Quantitative Imaging features Improve Discrimination of Malignancy in Pulmonary nodules.
Ontology highlight
ABSTRACT:
SUBMITTER: Balagurunathan Y
PROVIDER: S-EPMC6561979 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:PurposeTo quantitatively assess the value of dual-energy CT (DECT) in differentiating malignancy and benignity of solitary pulmonary nodules.Materials and methodsSixty-three patients with solitary pulmonary nodules detected by CT plain scan underwent contrast enhanced CT scans in arterial phase (AP) and venous phase (VP) with spectral imaging mode for tumor type differentiation. The Gemstone Spectral Imaging (GSI) viewer was used for image display and data analysis. Region of interest was placed on the relatively homogeneous area of the nodule to measure iodine concentration (IC) on iodine-based material decomposition images and CT numbers on monochromatic image sets to generate spectral HU curve. Normalized IC (NIC), slope of the spectral HU curve (?HU) and net CT number enhancement on 70keV images were calculated. The two-sample t-test was used to compare quantitative parameters. Receiver operating characteristic curves were generated to calculate sensitivity and specificity.ResultsThere were 63 nodules, with 37 malignant nodules (59%) and 26 benign nodules (41%). NIC, ?HU and net CT number enhancement on 70keV images for malignant nodules were all greater than those of benign nodules. NIC and ?HU had intermediate to high performances to differentiate malignant nodules from benign ones with the areas under curve of 0.89 and 0.86 respectively in AP, 0.96 and 0.89 respectively in VP. Using 0.30 as a threshold value for NIC in VP, one could obtain sensitivity of 93.8% and specificity of 85.7% for differentiating malignant from benign solitary pulmonary nodules. These values were statistically higher than the corresponding values of 74.2% and 53.8% obtained with the conventional CT number enhancement.ConclusionsDECT imaging with GSI mode provides more promising value in quantitative way for distinguishing malignant nodules from benign ones than CT enhancement numbers.
| S-EPMC4739615 | biostudies-literature
Project description:Radiomics is to provide quantitative descriptors of normal and abnormal tissues during classification and prediction tasks in radiology and oncology. Quantitative Imaging Network members are developing radiomic "feature" sets to characterize tumors, in general, the size, shape, texture, intensity, margin, and other aspects of the imaging features of nodules and lesions. Efforts are ongoing for developing an ontology to describe radiomic features for lung nodules, with the main classes consisting of size, local and global shape descriptors, margin, intensity, and texture-based features, which are based on wavelets, Laplacian of Gaussians, Law's features, gray-level co-occurrence matrices, and run-length features. The purpose of this study is to investigate the sensitivity of quantitative descriptors of pulmonary nodules to segmentations and to illustrate comparisons across different feature types and features computed by different implementations of feature extraction algorithms. We calculated the concordance correlation coefficients of the features as a measure of their stability with the underlying segmentation; 68% of the 830 features in this study had a concordance CC of ≥0.75. Pairwise correlation coefficients between pairs of features were used to uncover associations between features, particularly as measured by different participants. A graphical model approach was used to enumerate the number of uncorrelated feature groups at given thresholds of correlation. At a threshold of 0.75 and 0.95, there were 75 and 246 subgroups, respectively, providing a measure for the features' redundancy.
| S-EPMC5279995 | biostudies-literature
Project description:ObjectivesDistinction of malignant pulmonary nodules from the benign ones based on computed tomography (CT) images can be time-consuming but significant in routine clinical management. The advent of artificial intelligence (AI) has provided an opportunity to improve the accuracy of cancer risk prediction.MethodsA total of 8950 detected pulmonary nodules with complete pathological results were retrospectively enrolled. The different radiological manifestations were identified mainly as various nodules densities and morphological features. Then, these nodules were classified into benign and malignant groups, both of which were subdivided into finer specific pathological types. Here, we proposed a deep convolutional neural network for the assessment of lung nodules named DeepLN to identify the radiological features and predict the pathologic subtypes of pulmonary nodules.ResultsIn terms of density, the area under the receiver operating characteristic curves (AUCs) of DeepLN were 0.9707 (95% confidence interval, CI: 0.9645-0.9765), 0.7789 (95%CI: 0.7569-0.7995), and 0.8950 (95%CI: 0.8822-0.9088) for the pure-ground glass opacity (pGGO), mixed-ground glass opacity (mGGO) and solid nodules. As for the morphological features, the AUCs were 0.8347 (95%CI: 0.8193-0.8499) and 0.9074 (95%CI: 0.8834-0.9314) for spiculation and lung cavity respectively. For the identification of malignant nodules, our DeepLN algorithm achieved an AUC of 0.8503 (95%CI: 0.8319-0.8681) in the test set. Pertaining to predicting the pathological subtypes in the test set, the multi-task AUCs were 0.8841 (95%CI: 0.8567-0.9083) for benign tumors, 0.8265 (95%CI: 0.8004-0.8499) for inflammation, and 0.8022 (95%CI: 0.7616-0.8445) for other benign ones, while AUCs were 0.8675 (95%CI: 0.8525-0.8813) for lung adenocarcinoma (LUAD), 0.8792 (95%CI: 0.8640-0.8950) for squamous cell carcinoma (LUSC), 0.7404 (95%CI: 0.7031-0.7782) for other malignant ones respectively in the malignant group.ConclusionsThe DeepLN based on deep learning algorithm represented a competitive performance to predict the imaging characteristics, malignancy and pathologic subtypes on the basis of non-invasive CT images, and thus had great possibility to be utilized in the routine clinical workflow.
| S-EPMC9130467 | biostudies-literature
Project description:Over 80,000 people undergo pulmonary resection for a lung nodule in the United States each year. Small nodules are frequently missed or difficult to find despite preoperative imaging. We hypothesized that near-infrared (NIR) imaging technology could be used to identify and locate lung nodules during surgery.We enrolled 18 patients who were diagnosed with a pulmonary nodule that required resection. All patients had a fine-cut 1-mm computed tomography scan preoperatively. The patients were given systemic 5 mg/kg indocyanine green and then underwent an open thoracotomy 24 hours later. The NIR imaging was used to identify the primary nodule and search for additional nodules that were not found by visual inspection or manual palpation of the ipsilateral lung.Manual palpation and visual inspection identified all 18 primary pulmonary nodules and no additional lesions. Intraoperative NIR imaging detected 16 out of the 18 primary nodules. The NIR imaging also identified 5 additional subcentimeter nodules; 3 metastatic adenocarcinomas and 2 metastatic sarcomas. This technology could identify nodules as small as 0.2 cm and as deep as 1.3 cm from the pleural surface. This approach discovered 3 nodules that were in different lobes than the primary tumor. Nodule fluorescence was independent of size, metabolic activity, histology, tumor grade and vascularity.This is the first-in-human demonstration of identifying pulmonary nodules during thoracic surgery with NIR imaging without a priori knowledge of their location or existence. The NIR imaging can detect pulmonary nodules during lung resections that are poorly visualized on computed tomography and difficult to discriminate on finger palpation.
| S-EPMC4185369 | biostudies-literature
Project description:OBJECTIVES:The post-imaging, mathematical predictive model was established by combining demographic and imaging characteristics with a pulmonary nodule risk score. The prediction model provides directions for the treatment of pulmonary nodules. Many studies have established predictive models for pulmonary nodules in different populations. However, the predictive factors contained in each model were significantly different. We hypothesized that applying different models to local research groups will make a difference in predicting the benign and malignant lung nodules, distinguishing between early and late lung cancers, and between adenocarcinoma and squamous cell carcinoma. In the present study, we compared four widely used and well-known mathematical prediction models. MATERIALS AND METHODS:We performed a retrospective study of 496 patients from January 2017 to October 2019, they were diagnosed with nodules by pathological. We evaluate models' performance by viewing 425 malignant and 71 benign patients' computed tomography results. At the same time, we use the calibration curve and the area under the receiver operating characteristic curve whose abbreviation is AUC to assess one model's predictive performance. RESULTS:We find that in distinguishing the Benign and the Malignancy, Peking University People's Hospital model possessed excellent performance (AUC = 0.63), as well as differentiating between early and late lung cancers (AUC = 0.67) and identifying lung adenocarcinoma (AUC = 0.61). While in the identification of lung squamous cell carcinoma, the Veterans Affairs model performed the best (AUC = 0.69). CONCLUSIONS:Geographic disparities are an extremely important influence factors, and which clinical features contained in the mathematical prediction model are the key to affect the precision and accuracy.
| S-EPMC7048676 | biostudies-literature
Project description:BackgroundTo develop and validate a deep learning-based model on CT images for the malignancy and invasiveness prediction of pulmonary subsolid nodules (SSNs).Materials and methodsThis study retrospectively collected patients with pulmonary SSNs treated by surgery in our hospital from 2012 to 2018. Postoperative pathology was used as the diagnostic reference standard. Three-dimensional convolutional neural network (3D CNN) models were constructed using preoperative CT images to predict the malignancy and invasiveness of SSNs. Then, an observer reader study conducted by two thoracic radiologists was used to compare with the CNN model. The diagnostic power of the models was evaluated with receiver operating characteristic curve (ROC) analysis.ResultsA total of 2,614 patients were finally included and randomly divided for training (60.9%), validation (19.1%), and testing (20%). For the benign and malignant classification, the best 3D CNN model achieved a satisfactory AUC of 0.913 (95% CI: 0.885-0.940), sensitivity of 86.1%, and specificity of 83.8% at the optimal decision point, which outperformed all observer readers' performance (AUC: 0.846±0.031). For pre-invasive and invasive classification of malignant SSNs, the 3D CNN also achieved satisfactory AUC of 0.908 (95% CI: 0.877-0.939), sensitivity of 87.4%, and specificity of 80.8%.ConclusionThe deep-learning model showed its potential to accurately identify the malignancy and invasiveness of SSNs and thus can help surgeons make treatment decisions.
| S-EPMC8351466 | biostudies-literature
Project description:BACKGROUND:Mathematical predictive model is an effective method for preliminarily identifying the malignant pulmonary nodules. As the epidemiological trend of lung cancer changes, the detection rate of ground-glass-opacity (GGO) like early stage lung cancer is increasing rapidly, timely and proper clinical management can effectively improve the patients' prognosis. Our study aims to establish a novel predictive model of malignancy for non-solid pulmonary nodules, which would provide an objective evidence for invasive procedure and avoid unnecessary operation and the consequences. METHODS:We retrospectively analyzed the basic demographics, serum tumor markers and imaging features of 362 cases of non-solid pulmonary nodule from January 2013 to April 2018. All nodules received biopsy or surgical resection, and got pathological diagnosis. Cases were randomly divided into two groups. The modeling group was used for univariate analysis and logistic regression to determine independent risk factors and establish the predictive model. Data of the validation group was used to validate the predictive value and make a comparison with other models. RESULTS:Of the 362 cases with non-solid pulmonary nodule, 313 (86.5%) cases were diagnosed as AAH/AIS, MIA or invasive adenocarcinoma, 49 cases were diagnosed as benign lesions. Age, serum tumor markers CEA and Cyfra21-1, consolidation tumor ratio value, lobulation and calcification were identified as independent risk factors. The AUC value of the ROC curve was 0.894, the predictive sensitivity and specificity were 87.6%, 69.7%, the positive and negative predictive value were 94.8%, 46.9%. The validated predictive value is significantly better than that of the VA, Brock and GMUFH models. CONCLUSIONS:Proved with high predictive sensitivity and positive predictive value, this novel model could help enable preliminarily screening of "high-risk" non-solid pulmonary nodules before biopsy or surgical excision, and minimize unnecessary invasive procedure. This model achieved preferable predictive value, might have great potential for clinical application.
| S-EPMC6348162 | biostudies-literature
Project description:Early identification and classification of pulmonary nodules are essential for improving the survival rates of individuals with lung cancer and are considered to be key requirements for computer-assisted diagnosis. To address this topic, the present study proposed a method for predicting the malignant phenotype of pulmonary nodules based on weighted voting rules. This method used the pulmonary nodule regions of interest as the input data and extracted the features of the pulmonary nodules using the Denoising Auto Encoder, ResNet-18. Moreover, the software also modifies texture and shape features to assess the malignant phenotype of the pulmonary nodules. Based on their classification accuracy (Acc), the different classifiers were assigned to different weights. Finally, an integrated classifier was obtained to score the malignant phenotype of the pulmonary nodules. The present study included training and testing experiments conducted by extracting the corresponding lung nodule image data from the Lung Image Database Consortium-Image Database Resource Initiative. The results of the present study indicated a final classification Acc of 93.10±2.4%, demonstrating the feasibility and effectiveness of the proposed method. This method includes the powerful feature extraction ability of deep learning combined with the ability to use traditional features in image representation.
| S-EPMC7288754 | biostudies-literature
Project description:IntroductionMalignant cerebral edema develops in a small subset of patients with hemispheric strokes, precipitating deterioration and death if decompressive hemicraniectomy (DHC) is not performed in a timely manner. Predicting which stroke patients will develop malignant edema is imprecise based on clinical data alone. Head computed tomography (CT) imaging is often performed at baseline and 24-h. We determined the incremental value of incorporating imaging-derived features from serial CTs to enhance prediction of malignant edema.MethodsWe identified hemispheric stroke patients at three sites with NIHSS ≥ 7 who had baseline as well as 24-h clinical and CT imaging data. We extracted quantitative imaging features from baseline and follow-up CTs, including CSF volume, intracranial reserve (CSF/cranial volume), as well as midline shift (MLS) and infarct-related hypodensity volume. Potentially lethal malignant edema was defined as requiring DHC or dying with MLS over 5-mm. We built machine-learning models using logistic regression first with baseline data and then adding 24-h data including reduction in CSF volume (ΔCSF). Model performance was evaluated with cross-validation using metrics of recall (sensitivity), precision (predictive value), as well as area under receiver-operating-characteristic and precision-recall curves (AUROC, AUPRC).ResultsTwenty of 361 patients (6%) died or underwent DHC. Baseline clinical variables alone had recall of 60% with low precision (7%), AUROC 0.59, AUPRC 0.15. Adding baseline intracranial reserve improved recall to 80% and AUROC to 0.82 but precision remained only 16% (AUPRC 0.28). Incorporating ΔCSF improved AUPRC to 0.53 (AUROC 0.91) while all imaging features further improved prediction (recall 90%, precision 38%, AUROC 0.96, AUPRC 0.66).ConclusionIncorporating quantitative CT-based imaging features from baseline and 24-h CT enhances identification of patients with malignant edema needing DHC. Further refinements and external validation of such imaging-based machine-learning models are required.
| S-EPMC7738418 | biostudies-literature
Project description:PURPOSE:Diagnosis and resection of indeterminate pulmonary nodules (IPNs) is a growing challenge with increased utilization of chest computed tomography. Photoacoustic (PA) -guided surgical resection with local injection of indocyanine green (ICG) may have utility for IPNs that are suspicious for lung cancer. This preclinical study explores the potential of PA imaging (PAI) to detect ICG-labeled tumors. MATERIALS AND METHODS:ICG uptake by H460 lung cancer cells was evaluated in vitro. A phantom study was performed to analyze PA signal intensity according to ICG concentration and tissue thickness/depth using chicken breast. PA signals were measured up to 48 hours after injection of ICG (mixed with 5% agar) into healthy subcutaneous tissue, subcutaneous H460 tumors and right healthy lung in nude mice. RESULTS:Intracellular ICG fluorescence was detected in H460 cells co-incubated with ICG in vitro. The concentration dependence of the PA signal was logarithmic, and PA signal decline was exponential with increasing tissue depth. The PA signal of 2 mg/mL ICG was still detectable at a depth of 22 mm in chicken breast. The PA signal from ICG mixed with agar was detectable 48 hours post injection into subcutaneous tissue and subcutaneous H460 tumors in nude mice. Similar features of PA signals from ICG-agar in mice lung were obtained. CONCLUSION:The results from this preclinical study suggests that PAI of injected ICG-agar may be beneficial for identifying deeply located tumors. These features may be valuable for IPNs.
| S-EPMC7173852 | biostudies-literature