カナイ　タカユキ   KANAI Takayuki   金井　貴幸    所属   医学部 医学科（東京女子医科大学病院）    職種   講師
論文種別	原著
言語種別	英語
査読の有無	査読あり
表題	A deep-learning-based scatter correction with water equivalent path length map for digital radiography.
掲載誌名	正式名：Radiological physics and technology 略　 称：Radiol Phys Technol ISSNコード：18650341/18650333
掲載区分	国外
巻・号・頁	17(2),pp.488-503
著者・共著者	Hattori Masayuki, Tsubakiya Hisato, Lee Sung-Hyun, Kanai Takayuki, Suzuki Koji, Yuasa Tetsuya
発行年月	2024/06
概要	We proposed a new deep learning (DL) model for accurate scatter correction in digital radiography. The proposed network featured a pixel-wise water equivalent path length (WEPL) map of subjects with diverse sizes and 3D inner structures. The proposed U-Net model comprises two concatenated modules: one for generating a WEPL map and the other for predicting scatter using the WEPL map as auxiliary information. First, 3D CT images were used as numerical phantoms for training and validation, generating observed and scattered images by Monte Carlo simulation, and WEPL maps using Siddon's algorithm. Then, we optimised the model without overfitting. Next, we validated the proposed model's performance by comparing it with other DL models. The proposed model obtained scatter-corrected images with a peak signal-to-noise ratio of 44.24 ± 2.89 dB and a structural similarity index measure of 0.9987 ± 0.0004, which were higher than other DL models. Finally, scatter fractions (SFs) were compared with other DL models using an actual phantom to confirm practicality. Among DL models, the proposed model showed the smallest deviation from measured SF values. Furthermore, using an actual radiograph containing an acrylic object, the contrast-to-noise ratio (CNR) of the proposed model and the anti-scatter grid were compared. The CNR of the images corrected using the proposed model are 16% and 82% higher than those of the raw and grid-applied images, respectively. The advantage of the proposed method is that no actual radiography system is required for collecting training dataset, as the dataset is created from CT images using Monte Carlo simulation.
DOI	10.1007/s12194-024-00807-9
PMID	38696086