Murillo-González Alejandro, González David, Jaramillo Laura, Galeano Carlos, Tavera Fabby, Mejía Marcia, Hernández Alejandro, Rivera David Restrepo, Paniagua J G, Ariza-Jiménez Leandro, Garcés Echeverri José Julián, Diaz León Christian Andrés, Serna-Higuita Diana Lucia, Barrios Wayner, Arrázola Wiston, Mejía Miguel Ángel, Arango Sebastián, Marín Ramírez Daniela, Salinas-Miranda Emmanuel, Quintero O L
Department of Mathematical Sciences, Universidad EAFIT, Medellín, Colombia.
Radiology Department, Universidad CES, Medellín, Colombia.
Front Med Technol. 2022 Sep 28;4:980735. doi: 10.3389/fmedt.2022.980735. eCollection 2022.
Determination and development of an effective set of models leveraging Artificial Intelligence techniques to generate a system able to support clinical practitioners working with COVID-19 patients. It involves a pipeline including classification, lung and lesion segmentation, as well as lesion quantification of axial lung CT studies.
A deep neural network architecture based on DenseNet is introduced for the classification of weakly-labeled, variable-sized (and possibly sparse) axial lung CT scans. The models are trained and tested on aggregated, publicly available data sets with over 10 categories. To further assess the models, a data set was collected from multiple medical institutions in Colombia, which includes healthy, COVID-19 and patients with other diseases. It is composed of 1,322 CT studies from a diverse set of CT machines and institutions that make over 550,000 slices. Each CT study was labeled based on a clinical test, and no per-slice annotation took place. This enabled a classification into Normal vs. Abnormal patients, and for those that were considered abnormal, an extra classification step into Abnormal (other diseases) vs. COVID-19. Additionally, the pipeline features a methodology to segment and quantify lesions of COVID-19 patients on the complete CT study, enabling easier localization and progress tracking. Moreover, multiple ablation studies were performed to appropriately assess the elements composing the classification pipeline.
The best performing lung CT study classification models achieved 0.83 accuracy, 0.79 sensitivity, 0.87 specificity, 0.82 F1 score and 0.85 precision for the Normal vs. Abnormal task. For the Abnormal vs COVID-19 task, the model obtained 0.86 accuracy, 0.81 sensitivity, 0.91 specificity, 0.84 F1 score and 0.88 precision. The ablation studies showed that using the complete CT study in the pipeline resulted in greater classification performance, restating that relevant COVID-19 patterns cannot be ignored towards the top and bottom of the lung volume.
The lung CT classification architecture introduced has shown that it can handle weakly-labeled, variable-sized and possibly sparse axial lung studies, reducing the need for expert annotations at a per-slice level.
This work presents a working methodology that can guide the development of decision support systems for clinical reasoning in future interventionist or prospective studies.
确定并开发一套有效的模型，利用人工智能技术生成一个能够支持诊治新冠肺炎患者的临床医生的系统。这涉及一个流程，包括分类、肺部和病变分割，以及对轴向肺部CT研究进行病变定量分析。
引入一种基于密集连接网络（DenseNet）的深度神经网络架构，用于对标记较弱、大小可变（且可能稀疏）的轴向肺部CT扫描进行分类。这些模型在包含超过10个类别的汇总公开数据集上进行训练和测试。为了进一步评估这些模型，从哥伦比亚的多个医疗机构收集了一个数据集，其中包括健康人、新冠肺炎患者和患有其他疾病的患者。它由来自不同CT机器和机构的1322项CT研究组成，共有超过55万层切片。每项CT研究都根据临床检查进行标记，没有进行每层切片的注释。这使得能够将患者分为正常与异常，对于那些被认为异常的患者，还能进一步分为异常（其他疾病）与新冠肺炎。此外，该流程还具有一种方法，可在完整的CT研究中对新冠肺炎患者的病变进行分割和定量分析，从而更便于定位和进展跟踪。此外，还进行了多项消融研究，以适当评估构成分类流程的各个要素。
在正常与异常任务中，表现最佳的肺部CT研究分类模型的准确率为0.83，灵敏度为0.79，特异性为0.87，F1分数为0.82，精确率为0.85。在异常与新冠肺炎任务中，该模型的准确率为0.86，灵敏度为0.81，特异性为0.91，F1分数为0.84，精确率为0.88。消融研究表明，在流程中使用完整的CT研究可带来更高的分类性能，再次表明肺部容积顶部和底部的相关新冠肺炎模式不容忽视。
所引入的肺部CT分类架构表明，它能够处理标记较弱、大小可变且可能稀疏的轴向肺部研究，减少了每层切片级别上专家注释的需求。
这项工作提出了一种可行的方法，可指导未来干预性或前瞻性研究中临床推理决策支持系统的开发。
