Page 125 - 南京医科大学自然版
P. 125
第45卷第11期 丁 威,唐立钧,田 锋. 基于Swin Transformer的低活度PET影像质量恢复方法研究[J].
2025年11月 南京医科大学学报(自然科学版),2025,45(11):1649-1655 ·1655 ·
18
F⁃FDG PET/CT application in inflammation and infec⁃ YUAN L,ZHAO M,JIN H X,et al. Significance of low⁃
tion:a guide for image acquisition and interpretation[J]. dose fluorodeoxyglucose PET/CT for screening of malig⁃
Clin Transl Imaging,2021,9(4):299-339 nant tumors[J]. Chinese Remedies & Clinics,2013,13
[6] 张逸悦,李孝媛,高 擎,等. F⁃FDG⁃PET/MR 探究早 (8):980-982
18
期帕金森病脑代谢网络和功能网络改变特征[J]. 南 [13]MATSUBARA K,IBARAKI M,NEMOTO M,et al. A re⁃
京医科大学学报(自然科学版),2025,45(8):1132- view on AI in PET imaging[J]. Ann Nucl Med,2022,36
1139 (2):133-143
18
ZHANG Y Y,LI X Y,GAO Q,et al. F⁃FDG ⁃PET/MR [14]ZHOU L,SCHAEFFERKOETTER J,THAM I,et al. Su⁃
unveils altered features of brain metabolic and functional pervised learning with cyclegan for low ⁃ dose FDG PET
networks in early Parkinson’s disease[J]. Journal of Nan⁃ image denoising[J]. Med Image Anal,2020,65:1-9
jing Medical University(Natural Sciences),2025,45(8): [15]KAPLAN S,ZHU Y M. Full⁃dose PET image estimation
1132-1139 from low ⁃ dose PET image using deep learning:a pilot
[7] 孙 寒,丁重阳,丁 威,等. 基线 F⁃FDGPET/CT 代谢 study[J]. J Digit Imaging,2019,32(5):773-778
18
参数在 ENKTL 中的预后价值[J]. 南京医科大学学报 [16]CONZE P,ANDRADE G,SINGH V,et al. Current and
(自然科学版),2023,43(2):249-256 emerging trends in medical image segmentation with deep
SUN H,DING C Y,DING W,et al. The prognostic role of learning[J]. IEEE Trans Radiat Plasma Med Sci,2023,7
18F ⁃ FDG PET/CT baseline metabolic parameters in ex⁃ (6):545-569
tranodal natural killer/T ⁃ cell lymphoma[J]. Journal of [17]LI J,CHEN J,TANG Y,et al. Transforming medical imag⁃
Nanjing Medical University(Natural Sciences),2023,43 ing with transformers? A comparative review of key prop⁃
(2):249-256 erties,current progresses,and future perspectives[J].
[8] HOSONO M,TAKENAKA M,MONZEN H,et al. Cumu⁃ Med Image Anal,2023,85:1-38
lative radiation doses from recurrent PET ⁃ CT examina⁃ [18]RAPISARDA E,BETTINARDI V,THIELEMANS K,et
tions[J]. Br J Radiol,2021,94(1126):1-5 al. Image⁃based point spread function implementation in
[9] TSUNEKI M. Deep learning models in medical image anal⁃ a fully 3D OSEM reconstruction algorithm for PET[J].
ysis[J]. J Oral Biosci,2022,64(3):312-320 Phys Med Biol,2010,55(14):4131-4151
[10]SUGANYADEYI S,SEETHALAKSHMI V,BALASMY K. [19]XING Y,QIAO W,WANG T,et al. Deep learning⁃assisted
A review on deep learning in medical image analysis[J]. PET imaging achieves fast scan/low⁃dose examination[J].
Int J Multimed Inf Retr,2022,11(1):19-38 EJNMMI Phys,2022,9(1):7-23
[11]郭嘉杰,张志浩,项 磊,等. 基于人工智能的PET图像 [20]AKAMATSU G,TSUTSUI Y,DAISAKI H,et al. A review
增强方法的研究进展[J]. 中国医疗器械信息,2023,29 of harmonization strategies for quantitative PET[J]. Ann
(13):25-34 Nucl Med,2023,37(2):71-88
GUO J J,ZHANG Z H,XIANG L,et al. Research prog⁃ [21]TIAN F,LIU H,GU Y Y,et al. Personalized three⁃dimen⁃
ress of PET image enhancement methods based on artifi⁃ sional dose calculation method based on multi⁃modal im⁃
cial intelligence[J]. China Medical Device Information, ages in dosimetry assessment of prostate cancer with skull
2023,29(13):25-34 metastasis:a Monte Carlo simulation study[J]. EJNMMI
[12]原 凌,赵 铭,靳宏星,等. 低剂量F⁃氟代脱氧葡萄糖 Phys,2025,12(1):59-71
PET/CT 在体检中发现恶性肿瘤的意义[J]. 中国药物 [收稿日期] 2025-07-28
与临床,2013,13(8):980-962 (本文编辑:唐 震)

