Department of Radiation Oncology, Kaohsiung Chang Gung Memorial Hospital, Chang Gung University College of Medicine, No. 123, Dapei Rd., Niaosong Dist., Kaohsiung City 833, Taiwan
Dr. Yu-Jie Huang
Department of Radiation Oncology, Kaohsiung Chang Gung Memorial Hospital, Chang Gung University College of Medicine, No. 123, Dapei Rd., Niaosong Dist., Kaohsiung City 833, Taiwan
To identify pretreatment carcinoembryonic antigen (CEA) levels as a risk factor for para-aortic lymph node (PALN) recurrence following concurrent chemoradiotherapy (CCRT) for cervical cancer.
Tumor vasculature abnormality creates a microenvironment that is not suitable for anti-tumor immune response and thereby induces resistance to immunotherapy. Remodeling of dysfunctional tumor blood vessels by anti-angiogenic approaches, known as vascular normalization, reshapes the tumor microenvironment toward an immune-favorable one and improves the effectiveness of immunotherapy. The tumor vasculature serves as a potential pharmacological target with the capacity of promoting an anti-tumor immune response. In this review, the molecular mechanisms involved in tumor vascular microenvironment-modulated immune reactions are summarized. In addition, the evidence of pre-clinical and clinical studies for the combined targeting of pro-angiogenic signaling and immune checkpoint molecules with therapeutic potential are highlighted. The heterogeneity of endothelial cells in tumors that regulate tissue-specific immune responses is also discussed. The crosstalk between tumor endothelial cells and immune cells in individual tissues is postulated to have a unique molecular signature and may be considered as a potential target for the development of new immunotherapeutic approaches.
To scrutinize the pretreatment prognosticators on survival and late toxicities in a homogenous cohort of nasopharyngeal carcinoma (NPC) patients treated by simultaneous integrated boost intensity-modulated radiation therapy (SIB-IMRT). A total of 219 non-distant metastatic NPC patients consecutively treated by SIB-IMRT at a single institute were collected. The pretreatment factors including the socio-demographic variables, TNM stages, gross tumor volume (GTV), Epstein-Barr virus (EBV)-DNA, and hematologic inflammatory markers were analyzed. Cox model was used to screen the prognostic factors of late toxicities and four survival outcomes including locoregional relapse-free survival (LRRFS), distant metastasis-free survival (DMFS), failure-free survival (FFS), and overall survival (OS). Statistically significant inter-correlations were observed between the values of EBV-DNA, some hematologic inflammatory markers, GTV, and N classification. The 5-year LRRFS, DMFS, FFS, and OS rates were 87.9%, 89.4%, 79.4%, and 81.3%, respectively. Multivariate analysis revealed that advanced N classification (N2–3 vs. N0–1) remained the only significant negative prognosticator for all the four survival outcomes. An increased monocyte percentage and a decreased lymphocyte-to-monocyte ratio were significantly associated with poorer FFS and OS, respectively. Larger GTV was observed to be predictive of poorer LRRFS. Patients with T3–4 (HR: 3.5, 95% CI: 1.0–12.1, p = 0.048) or higher GTV (HR: 1.006, 95% CI: 1.001–1.011, p = 0.027) were associated with higher incidence of radiation neuropathy. N classification remains the most significant survival predictor for NPC patients treated by SIB-IMRT after adjusting these biomarkers. GTV impacts not only on locoregional control but also radiation neuropathy.
This study developed an automated temperature measurement and monitoring platform for dairy cattle. The platform used the YOLO V3-tiny (you only look once, YOLO) deep learning algorithm to identify and classify dairy cattle images. The system included a total of three layers of YOLO V3-tiny identification: (1) dairy cow body; (2) individual number (identity, ID); (3) thermal image of eye socket identification. We recorded each cow’s individual number and body temperature data after the three layers of identification, and carried out long-term body temperature tracking. The average prediction score of the recognition rate was 96%, and the accuracy was 90.0%. The thermal image of eye socket recognition rate was >99%. The area under the receiver operating characteristic curves (AUC) index of the prediction model was 0.813 (0.717–0.910). This showed that the model had excellent predictive ability. This system provides a rapid and convenient temperature measurement solution for ranchers. The improvement in dairy cattle image recognition can be optimized by collecting more image data. In the future, this platform is expected to replace the traditional solution of intrusive radio-frequency identification for individual recognition.
Using deep learning models to analyze patients with intracranial tumors, to study the image segmentation and standard results by clinical depiction complications of cerebral edema after receiving radiotherapy. In this study, patients with intracranial tumors receiving computer knife (CyberKnife M6) stereotactic radiosurgery were followed using the treatment planning system (MultiPlan 5.1.3) to obtain before-treatment and four-month follow-up images of patients. The TensorFlow platform was used as the core architecture for training neural networks. Supervised learning was used to build labels for the cerebral edema dataset by using Mask region-based convolutional neural networks (R-CNN), and region growing algorithms. The three evaluation coefficients DICE, Jaccard (intersection over union, IoU), and volumetric overlap error (VOE) were used to analyze and calculate the algorithms in the image collection for cerebral edema image segmentation and the standard as described by the oncologists. When DICE and IoU indices were 1, and the VOE index was 0, the results were identical to those described by the clinician.The study found using the Mask R-CNN model in the segmentation of cerebral edema, the DICE index was 0.88, the IoU index was 0.79, and the VOE index was 2.0. The DICE, IoU, and VOE indices using region growing were 0.77, 0.64, and 3.2, respectively. Using the evaluated index, the Mask R-CNN model had the best segmentation effect. This method can be implemented in the clinical workflow in the future to achieve good complication segmentation and provide clinical evaluation and guidance suggestions.