CLiP, catheter and line position dataset

Multi-task learning framework to predict the status of central venous catheter based on radiographs

Hospital patients can have catheters and lines inserted during the course of their admission to give medicines for the treatment of medical issues, especially the central venous catheter (CVC). However, malposition of CVC will lead to many complications, even death. Clinicians always detect the status of the catheter to avoid the above issues via X-ray images. To reduce the workload of clinicians and improve the efficiency of CVC status detection, a multi-task learning framework for catheter status classification based on the convolutional neural network (CNN) is proposed. The proposed framework contains three significant components which are modified HRNet, multi-task supervision including segmentation supervision and heatmap regression supervision as well as classification branch. The modified HRNet maintaining high-resolution features from the start to the end can ensure to generation of high-quality assisted information for classification. The multi-task supervision can assist in alleviating the presence of other line-like structures such as other tubes and anatomical structures shown in the X-ray image. Furthermore, during the inference, this module is also considered as an interpretation interface to show where the framework pays attention to. Eventually, the classification branch is proposed to predict the class of the status of the catheter. A public CVC dataset is utilized to evaluate the performance of the proposed method, which gains 0.823 AUC (Area under the ROC curve) and 82.6% accuracy in the test dataset. Compared with two state-of-the-art methods (ATCM method and EDMC method), the proposed method can perform best.

High-resolution feature based central venous catheter tip detection network in X-ray images

Hospital patients can have catheters and lines inserted during the course of their admission to give medicines for the treatment of medical issues, especially the central venous catheter (CVC). However, malposition of CVC will lead to many complications, even death. Clinicians always detect the malposition based on position detection of CVC tip via X-ray images. To reduce the workload of the clinicians and the percentage of malposition occurrence, we propose an automatic catheter tip detection framework based on a convolutional neural network (CNN). The proposed framework contains three essential components which are modified HRNet, segmentation supervision module, and deconvolution module. The modified HRNet can retain high-resolution features from start to end, ensuring the maintenance of precise information from the X-ray images. The segmentation supervision module can alleviate the presence of other line-like structures such as the skeleton as well as other tubes and catheters used for treatment. In addition, the deconvolution module can further increase the feature resolution on the top of the highest-resolution feature maps in the modified HRNet to get a higher-resolution heatmap of the catheter tip. A public CVC Dataset is utilized to evaluate the performance of the proposed framework. The results show that the proposed algorithm offering a mean Pixel Error of 4.11 outperforms three comparative methods (Ma's method, SRPE method, and LCM method). It is demonstrated to be a promising solution to precisely detect the tip position of the catheter in X-ray images.

Performance of Multiple Pretrained BERT Models to Automate and Accelerate Data Annotation for Large Datasets

PURPOSE

To develop and evaluate domain-specific and pretrained bidirectional encoder representations from transformers (BERT) models in a transfer learning task on varying training dataset sizes to annotate a larger overall dataset.

MATERIALS AND METHODS

The authors retrospectively reviewed 69 095 anonymized adult chest radiograph reports (reports dated April 2020-March 2021). From the overall cohort, 1004 reports were randomly selected and labeled for the presence or absence of each of the following devices: endotracheal tube (ETT), enterogastric tube (NGT, or Dobhoff tube), central venous catheter (CVC), and Swan-Ganz catheter (SGC). Pretrained transformer models (BERT, PubMedBERT, DistilBERT, RoBERTa, and DeBERTa) were trained, validated, and tested on 60%, 20%, and 20%, respectively, of these reports through fivefold cross-validation. Additional training involved varying dataset sizes with 5%, 10%, 15%, 20%, and 40% of the 1004 reports. The best-performing epochs were used to assess area under the receiver operating characteristic curve (AUC) and determine run time on the overall dataset.

RESULTS

The highest average AUCs from fivefold cross-validation were 0.996 for ETT (RoBERTa), 0.994 for NGT (RoBERTa), 0.991 for CVC (PubMedBERT), and 0.98 for SGC (PubMedBERT). DeBERTa demonstrated the highest AUC for each support device trained on 5% of the training set. PubMedBERT showed a higher AUC with a decreasing training set size compared with BERT. Training and validation time was shortest for DistilBERT at 3 minutes 39 seconds on the annotated cohort.

CONCLUSION

Pretrained and domain-specific transformer models required small training datasets and short training times to create a highly accurate final model that expedites autonomous annotation of large datasets.Keywords: Informatics, Named Entity Recognition, Transfer Learning Supplemental material is available for this article. ©RSNA, 2022See also the commentary by Zech in this issue.