Research on bone age of children with complete growth hormone deficiency from Sichuan area by Artificial Intelligence Assisted Bone Age Evaluation System

doi:10.3877/cma.j.issn.1673-5250.2022.04.011

Objective

To explore the accuracy of " Artificial Intelligence (AI) Assisted Bone Age Evaluation System (co-developed by Shanghai Chuyun Medical Technology Company Limited and West China Second Hospital of Sichuan University)" (hereinafter referred to as AI system) for diagnosis and bone age evaluation of children with complete growth hormone deficiency (CGHD).

Methods

A total of 66 children with CGHD from Sichuan area diagnosed in West China Second Hospital of Sichuan University from July 2014 to November 2019 were selected as research subjects and included into study group. And 67 children with normal height from Sichuan area who visited Department of Child Healthcare in cases collected hospital during the same period were selected as control and included into control group. Bone age of each child was examined by anteroposterior X-ray radiography of the left wrist joint. Bone ages of artificial TW₂CHN-radial, ulnar, and short bones (RUS) and TW₂CHN-carpal, TW₂CHN-20, TW₃-RUS and TW₃-carpal (hereinafter referred to as 5 traditional bone ages) and their corresponding percentiles in children with the same gender and age were blindly evaluated by two physicians using TW₂ Bone Age Scoring Method Southern Chinese Standard (hereinafter referred to as TW₂CHN) and TW₃ Bone Age Scoring Method Standard (hereinafter referred to as TW₃). Meanwhile, the AI system was used to evaluate bone age and percentile of AI-TW₂CHN-RUS, AI-TW₂CHN-carpal, AI-TW₂CHN-20, AI-TW₃-RUS and AI-TW₃-carpal (hereinafter referred to as 5 AI bone ages) of each subject by TW₂CHN and TW₃ methods respectively. Sensitivity, specificity, Youden index, accuracy, positive likelihood ratio, negative likelihood ratio, positive predictive value and negative predictive value of diagnosing CGHD children were calculated by using P₅₀, P₂₅, P₁₀, and P₃ values (collectively referred to as P_n values) of 5 traditional bone ages and 5 AI bone ages (hereinafter referred to as 10 bone ages) as critical values for diagnosis of CGHD in children. Kappa coefficient was used to evaluate the consistency of 5 traditional bone age percentile assessment results with the corresponding 5 AI bone age percentile assessment results, as well as the consistency of TW₂CHN-RUS bone age percentile assessment results for 133 subjects by two physicians. The receiver operating characteristic (ROC) curves of 10 bone age percentile assessment results in diagnosis of CGHD were plotted and area under the curve (AUC) was calculated. Bone ages of TW₂CHN and TW₃ were compared by paired t test. The procedures followed in this study were in line with the requirements of newly revised World Medical Association Declaration of Helsinki in 2013. There were no significant differences in age, gender composition and other general clinical data between two groups (P>0.05).

Results

① CGHD diagnosis results of two groups by using P_n values of 10 bone ages as critical values for diagnosis of CGHD children showed that the diagnostic accuracy was the highest (85.0%) when bone age ≤P₁₀ was used as the critical value for diagnosis of CGHD children except for TW₃-RUS bone age. As for TW₂CHN-RUS, TW₂CHN-carpal, TW₂CHN-20, TW₃-carpal, AI-TW₂CHN-RUS, AI-TW₂CHN-carpal, AI-TW₂CHN-20, AI-TW₃-carpal, and AI-TW₃-RUS bone ages, when bone age ≤P₂₅ was taken as the critical value, the diagnostic accuracy of CGHD was the highest, which were 81.9%, 75.2%, 88.0%, 78.2%, 75.2%, 73.6%, 81.2%, 72.9%, 78.9%, respectively. ② Consistency test results showed that bone age percentiles of two groups evaluated by TW₂CHN-RUS and AI-TW₂CHN-RUS, TW₂CHN-carpal and AI-TW₂CHN-carpal, TW₂CHN-20 and AI-TW₂CHN-20, TW₃-RUS and AI-TW₃-RUS, TW₃-carpal and AI-TW₃-carpal were moderately consistent, and the Kappa values were 0.445, 0.578, 0.570, 0.446 and 0.430, respectively ( all P<0.001). ③Consistency test of TW₂CHN-RUS bone age percentile evaluation results of two groups by two physicians showed that Kappa value was 0.790 (P<0.001), indicating a high consistency. ④ ROC curve analysis results of 10 bone age percentile for diagnosis of CGHD in two groups showed that AUC of TW₂CHN-RUS, TW₂CHN-carpal, TW₂CHN-20, TW₃-carpal, TW₃-RUS, AI-TW₂CHN-RUS, AI-TW₂CHN-carpal, AI-TW₂CHN-20, AI-TW₃-carpal, AI-TW₃-RUS bone ages for diagnosis of CGHD children were 0.932, 0.859, 0.915, 0.895, 0.844, 0.823, 0.805, 0.866, 0.860, 0.764 (all P<0.001). ⑤Bone ages of TW₃-RUS, TW₃-carpal, AI-TW₃-RUS and AI-TW₃-carpal in 133 subjects were significantly lower than those of TW₂CHN-RUS, TW₂CHN-carpal, AI-TW₂CHN-RUS and AI-TW₂CHN-carpal, respectively, and all differences were statistically significant (t=21.746, 25.287, 16.498, 9.290; P<0.001).

Conclusions

TW₂CHN and TW₃ method have clinical values in evaluation of bone ages and diagnosis of children with CGHD, and TW₂CHN-RUS bone age has the highest diagnostic efficiency for children with CGDH. Bone ages of children in Sichuan area evaluated by TW₃ method are lower than that of TW₂CHN method, and TW₃ method may not be completely applicable to children in Sichuan area. Bone age of CGHD children in Sichuan area evaluated by AI system has moderate consistency with the results of traditional manual bone age evaluation, but it can be used as an auxiliary tool to help clinicians accurately evaluate the bone age of children.

Key words: Dwarfism, pituitary, Age determination by skeleton, Growth hormone, Artificial intelligence, Tomography, X-ray, Sichuan area, Child

表1 以10种骨龄P₅₀、P₂₅、P₁₀、P₃值作为CGHD诊断临界值对133例受试儿CGHD诊断结果

骨龄百分位数		真阳性数(例)	假阳性数(例)	假阴性数(例)	真阴性数(例)	敏感度(%)	特异度(%)	约登指数(%)	阳性似然比	阴性似然比	阳性预测值(%)	阴性预测值(%)	准确率(%)
TW₂CHN-RUS骨龄
	≤P₅₀	66	25	0	42	100.0	62.7	62.7	2.680	0	72.6	100.0	81.2
	≤P₂₅	42	0	24	67	63.6	100.0	63.6	—	0.364	100.0	73.6	81.9
	≤P₁₀	13	0	53	67	19.7	100.0	19.7	—	0.803	100.0	55.8	60.1
	≤P₃	1	0	65	67	1.5	100.0	1.5	—	0.984	100.0	50.7	51.1
TW₂CHN-carpal骨龄
	≤P₅₀	66	39	0	28	100.0	41.8	41.8	1.718	0	62.8	100.0	70.7
	≤P₂₅	26	8	20	59	56.5	88.0	44.6	4.734	0.494	76.5	74.7	75.2
	≤P₁₀	18	2	48	65	27.2	97.0	24.3	9.136	0.750	90.0	57.5	62.4
	≤P₃	6	0	60	67	9.1	100.0	9.1	—	0.909	100.0	52.7	54.9
TW₂CHN-20骨龄
	≤P₅₀	66	47	0	20	100.0	29.8	29.8	1.425	0	58.4	100.0	64.7
	≤P₂₅	50	0	16	67	75.7	100.0	75.7	—	0.242	100.0	80.7	88.0
	≤P₁₀	23	0	43	67	34.8	100.0	34.8	—	0.651	100.0	60.9	67.7
	≤P₃	6	0	60	67	9.1	100.0	9.0	—	0.909	100.0	52.7	54.9
TW₃-carpal骨龄
	≤P₅₀	66	58	0	9	100.0	13.4	13.4	1.155	0	53.2	100.0	56.4
	≤P₂₅	62	25	4	42	93.9	62.7	56.6	2.517	0.097	71.3	91.3	78.2
	≤P₁₀	42	12	24	55	63.6	82.1	45.7	3.553	0.443	77.8	69.6	72.9
	≤P₃	20	1	46	66	30.3	98.5	28.8	20.303	0.708	95.2	58.9	64.6
TW₃-RUS骨龄
	≤P₅₀	66	61	0	6	100.0	9.0	9.0	1.098	0	52.0	100.0	54.1
	≤P₂₅	64	27	2	40	97.0	59.7	56.7	2.406	0.05	70.3	95.2	78.2
	≤P₁₀	53	7	13	60	80.3	89.6	69.9	7.686	0.22	88.3	82.2	85.0
	≤P₃	31	1	35	66	47.0	98.5	45.0	31.469	0.538	96.9	65.3	72.9
AI-TW₂CHN-RUS骨龄
	≤P₅₀	54	23	12	44	81.8	65.7	47.5	2.383	0.277	70.1	78.6	73.7
	≤P₂₅	34	1	32	66	51.5	98.5	50.0	34.515	0.492	97.1	67.3	75.2
	≤P₁₀	7	0	59	67	10.6	100.0	10.6	—	0.893	100.0	53.2	55.6
	≤P₃	0	0	66	67	0	100.0	0	—	1.000	—	50.4	50.4
AI-TW₂CHN-carpal骨龄
	≤P₅₀	62	37	4	30	93.9	44.8	38.7	1.701	0.135	62.6	88.2	69.2
	≤P₂₅	40	9	26	58	60.6	86.6	47.2	4.511	0.455	81.6	69.0	73.6
	≤P₁₀	13	2	53	65	19.7	97.0	16.7	6.598	0.827	86.7	55.1	58.6
	≤P₃	7	0	59	67	10.6	100.0	10.6	—	0.894	100.0	53.1	55.6
AI-TW₂CHN-20骨龄
	≤P₅₀	64	42	2	25	97.0	37.3	34.3	1.547	0.081	60.4	92.6	66.9
	≤P₂₅	43	2	23	65	65.1	97.0	62.1	21.826	0.359	95.6	73.9	81.2
	≤P₁₀	20	0	46	67	30.3	100.0	30.3	—	0.697	100.0	59.2	65.4
	≤P₃	6	0	60	67	9.1	100.0	9.1	—	0.909	100.0	52.8	54.9
AI-TW₃-carpal骨龄
	≤P₅₀	62	52	4	15	93.9	22.4	16.3	1.210	0.271	54.4	78.9	57.9
	≤P₂₅	51	21	15	46	77.3	68.7	45.9	2.465	0.331	70.8	75.4	72.9
	≤P₁₀	34	10	32	57	51.5	85.1	36.6	3.452	0.570	77.3	64.0	68.4
	≤P₃	12	2	54	65	18.2	97.0	15.2	6.091	0.843	85.7	54.6	57.9
AI-TW₃-RUS骨龄
	≤P₅₀	66	56	0	11	100.0	16.4	16.4	1.197	0	54.1	100.0	57.9
	≤P₂₅	56	18	10	49	84.8	73.1	58.0	3.158	0.207	75.7	83.0	78.9
	≤P₁₀	42	6	24	61	63.6	91.0	54.7	7.106	0.399	87.5	71.8	77.4
	≤P₃	15	0	51	67	22.7	100.0	22.7	—	0.773	100.0	56.8	61.7

表1 以10种骨龄P₅₀、P₂₅、P₁₀、P₃值作为CGHD诊断临界值对133例受试儿CGHD诊断结果

骨龄百分位数		真阳性数(例)	假阳性数(例)	假阴性数(例)	真阴性数(例)	敏感度(%)	特异度(%)	约登指数(%)	阳性似然比	阴性似然比	阳性预测值(%)	阴性预测值(%)	准确率(%)
TW₂CHN-RUS骨龄
	≤P₅₀	66	25	0	42	100.0	62.7	62.7	2.680	0	72.6	100.0	81.2
	≤P₂₅	42	0	24	67	63.6	100.0	63.6	—	0.364	100.0	73.6	81.9
	≤P₁₀	13	0	53	67	19.7	100.0	19.7	—	0.803	100.0	55.8	60.1
	≤P₃	1	0	65	67	1.5	100.0	1.5	—	0.984	100.0	50.7	51.1
TW₂CHN-carpal骨龄
	≤P₅₀	66	39	0	28	100.0	41.8	41.8	1.718	0	62.8	100.0	70.7
	≤P₂₅	26	8	20	59	56.5	88.0	44.6	4.734	0.494	76.5	74.7	75.2
	≤P₁₀	18	2	48	65	27.2	97.0	24.3	9.136	0.750	90.0	57.5	62.4
	≤P₃	6	0	60	67	9.1	100.0	9.1	—	0.909	100.0	52.7	54.9
TW₂CHN-20骨龄
	≤P₅₀	66	47	0	20	100.0	29.8	29.8	1.425	0	58.4	100.0	64.7
	≤P₂₅	50	0	16	67	75.7	100.0	75.7	—	0.242	100.0	80.7	88.0
	≤P₁₀	23	0	43	67	34.8	100.0	34.8	—	0.651	100.0	60.9	67.7
	≤P₃	6	0	60	67	9.1	100.0	9.0	—	0.909	100.0	52.7	54.9
TW₃-carpal骨龄
	≤P₅₀	66	58	0	9	100.0	13.4	13.4	1.155	0	53.2	100.0	56.4
	≤P₂₅	62	25	4	42	93.9	62.7	56.6	2.517	0.097	71.3	91.3	78.2
	≤P₁₀	42	12	24	55	63.6	82.1	45.7	3.553	0.443	77.8	69.6	72.9
	≤P₃	20	1	46	66	30.3	98.5	28.8	20.303	0.708	95.2	58.9	64.6
TW₃-RUS骨龄
	≤P₅₀	66	61	0	6	100.0	9.0	9.0	1.098	0	52.0	100.0	54.1
	≤P₂₅	64	27	2	40	97.0	59.7	56.7	2.406	0.05	70.3	95.2	78.2
	≤P₁₀	53	7	13	60	80.3	89.6	69.9	7.686	0.22	88.3	82.2	85.0
	≤P₃	31	1	35	66	47.0	98.5	45.0	31.469	0.538	96.9	65.3	72.9
AI-TW₂CHN-RUS骨龄
	≤P₅₀	54	23	12	44	81.8	65.7	47.5	2.383	0.277	70.1	78.6	73.7
	≤P₂₅	34	1	32	66	51.5	98.5	50.0	34.515	0.492	97.1	67.3	75.2
	≤P₁₀	7	0	59	67	10.6	100.0	10.6	—	0.893	100.0	53.2	55.6
	≤P₃	0	0	66	67	0	100.0	0	—	1.000	—	50.4	50.4
AI-TW₂CHN-carpal骨龄
	≤P₅₀	62	37	4	30	93.9	44.8	38.7	1.701	0.135	62.6	88.2	69.2
	≤P₂₅	40	9	26	58	60.6	86.6	47.2	4.511	0.455	81.6	69.0	73.6
	≤P₁₀	13	2	53	65	19.7	97.0	16.7	6.598	0.827	86.7	55.1	58.6
	≤P₃	7	0	59	67	10.6	100.0	10.6	—	0.894	100.0	53.1	55.6
AI-TW₂CHN-20骨龄
	≤P₅₀	64	42	2	25	97.0	37.3	34.3	1.547	0.081	60.4	92.6	66.9
	≤P₂₅	43	2	23	65	65.1	97.0	62.1	21.826	0.359	95.6	73.9	81.2
	≤P₁₀	20	0	46	67	30.3	100.0	30.3	—	0.697	100.0	59.2	65.4
	≤P₃	6	0	60	67	9.1	100.0	9.1	—	0.909	100.0	52.8	54.9
AI-TW₃-carpal骨龄
	≤P₅₀	62	52	4	15	93.9	22.4	16.3	1.210	0.271	54.4	78.9	57.9
	≤P₂₅	51	21	15	46	77.3	68.7	45.9	2.465	0.331	70.8	75.4	72.9
	≤P₁₀	34	10	32	57	51.5	85.1	36.6	3.452	0.570	77.3	64.0	68.4
	≤P₃	12	2	54	65	18.2	97.0	15.2	6.091	0.843	85.7	54.6	57.9
AI-TW₃-RUS骨龄
	≤P₅₀	66	56	0	11	100.0	16.4	16.4	1.197	0	54.1	100.0	57.9
	≤P₂₅	56	18	10	49	84.8	73.1	58.0	3.158	0.207	75.7	83.0	78.9
	≤P₁₀	42	6	24	61	63.6	91.0	54.7	7.106	0.399	87.5	71.8	77.4
	≤P₃	15	0	51	67	22.7	100.0	22.7	—	0.773	100.0	56.8	61.7

表2 2位医师对133例受试儿TW₂CHN-RUS骨龄百分位数评价结果的一致性检验(例)

医师B	医师A					合计
医师B	≤P₃	P₃~P₁₀	P₁₀~P₂₅	P₂₅~P₅₀	P₅₀~P₇₅	合计
≤P₃	1	0	1	0	0	2
P₃~P₁₀	0	9	3	0	0	12
P₁₀~P₂₅	0	3	23	2	0	28
P₂₅~P₅₀	0	0	2	43	3	48
P₅₀~P₇₅	0	0	0	4	37	41
P₇₅~P₉₀	0	0	0	0	2	2
合计	1	12	29	49	42	133

表2 2位医师对133例受试儿TW₂CHN-RUS骨龄百分位数评价结果的一致性检验(例)

医师B	医师A					合计
医师B	≤P₃	P₃~P₁₀	P₁₀~P₂₅	P₂₅~P₅₀	P₅₀~P₇₅	合计
≤P₃	1	0	1	0	0	2
P₃~P₁₀	0	9	3	0	0	12
P₁₀~P₂₅	0	3	23	2	0	28
P₂₅~P₅₀	0	0	2	43	3	48
P₅₀~P₇₅	0	0	0	4	37	41
P₇₅~P₉₀	0	0	0	0	2	2
合计	1	12	29	49	42	133

表3 10种骨龄百分位数评价结果对133例受试儿CGHD诊断的ROC曲线分析结果

骨龄	AUC	AUC 95%CI	P值	骨龄	AUC	AUC 95%CI	P值
TW₂CHN-RUS骨龄	0.932	0.894~0.970	<0.001	AI-TW₂CHN-RUS骨龄	0.823	0.752~0.895	<0.001
TW₂CHN-carpal骨龄	0.859	0.798~0.921	<0.001	AI-TW₂CHN-carpal骨龄	0.805	0.731~0.878	<0.001
TW₂CHN-20骨龄	0.915	0.867~0.963	<0.001	AI-TW₂CHN-20骨龄	0.866	0.805~0.927	<0.001
TW₃-RUS骨龄	0.895	0.839~0.951	<0.001	AI-TW₃-RUS骨龄	0.860	0.798~0.922	<0.001
TW₃-carpal骨龄	0.844	0.779~0.910	<0.001	AI-TW₃-carpal骨龄	0.764	0.683~0.846	<0.001

表3 10种骨龄百分位数评价结果对133例受试儿CGHD诊断的ROC曲线分析结果

骨龄	AUC	AUC 95%CI	P值	骨龄	AUC	AUC 95%CI	P值
TW₂CHN-RUS骨龄	0.932	0.894~0.970	<0.001	AI-TW₂CHN-RUS骨龄	0.823	0.752~0.895	<0.001
TW₂CHN-carpal骨龄	0.859	0.798~0.921	<0.001	AI-TW₂CHN-carpal骨龄	0.805	0.731~0.878	<0.001
TW₂CHN-20骨龄	0.915	0.867~0.963	<0.001	AI-TW₂CHN-20骨龄	0.866	0.805~0.927	<0.001
TW₃-RUS骨龄	0.895	0.839~0.951	<0.001	AI-TW₃-RUS骨龄	0.860	0.798~0.922	<0.001
TW₃-carpal骨龄	0.844	0.779~0.910	<0.001	AI-TW₃-carpal骨龄	0.764	0.683~0.846	<0.001

图1 10种骨龄百分位数评价结果对133例受试儿CGHD诊断的ROC曲线注：CGHD为完全性生长激素缺乏症。ROC曲线为受试者工作特征曲线。TW₂CHN为《TW₂骨龄评分法中国未成年人南方标准》。RUS为桡、尺、掌指骨，carpal为腕骨。AI为人工智能

表4 133例受试儿TW₂CHN与TW₃骨龄评价结果比较(岁，±s)

受试儿骨龄	例数	骨龄	受试儿骨龄	例数	骨龄	受试儿骨龄	例数	骨龄	受试儿骨龄	例数	骨龄
TW₂CHN-RUS骨龄	133	7.9±2.9	TW₂CHN-carpal骨龄	133	7.7±3.0	AI-TW₂CHN-RUS骨龄	133	8.1±2.9	AI-TW₂CHN-carpal骨龄	133	7.8±3.0
TW₃-RUS骨龄	133	6.9±2.8	TW₃-carpal骨龄	133	7.1±3.1	AI-TW₃-RUS骨龄	133	7.1±3.0	AI-TW₃-carpal骨龄	133	7.3±2.9
t值		21.746	t值		25.287	t值		16.498	t值		9.290
P值		<0.001	P值		<0.001	P值		<0.001	P值		<0.001

表4 133例受试儿TW₂CHN与TW₃骨龄评价结果比较(岁，±s)

受试儿骨龄	例数	骨龄	受试儿骨龄	例数	骨龄	受试儿骨龄	例数	骨龄	受试儿骨龄	例数	骨龄
TW₂CHN-RUS骨龄	133	7.9±2.9	TW₂CHN-carpal骨龄	133	7.7±3.0	AI-TW₂CHN-RUS骨龄	133	8.1±2.9	AI-TW₂CHN-carpal骨龄	133	7.8±3.0
TW₃-RUS骨龄	133	6.9±2.8	TW₃-carpal骨龄	133	7.1±3.1	AI-TW₃-RUS骨龄	133	7.1±3.0	AI-TW₃-carpal骨龄	133	7.3±2.9
t值		21.746	t值		25.287	t值		16.498	t值		9.290
P值		<0.001	P值		<0.001	P值		<0.001	P值		<0.001

[1]	中华医学会儿科学分会内分泌遗传代谢学组．矮身材儿童诊治指南[J]. 中华儿科杂志，2008, 46(6): 428-430. DOI: 10.3760/cma.j.issn.0578-1310.2008.06.107.
[2]	韩晓伟，董治亚，张婉玉，等. 矮小症病因及临床特征分析[J]. 临床儿科杂志，2019, 37(1): 39-42. DOI: 10.3969/j.issn.1000-3606.2019.01.010.
[3]	Richmond E, Rogol AD. Testing for growth hormone deficiency in children[J]. Growth Horm IGF Res, 2019, 50: 57-60. DOI: 10.1016/j.ghir.2019.12.002.
[4]	谭梦婷，钟华，徐小红，等. 骨龄测定评估儿童生长发育的价值分析[J]. 锦州医科大学学报，2019, 40(2): 27-29. DOI: 10.13847/j.cnki.lnmu.2019.02.009.
[5]	卢皓明．不同骨龄测评方法在特发性矮小症患儿数字骨龄片评价中的应用[J].现代医用影像学，2021, 30(7): 1307-1309. DOI: 10.3969/j.issn.1006-7035.2021.07.036.
[6]	易新容，何鑫，贾富全. CHN法评估呼和浩特地区汉族儿童青少年手腕部骨龄的结果分析[J]. 内蒙古医学杂志，2021, 53(8): 902-905,封2. DOI: 10.16096/J.cnki.nmgyxzz.2021.53.08.002.
[7]	叶义言．新版骨龄评分法概述[J]. 中华儿科杂志，2004, 42(1): 32-34. DOI: 10.3760/j.issn:0578-1310.2004.01.009.
[8]	叶义言，王创新. 儿童青少年骨龄评分方法的研究[J]. 湖南医科大学学报，1991, 16(4): 355-359.
[9]	陈卫富，周爱萍，顾红丹，等. 血清胰岛素样生长因子-1、胰岛素样生长因子结合蛋白-3及骨龄在矮小症儿童诊断中的价值[J]. 中国妇幼保健，2018, 33(9): 2047-2050. DOI: 10.7620/zgfybj.j.issn.1001-4411.2018.09.42.
[10]	邓演超，李全双，沈红艳，等. 胰岛素样生长因子在诊断儿童生长激素缺乏症中的临床价值[J].中国校医，2019, 33(11): 807-808, 814.
[11]	王永梅，江咏梅，于凡，等. 生长激素缺乏症儿童骨代谢标志物水平分析[J].国际检验医学杂志，2021, 42(15): 1807-1810. DOI: 10.3969/j.issn.1673-4130.2021.15.004.
[12]	宁刚，吴康敏，李开明，等. 骨龄测定及成年身高预测软件在儿科临床的应用价值[J]. 华西医科大学学报，2002, 33(2): 302-304. DOI: 10.3969/j.issn.1672-173X.2002.02.044.
[13]	叶义言．中国儿童骨龄评分法[M]. 北京：人民卫生出版社，2005: 63-172.
[14]	程琳． TW₂、TW₃两种骨龄评估方法用于GHD患儿骨龄推断的临床应用比较[D]. 南宁：广西医科大学，2012.
[15]	陈伟伟，刘焕欣，刘晶，等. 儿童身材矮小的病因分析及遗传学诊断[J]. 中国当代儿科杂志，2019, 21(4): 381-386. DOI: 10.7499/j.issn.1008-8830.2019.04.015.
[16]	李坚旭，卢秋婷，邱明慧，等. 265例儿童矮小症的病因分析[J]. 实用临床医学，2017, 18(1): 64-65. DOI: 10.13764/j.cnki.lcsy.2017.01.025.
[17]	白云．儿童矮小症的原因分析与预防[J]. 中国卫生标准管理，2021, 12(11): 8-10. DOI: 10.3969/j.issn.1674-9316.2021.11.003.
[18]	曹应琼，他卉，万莉，等. 2016年四川省儿童青少年学生生长发育与营养状况分析[J]. 现代预防医学，2019, 46(1): 48-52.
[19]	李彬，林家健，林育成，等. 人工智能在儿童骨龄X线影像诊断中的应用研究[J]. 中国医学工程，2022, 30(3): 83-85. DOI: 10.19338/j.issn.1672-2019.2022.03.020.
[20]	宁刚，曲海波，刘关键，等. TW法在女性患儿特发性性早熟尺桡骨和手短骨骨龄评价的诊断性试验研究[J/OL]. 中华妇幼临床医学杂志(电子版), 2008, 4(5): 16-20. DOI: 10.3969/j.issn.1673-5250.2008.05.005.
[21]	崔蕴璞，张铭涛，王新利. 不同病因矮身材儿童TW₂-R、C、T骨龄评分特征研究[J]. 中国当代儿科杂志，2015, 7(5): 464-468. DOI: 10.7499/j.issn.1008-8830.2015.05.010.
[22]	白万晶，宁刚，曲海波，等. TW₂法3种标准用于中枢性性早熟患儿骨龄推断的比较[J]. 法医学杂志，2010, 26(3): 181-184. DOI: 10.3969/j.issn.1004-5619.2010.03.006.
[23]	胡婷鸿，火忠，刘太昂，等. 基于深度学习实现维吾尔族青少年左手腕关节骨龄自动化评估[J]. 法医学杂志，2018, 34(1): 27-32. DOI: 10.3969/j.issn.1004-5619.2018.01.006.
[24]	占梦军，张世杰，刘力，等. 基于深度学习自动化评估四川汉族青少年左手腕关节骨龄[J]. 中国法医学杂志，2019, 34(5): 427-432. DOI: 10.13618/j.issn.1001-5728.2019.05.002.
[25]	杨姣．人工智能在儿童骨龄影像诊断的应用及发展[J]. 江苏卫生事业管理，2020, 31(1): 89-92. DOI: 10.3969/j.issn.1005-7803.2020.01.027.
[26]	次旦旺久，拉巴顿珠，王凤丹，等. 三种方法评估藏族儿童骨龄效果比较及藏族儿童骨龄发育特点[J]. 协和医学杂志，2021, 12(3): 411-416. DOI: 10.12290/xhyxzz.20200259.
[27]	彭乐媛，段玉梅，王永芹，等. 4种新型人工智能算法在区域人群骨龄测定中的价值[J]. 中国医学装备，2021, 18(11): 113-117. DOI: 10.3969/J.ISSN.1672-8270.2021.11.027.

[1]	Xuan Zhang, Yutong Ma, Yuqian Miao, Yun Zhang, Shiwen Wu, Xiaochu Dang, Yingying Chen, Zhaoming Zhong, Xuejuan Wang, Miao Hu, Yanfeng Sun, Xiuzhu Ma, Faqin Lyu, Haiyan Kou. Ultrasound assessment of diaphragm function in pediatric patients with Duchenne muscular dystrophy[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(10): 1068-1073.
[2]	Baofu Zhang, Jin Yu, Jingjing Ye, Jiangen Yu, Xiaohui Ma, Xiwang Liu. Echocardioimagedata diagnosis of anomalous pulmonary venous connection caused by congenital malposition of the septum primum[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(10): 1074-1080.
[3]	Dan Han, Ting Wang, Huan Xiao, Lirong Zhu, Jingyu Chen, Yi Tang. Diagnostic value of contrast enhanced ultrasound versus contrast enhanced computed tomography in benign and malignant liver lesions in children[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(09): 939-944.
[4]	Meifang Zhang, Ying Tan, Qiaozhen Zhu, Xin Wen, Ying Yuan, Yue Qin, Hongbo Guo, Lingxiu Hou, Wenlan Huang, Guiyan Peng, Shengli Li. Artificial intelligence-based quality control of mid-sagittal plane ultrasound images for first trimester fetal crown-rump length[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(09): 945-950.
[5]	Tingting Liu, Yanbing Lin, Shan Wang, Murong Chen, Zijian Tang, Dongling Dai, Bei Xia. Evaluation of metabolic dysfunction-associated fatty liver disease in children by ultrasound-guided attenuation parameter[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(08): 787-794.
[6]	Yuhan Zhou, Huan Xiao, Chunjiang Yang, Juan Zhou, Lirong Zhu, Juan Xu, Fangting Mou. Diagnostic value of ultrasound in children with temporary hip synovitis[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(08): 795-800.
[7]	Jiu Wang, Jun Chen, Xia Zhu, Yangjin Mima, Sheng Zhao, Xinlin Chen, Jianhua Li, Shuang Wang. Effect of implementing fetal systemic ultrasound screening in Material and Child Health Hospital of Shannan[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(07): 728-733.
[8]	Jie Mi, Chen Chen, Jialing Li, Haina Pei, Hengbo Zhang, Fei Li, Dongjie Li. Analysis of the characteristics of children's head and face trauma[J]. Chinese Journal of Injury Repair and Wound Healing(Electronic Edition), 2023, 18(06): 511-515.
[9]	Tao Ma, Chunwei Ye, Tao Liu, Wenxi Peng, Zhipeng Li. Comparison of laparoscopic and open disconnected pyeloplasty in the treatment of ureteropelvic junction obstruction in children[J]. Chinese Journal of Endourology(Electronic Edition), 2023, 17(06): 605-610.
[10]	Lei Wang, Shaohua Wang, Haizhen Niu, Tengfei Yin. Application of early warning intervention based on risk assessment in perioperative nursing of children with inguinal hernia[J]. Chinese Journal of Hernia and Abdominal Wall Surgery(Electronic Edition), 2023, 17(06): 768-772.
[11]	Fang Li, Rui Xu, Yangyang Li, Xiuquan Shi. Application of the concept of evidence-based medicine in children with inguinal hernia[J]. Chinese Journal of Hernia and Abdominal Wall Surgery(Electronic Edition), 2023, 17(06): 782-786.
[12]	Xiaowei Xing, Yuchen Liu, Bing Zhao, Minggang Wang. A research on predictive value of convolutional neural network based on preoperative abdominal CT for recurrence of incisional hernia after surgical repair[J]. Chinese Journal of Hernia and Abdominal Wall Surgery(Electronic Edition), 2023, 17(06): 677-681.
[13]	Xiangyu Zhu, Jianmei Wang, Hui Zhang, Hongying Ye. Correlation analysis between left ventricular function parameters and liver cirrhosis using non-invasive left ventricular pressure-strain cycle[J]. Chinese Journal of Digestion and Medical Imageology(Electronic Edition), 2023, 13(06): 494-498.
[14]	Shaohong Zhuo, Xiuling Lin, Cuimei Zhou, Weilian Xiong, Xingzao Ma. Application value of CD64 index combined with serum SAA/CRP and PCT in the diagnosis of children with infectious gastrointestinal diseases[J]. Chinese Journal of Digestion and Medical Imageology(Electronic Edition), 2023, 13(06): 505-509.
[15]	Jing Li, Lingling Zhang, Wei Xing. Value of concept of interest induction before anesthesia induction in pediatric surgery and its effect on family satisfaction[J]. Chinese Journal of Clinicians(Electronic Edition), 2023, 17(07): 812-817.

Viewed

Full text

Abstract

Please choose a citation manager

Content to export