Lung-Optimized Deep- Learning-Based Reconstruction for Ultralow-Dose CT

被引：15

作者：

Goto, Makoto ^{[1
]}

Nagayama, Yasunori ^{[2
]}

Sakabe, Daisuke ^{[1
]}

Emoto, Takafumi ^{[1
]}

Kidoh, Masafumi ^{[2
]}

Oda, Seitaro ^{[2
]}

Nakaura, Takeshi ^{[2
]}

Taguchi, Narumi ^{[2
]}

Funama, Yoshinori ^{[3
]}

Takada, Sentaro ^{[2
]}

Uchimura, Ryutaro ^{[2
]}

Hayashi, Hidetaka ^{[2
]}

Hatemura, Masahiro ^{[1
]}

Kawanaka, Koichi ^{[2
]}

Hirai, Toshinori ^{[2
]}

机构：

[1] Kumamoto Univ Hosp, Dept Cent Radiol, Chuo Ku, Kumamoto 8608556, Japan

[2] Kumamoto Univ, Grad Sch Med Sci, Dept Diagnost Radiol, 1-1-1 Honjo,Chuo Ku, Kumamoto 8608556, Japan

[3] Kumamoto Univ, Fac Life Sci, Dept Med Radiat Sci, Chuo Ku, Kumamoto 8620976, Japan

来源：

ACADEMIC RADIOLOGY | 2023年 / 30卷 / 03期

关键词：

CT; Lung; Deep-learning; Image reconstruction; Ultralow-dose; FILTERED BACK-PROJECTION; SUBMILLISIEVERT CHEST CT; TASK-BASED PERFORMANCE; ITERATIVE-RECONSTRUCTION; IMAGE QUALITY; COMPUTED-TOMOGRAPHY; ALGORITHMS; PHANTOM;

D O I：

10.1016/j.acra.2022.04.025

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

Rationale and Objectives: To evaluate the image properties of lung-specialized deep-learning-based reconstruction (DLR) and its appli-cability in ultralow-dose CT (ULDCT) relative to hybrid-(HIR) and model-based iterative-reconstructions (MBIR).Materials and Methods: An anthropomorphic chest phantom was scanned on a 320-row scanner at 50-mA (low-dose-CT 1 [LDCT-1]), 25-mA (LDCT-2), and 10-mA (ULDCT). LDCT were reconstructed with HIR; ULDCT images were reconstructed with HIR (ULDCT-HIR), MBIR (ULDCT-MBIR), and DLR (ULDCT-DLR). Image noise and contrast-to-noise ratio (CNR) were quantified. With the LDCT images as reference standards, ULDCT image qualities were subjectively scored on a 5-point scale (1 = substantially inferior to LDCT-2, 3 = compara-ble to LDCT-2, 5 = comparable to LDCT-1). For task-based image quality analyses, a physical evaluation phantom was scanned at seven doses to achieve the noise levels equivalent to chest phantom; noise power spectrum (NPS) and task-based transfer function (TTF) were evaluated. Clinical ULDCT (10-mA) images obtained in 14 nonobese patients were reconstructed with HIR, MBIR, and DLR; the subjective acceptability was ranked. Results: Image noise was lower and CNR was higher in ULDCT-DLR and ULDCT-MBIR than in LDCT-1, LDCT-2, and ULDCT-HIR (p < 0.01). The overall quality of ULDCT-DLR was higher than of ULDCT-HIR and ULDCT-MBIR (p < 0.01), and almost comparable with that of LDCT-2 (mean score: 3.4 +/- 0.5). DLR yielded the highest NPS peak frequency and TTF50% for high-contrast object. In clinical ULDCT images, the subjective acceptability of DLR was higher than of HIR and MBIR (p < 0.01).Conclusion: DLR optimized for lung CT improves image quality and provides possible greater dose optimization opportunity than HIR and MBIR.

引用

页码：431 / 440

页数：10

共 41 条

[1]

AAPM, PROT LUNG CANC SCREE

[2] Deep learning reconstruction improves image quality of abdominal ultra-high-resolution CT [J].