Page 77 - 南京医科大学自然版
P. 77
第45卷第6期 徐思雨,张永杰,田 水,等. 深度学习重建算法在胰腺HASTE⁃T2WI序列中的临床应用价值[J].
2025年6月 南京医科大学学报(自然科学版),2025,45(6):810-815,825 ·815 ·
Conflict of Interests: HASTE T2 weighted image with reduced echo time for de⁃
All authors declare no conflict of interests. tecting focal liver lesions in patients at risk of developing
作者贡献声明: hepatocellular carcinoma[J]. Eur J Radiol,2022,157:
徐思雨设计本研究方案,实施研究过程,起草和撰写稿 110588
件,获取、分析或解释本研究的数据;张永杰获取、分析或解 [7] GINOCCHIO L A,SMEREKA P N,TONG A,et al. Accel⁃
释本研究的数据,指导性支持;田水获取、分析或解释本研究 erated T2⁃weighted MRI of the liver at 3 T using a single⁃
的数据,对稿件重要内容进行了修改。王建伟提出研究选 shot technique with deep learning ⁃ based image recon⁃
题,设计本研究的方案,对稿件重要的内容进行了修改,终审 struction:impact on the image quality and lesion detec⁃
论文。 tion[J]. Abdom Radiol(NY),2023,48(1):282-290
Author’s Contributions: [8] 唐蛰雨,李绍钦,贾中芝. 基于CT图像的深度学习在主
XU Siyu designed the research plan,conducted the re⁃ 动脉夹层中的应用进展[J]. 南京医科大学学报(自然
search process,drafted and wrote the manuscript,obtained,ana⁃ 科学版),2024,44(8):1174-1178
lyzed or interpreted the data of this study;ZHANG Yongjie ob⁃ TANG Y Z,LI S Q,JIA Z Z. The application progress of
tained,analyzed or interpreted the data of this study,provided deep learning based on CT images in aortic dissection[J].
guiding support;TIAN Shui obtained,analyzed or interpreted Journal of Nanjing Medical University(Natural Sciences),
the data of this study,and made significant intellectual contribu⁃ 2024(8):1174-1178
tions to the manuscript;WANG Jianwei proposed the research [9] SUN S ,TAN E T ,MINTZ D N ,et al. Evaluation of
topic,designed the research plan,made significant intellectual deep learning reconstructed high ⁃ resolution 3D lumbar
contributions to the manuscript,and reviewed the final version spine MRI[J]. Eur Radiol,2022,32(9):6167-6177
of the paper. [10]HERRMANN J,KOERZDOERFER G,NICKEL D,et al.
[参考文献] Feasibility and implementation of a deep learning MR re⁃
construction for TSE sequences in musculoskeletal imag⁃
[1] 喻 悦,王瑜亮,张 晓. 葡萄糖代谢重编程在胰腺癌
ing[J]. Diagnostics(Basel).2021,11(8):1484
耐药中的研究进展[J]. 南京医科大学学报(自然科学
[11]可 赞,李 亮,宋鑫洋,等. 基于深度学习重建技术改
版),2024,44(4):524-535
善前列腺 T2WI 图像质量的研究[J]. 磁共振成像,
YU Y,WANG Y L,ZHANG X. Research progress of glu⁃
2023,14(5):41-47
cose metabolic reprogrammingin drug resistance of pan⁃
KE Z,LI L,SONG X Y,et al. Novel deep learning⁃based
creatic cancer[J]. Journal of Nanjing Medical University
T2⁃weighted imaging of the prostate provides superior im⁃
(Natural Sciences),2024,44(4):524-535
age quality[J]. Magnetic Resonance Imaging,2023,14
[2] 王 莎,张艳利,陈圆圆,等. 影像组学在胰腺炎中的应
(5):41-47
用研究进展[J]. 放射学实践,2024,39(1):42-48
[12]杨正汉,冯 逢,郑卓肇,等. 磁共振成像技术指南第二
WANG S,ZHANG Y L,CHEN Y Y,et al. Research prog⁃
版[M]. 北京:中国协会医科大学出版社,2023
ress on the application of rdiomics in pancreatitis[J]. Ra⁃
YANG Z H,FENG F,ZHENG Z Z,et al. A guide to tech⁃
diological Practice,2024,39(1):42-48
nical of Magnetic Resonance Imaging,second edition
[3] TAJIMA T,AKAI H,YASAKA K,et al. Clinical feasibili⁃
[M]. Beijing:Peking Union Medical College Press,2023
ty of an abdominal thin⁃slicebreath⁃hold single⁃shot fast
[13]TAKAYAM Y,SATO K,TANAKA S,et al. Deep learning
spin echo sequence processed using a deep learning ⁃
⁃based magnetic resonance imaging reconstruction for im⁃
based noise⁃reduction approach[J]. Magnetic Resonance
proving the image quality of reduced⁃field⁃of⁃view diffu⁃
Imaging,2022,90:76-83
sion⁃weighted imaging of the pancreas[J]. World J Radi⁃
[4] LIU K,LI Q,WANG X X,et al. Feasibility of deep learn⁃
ol,2023,15(12):338-349
ing⁃reconstructed thin⁃slice single⁃breath⁃hold HASTE
[14]GASSENMAIER S,KÜSTNER T,NICKEL D,et al. Deep
for detecting pancreatic lesions:a comparison with two
conventional T2⁃weighted imaging sequences[J]. Res Di⁃ Learning applications in magnetic resonance imaging:has
the future become present?[J]. Diagnostics(Basel),
agn Interv Imaging,2024,31(9):100038
[5] HERRMANN J,NICKEL D,MUGLER J P 3RD,et al. De⁃ 2021,11(12):2181
velopment and evaluation of deep learning ⁃ accelerated [15]KANIEWSKAM,DEININGER⁃CZERMAKE,GETZMANN
single⁃breath⁃hold abdominal HASTE at 3 T using vari⁃ J M,et al. Application of deep learning⁃based image re⁃
able refocusing flip angles[J]. Invest Radiol,2021,56: construction in MR imaging of the shoulder joint to im⁃
prove image quality and reduce scan time[J]. Eur Radiol,
645-652
[6] HANA S,LEE J M,KIMA S W,et al. Evaluation of (下转第825页)

