Deep learning-based conditional inpainting for restoration of artifact-affected 4D CT images
Standard
Deep learning-based conditional inpainting for restoration of artifact-affected 4D CT images. / Madesta, Frederic; Sentker, Thilo; Gauer, Tobias; Werner, René.
in: MED PHYS, Jahrgang 51, Nr. 5, 05.2024, S. 3437-3454.Publikationen: SCORING: Beitrag in Fachzeitschrift/Zeitung › SCORING: Zeitschriftenaufsatz › Forschung › Begutachtung
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Deep learning-based conditional inpainting for restoration of artifact-affected 4D CT images
AU - Madesta, Frederic
AU - Sentker, Thilo
AU - Gauer, Tobias
AU - Werner, René
N1 - © 2023 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.
PY - 2024/5
Y1 - 2024/5
N2 - BACKGROUND: 4D CT imaging is an essential component of radiotherapy of thoracic and abdominal tumors. 4D CT images are, however, often affected by artifacts that compromise treatment planning quality and image information reliability.PURPOSE: In this work, deep learning (DL)-based conditional inpainting is proposed to restore anatomically correct image information of artifact-affected areas.METHODS: The restoration approach consists of a two-stage process: DL-based detection of common interpolation (INT) and double structure (DS) artifacts, followed by conditional inpainting applied to the artifact areas. In this context, conditional refers to a guidance of the inpainting process by patient-specific image data to ensure anatomically reliable results. The study is based on 65 in-house 4D CT images of lung cancer patients (48 with only slight artifacts, 17 with pronounced artifacts) and two publicly available 4D CT data sets that serve as independent external test sets.RESULTS: Automated artifact detection revealed a ROC-AUC of 0.99 for INT and of 0.97 for DS artifacts (in-house data). The proposed inpainting method decreased the average root mean squared error (RMSE) by 52 % (INT) and 59 % (DS) for the in-house data. For the external test data sets, the RMSE improvement is similar (50 % and 59 %, respectively). Applied to 4D CT data with pronounced artifacts (not part of the training set), 72 % of the detectable artifacts were removed.CONCLUSIONS: The results highlight the potential of DL-based inpainting for restoration of artifact-affected 4D CT data. Compared to recent 4D CT inpainting and restoration approaches, the proposed methodology illustrates the advantages of exploiting patient-specific prior image information.
AB - BACKGROUND: 4D CT imaging is an essential component of radiotherapy of thoracic and abdominal tumors. 4D CT images are, however, often affected by artifacts that compromise treatment planning quality and image information reliability.PURPOSE: In this work, deep learning (DL)-based conditional inpainting is proposed to restore anatomically correct image information of artifact-affected areas.METHODS: The restoration approach consists of a two-stage process: DL-based detection of common interpolation (INT) and double structure (DS) artifacts, followed by conditional inpainting applied to the artifact areas. In this context, conditional refers to a guidance of the inpainting process by patient-specific image data to ensure anatomically reliable results. The study is based on 65 in-house 4D CT images of lung cancer patients (48 with only slight artifacts, 17 with pronounced artifacts) and two publicly available 4D CT data sets that serve as independent external test sets.RESULTS: Automated artifact detection revealed a ROC-AUC of 0.99 for INT and of 0.97 for DS artifacts (in-house data). The proposed inpainting method decreased the average root mean squared error (RMSE) by 52 % (INT) and 59 % (DS) for the in-house data. For the external test data sets, the RMSE improvement is similar (50 % and 59 %, respectively). Applied to 4D CT data with pronounced artifacts (not part of the training set), 72 % of the detectable artifacts were removed.CONCLUSIONS: The results highlight the potential of DL-based inpainting for restoration of artifact-affected 4D CT data. Compared to recent 4D CT inpainting and restoration approaches, the proposed methodology illustrates the advantages of exploiting patient-specific prior image information.
U2 - 10.1002/mp.16851
DO - 10.1002/mp.16851
M3 - SCORING: Journal article
C2 - 38055336
VL - 51
SP - 3437
EP - 3454
JO - MED PHYS
JF - MED PHYS
SN - 0094-2405
IS - 5
ER -