RESUMEN
OBJECTIVE@#In order to improve the accuracy of the current pulmonary nodule location detection method based on CT images, reduce the problem of missed detection or false detection, and effectively assist imaging doctors in the diagnosis of pulmonary nodules.@*METHODS@#Propose a novel method for detecting the location of pulmonary nodules based on multiscale convolution. First, image preprocessing methods are used to eliminate the noise and artifacts in lung CT images. Second, multiple adjacent single-frame CT images are selected to be concatenate into multi-frame images, and the feature extraction is carried out through the artificial neural network model U-Net improved by multi-scale convolution to enhanced feature extraction capability for pulmonary nodules of different sizes and shapes, so as to improve the accuracy of feature extraction of pulmonary nodules. Finally, using point detection to improve the loss function of U-Net training process, the accuracy of pulmonary nodule location detection is improved.@*RESULTS@#The accuracy of detecting pulmonary nodules equal or larger than 3 mm and smaller than 3 mm are 98.02% and 96.94% respectively.@*CONCLUSIONS@#This method can effectively improve the detection accuracy of pulmonary nodules on CT image sequence, and can better meet the diagnostic needs of pulmonary nodules.
Asunto(s)
Humanos , Neoplasias Pulmonares/diagnóstico por imagen , Nódulo Pulmonar Solitario/diagnóstico por imagen , Tomografía Computarizada por Rayos X , Redes Neurales de la ComputaciónRESUMEN
Objective: To investigate the detection and diagnostic efficacy of chest radiographs for ≤30 mm pulmonary nodules and the factors affecting them, and to compare the level of consistency among readers. Methods: A total of 43 patients with asymptomatic pulmonary nodules who consulted in Cancer Hospital, Chinese Academy of Medical Sciences from 2012 to 2014 and had chest CT and X-ray chest radiographs during the same period were retrospectively selected, and one nodule ≤30 mm was visible on chest CT images in the whole group (total 43 nodules in the whole group). One senior radiologist with more than 20 years of experience in imaging diagnosis reviewed CT images and recording the size, morphology, location, and density of nodules was selected retrospectively. Six radiologists with different levels of experience (2 residents, 2 attending physicians and 2 associate chief physicians independently reviewed the chest images and recorded the time of review, nodule detection, and diagnostic opinion. The CT imaging characteristics of detected and undetected nodules on X images were compared, and the factors affecting the detection of nodules on X-ray images were analyzed. Detection sensitivity and diagnosis accuracy rate of 6 radiologists were calculated, and the level of consistency among them was compared to analyze the influence of radiologists' seniority and reading time on the diagnosis results. Results: The number of nodules detected by all 6 radiologists was 17, with a sensitivity of detection of 39.5%(17/43). The number of nodules detected by ≥5, ≥4, ≥3, ≥2, and ≥1 physicians was 20, 21, 23, 25, and 28 nodules, respectively, with detection sensitivities of 46.5%, 48.8%, 53.5%, 58.1%, and 65.1%, respectively. Reasons for false-negative result of detection on X-ray images included the size, location, density, and morphology of the nodule. The sensitivity of detecting ≤30 mm, ≤20 mm, ≤15 mm, and ≤10 mm nodules was 46.5%-58.1%, 45.9%-54.1%, 36.0%-44.0%, and 36.4% for the 6 radiologists, respectively; the diagnosis accuracy rate was 19.0%-85.0%, 16.7%-6.5%, 18.2%-80.0%, and 0%-75.0%, respectively. The consistency of nodule detection among 6 doctors was good (Kappa value: 0.629-0.907) and the consistency of diagnostic results among them was moderate or poor (Kappa value: 0.350-0.653). The higher the radiologist's seniority, the shorter the time required to read the images. The reading time and the seniority of the radiologists had no significant influence on the detection and diagnosis results (P>0.05). Conclusions: The ability of radiographs to detect lung nodules ≤30 mm is limited, and the ability to determine the nature of the nodules is not sufficient, and the increase in reading time and seniority of the radiologists will not improve the diagnostic accuracy. X-ray film exam alone is not suitable for lung cancer diagnosis.
Asunto(s)
Humanos , Estudios Retrospectivos , Nódulo Pulmonar Solitario/diagnóstico por imagen , Radiografía , Nódulos Pulmonares Múltiples/diagnóstico por imagen , Tomografía Computarizada por Rayos X/métodos , Neoplasias Pulmonares/diagnóstico por imagen , Sensibilidad y Especificidad , Interpretación de Imagen Radiográfica Asistida por Computador/métodosRESUMEN
BACKGROUND@#The localization of pulmonary nodules is related to whether the lesions can be found and removed accurately and quickly. It is an important link for the success of minimally invasive video-assisted thoracic surgery (VATS). This study investigated the feasibility of medical glue localization under VATS video-assisted thoracoscopic computed tomography (CT) guidance for single pulmonary nodule and more than two pulmonary nodules, and compared with the accuracy and safety of single nodule localization.@*METHODS@#A retrospective analysis of the clinical data of patients who underwent unilateral CT-guided medical glue localization before VATS from November 2018 to March 2021 were performed, the patients was divided into multiple pulmonary nodules group (localized nodules ≥2) and single pulmonary nodule group according to the number of localized nodules. The localization time, success rate and complication rate of the two groups were compared.@*RESULTS@#There were 126 nodules in the two groups, including 62 in single pulmonary nodule group and 64 in multiple pulmonary nodules group. The average single nodule localization time was (13.23±4.5) min in single pulmonary nodule group and (10.52±2.8) min in multiple pulmonary nodules group, the difference between the two groups is statistically significant (P<0.05). The localization success rate of single pulmonary nodule group and multiple pulmonary nodules group were 100% and 98.4% separately, the difference between the two groups was not statistically significant (P>0.05). All VATS were successfully completed after localization. The incidence of pneumothorax was higher in multiple pulmonary nodules group than in single pulmonary nodule group (P=0.07).@*CONCLUSIONS@#Compared with localization of single lung nodule, unilateral CT-guided medical glue localization for multiple pulmonary nodules before VATS is also feasible and accuracy, it is worthy of clinical application. But the higher rate of pneumothorax should be paid attention to.
Asunto(s)
Humanos , Neoplasias Pulmonares/cirugía , Nódulos Pulmonares Múltiples/cirugía , Neumotórax , Estudios Retrospectivos , Nódulo Pulmonar Solitario/cirugía , Cirugía Torácica Asistida por Video , Tomografía Computarizada por Rayos XRESUMEN
The incidence and mortality of lung cancer rank first among all malignant tumors in China. With the popularization of high resolution computed tomography (CT) in clinic, chest CT has become an important means of clinical screening for early lung cancer and reducing the mortality of lung cancer. Imaging findings of early lung adenocarcinoma often show partial solid nodules with ground glass components. With the development of imaging, the relationship between the imaging features of some solid nodules and their prognosis has attracted more and more attention. At the same time, with the development of 3D-reconstruction technology, clinicians can improve the accuracy of diagnosis and treatment of such nodules.This article focuses on the traditional imaging analysis of partial solid nodules and the imaging analysis based on 3D reconstruction, and systematically expounds the advantages and disadvantages of both. .
Asunto(s)
Humanos , Adenocarcinoma del Pulmón/patología , Procesamiento de Imagen Asistido por Computador , Neoplasias Pulmonares/patología , Nódulo Pulmonar Solitario/patología , Tomografía Computarizada por Rayos XRESUMEN
Low-dose computed tomography (CT) for lung cancer screening has been proven to reduce lung cancer deaths in the screening group compared with the control group. The increasing number of pulmonary nodules being detected by CT scans significantly increase the workload of the radiologists for scan interpretation. Artificial intelligence (AI) has the potential to increase the efficiency of pulmonary nodule discrimination and has been tested in preliminary studies for nodule management. As more and more artificial AI products are commercialized, the consensus statement has been organized in a collaborative effort by Thoracic Surgery Committee, Department of Simulated Medicine, Wu Jieping Medical Foundation to aid clinicians in the application of AI-assisted management for pulmonary nodules. .
Asunto(s)
Humanos , Inteligencia Artificial , China , Detección Precoz del Cáncer , Neoplasias Pulmonares/diagnóstico por imagen , Nódulos Pulmonares Múltiples , Sensibilidad y Especificidad , Nódulo Pulmonar SolitarioRESUMEN
With the wide application of high-resolution chest CT in health check-up, the ground glass nodule(GGN) has been increasingly detected. GGNs have a complex etiology and image features, which can develop fast or very slowly. Therefore, whether to follow up or to resect it is usually very difficult to be determined. Overdiagnosis or overtreatment frequently happens. According to the development of GGNs, the process can be clinically divided into four stages: biological onset stage (pre-detection stage), observational stage, clinical treatment stage and postoperative follow-up stage. This review summarizes the progress on the natural development process, imaging monitoring and differentiation, the optimal time of surgical treatment for GGNs based on the decision of multidisciplinary team. This revie wmay be helpful for clinicians to understand the rule of GGN development in the follow-up, and find an optimal time to give surgical intervention for improving the prognosis of and life quality of the GGN patients.
Asunto(s)
Humanos , Estudios de Seguimiento , Neoplasias Pulmonares/cirugía , Nódulos Pulmonares Múltiples/cirugía , Estudios Retrospectivos , Nódulo Pulmonar Solitario/cirugíaRESUMEN
Introducción. El cáncer de pulmón es la primera causa de mortalidad por cáncer a nivel mundial, lo que hace que sea considerado un problema de salud pública. Existen diferentes hallazgos imagenológicos que hacen sospechar la presencia de cáncer de pulmón, uno de los cuales son los nódulos pulmonares; sin embargo, estos también pueden verse en entidades benignas.Métodos. Se incluyeron 66 pacientes con biopsia de nódulo pulmonar en la Clínica Reina Sofía, en la ciudad de Bogotá, D.C., Colombia, entre el 1° de marzo del 2017 y el 28 de febrero del 2020. Se analizaron las características demográficas de los pacientes, las características morfológicas e histopatológicas de los nódulos pulmonares y la correlación entre sus características imagenológicas e histopatológicas. Resultados. El 69,2 % de los nódulos estudiados tenían etiología maligna, de estos el 55,5 % era de origen metástasico y el 44,5 % eran neoplasias primarias de pulmón, con patrón sólido en el 70,6 % de los casos. El patrón histológico más frecuente fue adenocarcinoma. Respecto a las características radiológicas, en su mayoría los nódulos malignos medían de 1 a 2 cm, de morfología lisa y distribución múltiple, localizados en lóbulos superiores. Conclusiones. La caracterización de los nódulos pulmonares brinda información relevante que orienta sobre los diagnósticos más frecuentes en nuestro medio, cuando se estudian nódulos sospechosos encontrados incidentalmente o en el seguimiento de otro tumor. Como el nódulo es la manifestación del cáncer temprano del pulmón, establecer programas de tamización que permitan el diagnóstico oportuno, es hoy día una imperiosa necesidad, para reducir la mortalidad.
Introduction. Lung cancer is the leading cause of cancer mortality worldwide, which makes it a public health problem. There are different imaging findings that suggest the presence of lung cancer, one of which is pulmonary nodules; however, these can also be seen in benign entities. Methods. A total of 66 patients with pulmonary nodule biopsy at Clínica Reina Sofía, in the city of Bogotá D.C. were included between March 1, 2017 and February 28, 2020. The demographic characteristics of the patients, the morphologic and histopathologic characteristics of the pulmonary nodules and their correlation with their pathological diagnosis were analyzed.Results. 69.2% of the nodules studied had malignant etiology, of these 55.5% were of metastatic origin, and 44.5% were primary lung neoplasms, with a solid pattern in 70.6% of the cases. The most frequent histological pattern was adenocarcinoma. Regarding the radiological characteristics, most of the malignant nodules measure 1 to 2 cm, of smooth morphology and had multiple distribution, located in the upper lobes. Conclusions. The characterization of pulmonary nodules provides relevant information that guides the most fre-quent diagnoses in our setting, when suspicious nodules found incidentally or in the follow-up of another tumor are studied. As the nodule is the manifestation of early lung cancer, establishing screening programs that allow timely diagnosis is an urgent need to reduce mortality.
Asunto(s)
Humanos , Nódulo Pulmonar Solitario , Neoplasias Pulmonares , Patología , Biopsia con Aguja , Diagnóstico por Imagen , DiagnósticoRESUMEN
BACKGROUND@#Computed tomography images are easy to misjudge because of their complexity, especially images of solitary pulmonary nodules, of which diagnosis as benign or malignant is extremely important in lung cancer treatment. Therefore, there is an urgent need for a more effective strategy in lung cancer diagnosis. In our study, we aimed to externally validate and revise the Mayo model, and a new model was established.@*METHODS@#A total of 1450 patients from three centers with solitary pulmonary nodules who underwent surgery were included in the study and were divided into training, internal validation, and external validation sets (n = 849, 365, and 236, respectively). External verification and recalibration of the Mayo model and establishment of new logistic regression model were performed on the training set. Overall performance of each model was evaluated using area under receiver operating characteristic curve (AUC). Finally, the model validation was completed on the validation data set.@*RESULTS@#The AUC of the Mayo model on the training set was 0.653 (95% confidence interval [CI]: 0.613-0.694). After re-estimation of the coefficients of all covariates included in the original Mayo model, the revised Mayo model achieved an AUC of 0.671 (95% CI: 0.635-0.706). We then developed a new model that achieved a higher AUC of 0.891 (95% CI: 0.865-0.917). It had an AUC of 0.888 (95% CI: 0.842-0.934) on the internal validation set, which was significantly higher than that of the revised Mayo model (AUC: 0.577, 95% CI: 0.509-0.646) and the Mayo model (AUC: 0.609, 95% CI, 0.544-0.675) (P < 0.001). The AUC of the new model was 0.876 (95% CI: 0.831-0.920) on the external verification set, which was higher than the corresponding value of the Mayo model (AUC: 0.705, 95% CI: 0.639-0.772) and revised Mayo model (AUC: 0.706, 95% CI: 0.640-0.772) (P < 0.001). Then the prediction model was presented as a nomogram, which is easier to generalize.@*CONCLUSIONS@#After external verification and recalibration of the Mayo model, the results show that they are not suitable for the prediction of malignant pulmonary nodules in the Chinese population. Therefore, a new model was established by a backward stepwise process. The new model was constructed to rapidly discriminate benign from malignant pulmonary nodules, which could achieve accurate diagnosis of potential patients with lung cancer.
Asunto(s)
Humanos , Pulmón , Neoplasias Pulmonares/diagnóstico por imagen , Nódulos Pulmonares Múltiples , Medición de Riesgo , Nódulo Pulmonar Solitario/diagnóstico por imagen , Tomografía Computarizada por Rayos XRESUMEN
Objective To investigate the application value of indocyanine green(ICG)in the localization of small pulmonary nodules in video-assisted thoracoscopic surgery(VATS). Methods We retrospectively analyzed the clinical data of 45 patients with small nodules(diameter<1 cm)who received preoperative localization with ICG and underwent VATS wedge resection from October 2020 to February 2021.The data for analysis included patients age,nodule diameter,distance from the parietal pleura,nodule density,success rate of localization,time of localization,incidence of complications,and pathological findings. Results The success rate of localization was 100%.The average nodule size was 6.3 mm,and the nodules were(10±11)mm from the parietal pleura.After localization of 59 nodules,13(22.0%)cases were found to have mild pneumothorax,and 4(6.7%)cases were found to have mild hemorrhage.The success rate of operation was 100%,and 43(72.9%)cases were confirmed adenocarcinoma by postoperative pathology. Conclusion ICG has a high success rate and good safety in the localization of small pulmonary nodules in VATS.
Asunto(s)
Humanos , Verde de Indocianina , Neoplasias Pulmonares/cirugía , Estudios Retrospectivos , Nódulo Pulmonar Solitario/cirugía , Cirugía Torácica Asistida por Video , Tomografía Computarizada por Rayos XRESUMEN
ABSTRACT Objective: to report the preoperative localization of pulmonary nodules with the placement of a guidewire oriented by Computed Tomography. Methods: the nodules were marked using a needle in the shape of a hook or another in the shape of a Q, guided by tomography. The choice of the location for the marking was the shortest distance from the chest wall to the nodule. The marking procedure was performed under local anesthesia and a tomographic control was obtained immediately at the end. Patients were referred to the operating room. Surgical resection occurred less than two hours after the needle placement. Results: between February 2017 and October 2019, 22 patients aged 43 to 82 years (mean 62.1) were included. The nodules had diameters that varied from 4 to 30 mm and the distance between the nodules and the pleural surface varied from 2 to 43 mm. The location and resection of the nodules were successfully performed in all cases. The guidewire was displaced in five cases. Five patients presented pneumothorax, with the space between the visceral and parietal pleura varying from 2 to 19 mm. In nine patients, an intraparenchymal hematoma of 6 to 35 mm in length was observed without signs, symptoms, or hemodynamic and ventilatory repercussions. The histopathological study was conclusive in all patients. Conclusions: the localization of pulmonary nodules through guidewires proved to be safe, reliable, and feasible in this series of cases. There was no need for surgical intervention to treat complications.
RESUMO Objetivo: relatar a marcação pré-operatória de nódulos pulmonares com o posicionamento de um fio-guia orientado por Tomografia Computadorizada. Métodos: os nódulos foram marcados utilizando-se agulha em formato de anzol ou outra em formato de Q, orientada por tomografia. A escolha do local para a realização da marcação foi o de menor distância da parede torácica até à lesão. O procedimento de marcação foi realizado sob anestesia local e controle tomográfico foi obtido imediatamente ao término da marcação. Os pacientes foram encaminhados ao centro cirúrgico. A ressecção cirúrgica ocorreu em tempo inferior a duas horas após a marcação. Resultados: entre fevereiro de 2017 e outubro de 2019, 22 pacientes, com faixa etária entre 43 e 82 anos (média 62,1) foram incluídos. Os nódulos apresentavam diâmetros que variaram de 4 a 30mm e, a distância entre os nódulos e a superfície pleural variou de 2 a 43mm. A localização e a resseção dos nódulos foram realizadas com sucesso em todos os casos. Houve deslocamento do fio-guia em cinco casos. Cinco pacientes apresentaram pneumotóraces, com o espaço entre as pleuras visceral e parietal variando de 2 a 19mm. Em nove pacientes, foi observado hematoma intraparenquimatoso com 6 a 35mm de extensão sem sinais, sintomas ou repercussão hemodinâmica e ventilatória. O estudo histopatológico foi conclusivo em todos os pacientes. Conclusões: a marcação de nódulos pulmonares por meio de fios marcadores se mostrou segura, confiável e factível nesta série de casos. Não houve necessidade de intervenção para o tratamento de complicações associadas ao método.
Asunto(s)
Humanos , Adulto , Anciano , Anciano de 80 o más Años , Nódulo Pulmonar Solitario , Nódulos Pulmonares Múltiples , Neoplasias Pulmonares/cirugía , Neoplasias Pulmonares/diagnóstico por imagen , Cuidados Preoperatorios , Estudios Retrospectivos , Cirugía Torácica Asistida por Video , Pulmón , Persona de Mediana EdadRESUMEN
BACKGROUND@#Computed tomography (CT) three-dimensional reconstruction technology is increasingly used in preoperative planning of patients with ground glass nodule (GGN), but how to accurately locate the nodule and ensure the safe resection edge is still a difficult problem for clinicians. The purpose of this study was to investigate the accuracy, convenience and safety of CT three-dimensional reconstruction combined with intraoperative natural collapse localization in total thoracoscopic segmental pneumonectomy.@*METHODS@#A total of 45 patients with radiographic findings of pulmonary GGN admitted from July 2019 to December 2019 were selected as the study group. All patients received thin-slice CT scan and underwent preoperative three-dimensional reconstruction. After anesthesia, the small thoracic operation opening and the airway of the patients were quickly opened, and the lung was rapidly and naturally collapsed by pressure difference. GGN were positioned according to the natural marker line, and marked with 3-0 prolene line. After specimen removal, the distance between the GGN and the suture mark, the distance between the GGN and the incision margin were measured, and the incision margin was routinely examined. The general clinical data, pathological data and postoperative complications were counted and compared with 45 consecutive patients who were located with hookwire positioning needle in the same period.@*RESULTS@#The average localization time of non-invasive GGN with natural lung collapse during operation was 6.9 min, and the localization accuracy was 90.6%. There were 2 cases of extensive pleural adhesion and 1 case of emphysema. Postoperative pathology was confirmed as lung adenocarcinoma, and the examination of incision margin was negative. No GGNs were scanned again after surgery, and the precise resection rate of lung segment was 100.0%.@*CONCLUSIONS@#CT three-dimensional reconstruction combined with GGN localization of natural lung collapse during operation can shorten the time of searching for GGN during operation and guarantee the safety of the incision margin. It is a more economical and convenient localization method and makes pulmonary segment resection more accurate.
Asunto(s)
Humanos , Imagenología Tridimensional , Pulmón/cirugía , Neoplasias Pulmonares/cirugía , Atelectasia Pulmonar , Estudios Retrospectivos , Nódulo Pulmonar Solitario , Cirugía Torácica Asistida por Video , Tomografía Computarizada por Rayos XRESUMEN
The magnetic anchoring lung nodule positioning device is composed of a target magnet, an anchor magnet, a coaxial puncture needle and a puncture navigation template, through these, a new type of accurate positioning technology for small pulmonary nodules is derived. The device inserts the target magnet into the both sides nearby the lung nodule under the guidance of CT. Helped by the mutual attraction of the two target magnets, they can be fixed in the lung tissue, avoiding the movement in the lung, and accurately positioning the target lung nodule before surgery. In thoracoscopic surgery, the anchor magnet and the target magnet attract each other to achieve the purpose of positioning the target nodule. The device uses the characteristics of non-contact suction of magnetic materials biomedical engineering technology, eliminating the previous procedure of direct interaction with the positioning marks, finally achieves the target of precise positioning of lung nodules and rapid surgical removal.
Asunto(s)
Humanos , Pulmón , Neoplasias Pulmonares , Fenómenos Magnéticos , Imanes , Nódulo Pulmonar Solitario , Cirugía Torácica Asistida por Video , Tomografía Computarizada por Rayos XRESUMEN
Introducción: El nódulo pulmonar es un hallazgo generalmente incidental. Su detección ha aumentado observándose hasta en 13 por ciento de las tomografías. El diagnóstico diferencial plantea un desafío. Objetivo: Describir el caso de un paciente con nódulos pulmonares múltiples y su abordaje a partir de recomendaciones basadas en la evidencia. Caso clínico: Se presenta el caso de un paciente de 35 años con sintomatología inespecífica y nódulos pulmonares múltiples incidentales en estudios cervicotorácicos. Se analizaron etiologías posibles según datos clínicos, epidemiológicos, radiológicos y probabilidad de malignidad. Las recomendaciones basadas en la evidencia dirigieron el manejo. Dada la probabilidad intermedia de malignidad se indicó seguimiento escanográfico en 3 a 6 meses. Conclusiones: El caso presentado pretende reforzar destrezas clínicas en el manejo de esta entidad repercutiendo favorablemente en la morbimortalidad. Busca además impulsar el desarrollo de estrategias de tamizaje en poblaciones de riesgo(AU)
Introduction: The pulmonary nodule is a generally incidental finding. Its detection has increased, being observed in up to 13 percent of CT scans. Differential diagnosis poses a challenge. Objective: To describe the case of a patient with multiple pulmonary nodules and the approach to it based on evidence-based recommendations. Clinical case report: The case of a 35-year-old patient with nonspecific symptoms and incidental multiple pulmonary nodules in cervicothoracic studies is reported. Possible etiologies were analyzed according to clinical, epidemiological, radiological data and probability of malignancy. Evidence-based recommendations guided management. Given the intermediate probability of malignancy, a scan follow-up was indicated in 3 to 6 months. Conclusions: This case aims to reinforce clinical skills in the management of this entity, favourably impacting on morbidity and mortality. It also seeks to promote the development of screening strategies in populations at risk(AU)
Asunto(s)
Humanos , Masculino , Adulto , Tomografía Computarizada por Rayos X/métodos , Nódulo Pulmonar Solitario/etiología , Nódulo Pulmonar Solitario/diagnóstico por imagen , Hallazgos Incidentales , Colombia , Granuloma/diagnósticoRESUMEN
Introducción: el nódulo pulmonar solitario es uno de los problemas más frecuentes en la práctica del radiólogo, que constituye un hallazgo incidental habitual en los estudios torácicos realizados durante el ejercicio clínico diario. Objetivo: implementar un sistema de diagnóstico asistido por computadora que facilite la detección del nódulo pulmonar solitario en las series de imágenes de tomografía computarizada multicorte. Métodos: se utilizó Matlab para el desarrollo y evaluación de un conjunto de algoritmos que constituyen elementos necesarios de un sistema de diagnóstico asistido por computadora. En orden: un algoritmo para la extracción de las regiones de interés, algoritmo para la extracción de características y un algoritmo de detección de nódulo pulmonar solitario para el cual se probaron varios clasificadores. La evaluación de los algoritmos fue efectuada en base a las anotaciones realizada por especialistas a la colección de imágenes LIDC-IDRI (Lung Image Database Consortium). Resultados: el método de segmentación empleado para extracción de las regiones de interés permitió generar la adecuada división de las imágenes originales en regiones significativas. El algoritmo utilizado en la detección mostró para el conjunto de prueba además de buena exactitud (de 96,4 por ciento), un buen balance de sensibilidad (91,5 por ciento) para una tasa de 0,84 falsos positivos por imagen. Conclusiones: el trabajo de investigación y la implementación realizada se reflejan en la construcción de una interfaz gráfica en Matlab como prototipo del sistema de diagnóstico asistido por computadora, con el que se puede contribuir a detectar más fácilmente el NPS(AU)
Introduction: solitary pulmonary nodules are one of the most frequent problems in radiographic practice. They are a common incidental finding in chest studies conducted during routine clinical work. Objective: implement a computer-assisted diagnostic system facilitating detection of solitary pulmonary nodules in multicut computerized tomography image series. Methods: Matlab was used to develop and evaluate a set of algorithms constituting necessary components of a computer-assisted diagnostic system. The order was the following: an algorithm to extract regions of interest, another to extract characteristics, and another to detect solitary pulmonary nodules, for which several classifiers were tested. Evaluation of the algorithms was based on notes taken by specialists on the LIDC-IDRI (Lung Image Database Consortium) image collection. Results: the segmentation method used for extraction of regions of interest made it possible to create a suitable division of the original images into significant regions. The algorithm used for detection found that the test set exhibited good accuracy (96.4%), a good sensitivity balance (91.5%), and a 0.84 rate of false positives per image. Conclusions: the research and implementation work done is reflected in the construction of a Matlab graphic interface serving as a prototype for a computer-assisted diagnostic system which may facilitate detection of SPNs.
Asunto(s)
Humanos , Tomografía Computarizada por Rayos X/métodos , Diagnóstico por Computador/métodos , Nódulo Pulmonar Solitario/diagnóstico por imagen , AlgoritmosRESUMEN
Resumen Objetivo: Describir los diagnósticos histopatológicos a partir de los casos de las pacientes con cáncer de mama que fueron llevadas a resección de nódulos pulmonares en el Instituto Nacional de Cancerología (INC). Materiales y métodos: Se desarrolló un estudio tipo serie de casos donde se describen las características clínicas, histológicas y anatomopatológicas de un grupo de pacientes con diagnóstico confirmado de cáncer de mama de novo o que durante su enfermedad presentaron nódulos pulmonares que requirieron resección quirúrgica mediante cuña pulmonar o lobectomía en el INC, entre el 1 de enero de 2015 y el 30 de abril de 2018. Resultados: En el periodo de estudio se realizaron 225 resecciones en cuña pulmonar y lobectomías, 55 de estos pacientes tenían diagnóstico de cáncer de mama, de los cuales el 69,1% fueron de origen neoplásico, 26 pacientes fueron metástasis de cáncer mama (47,3%), 9 pacientes tenían segundo primario pulmonar (16,4%) y un paciente tenía concomitantemente cáncer primario pulmonar y una metástasis de mama (1,8%). Otras 2 pacientes tenían metástasis de otros órganos, uno de recto y uno de tiroides (3,6%), mientras que las 17 pacientes restantes presentaron reporte de lesiones pulmonares benignas en la anatomía patológica (30,9%). Conclusión: La presencia de nódulos pulmonares en pacientes con cáncer de mama no siempre son secundarias a enfermedad metastásica en pulmón; pueden existir otras etiologías como cáncer primario pulmonar, metástasis de otros órganos, tumores benignos o infecciones. Conocer la etiología de los nódulos pulmonares en pacientes con cáncer de mama es determinante para evaluar las opciones terapéuticas que pueden variar desde el manejo quirúrgico hasta el manejo sistémico.
Abstract Objectives: To describe the histopathological diagnoses of patients with breast cancer who underwent resection of pulmonary nodules at the National Cancer Institute (INC) of Bogotá. Materials and methods: A case-series study was developed to describe the clinical, histological and anatomopathological characteristics of a sample of patients with a diagnosis of de novo metastatic breast cancer or whom presented with pulmonary nodules during their disease that required surgical resection by wedge pulmonary or lobectomy in the INC, between January 1, 2015 and April 30, 2018. Results: During the study period, 225 resections were performed in lung wedge and lobectomies, 55 of these patients had a diagnosis of breast cancer, of which 69.1% were of neoplastic origin, 26 (47.3%) were metastatic of breast cancer, 9 (16.4%) second primary pulmonary and 1 (1.8%) patient had concomitantly primary lung cancer and a breast metastasis. Another 2 (3.6%) patients had metastases from other organs, one from the rectum and one from the thyroid, while the remaining 17 (30.9%) patients presented a report of benign lung lesions in the pathology. Conclusion: The presence of pulmonary nodules in patients with breast cancer are not always secondary to metastatic disease. Other etiologies may exist, such as primary pulmonary cancer, metastasis from other cancers, benign lung tumors or infections. Knowing the etiology of pulmonary nodules in patients with breast cancer is crucial to evaluate the therapeutic options that can vary from surgical management to systemic management.
Asunto(s)
Humanos , Neoplasias de la Mama , Nódulo Pulmonar Solitario , Nódulos Pulmonares Múltiples , Metástasis de la NeoplasiaRESUMEN
To evaluate the value and clinical effect of different preoperative localization techniques for solitary pulmonary nodules (SPN) before single-port thoracoscopic surgery.From January 2018 to June 2019, 54 patients diagnosed with solitary pulmonary nodules received single-port thoracoscopic surgery in Thoracic Department of General Hospital of Southern Theater Command of PLA. Based on the location methods of the nodules, the patients were divided into group A (34 cases) with preoperative CT-guided Hook-wire (a common positioning needle usually using in mammary gland) positioning and group B (20 cases) with preoperative CT-guided methylene blue location.The success rate of localization in group A was 94.18% (32/34), significantly higher than that in group B [85% (17/20), < 0.05). No intraoperative conversion to thoracotomy occurred in group A, while the conversion rate was 10% (2/20) in group B ( < 0.05). The average positioning cost was significantly higher in group A than in group B (1715±109 1021±86 RMB yuan, < 0.05), but the total hospitalization cost was similar between the two groups (50 114±3788 47871±5902 RMB yuan, >0.05). The length of hospital stay was significantly shorter in group A than in group B (6.71±1.23 8.19±2.61 days, < 0.05).Compared with the traditional methylene blue localization method, Hook-wire localization positioning can significantly increase the success rate of localization, and can be used as the standard preoperative localization method in patients undergoing single-port thoracoscopic pulmonary nodule resection, especially in those with deep nodule location from the visceral pleura.
Asunto(s)
Humanos , Neoplasias Pulmonares , Cuidados Preoperatorios , Nódulo Pulmonar Solitario , Cirugía Torácica Asistida por Video , Tomografía Computarizada por Rayos XRESUMEN
OBJECTIVE@#To explore the prognosis factors that influence the postoperative survival rate in patients with malignant solitary pulmonary nodules and to provide a reference for the prognosis risk stratification of early lung cancer patients.@*METHODS@#In this study, we retrospectively reviewed 172 patients who were admitted to Peking University First Hospital from April 2006 to December 2013. All cases were radiologically defined as solitary pulmonary nodule and were pathologically confirmed to be stage Ia non-small cell lung cancer after surgical procedure. The patients' clinical and follow-up data were summarized and analyzed. The relevance between survival time and factors that may affect patients' prognosis was evaluated, which included gender, age, clinical symptoms, smoking history, comorbidity index, tumor biomarkers, nodule type, type of surgery, nodule location, nodule histopathological type, nodule size, histopathological differentiation grade, proliferating cell nuclear antigen Ki-67 expression level and epidermal growth factor receptor (EGFR) gene mutation. Kaplan-Meier survival analysis, Cox univariant and multivariant regression analysis were conducted to evaluate the factors affecting prognosis.@*RESULTS@#The 3-year overall survival rate of the atients with malignant solitary pulmonary nodules was 93.6%, and the 5-year overall survival rate was 89.8%. KaplanMeier survival analysis and Cox univariant regression analysis showed that the overall survival rate of the male patients was significantly lower than that of the female patients. In addition, the elderly patients with histopathology characterized as high Ki-67 proliferation index were also associated with the worse overall survival (P<0.05). Cox multivariant regression analysis demonstrated that age more than 65 years as well as the high Ki-67 expression level were independent risk factors for overall survival in patients with malignant solitary pulmonary nodules (age: P=0.023, HR=3.531, 95%CI 1.190-10.472; Ki-67: P=0.004, HR=1.021, 95%CI 1.007-1.035).@*CONCLUSION@#For patients with malignant solitary pulmonary nodules, with pathological defined as stage Ia non-small cell lung cancer, age, gender and Ki-67 expression levels might be important prognostic factors. Comprehensive consideration of Ki-67 proliferation index and clinical pathological features may help to stratify the prognosis more accurately and guide the selection of appropriate therapeutic strategies, which needs to be verified by multi-center studies.
Asunto(s)
Anciano , Femenino , Humanos , Masculino , Carcinoma de Pulmón de Células no Pequeñas , Neoplasias Pulmonares , Pronóstico , Estudios Retrospectivos , Nódulo Pulmonar SolitarioRESUMEN
OBJETIVO: Determinar el rendimiento diagnóstico del PET/CT en el estudio de nódulo pulmonar (NP) utilizando SUVmax. MÉTODO: Se revisó la base de datos de PET/CT, seleccionando aquellos solicitados para estudio de NP sólido. Se incluyeron sólo aquellos NP confirmados como malignos o benignos. Se excluyó NP subsólidos, masas pulmonares (> 3 cm), y pacientes con metástasis conocidas. Se midió SUVmax de las lesiones, determinando mejores valores de corte para malignidad y benignidad. RESULTADOS: De los 140 NP estudiados, el 60% (84/140) fueron confirmados como malignos y el 40% como benignos (100% y 59,6% de confirmación histológica, respectivamente). Un SUVmax ≤ 1,0 mostró sensibilidad 98,8%, valor predictivo negativo (VPN) 96,2%, y Likelihood ratio negativo (LR -) 0,027. Un SUVmax ≤ 2,5 no fue capaz de asegurar razonablemente benignidad con VPN 69,4%, y LR - 0,295. Valores de SUV > 2,5 y 5,0 se asociaron a malignidad en 83% y 93% de los casos, respectivamente (LR+ 3,333 y 8,889). CONCLUSIÓN: El PET/CT presenta alto rendimiento diagnóstico en estimar la naturaleza de un NP Un valor de SUVmax ≤ 1 es altamente predictivo de benignidad, y un valor de SUVmax ≥ 2,5 de malignidad. Valores entre 1,0 y 2,5 no permiten caracterizar eficientemente los NP.
AIM: To establish the diagnostic accuracy of PET/CT in study of solid lung nodule (LN) using SUVmax index. METHOD: We revised PET/CT data base, selecting those scans asked to evaluate a solid LN. Only confirmed malign o benign LN were included. Subsolid LN, lung masses (> 3 cm), and known or suspected lung metastases were excluded. SUVmax was measured in each LN, and best cutoff for malignant and benign lesion was calculated. RESULTS: Of the whole group of 140 LN, 60% were confirmed as malignant, and 40% as benign (100% and 59,6% of histological confirmation, respectively). SUVmax ≤ 1,0 showed sensibility of 98,8%, negative predictive value (NPV) of 96,2%, and negative likelihood ratio (LR —) of 0,027. SUVmax ≤ 2,5 was not able to guarantee reasonably benign nature of LN, showing NPV of 69,4% and LR - of 0,295. SUVmax > 2,5 and > 5,0 was associated to malign lesion in 83% and 93% of cases, respectively (LR + of 3,333 and 8,889). CONCLUSION: PET/CT shows high accuracy estimating the nature of solid LN. SUVmax ≤ 1,0 is highly predictive of benignity, and SUVmax ≥ 2,5 is highly predictive of malignancy. SUVmax values between 1,0 and 2,5 were not able to characterize efficiently LN.
Asunto(s)
Humanos , Masculino , Femenino , Adulto , Persona de Mediana Edad , Anciano , Anciano de 80 o más Años , Adulto Joven , Nódulo Pulmonar Solitario/diagnóstico por imagen , Tomografía Computarizada por Tomografía de Emisión de Positrones/métodos , Neoplasias Pulmonares/diagnóstico por imagen , Valor Predictivo de las Pruebas , Sensibilidad y Especificidad , Nódulo Pulmonar Solitario/patología , Neoplasias Pulmonares/patologíaRESUMEN
OBJECTIVE: To evaluate the efficacy of the morphologic-metabolic (M-M) dissociation sign based on computed tomography (CT) and fluorine-18-fluorodeoxyglucose positron emission tomography (PET)/CT in discriminating invasive mucinous adenocarcinoma (IMA) from invasive non-mucinous adenocarcinomas (ADCs) of the lung. MATERIALS AND METHODS: The Institutional Review Board approved this retrospective study. Among surgically resected solitary pulmonary nodule (SPN)-type ADCs (< 3 cm in diameter), 35 patients with IMAs and 329 with invasive non-mucinous ADCs were included. Morphologic malignancy was established if the tumor with lobulated or spiculated margin on CT presented a tumor shadow disappearance rate of < 0.5. The M-M dissociation sign was determined when a malignant-morphologic nodule on CT showed maximum standardized uptake value (SUVmax) < 3.5 on PET/CT. RESULTS: Among 35 IMAs (size: 21 ± 7 mm, SUVmax: 1.8 ± 2.0) and 329 invasive non-mucinous ADCs (size: 21 ± 6 mm, SUVmax: 4.6 ± 4.2), the M-M dissociation sign was observed in 54% of IMAs (19/35) and 10% of invasive non-mucinous ADCs (34/329) (p < 0.001). The diagnostic performance of the sign in discriminating IMA from invasive non-mucinous ADCs showed a sensitivity of 54.3% (95% confidence interval [CI], 36.7–71.2), specificity 89.7% (95% CI, 85.9–92.7), positive predictive value 35.8% (95% CI, 26.5–46.5), and negative predictive value 94.9% (95% CI, 92.8–96.4). Multivariate analyses revealed metabolic benignity (odds ratio [OR] 2.99; 95% CI, 1.01–8.93; p = 0.047) and M-M dissociation sign (OR 6.35; 95% CI, 2.76–14.62; p < 0.001) to be significant predictors of SPN-type IMAs. CONCLUSION: Identification of the absence of M-M dissociation sign is an accurate indicator for excluding IMA from SPN-type lung ADCs.
Asunto(s)
Humanos , Adenocarcinoma , Adenocarcinoma Mucinoso , Diagnóstico , Comités de Ética en Investigación , Fluorodesoxiglucosa F18 , Pulmón , Mucinas , Análisis Multivariante , Tomografía de Emisión de Positrones , Tomografía Computarizada por Tomografía de Emisión de Positrones , Estudios Retrospectivos , Sensibilidad y Especificidad , Nódulo Pulmonar SolitarioRESUMEN
Lung cancer has the highest mortality rate among all malignant tumors. The key to reducing lung cancer mortality is the accurate diagnosis of pulmonary nodules in early-stage lung cancer. Computer-aided diagnostic techniques are considered to have potential beyond human experts for accurate diagnosis of early pulmonary nodules. The detection and classification of pulmonary nodules based on deep learning technology can continuously improve the accuracy of diagnosis through self-learning, and is an important means to achieve computer-aided diagnosis. First, we systematically introduced the application of two dimension convolutional neural network (2D-CNN), three dimension convolutional neural network (3D-CNN) and faster regions convolutional neural network (Faster R-CNN) techniques in the detection of pulmonary nodules. Then we introduced the application of 2D-CNN, 3D-CNN, multi-stream multi-scale convolutional neural network (MMCNN), deep convolutional generative adversarial networks (DCGAN) and transfer learning technology in classification of pulmonary nodules. Finally, we conducted a comprehensive comparative analysis of different deep learning methods in the detection and classification of pulmonary nodules.