Image quality and metal artifact reduction in total hip arthroplasty CT: deep learning-based algorithm versus virtual monoenergetic imaging and orthopedic metal artifact reduction
Abstract Background To compare image quality, metal artifacts, and diagnostic confidence of conventional computed tomography (CT) images of unilateral total hip arthroplasty patients (THA) with deep learning-based metal artifact reduction (DL-MAR) to conventional CT and 130-keV monoenergetic images...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-03-01
|
| Series: | European Radiology Experimental |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s41747-024-00427-3 |
| _version_ | 1797259523725983744 |
|---|---|
| author | Mark Selles Ruud H. H. Wellenberg Derk J. Slotman Ingrid M. Nijholt Jochen A. C. van Osch Kees F. van Dijke Mario Maas Martijn F. Boomsma |
| author_facet | Mark Selles Ruud H. H. Wellenberg Derk J. Slotman Ingrid M. Nijholt Jochen A. C. van Osch Kees F. van Dijke Mario Maas Martijn F. Boomsma |
| author_sort | Mark Selles |
| collection | DOAJ |
| description | Abstract Background To compare image quality, metal artifacts, and diagnostic confidence of conventional computed tomography (CT) images of unilateral total hip arthroplasty patients (THA) with deep learning-based metal artifact reduction (DL-MAR) to conventional CT and 130-keV monoenergetic images with and without orthopedic metal artifact reduction (O-MAR). Methods Conventional CT and 130-keV monoenergetic images with and without O-MAR and DL-MAR images of 28 unilateral THA patients were reconstructed. Image quality, metal artifacts, and diagnostic confidence in bone, pelvic organs, and soft tissue adjacent to the prosthesis were jointly scored by two experienced musculoskeletal radiologists. Contrast-to-noise ratios (CNR) between bladder and fat and muscle and fat were measured. Wilcoxon signed-rank tests with Holm-Bonferroni correction were used. Results Significantly higher image quality, higher diagnostic confidence, and less severe metal artifacts were observed on DL-MAR and images with O-MAR compared to images without O-MAR (p < 0.001 for all comparisons). Higher image quality, higher diagnostic confidence for bone and soft tissue adjacent to the prosthesis, and less severe metal artifacts were observed on DL-MAR when compared to conventional images and 130-keV monoenergetic images with O-MAR (p ≤ 0.014). CNRs were higher for DL-MAR and images with O-MAR compared to images without O-MAR (p < 0.001). Higher CNRs were observed on DL-MAR images compared to conventional images and 130-keV monoenergetic images with O-MAR (p ≤ 0.010). Conclusions DL-MAR showed higher image quality, diagnostic confidence, and superior metal artifact reduction compared to conventional CT images and 130-keV monoenergetic images with and without O-MAR in unilateral THA patients. Relevance statement DL-MAR resulted into improved image quality, stronger reduction of metal artifacts, and improved diagnostic confidence compared to conventional and virtual monoenergetic images with and without metal artifact reduction, bringing DL-based metal artifact reduction closer to clinical application. Key points • Metal artifacts introduced by total hip arthroplasty hamper radiologic assessment on CT. • A deep-learning algorithm (DL-MAR) was compared to dual-layer CT images with O-MAR. • DL-MAR showed best image quality and diagnostic confidence. • Highest contrast-to-noise ratios were observed on the DL-MAR images. Graphical Abstract |
| first_indexed | 2024-04-24T23:10:47Z |
| format | Article |
| id | doaj.art-b7fb379f726a41a4b3351c1a0dbe1821 |
| institution | Directory Open Access Journal |
| issn | 2509-9280 |
| language | English |
| last_indexed | 2024-04-24T23:10:47Z |
| publishDate | 2024-03-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Radiology Experimental |
| spelling | doaj.art-b7fb379f726a41a4b3351c1a0dbe18212024-03-17T12:14:04ZengSpringerOpenEuropean Radiology Experimental2509-92802024-03-018111110.1186/s41747-024-00427-3Image quality and metal artifact reduction in total hip arthroplasty CT: deep learning-based algorithm versus virtual monoenergetic imaging and orthopedic metal artifact reductionMark Selles0Ruud H. H. Wellenberg1Derk J. Slotman2Ingrid M. Nijholt3Jochen A. C. van Osch4Kees F. van Dijke5Mario Maas6Martijn F. Boomsma7Department of RadiologyDepartment of Radiology & Nuclear Medicine, Amsterdam University Medical CentreDepartment of RadiologyDepartment of RadiologyDepartment of Medical PhysicsDepartment of Radiology & Nuclear Medicine, Noordwest ZiekenhuisgroepDepartment of Radiology & Nuclear Medicine, Amsterdam University Medical CentreDepartment of RadiologyAbstract Background To compare image quality, metal artifacts, and diagnostic confidence of conventional computed tomography (CT) images of unilateral total hip arthroplasty patients (THA) with deep learning-based metal artifact reduction (DL-MAR) to conventional CT and 130-keV monoenergetic images with and without orthopedic metal artifact reduction (O-MAR). Methods Conventional CT and 130-keV monoenergetic images with and without O-MAR and DL-MAR images of 28 unilateral THA patients were reconstructed. Image quality, metal artifacts, and diagnostic confidence in bone, pelvic organs, and soft tissue adjacent to the prosthesis were jointly scored by two experienced musculoskeletal radiologists. Contrast-to-noise ratios (CNR) between bladder and fat and muscle and fat were measured. Wilcoxon signed-rank tests with Holm-Bonferroni correction were used. Results Significantly higher image quality, higher diagnostic confidence, and less severe metal artifacts were observed on DL-MAR and images with O-MAR compared to images without O-MAR (p < 0.001 for all comparisons). Higher image quality, higher diagnostic confidence for bone and soft tissue adjacent to the prosthesis, and less severe metal artifacts were observed on DL-MAR when compared to conventional images and 130-keV monoenergetic images with O-MAR (p ≤ 0.014). CNRs were higher for DL-MAR and images with O-MAR compared to images without O-MAR (p < 0.001). Higher CNRs were observed on DL-MAR images compared to conventional images and 130-keV monoenergetic images with O-MAR (p ≤ 0.010). Conclusions DL-MAR showed higher image quality, diagnostic confidence, and superior metal artifact reduction compared to conventional CT images and 130-keV monoenergetic images with and without O-MAR in unilateral THA patients. Relevance statement DL-MAR resulted into improved image quality, stronger reduction of metal artifacts, and improved diagnostic confidence compared to conventional and virtual monoenergetic images with and without metal artifact reduction, bringing DL-based metal artifact reduction closer to clinical application. Key points • Metal artifacts introduced by total hip arthroplasty hamper radiologic assessment on CT. • A deep-learning algorithm (DL-MAR) was compared to dual-layer CT images with O-MAR. • DL-MAR showed best image quality and diagnostic confidence. • Highest contrast-to-noise ratios were observed on the DL-MAR images. Graphical Abstracthttps://doi.org/10.1186/s41747-024-00427-3Arthroplasty (replacement, hip)Artificial intelligenceArtifactsDeep learningTomography (x-ray computed) |
| spellingShingle | Mark Selles Ruud H. H. Wellenberg Derk J. Slotman Ingrid M. Nijholt Jochen A. C. van Osch Kees F. van Dijke Mario Maas Martijn F. Boomsma Image quality and metal artifact reduction in total hip arthroplasty CT: deep learning-based algorithm versus virtual monoenergetic imaging and orthopedic metal artifact reduction European Radiology Experimental Arthroplasty (replacement, hip) Artificial intelligence Artifacts Deep learning Tomography (x-ray computed) |
| title | Image quality and metal artifact reduction in total hip arthroplasty CT: deep learning-based algorithm versus virtual monoenergetic imaging and orthopedic metal artifact reduction |
| title_full | Image quality and metal artifact reduction in total hip arthroplasty CT: deep learning-based algorithm versus virtual monoenergetic imaging and orthopedic metal artifact reduction |
| title_fullStr | Image quality and metal artifact reduction in total hip arthroplasty CT: deep learning-based algorithm versus virtual monoenergetic imaging and orthopedic metal artifact reduction |
| title_full_unstemmed | Image quality and metal artifact reduction in total hip arthroplasty CT: deep learning-based algorithm versus virtual monoenergetic imaging and orthopedic metal artifact reduction |
| title_short | Image quality and metal artifact reduction in total hip arthroplasty CT: deep learning-based algorithm versus virtual monoenergetic imaging and orthopedic metal artifact reduction |
| title_sort | image quality and metal artifact reduction in total hip arthroplasty ct deep learning based algorithm versus virtual monoenergetic imaging and orthopedic metal artifact reduction |
| topic | Arthroplasty (replacement, hip) Artificial intelligence Artifacts Deep learning Tomography (x-ray computed) |
| url | https://doi.org/10.1186/s41747-024-00427-3 |
| work_keys_str_mv | AT markselles imagequalityandmetalartifactreductionintotalhiparthroplastyctdeeplearningbasedalgorithmversusvirtualmonoenergeticimagingandorthopedicmetalartifactreduction AT ruudhhwellenberg imagequalityandmetalartifactreductionintotalhiparthroplastyctdeeplearningbasedalgorithmversusvirtualmonoenergeticimagingandorthopedicmetalartifactreduction AT derkjslotman imagequalityandmetalartifactreductionintotalhiparthroplastyctdeeplearningbasedalgorithmversusvirtualmonoenergeticimagingandorthopedicmetalartifactreduction AT ingridmnijholt imagequalityandmetalartifactreductionintotalhiparthroplastyctdeeplearningbasedalgorithmversusvirtualmonoenergeticimagingandorthopedicmetalartifactreduction AT jochenacvanosch imagequalityandmetalartifactreductionintotalhiparthroplastyctdeeplearningbasedalgorithmversusvirtualmonoenergeticimagingandorthopedicmetalartifactreduction AT keesfvandijke imagequalityandmetalartifactreductionintotalhiparthroplastyctdeeplearningbasedalgorithmversusvirtualmonoenergeticimagingandorthopedicmetalartifactreduction AT mariomaas imagequalityandmetalartifactreductionintotalhiparthroplastyctdeeplearningbasedalgorithmversusvirtualmonoenergeticimagingandorthopedicmetalartifactreduction AT martijnfboomsma imagequalityandmetalartifactreductionintotalhiparthroplastyctdeeplearningbasedalgorithmversusvirtualmonoenergeticimagingandorthopedicmetalartifactreduction |