-
Categories
-
Pharmaceutical Intermediates
-
Active Pharmaceutical Ingredients
-
Food Additives
- Industrial Coatings
- Agrochemicals
- Dyes and Pigments
- Surfactant
- Flavors and Fragrances
- Chemical Reagents
- Catalyst and Auxiliary
- Natural Products
- Inorganic Chemistry
-
Organic Chemistry
-
Biochemical Engineering
- Analytical Chemistry
- Cosmetic Ingredient
-
Pharmaceutical Intermediates
Promotion
ECHEMI Mall
Wholesale
Weekly Price
Exhibition
News
-
Trade Service
Dynamic-enhanced (DCE) MRI can be used to grade astrocytoma as well as to identify pseudo-progressive tumors
.
More specifically, pharmacokinetic (PK) parameters derived from DCE MRI, such as volume transfer constant (K trans ), extravascular extracellular space fraction or extravascular extracellular space volume per unit tissue (V e ), and plasma Interstitial volume fraction (V p ) can be used to evaluate tumor angiogenesis (V p ) and microcirculation permeability (K trans and Ve ), and it can also characterize tumors through dynamic changes in signal intensity (SI)
Dynamic-enhanced (DCE) MRI can be used to grade astrocytoma as well as to identify pseudo-progressive tumors
However, the AIF (AIF DCE DCE ) of DCE MRI is extremely susceptible to noise, which reduces the reliability of PK parameters .
In the field of radioomics, the combination of diffusion and perfusion MRI can improve the diagnostic performance of predictive models such as survival prediction and false progression of glioblastoma .
However, the radiomic characteristics obtained from DCE perfusion MRI vary with AIF, so the reliability is low .
At this stage, a neural network model, the adversarial network performs well in various image conversion tasks .
Studies have shown that the adversarial network improves the performance and stability of a number of tasks related to medical imaging .
diagnosis
Recently, a study published in the journal Radiology developed a deep learning model to improve the reliability of AIF in DCE MRI, and verified the reliability and diagnostic performance of PK parameters in astrocytoma grading through improved AIF.
.
.
This retrospective study included 386 patients diagnosed with astrocytoma by histopathological analysis from April 2010 to January 2018 (mean age 52 years ± 16 years [standard deviation]; 226 males) Each patient received dynamic magnetic susceptibility contrast (DSC) enhancement and DCE MRI before surgery
.
Obtain AIF from DSC-enhanced MRI (AIF DSC ), and measure AIF on DCE MRI (AIF DCE )
This retrospective study included 386 patients diagnosed with astrocytoma by histopathological analysis from April 2010 to January 2018 (mean age 52 years ± 16 years [standard deviation]; 226 males) Each patient received dynamic magnetic susceptibility contrast (DSC) enhancement and DCE MRI before surgery
In astrocytoma grading, the PK parameters derived from AIF generated DSC generated DSC and DSC have higher AUC than those derived from AIF DCE DCE (average K trans trans , 0.
88 [95% confidence interval {CI}: 0.
81, 0.
93] vs 0.
Table 1 The diagnostic performance of dynamic magnetic resonance enhanced pharmacokinetic parameters in distinguishing high-grade and low-grade astrocytomas
.
.
Figure 1 Representative K trans (left), Ve (middle) and Vp (right) derived from (A) AIF DCE , (B) AIFDSC and (C) AIF generated DSC .
Each row represents three different AIFs, and each column represents three different PK parameter maps .
It should be noted that the PK parameter diagram derived from AIF generated DSC (C) is almost the same as the PK parameter diagram derived from AIF DSC (B) .
The color bars indicate the highest and lowest values of each PK parameter in this case .
Each row represents three different AIFs, and each column represents three different PK parameter maps .
It should be noted that the PK parameter diagram derived from AIF generated DSC (C) is almost the same as the PK parameter diagram derived from AIF DSC (B) .
The color bars indicate the highest and lowest values of each PK parameter in this case .
Figure 1 Representative K trans trans (left), Ve (middle) and Vp (right) derived from (A) AIF DCE DCE , (B) AIFDSC and (C) AIF generated DSC generated DSC .
Each row represents three different AIFs, and each column represents three different PK parameter maps .
It should be noted that the PK parameter diagram derived from AIF generated DSC generated DSC (C) is almost the same as the PK parameter diagram derived from AIF DSC DSC (B) .
The color bars indicate the highest and lowest values of each PK parameter in this case.
This research has developed a deep learning algorithm that improves the reliability and diagnostic performance of dynamic contrast-enhanced MRI pharmacokinetic parameters, and verifies the effectiveness of the algorithm as a clinical application for astrocytoma grading It provides technical support for accurately formulating treatment plans and predicting patient prognosis before clinical surgery, and opens the way for more complex related research such as predicting the false progression of glioma and gene mutations
.
.
Original source:
Original source:Kyu Sung Choi , Sung-Hye You , Yoseob Han , et al.
Improving the Reliability of Pharmacokinetic Parameters at Dynamic Contrast-enhanced MRI in Astrocytomas: A Deep Learning Approach .
DOI: 10.
1148/radiol.
2020192763Sung Choi kyu , Sung-Hye by You , Yoseob Han , et Al.
Improving the Parameters AT.
Pharmacokinetic The Reliability of the Dynamic Contrast-Enhanced Astrocytomas in the MRI: A Deep Learning Approach .
The DOI: 10.
1148 / radiol.
2020192763 10.
1148 / radiol.
2020192763 in this message
