Malignant Peripheral Pulmonary Lesions Research Articles

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.

To construct a predictive model for benign and malignant peripheral pulmonary lesions (PPLs) using a random forest algorithm based on grayscale ultrasound and ultrasound contrast, and to evaluate its diagnostic value. We selected 254 patients with PPLs detected using chest lung computed tomography between October 2021 and July 2023, including 161 malignant and 93 benign lesions. Relevant variables for judging benign and malignant PPLs were screened using logistic regression analysis. A model was constructed using the random forest algorithm, and the test set was verified. Correlations between these relevant variables and the diagnosis of benign and malignant PPLs were evaluated. Age, lesion shape, size, angle between the lesion border and chest wall, boundary clarity, edge regularity, air bronchogram, vascular signs, enhancement patterns, enhancement intensity, homogeneity of enhancement, number of non-enhancing regions, non-enhancing region type, arrival time (AT) of the lesion, lesion-lung AT difference, AT difference ratio, and time to peak were the relevant variables for judging benign and malignant PPLs. Consequently, a model and receiver operating characteristic curve were constructed with an AUC of 0.92 and an accuracy of 88.2%. The test set results showed that the model had good predictive ability. The index with the highest correlation for judging benign and malignant PPLs was the AT difference ratio. Other important factors were lesion size, patient age, and lesion morphology. The random forest algorithm model constructed based on clinical data and ultrasound imaging features has clinical application value for predicting benign and malignant PPLs.

Peripheral Pulmonary Lesions Classification Using Endobronchial Ultrasonography Images Based on Bagging Ensemble Learning and Down-Sampling Technique

Lung cancer is the second most common cancer in the world, with an average five-year survival rate of 15 percent. Approximately 238,340 people were diagnosed in the US in 2023 based on the estimation of the American Cancer Society, and 127,070 people died from it. Cancer has always been a big problem for scientists. There has never been a good solution. So, the early detection of cancer is particularly important. In recent years, endobronchial ultrasonography (EBUS) images have been used more and more in the diagnosis of lung cancer because of their advantages of good real-time performance, no radiation, and superior performance. This research aims to develop a computer-aided diagnosis (CAD) system to differentiate benign and malignant peripheral pulmonary lesions (PPLs). The efficacy of this framework was evaluated on a dataset comprising 69 cases of lung carcinoma, encompassing 59 malignant instances and 10 benign cases. The final experimental results of accuracy, F1-Score, AUC, PPV, NPV, sensitivity, and specificity were 0.7, 0.63, 0.75, 0.84, 0.68, 0.56, and 0.85, respectively. From the experiment results, the developed CAD system has the potential ability to diagnose PPLs by using the EBUS images based on Deep Learning.

Contrast-Enhanced Ultrasound in Distinguishing between Malignant and Benign Peripheral Pulmonary Consolidations: The Debated Utility of the Contrast Enhancement Arrival Time

Background. Limited studies and observations conducted on a too small number of patients prevent determining the actual clinical utility of pulmonary contrast-enhanced ultrasound (CEUS). The aim of the present study was to examine the efficacy of contrast enhancement (CE) arrival time (AT) and other dynamic CEUS findings for differentiating between malignant and benign peripheral lung lesions. Methods. 317 inpatients and outpatients (215 men, 102 women; mean age: 52 years) with peripheral pulmonary lesions were included in the study and underwent pulmonary CEUS. Patients were examined in a sitting position after receiving an intravenous injection of 4.8 mL of sulfur hexafluoride microbubbles stabilized by a phospholipid shell as ultrasound contrast agent (SonoVue-Bracco; Milan, Italy). Each lesion was observed for at least 5 min in real-time and the following temporal characteristics of enhancement were detected: the arrival time (AT) of microbubbles in the target lesion; the enhancement pattern; the wash-out time (WOT) of microbubbles. Results were then compared in light of the definitive diagnosis of community acquired pneumonia (CAP) or malignancies, which was not known at the time of CEUS examination. All malignant cases were diagnosed by histological results, while pneumonia was diagnosed on the basis of clinical and radiological follow-up, laboratory findings and, in some cases, histology. Results. CE AT has not been shown to differ between benign and malignant peripheral pulmonary lesions. The overall diagnostic accuracy and sensibility of a CE AT cut-off value < 10 s in discriminating benign lesions were low (diagnostic accuracy: 47.6%; sensibility: 5.3%). Poor results were also obtained in the sub-analysis of small (mean diameter < 3 cm) and large (mean diameter > 3 cm) lesions. No differences were recorded in the type of CE pattern showed between benign and malignant peripheral pulmonary lesions. In benign lesions we observed a higher frequency of delayed CE wash-out time (WOT) > 300 s. Anyhow, a CE WOT cut-off value > 300 s showed low diagnostic accuracy (53.6%) and sensibility (16.5%) in discriminating between pneumonias and malignancies. Similar results were also obtained in the sub-analysis by lesion size. Squamous cell carcinomas showed a more delayed CE AT compared to other histopathology subtypes. However, such a difference was statistically significant with undifferentiated lung carcinomas. Conclusions. Due to an overlap of CEUS timings and patterns, dynamic CEUS parameters cannot effectively differentiate between benign and malignant peripheral pulmonary lesions. Chest CT remains the gold standard for lesion characterization and the eventual identification of other pneumonic non-subpleural localizations. Furthermore, in the case of malignancy, a chest CT is always needed for staging purposes.

Proposal of a novel pipeline involving precise bronchoscopy of distal peripheral pulmonary lesions for genetic testing

Next-generation sequencing (NGS) has become increasingly more important for lung cancer management. We now expect biopsies to be sensitive, safe, and yielding sufficient samples for NGS. In this study, we propose ultraselective biopsy (USB) with sample volume adjustment (SVA) as a novel method that integrates an ultrathin bronchoscope, radial probe endobronchial ultrasound, and the direct oblique method for ultraselective navigation, and adjustment of sample volume for NGS. Our purpose was to estimate the diagnostic potential and the applicability of USB-SVA for amplicon-based NGS analysis. The diagnostic yield of bronchoscopy in forty-nine patients with malignant peripheral pulmonary lesions (PPLs) was retrospectively analyzed, and amplicon-based NGS analysis was performed on samples from some patients using USB. The diagnostic yields of distal PPLs in the USB group were significantly higher than those in the non-USB group (90.5% vs. 50%, respectively, p = 0.015). The extracted amounts of nucleic acids were at least five times the minimum requirement and the sequence quality met the criteria for the Oncomine™ Target Test. Only the tumor cell content of some samples was insufficient. The feasibility of the pipeline for USB, SVA, and amplicon-based NGS in distal PPLs was demonstrated.

Role of Contrast-Enhanced Ultrasound in Pulmonary Lesions: 5-Year Experience at a Single Center.

Contrast-enhanced ultrasound (CEUS) for the differentiation of benign and malignant peripheral pulmonary lesions has been considered experimental for many years. This study was aimed at evaluating the feasibility of CEUS as a diagnostic modality in this area of discussion. CEUS diagnostic accuracy was explored by comparison with contrast-enhanced computed tomography (CECT). The collective included 449 patients with 449 definitive diagnoses (benign, 178; malignant, 271). Logistic regression analysis of CEUS data revealed that delayed time to enhancement, chaotic pattern of distribution of vessels and mild extent of enhancement were independent risk factors for predicting malignancy. Time to wash-out and homogeneity of enhancement did not differ between the two groups (p > 0.05). Based on histopathology or clinical follow-up as a reference standard, CEUS and CECT had similar diagnostic accuracies of 80.16% and 81.75%, respectively. CEUS is a potentially useful imaging tool for diagnosing peripheral pulmonary lesions.

Time Difference of Arrival on Contrast-Enhanced Ultrasound in Distinguishing Benign Inflammation From Malignant Peripheral Pulmonary Lesions.

IntroductionWorldwide, the incidence and mortality of lung cancer are at the highest levels, and the most lesions are located in the lung periphery. Despite extensive screening and diagnosis, the pathologic types of peripheral pulmonary lesions (PPLs) are difficult to diagnose by noninvasive examination. This study aimed to identify a novel index—time difference of arrival (TDOA)—to discriminate between benign inflammation and malignant PPLs.MethodsUsing contrast-enhanced ultrasound (CEUS), we retrospectively analyzed 96 patients with PPLs who had undergone biopsy to confirm the pathologic types. All data were collected from Dazhou Central Hospital between December 2012 and July 2019. The parameters of CEUS were analyzed by two assistant chief physicians of ultrasound diagnosis. Area under the receiver operating characteristic curve analysis, sensitivity, specificity, positive predictive value, and negative predictive value were calculated to assess the diagnostic ability of different indices.ResultsWe found that the TDOA significantly distinguished benign inflammation from malignant lesions. The TDOA was markedly increased in patients with malignant lesions than benign inflammation lesions (P < 0.001). Compared with conventional time-intensity curve (TIC) indices, TDOA showed high diagnostic accuracy (area under the curve = 0.894). Moreover, conventional diagnostic indices did not affect the diagnostic performance of TDOA by adjusting the receiver operating characteristic curve.ConclusionTDOA is feasible for the diagnosis of benign inflammation and malignant PPLs.

Endobronchial Ultrasound Combined with Clinical Data for Predicting Malignant Peripheral Pulmonary Lesions.

IntroductionThis study was to develop a simple model for predicting malignancy of peripheral pulmonary lesions (PPLs) based on endobronchial ultrasonography (EBUS) and clinical findings.MethodsPatients who had EBUS for PPLs were analyzed and compared on the EBUS imaging characteristics and clinical data. The malignancy prediction model was established by the logistic equation of probability of malignant PPL based on the data of 135 patients. The model was tested on an additional 50 patients for efficiency.ResultsAmong 135 prospectively enrolled patients, 77 (57%) patients had malignant and 58 (43%) had benign lesions with the size of 36.5±19.9 mm. Univariate analysis demonstrated a significant (P<0.05) difference in the serum CEA (borderline 15 µg/mL) and smoking history between malignant and benign lesions but a non-significant (P>0.05) difference in age (50 years as the cutoff value) and history of extra-thoracic malignancies. Logistic analysis of multiple factors showed that smoking history, serum CEA, borderline, air bronchogram, heterogeneous echo, and anechoic areas were significant (P<0.02) risk factors for malignant lesions. The malignancy prediction model was established by the logistic equation of probability of malignant PPL (P) = l/[l+e–Z], where Z=−2.986+1.993X1+2.293X2+l.552X3+1.616X4–2.011X5+1.718X6, e is the base of the natural logarithm, X1 is the smoking history, X2 is the serum CEA, X3 is the borderline, X4 is the heterogenicity, X5 is the air bronchogram, and X6 is the anechoic area. The receiver operating characteristic curve had an area under the curve (AUC) of 0.926 (95% confidence interval: 0.883–0.969). The sensitivity, specificity, and accuracy were 88.2% (30/34), 75.0% (12/16), and 92.0% (46/50), respectively, for the logistic equation to predict the malignancy.ConclusionEndobronchial ultrasonography is a safe and practical method, and the model combining EBUS and clinical data can accurately predict the malignancy of peripheral pulmonary lesions.

Time Difference of Arrival on Contrast-Enhanced Ultrasound in Distinguishing the Benign and Malignant Peripheral Pulmonary Lesions

Background: The incidence and mortality of lung cancer are the highest in the world, and the most lesions are located in lung periphery. Despite the greatest degree of screening and diagnosis, the pathologic types of peripheral pulmonary lesions (PPLs) are difficult to diagnose by noninvasive examination. Here, we found a novel index time difference of arrival (TDOA) to discriminate between benign and malignant lesions of PPLs. Methods: We retrospectively analyzed 96 patients with PPLs using the contrast-enhanced ultrasound (CEUS), who had undergone biopsy to confirm the pathologic types. All the data collected from Dazhou Central Hospital between December 2012 and July 2019. The parameters of CEUS analyzed by two assistant chief physicians of ultrasound diagnosis. Area under the receiver operating characteristic curve analysis, sensitivity, specificity, positive predictive value and negative predictive value were performed to assess the diagnostic ability of different indices. Findings: We found that the TDOA significantly distinguished benign from malignant lesions. The TDOA was markedly increased in patients with malignant lesions than benign lesions (P<0*001). Compared with conventional time-intensity curve (TIC) indices, the TDOA showed high diagnostic accuracy (area under the curve, 0*894). Moreover, conventional diagnostic indices did not affect the diagnostic performance of TDOA by adjusted the receiver operating characteristic curve. Interpretation: Our results suggest that the TDOA is feasible for the diagnosis of the patients with PPLs. Funding Statement: This article was funded by the National Natural Science Foundation of China (81902861), the Scientific Research Fund of Sichuan health and Health Committee (No. 18PJ361) and the Scientific Research Fund of Technology Bureau in Sichuan Province (No. 2018138, No. 2018JY0324). Declaration of Interests: All authors declare no competing interests of this study. Ethics Approval Statement: The study was approved by the Ethics Committee of Dazhou Central Hospital, Sichuan, China.

Radial endobronchial ultrasound for the diagnosis of malignant peripheral pulmonary lesions deemed unsuitable for percutaneous CT guided biopsy in a regional ‘Difficult Thoracic Biopsy’ service

Radial endobronchial ultrasound for the diagnosis of malignant peripheral pulmonary lesions deemed unsuitable for percutaneous CT guided biopsy in a regional ‘Difficult Thoracic Biopsy’ service

Initial experience with transbronchial cryoablation as a novel local treatment for malignant peripheral lung lesions

IntroductionPercutaneous cryoablation has been adopted for small, malignant peripheral pulmonary lesions and has yielded favourable results as a less invasive local treatment. A transbronchial approach may reduce the risks of...

Radial endobronchial ultrasonography with distance measurement through a thin bronchoscope for the diagnosis of malignant peripheral pulmonary lesions.

Peripheral pulmonary lesions (PPLs) are being discovered more frequently. We investigated efficiency, safety, and influencing factors in radial probe endobronchial ultrasound with distance measurement (rEBUS-D) using a thin bronchoscope during transbronchial biopsy (TBB) for the diagnosis of malignant PPLs. Patients with PPLs who underwent rEBUS were retrospectively analyzed. Cases with rEBUS-D and a gold-standard final diagnosis were considered. rEBUS was completed in 589 cases; 328 were analyzed. The lesion discovery rate was 85.06%; the overall rEBUS-D-TBB diagnostic rate was 54.88%. There were 193 cases of malignant tumors. The sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of rEBUS-D-TBB in the diagnosis of malignant PPLs were 63.73%, 100%, 100%, 65.85%, and 78.40%, respectively. Single- and multi-factor analyses showed that lesion size, ultrasound probe position, and a positive bronchus sign on thoracic computed tomography (CT) were significant factors influencing diagnosis (all P=0.000); probe position and the bronchus sign were independent influencing factors. The effect of lesion distribution on diagnosis was not significant. In seven cases, postoperative pathology showed mixed tumors. Two cases of malignant tumors were combined with benign pathology; rEBUS-D-TBB did not suggest two pathologies. Thirteen cases had 50-100 mL of blood loss (3.96%); no pneumothorax or infection was observed. rEBUS-D-TBB had high sensitivity, 100% specificity, excellent safety, and a lower cost than rEBUS-GS-TBB in the diagnosis of malignant PPLs. Larger lesions, a positive bronchus sign on CT, and ultrasound probe position at the lesion's center yielded higher diagnostic rates.

Echoic Features as Predictors of Diagnostic Yield of Endobronchial Ultrasound-Guided Transbronchial Lung Biopsy in Peripheral Pulmonary Lesions

The endobronchial ultrasound (EBUS) features of peripheral pulmonary lesions (PPLs) are associated with histopathologic presentation. Certain histologic and radiologic characteristics of peripheral pulmonary lesions affect the diagnostic yield of transbronchial lung biopsies (TBLB). This study aimed to assess the feasibility of EBUS echoic features as predictors of diagnostic yield of TBLB. Four hundred and eight patients with PPLs underwent TBLB. The yields of TBLB in lesions with characteristic EBUS features were compared with those without such features. The overall diagnostic yield of TBLB was 64.2%. Lesion diameter (≥3 cm vs. <3 cm; 69.1% vs. 58.5%, p < 0.05), location of the EBUS probe (within vs. adjacent to lesions; 73.2% vs. 46.3%, p < 0.01) and lesion echogenicity (heterogeneous vs. homogeneous; 76.7% vs. 52.0%, p < 0.01) were associated with higher TBLB yields. In malignant PPLs, the echoic features associated with higher TBLB yields were lesion diameter (≥3 cm vs. <3 cm; 74.4% vs. 62.5%, p < 0.05), location of the EBUS probe (within vs. adjacent to lesions; 78.7% vs. 47.4%, p < 0.01), echoic feature of the margin (noncontinuous vs. continuous; 77.0% vs. 62.4%, p < 0.01) and lesion echogenicity (heterogeneous vs. homogeneous; 77.7% vs. 53.9%, p < 0.01). EBUS probe location, echoic feature of the margin and lesion echogenicity were independent predictors according to the results of multivariate analysis. In conclusion, EBUS features are feasible predictors of diagnostic yield of TBLB in peripheral lung lesions.

Video-assisted thoracoscopic resection of pulmonary lesions

Aims To determine the role of video-assisted thoracoscopic resection in the diagnosis of benign or malignant peripheral pulmonary lesions. Patients and method In 157 patients, between 1996 and 2001, video-assisted thoracoscopy was used to remove a pulmonary lesion. Conversion rate, complications and histology are presented. Results In 21 patients, conversion to a thoracotomy was necessary, four times because the pulmonary lesion was malignant and seventeen times due to technical difficulties. In patients without any previous history of malignant disease ( n=100), 80% of the lesions were benign. In patients with malignant pulmonary lesions ( n=21), curative resection was possible, 3 through VATS and 4 through thoracotomy. Pulmonary lesions in patients with a previous history of malignant disease were malignant in 42 patients. Curative VATS resection of a solitary lesion was performed in 9 patients, in 10 patients thoracotomy was necessary to remove multiple lesions. Conclusions With a pre-operative selection of the patients the rate of secondary thoracotomies due to bronchial carcinoma is low (4%). In patients with a previous history of malignant disease, 22% of the pulmonary lesions are benign. VATS is a safe diagnostic method, with little discomfort for the patient.