- Quantification of T2-FLAIR Mismatch in Nonenhancing Diffuse Gliomas Using Digital Subtraction
The T2-FLAIR mismatch sign on MR imaging, usually determined by visual assessment, is a highly specific imaging biomarker of IDH-mutant astrocytomas. The authors of this study quantified the degree of T2-FLAIR mismatch in nonenhancing diffuse gliomas. Thresholds of ≥42% T2-FLAIR mismatch volume classified IDH-mutant astrocytoma with a specificity/sensitivity of 100%/19.6% (TCIA) and 100%/31.6% (institutional). They also found that grades 3–4 compared with grade 2 IDH-mutant astrocytomas (P<.05) had a higher percentage T2-FLAIR mismatch volume.
- AI-Assisted Summarization of Radiologic Reports: Evaluating GPT3davinci, BARTcnn, LongT5booksum, LEDbooksum, LEDlegal, and LEDclinical
This study quantitatively evaluated the performance of natural language processing models using real, longitudinal brain aneurysm imaging reports to objectively understand the strength and weakness of these new technologies.
- Discrimination of Hemorrhage and Contrast Media in a Head Phantom on Photon-Counting Detector CT Data
Photon-counting detector CT acquires spectral information that allows for material differentiation. CT scan can be separated into the attenuation resulting from remaining iodine and soft tissue, generating contrast media maps and virtual noncontrast series. In this study, the authors demonstrated that PCD-CT can reliably differentiate between blood and iodine and accurately determine several iodine concentrations in an anthropomorphic head phantom.