2021
Lee, Eung-Joo; Plishker, William; Hata, Nobuhiko; Shyn, Paul B.; Silverman, Stuart G.; Bhattacharyya, Shuvra S.; Shekhar, Raj
Rapid Quality Assessment of Nonrigid Image Registration Based on Supervised Learning Journal Article
In: JOURNAL OF DIGITAL IMAGING, vol. 34, no. 6, pp. 1376–1386, 2021, ISSN: 0897-1889, 1618-727X, (Num Pages: 11 Place: New York Publisher: Springer Web of Science ID: WOS:000706904600001).
Abstract | Links | BibTeX | Tags: HEPATECTOMY, HEPATOCELLULAR-CARCINOMA, METASTASES, Multimodality image registration, PERCUTANEOUS RADIOFREQUENCY ABLATION, PROGRESSION, Quality assessment, Registration quality metric, RESECTION, Supervised learning, VALIDATION
@article{lee_rapid_2021,
title = {Rapid Quality Assessment of Nonrigid Image Registration Based on Supervised Learning},
author = {Eung-Joo Lee and William Plishker and Nobuhiko Hata and Paul B. Shyn and Stuart G. Silverman and Shuvra S. Bhattacharyya and Raj Shekhar},
doi = {10.1007/s10278-021-00523-5},
issn = {0897-1889, 1618-727X},
year = {2021},
date = {2021-12-01},
journal = {JOURNAL OF DIGITAL IMAGING},
volume = {34},
number = {6},
pages = {1376–1386},
abstract = {When preprocedural images are overlaid on intraprocedural images, interventional procedures benefit in that more structures are revealed in intraprocedural imaging. However, image artifacts, respiratory motion, and challenging scenarios could limit the accuracy of multimodality image registration necessary before image overlay. Ensuring the accuracy of registration during interventional procedures is therefore critically important. The goal of this study was to develop a novel framework that has the ability to assess the quality (i.e., accuracy) of nonrigid multimodality image registration accurately in near real time. We constructed a solution using registration quality metrics that can be computed rapidly and combined to form a single binary assessment of image registration quality as either successful or poor. Based on expert-generated quality metrics as ground truth, we used a supervised learning method to train and test this system on existing clinical data. Using the trained quality classifier, the proposed framework identified successful image registration cases with an accuracy of 81.5%. The current implementation produced the classification result in 5.5 s, fast enough for typical interventional radiology procedures. Using supervised learning, we have shown that the described framework could enable a clinician to obtain confirmation or caution of registration results during clinical procedures.},
note = {Num Pages: 11
Place: New York
Publisher: Springer
Web of Science ID: WOS:000706904600001},
keywords = {HEPATECTOMY, HEPATOCELLULAR-CARCINOMA, METASTASES, Multimodality image registration, PERCUTANEOUS RADIOFREQUENCY ABLATION, PROGRESSION, Quality assessment, Registration quality metric, RESECTION, Supervised learning, VALIDATION},
pubstate = {published},
tppubtype = {article}
}
When preprocedural images are overlaid on intraprocedural images, interventional procedures benefit in that more structures are revealed in intraprocedural imaging. However, image artifacts, respiratory motion, and challenging scenarios could limit the accuracy of multimodality image registration necessary before image overlay. Ensuring the accuracy of registration during interventional procedures is therefore critically important. The goal of this study was to develop a novel framework that has the ability to assess the quality (i.e., accuracy) of nonrigid multimodality image registration accurately in near real time. We constructed a solution using registration quality metrics that can be computed rapidly and combined to form a single binary assessment of image registration quality as either successful or poor. Based on expert-generated quality metrics as ground truth, we used a supervised learning method to train and test this system on existing clinical data. Using the trained quality classifier, the proposed framework identified successful image registration cases with an accuracy of 81.5%. The current implementation produced the classification result in 5.5 s, fast enough for typical interventional radiology procedures. Using supervised learning, we have shown that the described framework could enable a clinician to obtain confirmation or caution of registration results during clinical procedures.