In this paper, we introduce XGLUE, a new benchmark dataset that can be used to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora and evaluate their performance across a diverse set of cross-lingual tasks. Comparing to GLUE (Wang et al., 2019), which is labeled in English for natural language understanding tasks only, XGLUE has two main advantages: (1) it provides 11 diversified tasks that cover both natural language understanding and generation scenarios; (2) for each task, it provides labeled data in multiple languages. We extend a recent cross-lingual pre-trained model Unicoder to cover both understanding and generation tasks, which is evaluated on XGLUE as a strong baseline. We also evaluate the base versions (12-layer) of Multilingual BERT, XLM and XLM-R for comparison. 1

Purpose To develop an automated magnetic resonance imaging (MRI) parotid segmentation method to monitor radiation-induced parotid gland changes in patients after head and neck radiation therapy (RT). Methods and Materials The proposed method combines the atlas registration method, which captures the global variation of anatomy, with a machine learning technology, which captures the local statistical features, to automatically segment the parotid glands from the MRIs. The segmentation method consists of 3 major steps. First, an atlas (pre-RT MRI and manually contoured parotid gland mask) is built for each patient. A hybrid deformable image registration is used to map the pre-RT MRI to the post-RT MRI, and the transformation is applied to the pre-RT parotid volume. Second, the kernel support vector machine (SVM) is trained with the subject-specific atlas pair consisting of multiple features (intensity, gradient, and others) from the aligned pre-RT MRI and the transformed parotid volume. Third, the well-trained kernel SVM is used to differentiate the parotid from surrounding tissues in the post-RT MRIs by statistically matching multiple texture features. A longitudinal study of 15 patients undergoing head and neck RT was conducted: baseline MRI was acquired prior to RT, and the post-RT MRIs were acquired at 3-, 6-, and 12-month follow-up examinations. The resulting segmentations were compared with the physicians' manual contours. Results Successful parotid segmentation was achieved for all 15 patients (42 post-RT MRIs). The average percentage of volume differences between the automated segmentations and those of the physicians' manual contours were 7.98% for the left parotid and 8.12% for the right parotid. The average volume overlap was 91.1% ± 1.6% for the left parotid and 90.5% ± 2.4% for the right parotid. The parotid gland volume reduction at follow-up was 25% at 3 months, 27% at 6 months, and 16% at 12 months. Conclusions We have validated our automated parotid segmentation algorithm in a longitudinal study. This segmentation method may be useful in future studies to address radiation-induced xerostomia in head and neck radiation therapy.

Background and purposesThis study compared VMAT and IMRT plans for intact breast radiotherapy for left sided breast cancer and evaluated the irradiated dose of planning target volume and OARs, especially focusing on heart and coronary artery.Materials and methodsEleven patients with left sided breast cancer whose breast was relatively smaller (the mean volumes is 296 cc) treated with breast-conserving surgery were prescribed radiotherapy of 50 Gy in 25 fractions using two or four-field step and shoot IMRT (2 or 4-F IMRT), and one or two-arc VMAT (1 or 2-arc VMAT). The 10 Gy electron boost to the tumor bed after delivery of 50 Gy was not included in the analysis. Multiple planning parameters for the PTV and the PRV-OARs were measured and analyzed.ResultsTreatment plans generated using VMAT had better PTV homogeneity than the IMRT plans. For the PRV-OARs, the 1-arc VMAT had significantly higher Dmean and V5 for left lung and heart, and showed worse Dmean for liver, esophagus, spinal cord, contralateral lung and breast. In contrast, the 2-arc VMAT and the 2-F or 4-F IMRT plans showed better results for the PRV-OARs than the 1-arc VMAT. However, for the heart and coronary artery, the 1-arc VMAT showed better V20 and V40 compared with the other plans. Moreover, the 2 F-IMRT had specially advantage on V5 and V20 for heart and V5 for coronary arteries, the 2-F IMRT also showed a greater MU and treatment times. Using the table of quality score to evaluate the plans, we found that 2-F IMRT had the highest scores of 13, followed by the 2-arc VMAT plan (10 points) and 1-arc VMAT plan (8 points), and finally the 4-F IMRT plan (6 points). Moreover, when a dose comparison for heart minus coronary artery was calculated, the V20 and V40 for the rest of heart in all plans were very small and closed, indicating the dose to the coronary artery contributed dramatically to the high dose volumes for the entire heart.ConclusionsCompared to other plans, the 2-F IMRT plan with fewer monitor units and shorter delivery time is an appropriate technique for left sided breast cancer, which achieved good PTV coverage and sparing of organs at risk besides for the heart and coronary artery.

No abstract