Deformable multi-modal medical image registration aligns the anatomical structures of different modalities to the same coordinate system through a spatial transformation. Due to the difficulties of collecting ground-truth registration labels, existing methods often adopt the unsupervised multi-modal image registration setting. However, it is hard to design satisfactory metrics to measure the similarity of multi-modal images, which heavily limits the multi-modal registration performance. Moreover, due to the contrast difference of the same organ in multi-modal images, it is difficult to extract and fuse the representations of different modal images. To address the above issues, we propose a novel unsupervised multi-modal adversarial registration framework that takes advantage of image-to-image translation to translate the medical image from one modality to another. In this way, we are able to use the well-defined uni-modal metrics to better train the models. Inside our framework, we propose two improvements to promote accurate registration. First, to avoid the translation network learning spatial deformation, we propose a geometry-consistent training scheme to encourage the translation network to learn the modality mapping solely. Second, we propose a novel semi-shared multi-scale registration network that extracts features of multi-modal images effectively and predicts multi-scale registration fields in an coarse-to-fine manner to accurately register the large deformation area. Extensive experiments on brain and pelvic datasets demonstrate the superiority of the proposed method over existing methods, revealing our framework has great potential in clinical application.

The purpose of this study was to evaluate the brachial plexus (BP) dose of postmastectomy radiotherapy (PMRT) to the ipsilateral supraclavicular (ISCL) area, and report the characteristics of radiation-induced brachial plexus neuropathy (RIBPN). The BP dose of 31 patients who received adjuvant PMRT to the ISCL area and chest wall using three-dimensional conformal radiotherapy (3DCRT) and the records of 3 patients with RIBPN were retrospectively analyzed based on the standardized Radiation Therapy Oncology Group-endorsed guidelines. The total dose to the ISCL area and chest wall was 50 Gy in 25 fractions. Patients with a higher number of removed lymph nodes (RLNs) had a higher risk of RIBPN (hazard ratio [HR]: 1.189, 95% confidence interval [CI]: 1.005-1.406, p = 0.044). In 31 patients treated with 3DCRT, the mean dose to the BP without irradiation to the ISCL area was significantly less than that with irradiation to the ISCL area (0.97 ± 0.20 vs. 44.39 ± 4.13 Gy, t = 136.75, p <0.001). In the 3DCRT plans with irradiation to the ISCL area and chest wall, the maximum dose to the BP was negatively correlated with age (r = −0.40, p = 0.026), body mass index (BMI) (r = −0.44, p = 0.014), and body weight (r = −0.45, p = 0.011). Symptoms of the 3 patients with RIBPN occurred 37–65 months after radiotherapy, and included progressive upper extremity numbness, pain, and motor disturbance. After treatment, 1 patient was stable, and the other 2 patients’ symptoms worsened. The incidence of RIBPN was higher in patients with a higher number of RLNs after PMRT. The dose to the BP is primarily from irradiation of the ISCL area, and is higher in slim and young patients. Prevention should be the main focus of managing RIBPN, and the BP should be considered an organ-at-risk when designing a radiotherapy plan for the ISCL area.

Purpose: Previously, the evaluation of xerostomia depended on subjective grading systems, rather than the accurate saliva amount reduction. Our aim was to quantify acute xerostomia with reduced saliva amount, and apply radiomics, dose-volume histogram (DVH) criteria and clinical features to predict saliva amount reduction by machine learning techniques.Material and methods: Computed tomography (CT) of parotid glands, DVH, and clinical data of 52 patients were collected to extract radiomics, DVH criteria and clinical features, respectively. Firstly, radiomics, DVH criteria and clinical features were divided into 3 groups for feature selection, in order to alleviate the masking effect of the number of features in different groups. Secondly, the top features in the 3 groups composed integrated features, and features selection was performed again for integrated features. In this study, feature selection was used as a combination of eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP) to alleviate multicollinearity. Finally, 6 machine learning techniques were used for predicting saliva amount reduction. Meanwhile, top radiomics features were modeled using the same machine learning techniques for comparison.Result: 17 integrated features (10 radiomics, 4 clinical, 3 DVH criteria) were selected to predict saliva amount reduction, with a mean square error (MSE) of 0.6994 and a R²score of 0.9815. Top 17 and 10 selected radiomics features predicted saliva amount reduction, with MSE of 0.7376, 0.7519, and R²score of 0.9805, 0.9801, respectively.Conclusion: With the same number of features, integrated features (radiomics + DVH criteria + clinical) performed better than radiomics features alone. The important DVH criteria and clinical features mainly included, white blood cells (WBC), parotid_glands_Dmax, Age, parotid_glands_V15, hemoglobin (Hb), BMI and parotid_glands_V45.