PURPOSE Image analysis is one of the most promising applications of artificial intelligence (AI) in health care, potentially improving prediction, diagnosis, and treatment of diseases. Although scientific advances in this area critically depend on the accessibility of large-volume and high-quality data, sharing data between institutions faces various ethical and legal constraints as well as organizational and technical obstacles. METHODS The Joint Imaging Platform (JIP) of the German Cancer Consortium (DKTK) addresses these issues by providing federated data analysis technology in a secure and compliant way. Using the JIP, medical image data remain in the originator institutions, but analysis and AI algorithms are shared and jointly used. Common standards and interfaces to local systems ensure permanent data sovereignty of participating institutions. RESULTS The JIP is established in the radiology and nuclear medicine departments of 10 university hospitals in Germany (DKTK partner sites). In multiple complementary use cases, we show that the platform fulfills all relevant requirements to serve as a foundation for multicenter medical imaging trials and research on large cohorts, including the harmonization and integration of data, interactive analysis, automatic analysis, federated machine learning, and extensibility and maintenance processes, which are elementary for the sustainability of such a platform. CONCLUSION The results demonstrate the feasibility of using the JIP as a federated data analytics platform in heterogeneous clinical information technology and software landscapes, solving an important bottleneck for the application of AI to large-scale clinical imaging data.

Background Natural Language Understanding enables automatic extraction of relevant information from clinical text data, which are acquired every day in hospitals. In 2018, the language model Bidirectional Encoder Representations from Transformers (BERT) was introduced, generating new state-of-the-art results on several downstream tasks. The National NLP Clinical Challenges (n2c2) is an initiative that strives to tackle such downstream tasks on domain-specific clinical data. In this paper, we present the results of our participation in the 2019 n2c2 and related work completed thereafter. Objective The objective of this study was to optimally leverage BERT for the task of assessing the semantic textual similarity of clinical text data. Methods We used BERT as an initial baseline and analyzed the results, which we used as a starting point to develop 3 different approaches where we (1) added additional, handcrafted sentence similarity features to the classifier token of BERT and combined the results with more features in multiple regression estimators, (2) incorporated a built-in ensembling method, M-Heads, into BERT by duplicating the regression head and applying an adapted training strategy to facilitate the focus of the heads on different input patterns of the medical sentences, and (3) developed a graph-based similarity approach for medications, which allows extrapolating similarities across known entities from the training set. The approaches were evaluated with the Pearson correlation coefficient between the predicted scores and ground truth of the official training and test dataset. Results We improved the performance of BERT on the test dataset from a Pearson correlation coefficient of 0.859 to 0.883 using a combination of the M-Heads method and the graph-based similarity approach. We also show differences between the test and training dataset and how the two datasets influenced the results. Conclusions We found that using a graph-based similarity approach has the potential to extrapolate domain specific knowledge to unseen sentences. We observed that it is easily possible to obtain deceptive results from the test dataset, especially when the distribution of the data samples is different between training and test datasets.

No abstract

Writing the conclusion section of radiology reports is essential for communicating the radiology findings and its assessment to physician in a condensed form. In this work, we employ a transformer-based Seq2Seq model for generating the conclusion section of German radiology reports. The model is initialized with the pretrained parameters of a German BERT model and fine-tuned in our downstream task on our domain data. We proposed two strategies to improve the factual correctness of the model. In the first method, next to the abstractive learning objective, we introduce an extraction learning objective to train the decoder in the model to both generate one summary sequence and extract the key findings from the source input. The second approach is to integrate the pointer mechanism into the transformer-based Seq2Seq model. The pointer network helps the Seq2Seq model to choose between generating tokens from the vocabulary or copying parts from the source input during generation. The results of the automatic and human evaluations show that the enhanced Seq2Seq model is capable of generating human-like radiology conclusions and that the improved models effectively reduce the factual errors in the generations despite the small amount of training data.