一种基于放射组学的方法，利用肾上腺和肾上腺周围脂肪的 CT 图像，公平分配 COVID-19 医疗资源。

A radiomics based approach using adrenal gland and periadrenal fat CT images to allocate COVID-19 health care resources fairly.

机构信息

Department of Medical Imaging, International Exemplary Cooperation Base of Precision Imaging for Diagnosis and Treatment, NHC Key Laboratory of Pulmonary Immune-related Diseases, Guizhou Provincial People's Hospital, No. 83 Zhongshan East Road, Nan Ming District, 550002, Guiyang, Guiyang, Guizhou Province, China.

School Of Medicine, Guizhou University, 550000, Guiyang, Guizhou province, China.

出版信息

BMC Med Imaging. 2023 Nov 10;23(1):181. doi: 10.1186/s12880-023-01145-9.

DOI:10.1186/s12880-023-01145-9

PMID:37950171

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10636917/

Abstract

BACKGROUND

The value of radiomics features from the adrenal gland and periadrenal fat CT images for predicting disease progression in patients with COVID-19 has not been studied extensively. We assess the value of radiomics features from the adrenal gland and periadrenal fat CT images in predicting COVID-19 disease exacerbation.

METHODS

A total of 1,245 patients (685 moderate and 560 severe patients) were enrolled in a retrospective study. We proposed a 3D V-net to segment adrenal glands in onset CT images automatically, and periadrenal fat was obtained using inflation operation around the adrenal gland. Next, we built a clinical model (CM), three radiomics models (adrenal gland model [AM], periadrenal fat model [PM], and fusion of adrenal gland and periadrenal fat model [FM]), and radiomics nomogram (RN) after radiomics features extracted.

RESULTS

The auto-segmentation framework yielded a dice value 0.79 in the training set. CM, AM, PM, FM, and RN obtained AUCs of 0.717, 0.716, 0.736, 0.760, and 0.833 in the validation set. FM and RN had better predictive efficacy than CM (P < 0.0001) in the training set. RN showed that there was no significant difference in the validation set (mean absolute error [MAE] = 0.04) and test set (MAE = 0.075) between predictive and actual results. Decision curve analysis showed that if the threshold probability was between 0.4 and 0.8 in the validation set or between 0.3 and 0.7 in the test set, it could gain more net benefits using RN than FM and CM.

CONCLUSIONS

Radiomics features extracted from the adrenal gland and periadrenal fat CT images are related to disease exacerbation in patients with COVID-19.

摘要

背景

尚未广泛研究从肾上腺和肾上腺周围脂肪 CT 图像的放射组学特征预测 COVID-19 患者疾病进展的价值。我们评估了从肾上腺和肾上腺周围脂肪 CT 图像的放射组学特征预测 COVID-19 疾病恶化的价值。

方法

共纳入 1245 例患者（685 例中度和 560 例重度患者）进行回顾性研究。我们提出了一种 3D V-net 来自动分割发病 CT 图像中的肾上腺，使用围绕肾上腺的膨胀操作获得肾上腺周围脂肪。然后，我们构建了一个临床模型（CM）、三个放射组学模型（肾上腺模型[AM]、肾上腺周围脂肪模型[PM]和肾上腺和肾上腺周围脂肪融合模型[FM]）以及放射组学列线图（RN），提取放射组学特征后。

结果

自动分割框架在训练集中的骰子值为 0.79。CM、AM、PM、FM 和 RN 在验证集中的 AUC 分别为 0.717、0.716、0.736、0.760 和 0.833。在训练集中，FM 和 RN 比 CM 具有更好的预测效果（P<0.0001）。在验证集（平均绝对误差[MAE] = 0.04）和测试集（MAE = 0.075）中，RN 显示预测结果与实际结果之间没有显著差异。决策曲线分析表明，如果在验证集中阈值概率在 0.4 到 0.8 之间，或者在测试集中阈值概率在 0.3 到 0.7 之间，那么使用 RN 比 FM 和 CM 可以获得更多的净收益。