ABSTRACT
INTRODUCTION: Early diagnosis of lung cancer (LC) is crucial to improve survival rates. Radiomics models hold promise for enhancing LC diagnosis. This study assesses the impact of integrating a clinical and a radiomic model based on deep learning to predict the malignancy of pulmonary nodules (PN). METHODOLOGY: Prospective cross-sectional study of 97 PNs from 93 patients. Clinical data included epidemiological risk factors and pulmonary function tests. The region of interest of each chest CT containing the PN was analysed. The radiomic model employed a pre-trained convolutional network to extract visual features. From these features, 500 with a positive standard deviation were chosen as inputs for an optimised neural network. The clinical model was estimated by a logistic regression model using clinical data. The malignancy probability from the clinical model was used as the best estimate of the pre-test probability of disease to update the malignancy probability of the radiomic model using a nomogram for Bayes' theorem. RESULTS: The radiomic model had a positive predictive value (PPV) of 86%, an accuracy of 79% and an AUC of 0.67. The clinical model identified DLCO, obstruction index and smoking status as the most consistent clinical predictors associated with outcome. Integrating the clinical features into the deep-learning radiomic model achieves a PPV of 94%, an accuracy of 76% and an AUC of 0.80. CONCLUSIONS: Incorporating clinical data into a deep-learning radiomic model improved PN malignancy assessment, boosting predictive performance. This study supports the potential of combined image-based and clinical features to improve LC diagnosis.
ABSTRACT
BACKGROUND: COVID-19 infection, especially in cases with pneumonia, is associated with a high rate of pulmonary embolism (PE). In patients with contraindications for CT pulmonary angiography (CTPA) or non-diagnostic CTPA, perfusion single-photon emission computed tomography/computed tomography (Q-SPECT/CT) is a diagnostic alternative. The goal of this study is to develop a radiomic diagnostic system to detect PE based only on the analysis of Q-SPECT/CT scans. METHODS: This radiomic diagnostic system is based on a local analysis of Q-SPECT/CT volumes that includes both CT and Q-SPECT values for each volume point. We present a combined approach that uses radiomic features extracted from each scan as input into a fully connected classification neural network that optimizes a weighted cross-entropy loss trained to discriminate between three different types of image patterns (pixel sample level): healthy lungs (control group), PE and pneumonia. Four types of models using different configuration of parameters were tested. RESULTS: The proposed radiomic diagnostic system was trained on 20 patients (4,927 sets of samples of three types of image patterns) and validated in a group of 39 patients (4,410 sets of samples of three types of image patterns). In the training group, COVID-19 infection corresponded to 45% of the cases and 51.28% in the test group. In the test group, the best model for determining different types of image patterns with PE presented a sensitivity, specificity, positive predictive value and negative predictive value of 75.1%, 98.2%, 88.9% and 95.4%, respectively. The best model for detecting pneumonia presented a sensitivity, specificity, positive predictive value and negative predictive value of 94.1%, 93.6%, 85.2% and 97.6%, respectively. The area under the curve (AUC) was 0.92 for PE and 0.91 for pneumonia. When the results obtained at the pixel sample level are aggregated into regions of interest, the sensitivity of the PE increases to 85%, and all metrics improve for pneumonia. CONCLUSION: This radiomic diagnostic system was able to identify the different lung imaging patterns and is a first step toward a comprehensive intelligent radiomic system to optimize the diagnosis of PE by Q-SPECT/CT. HIGHLIGHTS: Artificial intelligence applied to Q-SPECT/CT is a diagnostic option in patients with contraindications to CTPA or a non-diagnostic test in times of COVID-19.
ABSTRACT
Introducción: La implementación del protocolo ERAS (Enhanced Recovery After Surgery) en cirugía torácica ha implicado un cambio en el manejo perioperatorio de los pacientes. Una de las nuevas recomendaciones es evitar la colocación sistémica de sondaje vesical en cirugía pulmonar.Existe poca evidencia en la bibliografía sobre las complicaciones nefrourológicas postoperatorias. Por ello, diseñamos un estudio con el fin de evaluar la incidencia de complicaciones nefrourológicas en la población sometida a resección pulmonar por videotoracoscopia en función del uso o no del sondaje vesical.Material y Método: Realizamos un estudio longitudinal prospectivo en la Unidad de Reanimación Postanestésica en un hospital de tercer nivel durante el periodo comprendido entre abril 2019 y julio del 2020 a los pacientes sometidos a resección pulmonar por videotoracoscopia. Se recogieron variables perioperatorias así como la presencia de complicaciones nefrourológicas.Resultados De los 62 pacientes que ingresaron en URPA sin sondaje vesical, 5 presentaron complicaciones nefrourológicas en las primeras 24 horas postquirúrgicas. 3 de los 5 presentaban volúmenes vesicales estimados por ecografía altos (>300 ml) a la llegada a la URPA y 4 pacientes los presentaban a las 4 horas después de la cirugía. Estas complicaciones no implicaron un deterioro significativo de la función renal durante el ingreso hospitalario.Conclusiones: La recomendación de evitar el sondaje urinario en cirugía de resección pulmonar parece una práctica segura. Sería muy interesante disponer de herramientas que permitan una detección y monitorización de los pacientes con riesgo incrementado para favorecer la detección precoz de complicaciones. (AU)
Introduction: The implementation of the ERAS (Enhanced Recovery After Surgery) protocol in thoracic surgery has changed the perioperative management of patients. One of the new recommendations is to avoid systematic urinary catheterization during lung surgery.There is little scientific evidence on postoperative urological and renal complications. Therefore, a study was conducted to evaluate the incidence of urological and renal complications in the population undergoing video-assisted thoracoscopy lung resection by according to the use or not of urinary catheterization.Method: A prospective longitudinal study in the Postanaesthesia Care Unit (PACU) at a tertiary hospital during the period April 2019 to July 2020 was conducted. Patients undergoing video-assisted thoracoscopy lung resection were included.Results: Amongst the 62 patients that were admitted in the PACU without urinary catheter, 5 developed urological or renal complications in the first 24 hours after surgery. 3 out of 5 had high sonographic estimated bladder volume (>300 ml) on their PACU admission and 4 out of 5 had high volume 4 hours after surgery. These complications didnt have a clinically relevant impact on the renal function during hospital stay.Conclusions: The recommendation to avoid urinary catheterisation in lung resection surgery seems to be a safe practice. It would be relevant to have tools that allow detection and monitoring of patients at increased risk to favour early detection of complications. (AU)
Subject(s)
Humans , Thoracic Surgery , Postoperative Complications , Urinary Catheters , Postoperative Care , PatientsABSTRACT
OBJECTIVES: Systematic mediastinal staging (sampling all visible nodes measuring ≥ 5 mm from N3 station to N1, regardless of PET/CT (positron emission tomography/computed tomography) by endobronchial ultrasound transbronchial needle aspiration (EBUS-TBNA) is a decisive step in patients with non-small cell lung cancer (NSCLC). We analyzed the prevalence of N3 disease and the utility of systematic staging in the subgroup of patients who underwent EBUS-TBNA staging without showing mediastinal lesions on the PET/CT (N0/N1). MATERIAL AND METHODS: We conducted a retrospective analysis of a prospectively collected database that included 174 patients with a final diagnosis of NSCLC, with N0/N1 disease on PET/CT who underwent a systematic EBUS-TBNA staging. RESULTS: 174 consecutive patients were included. Systematic EBUS-TBNA detected N2 mediastinal involvement in 21 (12 %) cases, and no cases of N3 disease were detected (neither hilar nor mediastinal). Of the remaining 153 patients N0/N1 EBUS-TBNA, 122 underwent lung resection that revealed 4 cases of N2 disease while 117 were confirmed to be N0/N1. Thirty-three patients with N0/1 disease after EBUS-TBNA did not undergo surgery and were excluded for the NPV calculation. Sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV) and overall accuracy of systematic EBUS was 84 %, 100 %, 96.7 %, 100 % and 97 % respectively. CONCLUSION: Systematic EBUS-TBNA is a very accurate method for lymph node staging in patients with NSCLC without mediastinal involvement on PET/CT. Pending more studies, the absence of contralateral hilar nodal involvement in our series, questions the need for a contralateral hilar sampling in this subgroup of patients.
