scholarly journals Convolutional Neural Networks Promising in Lung Cancer T-Parameter Assessment on Baseline FDG-PET/CT

2018 ◽  
Vol 2018 ◽  
pp. 1-6 ◽  
Author(s):  
Margarita Kirienko ◽  
Martina Sollini ◽  
Giorgia Silvestri ◽  
Serena Mognetti ◽  
Emanuele Voulaz ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Fdg Pet ◽  
Area Under The Curve ◽  
Ct Images ◽  
Tnm System ◽  
Positron Emission ◽  
Pet Ct ◽  
Test Sets ◽  
Fdg Pet Ct

Aim. To develop an algorithm, based on convolutional neural network (CNN), for the classification of lung cancer lesions as T1-T2 or T3-T4 on staging fluorodeoxyglucose positron emission tomography (FDG-PET)/CT images. Methods. We retrospectively selected a cohort of 472 patients (divided in the training, validation, and test sets) submitted to staging FDG-PET/CT within 60 days before biopsy or surgery. TNM system seventh edition was used as reference. Postprocessing was performed to generate an adequate dataset. The input of CNNs was a bounding box on both PET and CT images, cropped around the lesion centre. The results were classified as Correct (concordance between reference and prediction) and Incorrect (discordance between reference and prediction). Accuracy (Correct/[Correct + Incorrect]), recall (Correctly predicted T3-T4/[all T3-T4]), and specificity (Correctly predicted T1-T2/[all T1-T2]), as commonly defined in deep learning models, were used to evaluate CNN performance. The area under the curve (AUC) was calculated for the final model. Results. The algorithm, composed of two networks (a “feature extractor” and a “classifier”), developed and tested achieved an accuracy, recall, specificity, and AUC of 87%, 69%, 69%, and 0.83; 86%, 77%, 70%, and 0.73; and 90%, 47%, 67%, and 0.68 in the training, validation, and test sets, respectively. Conclusion. We obtained proof of concept that CNNs can be used as a tool to assist in the staging of patients affected by lung cancer.

scholarly journals FDG PET/CT Overcomes Discordance Between Clinical and Pathologic TNM Classification of Small-size Primary Lung Cancer: Influence on Postoperative Prognosis

2018 ◽  
Vol 19 (1) ◽  
pp. e37-e45 ◽  
Author(s):  
Hiroyasu Umakoshi ◽  
Shingo Iwano ◽  
Kohei Yokoi ◽  
Shinji Ito ◽  
Rintaro Ito ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Fdg Pet ◽  
Tnm Classification ◽  
Primary Lung Cancer ◽  
Postoperative Prognosis ◽  
Pet Ct ◽  
Fdg Pet Ct

scholarly journals Molecular imaging and immunotherapy

2020 ◽  
Vol 35 (1_suppl) ◽  
pp. 37-41
Author(s):  
Laura Evangelista
Keyword(s):  
Computed Tomography ◽  
Lung Cancer ◽  
Positron Emission Tomography ◽  
Clinical Practice ◽  
Fdg Pet ◽  
Emission Tomography ◽  
Positron Emission ◽  
Pet Ct ◽  
Fdg Pet Ct

The utility of positron emission tomography (PET) for the evaluation of response to immunotherapy has been considered a hot topic, particularly in the last 2 to 3 years. Different experiences have been collected in clinical practice, with 18F-Fluorodeoxyglucose (FDG) PET/computed tomography (CT), particularly in patients affected by lymphoma, malignant melanoma, and lung cancer. It has been tested in different settings of disease, from the prediction to the prognosis relative to the response to immunotherapy. In the present mini-review, some evidence is reported about the role of FDG PET/CT in patient candidates to or treated with immunotherapy.

Pseudomesotheliomatous lung cancer mimicking mesothelioma on 18F-FDG PET/CT images: report of 2 cases

2013 ◽  
Vol 31 (8) ◽  
pp. 542-545 ◽  
Author(s):  
Takatoshi Nakamori ◽  
Shigeru Kosuda ◽  
Yukishige Kyoto ◽  
Akira Fujikawa ◽  
Yutaka Naoi ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Fdg Pet ◽  
Ct Images ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

scholarly journals Diagnostic Performance of PET or PET/CT with Different Radiotracers in Patients with Suspicious Lung Cancer or Pleural Tumours according to Published Meta-Analyses

2020 ◽  
Vol 2020 ◽  
pp. 1-7 ◽  
Author(s):  
Filippo Lococo ◽  
Barbara Muoio ◽  
Marco Chiappetta ◽  
Dania Nachira ◽  
Leonardo Petracca Ciavarella ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Positron Emission Tomography ◽  
Fdg Pet ◽  
Diagnostic Performance ◽  
Emission Tomography ◽  
Evidence Based ◽  
Positron Emission ◽  
Pet Ct ◽  
Meta Analyses ◽  
Fdg Pet Ct

Purpose. Several meta-analyses have reported data about the diagnostic performance of positron emission tomography or positron emission tomography/computed tomography (PET or PET/CT) with different radiotracers in patients with suspicious lung cancer (LC) or pleural tumours (PT). This review article aims at providing an overview on the recent evidence-based data in this setting. Methods. A comprehensive literature search of meta-analyses published in PubMed/MEDLINE and Cochrane Library database from January 2010 through March 2020 about the diagnostic performance of PET or PET/CT with different radiotracers in patients with suspicious LC or PT was performed. This combination of keywords was used: (A) “PET” OR “positron emission tomography” AND (B) “lung” OR “pulmonary” OR “pleur∗” AND (C) meta-analysis. Only meta-analyses on PET or PET/CT in patients with suspicious LC or PT were selected. Results. We have summarized the diagnostic performance of PET or PET/CT with fluorine-18 fluorodeoxyglucose (18F-FDG) and other radiotracers taking into account 17 meta-analyses. Evidence-based data demonstrated a good diagnostic performance of 18F-FDG PET or PET/CT for the characterization of solitary pulmonary nodules (SPNs) or pleural lesions with overall higher sensitivity than specificity. Evidence-based data do not support the routine use of dual time point (DTP) 18F-FDG PET/CT or fluorine-18 fluorothymidine (18F-FLT) PET/CT in the differential diagnosis of SPNs. Even if 18F-FDG PET/CT has high sensitivity and specificity as a selective screening modality for LC, its role in this setting remains unknown. Conclusions. Evidence-based data about the diagnostic performance of PET/CT with different radiotracers for suspicious LC or PT are increasing, with good diagnostic performance of 18F-FDG PET/CT. More prospective multicenter studies and cost-effectiveness analyses are warranted.

scholarly journals Role of integrated F-18 fluoro-deoxy-glucose positron emission tomography and computed tomography in evaluation of lung cancer

2012 ◽  
Vol 20 (3-4) ◽  
pp. 107-111
Author(s):  
Dragana Sobic-Saranovic
Keyword(s):  
Lung Cancer ◽  
Fdg Pet ◽  
Small Cell ◽  
Emission Tomography ◽  
Small Cell Lung ◽  
Positron Emission ◽  
Pet Ct ◽  
Fdg Pet Ct

Lung cancer is one of the leading causes of death in the world. It is generally divided in two groups: non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC). Positron emission tomography (PET)/CT using the glucose analogue labeled with 18-fluor (F-18): fluoro-deoxy-glucose (F-18-FDG), is unique integrated imaging modality that offers simultaneous anatomic and metabolic information valuable in the diagnosis, staging and follow-up of both types of lung cancer and in particular in NSCLC. FDG accumulation in tissue is proportional to the amount of glucose utilization. Increased consumption of glucose is a characteristic of almost all types of lung cancer except in bronchoalveolar carcinoma and well differentiated neuroendocrine tumors. The objective of this brief review is to highlight the clinical role of F-18-FDG PET/CT in detection, staging, re-staging, and assessment of therapy response and follow up in lung cancer. The performance of F-18-FDG PET/CT in specific clinical situations is of special interest: in the differentiation of indeterminate lung lesions, the staging of NSCLC for lymph node and extra thoracic metastases, for therapy planning, the detection of recurrent lung cancer and the use in SCLC. In conclusion, F-18-FDG PET/CT helps in characterization of suspicious lesions, provides more precise staging of NSCLC than other imaging techniques, allows better patients? selection for new modalities of treatment, helps in restaging after induction therapy, allows better delineation for radiotherapy planning and helps in follow up evaluation by differentiating residual or recurrent tumor from post treatment scar.

Pulmonary F-18 FDG uptake of non-tumor area in lung cancer patients to provide risk stratification in postoperative acute exacerbation of interstitial lung disease.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e13165-e13165
Author(s):  
Takashi Yamamichi ◽  
Yoshihisa Shimada ◽  
Yojiro Makino ◽  
Masatoshi Kakihana ◽  
Naohiro Kajiwara ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Acute Exacerbation ◽  
Fdg Pet ◽  
Clinical Decision Making ◽  
Pulmonary Resection ◽  
Lung Tumor ◽  
Area Under The Curve ◽  
Pet Ct ◽  
Clinical Records ◽  
Fdg Pet Ct

e13165 Background: The incidence of lung cancer in patients with idiopathic pulmonary fibrosis (IPF) is higher than the general population. In IPF patients with lung cancer, postoperative acute exacerbation (AE) is considered a fatal comorbidity. This study aimed to investigate whether FDG-PET/CT can be used to assess the risk of postoperative AE of IPF and severe respiratory adverse events (SRAE),which are defined as grade 3a or more severe respiratory complications such as AE, bacterial pneumonia, empyema, and bronchial fistula based upon Clavian-Dindo classification. Methods: We identified 822 patients with lung cancer who had preoperative FDG-PET/CT and subsequent pulmonary resection from July 2012 to July 2018. We reviewed the patients’ clinical records and transferredthe preoperative FDG-PET/CT images of each patient to SynapseVincent system (Fujifilm Corporation, Tokyo, Japan) for measuring SUV value of the lung.Inevery case, both SUVmax of main tumor (tumor-SUVmax) and non-lung tumor part (NLT-SUVmax) were measured. Univariate and multivariate analyses were performed for exploring significant parameters associated with AE and SRAE. Results: The cohort in this study consisted of 460 men and 362 women (mean age 67.9 ± 10.1 years; range 23–87). SRAE was observed in 35 (4.2%) patients including those with AE (n = 16, 1.9%). NLT-SUVmax and presence of IPF on CT were the independent predictive factors for both AE and SRAE. The receiver operating characteristic (ROC) area under the curve (AUC) of significant factors associated with AE and SRAE was measured, and cut-off levels on ROC curves for significant parameters associated with AE and SRAE were 1.69 and 1.55, respectively. The risk rates for the incidence of AE and SRAE according to NLT-SUVmax and chest CT findings were 19.0 % and 30.2% of the patients with positive IPF on CT and NLT-SUV max ≥1.69. Conclusions: NLT-SUVmax was the independent predictor of the incidence of AE and SRAE for patients who underwent pulmonary resection. FDG/PET-CT can be used in routine clinical practice to identify high-risk individuals for AE who require careful and intensive observation after pulmonary resection and that can facilitate clinical decision-making.

Sign in / Sign up

Export Citation Format

Share Document