Related Experiment Video
Updated: Dec 13, 2025
Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model
Published on: April 18, 2015
Improving the Reliability of Pharmacokinetic Parameters at Dynamic Contrast-enhanced MRI in Astrocytomas: A Deep
Kyu Sung Choi1, Sung-Hye You1, Yoseob Han1
1From the Graduate School of Medical Science and Engineering, Korea Advanced Institute for Science and Technology (KAIST), Daejeon, Republic of Korea (K.S.C., B.J.); Department of Radiology, Korea University College of Medicine, Anam Hospital, Seoul, Republic of Korea (S.H.Y.); Bio Imaging and Signal Processing Laboratory, Department of Bio and Brain Engineering, Korea Advanced Institute for Science and Technology (KAIST), Daejeon, Republic of Korea (Y.H., J.C.Y.); Department of Radiology, Seoul National University Hospital, 101 Daehangno, Jongno-gu, Seoul 110-744, Republic of Korea (S.H.C.); Department of Radiology, Seoul National University College of Medicine, Seoul, Republic of Korea (S.H.C.); Center for Nanoparticle Research, Institute for Basic Science (IBS), Seoul, Republic of Korea (S.H.C.); KAIST Institute for Health Science and Technology, Korea Advanced Institute for Science and Technology (KAIST), Daejeon, Republic of Korea (B.J.); and KAIST Institute for Artificial Intelligence, Korea Advanced Institute for Science and Technology (KAIST), Daejeon, Republic of Korea (B.J.).
Abstract:
Background Pharmacokinetic (PK) parameters obtained from dynamic contrast agent-enhanced (DCE) MRI evaluates the microcirculation permeability of astrocytomas, but the unreliability from arterial input function (AIF) remains a challenge. Purpose To develop a deep learning model that improves the reliability of AIF for DCE MRI and to validate the reliability and diagnostic performance of PK parameters by using improved AIF in grading astrocytomas. Materials and Methods This retrospective study included 386 patients (mean age, 52 years ± 16 [standard deviation]; 226 men) with astrocytomas diagnosed with histopathologic analysis who underwent dynamic susceptibility contrast (DSC)-enhanced and DCE MRI preoperatively from April 2010 to January 2018. The AIF was obtained from each sequence: AIF obtained from DSC-enhanced MRI (AIFDSC) and AIF measured at DCE MRI (AIFDCE). The model was trained to translate AIFDCE into AIFDSC, and after training, outputted neural-network-generated AIF (AIFgenerated DSC) with input AIFDCE. By using the three different AIFs, volume transfer constant (Ktrans), fractional volume of extravascular extracellular space (Ve), and vascular plasma space (Vp) were averaged from the tumor areas in the DCE MRI. To validate the model, intraclass correlation coefficients and areas under the receiver operating characteristic curve (AUCs) of the PK parameters in grading astrocytomas were compared by using different AIFs. Results The AIF-generated, DSC-derived PK parameters showed higher AUCs in grading astrocytomas than those derived from AIFDCE (mean Ktrans, 0.88 [95% confidence interval {CI}: 0.81, 0.93] vs 0.72 [95% CI: 0.63, 0.79], P = .04; mean Ve, 0.87 [95% CI: 0.79, 0.92] vs 0.70 [95% CI: 0.61, 0.77], P = .049, respectively). Ktrans and Ve showed higher intraclass correlation coefficients for AIFgenerated DSC than for AIFDCE (0.91 vs 0.38, P < .001; and 0.86 vs 0.60, P < .001, respectively). In AIF analysis, baseline signal intensity (SI), maximal SI, and wash-in slope showed higher intraclass correlation coefficients with AIFgenerated DSC than AIFDCE (0.77 vs 0.29, P < .001; 0.68 vs 0.42, P = .003; and 0.66 vs 0.45, P = .01, respectively. Conclusion A deep learning algorithm improved both reliability and diagnostic performance of MRI pharmacokinetic parameters for differentiating astrocytoma grades. © RSNA, 2020 Online supplemental material is available for this article.
Insights
A deep learning model improved arterial input function (AIF) reliability for dynamic contrast-enhanced (DCE) MRI. This enhances pharmacokinetic (PK) parameter accuracy in grading astrocytomas.
Area of Science:
- Radiology
- Medical Imaging
- Artificial Intelligence in Medicine
Background:
- Pharmacokinetic (PK) parameters from dynamic contrast-enhanced (DCE) MRI assess astrocytoma microcirculation permeability.
- Arterial input function (AIF) unreliability poses a challenge for accurate PK parameter estimation.
- Improving AIF reliability is crucial for precise astrocytoma characterization.
Purpose of the Study:
- To develop a deep learning model for enhancing AIF reliability in DCE MRI.
- To validate the diagnostic performance of PK parameters using the improved AIF for astrocytoma grading.
Main Methods:
- A retrospective study included 386 astrocytoma patients undergoing both DSC-enhanced and DCE MRI.
- A deep learning model translated AIF from DCE MRI (AIFDCE) to AIF derived from DSC-enhanced MRI (AIFDSC), creating AIFgenerated DSC.
- PK parameters (Ktrans, Ve, Vp) were calculated using AIFDSC, AIFDCE, and AIFgenerated DSC for comparison.
Main Results:
- The AIF-generated PK parameters demonstrated superior diagnostic performance (higher AUCs) in grading astrocytomas compared to AIFDCE.
- Key parameters like Ktrans and Ve showed significantly higher intraclass correlation coefficients with AIFgenerated DSC than with AIFDCE.
- AIF analysis revealed improved reliability of baseline SI, maximal SI, and wash-in slope with AIFgenerated DSC.
Conclusions:
- A deep learning algorithm effectively improved the reliability and diagnostic performance of MRI-derived PK parameters.
- The enhanced PK parameters aid in differentiating astrocytoma grades more accurately.
- This approach offers a promising solution for overcoming AIF-related challenges in DCE MRI.
More Related Videos
12:50Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
Published on: April 14, 2014
04:48Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022