Show simple item record

dc.contributor.authorJackson, P
dc.contributor.authorHardcastle, N
dc.contributor.authorDawe, N
dc.contributor.authorKron, T
dc.contributor.authorHofman, MS
dc.contributor.authorHicks, RJ
dc.date.accessioned2020-12-17T04:31:58Z
dc.date.available2020-12-17T04:31:58Z
dc.date.issued2018-06-14
dc.identifier.citationJackson, P., Hardcastle, N., Dawe, N., Kron, T., Hofman, M. S. & Hicks, R. J. (2018). Deep Learning Renal Segmentation for Fully Automated Radiation Dose Estimation in Unsealed Source Therapy. FRONTIERS IN ONCOLOGY, 8 (JUN), https://doi.org/10.3389/fonc.2018.00215.
dc.identifier.issn2234-943X
dc.identifier.urihttp://hdl.handle.net/11343/255349
dc.description.abstractBackground: Convolutional neural networks (CNNs) have been shown to be powerful tools to assist with object detection and-like a human observer-may be trained based on a relatively small cohort of reference subjects. Rapid, accurate organ recognition in medical imaging permits a variety of new quantitative diagnostic techniques. In the case of therapy with targeted radionuclides, it may permit comprehensive radiation dose analysis in a manner that would often be prohibitively time-consuming using conventional methods. Methods: An automated image segmentation tool was developed based on three-dimensional CNNs to detect right and left kidney contours on non-contrast CT images. Model was trained based on 89 manually contoured cases and tested on a cohort of patients receiving therapy with 177Lu-prostate-specific membrane antigen-617 for metastatic prostate cancer. Automatically generated contours were compared with those drawn by an expert and assessed for similarity based on dice score, mean distance-to-agreement, and total segmented volume. Further, the contours were applied to voxel dose maps computed from post-treatment quantitative SPECT imaging to estimate renal radiation dose from therapy. Results: Neural network segmentation was able to identify right and left kidneys in all patients with a high degree of accuracy. The system was integrated into the hospital image database, returning contours for a selected study in approximately 90 s. Mean dice score was 0.91 and 0.86 for right and left kidneys, respectively. Poor performance was observed in three patients with cystic kidneys of which only few were included in the training data. No significant difference in mean radiation absorbed dose was observed between the manual and automated algorithms. Conclusion: Automated contouring using CNNs shows promise in providing quantitative assessment of functional SPECT and possibly PET images; in this case demonstrating comparable accuracy for radiation dose interpretation in unsealed source therapy relative to a human observer.
dc.languageEnglish
dc.publisherFRONTIERS MEDIA SA
dc.rights.urihttps://creativecommons.org/licenses/by/4.0
dc.titleDeep Learning Renal Segmentation for Fully Automated Radiation Dose Estimation in Unsealed Source Therapy
dc.typeJournal Article
dc.identifier.doi10.3389/fonc.2018.00215
melbourne.affiliation.departmentSir Peter MacCallum Department of Oncology
melbourne.affiliation.departmentSchool of Physics
melbourne.affiliation.departmentMedicine (St Vincent's)
melbourne.affiliation.facultyMedicine, Dentistry & Health Sciences
melbourne.affiliation.facultyScience
melbourne.source.titleFrontiers in Oncology
melbourne.source.volume8
melbourne.source.issueJUN
dc.rights.licenseCC BY
melbourne.elementsid1336367
melbourne.contributor.authorJackson, Price
melbourne.contributor.authorKron, Tomas
melbourne.contributor.authorHofman, Michael
melbourne.contributor.authorHicks, Rodney
melbourne.contributor.authorDawe, Edmund
melbourne.contributor.authorHardcastle, Nicholas
dc.identifier.eissn2234-943X
melbourne.accessrightsOpen Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record