Colin Jacobs

Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks

We propose a novel Computer-Aided Detection (CAD) system for pulmonary nodules using multi-view convolutional networks (ConvNets), for which discriminative features are automatically learnt from the training data. The network is fed with nodule candidates obtained by combining three candidate detectors specifically designed for solid, subsolid, and large nodules. For each candidate, a set of 2-D patches from differently oriented planes is extracted. The proposed architecture comprises multiple streams of 2-D ConvNets, for which the outputs are combined using a dedicated fusion method to get the final classification. Data augmentation and dropout are applied to avoid overfitting. On 888 scans of the publicly available LIDC-IDRI dataset, our method reaches high detection sensitivities of 85.4% and 90.1% at 1 and 4 false positives per scan, respectively. An additional evaluation on independent datasets from the ANODE09 challenge and DLCST is performed. We showed that the proposed multi-view ConvNets is highly suited to be used for false positive reduction of a CAD system.

Off-the-shelf convolutional neural network features for pulmonary nodule detection in computed tomography scans

Convolutional neural networks (CNNs) have emerged as the most powerful technique for a range of different tasks in computer vision. Recent work suggested that CNN features are generic and can be used for classification tasks outside the exact domain for which the networks were trained. In this work we use the features from one such network, OverFeat, trained for object detection in natural images, for nodule detection in computed tomography scans. We use 865 scans from the publicly available LIDC data set, read by four thoracic radiologists. Nodule candidates are generated by a state-of-the-art nodule detection system. We extract 2D sagittal, coronal and axial patches for each nodule candidate and extract 4096 features from the penultimate layer of OverFeat and classify these with linear support vector machines. We show for various configurations that the off-the-shelf CNN features perform surprisingly well, but not as good as the dedicated detection system. When both approaches are combined, significantly better results are obtained than either approach alone. We conclude that CNN features have great potential to be used for detection tasks in volumetric medical data.

Automatic Detection of Subsolid Pulmonary Nodules in Thoracic Computed Tomography Images

Subsolid pulmonary nodules occur less often than solid pulmonary nodules, but show a much higher malignancy rate. Therefore, accurate detection of this type of pulmonary nodules is crucial. In this work, a computer-aided detection (CAD) system for subsolid nodules in computed tomography images is presented and evaluated on a large data set from a multi-center lung cancer screening trial. The paper describes the different components of the CAD system and presents experiments to optimize the performance of the proposed CAD system. A rich set of 128 features is defined for subsolid nodule candidates. In addition to previously used intensity, shape and texture features, a novel set of context features is introduced. Experiments show that these features significantly improve the classification performance. Optimization and training of the CAD system is performed on a large training set from one site of a lung cancer screening trial. Performance analysis on an independent test from another site of the trial shows that the proposed system reaches a sensitivity of 80% at an average of only 1.0 false positive detections per scan. A retrospective analysis of the output of the CAD system by an experienced thoracic radiologist shows that the CAD system is able to find subsolid nodules which were not contained in the screening database.

Observer Variability for Classification of Pulmonary Nodules on Low-Dose CT Images and Its Effect on Nodule Management

PURPOSE To examine the factors that affect inter- and intraobserver agreement for pulmonary nodule type classification on low-radiation-dose computed tomographic (CT) images, and their potential effect on patient management. MATERIALS AND METHODS Nodules (n = 160) were randomly selected from the Dutch-Belgian Lung Cancer Screening Trial cohort, with equal numbers of nodule types and similar sizes. Nodules were scored by eight radiologists by using morphologic categories proposed by the Fleischner Society guidelines for management of pulmonary nodules as solid, part solid with a solid component smaller than 5 mm, part solid with a solid component 5 mm or larger, or pure ground glass. Inter- and intraobserver agreement was analyzed by using Cohen κ statistics. Multivariate analysis of variance was performed to assess the effect of nodule characteristics and image quality on observer disagreement. Effect on nodule management was estimated by differentiating CT follow-up for ground-glass nodules, solid nodules 8 mm or smaller, and part-solid nodules smaller than 5 mm from immediate diagnostic work-up for solid nodules larger than 8 mm and part-solid nodules 5 mm or greater. RESULTS Pair-wise inter- and intraobserver agreement was moderate (mean κ, 0.51 [95% confidence interval, 0.30, 0.68] and 0.57 [95% confidence interval, 0.47, 0.71]). Categorization as part-solid nodules and location in the upper lobe significantly reduced observer agreement (P = .012 and P < .001, respectively). By considering all possible reading pairs (28 possible combinations of observer pairs × 160 nodules = 4480 possible agreements or disagreements), a discordant nodule classification was found in 36.4% (1630 of 4480), related to presence or size of a solid component in 88.7% (1446 of 1630). Two-thirds of these discrepant readings (1061 of 1630) would have potentially resulted in different nodule management. CONCLUSION There is moderate inter- and intraobserver agreement for nodule classification by using current recommendations for low-radiation-dose CT examinations of the chest. Discrepancies in nodule categorization were mainly caused by disagreement on the size and presence of a solid component, which may lead to different management in the majority of cases with such discrepancies. (©) RSNA, 2015.

Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge

HighlightsA novel objective evaluation framework for nodule detection algorithms using the largest publicly available LIDC‐IDRI data set.The impact of combining individual systems on the detection performance was investigated.The combination of classical candidate detectors and a combination of deep learning architectures generates excellent results, better than any individual system.Our observer study has shown that CAD detects nodules that were missed by expert readers.We released this set of additional nodules for further development of CAD systems. Graphical abstract Figure. No caption available. ABSTRACT Automatic detection of pulmonary nodules in thoracic computed tomography (CT) scans has been an active area of research for the last two decades. However, there have only been few studies that provide a comparative performance evaluation of different systems on a common database. We have therefore set up the LUNA16 challenge, an objective evaluation framework for automatic nodule detection algorithms using the largest publicly available reference database of chest CT scans, the LIDC‐IDRI data set. In LUNA16, participants develop their algorithm and upload their predictions on 888 CT scans in one of the two tracks: 1) the complete nodule detection track where a complete CAD system should be developed, or 2) the false positive reduction track where a provided set of nodule candidates should be classified. This paper describes the setup of LUNA16 and presents the results of the challenge so far. Moreover, the impact of combining individual systems on the detection performance was also investigated. It was observed that the leading solutions employed convolutional networks and used the provided set of nodule candidates. The combination of these solutions achieved an excellent sensitivity of over 95% at fewer than 1.0 false positives per scan. This highlights the potential of combining algorithms to improve the detection performance. Our observer study with four expert readers has shown that the best system detects nodules that were missed by expert readers who originally annotated the LIDC‐IDRI data. We released this set of additional nodules for further development of CAD systems.

Towards a close computed tomography monitoring approach for screen detected subsolid pulmonary nodules

Pulmonary subsolid nodules (SSNs) have a high likelihood of malignancy, but are often indolent. A conservative treatment approach may therefore be suitable. The aim of the current study was to evaluate whether close follow-up of SSNs with computed tomography may be a safe approach. The study population consisted of participants of the Dutch-Belgian lung cancer screening trial (Nederlands Leuvens Longkanker Screenings Onderzoek; NELSON). All SSNs detected during the trial were included in this analysis. Retrospectively, all persistent SSNs and SSNs that were resected after first detection were segmented using dedicated software, and maximum diameter, volume and mass were measured. Mass doubling time (MDT) was calculated. In total 7135 volunteers were included in the current analysis. 264 (3.3%) SSNs in 234 participants were detected during the trial. 147 (63%) of these SSNs in 126 participants disappeared at follow-up, leaving 117 persistent or directly resected SSNs in 108 (1.5%) participants available for analysis. The median follow-up time was 95 months (range 20–110 months). 33 (28%) SSNs were resected and 28 of those were (pre-) invasive. None of the non-resected SSNs progressed into a clinically relevant malignancy. Persistent SSNs rarely developed into clinically manifest malignancies unexpectedly. Close follow-up with computed tomography may be a safe option to monitor changes. Persistent subsolid pulmonary nodules may be safely monitored with follow-up computed tomography http://ow.ly/CqWN1

Automatic detection of large pulmonary solid nodules in thoracic CT images

PURPOSE Current computer-aided detection (CAD) systems for pulmonary nodules in computed tomography (CT) scans have a good performance for relatively small nodules, but often fail to detect the much rarer larger nodules, which are more likely to be cancerous. We present a novel CAD system specifically designed to detect solid nodules larger than 10 mm. METHODS The proposed detection pipeline is initiated by a three-dimensional lung segmentation algorithm optimized to include large nodules attached to the pleural wall via morphological processing. An additional preprocessing is used to mask out structures outside the pleural space to ensure that pleural and parenchymal nodules have a similar appearance. Next, nodule candidates are obtained via a multistage process of thresholding and morphological operations, to detect both larger and smaller candidates. After segmenting each candidate, a set of 24 features based on intensity, shape, blobness, and spatial context are computed. A radial basis support vector machine (SVM) classifier was used to classify nodule candidates, and performance was evaluated using ten-fold cross-validation on the full publicly available lung image database consortium database. RESULTS The proposed CAD system reaches a sensitivity of 98.3% (234/238) and 94.1% (224/238) large nodules at an average of 4.0 and 1.0 false positives/scan, respectively. CONCLUSIONS The authors conclude that the proposed dedicated CAD system for large pulmonary nodules can identify the vast majority of highly suspicious lesions in thoracic CT scans with a small number of false positives.

Normal range of emphysema and air trapping on CT in young men.

OBJECTIVE The purpose of our study was to assess the normal range of CT measures of emphysema and air trapping in young men with normal lung function. MATERIALS AND METHODS A cohort of 70 young men with high-normal spirometry and body plethysmography underwent paired inspiratory and expiratory CT. Visual and quantitative scores of emphysema and air trapping were obtained. On CT, emphysema was defined as the 15th percentile of the attenuation curve (Perc(15)), and as the percentage of inspiratory voxels below -950 (IN(-950)) and below -960 (IN(-960)) HU. On CT, air trapping was defined as the expiratory-to-inspiratory ratio of mean lung density (EI-ratio(MLD)), and the percentage of voxels below -856 HU in expiration (EXP(-856)). Means, medians, and upper limits of normal (ULN) are presented for the total population and for smokers and nonsmokers separately. RESULTS The mean age (± SD) of the subjects was 36.1 ± 9.3 years. Smoking history was limited (range, 0-11 pack-years). Spirometry was high normal, ranging from 113% to 160% of predicted for vital capacity (VC), and from 104% to 140% of predicted for forced expiratory volume in 1 second (FEV(1)). The ULN was 2.73% for IN(-950), 0.87% for IN(-960), -936 HU for Perc(15), 89.0% for EI-ratio(MLD), and 17.2% for EXP(-856).Visual CT scores showed minimal emphysema in eight (11%), > 5 lobules of air trapping in five (7%), and segmental air trapping in three (4%) subjects. CT measures were similar for never- and ever-smokers. CONCLUSION We report the normal range of CT values for young male subjects with normal lung function, which is important to define pulmonary disease.

Predictive Accuracy of the PanCan Lung Cancer Risk Prediction Model -External Validation based on CT from the Danish Lung Cancer Screening Trial

ObjectivesLung cancer risk models should be externally validated to test generalizability and clinical usefulness. The Danish Lung Cancer Screening Trial (DLCST) is a population-based prospective cohort study, used to assess the discriminative performances of the PanCan models.MethodsFrom the DLCST database, 1,152 nodules from 718 participants were included. Parsimonious and full PanCan risk prediction models were applied to DLCST data, and also coefficients of the model were recalculated using DLCST data. Receiver operating characteristics (ROC) curves and area under the curve (AUC) were used to evaluate risk discrimination.ResultsAUCs of 0.826–0.870 were found for DLCST data based on PanCan risk prediction models. In the DLCST, age and family history were significant predictors (p = 0.001 and p = 0.013). Female sex was not confirmed to be associated with higher risk of lung cancer; in fact opposing effects of sex were observed in the two cohorts. Thus, female sex appeared to lower the risk (p = 0.047 and p = 0.040) in the DLCST.ConclusionsHigh risk discrimination was validated in the DLCST cohort, mainly determined by nodule size. Age and family history of lung cancer were significant predictors and could be included in the parsimonious model. Sex appears to be a less useful predictor.Key points• High accuracy in logistic modelling for lung cancer risk stratification of nodules.• Lung cancer risk prediction is primarily based on size of pulmonary nodules.• Nodule spiculation, age and family history of lung cancer are significant predictors.• Sex does not appear to be a useful risk predictor.

Solid, part-solid, or non-solid?: classification of pulmonary nodules in low-dose chest computed tomography by a computer-aided diagnosis system.

ObjectivesThe purpose of this study was to develop and validate a computer-aided diagnosis (CAD) tool for automatic classification of pulmonary nodules seen on low-dose computed tomography into solid, part-solid, and non-solid. Materials and MethodsStudy lesions were randomly selected from 2 sites participating in the Dutch-Belgian NELSON lung cancer screening trial. On the basis of the annotations made by the screening radiologists, 50 part-solid and 50 non-solid pulmonary nodules with a diameter between 5 and 30 mm were randomly selected from the 2 sites. For each unique nodule, 1 low-dose chest computed tomographic scan was randomly selected, in which the nodule was visible. In addition, 50 solid nodules in the same size range were randomly selected. A completely automatic 3-dimensional segmentation-based classification system was developed, which analyzes the pulmonary nodule, extracting intensity-, texture-, and segmentation-based features to perform a statistical classification. In addition to the nodule classification by the screening radiologists, an independent rating of all nodules by 3 experienced thoracic radiologists was performed. Performance of CAD was evaluated by comparing the agreement between CAD and human experts and among human experts using the Cohen &kgr; statistics. ResultsPairwise agreement for the differentiation between solid, part-solid, and non-solid nodules between CAD and each of the human experts had a &kgr; range between 0.54 and 0.72. The interobserver agreement among the human experts was in the same range (&kgr; range, 0.56–0.81). ConclusionsA novel automated classification tool for pulmonary nodules achieved good agreement with the human experts, yielding &kgr; values in the same range as the interobserver agreement. Computer-aided diagnosis may aid radiologists in selecting the appropriate workup for pulmonary nodules.