Accurate target volume delineation is crucial for the radiotherapy of tumors. Diffusion and perfusion magnetic resonance imaging (MRI) can provide functional information about brain tumors, and they are able to detect tumor volume and physiological changes beyond the lesions shown on conventional MRI. This review examines recent studies that utilized diffusion and perfusion MRI for tumor volume definition in radiotherapy of brain tumors, and it presents the opportunities and challenges in the integration of multimodal functional MRI into clinical practice. The results indicate that specialized and robust post-processing algorithms and tools are needed for the precise alignment of targets on the images, and comprehensive validations with more clinical data are important for the improvement of the correlation between histopathologic results and MRI parameter images.
Purpose To develop a new IMRT technique to simplify the process and improve efficiency in radiotherapy treatment planning for craniospinal irradiation (CSI) treatment. Methods Image data of 9 patients who received CSI treatment in 2012 were used, the prescription was 36Gy in 20 fractions. Two treatment plans were created for each patient, one was with the new technique called three-isocenter overlap-junction (TIOJ) IMRT and the other was with the three-isocenter jagged-junction (TIJJ) IMRT technique. The comparative study was conducted using the parameters of heterogeneity index (HI), conformity index (CI), and doses to the organs at risk (OARs). Results Comparing the TIOJ IMRT plans with the TIJJ IMRT plans, the average homogeneity index is 0.071 ± 0.003 and 0.077 ± 0.002, respectively, and the averaged conformity number is 0.80 ± 0.012 and 0.80 ± 0.009, respectively. There are no significant differences (p > 0.05). Both plans provide satisfactory sparing for the OARs. Conclusions The TIOJ IMRT technique for CSI treatment planning can create similar plans as with the TIJJ IMRT technique, but the new technique greatly simplifies the steps required to manually set field widths and boundaries and improved efficiency.
In the field of gliomas research, the broad availability of genetic and image information originated by computer technologies and the booming of biomedical publications has led to the advent of the big-data era. Machine learning methods were applied as possible approaches to speed up the data mining processes. In this article, we reviewed the present situation and future orientations of machine learning application in gliomas within the context of workflows to integrate analysis for precision cancer care. Publicly available tools or algorithms for key machine learning technologies in the literature mining for glioma clinical research were reviewed and compared. Further, the existing solutions of machine learning methods and their limitations in glioma prediction and diagnostics, such as overfitting and class imbalanced, were critically analyzed.