Highly accurate model for prediction of lung nodule malignancy with CT scans.
Ontology highlight
ABSTRACT:
SUBMITTER: Causey JL
PROVIDER: S-EPMC6006355 | biostudies-literature | 2018 Jun
REPOSITORIES: biostudies-literature
Publications
Highly accurate model for prediction of lung nodule malignancy with CT scans.
Causey Jason L JL Zhang Junyu J Ma Shiqian S Jiang Bo B Qualls Jake A JA Politte David G DG Prior Fred F Zhang Shuzhong S Huang Xiuzhen X
Scientific reports 20180618 1
Computed tomography (CT) examinations are commonly used to predict lung nodule malignancy in patients, which are shown to improve noninvasive early diagnosis of lung cancer. It remains challenging for computational approaches to achieve performance comparable to experienced radiologists. Here we present NoduleX, a systematic approach to predict lung nodule malignancy from CT data, based on deep learning convolutional neural networks (CNN). For training and validation, we analyze >1000 lung nodul ...[more]
Similar Datasets
Project description:BackgroundChest Computed tomography (CT) scans detect lung nodules and assess pulmonary fibrosis. While pulmonary fibrosis indicates increased lung cancer risk, current clinical practice characterizes nodule risk of malignancy based on nodule size and smoking history; little consideration is given to the fibrotic microenvironment.PurposeTo evaluate the effect of incorporating fibrotic microenvironment into classifying malignancy of lung nodules in chest CT images using deep learning techniques.Materials and methodsWe developed a visualizable 3D classification model trained with in-house CT dataset for the nodule malignancy classification task. Three slightly-modified datasets were created: (1) nodule alone (microenvironment removed); (2) nodule with surrounding lung microenvironment; and (3) nodule in microenvironment with semantic fibrosis metadata. For each of the models, tenfold cross-validation was performed. Results were evaluated using quantitative measures, such as accuracy, sensitivity, specificity, and area-under-curve (AUC), as well as qualitative assessments, such as attention maps and class activation maps (CAM).ResultsThe classification model trained with nodule alone achieved 75.61% accuracy, 50.00% sensitivity, 88.46% specificity, and 0.78 AUC; the model trained with nodule and microenvironment achieved 79.03% accuracy, 65.46% sensitivity, 85.86% specificity, and 0.84 AUC. The model trained with additional semantic fibrosis metadata achieved 80.84% accuracy, 74.67% sensitivity, 84.95% specificity, and 0.89 AUC. Our visual evaluation of attention maps and CAM suggested that both the nodules and the microenvironment contributed to the task.ConclusionThe nodule malignancy classification performance was found to be improving with microenvironment data. Further improvement was found when incorporating semantic fibrosis information.
| S-EPMC10787502 | biostudies-literature
Project description:BackgroundA calibration phantom-based method has been developed for predicting small lung nodule volume measurement bias and precision that is specific to a particular computed tomography (CT) scanner and acquisition protocol.MethodsThe approach involves CT scanning a simple reference object with a specific acquisition protocol, analyzing the scan to estimate the fundamental imaging properties of the CT acquisition system, generating numerous simulated images of a target geometry using the fundamental imaging properties, measuring the simulated images with a standard nodule volume segmentation algorithm, and calculating bias and precision performance statistics from the resulting volume measurements. We evaluated the ability of this approach to predict volume measurement bias and precision of Teflon spheres (diameters =4.76, 6.36, and 7.94 mm) placed within an anthropomorphic chest phantom when using 3M Scotch Magic™ tape as the reference object. CT scanning of the spheres was performed with 0.625, 1.25, and 2.5 mm slice thickness and spacing.ResultsThe study demonstrated good agreement between predicted volumetric performance and observed volume measurement performance for both volumetric measurement bias and precision. The predicted and observed volume mean for all slice thicknesses was found to be 28% and 13% lower on average than the manufactured sphere volume, respectively. When restricted to 0.625 and 1.25 mm slice thickness scans, which are recommended for small lung nodule volume measurement, we found that the difference between predicted and observed volume coefficient of variation was less than 1.0 %. The approach also showed a resilience to varying CT image acquisition protocols, a critical capability when deploying in a real-world clinical setting.ConclusionsThis is the first report of a calibration phantom-based method's ability to predict both small lung nodule volume measurement bias and precision. Volume measurement bias and precision for small lung nodules can be predicted using simple low-cost reference objects to estimate fundamental CT image characteristics and modeling and simulation techniques. The approach demonstrates an improved method for predicting task specific, clinically relevant measurement performance using advanced and fully automated image analysis techniques and low-cost reference objects.
| S-EPMC10498266 | biostudies-literature
Project description:Spiculations/lobulations, sharp/curved spikes on the surface of lung nodules, are good predictors of lung cancer malignancy and hence, are routinely assessed and reported by radiologists as part of the standardized Lung-RADS clinical scoring criteria. Given the 3D geometry of the nodule and 2D slice-by-slice assessment by radiologists, manual spiculation/lobulation annotation is a tedious task and thus no public datasets exist to date for probing the importance of these clinically-reported features in the SOTA malignancy prediction algorithms. As part of this paper, we release a large-scale Clinically-Interpretable Radiomics Dataset, CIRDataset, containing 956 radiologist QA/QC'ed spiculation/lobulation annotations on segmented lung nodules from two public datasets, LIDC-IDRI (N=883) and LUNGx (N=73). We also present an end-to-end deep learning model based on multi-class Voxel2Mesh extension to segment nodules (while preserving spikes), classify spikes (sharp/spiculation and curved/lobulation), and perform malignancy prediction. Previous methods have performed malignancy prediction for LIDC and LUNGx datasets but without robust attribution to any clinically reported/actionable features (due to known hyperparameter sensitivity issues with general attribution schemes). With the release of this comprehensively-annotated CIRDataset and end-to-end deep learning baseline, we hope that malignancy prediction methods can validate their explanations, benchmark against our baseline, and provide clinically-actionable insights. Dataset, code, pretrained models, and docker containers are available at https://github.com/nadeemlab/CIR.
| S-EPMC9527770 | biostudies-literature
Project description:Classification of benign and malignant in lung nodules using chest CT images is a key step in the diagnosis of early-stage lung cancer, as well as an effective way to improve the patients' survival rate. However, due to the diversity of lung nodules and the visual similarity of lung nodules to their surrounding tissues, it is difficult to construct a robust classification model with conventional deep learning-based diagnostic methods. To address this problem, we propose a multi-model ensemble learning architecture based on 3D convolutional neural network (MMEL-3DCNN). This approach incorporates three key ideas: (1) Constructed multi-model network architecture can be well adapted to the heterogeneity of lung nodules. (2) The input that concatenated of the intensity image corresponding to the nodule mask, the original image, and the enhanced image corresponding to which can help training model to extract advanced feature with more discriminative capacity. (3) Select the corresponding model to different nodule size dynamically for prediction, which can improve the generalization ability of the model effectively. In addition, ensemble learning is applied in this paper to further improve the robustness of the nodule classification model. The proposed method has been experimentally verified on the public dataset, LIDC-IDRI. The experimental results show that the proposed MMEL-3DCNN architecture can obtain satisfactory classification results.
| S-EPMC7649841 | biostudies-literature
Project description:ObjectivesBoth radiomics and deep learning methods have shown great promise in predicting lesion malignancy in various image-based oncology studies. However, it is still unclear which method to choose for a specific clinical problem given the access to the same amount of training data. In this study, we try to compare the performance of a series of carefully selected conventional radiomics methods, end-to-end deep learning models, and deep-feature based radiomics pipelines for pulmonary nodule malignancy prediction on an open database that consists of 1297 manually delineated lung nodules.MethodsConventional radiomics analysis was conducted by extracting standard handcrafted features from target nodule images. Several end-to-end deep classifier networks, including VGG, ResNet, DenseNet, and EfficientNet were employed to identify lung nodule malignancy as well. In addition to the baseline implementations, we also investigated the importance of feature selection and class balancing, as well as separating the features learned in the nodule target region and the background/context region. By pooling the radiomics and deep features together in a hybrid feature set, we investigated the compatibility of these two sets with respect to malignancy prediction.ResultsThe best baseline conventional radiomics model, deep learning model, and deep-feature based radiomics model achieved AUROC values (mean ± standard deviations) of 0.792 ± 0.025, 0.801 ± 0.018, and 0.817 ± 0.032, respectively through 5-fold cross-validation analyses. However, after trying out several optimization techniques, such as feature selection and data balancing, as well as adding context features, the corresponding best radiomics, end-to-end deep learning, and deep-feature based models achieved AUROC values of 0.921 ± 0.010, 0.824 ± 0.021, and 0.936 ± 0.011, respectively. We achieved the best prediction accuracy from the hybrid feature set (AUROC: 0.938 ± 0.010).ConclusionThe end-to-end deep-learning model outperforms conventional radiomics out of the box without much fine-tuning. On the other hand, fine-tuning the models lead to significant improvements in the prediction performance where the conventional and deep-feature based radiomics models achieved comparable results. The hybrid radiomics method seems to be the most promising model for lung nodule malignancy prediction in this comparative study.
| S-EPMC8718670 | biostudies-literature
Project description:Currently, the new coronavirus disease (COVID-19) is one of the biggest health crises threatening the world. Automatic detection from computed tomography (CT) scans is a classic method to detect lung infection, but it faces problems such as high variations in intensity, indistinct edges near lung infected region and noise due to data acquisition process. Therefore, this article proposes a new COVID-19 pulmonary infection segmentation depth network referred as the Attention Gate-Dense Network- Improved Dilation Convolution-UNET (ADID-UNET). The dense network replaces convolution and maximum pooling function to enhance feature propagation and solves gradient disappearance problem. An improved dilation convolution is used to increase the receptive field of the encoder output to further obtain more edge features from the small infected regions. The integration of attention gate into the model suppresses the background and improves prediction accuracy. The experimental results show that the ADID-UNET model can accurately segment COVID-19 lung infected areas, with performance measures greater than 80% for metrics like Accuracy, Specificity and Dice Coefficient (DC). Further when compared to other state-of-the-art architectures, the proposed model showed excellent segmentation effects with a high DC and F1 score of 0.8031 and 0.82 respectively.
| S-EPMC7924694 | biostudies-literature
Project description:BackgroundPartial volume averaging and tilt relative to the scan plane on transverse images limit the accuracy of airway wall thickness measurements on CT scan, confounding assessment of the relationship between airway remodeling and clinical status in COPD. The purpose of this study was to assess the effect of partial volume averaging and tilt corrections on airway wall thickness measurement accuracy and on relationships between airway wall thickening and clinical status in COPD.MethodsAirway wall thickness measurements in 80 heavy smokers were obtained on transverse images from low-dose CT scan using the open-source program Airway Inspector. Measurements were corrected for partial volume averaging and tilt effects using an attenuation- and geometry-based algorithm and compared with functional status.ResultsThe algorithm reduced wall thickness measurements of smaller airways to a greater degree than larger airways, increasing the overall range. When restricted to analyses of airways with an inner diameter < 3.0 mm, for a theoretical airway of 2.0 mm inner diameter, the wall thickness decreased from 1.07 ± 0.07 to 0.29 ± 0.10 mm, and the square root of the wall area decreased from 3.34 ± 0.15 to 1.58 ± 0.29 mm, comparable to histologic measurement studies. Corrected measurements had higher correlation with FEV₁, differed more between BMI, airflow obstruction, dyspnea, and exercise capacity (BODE) index scores, and explained a greater proportion of FEV1 variability in multivariate models.ConclusionsCorrecting for partial volume averaging improves accuracy of airway wall thickness estimation, allowing direct measurement of the small airways to better define their role in COPD.
| S-EPMC3653346 | biostudies-literature
Project description:BackgroundPrediction rules for intracranial traumatic findings in patients with minor head injury are designed to reduce the use of computed tomography (CT) without missing patients at risk for complications. This study investigates whether alternative modelling techniques might improve the applicability and simplicity of such prediction rules.MethodsWe included 3181 patients with minor head injury who had received CT scans between February 2002 and August 2004. Of these patients 243 (7.6%) had intracranial traumatic findings and 17 (0.5%) underwent neurosurgical intervention. We analyzed sensitivity, specificity and area under the ROC curve (AUC-value) to compare the performance of various modelling techniques by 10 × 10 cross-validation. The techniques included logistic regression, Bayes network, Chi-squared Automatic Interaction Detection (CHAID), neural net, support vector machines, Classification And Regression Trees (CART) and "decision list" models.ResultsThe cross-validated performance was best for the logistic regression model (AUC 0.78), followed by the Bayes network model and the neural net model (both AUC 0.74). The other models performed poorly (AUC < 0.70). The advantage of the Bayes network model was that it provided a graphical representation of the relationships between the predictors and the outcome.ConclusionsNo alternative modelling technique outperformed the logistic regression model. However, the Bayes network model had a presentation format which provided more detailed insights into the structure of the prediction problem. The search for methods with good predictive performance and an attractive presentation format should continue.
| S-EPMC3212831 | biostudies-literature
Project description:PurposeDetermination and development of an effective set of models leveraging Artificial Intelligence techniques to generate a system able to support clinical practitioners working with COVID-19 patients. It involves a pipeline including classification, lung and lesion segmentation, as well as lesion quantification of axial lung CT studies.ApproachA deep neural network architecture based on DenseNet is introduced for the classification of weakly-labeled, variable-sized (and possibly sparse) axial lung CT scans. The models are trained and tested on aggregated, publicly available data sets with over 10 categories. To further assess the models, a data set was collected from multiple medical institutions in Colombia, which includes healthy, COVID-19 and patients with other diseases. It is composed of 1,322 CT studies from a diverse set of CT machines and institutions that make over 550,000 slices. Each CT study was labeled based on a clinical test, and no per-slice annotation took place. This enabled a classification into Normal vs. Abnormal patients, and for those that were considered abnormal, an extra classification step into Abnormal (other diseases) vs. COVID-19. Additionally, the pipeline features a methodology to segment and quantify lesions of COVID-19 patients on the complete CT study, enabling easier localization and progress tracking. Moreover, multiple ablation studies were performed to appropriately assess the elements composing the classification pipeline.ResultsThe best performing lung CT study classification models achieved 0.83 accuracy, 0.79 sensitivity, 0.87 specificity, 0.82 F1 score and 0.85 precision for the Normal vs. Abnormal task. For the Abnormal vs COVID-19 task, the model obtained 0.86 accuracy, 0.81 sensitivity, 0.91 specificity, 0.84 F1 score and 0.88 precision. The ablation studies showed that using the complete CT study in the pipeline resulted in greater classification performance, restating that relevant COVID-19 patterns cannot be ignored towards the top and bottom of the lung volume.DiscussionThe lung CT classification architecture introduced has shown that it can handle weakly-labeled, variable-sized and possibly sparse axial lung studies, reducing the need for expert annotations at a per-slice level.ConclusionsThis work presents a working methodology that can guide the development of decision support systems for clinical reasoning in future interventionist or prospective studies.
| S-EPMC9554434 | biostudies-literature
Project description:BackgroundPre-treatment FDG-PET/CT scans were analyzed with machine learning to predict progression of lung malignancies and overall survival (OS).MethodsA retrospective review across three institutions identified patients with a pre-procedure FDG-PET/CT and an associated malignancy diagnosis. Lesions were manually and automatically segmented, and convolutional neural networks (CNNs) were trained using FDG-PET/CT inputs to predict malignancy progression. Performance was evaluated using area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. Image features were extracted from CNNs and by radiomics feature extraction, and random survival forests (RSF) were constructed to predict OS. Concordance index (C-index) and integrated brier score (IBS) were used to evaluate OS prediction.Findings1168 nodules (n=965 patients) were identified. 792 nodules had progression and 376 were progression-free. The most common malignancies were adenocarcinoma (n=740) and squamous cell carcinoma (n=179). For progression risk, the PET+CT ensemble model with manual segmentation (accuracy=0.790, AUC=0.876) performed similarly to the CT only (accuracy=0.723, AUC=0.888) and better compared to the PET only (accuracy=0.664, AUC=0.669) models. For OS prediction with deep learning features, the PET+CT+clinical RSF ensemble model (C-index=0.737) performed similarly to the CT only (C-index=0.730) and better than the PET only (C-index=0.595), and clinical only (C-index=0.595) models. RSF models constructed with radiomics features had comparable performance to those with CNN features.InterpretationCNNs trained using pre-treatment FDG-PET/CT and extracted performed well in predicting lung malignancy progression and OS. OS prediction performance with CNN features was comparable to a radiomics approach. The prognostic models could inform treatment options and improve patient care.FundingNIH NHLBI training grant (5T35HL094308-12, John Sollee).
| S-EPMC9278031 | biostudies-literature