The algorithm is the first step towards developing an artificial intelligence-augmented radiology workflow that can support image interpretation to improve diagnosis and prognosis.
A newly developed algorithm was able to accurately classify six different types of brain tumor and discriminate pathologic from healthy magnetic resonance imaging (MRI) scans, according to a study published in Radiology: Artificial Intelligence. Moreover, this was achieved from a single scan per patient without the need of any additional manual input.
In this retrospective study, Satrajit Chakrabarty, Ph.D. candidate in electrical engineering at Washington University in St Louis, and colleagues developed a three-dimensional (3D) convolutional neural network model for classifying MRI scans into a healthy class and six tumor classes: high-grade glioma, low-grade glioma, brain metastases, meningioma, pituitary adenoma and acoustic neuroma.
“This is the first study to address the most common intracranial tumor-types and directly determine the tumor class as well as detect the absence of tumor from a 3D MR volume,” the authors said. “Without the assistance of any manually segmented tumor or bounding box, the convolutional neural network model…could classify six brain tumor types and discriminate
healthy from pathological scans from a single post-contrast T1-weighted scan per patient.”
The researchers included 2105 preoperative post-contrast T1-weighted MRI scans from four publicly available datasets, and 1396 scans were used to train the model, while 361 scans were assigned to an internal test dataset and 348 scans were assigned to an external test dataset.
On the internal test dataset, across the seven different classes, the model achieved sensitivity of 87% to 100%, a positive predictive value (PPV) of 85% to100%, area under the receiver operating characteristic curve (AUC) of 0.98 to 1.00 and precision-recall curve (AUPRC) of 0.91 to 1.00. On the external test dataset, comprising high-grade glioma and low-grade glioma, the model achieved sensitivity of 91% to 97%, a PPV of 73% to 99%, AUC of 0.97 to 0.98 and AUPRC of 0.9 to 1.0.
Of the seven classes addressed, more errors were observed for high-grade glioma, low-grade glioma and healthy. The authors explained that the reason for the misclassification between low-grade glioma and healthy classes may be due to less contrast enhancement of low-grade gliomas in post-contrast T1-weighted MRI scans due to less disruption of the blood-brain barrier.
“The model can be extended to other brain tumor types or neurologic disorders that exhibit
anomalous intensity profiles in MRI scans,” the authors said. “The network is the first step toward developing an artificial intelligence-augmented radiology workflow that can support image interpretation by providing quantitative information and statistics to the clinician to help improve diagnosis and prognosis.”
Stay at the forefront of radiology with the Diagnostic Imaging newsletter, delivering the latest news, clinical insights, and imaging advancements for today’s radiologists.
Large Medicare Study Shows Black Men Less Likely to Receive PET and MRI for Prostate Cancer Imaging
August 2nd 2025An analysis of over 749,000 Medicare beneficiaries diagnosed with prostate cancer over a five-year period found that Black men were 13 percent less likely to receive PET imaging and 16 percent less likely to receive MRI in comparison to White men.
The Reading Room Podcast: Current and Emerging Insights on Abbreviated Breast MRI, Part 3
August 2nd 2025In the last of a three-part podcast episode, Stamatia Destounis, MD, Emily Conant, MD and Habib Rahbar, MD, share additional insights on practical considerations and potential challenges in integrating abbreviated breast MRI into clinical practice, and offer their thoughts on future research directions.
The Reading Room Podcast: A Closer Look at Remote MRI Safety, Part 3
August 2nd 2025In the third of a three-part podcast episode, Emanuel Kanal, M.D. and Tobias Gilk, MRSO, MRSE, discuss strategies for maintaining the integrity of time-out procedures and communication with remote MRI scanning.
Study Reveals Significant Prevalence of Abnormal PET/MRI and Dual-Energy CT Findings with Long Covid
August 2nd 2025In a prospective study involving nearly 100 patients with Long Covid, 57 percent of patients had PET/MRI abnormalities and 90 percent of the cohort had abnormalities on dual-energy CT scans.