring nnU-Net models and standard 3D U-Net models with MONAI were trained on 200 infarcts using DWI, ADC, and FLAIR sequences separately and in all combinations. Segmentation results were compared between models using paired t-test comparison on a hold-out test set of 50 cases. The highest performing model was externally validated on a clinical dataset of 50 MRIs. nnU-Net with DWI sequences attained a Dice score of 0.810 ± 0.155. There was no statistically significant difference when DWI sequences were supplemented with ADC and FLAIR images (Dice score of 0.813 ± 0.150; p = 0.15). nnU-Net models significantly outperformed standard U-Net models for all sequence combinations (p < 0.001). On the external dataset, Dice scores measured 0.704 ± 0.199 for positive cases with false positives with intracranial hemorrhage. Highly optimized neural networks such as nnU-Net provide excellent stroke segmentation even when only provided DWI images, without significant improvement from other sequences. This differs from-and significantly outperforms-standard U-Net architectures. Results translated well to the external clinical environment and provide the groundwork for optimized acute stroke segmentation on MRI.

Improving follow-up rates by optimizing patient educational materials in retinopathy of prematurity.

PURPOSE: To examine the impact of newly designed retinopathy of prematurity (ROP) patient educational materials adherent to health literacy guidelines on improving parent understanding of ROP, perceived importance of follow-up care, and subsequent outpatient follow-up attendance rates. METHODS: This was a repeated-measures study of parents of premature infants at risk for developing ROP. ROP educational materials were redesigned to adhere to current NIH and AMA reading level guidelines. Participants completed surveys that assessed understanding of ROP and perceived importance of clinic follow-up before and after receiving either materials currently available on the website of the American Association for Pediatric Ophthalmology and Strabismus (AAPOS), or the newly designed materials. Results were analyzed to evaluate for an improvement in parent knowledge of ROP and follow-up compliance. RESULTS: Parent ROP knowledge scores improved significantly after receiving educational materials for both the AAPOS materials (55.9% vs 83.7% [P < 0.001]) and the new materials (60.9% vs 91.8% [P < 0.001]). Average post-survey ROP knowledge scores were significantly higher among participants that received the new materials compared to the AAPOS materials (91.8% vs 83.7%, [P < 0.001]). Follow-up attendance rates improved in both groups, with a significantly improved rate from pre-study baseline among the new materials group (80.0% vs 68.2%, [P = 0.008). CONCLUSIONS: Implementation of educational materials significantly improved parent understanding of ROP; combined with knowledge assessment, it also improved follow-up compliance. Materials designed to adhere to health literacy guidelines are the most effective resources for improving knowledge of ROP and follow-up attendance.

An in vitro culture model to study the dynamics of colonic microbiota in Syrian golden hamsters and their susceptibility to infection with Clostridium difficile.

Clostridium difficile infections (CDI) are caused by colonization and growth of toxigenic strains of C. difficile in individuals whose intestinal microbiota has been perturbed, in most cases following antimicrobial therapy. Determination of the protective commensal gut community members could inform the development of treatments for CDI. Here, we utilized the lethal enterocolitis model in Syrian golden hamsters to analyze the microbiota disruption and recovery along a 20-day period following a single dose of clindamycin on day 0, inducing in vivo susceptibility to C. difficile infection. To determine susceptibility in vitro, spores of strain VPI 10463 were cultured with and without soluble hamster fecal filtrates and growth was quantified by quantitative PCR and toxin immunoassay. Fecal microbial population changes over time were tracked by 16S ribosomal RNA gene analysis via V4 sequencing and the PhyloChip assay. C. difficile culture growth and toxin production were inhibited by the presence of fecal extracts from untreated hamsters but not extracts collected 5 days post-administration of clindamycin. In vitro inhibition was re-established by day 15, which correlated with resistance of animals to lethal challenge. A substantial fecal microbiota shift in hamsters treated with antibiotics was observed, marked by significant changes across multiple phyla including Bacteroidetes and Proteobacteria. An incomplete return towards the baseline microbiome occurred by day 15 correlating with the inhibition of C. difficile growth in vitro and in vivo. These data suggest that soluble factors produced by the gut microbiota may be responsible for the suppression of C. difficile growth and toxin production.