Faculty Bibliography

BACKGROUND AND PURPOSE/OBJECTIVE:Assessment of brain lesions on magnetic resonance imaging (MRI) is crucial for research in multiple sclerosis (MS). Manual segmentation is time-consuming and inconsistent. We aimed to develop an automated MS lesion segmentation algorithm for T2-weighted fluid-attenuated inversion recovery (FLAIR) MRI. METHODS:We developed FLAIR Lesion Analysis in Multiple Sclerosis (FLAMeS), a deep learning-based MS lesion segmentation algorithm based on the nnU-Net 3D full-resolution U-Net and trained on 668 FLAIR 1.5 and 3 tesla scans from persons with MS. FLAMeS was evaluated on three external datasets: MSSEG-2 (n = 14), MSLesSeg (n = 51), and a clinical cohort (n = 10), and compared to SAMSEG, LST-LPA, and LST-AI. Performance was assessed qualitatively by two blinded experts and quantitatively by comparing automated and ground truth lesion masks using standard segmentation metrics. RESULTS:, whereas the benchmark methods missed larger lesions in addition to smaller ones. CONCLUSIONS:FLAMeS is an accurate, robust method for MS lesion segmentation that outperforms other publicly available methods.

Objectives Stroke and post-stroke complications are associated with high morbidity, mortality, and cost. Our objective was to examine healthcare utilization and hospice enrollment for stroke patients at the end of life. Materials and methods The 2014 Nationwide Readmissions Database is a national database of > 14 million admissions. We used validated ICD-9 codes to identify fatal ischemic stroke, summarized demographics and hospitalization characteristics, and examined healthcare use within 30 days before fatal stroke admission. We used de-identified 2014 Medicare hospice data to identify stroke and non-stroke patients admitted to hospice. Results Among IS admissions in 2014 (n = 472,969), 22652 (4.8%) had in-hospital death. 28.2% with fatal IS had two or more hospitalizations in 2014. Among those with fatal IS admission, 13.0% were admitted with cerebrovascular disease within 30 days of fatal IS admission. Half of stroke patients discharged to hospice from the Medicare dataset were hospitalized with cerebrovascular disease within the thirty days prior to hospice enrollment. Within the study year, 6.9% of hospice enrollees had one or more emergency room visits, 31.7% had one or more inpatient encounters, and 5.2% had one or more nursing facility encounters (compared to 21.4%, 70.6%, and 27.2% respectively in the 30-day period prior to enrollment). Conclusions High rates of readmission prior to fatal stroke may indicate opportunity for improvement in acute stroke management, secondary prevention, and palliative care involvement as encouraged by AHA/ASA guidelines. For patients who are expected to survive 6 months or less, hospice may offer goal-concordant services for patients and caregivers who desire comfort-focused care.