Publications by authors named "Jan Lost"
Background: Glioma, the most prevalent primary brain tumor, poses challenges in prognosis, particularly in the high-grade subclass, despite advanced treatments. The recent shift in tumor classification underscores the crucial role of isocitrate dehydrogenase (IDH) mutation status in the clinical care of glioma patients. However, conventional methods for determining IDH status, including biopsy, have limitations.
View Article and Find Full Text PDFArticle Synopsis
- The study compares volumetric measurements of pediatric low-grade gliomas (pLGG) to simpler 2D methods traditionally used in clinical trials, aiming to determine which is more effective for assessing tumor response.
- An expert neuroradiologist assessed both solid and whole tumor volumes from MRI scans, finding that 3D volumetric analysis significantly outperformed 2D assessments in classifying tumor progression based on the BT-RADS criteria.
- Results showed that using 3D volume thresholds provided strong sensitivity for detecting tumor progression, suggesting that volumetric methods could enhance clinical management of pLGG.
Gliomas with CDKN2A mutations are known to have worse prognosis but imaging features of these gliomas are unknown. Our goal is to identify CDKN2A specific qualitative imaging biomarkers in glioblastomas using a new informatics workflow that enables rapid analysis of qualitative imaging features with Visually AcceSAble Rembrandtr Images (VASARI) for large datasets in PACS. Sixty nine patients undergoing GBM resection with CDKN2A status determined by whole-exome sequencing were included.
View Article and Find Full Text PDFArticle Synopsis
- Gliomas have varied molecular profiles that can impact patient survival and treatment choices, but existing diagnostic methods are often invasive and complex due to tumor heterogeneity.
- A systematic review analyzed various machine learning algorithms predicting glioma molecular subtypes based on MRI data, screening thousands of studies to find 85 relevant articles.
- Despite promising accuracy rates in internal validations (up to 88% for IDH mutation status), the review noted significant bias and limitations due to a lack of external validation and incomplete data across studies.
The translation of AI-generated brain metastases (BM) segmentation into clinical practice relies heavily on diverse, high-quality annotated medical imaging datasets. The BraTS-METS 2023 challenge has gained momentum for testing and benchmarking algorithms using rigorously annotated internationally compiled real-world datasets. This study presents the results of the segmentation challenge and characterizes the challenging cases that impacted the performance of the winning algorithms.
View Article and Find Full Text PDFBackground: While there are innumerable machine learning (ML) research algorithms used for segmentation of gliomas, there is yet to be a US FDA cleared product. The aim of this study is to explore the systemic limitations of research algorithms that have prevented translation from concept to product by a review of the current research literature.
Methods: We performed a systematic literature review on 4 databases.