Scoring model of convex probe endobronchial ultrasound multimodal imaging in differentiating benign and malignant lung lesions

Abstract

Background: Convex probe endobronchial ultrasound images can reflect the morphology, blood flow status and stiffness of the lesions. Endobronchial ultrasound multimodal imaging has great value for the diagnosis of intrathoracic lymph nodes. This study aimed to analyze the application of endobronchial ultrasound multimodal imaging on lung lesions. Methods: Patients undergoing endobronchial ultrasound-guided transbronchial needle aspiration in Shanghai Chest Hospital from July 2018 to December 2019 were retrospectively enrolled. Nine grayscale features (long and short axes, margin, shape, lobulation sign, echogenicity, necrosis, liquefaction, calcification, and air-bronchogram), blood flow volume and elastography five-score method were analyzed to explore the best diagnostic method. The gold standard for diagnosing lesions depends on the histological and cytopathological findings of endobronchial ultrasound-guided transbronchial needle aspiration, transthoracic biopsy, resected sample of lesions, microbiological examination or clinical follow-up of at least 6 months. Results: Endobronchial ultrasound multimodal imaging of 97 malignant lung lesions and 19 benign lung lesions from 116 patients were analyzed. There were statistically significant differences in distinct margin, presence of lobulation sign, presence of necrosis, and elastography grading score 4-5 between malignant and benign lung lesions, among which presence of lobulation sign and elastography grading score 4-5 were independent predictors. A diagnostic scoring model was then constructed based on the above four features, and when two or more features were present, the sensitivity, specificity, positive predictive value, negative predictive value and accuracy for malignant lung lesions prediction were 92.78%, 57.89%, 91.84%, 61.11% and 87.07%, respectively. Conclusions: The combination of endobronchial ultrasound grayscale and elastography has potential value for malignant and benign lung lesions differentiation. The diagnostic scoring model established in this study needs further validation to guide the malignant and benign diagnosis of lung lesions.

Prediction of lymph node metastasis in operable cervical cancer using clinical parameters and deep learning with MRI data: a multicentre study

“…The larger the tumour volume is, the deeper the surrounding invasion and the more LNM and lymphovascular space invasion (LVSI), and tumour volume can better predict LVSI and LNM status than the largest tumour diameter [ 24 ]. LNs with a short diameter ≥ 10 mm are generally regarded as LNM [ 25 ], so we divided the maximum short diameter of lymph nodes on MR images into two groups according to the cut-off value of 10 mm. The results showed that the probability of LNM in patients with an LN short diameter ≥ 10 mm was significantly higher than that in patients with an LN short diameter < 10 mm.…”

Diagnosis of benign and malignant peripheral lung lesions based on a feature model constructed by the random forest algorithm for grayscale and contrast-enhanced ultrasound

“…Malignant cells grow rapidly and spread through blood vessels and bronchi, resulting in increased longitudinal diameter. During growth, surrounding tissues can exert a certain tension, resulting in larger malignant tumors in a ball, spindle, or irregular shape, with clear lesion boundaries (20,21). The research by Gould et al (22) shows that the size of the lesion is a key factor, and that the larger the diameter of the lesion, the higher the possibility of malignant lesions.…”

The synergized diagnostic value of VTQ with chemokine CXCL13 in lung tumors

“…In recent years, lung ultrasound has gained increasing popularity in clinical practice due to the continuous improvement of ultrasound diagnostic equipment. It is easy to use, affordable, reproducible, and does not involve radiation, making it particularly suitable for emergency patients who cannot undergo invasive operations (8)(9)(10)(11)(12)(13)(14). Virtual touch tissue quantification (VTQ) has been confirmed to have several advantages in diagnosing various lung diseases.…”