Search

Background To predict treatment response and 2 years overall survival (OS) of radio-chemotherapy in patients with esophageal cancer (EC) by radiomics based on the computed tomography (CT) images. Methods This study retrospectively collected 171 nonsurgical EC patients treated with radiochemotherapy from Jan 2010 to Jan 2019. 80 patients were randomly divided into training (n = 64) and validation (n = 16) cohorts to predict the radiochemotherapy response. The models predicting treatment response were established by Lasso and logistic regression. A total of 156 patients were allocated into the training cohort (n = 110), validation cohort (n = 23) and test set (n = 23) to predict 2-year OS. The models predicting 2-year OS were established by the Lasso Cox model and Cox proportional hazards model. Results To predict the radiochemotherapy response, WFK as a radiomics feature, and clinical stages and clinical M stages (cM) as clinical features were selected to construct the clinical-radiomics model, achieving 0.78 and 0.75 AUC (area under the curve) in the training and validation sets, respectively. Furthermore, radiomics features called WFI and WGI combined with clinical features (smoking index, pathological types, cM) were the optimal predictors to predict 2-year OS. The AUC values of the clinical-radiomics model were 0.71 and 0.70 in the training set and validation set, respectively. Conclusions This study demonstrated that planning CT-based radiomics showed the predictability of the radiochemotherapy response and 2-year OS in nonsurgical esophageal carcinoma. The predictive results prior to treatment have the potential to assist physicians in choosing the optimal therapeutic strategy to prolong overall survival.

We evaluated whether radiomic features extracted from planning computed tomography (CT) scans predict clinical end points in patients with locally advanced cervical cancer (LACC) undergoing intensity-modulated radiation therapy and brachytherapy.A retrospective cohort study.Xiangya Hospital of Central South University, Changsha, Hunan, China.Two hundred and fifty-seven LACC patients who were treated with intensity-modulated radiotherapy from 2014 to 2017.Patients were allocated into the training/validation sets (3:1 ratio) using proportional random sampling, resulting in the same proportion of groups in the two sets. We extracted 254 radiomic features from each of the gross target volume, pelvis and sacral vertebrae. The sequentially backward elimination support vector machine algorithm was used for feature selection and end point prediction.Clinical end points include tumour complete response (CR), 5-year overall survival (OS), anaemia, and leucopenia.A combination of ten clinicopathological parameters and 34 radiomic features performed best for predicting CR (validation balanced accuracy: 80.8%). The validation balanced accuracy of 54 radiomic features was 85.8% for OS, and their scores can stratify patients into the low-risk and high-risk groups (5-year OS: 95.5% versus 36.4%, p 0.001). The clinical and radiomic models were also predictive of anaemia and leucopenia (validation balanced accuracies: 71.0% and 69.9%).This study demonstrated that combining clinicopathological parameters with CT-based radiomics may have value for predicting clinical end points in LACC. If validated, this model may guide therapeutic strategy to optimise the effectiveness and minimise toxicity or treatment for LACC.

Objectives: We evaluated radiotherapy planning CT-based radiomics for predicting clinical endpoints [tumor complete response (CR), 5-year overall survival (OS), hypohemoglobin, and leucopenia] after intensity-modulated radiation therapy (IMRT) in locally advanced cervical cancer (LACC). Methods: This study retrospectively collected 257 LACC patients treated with IMRT from 2014 to 2017. Patients were allocated into the training/validation sets (3:1 ratio) using proportional random sampling, resulting in the same proportion of groups in the two sets. We extracted 254 radiomic features from each of the gross target volume (GTV), pelvis, and sacral vertebrae in planning CT images. The sequentially backward elimination support vector machine algorithm was used for feature selection and endpoint prediction. Model performance was evaluated using area under the curve (AUC). Results: A combination of 10 clinicopathological parameters and 34 radiomic features achieved the best performance for predicting CR [validation balanced accuracy: 80.79%]. For OS, 54 radiomic features showed good prediction accuracy [validation balanced accuracy: 85.75%], and the threshold value of their scores can stratify patients into the low-risk and high-risk groups (P

Entity relation extraction technology can be used to extract entities and relations from medical literature, and automatically establish professional mapping knowledge domains. The classical text classification model, convolutional neural networks for sentence classification (TEXTCNN), has been shown to have good classification performance, but also has a long-distance dependency problem, which is a common problem of convolutional neural networks (CNNs). Recurrent neural networks (RNN) address the long-distance dependency problem but cannot capture text features at a specific scale in the text.To solve these problems, this study sought to establish a model with a multi-scale convolutional recurrent neural network for Sentence Classification (TEXTCRNN) to address the deficiencies in the 2 neural network structures. In entity relation extraction, the entity pair is generally composed of a subject and an object, but as the subject in the entity pair of medical literature is always omitted, it is difficult to use this coding method to obtain general entity position information. Thus, we proposed a new coding method to obtain entity position information to re-establish the relationship between subject and object and complete the entity relation extraction.By comparing the benchmark neural network model and 2 typical multi-scale TEXTCRNN models, the TEXTCRNN [bidirectional long- and short-term memory (BiLSTM)] and TEXTCRNN [double-layer stacking gated recurrent unit (GRU)], the results showed that the multi-scale CRNN model had the best F1 value performance, and the TEXTCRNN (double-layer stacking GRU) was more capable of entity relation classification when the same entity word did not belong to the same entity relation.The experimental results of the entity relation extraction from

BACKGROUND: Extracting entities and their relationships from electronic medical records (EMRs) is an important research direction in the development of medical informatization. Recently, a method was proposed to transform entity relation extraction into entity recognition by using annotation rules, and then solve the problem of relation extraction by an entity recognition model. However, this method cannot deal with one-to-many entity relationship problems. METHODS: This paper combined the bidirectional long- and short-term memory-conditional random field (BiLSTM-CRF) deep learning model with an improvement of sequence annotation rules, hided relationships between entities in entity labels, then the problem of one-to-many named entity relation extraction in EMRs was transformed into entity recognition based on relation sets, and entity extraction was carried out through the entity recognition model. RESULTS: Entity extraction was achieved through the entity recognition model. The result of entity recognition was transformed into the corresponding entity relationship, thus completing the task of one-to-many entity relation extraction by the improved annotation rules, the accuracy rate of proposed method reaches 83.46%, the recall rate is 81.12%, and the value of comprehensive index F1 is 0.8227. CONCLUSIONS: Through the annotation analysis of EMRs, our experimental results show that the improved annotation rules can effectively complete the task of one-to-many medical entity relation extraction from EMRs.