Radiomics Nomogram Analyses for Differentiating Pneumonia and Acute Paraquat Lung Injury

Abstract

Paraquat poisoning has become a serious public health problem in some Asian countries because of misuse or suicide. We sought to develop and validate a radiomics nomogram incorporating radiomics signature and laboratory bio-markers, for differentiating bacterial pneumonia and acute paraquat lung injury. 180 patients with pneumonia and acute paraquat who underwent CT examinations between December 2014 and October 2017 were retrospectively evaluated for testing and validation. Clinical information including demographic data, clinical symptoms and laboratory test were also recorded. A prediction model was built by using backward logistic regression and presented on a nomogram. The radiomics-based features yielded areas under the receiver operating characteristic curve of 0.870 (95% CI 0.757–0.894), sensitivity of 0.857, specificity of 0.804, positive predictive value of 83.3%, negative predictive value of 0.818 in the primary cohort, while in the validation cohort the model showed similar results (0.865 (95% CI 0.686–0.907), 0.833, 0.792, 81.5%, respectively). The individualized nomogram included radiomics signature, body temperature, nausea and vomiting, and aspartate transaminase. We have developed a radiomics nomogram that combination of the radiomics features and clinical risk factors to differentiate paraquat lung injury and pneumonia for patients with an unclear medical history of exposure to paraquat poisoning, providing appropriate therapy decision support.

The study of automatic machine learning base on radiomics of non-focus area in the first chest CT of different clinical types of COVID-19 pneumonia

“…Therefore, even if no lesions are found on the CT images, we can also analyze different types of texture features extracted to determine whether the lung tissue is damaged. In this study, through the analysis of AUTO-ML classification model, there are significant differences in the texture characteristics of non-focus area in the first CT image between the moderate and severe groups, and there are also significant differences between the moderate and severe groups and the control group, which is similar to the results of Yanling’s study of different types of pneumonia with radiomics 15 .…”

“…In this study, we used Python language (version 3.7.4) program to call the Pyrometric package (version 2.2.0) 14 , 15 . In the process of program running, seven filters are used to process the original VOI.…”

The study of non-focus area in the first chest CT of different clinical types of COVID-19 pneumonia: A study on automatic machine learning of Radiomics

“…Therefore, even if no lesions are found on the CT images, we can also analyze different types of texture features extracted to determine whether the lung tissue is damaged. In this study, through the analysis of AUTO-ML classi cation model, there are signi cant differences in the texture characteristics of non-focus area in the rst CT image between the moderate and severe groups, and there are also signi cant differences between the moderate and severe groups and the control group, which is similar to the results of Yanling's study of different types of pneumonia with radiomics [11] .…”

“…Image texture feature extraction is realized by Pyradiomics package (version 2.2.0) in Python 3.7 [10,11] .…”

CT-based Radiomics Combined with Signs: A Valuable Tool to help Physician Discriminate COVID-19 and Other Viral Pneumonia

“…In previous studies, radiomics had outstanding performance in the diagnosis, staging, prognosis, and treatment response prediction of tumors [13][14][15] . In addition, radiomics can give rise to a deeper understanding of the heterogeneity of pneumonia lesions [19,25,26] . Therefore, radiomics is theoretically a feasible method to distinguish COVID-19 pneumonia from other viral pneumonia.…”