RESUMEN

OBJECTIVE: This study aimed to evaluate the diagnostic performance and procedural characteristics of fluoroscopy-guided percutaneous transthoracic pleural forceps biopsy (PTPFB) in patients with exudative pleural effusion. MATERIALS AND METHODS: Patients with exudative pleural effusion who underwent PTPFB between May 1, 2014, and February 28, 2023, were included in this retrospective study. The interval between percutaneous catheter drainage (PCD) and PTPFB, number of biopsies, procedural time, and procedure-related complications were evaluated. The sensitivity, specificity, and accuracy of diagnosing malignancy were computed for pleural cytology using PCD drainage, PTPFB, and combined PTPFB and pleural cytology. RESULTS: Seventy-one patients, comprising 50 male and 21 female (mean age, 69.5 ± 15.3 years), were included in this study. The final diagnoses were benign lesions in 48 patients (67.6%) and malignant in 23 patients (32.4%). The overall interval between PCD and biopsy was 2.4 ± 3.7 days. The interval between PCD and biopsy in the group that underwent delayed PTPFB was 5.2 ± 3.9 days. The mean number of biopsies was 4.5 ± 1.3. The mean procedural time was 4.4 ± 2.1 minutes. Minor bleeding complications were reported in one patient (1.4%). The sensitivity, specificity, and accuracy for pleural cytology, PTPFB, and combined PTPFB and pleural cytology were 47.8% (11/23), 100% (48/48), and 83.1% (59/71), respectively; 65.2% (15/23), 100% (48/48), and 88.7% (63/71), respectively; and 78.3% (18/23), 100% (48/48), and 93.0% (66/71), respectively. The sensitivity and accuracy of cytology combined with PTPFB were significantly higher than those of cytological testing alone (P = 0.008 and 0.001, respectively). CONCLUSION: Fluoroscopy-guided PTPFB is an accurate and safe diagnostic technique for patients with exudative pleural effusion, with acceptable diagnostic performance, low complication rates, and reasonable procedural times.

Asunto(s)

RESUMEN

Multiple myeloma is a rare haematological malignancy characterised by the clonal proliferation of plasma cells within the bone marrow. Typical manifestations include bone pain, fatigue and monoclonal protein elevation in serum and urine. Less than 1% of cases develop myelomatous pleural effusion, a severe complication indicative of advanced disease and a very poor prognosis.Here, we present a case of a woman with a new diagnosis of multiple myeloma complicated by bilateral myelomatous pleural effusions as the initial presentation. This case underscores the diverse clinical spectrum of multiple myeloma, the significance of timely diagnosis and the threatening implications associated with myelomatous pleural effusions.

Asunto(s)

RESUMEN

OBJECTIVE: This study aimed to evaluate the added value of 40 keV virtual mono-energetic images (VMIs) obtained from dual-layer detector CT (DLCT) for diagnosing malignant pleural effusion (MPE) in patients presenting with unilateral pleural effusion on chest CT. MATERIALS AND METHODS: This retrospective study included 75 patients with unilateral pleural effusion who underwent contrast-enhanced chest CT scans using DLCT. Quantitative and qualitative assessments of the visibility of pleural thickening were conducted on both conventional 120 kVp images and 40 keV VMIs. Two independent radiologists reviewed chest CT scans with or without 40 keV VMIs to detect pleural nodules or nodular thickening for the diagnosis of MPE. Diagnostic performances were compared and independent predictors of MPE were identified through multivariate logistic regression analysis using CT and clinicopathologic findings. RESULTS: Pleural thickening associated with MPE demonstrated a higher contrast-to-noise ratio value and greater visual conspicuity in 40 keV VMIs compared to benign effusions (p < 0.05). For both readers, the use of 40 keV VMIs significantly improved (p < 0.05) the diagnostic performance in terms of sensitivity and area under the curve (AUC) for diagnosing MPE through the detection of pleural nodularity. Inter-observer agreements between the two readers were substantial for both 120 kVp images alone and the combined use of 40 keV VMIs. Initial cytology results and pleural nodularity at 40 keV were identified as independent predictors of MPE. CONCLUSION: The use of 40 keV VMIs from DLCT can improve diagnostic performance of readers in detecting MPE among patients with unilateral pleural effusion.

Asunto(s)

Asunto(s)

RESUMEN

INTRODUCTION: There are no defined criteria for deciding to remove a non-functioning indwelling pleural catheter (IPC) when lung re-expansion on chest X-ray is incomplete. Chest computed tomography (chest CT) is usually used. The objective of this work is to validate the usefulness of chest ultrasound performed by a pulmonologist and by a radiologist compared to chest CT. PATIENTS AND METHODS: Prospective, descriptive, multidisciplinary and multicenter study including patients with malignant pleural effusion and non-functioning IPC without lung reexpansion. Decisions made on the basis of chest ultrasound performed by a pulmonologist, and performed by a radiologist, were compared with chest CT as the gold standard. RESULTS: 18 patients were analyzed, all of them underwent ultrasound by a pulmonologist and chest CT and in 11 of them also ultrasound by a radiologist. The ultrasound performed by the pulmonologist presents a sensitivity of 60%, specificity of 100%, PPV 100% and NPV 66% in the decision of the correct removal of the IPC. The concordance of both ultrasounds (pulmonologist and radiologist) was 100%, with a kappa index of 1. The 4 discordant cases were those in which the IPC was not located on the ultrasound. CONCLUSIONS: Thoracic ultrasound performed by an expert pulmonologist is a valid and simple tool to determine spontaneous pleurodesis and remove a non-functioning IPC, which would make it possible to avoid chest CT in those cases in which lung reexpansion is observed with ultrasonography.

Asunto(s)

Asunto(s)

RESUMEN

INTRODUCTION: Distinguishing between malignant pleural effusion (MPE) and benign pleural effusion (BPE) poses a challenge in clinical practice. We aimed to construct and validate a combined model integrating radiomic features and clinical factors using computerized tomography (CT) images to differentiate between MPE and BPE. METHODS: A retrospective inclusion of 315 patients with pleural effusion (PE) was conducted in this study (training cohort: n = 220; test cohort: n = 95). Radiomic features were extracted from CT images, and the dimensionality reduction and selection processes were carried out to obtain the optimal radiomic features. Logistic regression (LR), support vector machine (SVM), and random forest were employed to construct radiomic models. LR analyses were utilized to identify independent clinical risk factors to develop a clinical model. The combined model was created by integrating the optimal radiomic features with the independent clinical predictive factors. The discriminative ability of each model was assessed by receiver operating characteristic curves, calibration curves, and decision curve analysis (DCA). RESULTS: Out of the total 1,834 radiomic features extracted, 15 optimal radiomic features explicitly related to MPE were picked to develop the radiomic model. Among the radiomic models, the SVM model demonstrated the highest predictive performance [area under the curve (AUC), training cohort: 0.876, test cohort: 0.774]. Six clinically independent predictive factors, including age, effusion laterality, procalcitonin, carcinoembryonic antigen, carbohydrate antigen 125 (CA125), and neuron-specific enolase (NSE), were selected for constructing the clinical model. The combined model (AUC: 0.932, 0.870) exhibited superior discriminative performance in the training and test cohorts compared to the clinical model (AUC: 0.850, 0.820) and the radiomic model (AUC: 0.876, 0.774). The calibration curves and DCA further confirmed the practicality of the combined model. CONCLUSION: This study presented the development and validation of a combined model for distinguishing MPE and BPE. The combined model was a powerful tool for assisting in the clinical diagnosis of PE patients.

Asunto(s)

RESUMEN

ABSTRACT: Radiopharmaceuticals can accumulate in malignant or nonmalignant pleural effusion on γ and PET imaging, and effusion shows a pattern of diffusely or focally increased activity. Herein, we report atypical layering of FDG in pleural effusion on PET/CT of 3 patients with metastatic gynecological cancer.

Asunto(s)

RESUMEN

Objetivo En nuestro estudio el objetivo fue investigar la contribución de los hallazgos de la tomografía por emisión de positrones (PET)/tomografía computarizada (TC) en la diferenciación no invasiva entre el derrame pleural (DP) de origen benigno (DPB) y maligno (DPM) en pacientes diagnosticadas de un carcinoma de ovario (CO). Material y método Se incluyeron en el estudio a 32 pacientes diagnosticadas de CO con DP. Se efectuó análisis comparativo entre el DPB y el DPM para los siguientes parámetros: SUVmáx. del DP, índice objeto/fondo (TBRp: target/background ratio) del DP, dividiendo el SUVmáx. del DP por el SUVmedio del flujo sanguíneo mediastínico (MBP: medistinal blood pool), engrosamiento pleural, adenopatías supradiafragmáticas, DP unilateral o bilateral, diámetro del DP, edad de la paciente y niveles de CA125. Resultados La edad media de las 32 pacientes fue de 57±2,8 años. Se observó mayor frecuencia significativa de un TBRp>1,1, engrosamiento pleural y ganglios linfáticos supradiafragmáticos en el DPM respecto al DPB. Aunque no se detectó ningún nódulo pleural en las pacientes con DPB, estos estuvieron presentes en 7 pacientes con DPM. En la distinción DMP-DBP la sensibilidad del TBRp fue del 95,2% y la especificidad del 72,7%, la sensibilidad del engrosamiento pleural fue del 80,9%, y la especificidad del 81,8%, la sensibilidad de los ganglios linfáticos supradiafragmáticos fue del 38% y la especificidad del 90,9%, y la sensibilidad del nódulo pleural fue del 33,3% y la especificidad del 100%. No hubo diferencias significativas entre los 2 grupos respecto al resto de factores. Conclusión El engrosamiento pleural y el valor de TBRp determinados en la PET/TC pueden contribuir a la diferenciación entre DMP y DBP, especialmente en aquellas pacientes con CO en estadio avanzado y mal estado general, o que no son tributarias de ser sometidas a tratamiento quirúrgico (AU)

Objective The present study investigates the ability of non-invasive contribution of positron emission tomography (PET)/computed tomography (CT) to distinguish between benign pleural effusions (BPE) and malignant pleural effusions (MPE) in patients diagnosed with ovarian carcinoma (OC). Material and method Included in the study were 32 OC patients with a PE diagnosis. The cases with BPE and MPE were compared in terms of the PE maximum standardized uptake value (SUVmax), PE SUVmax/mean standardized uptake (SUVmean) value of the mediastinal blood pool (TBRp), the presence of pleural thickening, the presence of supradiaphragmatic lymph node, unilateral or bilateral PE, pleural effusion diameter, patient age and CA125 value. Results The mean age of the 32 patients was 57±2.8 years. TBRp>1.1, pleural thickening and supradiaphragmatic lymph node were observed significantly more frequently in the MPE than the BPE cases. While no pleural nodules were detected in patients with BPE, they were present in 7 of the patients with MPE. The rates of distinction between the MPE and BPE cases were as follows: the sensitivity of the TBRp value was 95.2% and specificity was 72.7%; the sensitivity of pleural thickness was 80.9% and specificity was 81.8%; the sensitivity of supradiaphragmatic lymph node was 38% and specificity was 90.9%; and the sensitivity of the pleural nodule was 33.3% and specificity was 100%. There were no significant differences between two groups in any other factors. Conclusion Pleural thickening and TBRp values ascertained through PET/CT may aid the distinction between MPE-BPE, especially in patients with advanced stage OC with a poor general condition, or those who cannot undergo surgery (AU)

Asunto(s)

Asunto(s)

RESUMEN

Background and objectives The results of previous PET-CT studies are contradictory for discriminating malignant from benign pleural effusions. We purpose to develop a PET-CT score for differentiating between benign and malignant effusions. Patients and methods We conducted a prospective study of consecutive patients with pleural effusions undergoing PET-CT from October 2013 to October 2019 (referral cohort). PET-CT scan features evaluated using the SUV were: linear thickening; nodular thickening; nodules; masses; circumferential thickening; mediastinal and fissural pleural involvement; intrathoracic lymph nodes; pleural loculation; inflammatory consolidation; pleural calcification; cardiomegaly; pericardial effusion; bilateral effusion; lung mass; liver metastasis and other extra-pleural malignancy. The results were validated in an independent prospective cohort from November 2019 to June 2021. Results One hundred and ninety-nine patients were enrolled in the referral cohort (91 with malignant effusions and 108 benign). The most useful parameters for the development of a PET-CT score were: nodular pleural thickening, pleural nodules with SUV>7.5, lung mass or extra pleural malignancy (10 points each), mammary lymph node with SUV>4.5 (5 points) and cardiomegaly (−1 point). With a cut-off value of >9 points in the referral cohort, the score established the diagnosis of malignant pleural effusion with sensitivity 87.9%, specificity 90.7%, positive predictive value 88.9%, negative predictive value 89.9%, positive likelihood ratio 7.81 and negative likelihood ratio 0.106. These results were validated in an independent prospective cohort of 75 patients. Conclusions PET-CT score was shown to provide relevant information for the identification of malignant pleural effusion (AU)

Antecedentes y objetivos Los estudios PET-TAC previos en el análisis del derrame pleural son contradictorios. Nuestro objetivo es desarrollar una puntuación mediante PET-TAC para diferenciar entre derrames benignos y malignos. Pacientes y métodos Estudio prospectivo en pacientes con derrame pleural a los que se realizó una PET-TAC desde octubre de 2013 hasta octubre de 2019 (cohorte de referencia). Los datos analizados fueron: engrosamiento lineal; engrosamiento nodular; nódulos; masas; engrosamiento circunferencial; afectación pleural mediastínica y cisural; ganglios linfáticos torácicos; loculación pleural; consolidación; calcificación pleural; cardiomegalia; derrame pericárdico; derrame bilateral; masa pulmonar; metástasis hepáticas y otras neoplasias malignas extrapleurales. Se calculó el SUV de todos estos parámetros. Los resultados se validaron en una cohorte independiente. Resultados Se incluyó a 199 pacientes en la cohorte de referencia (91 derrames malignos y 108 benignos). Los parámetros que mostraron más utilidad para discriminar ambos derrames y desarrollar una puntuación fueron: engrosamiento pleural nodular, nódulos pleurales con SUV > 7,5, masa pulmonar o malignidad extrapleural (10 puntos cada uno), ganglio en cadena mamaria con SUV > 4,5 (5 puntos) y cardiomegalia (–1 punto). Con un punto de corte > 9 en la cohorte de derivación, se estableció el diagnóstico de derrame pleural maligno con una sensibilidad del 87,9%, especificidad del 90,7%, valor predictivo positivo del 88,9%, valor predictivo negativo del 89,9% razón de verosimilitud positiva del 7,81 y razón de verosimilitud negativa del 0,106. Estos resultados fueron validados en una cohorte prospectiva independiente de 75 pacientes. Conclusiones Una puntuación basada en PET-TAC proporciona información relevante para el diagnóstico del derrame pleural maligno (AU)

Asunto(s)

RESUMEN

BACKGROUND AND OBJECTIVES: The results of previous PET-CT studies are contradictory for discriminating malignant from benign pleural effusions. We purpose to develop a PET-CT score for differentiating between benign and malignant effusions. PATIENTS AND METHODS: We conducted a prospective study of consecutive patients with pleural effusions undergoing PET-CT from October 2013 to October 2019 (referral cohort). PET-CT scan features evaluated using the SUV were: linear thickening; nodular thickening; nodules; masses; circumferential thickening; mediastinal and fissural pleural involvement; intrathoracic lymph nodes; pleural loculation; inflammatory consolidation; pleural calcification; cardiomegaly; pericardial effusion; bilateral effusion; lung mass; liver metastasis and other extra-pleural malignancy. The results were validated in an independent prospective cohort from November 2019 to June 2021. RESULTS: One hundred and ninety-nine patients were enrolled in the referral cohort (91 with malignant effusions and 108 benign). The most useful parameters for the development of a PET-CT score were: nodular pleural thickening, pleural nodules with SUV>7.5, lung mass or extra pleural malignancy (10 points each), mammary lymph node with SUV>4.5 (5 points) and cardiomegaly (-1 point). With a cut-off value of >9 points in the referral cohort, the score established the diagnosis of malignant pleural effusion with sensitivity 87.9%, specificity 90.7%, positive predictive value 88.9%, negative predictive value 89.9%, positive likelihood ratio 7.81 and negative likelihood ratio 0.106. These results were validated in an independent prospective cohort of 75 patients. CONCLUSIONS: PET-CT score was shown to provide relevant information for the identification of malignant pleural effusion.

Asunto(s)

RESUMEN

BACKGROUND: The incidence of tract seeding after the placement of indwelling pleural catheter (IPC) for malignant pleural effusion drainage has been variable in the literature. RESEARCH QUESTION: To evaluate the incidence of IPC-related cancer tract seeding and find out related demographic, clinical or imaging factors to the tract seeding. STUDY DESIGN AND METHODS: This retrospective study included 124 consecutive patients seen between January 2011 and December 2021 who underwent IPC placement for malignant pleural effusion drainage. Chest radiographs before IPC placement and serial chest CT studies were obtained. One patient was diagnosed pathologically, and the other patients were diagnosed as tract seeding radiologically. The incidence of and related factors to tract seeding were assessed by reviewing medical records and imaging studies. RESULTS: The incidence of IPC tract seeding was 21.7% (27 of 124 malignant effusions). Of 27 patients, 15 had primary lung cancer and remaining 12 had extra-thoracic malignancy. Adenocarcinoma (19 of 27, 70.3%) either from the lung (N = 12) or extra-thoracic malignancy (N = 7) was the most common cell type. Mean time elapsed until tract seeding occurrence after IPC placement was 96 days (ranges; 28-306 days). The survival in seeding group after IPC placement was 185 days (ranges, 32-457 days). On odd ratio analysis, the presence of mediastinal pleural thickening (OR [95% CI]; 9.79 (2.67-35.84), p = 0.001) was significantly related to the occurrence of tract seeding. Neither tumor volume within pleural space (p = 0.168), duration of IPC indwelling (p = 0.142), days of survival after IPC placement (p = 0.26), nor pleural effusion amount (p = 0.481) was related to the tract seeding. INTERPRETATION: IPC tract seeding is seen in 27 (21.7%) of 124 malignant pleural effusion patients, particularly with adenocarcinoma cytology. CT features of mediastinal pleural thickening are related to the occurrence of tract seeding.

Asunto(s)

RESUMEN

INTRODUCTION: Malignant pleural effusions are common in advanced malignancy and associated with overall poor survival. The presence of sarcopenia (decreased muscle mass) is associated with poor outcomes in numerous disease states, however, its relationship to malignant pleural disease has not been defined. We sought to understand if there was an association between decreased survival and decreased muscle mass in patients with malignant pleural effusion. METHODS: Patients with malignant pleural disease undergoing indwelling tunneled pleural catheter placement were retrospectively reviewed. Computed tomography was reviewed and cross-sectional area of pectoralis and paraspinous muscle areas were calculated. Overall survival and associations with muscle mass were calculated. RESULTS: A total of 309 patients were available for analysis, with a median age of 67 years and the majority female (58%). The median survival was 129 days from initial pleural drainage to death. Regression analysis and Kaplan-Meier survival analysis did not reveal an association with survival and muscle mass for the entire population. However, Kaplan-Meier survival analysis of the lung cancer subgroup revealed the presence of decreased muscle mass and decreased survival time. CONCLUSION: The presence of decreased muscle mass within a lung cancer population that has malignant pleural effusions are associated with decreased survival. However, the presence of decreased muscle mass within a heterogenous population of malignant pleural disease was not associated with decreased overall survival time. Further study of the role that sarcopenia may play in malignant pleural disease is warranted.

Asunto(s)

RESUMEN

Non-expandable lung (NEL) often occurs during pleural fluid drainage in patients with malignant pleural effusion (MPE). However, data regarding the predictors and prognostic impact of NEL on primary lung cancer patients with MPE receiving pleural fluid drainage, compared to malignant pleural mesothelioma (MPM), are limited. This study was aimed to investigate the clinical characteristics of lung cancer patients with MPE developing NEL following ultrasonography (USG)-guided percutaneous catheter drainage (PCD) and compare the clinical outcomes between those with and without NEL. Clinical, laboratory, pleural fluid, and radiologic data and survival outcomes of lung cancer patients with MPE undergoing USG-guided PCD were retrospectively reviewed and compared between those with and without NEL. Among 121 primary lung cancer patients with MPE undergoing PCD, NEL occurred in 25 (21%). Higher pleural fluid lactate dehydrogenase (LDH) levels and presence of endobronchial lesions were associated with development of NEL. The median time to catheter removal was significantly extended in those with NEL compared to those without (P = .014). NEL was significantly associated with poor survival outcome in lung cancer patients with MPE undergoing PCD, along with poor Eastern Cooperative Oncology Group (ECOG) performance status (PS), the presence of distant metastasis, higher serum C-reactive protein (CRP) levels, and not receiving chemotherapy. NEL developed in one-fifth of lung cancer patients undergoing PCD for MPE and was associated with high pleural fluid LDH levels and the presence of endobronchial lesions. NEL may negatively affect overall survival in lung cancer patients with MPE receiving PCD.

Asunto(s)

RESUMEN

OBJECTIVE: The present study investigates the ability of non-invasive contribution of positron emission tomography (PET)/computed tomography (CT) to distinguish between benign pleural effusions (BPE) and malignant pleural effusions (MPE) in patients diagnosed with ovarian carcinoma (OC). MATERIAL AND METHODS: Included in the study were 32 OC patients with a PE diagnosis. The cases with BPE and MPE were compared in terms of the PE maximum standardized uptake value (SUVmax), PE SUVmax/mean standardized uptake (SUVmean) value of the mediastinal blood pool (TBRp), the presence of pleural thickening, the presence of supradiaphragmatic lymph node, unilateral or bilateral PE, pleural effusion diameter, patient age and CA125 value. RESULTS: The mean age of the 32 patients was 57±2.8 years. TBRp>1.1, pleural thickening and supradiaphragmatic lymph node were observed significantly more frequently in the MPE than the BPE cases. While no pleural nodules were detected in patients with BPE, they were present in 7 of the patients with MPE. The rates of distinction between the MPE and BPE cases were as follows: the sensitivity of the TBRp value was 95.2% and specificity was 72.7%; the sensitivity of pleural thickness was 80.9% and specificity was 81.8%; the sensitivity of supradiaphragmatic lymph node was 38% and specificity was 90.9%; and the sensitivity of the pleural nodule was 33.3% and specificity was 100%. There were no significant differences between two groups in any other factors. CONCLUSIONS: Pleural thickening and TBRp values ascertained through PET/CT may aid the distinction between MPE-BPE, especially in patients with advanced stage OC with a poor general condition, or those who cannot undergo surgery.

Asunto(s)

RESUMEN

BACKGROUND: The pleura is a serous membrane that surrounds the lungs. The visceral surface secretes fluid into the serous cavity and the parietal surface ensures a regular absorption of this fluid. If this balance is disturbed, fluid accumulation occurs in the pleural space called "Pleural Effusion". Today, accurate diagnosis of pleural diseases is becoming more critical, as advances in treatment protocols have contributed positively to prognosis. Our aim is to perform computer-aided numerical analysis of Computed Tomography (CT) images from patients showing pleural effusion images on CT and to examine the prediction of malignant/benign distinction using deep learning by comparing with the cytology results. METHODS: The authors classified 408 CT images from 64 patients whose etiology of pleural effusion was investigated using the deep learning method. 378 of the images were used for the training of the system; 15 malignant and 15 benign CT images, which were not included in the training group, were used as the test. RESULTS: Among the 30 test images evaluated in the system; 14 of 15 malignant patients and 13 of 15 benign patients were estimated with correct diagnosis (PPD: 93.3%, NPD: 86.67%, Sensitivity: 87.5%, Specificity: 92.86%). CONCLUSION: Advances in computer-aided diagnostic analysis of CT images and obtaining a pre-diagnosis of pleural fluid may reduce the need for interventional procedures by guiding physicians about which patients may have malignancies. Thus, it is cost and time-saving in patient management, allowing earlier diagnosis and treatment.

Asunto(s)

RESUMEN

Rationale: The diagnostic yield of traditional ultrasound-guided pleural biopsy remains unsatisfactory, particularly when the pleural thickness is ⩽5 mm and/or no pleural nodules are detected. Pleural ultrasound elastography (UE) has a better diagnostic yield than traditional ultrasound for malignant pleural effusion (MPE). However, studies on UE-guided pleural biopsies are lacking. Objectives: To evaluate the feasibility and safety of UE-guided pleural biopsy. Methods: In this multicenter prospective single-arm trial, patients with pleural effusion whose pleural thickness was ⩽5 mm with no pleural nodules were enrolled between July 2019 and August 2021. The diagnostic yield of UE-guided pleural biopsy for pleural effusion and its sensitivity for detecting MPE were evaluated. Results: Ninety-eight patients (mean age, 62.4 ± 13.2 yr; 65 men) were prospectively enrolled. The diagnostic yield of UE-guided pleural biopsy for making any diagnosis was 92.9% (91/98), and its sensitivity for MPE was 88.7% (55/62). In addition, its sensitivity for pleural tuberculosis was 69.6% (16/23). The rate of postoperative chest pain was acceptable, and there was no pneumothorax. Conclusions: UE-guided pleural biopsy is a novel technique for diagnosing MPE with good diagnostic yield and sensitivity. Clinical trial registered with https://www.chictr.org.cn (ChiCTR2000033572).

Asunto(s)

Asunto(s)

RESUMEN

INTRODUCTION: This study aimed to construct artificial intelligence models based on thoracic CT images to perform segmentation and classification of benign pleural effusion (BPE) and malignant pleural effusion (MPE). METHODS: A total of 918 patients with pleural effusion were initially included, with 607 randomly selected cases used as the training cohort and the other 311 as the internal testing cohort; another independent external testing cohort with 362 cases was used. We developed a pleural effusion segmentation model (M1) by combining 3D spatially weighted U-Net with 2D classical U-Net. Then, a classification model (M2) was built to identify BPE and MPE using a CT volume and its 3D pleural effusion mask as inputs. RESULTS: The average Dice similarity coefficient, Jaccard coefficient, precision, sensitivity, Hausdorff distance 95% (HD95) and average surface distance indicators in M1 were 87.6±5.0%, 82.2±6.2%, 99.0±1.0%, 83.0±6.6%, 6.9±3.8 and 1.6±1.1, respectively, which were better than those of the 3D U-Net and 3D spatially weighted U-Net. Regarding M2, the area under the receiver operating characteristic curve, sensitivity and specificity obtained with volume concat masks as input were 0.842 (95% CI 0.801 to 0.878), 89.4% (95% CI 84.4% to 93.2%) and 65.1% (95% CI 57.3% to 72.3%) in the external testing cohort. These performance metrics were significantly improved compared with those for the other input patterns. CONCLUSIONS: We applied a deep learning model to the segmentation of pleural effusions, and the model showed encouraging performance in the differential diagnosis of BPE and MPE.

Asunto(s)