Yan Taocui, Qin Jinjie, Zhang Yulin, Li Qiuni, Han Baoru, Jin Xin
Medical Data Science Academy, College of Medical Informatics, Chongqing Medical University, Chongqing, China.
Department of Radiology, Children's Hospital of Chongqing Medical University, Chongqing, China.
Front Pediatr. 2023 Feb 23;11:1131273. doi: 10.3389/fped.2023.1131273. eCollection 2023.
To explore the application of the proposed intelligent image processing method in the diagnosis of aortic coarctation computed tomography angiography (CTA) and to clarify its value in the diagnosis of aortic coarctation based on the diagnosis results.
Fifty-three children with coarctation of the aorta (CoA) and forty children without CoA were selected to constitute the study population. CTA was performed on all subjects. The minimum diameters of the ascending aorta, proximal arch, distal arch, isthmus, and descending aorta were measured using manual and intelligent methods, respectively. The Wilcoxon signed-rank test was used to analyze the differences between the two measurements. The surgical diagnosis results were used as the gold standard, and the diagnostic results obtained by the two measurement methods were compared with the gold standard to quantitatively evaluate the diagnostic results of CoA by the two measurement methods. The Kappa test was used to analyze the consistency of intelligence diagnosis results with the gold standard.
Whether people have CoA or not, there was a significant difference ( < 0.05) in the measurements of the minimum diameter at most sites using the two methods. However, close final diagnoses were made using the intelligent method and the manual. Meanwhile, the intelligent measurement method obtained higher accuracy, specificity, and AUC (area under the curve) compared to manual measurement in diagnosing CoA based on Karl's classification (accuracy = 0.95, specificity = 0.9, and AUC = 0.94). Furthermore, the diagnostic results of the intelligence method applied to the three criteria agreed well with the gold standard (all kappa ≥ 0.8). The results of the comparative analysis showed that Karl's classification had the best diagnostic effect on CoA.
The proposed intelligent method based on image processing can be successfully applied to assist in the diagnosis of CoA.
探讨所提出的智能图像处理方法在主动脉缩窄计算机断层扫描血管造影（CTA）诊断中的应用，并根据诊断结果阐明其在主动脉缩窄诊断中的价值。
选取53例主动脉缩窄（CoA）患儿和40例无CoA患儿组成研究人群。对所有受试者进行CTA检查。分别采用手动和智能方法测量升主动脉、主动脉弓近端、主动脉弓远端、峡部和降主动脉的最小直径。采用Wilcoxon符号秩检验分析两种测量方法之间的差异。以手术诊断结果作为金标准，将两种测量方法获得的诊断结果与金标准进行比较，以定量评估两种测量方法对CoA的诊断结果。采用Kappa检验分析智能诊断结果与金标准的一致性。
无论是否患有CoA，两种方法在大多数部位最小直径的测量上均存在显著差异（<0.05）。然而，智能方法和手动方法得出的最终诊断结果相近。同时，基于卡尔分类法，在诊断CoA时，智能测量方法相比手动测量获得了更高的准确性、特异性和曲线下面积（AUC）（准确性 = 0.95，特异性 = 0.9，AUC = 0.94）。此外，应用于三个标准的智能方法诊断结果与金标准吻合良好（所有kappa≥0.8）。对比分析结果表明，卡尔分类法对CoA的诊断效果最佳。
所提出的基于图像处理的智能方法可成功应用于辅助CoA的诊断。
Zotero 插件
