Tumor Multiregional Mean Apparent Propagator (MAP) Features in Evaluating Gliomas-A Comparative Study With Diffusion Kurtosis Imaging (DKI)

The Value of Multi-directional High b-Value DWI in the Assessment of Muscular Invasion in Bladder Urothelial Carcinoma: In Comparison with VI-RADS

RATIONALE AND OBJECTIVES

To predict the muscular invasion status of bladder urothelial carcinoma (UCB) using quantitative parameters from multi-directional high b-value diffusion-weighted imaging (MDHB-DWI), and compare these parameters with the Vesical Imaging Reporting and Data System (VI-RADS).

METHODS

In this prospective study, patients with pathologically confirmed UCB were enrolled between May 2023 and May 2024. All participants underwent preoperative MRI, including MDHB-DWI and conventional MRI. The average quantitative parameter values of MDHB-DWI (diffusion kurtosis imaging [DKI], diffusion tensor imaging [DTI], mean apparent propagator [MAP] and neurite orientation dispersion and density imaging [NODDI]) and apparent diffusion coefficient (ADC) values were compared between non-muscle invasive (NMIBC) and muscle-invasive (MIBC) groups using the T-test or rank sum test. Quantitative MRI models were developed using multivariate logistic regression analyses based on significant diffusion parameters obtained from MDHB-DWI. Receiver operating characteristic (ROC) curves were plotted, and DeLong's test was applied to compare the area under the curve (AUC) of the model with that of VI-RADS.

RESULTS

A total of 76 patients with UCB (56 males; NMIBC/MIBC=51/25) were included. Axial diffusivity (AD) from DKI and mean diffusivity (MD) from DTI were identified as independent predictors for constructing a quantitative MRI model. The AUC of the model was 0.936, significantly outperforming VI-RADS (AUC=0.831) (p = 0.007).

CONCLUSION

DKI-AD and DTI-MD from MDHB-DWI demonstrate a robust ability to differentiate muscular invasion in UCB. Their combination significantly improves diagnostic efficiency compared to VI-RADS.

Super-resolution reconstruction improves multishell diffusion: using radiomics to predict adult-type diffuse glioma IDH and grade

Objectives

Multishell diffusion scanning is limited by low spatial resolution. We sought to improve the resolution of multishell diffusion images through deep learning-based super-resolution reconstruction (SR) and subsequently develop and validate a prediction model for adult-type diffuse glioma, isocitrate dehydrogenase status and grade 2/3 tumors.

Materials and methods

A simple diffusion model (DTI) and three advanced diffusion models (DKI, MAP, and NODDI) were constructed based on multishell diffusion scanning. Migration was performed with a generative adversarial network based on deep residual channel attention networks, after which images with 2x and 4x resolution improvements were generated. Radiomic features were used as inputs, and diagnostic models were subsequently constructed via multiple pipelines.

Results

This prospective study included 90 instances (median age, 54.5 years; 39 men) diagnosed with adult-type diffuse glioma. Images with both 2x- and 4x-improved resolution were visually superior to the original images, and the 2x-improved images allowed better predictions than did the 4x-improved images (P<.001). A comparison of the areas under the curve among the multiple pipeline-constructed models revealed that the advanced diffusion models did not have greater diagnostic performance than the simple diffusion model (P>.05). The NODDI model constructed with 2x-improved images had the best performance in predicting isocitrate dehydrogenase status (AUC_validation=0.877; Brier score=0.132). The MAP model constructed with the original images performed best in classifying grade 2 and grade 3 tumors (AUC_validation=0.806; Brier score=0.168).

Conclusion

SR improves the resolution of multishell diffusion images and has different advantages in achieving different goals and creating different target diffusion models.