Your browser doesn't support javascript.
loading
Deep learning-based reconstruction on cardiac CT yields distinct radiomic features compared to iterative and filtered back projection reconstructions.
Chun, Sei Hyun; Suh, Young Joo; Han, Kyunghwa; Kwon, Yonghan; Kim, Aaron Youngjae; Choi, Byoung Wook.
Afiliación
  • Chun SH; Department of Radiology, Severance Hospital, Research Institute of Radiological Science, Center for Clinical Imaging Data Science, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Korea.
  • Suh YJ; Department of Radiology, Severance Hospital, Research Institute of Radiological Science, Center for Clinical Imaging Data Science, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Korea. rongzusuh@gmail.com.
  • Han K; Department of Radiology, Severance Hospital, Research Institute of Radiological Science, Center for Clinical Imaging Data Science, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Korea.
  • Kwon Y; Department of Biostatistics and Computing, Yonsei University Graduate School, Seoul, Korea.
  • Kim AY; Weill Cornell Medicine-Qatar, Doha, Qatar.
  • Choi BW; Department of Radiology, Severance Hospital, Research Institute of Radiological Science, Center for Clinical Imaging Data Science, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Korea.
Sci Rep ; 12(1): 15171, 2022 09 07.
Article en En | MEDLINE | ID: mdl-36071138
We aimed to determine the effects of deep learning-based reconstruction (DLR) on radiomic features obtained from cardiac computed tomography (CT) by comparing with iterative reconstruction (IR), and filtered back projection (FBP). A total of 284 consecutive patients with 285 cardiac CT scans that were reconstructed with DLR, IR, and FBP, were retrospectively enrolled. Radiomic features were extracted from the left ventricular (LV) myocardium, and from the periprosthetic mass if patients had cardiac valve replacement. Radiomic features of LV myocardium from each reconstruction were compared using a fitting linear mixed model. Radiomics models were developed to diagnose periprosthetic abnormality, and the performance was evaluated using the area under the receiver characteristics curve (AUC). Most radiomic features of LV myocardium (73 of 88) were significantly different in pairwise comparisons between all three reconstruction methods (P < 0.05). The radiomics model on IR exhibited the best diagnostic performance (AUC 0.948, 95% CI 0.880-1), relative to DLR (AUC 0.873, 95% CI 0.735-1) and FBP (AUC 0.875, 95% CI 0.731-1), but these differences did not reach significance (P > 0.05). In conclusion, applying DLR to cardiac CT scans yields radiomic features distinct from those obtained with IR and FBP, implying that feature robustness is not guaranteed when applying DLR.
Asunto(s)

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Interpretación de Imagen Radiográfica Asistida por Computador / Aprendizaje Profundo Tipo de estudio: Observational_studies / Prognostic_studies Límite: Humans Idioma: En Revista: Sci Rep Año: 2022 Tipo del documento: Article

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Interpretación de Imagen Radiográfica Asistida por Computador / Aprendizaje Profundo Tipo de estudio: Observational_studies / Prognostic_studies Límite: Humans Idioma: En Revista: Sci Rep Año: 2022 Tipo del documento: Article
...