Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 21.891
Filtrar
1.
Medicine (Baltimore) ; 99(45): e23114, 2020 Nov 06.
Artigo em Inglês | MEDLINE | ID: mdl-33157987

RESUMO

To investigate the value of percentile base on computed tomography (CT) histogram analysis for distinguishing invasive adenocarcinoma (IA) from adenocarcinoma in situ (AIS) or micro invasive adenocarcinoma (MIA) appearing as pure ground-glass nodules.A total of 42 cases of pure ground-glass nodules that were surgically resected and pathologically confirmed as lung adenocarcinoma between January 2015 and May 2019 were included. Cases were divided into IA and AIS/MIA in the study. The percentile on CT histogram was compared between the 2 groups. Univariate and multivariate logistic regression were used to determine which factors demonstrated a significant effect on invasiveness. The receiver operating characteristic (ROC) curve and the area under the curve (AUC) was used to evaluate the predictive ability of individual characteristics and the combined model.The 4 histogram parameters (25th percentile, 55th percentile, 95th percentile, 97.5th percentile) and the combined model all showed a certain diagnostic value. The combined model demonstrated the best diagnostic performance. The AUC values were as follows: 25th percentile = 0.693, 55th percentile = 0.706, 95th percentile = 0.713, 97.5th percentile = 0.710, and combined model = 0.837 (all P < .05).The percentile of histogram parameters help to improve the ability to radiologically determine the invasiveness of lung adenocarcinoma appearing as pure ground-glass nodules.


Assuntos
Adenocarcinoma in Situ/diagnóstico por imagem , Adenocarcinoma in Situ/patologia , Adenocarcinoma de Pulmão/diagnóstico por imagem , Adenocarcinoma de Pulmão/patologia , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/patologia , Tomografia Computadorizada por Raios X , Adulto , Idoso , Área Sob a Curva , Diagnóstico Diferencial , Feminino , Humanos , Modelos Logísticos , Masculino , Pessoa de Meia-Idade , Invasividade Neoplásica , Estudos Retrospectivos , Tomografia Computadorizada por Raios X/estatística & dados numéricos
2.
Kyobu Geka ; 73(11): 920-923, 2020 Oct.
Artigo em Japonês | MEDLINE | ID: mdl-33130714

RESUMO

A 71-year-old man with a history of smoking 1 pack of cigarettes per day for the past 53 years visited our department with chest pain, and was diagnosed as spontaneous pneumothorax. A chest computed tomography scan revealed a nodular shadow in the upper portion of the left lobe of the lung, which was found to be adenocarcinoma by transbronchial lung biopsy. A left upper lobectomy and lymphadenectomy were performed. The pathological diagnosis was a high-grade fetal lung adenocarcinoma (H-FLAC) with a hepatoid adenocarcinoma component (pT2aN0M0, pStage I B). H-FLAC comprises at least 50% fetal lung-like cells, while hepatoid adenocarcinoma comprises hepatocellular carcinoma-like cells. Following the diagnosis, adjuvant chemotherapy with uracil-tegafur was started. Although both these neoplasms are known to have a poor prognosis, no recurrences were observed at 11 months postsurgery.


Assuntos
Adenocarcinoma de Pulmão , Adenocarcinoma , Neoplasias Hepáticas , Neoplasias Pulmonares , Adenocarcinoma/cirurgia , Adenocarcinoma de Pulmão/diagnóstico por imagem , Idoso , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Masculino , Recidiva Local de Neoplasia
3.
Kyobu Geka ; 73(11): 961-963, 2020 Oct.
Artigo em Japonês | MEDLINE | ID: mdl-33130725

RESUMO

The case is 77 years old, female. She was referred to a local doctor with a chief complaint of cough and wheezing and was treated as asthma. However, symptoms did not improve and she was referred to our hospital. She had a history of right upper lobectomy for lung cancer about 2 years before, with the pathological diagnosis of adenosquamous cell carcinoma, pT1aN0M0, stage I A. Chest computed tomography (CT) scan showed a pedunculated polypoid mass almost occupying the lumen in the trachea immediately above the tracheal bifurcation, and the emergency bronchoscopic resection using a high-frequency snare under general anesthesia was performed. Postoperatively, 50 Gray of radiotherapy was added.


Assuntos
Carcinoma Adenoescamoso , Neoplasias Pulmonares , Neoplasias da Traqueia , Idoso , Carcinoma Adenoescamoso/diagnóstico por imagem , Carcinoma Adenoescamoso/cirurgia , Feminino , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/cirurgia , Recidiva Local de Neoplasia , Traqueia , Neoplasias da Traqueia/diagnóstico por imagem , Neoplasias da Traqueia/cirurgia
4.
Kyobu Geka ; 73(11): 968-971, 2020 Oct.
Artigo em Japonês | MEDLINE | ID: mdl-33130727

RESUMO

A 57-year-old woman was referred to our hospital for investigation of multiple tiny nodules in the lung fields bilaterally on computed tomography (CT). Video-assisted thoracoscopic lung biopsy was performed to diagnose the pulmonary lesions. Histological analysis showed nodular lesions with interstitial proliferation of uniform, round to oval cells with variable widening of the alveolar septa. Immunohistochemically, the cells were positive for EMA, CD56 and the progesterone receptor, but negative for chromogranin and synaptophysin. The diagnosis was "diffuse pulmonary meningotheliomatosis", with multiple diffuse "minute pulmonary meningothelial-like nodules". Diffuse pulmonary meningotheliomatosis should be kept in mind when we encounter small nodular shadows on a CT scan.


Assuntos
Neoplasias Pulmonares , Biópsia , Diagnóstico Diferencial , Feminino , Humanos , Pulmão , Neoplasias Pulmonares/diagnóstico por imagem , Pessoa de Meia-Idade , Tomografia Computadorizada por Raios X
5.
Kyobu Geka ; 73(10): 829-833, 2020 Sep.
Artigo em Japonês | MEDLINE | ID: mdl-33130774

RESUMO

While cases of surgical resection for primary lung cancers are increasing, lung cancer requiring vertebrectomy is rare. A high complication rate and recurrence rate have been reported after surgical resection for lung cancer with vertebral invasion. However, select patients who achieve complete resection after effective preoperative chemoradiotherapy show a better survival rate than others. Preoperative computed tomography and magnetic resonance imaging are necessary to consider surgical strategies and how to resect and reconstruct the vertebral body and chest wall with a clear margin before surgery. A 3-dimensional imaging or simulation model is useful for such ends. Several surgical approaches have been developed, such as the transmanubrial, posterior, posterolateral, or the combination thereof. Proper vertebrectomy( total, hemi, part of a vertebra, or only the transverse process of a vertebra) and reconstruction approaches should be decided in conjunction with orthopedic surgeons. While evidence is lacking, establishing proper surgical indications and developing effective strategies to achieve complete resection with a clear margin are the most critical points in lung cancer requiring vertebrectomy.


Assuntos
Neoplasias Pulmonares , Neoplasias da Coluna Vertebral , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/cirurgia , Recidiva Local de Neoplasia , Pneumonectomia , Neoplasias da Coluna Vertebral/diagnóstico por imagem , Neoplasias da Coluna Vertebral/cirurgia , Coluna Vertebral , Resultado do Tratamento
6.
Rev Med Suisse ; 16(713): 2086-2091, 2020 Nov 04.
Artigo em Francês | MEDLINE | ID: mdl-33146956

RESUMO

The NLST study in the United States showed, in 2011, that low-dose lung CT scans can reduce lung cancer mortality but was limited in its routine recommendation by 96% of false positive screening results. The European NELSON trial, published in 2020, confirmed a 24% decrease in lung cancer mortality and, by using lung nodule volume and volume doubling time, decreased false positive results to 56% of positive tests. The implementation of screening programs is now expected in Europe, including Switzerland. In anticipation, we have developed a decision aid to present patients with the benefits (decreased lung cancer mortality), risks (false positives and indeterminate results), and uncertainties (incidental findings) of lung cancer screening.


Assuntos
Detecção Precoce de Câncer , Neoplasias Pulmonares , Europa (Continente) , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/epidemiologia , Programas de Rastreamento , Suíça/epidemiologia , Estados Unidos
7.
Medicine (Baltimore) ; 99(42): e22636, 2020 Oct 16.
Artigo em Inglês | MEDLINE | ID: mdl-33080701

RESUMO

INTRODUCTION: The cervix is a rare site of metastasis from advanced lung adenocarcinoma. Driven gene detection is particularly important for the treatment of advanced lung adenocarcinoma. PATIENT CONCERNS: A 49-year-old Chinese female was sent to our hospital because of lumbago and sacroiliac joint pain; she was unable to walk and had vaginal bleeding. The following examinations were performed: imaging, colposcopy, bronchoscopy, immunohistochemistry and next-generation sequencing. DIAGNOSIS: According to the clinical manifestations and the examination results, the diagnosis was lung adenocarcinoma with cervical, brain, adrenal gland and bone metastases. More importantly, EGFR gene mutations (del19) were detected in both the primary lung lesion and uterine cervical biopsy specimen. INTERVENTIONS: Osimertinib was chosen as the first-line treatment. OUTCOMES: Lumbago and sacroiliac joint pain were significantly relieved. The levels of tumor markers decreased. Primary injuries and metastatic sites were significantly reduced. CONCLUSION: Physicians should be alert to the signals of vaginal bleeding and consider that primary lung adenocarcinoma may metastasize to the uterine cervix.


Assuntos
Adenocarcinoma/secundário , Genes erbB-1 , Neoplasias Pulmonares/patologia , Neoplasias Uterinas/secundário , Acrilamidas/uso terapêutico , Adenocarcinoma/diagnóstico por imagem , Adenocarcinoma/tratamento farmacológico , Adenocarcinoma/genética , Compostos de Anilina/uso terapêutico , Antineoplásicos/uso terapêutico , Feminino , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/tratamento farmacológico , Neoplasias Pulmonares/genética , Pessoa de Meia-Idade , Metástase Neoplásica , Deleção de Sequência , Neoplasias Uterinas/diagnóstico por imagem , Neoplasias Uterinas/tratamento farmacológico , Neoplasias Uterinas/genética
8.
Med Clin North Am ; 104(6): 1037-1050, 2020 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-33099449

RESUMO

Lung cancer screening with low-dose computed tomography provides an opportunity to save lives by early detection of the deadliest cancer in the United States. Uptake of lung cancer screening has been quite low but may be improving. Clinician and patient education, integration of lung cancer screening protocols into electronic medical records, support for shared decision making and tobacco cessation, and improved communication between referral centers and clinicians are all important areas for improvement for lung cancer screening to reach its potential in improving morbidity and mortality from lung cancer.


Assuntos
Neoplasias Pulmonares/prevenção & controle , Atenção Primária à Saúde , Detecção Precoce de Câncer , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Padrões de Prática Médica/estatística & dados numéricos , Abandono do Hábito de Fumar , Tomografia Computadorizada por Raios X , Estados Unidos
10.
Nat Commun ; 11(1): 5228, 2020 10 16.
Artigo em Inglês | MEDLINE | ID: mdl-33067442

RESUMO

Two major treatment strategies employed in non-small cell lung cancer, NSCLC, are tyrosine kinase inhibitors, TKIs, and immune checkpoint inhibitors, ICIs. The choice of strategy is based on heterogeneous biomarkers that can dynamically change during therapy. Thus, there is a compelling need to identify comprehensive biomarkers that can be used longitudinally to help guide therapy choice. Herein, we report a 18F-FDG-PET/CT-based deep learning model, which demonstrates high accuracy in EGFR mutation status prediction across patient cohorts from different institutions. A deep learning score (EGFR-DLS) was significantly and positively associated with longer progression free survival (PFS) in patients treated with EGFR-TKIs, while EGFR-DLS is significantly and negatively associated with higher durable clinical benefit, reduced hyperprogression, and longer PFS among patients treated with ICIs. Thus, the EGFR-DLS provides a non-invasive method for precise quantification of EGFR mutation status in NSCLC patients, which is promising to identify NSCLC patients sensitive to EGFR-TKI or ICI-treatments.


Assuntos
Carcinoma Pulmonar de Células não Pequenas/diagnóstico por imagem , Aprendizado Profundo , Neoplasias Pulmonares/diagnóstico por imagem , Inibidores de Proteínas Quinases/administração & dosagem , Idoso , Carcinoma Pulmonar de Células não Pequenas/tratamento farmacológico , Carcinoma Pulmonar de Células não Pequenas/genética , Carcinoma Pulmonar de Células não Pequenas/mortalidade , Receptores ErbB/genética , Receptores ErbB/metabolismo , Feminino , Humanos , Neoplasias Pulmonares/tratamento farmacológico , Neoplasias Pulmonares/genética , Neoplasias Pulmonares/mortalidade , Masculino , Pessoa de Meia-Idade , Mutação , Tomografia Computadorizada com Tomografia por Emissão de Pósitrons , Intervalo Livre de Progressão
11.
Medicine (Baltimore) ; 99(43): e22772, 2020 Oct 23.
Artigo em Inglês | MEDLINE | ID: mdl-33120787

RESUMO

Lung cancer is 1 of the leading causes of cancer-related deaths and bronchoscopy is an essential tool for the diagnosis. The diagnostic yield varies based on the characteristics of the lesion and bronchoscopic techniques employed. There is limited data regarding outcomes of patients suspected of thoracic malignancies with a non-diagnostic initial bronchoscopy. The goal of the study was to evaluate the outcomes of patients with a non-diagnostic bronchoscopy for suspected thoracic malignancies and to evaluate variables predictive of a diagnostic bronchoscopy.Retrospective analysis of adult patients at BronxCare Hospital Center who underwent bronchoscopy for suspected thoracic malignancy. The study period was January 2012 to February 2019. Exclusion criteria included patients who underwent only inspection bronchoscopy or bronchoalveolar lavage as the diagnostic yield for malignancy with these techniques is low. All other bronchoscopic procedures were included that is, endobronchial biopsies, transbronchial biopsies, and endobronchial ultrasound guided-transbronchial needle aspiration. Bronchoscopy was considered diagnostic when a specific histopathological diagnosis was established.311 patients underwent bronchoscopy to rule out malignancy. A diagnosis was obtained in 153 (49.2%) patients, 81 (52.9%) had primary lung cancer and 14 (9.15%) other malignancies. 158 (50.8%) patients had initial non-diagnostic bronchoscopy; 86 (54.43%) were lost to follow up. Of the remaining 72 (45.57%) patients, radiological resolution or stability was observed in 51 (70.8%) patients. Primary lung cancer was found in 13 (18.05%) patients and other malignancies in 5 (6.94%). Predictive of a diagnostic bronchoscopy was the performance of endobronchial biopsies and endobronchial ultrasound guided-transbronchial needle aspiration.This study highlights some of the barriers to the timely diagnosis of thoracic malignancies. Following patients with a non-diagnostic procedure as well as all those patients with diagnosed malignancies it of the utmost importance. In patients available for follow up, close to 25% of additional cases with treatable malignancy could be identified and patients diagnosed with cancer could receive timely treatment.


Assuntos
Broncoscopia/estatística & dados numéricos , Neoplasias Torácicas/diagnóstico por imagem , Neoplasias Torácicas/patologia , Idoso , Broncoscopia/efeitos adversos , Broncoscopia/métodos , Aspiração por Agulha Fina Guiada por Ultrassom Endoscópico , Feminino , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/patologia , Masculino , Pessoa de Meia-Idade , Estudos Retrospectivos
12.
Eur J Radiol ; 132: 109338, 2020 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-33068840

RESUMO

OBJECTIVES: The aim of our study was to investigate the value of a simple metabolic heterogeneity parameter, COV (coefficient of variation), by 18 F-fluorodeoxyglucose (FDG) positron emission tomography (PET) in the prognosis prediction of central lung cancer in early and locally advanced non-small-cell lung cancer (NSCLC). METHODS: Seventy-three patients with NSCLC manifesting as central lung cancer were included retrospectively, and we used the COV to evaluate metabolic heterogeneity. Univariate and multivariate analyses were used to evaluate the predictive value in terms of overall survival (OS) and progression-free survival (PFS). RESULT: For all 73 patients with pathologically confirmed NSCLC, 69.9 % had SCC, and 30.1 % had ADC or other types of NSCLC. The COV was a statistically significant factor in the univariate analysis for the OS rate. The optimal cut-off value was 23.1366, with sensitivity = 0.737 and specificity = 0.771. The COV values were dichotomized by this value and included with atelectasis in the Cox multivariate analysis. Both COV and atelectasis were independent risk factors for OS as follows: for COV (HR, 3.162, P = 0.0002), the 2-year OS rate was 62.5 % and 26.9 % in the low and high COV groups, respectively. For atelectasis (HR 2.047, P = 0.041), the 2-year OS rate was 30.6 % and 65.2 % in the groups with and without atelectasis, respectively (P = 0.017). For PFS, only COV (HR, 2.636, P = 0.001) was a significant predictor. The 2-year PFS rate was 29.7 % in the low COV group and 8% in the high COV group. CONCLUSION: The pre-treatment metabolic heterogeneity parameter COV is a simple and easy way to predict the OS and PFS of patients with NSCLC manifesting as central lung cancer. Therefore, COV plays an important role in prognostic risk classification in NSCLC. The presence of atelectasis could also be a risk factor for poor prognosis of OS.


Assuntos
Carcinoma Pulmonar de Células não Pequenas/diagnóstico por imagem , Carcinoma Pulmonar de Células não Pequenas/mortalidade , Fluordesoxiglucose F18 , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/mortalidade , Tomografia Computadorizada com Tomografia por Emissão de Pósitrons/métodos , Tomografia Computadorizada com Tomografia por Emissão de Pósitrons/estatística & dados numéricos , Idoso , Estudos de Avaliação como Assunto , Feminino , Humanos , Interpretação de Imagem Assistida por Computador/métodos , Pulmão/diagnóstico por imagem , Masculino , Pessoa de Meia-Idade , Prognóstico , Compostos Radiofarmacêuticos , Reprodutibilidade dos Testes , Estudos Retrospectivos , Taxa de Sobrevida
13.
Int J Med Sci ; 17(16): 2561-2569, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33029098

RESUMO

Background: During the outbreak period of COVID-19 pneumonia, cancer patients have been neglected and in greater danger. Furthermore, the differential diagnosis between COVID-19 pneumonia and radiation pneumonitis in cancer patients remains a challenge. This study determined their clinical presentations and radiological features in order to early diagnose and separate COVID-19 pneumonia from radiation pneumonitis patients promptly. Methods and Findings: From January 21, 2020 to February 18, 2020, 112 patients diagnosed with suspected COVID-19 were selected consecutively. A retrospective analysis including all patients' presenting was performed. Four patients from 112 suspected individals were selected, including 2 males and 2 females with a median age of 54 years (range 39-64 years). After repeated pharyngeal swab nucleic acid tests, 1 case was confirmed and 3 cases were excluded from COVID-19 pneumonia. Despite the comparable morphologic characteristics of lung CT imaging, the location, extent, and distribution of lung lesions between COVID-19 pneumonia and radiation pneumonitis differed significantly. Conclusions: Lung CT imaging combined with clinical and laboratory findings can facilitate early diagnosis and appropriate management of COVID-19 pneumonia with a history of malignancy and radiation therapy.


Assuntos
Betacoronavirus , Infecções por Coronavirus/diagnóstico por imagem , Diagnóstico Diferencial , Neoplasias/radioterapia , Pneumonia Viral/diagnóstico por imagem , Pneumonite por Radiação/diagnóstico por imagem , Adulto , Técnicas de Laboratório Clínico , Infecções por Coronavirus/diagnóstico , Neoplasias Esofágicas/diagnóstico por imagem , Neoplasias Esofágicas/patologia , Neoplasias Esofágicas/radioterapia , Feminino , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/radioterapia , Masculino , Pessoa de Meia-Idade , Neoplasias Nasofaríngeas/diagnóstico por imagem , Neoplasias Nasofaríngeas/patologia , Neoplasias Nasofaríngeas/radioterapia , Neoplasias/virologia , Pandemias , Estudos Retrospectivos , Tomografia Computadorizada por Raios X
14.
Ann Palliat Med ; 9(5): 3373-3378, 2020 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-33065788

RESUMO

BACKGROUND: The coronavirus disease (COVID-19) poses an unprecedented challenge to health and epidemic prevention system, especially the healthcare of patients with cancer. We sought to study the impact of COVID-19 on lung cancer patients in our center. METHODS: We initiated a retrospectively study to analyze the impact of COVID-19 on lung cancer patients in our center, who were accepted for routine anticancer treatment before the epidemic and planned to return to hospital in January and February of 2020. RESULTS: A total of 161 cases of lung cancer were included in the final analysis. As of April 15, 95 patients had delayed their return visit, and 47 cases were finally designated as having delayed admission during the epidemic and having to discontinue or delay their regular anticancer treatments. Of these 47 delayed patients, 33 were evaluated for tumor status using a computed tomography scan, 6 of these 33 cases (18.18%) were diagnosed as progressive disease (PD), and 5 cases did not return for visit. CONCLUSIONS: This is the first study investigating impact of COVID-19 on non-COVID-19 lung cancer patients during the pandemic. The study demonstrates the significant impact of the COVID-19 crisis on oncological care, indicating the need for appropriate change of treatment decisions and continued follow-up and psycho-oncological support during this pandemic.


Assuntos
Antineoplásicos/uso terapêutico , Carcinoma Pulmonar de Células não Pequenas/terapia , Infecções por Coronavirus , Imunoterapia , Neoplasias Pulmonares/terapia , Pandemias , Pneumonia Viral , Radioterapia , Carcinoma de Pequenas Células do Pulmão/terapia , Tempo para o Tratamento/estatística & dados numéricos , Adulto , Idoso , Idoso de 80 Anos ou mais , Betacoronavirus , Carcinoma Pulmonar de Células não Pequenas/diagnóstico por imagem , Quimiorradioterapia , China , Assistência à Saúde , Progressão da Doença , Feminino , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Masculino , Pessoa de Meia-Idade , Estadiamento de Neoplasias , Estudos Retrospectivos , Carcinoma de Pequenas Células do Pulmão/diagnóstico por imagem
15.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1556-1559, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018289

RESUMO

Because of the significance of bronchial lesions as indicators of early lung cancer and squamous cell carcinoma, a critical need exists for early detection of bronchial lesions. Autofluorescence bronchoscopy (AFB) is a primary modality used for bronchial lesion detection, as it shows high sensitivity to suspicious lesions. The physician, however, must interactively browse a long video stream to locate lesions, making the search exceedingly tedious and error prone. Unfortunately, limited research has explored the use of automated AFB video analysis for efficient lesion detection. We propose a robust automatic AFB analysis approach that distinguishes informative and uninformative AFB video frames in a video. In addition, for the informative frames, we determine the frames containing potential lesions and delineate candidate lesion regions. Our approach draws upon a combination of computer-based image analysis, machine learning, and deep learning. Thus, the analysis of an AFB video stream becomes more tractable. Using patient AFB video, 99.5%/90.2% of test frames were correctly labeled as informative/uninformative by our method versus 99.2%/47.6% by ResNet. In addition, ≥97% of lesion frames were correctly identified, with false positive and false negative rates ≤3%.Clinical relevance-The method makes AFB-based bronchial lesion analysis more efficient, thereby helping to advance the goal of better early lung cancer detection.


Assuntos
Broncoscopia , Neoplasias Pulmonares , Lesões Pré-Cancerosas , Brônquios , Fluorescência , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Lesões Pré-Cancerosas/diagnóstico por imagem
16.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1229-1233, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018209

RESUMO

AIChest4All is the name of the model used to label and screening diseases in our area of focus, Thailand, including heart disease, lung cancer, and tuberculosis. This is aimed to aid radiologist in Thailand especially in rural areas, where there is immense staff shortages. Deep learning is used in our methodology to classify the chest X-ray images from datasets namely, NIH set, which is separated into 14 observations, and the Montgomery and Shenzhen set, which contains chest X-ray images of patients with tuberculosis, further supplemented by the dataset from Udonthani Cancer hospital and the National Chest Institute of Thailand. The images are classified into six categories: no finding, suspected active tuberculosis, suspected lung malignancy, abnormal heart and great vessels, Intrathoracic abnormal findings, and Extrathroacic abnormal findings. A total of 201,527 images were used. Results from testing showed that the accuracy values of the categories heart disease, lung cancer, and tuberculosis were 94.11%, 93.28%, and 92.32%, respectively with sensitivity values of 90.07%, 81.02%, and 82.33%, respectively and the specificity values were 94.65%, 94.04%, and 93.54%, respectively. In conclusion, the results acquired have sufficient accuracy, sensitivity, and specificity values to be used. Currently, AIChest4All is being used to help several of Thailand's government funded hospitals, free of charge.Clinical relevance- AIChest4All is aimed to aid radiologist in Thailand especially in rural areas, where there is immense staff shortages. It is being used to help several of Thailand's goverment funded hospitals, free of charege to screening heart disease, lung cancer, and tubeculosis with 94.11%, 93.28%, and 92.32% accuracy.


Assuntos
Neoplasias Pulmonares , Tuberculose , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Programas de Rastreamento , Sensibilidade e Especificidade , Tailândia
17.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1254-1257, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018215

RESUMO

Computer-aided Diagnosis (CAD) systems have long aimed to be used in clinical practice to help doctors make decisions by providing a second opinion. However, most machine learning based CAD systems make predictions without explicitly showing how their predictions were generated. Since the cognitive process of the diagnostic imaging interpretation involves various visual characteristics of the region of interest, the explainability of the results should leverage those characteristics. We encode visual characteristics of the region of interest based on pairs of similar images rather than the image content by itself. Using a Siamese convolutional neural network (SCNN), we first learn the similarity among nodules, then encode image content using the SCNN similarity-based feature representation, and lastly, we apply the K-nearest neighbor (KNN) approach to make diagnostic characterizations using the Siamese-based image features. We demonstrate the feasibility of our approach on spiculation, a visual characteristic that radiologists consider when interpreting the degree of cancer malignancy, and the NIH/NCI Lung Image Database Consortium (LIDC) dataset that contains both spiculation and malignancy characteristics for lung nodules.Clinical Relevance - This establishes that spiculation can be quantified to automate the diagnostic characterization of lung nodules in Computed Tomography images.


Assuntos
Neoplasias Pulmonares , Interpretação de Imagem Radiográfica Assistida por Computador , Humanos , Pulmão , Neoplasias Pulmonares/diagnóstico por imagem , Redes Neurais de Computação , Tomografia Computadorizada por Raios X
18.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1791-1794, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018346

RESUMO

Low dose computed tomography (LDCT) is the current gold-standard for lung cancer diagnosis. However, accuracy of diagnosis is limited by the radiologist's ability to discern cancerous from non-cancerous nodules. To assist with diagnoses, a 4D-CT lung elastography method is proposed to distinguish nodules based on tissue stiffness properties. The technique relies on a patient-specific inverse finite element (FE) model of the lung solved using an optimization algorithm. The FE model incorporates hyperelastic material properties for tumor and healthy regions and was deformed according to respiration physiology. The tumor hyperelastic parameters and trans-pulmonary pressure were estimated using an optimization algorithm that maximizes similarity between the actual and simulated tumor and lung image data. The proposed technique was evaluated using an in-silico study where the lung tumor elastic properties were assumed. Following that evaluation, the technique was applied to clinical 4D-CT data of two lung cancer patients. Results from the evaluation study show that the elastography technique recovered known tumor parameters with only 6% error. Tumor hyperelastic properties from the clinical data are also reported. Results from this proof of concept study demonstrate the ability to perform lung elastography with 4D-CT data alone. Advancements in the technique could lead to improved diagnoses and timely treatment of lung cancer.


Assuntos
Técnicas de Imagem por Elasticidade , Neoplasias Pulmonares , Algoritmos , Tomografia Computadorizada Quadridimensional , Humanos , Pulmão/diagnóstico por imagem , Neoplasias Pulmonares/diagnóstico por imagem
19.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1891-1894, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018370

RESUMO

Fluorescence lifetime is effective in discriminating cancerous tissue from normal tissue, but conventional discrimination methods are primarily based on statistical approaches in collaboration with prior knowledge. This paper investigates the application of deep convolutional neural networks (CNNs) for automatic differentiation of ex-vivo human lung cancer via fluorescence lifetime imaging. Around 70,000 fluorescence images from ex-vivo lung tissue of 14 patients were collected by a custom fibre-based fluorescence lifetime imaging endomicroscope. Five state-of-the-art CNN models, namely ResNet, ResNeXt, Inception, Xception, and DenseNet, were trained and tested to derive quantitative results using accuracy, precision, recall, and the area under receiver operating characteristic curve (AUC) as the metrics. The CNNs were firstly evaluated on lifetime images. Since fluorescence lifetime is independent of intensity, further experiments were conducted by stacking intensity and lifetime images together as the input to the CNNs. As the original CNNs were implemented for RGB images, two strategies were applied. One was retaining the CNNs by putting intensity and lifetime images in two different channels and leaving the remaining channel blank. The other was adapting the CNNs for two-channel input. Quantitative results demonstrate that the selected CNNs are considerably superior to conventional machine learning algorithms. Combining intensity and lifetime images introduces noticeable performance gain compared with using lifetime images alone. In addition, the CNNs with intensity-lifetime RGB image is comparable to the modified two-channel CNNs with intensity-lifetime two-channel input for accuracy and AUC, but significantly better for precision and recall.


Assuntos
Aprendizado Profundo , Neoplasias Pulmonares , Algoritmos , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Aprendizado de Máquina , Redes Neurais de Computação
20.
Pediatrics ; 146(5)2020 11.
Artigo em Inglês | MEDLINE | ID: mdl-33060256

RESUMO

We report a 16-year-old phenotypic female with 46,XY complete gonadal dysgenesis and metastatic dysgerminoma, unexpectedly discovered through direct-to-consumer (DTC) commercial genetic testing. This case underscores the importance of timely interdisciplinary care, including psychosocial intervention and consideration of gonadectomy, to optimize outcomes for individuals with differences of sex development. Her unique presentation highlights the implications of DTC genetic testing in a new diagnostic era and informs general pediatricians as well as specialists of nongenetic services about the value, capabilities, and limitations of DTC testing.


Assuntos
Publicidade Direta ao Consumidor , Disgerminoma/secundário , Testes Genéticos/métodos , Disgenesia Gonadal 46 XY/diagnóstico , Gonadoblastoma/secundário , Neoplasias Ovarianas/patologia , Adolescente , Biomarcadores Tumorais/sangue , Disgerminoma/sangue , Disgerminoma/diagnóstico por imagem , Disgerminoma/genética , Feminino , Identidade de Gênero , Genes sry/genética , Disgenesia Gonadal 46 XY/sangue , Gonadoblastoma/sangue , Gonadoblastoma/diagnóstico por imagem , Gonadoblastoma/genética , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/secundário , Neoplasias Ovarianas/diagnóstico por imagem , Fenótipo
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA