[A clinical-radiomics nomogram for differentiating focal organizing pneumonia and lung adenocarcinoma]

OBJECTIVE

To evaluate the performance of a clinical-radiomics model for differentiating focal organizing pneumonia (FOP) and lung adenocarcinoma (LUAD).

METHODS

We retrospectively analyzed the data of 60 patients with FOP confirmed by postoperative pathology at the First Medical Center of the Chinese PLA General Hospital from January, 2019 to December, 2022, who were matched with 120 LUAD patients using propensity score matching in a 1∶2 ratio. The independent risk factors for FOP were identified by logistic regression analysis of the patients' clinical data. The cohort was divided into a training set (144 patients) and a test set (36 patients) by random sampling. Python 3.7 was used for extracting 1835 features from CT image data of the patients. The radiographic features and clinical data were used to construct the model, whose performance was validated using ROC curves in both the training and test sets. The diagnostic efficacy of the model for FOP and LUAD was evaluated and a diagnostic nomogram was constructed.

RESULTS

Statistical analysis revealed that an history of was an independent risk factor for FOP (P=0.016), which was correlated with none of the hematological findings (P > 0.05). Feature extraction and dimensionality reduction in radiomics yielded 30 significant labels for distinguishing the two diseases. The top 3 most discriminative radiomics labels were GraylevelNonUniformity, SizeZoneNonUniformity and shape-Sphericity. The clinical-radiomics model achieved an AUC of 0.909 (95% CI: 0.855-0.963) in the training set and 0.901 (95% CI: 0.803-0.999) in the test set. The model showed a sensitivity of 85.4%, a specificity of 83.5%, and an accuracy of 84.0% in the training set, as compared with 94.7%, 70.6%, and 83.3% in the test set, respectively.

CONCLUSION

The clinical-radiomics nomogram model shows a good performance for differential diagnosis of FOP and LUAD and may help to minimize misdiagnosis-related overtreatment and improve the patients' outcomes.

Algorithmic Approach to the Diagnosis of Organizing Pneumonia: A Correlation of Clinical, Radiologic, and Pathologic Features

Organizing pneumonia (OP), characterized histopathologically by patchy filling of alveoli and bronchioles by loose plugs of connective tissue, may be seen in a variety of conditions. These include but are not limited to after an infection, drug reactions, radiation therapy, and collagen vascular diseases. When a specific cause is responsible for this entity, it is referred to as "secondary OP." When an extensive search fails to reveal a cause, it is referred to as "cryptogenic OP" (previously called "bronchiolitis obliterans with OP"), which is a clinical, radiologic, and pathologic entity classified as an interstitial lung disease. The clinical presentation of OP often mimics that of other disorders, such as infection and cancer, which can result in a delay in diagnosis and inappropriate management of the underlying disease. The radiographic presentation of OP is polymorphous but often has subpleural consolidations with air bronchograms or solitary or multiple nodules, which can wax and wane. Diagnosis of OP sometimes requires histopathologic confirmation and exclusion of other possible causes. Treatment usually requires a prolonged steroid course, and disease relapse is common. The aim of this article is to summarize the clinical, radiographic, and histologic presentations of this disease and to provide a practical diagnostic algorithmic approach incorporating clinical history and characteristic imaging patterns.

Comparison of Spectral and Perfusion Computed Tomography Imaging in the Differential Diagnosis of Peripheral Lung Cancer and Focal Organizing Pneumonia

Objective

To investigate the spectral and perfusion computed tomography (CT) findings of peripheral lung cancer (PLC) and focal organizing pneumonia (FOP) and to compare the accuracy of spectral and perfusion CT imaging in distinguishing PLC from FOP.

Materials and Methods

Patients who were suspected of having lung tumor and underwent “one-stop” chest spectral and perfusion CT, with their diagnosis confirmed pathologically, were prospectively enrolled from September 2020 to March 2021. Patients who were suspected of having lung tumor and underwent “one-stop” chest spectral and perfusion CT, with their diagnosis confirmed pathologically, were prospectively enrolled from September 2020 to March 2021. A total of 57 and 35 patients with PLC and FOP were included, respectively. Spectral parameters (CT_40keV, CT_70keV, CT_100keV, iodine concentration [IC], water concentration [WC], and effective atomic number [Zeff]) of the lesions in the arterial and venous phases were measured in both groups. The slope of the spectral curve (K_70keV) was calculated. The perfusion parameters, including blood volume (BV), blood flow (BF), mean transit time (MTT), and permeability surface (PS), were measured simultaneously in both groups. The differences in the spectral and perfusion parameters between the groups were examined. Receiver operating characteristic (ROC) curves were generated to calculate and compare the area under the curve (AUC), sensitivity, specificity, and accuracy of both sets of parameters in both groups.

Results

The patients’ demographic and clinical characteristics were similar in both groups (P > 0.05). In the arterial and venous phases, the values of spectral parameters (CT_40keV, CT_70keV, spectral curve K_70keV, IC, and Zeff) were greater in the FOP group than in the PLC group (P < 0.05). In contrast, the values of the perfusion parameters (BV, BF, MTT, and PS) were smaller in the FOP group than in the PLC group (P < 0.05). The AUC of the combination of the spectral parameters was larger than that of the perfusion parameters. For the former imaging method, the AUC, sensitivity, and specificity were 0.89 (95% confidence interval [CI]: 0.82–0.96), 0.86, and 0.83, respectively. For the latter imaging method, the AUC, sensitivity, and specificity were 0.80 (95% CI: 0.70–0.90), 0.71, and 0.83, respectively. There was no significant difference in AUC between the two imaging methods (P > 0.05).

Conclusion

Spectral and perfusion CT both has the capability to differentiate PLC and FOP. However, compared to perfusion CT imaging, spectral CT imaging has higher diagnostic efficiency in distinguishing them.