16 June 2025 in Computerized Medical Imaging and Graphics
This study focuses on artificial intelligence-driven classification of glioma and Ki-67 leveling using T2w-FLAIR MRI, exploring the association of Ki-67 biomarkers with deep learning (DL) features through explainable artificial intelligence (XAI) and SHapley Additive exPlanations (SHAP). This IRB-approved study included 101 patients with glioma brain tumor acquired MR images with the T2W-FLAIR sequence. We extracted DL bottleneck features using ResNet50 from glioma MR images. Principal component analysis (PCA) was deployed for dimensionality reduction. XAI was used to identify potential features. The XGBosst classified the histologic grades of the glioma and the level of Ki-67. We integrated potential DL features with patient demographics (age and sex) and Ki-67 biomarkers, utilizing SHAP to determine the model's essential features and interactions. Glioma grade classification and Ki-67 level predictions achieved overall accuracies of 0.94 and 0.91, respectively. It achieved precision scores of 0.92, 0.94, and 0.96 for glioma grades 2, 3, and 4, and 0.88, 0.94, and 0.97 for Ki-67 levels (low: 5%≤Ki-6720%). Corresponding F1-scores were 0.95, 0.88, and 0.96 for glioma grades and 0.92, 0.93, and 0.87 for Ki-67 levels. SHAP analysis further highlighted a strong association between bottleneck DL features and Ki-67 biomarkers, demonstrating their potential to differentiate glioma grades and Ki-67 levels while offering valuable insights into glioma aggressiveness. This study demonstrates the precise classification of glioma grades and the prediction of Ki-67 levels to underscore the potential of AI-driven MRI analysis to enhance clinical decision-making in glioma management.
11 December 2021 in Magnetic Resonance in Medicine
16 July 2021 in Magnetic Resonance in Medicine
27 April 2023 in Magnetic Resonance in Medicine
Purpose: To develop a time‐efficient pulse sequence that acquires multiple diffusion‐weighted images with distinct diffusion times in a single shot by using multiple stimulated echoes (mSTE) with variable flip angles (VFA).Methods: The proposed diffusion‐weighted mSTE with VFA (DW‐mSTE‐VFA) sequence begins with two 90° RF pulses that straddle a diffusion gradient lobe (GD) to excite and restore one half of the magnetization into the longitudinal axis. The restored longitudinal magnetization was successively re‐excited by a series of RF pulses with VFA, each followed by another GD, to generate a set of stimulated echoes. Each of the multiple stimulated echoes was acquired with an EPI echo train. As such, the train of multiple stimulated echoes produced a set of diffusion‐weighted images with varying diffusion times in a single shot. This technique was experimentally demonstrated on a diffusion phantom, a fruit, and healthy human brain and prostate at 3 T.Results: In the phantom experiment, the mean ADC measured at different diffusion times using DW‐mSTE‐VFA were highly consistent (r = 0.999) with those from a commercial spin‐echo diffusion‐weighted EPI sequence. In the fruit and brain experiments, DW‐mSTE‐VFA exhibited similar diffusion‐time dependence to a standard diffusion‐weighted stimulated echo sequence. The ADC showed significant time dependence in the human brain (p = 0.003 in both white matter and gray matter) and prostate tissues (p = 0.003 in both peripheral zone and central gland).Conclusion: DW‐mSTE‐VFA offers a time‐efficient tool for investigating the diffusion‐time dependency in diffusion MRI studies.
20 December 2024 in bioRxiv
TCThe Acute to Chronic Pain Signatures Consortium
The Acute to Chronic Pain Signatures Consortium
+25
The Acute to Chronic Pain Signatures (A2CPS) project is a large-scale, multi-site initiative aimed at identifying biomarkers and biosignatures that predict the transition from acute to chronic pain. The project is collecting multimodal, longitudinal data from over 2,500 individuals at risk for developing chronic pain after surgery. Here we describe the neuroimaging component of A2CPS, including the acquisition protocols, processing pipelines, and contents of the initial data release. The imaging protocol includes structural, diffusion, resting-state and task-based functional magnetic resonance imaging (MRI) data. Data are collected across multiple clinical sites using different scanner manufacturers, with attention to protocol harmonization and quality control. The processing pipeline integrates several established neuroimaging tools to extract potential biomarkers, including measures of brain structure, connectivity, and pain-related neural signatures. The first data release includes pre-surgical imaging data for 595 participants, with high quality ratings across modalities (98.7% of sMRI, 99.8% of dMRI, and 94.6% of fMRI images were rated as acceptable or better). Initial analyses demonstrate expected relationships between brain-derived measures and clinical variables, such as associations between brain age and psychological factors. This dataset represents a valuable resource for both pain research and neuroimaging methods development, with future releases planned to include additional participants and expanded analysis pipelines and processed data derivatives.