Search

Objectives: To develop and validate the model for distinguishing brain abscess from cystic glioma by combining deep transfer learning (DTL) features and hand-crafted radiomics (HCR) features in conventional T1-weighted imaging (T1WI) and T2-weighted imaging (T2WI).Methods: This single-center retrospective analysis involved 188 patients with pathologically proven brain abscess (102) or cystic glioma (86). One thousand DTL and 105 HCR features were extracted from the T1WI and T2WI of the patients. Three feature selection methods and four classifiers, such as k-nearest neighbors (KNN), random forest classifier (RFC), logistic regression (LR), and support vector machine (SVM), for distinguishing brain abscess from cystic glioma were compared. The best feature combination and classifier were chosen according to the quantitative metrics including area under the curve (AUC), Youden Index, and accuracy.Results: In most cases, deep learning-based radiomics (DLR) features, i.e., DTL features combined with HCR features, contributed to a higher accuracy than HCR and DTL features alone for distinguishing brain abscesses from cystic gliomas. The AUC values of the model established, based on the DLR features in T2WI, were 0.86 (95% CI: 0.81, 0.91) in the training cohort and 0.85 (95% CI: 0.75, 0.95) in the test cohort, respectively.Conclusions: The model established with the DLR features can distinguish brain abscess from cystic glioma efficiently, providing a useful, inexpensive, convenient, and non-invasive method for differential diagnosis. This is the first time that conventional MRI radiomics is applied to identify these diseases. Also, the combination of HCR and DTL features can lead to get impressive performance.

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.