Radiomics Study for Discriminating Second Primary Lung Cancers From Pulmonary Metastases in Pulmonary Solid Lesions

Abstract

BackgroundThe objective of this study was to assess the value of quantitative radiomics features in discriminating second primary lung cancers (SPLCs) from pulmonary metastases (PMs).MethodsThis retrospective study enrolled 252 malignant pulmonary nodules with histopathologically confirmed SPLCs or PMs and randomly assigned them to a training or validation cohort. Clinical data were collected from the electronic medical records system. The imaging and radiomics features of each nodule were extracted from CT images.ResultsA rad-score was generated from the training cohort using the least absolute shrinkage and selection operator regression. A clinical and radiographic model was constructed using the clinical and imaging features selected by univariate and multivariate regression. A nomogram composed of clinical-radiographic factors and a rad-score were developed to validate the discriminative ability. The rad-scores differed significantly between the SPLC and PM groups. Sixteen radiomics features and four clinical-radiographic features were selected to build the final model to differentiate between SPLCs and PMs. The comprehensive clinical radiographic–radiomics model demonstrated good discriminative capacity with an area under the curve of the receiver operating characteristic curve of 0.9421 and 0.9041 in the respective training and validation cohorts. The decision curve analysis demonstrated that the comprehensive model showed a higher clinical value than the model without the rad-score.ConclusionThe proposed model based on clinical data, imaging features, and radiomics features could accurately discriminate SPLCs from PMs. The model thus has the potential to support clinicians in improving decision-making in a noninvasive manner.

CT radiomics model combined with clinical and radiographic features for discriminating peripheral small cell lung cancer from peripheral lung adenocarcinoma

“…Among the 1316 radiomics features extracted from CT images, the top 100 mRMR-ranked features were selected for training using the LASSO classifier ( 23 ). Finally, based on the retained 23 features, the rad-score formula was derived from the LASSO weighting coefficients, as shown in Figure 2 , and the rad-score of each lesion was calculated.…”

Radiomics in Lung Metastases: A Systematic Review

“…Zhong et al [ 77 ] analyzed MDCT images of 97 s primary lung cancers and 155 LM, and constructed a nomogram model integrating clinical data, imaging characteristics (such as distribution of lesions, central or peripheral type, contours, and spiculation), and radiomics features. They achieved an excellent (0.94 and 0.90 in the training and validation cohorts, respectively) discriminative capability to distinguish LM from second primitive lung cancer in patients with a history of cancer.…”

“…Three studies (37.5%) [ 55 , 56 , 68 ] evaluated the potential applicability of radiomics models in a clinical setting by means of DCA. In most studies (75%) [ 71 , 72 , 74 , 75 , 76 , 77 ] multiple segmentations were performed to evaluate the robustness of radiomics features in relation to segmentation variability.…”

V7 ENB‐guided thoracoscopic sublobectomy for stage IA synchronous multiple primary lung cancer

“…The overall rate of metachromatic MPLC after lung cancer treatment has previously been reported to be approximately 4%–10%. 21 , 22 However, there are no criteria for diagnosis and surgical resection of SMPLC to date. Precise localization and appropriate surgical procedures based on the number and location of nodules that completely resect and preserve lung function are required.…”

“…After comprehensive therapy, a second primary lung cancer known as metachromatic MPLC might develop in some patients. The overall rate of metachromatic MPLC after lung cancer treatment has previously been reported to be approximately 4%–10% 21,22 . However, there are no criteria for diagnosis and surgical resection of SMPLC to date.…”