Data-driven identification of tumor subregions based on intravoxel incoherent motion reveals association with proliferative activity

A Machine Learning Model Based on Unsupervised Clustering Multihabitat to Predict the Pathological Grading of Meningiomas

Purpose

We aim to develop and validate a machine learning model by enhanced MRI to determine the pathological grading of meningiomas with unsupervised clustering image analysis method, which are multihabitat to reflect the inherent heterogeneity of tumors.

Materials and Methods

A total of 120 patients with meningiomas confirmed by postoperative pathology were included in the study, including 60 patients with low-grade meningiomas (WHO grade I) and 60 patients with high-grade meningiomas (WHO grade II and WHO grade III). All patients underwent complete head enhanced magnetic resonance scans before surgery or any anti-tumor treatment. Enrolled patients in the group received surgical resection and obtained postoperative pathological data. The patients in the training group (84 people) and the test group (36 people) were randomly divided into two groups according to the ratio of 7 to 3. Multi-habitat features were extracted from MRI images based on enhanced T1. Machine learning method was used to model, which was used to distinguish high-grade meningioma from low-grade meningioma. At the same time, the obtained machine learning model was calibrated and evaluated.

Results

In patients with low-grade meningioma and high-grade meningioma, we found significant differences in Silhouette coefficient (P<0.05). In the machine learning model, the area under the curve was 0.838 in the training group (sensitivity, 67.65%; specificity, 88.82%) and 0.73 in the test group (sensitivity, 69.05%; specificity, 71.43%). After the analysis of calibration curve and decision curve analysis, the model had shown the potential of great application value.

Conclusions

Multi-habitat analysis based on enhanced MRI (T1) could accurately predict the pathological grading of meningiomas. This unsupervised image-based method could reflect the direct heterogeneity between high-grade meningiomas and low-grade meningiomas, which is of great significance for patients' treatment and prevention of recurrence.

VERDICT MRI for radiation treatment response assessment in neuroendocrine tumors

Noninvasive methods to study changes in tumor microstructure enable early assessment of treatment response and thus facilitate personalized treatment. The aim of this study was to evaluate the diffusion MRI model, Vascular, Extracellular and Restricted Diffusion for Cytometry in Tumors (VERDICT), for early response assessment to external radiation treatment and to compare the results with those of more studied sets of parameters derived from diffusion-weighted MRI data. Mice xenografted with human small intestine tumors were treated with external radiation treatment, and diffusion MRI experiments were performed on the day before and up to 2 weeks after treatment. The diffusion models VERDICT, ADC, IVIM, and DKI were fitted to MRI data, and the treatment response of each tumor was calculated based on pretreatment tumor growth and post-treatment tumor volume regression. Linear regression and correlation analysis were used to evaluate each model and their respective parameters for explaining the treatment response. VERDICT analysis showed significant changes from day -1 to day 3 for the intracellular and extracellular volume fraction, as well as the cell radius index (p < 0.05; Wilcoxon signed-rank test). The strongest correlation between the diffusion model parameters and the tumor treatment response was seen for the ADC, kurtosis-corrected diffusion coefficient, and intracellular volume fraction on day 3 (τ = 0.47, 0.52, and -0.49, respectively, p < 0.05; Kendall rank correlation coefficient). Of all the tested models, VERDICT held the strongest explanatory value for the tumor treatment response on day 3 (R²  = 0.75, p < 0.01; linear regression). In conclusion, VERDICT has potential for early assessment of external radiation treatment and may provide further insights into the underlying biological effects of radiation on tumor tissue. In addition, the results suggest that the time window for assessment of treatment response using dMRI may be narrow.

Perfusion-driven Intravoxel Incoherent Motion (IVIM) MRI in Oncology: Applications, Challenges, and Future Trends

Recent developments in MR hardware and software have allowed a surge of interest in intravoxel incoherent motion (IVIM) MRI in oncology. Beyond diffusion-weighted imaging (and the standard apparent diffusion coefficient mapping most commonly used clinically), IVIM provides information on tissue microcirculation without the need for contrast agents. In oncology, perfusion-driven IVIM MRI has already shown its potential for the differential diagnosis of malignant and benign tumors, as well as for detecting prognostic biomarkers and treatment monitoring. Current developments in IVIM data processing, and its use as a method of scanning patients who cannot receive contrast agents, are expected to increase further utilization. This paper reviews the current applications, challenges, and future trends of perfusion-driven IVIM in oncology.

Data-driven identification of tumor subregions based on intravoxel incoherent motion reveals association with proliferative activity

PURPOSE

Intravoxel incoherent motion (IVIM) analysis gives information on tissue diffusion and perfusion and may thus have a potential for e.g. tumor tissue characterization. This work aims to study if clustering based on IVIM parameter maps can identify tumor subregions, and to assess the relevance of obtained subregions by histological analysis.

METHODS

Fourteen mice with human neuroendocrine tumors were examined with diffusion-weighted imaging to obtain IVIM parameter maps. Gaussian mixture models with IVIM maps from all tumors as input were used to partition voxels into k clusters, where k = 2 was chosen for further analysis based on goodness of fit. Clustering was performed with and without the perfusion-related IVIM parameter D * , and with and without including spatial information. The validity of the clustering was assessed by comparison with corresponding histologically stained tumor sections. A Ki-67-based index quantifying the degree of tumor proliferation was considered appropriate for the comparison based on the obtained cluster characteristics.

RESULTS

The clustering resulted in one class with low diffusion and high perfusion and another with slightly higher diffusion and low perfusion. Strong agreement was found between tumor subregions identified by clustering and subregions identified by histological analysis, both regarding size and spatial agreement. Neither D * nor spatial information had substantial effects on the clustering results.

CONCLUSIONS

The results of this study show that IVIM parameter maps can be used to identify tumor subregions using a data-driven framework based on Gaussian mixture models. In the studied tumor model, the obtained subregions showed agreement with proliferative activity.