Intelligent Chest X-ray Worklist Prioritization by CNNs: A Clinical Workflow Simulation

Growing radiologic workload and shortage of medical experts worldwide often lead to delayed or even unreported examinations, which poses a risk for patient's safety in case of unrecognized findings in chest radiographs (CXR). The aim was to evaluate, whether deep learning algorithms for an intelligent worklist prioritization might optimize the radiology workflow and can reduce report turnaround times (RTAT) for critical findings, instead of reporting according to the First-In-First-Out-Principle (FIFO). Furthermore, we investigated the problem of false negative prediction in the context of worklist prioritization. To assess the potential benefit of an intelligent worklist prioritization, three different workflow simulations based on our analysis were run and RTAT were compared: FIFO (non-prioritized), Prio1 (prioritized) and Prio2 (prioritized, with RTATmax.). Examination triage was performed by "ChestXCheck", a convolutional neural network, classifying eight different pathological findings ranked in descending order of urgency: pneumothorax, pleural effusion, infiltrate, congestion, atelectasis, cardiomegaly, mass and foreign object. The average RTAT for all critical findings was significantly reduced by both Prio simulations compared to the FIFO simulation (e.g. pneumothorax: 32.1 min vs. 69.7 min; p < 0.0001), while the average RTAT for normal examinations increased at the same time (69.5 min vs. 90.0 min; p < 0.0001). Both effects were slightly lower at Prio2 than at Prio1, whereas the maximum RTAT at Prio1 was substantially higher for all classes, due to individual examinations rated false negative.Our Prio2 simulation demonstrated that intelligent worklist prioritization by deep learning algorithms reduces average RTAT for critical findings in chest X-ray while maintaining a similar maximum RTAT as FIFO.

When does Bone Suppression and Lung Field Segmentation Improve Chest X-Ray Disease Classification?

Chest radiography is the most common clinical examination type. To improve the quality of patient care and to reduce workload, methods for automatic pathology classification have been developed. In this contribution we investigate the usefulness of two advanced image pre-processing techniques, initially developed for image reading by radiologists, for the performance of Deep Learning methods. First, we use bone suppression, an algorithm to artificially remove the rib cage. Secondly, we employ an automatic lung field detection to crop the image to the lung area. Furthermore, we consider the combination of both in the context of an ensemble approach. In a five-times re-sampling scheme, we use Receiver Operating Characteristic (ROC) statistics to evaluate the effect of the pre-processing approaches. Using a Convolutional Neural Network (CNN), optimized for X-ray analysis, we achieve a good performance with respect to all pathologies on average. Superior results are obtained for selected pathologies when using pre-processing, i.e. for mass the area under the ROC curve increased by 9.95%. The ensemble with pre-processed trained models yields the best overall results.

Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification

The increased availability of X-ray image archives (e.g. the ChestX-ray14 dataset from the NIH Clinical Center) has triggered a growing interest in deep learning techniques. To provide better insight into the different approaches, and their applications to chest X-ray classification, we investigate a powerful network architecture in detail: the ResNet-50. Building on prior work in this domain, we consider transfer learning with and without fine-tuning as well as the training of a dedicated X-ray network from scratch. To leverage the high spatial resolutions of X-ray data, we also include an extended ResNet-50 architecture, and a network integrating non-image data (patient age, gender and acquisition type) in the classification process. In a systematic evaluation, using 5-fold re-sampling and a multi-label loss function, we evaluate the performance of the different approaches for pathology classification by ROC statistics and analyze differences between the classifiers using rank correlation. We observe a considerable spread in the achieved performance and conclude that the X-ray-specific ResNet-50, integrating non-image data yields the best overall results.