深度学习重建算法联合轴扫的低剂量胸部CT在儿童肺炎支原体肺炎中的诊断价值

doi:10.3969/j.issn.1006-5725.2025.21.019

Abstract

Abstract:

Objective To explore the diagnostic value of deep learning image reconstruction （DLIR） combined with low?dose chest computed tomography （CT） with axial scan in the diagnosis of mycoplasma pneumoniae pneumonia （MPP） in children， and to provide reference for clinical practice. Methods 160 cases MPP children from February 2024 to June 2025 were selected as study subjects， and low?dose chest CT with axial scan was performed on all patients. DLIR and conventional adaptive iterative reconstruction?V （ASIR?V） were used for image reconstruction. The objective image quality ［background noise （SD）， signal?to?noise ratio （SNR）， and contrast?to?noise ratio （CNR）］， subjective image quality， and CT sign detection rate were compared， and the consistency of DLIR and ASIR?V in the diagnosis of MPP severity and clinical diagnosis was compared. Results As the intensity of DLIR and the weight of ASIR increasd， SD gradually decreased， while SNR and CNR gradually increased. The high?strength DLIR （DLIR?H） SD was lower than that of ASIR with a blending level of 80% （ASIR?V80%）. The SNR and CNR were higher than those of ASIR?V80%， showing statistical significance （P < 0.05）. Ridit test showed that DLIR?H had the best subjective image quality score under different DLIR intensities， and ASIR?V80% had the best subjective image quality score under different ASIR weights. Furthermore， the subjective image quality score of DLIR?H was higher that of ASIR?V80%， and the differences were statistically significant （P < 0.05）. Using DLIR?H， the detection rates of air bronchogram， pulmonary consolidation， and interstitial infiltration （69.38%， 86.88%， 20.63%， respectively） were higher than those using ASIR?V80% （50.00%， 71.88%， 7.50%， respectively）， and the differences were statistically significant （P < 0.05）. Consistency analysis showed that the Kappa value between the diagnostic results of MPP severity using DLIR?H and clinical diagnosis was 0.856 （95%CI： 0.771 ~ 0.996）， while that between the diagnostic results of MPP severity using ASIR?V80% and clinical diagnosis was 0.498（95%CI： 0.346 ~ 0.650）. ROC analysis showed that the area under the curve （AUC） for diagnosing MPP severity was 0.925 （95%CI： 0.872 ~ 0.960） for DLIR?H and 0.729 （95%CI： 0.653 ~ 0.796） for ASIR?V80%， and the diagnostic value of DLIR?H was superior to that of ASIR?V80% （Z = 3.952， P < 0.001）. Conclusion DLIR can effectively improve image quality. DLIR?H combined with low?dose chest CT with axial scan has high diagnostic value for the severity of MPP， and can serve as a feasible solution for clinical diagnosis of MPP severity and reducing radiation dose.

Key words: reconstruction algorithm, chest CT, low-dose axial scan, image quality, children, mycoplasma pneumoniae pneumonia

CLC Number:

R563.1

Linmei HAN,Yingli REN,Yiman LI,Fen HUANG,Taoming. DU. Feasibility study of low⁃dose chest CT with deep learning reconstruction algorithm combined with axial scan in children with mycoplasma pneumoniae pneumonia[J]. The Journal of Practical Medicine, 2025, 41(21): 3428-3434.

Figures/Tables 7

Tab.1

Tab.2

Tab.3

Tab.4

Fig.1

Fig.2

Fig.3

References 26

[1]	陈茜茜，林秋玉，张湘云，等. 大环内酯类耐药肺炎支原体感染与儿童难治性肺炎支原体肺炎的关系［J］. 实用医学杂志，2024，40（22）：3190-3195.
[2]	XU M， LI Y， SHI Y，et al. Molecular epidemiology of Mycoplasma pneumoniae pneumonia in children，Wuhan，2020-2022［J］. BMC Microbiol，2024，24（1）：23-30. doi:10.1186/s12866-024-03180-0 doi: 10.1186/s12866-024-03180-0
[3]	陈海静，杨亚英，赵卫，等. 增强CT和MRI在鉴别鼻腔鼻窦鳞状细胞癌与淋巴瘤中的应用［J］. 实用医学杂志，2024，40（3）：394-399.
[4]	YANG S H， PU Q， LEI C T，et al. Low-dose CT denoising with a high-level feature refinement and dynamic convolution network［J］. Med Phys，2023，50（6）：3597-3611. doi:10.1002/mp.16175 doi: 10.1002/mp.16175
[5]	DENG J T， MA T， YAN J，et al. Effect of Low Tube Voltage （100 kV） Combined with ASIR-V on the Visualization and Image Quality of the Adamkiewicz Artery：A Comparison with 120 kV Protocol［J］. Diagnostics （Basel），2023，13（15）：2495-2499. doi:10.3390/diagnostics13152495 doi: 10.3390/diagnostics13152495
[6]	CAO J J， MROUEH N， MERCALDO N，et al. Detectability of Hypoattenuating Liver Lesions with Deep Learning CT Reconstruction：A Phantom and Patient Study［J］. Radiology，2024，313（1）：e232749. doi:10.1148/radiol.232749 doi: 10.1148/radiol.232749
[7]	ROSSI A， GENNARI A G， ETTER D，et al. Impact of deep learning image reconstructions （DLIR） on coronary artery calcium quantification［J］. Eur Radiol，2023，33（6）：3832-3838. doi:10.1007/s00330-022-09287-0 doi: 10.1007/s00330-022-09287-0
[8]	ZHONG JY， SHEN H L， CHEN Y，et al. Evaluation of Image Quality and Detectability of Deep Learning Image Reconstruction （DLIR） Algorithm in Single- and Dual-energy CT［J］. J Digit Imaging，2023，36（4）：1390-1407. doi:10.1007/s10278-023-00806-z doi: 10.1007/s10278-023-00806-z
[9]	中华医学会儿科学分会呼吸学组，《中华实用儿科临床杂志》编辑委员会. 儿童肺炎支原体肺炎诊治专家共识（2015年版）［J］. 中华实用儿科临床杂志，2015，30（17）：1304-1308.
[10]	DING G D， ZHANG X B， VINTURACHE A， et al. Challenges in the treatment of pediatric Mycoplasma pneumoniae pneumonia［J］. Eur J Pediatr，2024，183（7）：3001-3011. doi:10.1007/s00431-024-05519-1 doi: 10.1007/s00431-024-05519-1
[11]	袁静，陈庆仪，杨好贤，等. 含凝血功能五项Nomogram预测模型预测重症肺炎支原体肺炎患儿预后的效果研究［J］. 临床误诊误治，2023，36（3）：90-94.
[12]	YANG L X， SUN J H， LI J Y，et al. Dual-energy spectral CT imaging of pulmonary embolism with Mycoplasma pneumoniae pneumonia in children［J］. Radiol Med，2022，127（2）：154-161. doi:10.1007/s11547-021-01442-9 doi: 10.1007/s11547-021-01442-9
[13]	苏布德格日乐，刘伟民，斯琴格日勒，等. 儿童肺炎支原体肺炎急性期高分辨率CT特征与血清炎症因子、病情严重程度及预后的相关性［J］. 放射学实践，2023，38（9）：1173-1177.
[14]	DE SANTIS D， POLIDORI T， TREMAMUNNO G，et al. Deep learning image reconstruction algorithm： Impact on image quality in coronary computed tomography angiography［J］. Radiol Med，2023，128（4）：434-444. doi:10.1007/s11547-023-01607-8 doi: 10.1007/s11547-023-01607-8
[15]	KIM C H， CHUNG M J， CHA Y K，et al. The impact of deep learning reconstruction in low dose computed tomography on the evaluation of interstitial lung disease［J］. PLoS One，2023，18（9）：e0291745. doi:10.1371/journal.pone.0291745 doi: 10.1371/journal.pone.0291745
[16]	陈依林，刘元芬，王莉莉，等. 深度学习重建算法对低kV逆血流扫描下肢动脉CT血管成像图像质量的影响［J］. 中华放射学杂志，2022，56（11）：1188-1194.
[17]	YANG K， CAO J J， PISUCHPEN N，et al. CT image quality evaluation in the age of deep learning： Trade-off between functionality and fidelity［J］. Eur Radiol，2023，33（4）：2439-2449. doi:10.1007/s00330-022-09233-0 doi: 10.1007/s00330-022-09233-0
[18]	KANAN A， PEREIRA B， HORDONNEAU C，et al. Deep learning CT reconstruction improves liver metastases detection［J］. Insights Imaging，2024，15（1）：167-172. doi:10.1186/s13244-024-01753-1 doi: 10.1186/s13244-024-01753-1
[19]	TOIA G V， ZAMORA D A， SINGLETON M，et al. Detectability of Small Low-Attenuation Lesions With Deep Learning CT Image Reconstruction：A 24-Reader Phantom Study［J］. AJR Am J Roentgenol，2023，220（2）：283-295. doi:10.2214/ajr.22.28407 doi: 10.2214/ajr.22.28407
[20]	SVALKVIST A， FAGMAN E， VIKGREN J，et al. Evaluation of deep-learning image reconstruction for chest CT examinations at two different dose levels［J］. J Appl Clin Med Phys，2023，24（3）：e13871. doi:10.1002/acm2.13871 doi: 10.1002/acm2.13871
[21]	LEI L M， ZHOU Y H， GUO X X，et al. The value of a deep learning image reconstruction algorithm in whole-brain computed tomography perfusion in patients with acute ischemic stroke［J］.Quant Imaging Med Surg，2023，13（12）：8173-8189. doi:10.21037/qims-23-547 doi: 10.21037/qims-23-547
[22]	WANG H， LI X Y， WANG T Z，et al. The value of using a deep learning image reconstruction algorithm of thinner slice thickness to balance the image noise and spatial resolution in low-dose abdominal CT［J］. Quant Imaging Med Surg，2023，13（3）：1814-1824. doi:10.21037/qims-22-353 doi: 10.21037/qims-22-353
[23]	ZHENG Z， AI Z， LIANG Y，et al. Clinical value of deep learning image reconstruction on the diagnosis of pulmonary nodule for ultra-low-dose chest CT imaging［J］. Clin Radiol，2024，79（8）：628-636. doi:10.1016/j.crad.2024.04.008 doi: 10.1016/j.crad.2024.04.008
[24]	KOH S， LEE N K， KIM S，et al. The efficacy of low-dose CT with deep learning image reconstruction in the surveillance of incidentally detected pancreatic cystic lesions［J］. Abdom Radiol （NY），2023，48（8）：2585-2595. doi:10.1007/s00261-023-03958-2 doi: 10.1007/s00261-023-03958-2
[25]	ZHU H Y， HUANG Z K， CHEN Q H，et al. Feasibility of Sub-milliSievert Low-dose Computed Tomography with Deep Learning Image Reconstruction in Evaluating Pulmonary Subsolid Nodules：A Prospective Intra-individual Comparison Study［J］. Acad Radiol，2025，32（4）：2309-2319. doi:10.1016/j.acra.2024.11.042 doi: 10.1016/j.acra.2024.11.042
[26]	KLEMENZ A C， ALBRECHT L， MANZKE M，et al. Improved image quality in CT pulmonary angiography using deep learning-based image reconstruction［J］. Sci Rep，2024，14（1）：2494-2498. doi:10.1038/s41598-024-52517-2 doi: 10.1038/s41598-024-52517-2

项目	SD（HU）	SNR	CNR
ASIR-V20%	33.75 ± 5.02	10.81 ± 2.40	12.06 ± 3.49
ASIR-V50%	26.40 ± 4.81	12.96 ± 2.72	16.44 ± 3.65
ASIR-V80%	19.77 ± 4.53	16.67 ± 3.58	23.70 ± 4.22
F值	340.901	162.392	383.056
P值	< 0.001	< 0.001	< 0.001
DLIR-L	28.64 ± 4.04	12.11 ± 2.82	13.62 ± 3.74
DLIR-M	21.89 ± 3.50	16.45 ± 3.75	18.81 ± 3.92
DLIR-H	14.81 ± 4.15	20.95 ± 4.40	28.73 ± 4.31
F值	501.301	226.671	590.284
P值	< 0.001	< 0.001	< 0.001

项目	1分	2分	3分	4分	5分
ASIR-V20%	0（0.00）	11（6.88）	19（11.88）	99（61.88）	31（19.38）
ASIR-V50%	0（0.00）	6（3.75）	13（8.13）	95（59.38）	46（28.75）
ASIR-V80%	0（0.00）	2（1.25）	7（4.38）	82（51.25）	69（43.13）
χ²值	21.972
P值	< 0.001
DLIR-L	0（0.00）	0（0.00）	6（3.75）	116（72.50）	38（23.75）
DLIR-M	0（0.00）	0（0.00）	1（0.63）	99（61.88）	60（37.50）
DLIR-H	0（0.00）	0（0.00）	0（0.00）	64（40.00）	96（60.00）
χ²值	34.982
P值	< 0.001

CT征象	DLIR-H	ASIR-V80%	χ²值	P值
支气管壁增厚	146（91.25）	137（85.63）	2.475	0.116
空气支气管征	111（69.38）	80（50.00）	12.481	< 0.001
淋巴结肿大	53（33.13）	48（30.00）	0.362	0.548
间质增厚	31（19.38）	31（19.38）	0.000	1.000
肺实变影	139（86.88）	115（71.88）	10.995	0.001
间质浸润	33（20.63）	12（7.50）	11.404	0.001
胸腔积液	40（25.00）	34（21.25）	0.633	0.426

重建条件	临床诊断/例		合计	Kappa值	P值	95%CI
重建条件	轻度	重度	合计	Kappa值	P值	95%CI
DLIR-H				0.856	< 0.001	0.711 ~ 0.996
轻度	113	5	118
重度	4	38	42
合计	117	43	160
ASIR-V80%				0.498	< 0.001	0.346 ~ 0.650
轻度	108	20	128
重度	9	23	32
合计	117	43	160

Feasibility study of low⁃dose chest CT with deep learning reconstruction algorithm combined with axial scan in children with mycoplasma pneumoniae pneumonia

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 26

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Pao YU,Feng ZHU,Zheng GE,Bi ZHOU,Lixia ZHANG. Phenotypic characteristics of early lymphocyte subsets and bronchoscopy findings in children with severe Mycoplasma pneumoniae pneumonia [J]. The Journal of Practical Medicine, 2025, 41(7): 1062-1069.
[2]	Dongli LIU,Zilin QUAN,Lingxiu ZHONG,Qiqi CHEN,Wenqiao CAI,Senpei ZHUANG,Ying WEI,Huiyi PAN,Yawen. LIN. Construction and validation of a predictive model for antibiotic-associated diarrhea after surgery in children with congenital heart disease [J]. The Journal of Practical Medicine, 2025, 41(5): 683-690.
[3]	Peng XU,Yun ZHOU,Rong JIA,Can QI,Linmeng SHI,Jingda GAO,Dengwei CHU,Xu. GAO. Clinical efficacy of testicular fascial compartment decompression in the treatment of testicular torsion in children [J]. The Journal of Practical Medicine, 2025, 41(2): 220-224.
[4]	Zhiqing XIAO,Xue WU,Rui QIU,Jinghan CHI,Shaodong HUA,Bin ZHU,De CHANG. Construction and verification of multi⁃factor prediction model for refractory mycoplasma pneumoniae pneumonia in children [J]. The Journal of Practical Medicine, 2025, 41(13): 2004-2010.
[5]	Bingjie QUAN,Yijing LIU,Xiaoqin LI,Fang ZHOU. Clinical features of hepatitisassociatedaplastic anemia in children [J]. The Journal of Practical Medicine, 2025, 41(1): 84-89.
[6]	Qingwen WANG,Shuya ZHANG,Weilin XIONG,Xiaolei HU,Ziwei LI,Qingyin. GUO. Characteristics of oral flora and its metabolites in children with henoch⁃schonlein purpura [J]. The Journal of Practical Medicine, 2024, 40(9): 1244-1250.
[7]	Jun ZHENG,Qiye WU,Xia ZENG,Zhixian LEI,Dufei. ZHANG. Clinical characteristics and risk factors of the occurrence of hypoxic hepatitis in children with shock [J]. The Journal of Practical Medicine, 2024, 40(15): 2126-2132.
[8]	HU Haiyu, ZHANG Kunlong, CHU Jinhua, WANG Ningling, CHENG Yan.. The distribution and drug resistance ofpathogens of bloodstream infection in pediatric hematology depart⁃ ment in 2016⁃2021 [J]. The Journal of Practical Medicine, 2023, 39(8): 991-996.
[9]	JIN Bei, CHENG Cheng, ZHUANG Hongjie, OUYANG Xiaojun, LI Jie, CHEN Lizhi, JIANG Xiaoyun.. The clinicopathological features and long ⁃ term prognosis inlupus nephritis children of different gender [J]. The Journal of Practical Medicine, 2023, 39(8): 997-1001.
[10]	HUA Qun, HUANG Liqu, ZHOU Xin, BIAN Menglu, CHEN Jun, ZHU Shanliang.. The value of clinical interpretation combined with ultrasonic measurement of rectal transverse diameter in the diagnosis of cystorectal dysfunction in children [J]. The Journal of Practical Medicine, 2023, 39(6): 752-756.
[11]	Shijun YOU,Xue LIANG,Chunlian WANG,Yuhan. SONG. The effect of modified ginseng and schisandra decoction on the efficacy and inflammatory indicators of children with lobar pneumonia （lung spleen deficiency syndrome） caused by mycoplasma pneumonia infection [J]. The Journal of Practical Medicine, 2023, 39(24): 3281-3285.
[12]	Ruhai YAN,Lihong SUN,Yingtong YE,Ming. ZHANG. Clinical characteristics of 88 infants or young children with allergic rhinitis and follow⁃up after drug treatment [J]. The Journal of Practical Medicine, 2023, 39(23): 3101-3105.
[13]	Chenyang CHANG,Shaowen HU,Guoping DENG,Huifang ZHU,Kaiyuan. LUO. Predictive value of neutrophil to lymphocyte and platelet ratio in prognosis of children with sepsis [J]. The Journal of Practical Medicine, 2023, 39(22): 2958-2963.
[14]	Yalan HU,Ting WANG,Qiang. FU. Comparison of therapeutic effects between single⁃dose CTX intravenous pulse therapy and IVIG pulse therapy for severe gastrointestinal involvement of Henoch Schönlein purpura in children [J]. The Journal of Practical Medicine, 2023, 39(22): 2974-2978.
[15]	Li PENG,Lili ZHONG,Lin LIN,Han HUANG,Xiaofang DING,Min CHEN,Xiaojuan. LIN. Expression and clinical significance of MUC5AC in airway of children with mycoplasma pneumoniae pneumonia [J]. The Journal of Practical Medicine, 2023, 39(20): 2618-2622.