CT高分辨算法与标准算法图像重建密度测量对亚厘米肺结节鉴别诊断的临床价值

The clinical value of CT high-resolution algorithm and standard algorithm image reconstruction density measurement in the differential diagnosis of subcentimeter pulmonary nodules

目的探讨高分辨算法与标准算法重建图像对亚厘米肺结节CT值测量的差异性以及对良恶性鉴别诊断的价值。方法选取我院有手术病理结果的高分辨算法薄层重建图像测量CT值≥0 HU(根据CT值定义公式,水的CT值为0 HU)的亚厘米肺结节患者98例,且同时具有标准算法薄层重建图像。为进一步区分其内完全实性与少量含气结节,以水的CT值为界限,按照标准算法重建图像测量CT值结果≥0 HU(n=52)、<0 HU(n=46)分成两组,比较两组不同重建算法测得病灶CT值的差异,以及病理良恶性概率变化,分析诊断效能。结果全部病灶高分辨算法CT值均高于标准算法,其差值在两组间差异有统计学意义(P<0.01)。高分辨算法测得CT值≥0 HU的全部入组病例中,恶性占37%(36/98),良性占63%(62/98)。采用标准算法测得的病灶CT值仍然≥0 HU的病灶共52例,良性占比升至85%(44/52);病灶CT值变为<0 HU共46例,恶性占比升至61%(28/46)。ROC曲线显示标准算法图像CT值对病灶良恶性的鉴别诊断效能高于高分辨算法。结论采用标准算法重建图像观察和测量病灶的密度较高分辨算法更为真实准确。

Objective To investigate the difference between high-resolution and standard image reconstruction on subcentimeter lung nodule CT value measurement,and its influence on differential diagnosis of benign and malignant pulmonary nodules.Methods Ninety-eight patients with subcentimeter pulmonary nodules with CT value≥0 HU(according to the definition formula of CT value,the CT value of water is 0 HU)were selected by high-resolution thin-layer reconstruction images with surgical and pathological results in our hospital,and thin-layer reconstruction images with standard algorithm were also available.In order to further distinguish the completely solid nodular from the small number of air-bearing nodular,CT values of water were taken as the boundary,and the reconstructed images were divided into two groups according to the standard algorithm to measure CT values≥0 HU(n=52 cases)and<0 HU(n=46 cases).The differences of CT values measured by different reconstruction algorithms and the pathological benign and malignant probability changes between the two groups were compared,and the diagnostic efficiency was analyzed.Results All the CT values of the high-resolution algorithm were higher than those of the standard algorithm,and the difference was statistically significant between the two groups(P<0.01).Among all the enrolled cases with CT values≥0 HU measured by high-resolution algorithm,37%(36/98)were malignant and 63%(62/98)were benign.There were 52 cases of lesions whose CT value was still≥0 HU measured by standard algorithm,and the benign proportion increased to 85%(44/52).The CT value of the lesions was<0 HU in 46 cases,and the malignant rate increased to 61%(28/46).ROC curve showed that the CT value of standard algorithm was more effective than that of high resolution algorithm in differentiating benign and malignant lesions.Conclusion Using standard algorithm to reconstruct image to observe and measure lesion density is higher,and the resolution algorithm is more real and accurate.