Integrative Imaging Informatics for Cancer Research: Workflow Automation for Neuro-Oncology (I3CR-WANO).

PURPOSE: Efforts to use growing volumes of clinical imaging data to generate tumor evaluations continue to require significant manual data wrangling, owing to data heterogeneity. Here, we propose an artificial intelligence-based solution for the aggregation and processing of multisequence neuro-oncology MRI data to extract quantitative tumor measurements. MATERIALS AND METHODS: Our end-to-end framework (1) classifies MRI sequences using an ensemble classifier, (2) preprocesses the data in a reproducible manner, (3) delineates tumor tissue subtypes using convolutional neural networks, and (4) extracts diverse radiomic features. Moreover, it is robust to missing sequences and adopts an expert-in-the-loop approach in which the segmentation results may be manually refined by radiologists. After the implementation of the framework in Docker containers, it was applied to two retrospective glioma data sets collected from the Washington University School of Medicine (WUSM; n = 384) and The University of Texas MD Anderson Cancer Center (MDA; n = 30), comprising preoperative MRI scans from patients with pathologically confirmed gliomas. RESULTS: The scan-type classifier yielded an accuracy of >99%, correctly identifying sequences from 380 of 384 and 30 of 30 sessions from the WUSM and MDA data sets, respectively. Segmentation performance was quantified using the Dice Similarity Coefficient between the predicted and expert-refined tumor masks. The mean Dice scores were 0.882 (±0.244) and 0.977 (±0.04) for whole-tumor segmentation for WUSM and MDA, respectively. CONCLUSION: This streamlined framework automatically curated, processed, and segmented raw MRI data of patients with varying grades of gliomas, enabling the curation of large-scale neuro-oncology data sets and demonstrating high potential for integration as an assistive tool in clinical practice.

Streamlining the Process for Intravenous Tissue Plasminogen Activator.

BACKGROUND: For ischemic stroke, the chance of improved recovery is directly impacted by length of time from symptom onset to administration of intravenous tissue plasminogen activator (IV tPA). Despite the importance of rapid treatment, stroke centers struggle with achieving consistent door-to-needle times of less than 60 minutes. METHODS: We implemented a change in our response to the acute stroke patient by adding a dedicated stroke nurse and a nursing flow sheet focused on critical benchmarks before treatment. We collected data on patients treated with IV tPA preintervention and postintervention to determine whether our process increased the number of patients receiving tPA in less than 60 minutes. One hundred thirty-eight patients (n = 78 pre and 60 post) treated between 2009 and 2013 were included. Student t tests and χ tests were used to compare door-to-needle times preintervention and postintervention. RESULTS: By implementing this new approach, the mean time to treatment decreased from 82 to 78 minutes (P = .583). The percentage of patients successfully treated within 60 minutes of arrival improved from 28% to 52% (P = .005). Stroke severity and need for additional imaging were associated with increased time to treatment. CONCLUSION: The use of a stroke nurse and a nursing flow sheet as part of the acute stroke assessment significantly increases the proportion of patients treated with IV tPA within 60 minutes from hospital arrival.