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.

Modern neuro-oncology workflows are driven by large collections of high-dimensional MRI data obtained using varying acquisition protocols. The concomitant heterogeneity of this data makes extensive manual curation and pre-processing imperative prior to algorithmic use. The limited efforts invested towards automating this curation and processing are fragmented, do not encompass the entire workflow, or still require significant manual intervention. In this work, we propose an artificial intelligence-driven solution for transforming multi-modal raw neuro-oncology MRI Digital Imaging and Communications in Medicine (DICOM) data into quantitative tumor measurements. Our end-to-end framework classifies MRI scans into different structural sequence types, preprocesses the data, and uses convolutional neural networks to segment tumor tissue subtypes. Moreover, it adopts an expert-in-the-loop approach, where segmentation results may be manually refined by radiologists. This framework was implemented as Docker Containers (for command line usage and within the eXtensible Neuroimaging Archive Toolkit [XNAT]) and validated on a retrospective glioma dataset (n = 155) collected from the Washington University School of Medicine, comprising preoperative MRI scans from patients with histopathologically confirmed gliomas. Segmentation results were refined by a neuroradiologist, and performance was quantified using Dice Similarity Coefficient to compare predicted and expert-refined tumor masks. The scan-type classifier yielded a 99.71% accuracy across all sequence types. The segmentation model achieved mean Dice scores of 0.894 (± 0.225) for whole tumor segmentation. The proposed framework can automate tumor segmentation and characterization -thus streamlining workflows in a clinical setting as well as expediting standardized curation of large-scale neuro-oncology datasets in a research setting.

Multidisciplinary tumor boards (TB) are an essential part of brain tumor care, but quantifying the impact of imaging on patient management is challenging due to treatment complexity and a lack of quantitative outcome measures. This work uses a structured reporting system for classifying brain tumor MRIs, the brain tumor reporting and data system (BT-RADS), in a TB setting to prospectively assess the impact of imaging review on patient management. Published criteria were used to prospectively assign three separate BT-RADS scores (an initial radiology report, secondary TB presenter review, and TB consensus) to brain MRIs reviewed at an adult brain TB. Clinical recommendations at TB were noted and management changes within 90 days after TB were determined by chart review. In total, 212 MRIs in 130 patients (median age = 57 years) were reviewed. Agreement was 82.2% between report and presenter, 79.0% between report and consensus, and 90.1% between presenter and consensus. Rates of management change increased with increasing BT-RADS scores (0—3.1%, 1a—0%, 1b—66.7%, 2—8.3%, 3a—38.5%, 3b—55.9, 3c—92.0%, and 4—95.6%). Of 184 (86.8%) cases with clinical follow-up within 90 days after the tumor board, 155 (84.2%) of the recommendations were implemented. Structured scoring of MRIs provides a quantitative way to assess rates of agreement interpretation alongside how often management changes are recommended and implemented in a TB setting.