Use of BERT (Bidirectional Encoder Representations from Transformers)-Based Deep Learning Method for Extracting Evidences in Chinese Radiology Reports: Development of a Computer-Aided Liver Cancer Diagnosis Framework

Abstract

Background Liver cancer is a substantial disease burden in China. As one of the primary diagnostic tools for detecting liver cancer, dynamic contrast-enhanced computed tomography provides detailed evidences for diagnosis that are recorded in free-text radiology reports. Objective The aim of our study was to apply a deep learning model and rule-based natural language processing (NLP) method to identify evidences for liver cancer diagnosis automatically. Methods We proposed a pretrained, fine-tuned BERT (Bidirectional Encoder Representations from Transformers)-based BiLSTM-CRF (Bidirectional Long Short-Term Memory-Conditional Random Field) model to recognize the phrases of APHE (hyperintense enhancement in the arterial phase) and PDPH (hypointense in the portal and delayed phases). To identify more essential diagnostic evidences, we used the traditional rule-based NLP methods for the extraction of radiological features. APHE, PDPH, and other extracted radiological features were used to design a computer-aided liver cancer diagnosis framework by random forest. Results The BERT-BiLSTM-CRF predicted the phrases of APHE and PDPH with an F1 score of 98.40% and 90.67%, respectively. The prediction model using combined features had a higher performance (F1 score, 88.55%) than those using APHE and PDPH (84.88%) or other extracted radiological features (83.52%). APHE and PDPH were the top 2 essential features for liver cancer diagnosis. Conclusions This work was a comprehensive NLP study, wherein we identified evidences for the diagnosis of liver cancer from Chinese radiology reports, considering both clinical knowledge and radiology findings. The BERT-based deep learning method for the extraction of diagnostic evidence achieved state-of-the-art performance. The high performance proves the feasibility of the BERT-BiLSTM-CRF model in information extraction from Chinese radiology reports. The findings of our study suggest that the deep learning–based method for automatically identifying evidences for diagnosis can be extended to other types of Chinese clinical texts.

Deep Learning-Based Natural Language Processing in Radiology: The Impact of Report Complexity, Disease Prevalence, Dataset Size, and Algorithm Type on Model Performance

“…NLP has been applied in various applications in radiology to annotate texts or extract information [14][15][16]. Natural language processing has evolved from handcrafted rule-based algorithms to machine learning-based approaches and deep learning-based methods [17][18][19][20][21][22][23][24]. Deep learning is a subset of machine learning where features of the data are learned from the data by the application of multilayer neural networks [25,26].…”

Constructing High-Fidelity Phenotype Knowledge Graphs for Infectious Diseases With a Fine-Grained Semantic Information Model: Development and Usability Study

“…In recent years, machine learning, especially deep learning, has been widely used for processing medical information [ 41 - 44 ]. In this work, we also explored the potential of automatically constructing fine-grained phenotype knowledge graphs based on machine learning.…”

Patient Representation From Structured Electronic Medical Records Based on Embedding Technique: Development and Validation Study

“…The distributed embedding representations have the merits of low dimensionality and the capability for revealing the latent relationship among the represented objects [19]. Thus, the embedding-based or deep learning-based representation has been widely used in various applications, especially in the clinical NLP domains, to represent unstructured medical texts, including biomedical publications [27], clinical notes [28], and radiology reports [29][30][31]. With these representations, researchers could perform feature engineering with less expert effort and transform raw texts into low-dimensional dense vectors with clinical meanings and further identify implicit patterns in patients.…”