Publications

All Publications


  • Deep-Learning for Automated Classification of Inferior Vena Cava Filter Types on Radiographs. Journal of vascular and interventional radiology : JVIR Ni, J. C., Shpanskaya, K., Han, M., Lee, E. H., Do, B. H., Kuo, W. T., Yeom, K. W., Wang, D. S. 2019

    Abstract

    PURPOSE: To demonstrate the feasibility and evaluate the performance of a deep-learning convolutional neural network (CNN) classification model for automated identification of different types of inferior vena cava (IVC) filters on radiographs.MATERIALS AND METHODS: In total, 1,375 cropped radiographic images of 14 types of IVC filters were collected from patients enrolled in a single-center IVC filter registry, with 139 images withheld as a test set and the remainder used to train and validate the classification model. Image brightness, contrast, intensity, and rotation were varied to augment the training set. A 50-layer ResNet architecture with fixed pre-trained weights was trained using a soft margin loss over 50 epochs. The final model was evaluated on the test set.RESULTS: The CNN classification model achieved a F1 score of 0.97 (0.92-0.99) for the test set overall and of 1.00 for 10 of 14 individual filter types. Of the 139 test set images, 4 (2.9%) were misidentified, all mistaken for other filter types that appear highly similar. Heat maps elucidated salient features for each filter type that the model used for class prediction.CONCLUSIONS: A CNN classification model was successfully developed to identify 14 types of IVC filters on radiographs and demonstrated high performance. Further refinement and testing of the model is necessary before potential real-world application.

    View details for DOI 10.1016/j.jvir.2019.05.026

    View details for PubMedID 31542278

  • Deep Learning-Assisted Diagnosis of Cerebral Aneurysms Using the HeadXNet Model. JAMA network open Park, A., Chute, C., Rajpurkar, P., Lou, J., Ball, R. L., Shpanskaya, K., Jabarkheel, R., Kim, L. H., McKenna, E., Tseng, J., Ni, J., Wishah, F., Wittber, F., Hong, D. S., Wilson, T. J., Halabi, S., Basu, S., Patel, B. N., Lungren, M. P., Ng, A. Y., Yeom, K. W. 2019; 2 (6): e195600

    Abstract

    Deep learning has the potential to augment clinician performance in medical imaging interpretation and reduce time to diagnosis through automated segmentation. Few studies to date have explored this topic.To develop and apply a neural network segmentation model (the HeadXNet model) capable of generating precise voxel-by-voxel predictions of intracranial aneurysms on head computed tomographic angiography (CTA) imaging to augment clinicians' intracranial aneurysm diagnostic performance.In this diagnostic study, a 3-dimensional convolutional neural network architecture was developed using a training set of 611 head CTA examinations to generate aneurysm segmentations. Segmentation outputs from this support model on a test set of 115 examinations were provided to clinicians. Between August 13, 2018, and October 4, 2018, 8 clinicians diagnosed the presence of aneurysm on the test set, both with and without model augmentation, in a crossover design using randomized order and a 14-day washout period. Head and neck examinations performed between January 3, 2003, and May 31, 2017, at a single academic medical center were used to train, validate, and test the model. Examinations positive for aneurysm had at least 1 clinically significant, nonruptured intracranial aneurysm. Examinations with hemorrhage, ruptured aneurysm, posttraumatic or infectious pseudoaneurysm, arteriovenous malformation, surgical clips, coils, catheters, or other surgical hardware were excluded. All other CTA examinations were considered controls.Sensitivity, specificity, accuracy, time, and interrater agreement were measured. Metrics for clinician performance with and without model augmentation were compared.The data set contained 818 examinations from 662 unique patients with 328 CTA examinations (40.1%) containing at least 1 intracranial aneurysm and 490 examinations (59.9%) without intracranial aneurysms. The 8 clinicians reading the test set ranged in experience from 2 to 12 years. Augmenting clinicians with artificial intelligence-produced segmentation predictions resulted in clinicians achieving statistically significant improvements in sensitivity, accuracy, and interrater agreement when compared with no augmentation. The clinicians' mean sensitivity increased by 0.059 (95% CI, 0.028-0.091; adjusted P?=?.01), mean accuracy increased by 0.038 (95% CI, 0.014-0.062; adjusted P?=?.02), and mean interrater agreement (Fleiss ?) increased by 0.060, from 0.799 to 0.859 (adjusted P?=?.05). There was no statistically significant change in mean specificity (0.016; 95% CI, -0.010 to 0.041; adjusted P?=?.16) and time to diagnosis (5.71 seconds; 95% CI, 7.22-18.63 seconds; adjusted P?=?.19).The deep learning model developed successfully detected clinically significant intracranial aneurysms on CTA. This suggests that integration of an artificial intelligence-assisted diagnostic model may augment clinician performance with dependable and accurate predictions and thereby optimize patient care.

    View details for DOI 10.1001/jamanetworkopen.2019.5600

    View details for PubMedID 31173130

  • Upper extremity tumor embolization using a transradial artery approach: technical note. Radiology case reports Zaw, T., Ni, J. C., Park, J. K., Walsworth, M. 2016; 11 (3): 190?94

    Abstract

    Transradial access is being used with increasing frequency for interventional radiology procedures and offers several key advantages, including decreased access site complications and increased patient comfort. We report the technique of using transradial access to perform preoperative embolization of a humeral renal cell carcinoma metastasis and pathologic fracture. A transradial approach for performing humeral preoperative tumor embolization has not been previously reported, to our knowledge. In the appropriately selected patient, this approach may be safely used to perform upper extremity embolization.

    View details for DOI 10.1016/j.radcr.2016.05.018

    View details for PubMedID 27594948

    View details for PubMedCentralID PMC4996924

  • System architecture for a magnetically guided endovascular microcatheter BIOMEDICAL MICRODEVICES Sincic, R. S., Caton, C. J., Lillaney, P., Goodfriend, S., Ni, J., Martin, A. J., Losey, A. D., Shah, N., Yee, E. J., Evans, L., Malba, V., Bernhardt, A. F., Settecase, F., Cooke, D. L., Saeed, M., Wilson, M. W., Hetts, S. W. 2014; 16 (1): 97-106

    Abstract

    Magnetic resonance imaging (MRI) guided minimally invasive interventions are an emerging technology. We developed a microcatheter that utilizes micro-electromagnets manufactured on the distal tip, in combination with the magnetic field of a MRI scanner, to perform microcatheter steering during endovascular surgery. The aim of this study was to evaluate a user control system for operating, steering and monitoring this magnetically guided microcatheter. The magnetically-assisted remote control (MARC) microcatheter was magnetically steered within a phantom in the bore of a 1.5 T MRI scanner. Controls mounted in an interventional MRI suite, along with a graphical user interface at the MRI console, were developed with communication enabled via MRI compatible hardware modules. Microcatheter tip deflection measurements were performed by evaluating MRI steady-state free precession (SSFP) images and compared to models derived from magnetic moment interactions and composite beam mechanics. The magnitude and direction of microcatheter deflections were controlled with user hand, foot, and software controls. Data from two different techniques for measuring the microcatheter tip location within a 1.5 T MRI scanner showed correlation of magnetic deflections to our model (R(2): 0.88) with a region of linear response (R(2): 0.98). Image processing tools were successful in autolocating the in vivo microcatheter tip within MRI SSFP images. Our system showed good correlation to response curves and introduced low amounts of MRI noise artifact. The center of the artifact created by the energized microcatheter solenoid was a reliable marker for determining the degree of microcatheter deflection and auto-locating the in vivo microcatheter tip.

    View details for DOI 10.1007/s10544-013-9809-1

    View details for Web of Science ID 000331621600010

    View details for PubMedID 24132857

    View details for PubMedCentralID PMC3945604

Footer Links:

Stanford Medicine Resources: