<b><i>Background:</i></b> Primary liver cancer, around 90% are hepatocellular carcinoma in China, is the fourth most common malignancy and the second leading cause of tumor-related death, thereby posing a significant threat to the life and health of the Chinese people. <b><i>Summary:</i></b> Since the publication of <i>Guidelines for Diagnosis and Treatment of Primary Liver Cancer (2017 Edition)</i> in 2018, additional high-quality evidence has emerged with relevance to the diagnosis, staging, and treatment of liver cancer in and outside China that requires the guidelines to be updated. The new edition <i>(2019 Edition)</i> was written by more than 70 experts in the field of liver cancer in China. They reflect the real-world situation in China regarding diagnosing and treating liver cancer in recent years. <b><i>Key Messages:</i></b> Most importantly, the new guidelines were endorsed and promulgated by the Bureau of Medical Administration of the National Health Commission of the People’s Republic of China in December 2019.

RT as primary therapy resulted in good outcome in early-stage disease, and the addition of CT to RT was not accompanied by an improvement in survival.

Extranodal lymphomas (ENLs) comprise about a third of all non-Hodgkin lymphomas (NHL). Radiation therapy (RT) is frequently used as either primary therapy (particularly for indolent ENL), consolidation after systemic therapy, salvage treatment, or palliation. The wide range of presentations of ENL, involving any organ in the body and the spectrum of histological sub-types, poses a challenge both for routine clinical care and for the conduct of prospective and retrospective studies. This has led to uncertainty and lack of consistency in RT approaches between centers and clinicians. Thus far there is a lack of guidelines for the use of RT in the management of ENL. This report presents an effort by the International Lymphoma Radiation Oncology Group (ILROG) to harmonize and standardize the principles of treatment of ENL, and to address the technical challenges of simulation, volume definition and treatment planning for the most frequently involved organs. Specifically, detailed recommendations for RT volumes are provided. We have applied the same modern principles of involved site radiation therapy as previously developed and published as guidelines for Hodgkin lymphoma and nodal NHL. We have adopted RT volume definitions based on the International Commission on Radiation Units and Measurements (ICRU), as has been widely adopted by the field of radiation oncology for solid tumors. Organ-specific recommendations take into account histological subtype, anatomy, the treatment intent, and other treatment modalities that may be have been used before RT.

These data suggest that DDCNN can be used to segment the CTV and OARs accurately and efficiently. It was invariant to the body size, body shape, and age of the patients. DDCNN could improve the consistency of contouring and streamline radiotherapy workflows.

Purpose: To develop a method for predicting optimal dose distributions, given the planning image and segmented anatomy, by applying deep learning techniques to a database of previously optimized and approved Intensity-modulated radiation therapy treatment plans. Methods: Eighty cases of early-stage nasopharyngeal cancer (NPC) were included in the study. Seventy cases were chosen randomly as the training set and the remaining as the test set. The inputs were the images with structures, with each target and organs at risk (OARs) assigned a unique label. The outputs were dose maps, including coarse dose maps and converted fine dose maps (FDM) from convolution. Two types of input images with structures were used in the model building. One type of input included the images (with associated structures) without manipulation. The second type of input involved modifying the image gray label with information from radiation beam geometry. ResNet101 was chosen as the deep learning network for both. The accuracy of predicted dose distributions was evaluated against the corresponding dose as used in the clinic. A global three-dimensional gamma analysis was calculated for the evaluation.Results: The proposed model trained with the two different sets of input images and structures could both predict patient-specific dose distributions accurately. For the out-of-field dose distributions, the model obtained from the input with radiation geometry performed better (dose difference in %, 4.7 AE 6.1% vs 5.5 AE 7.9%, P < 0.05). The mean Gamma pass rates of dose distributions predicted with both types of input were comparable for most OARs (P > 0.05), except for the bilateral optic nerves and the optic chiasm. Conclusions: The proposed system with radiation geometry added to the input is a promising method to generate patient-specific dose distributions for radiotherapy. It can be applied to obtain the dose distributions slice-by-slice for planning quality assurance and for guiding automated planning.