Comparison Between Radiological Semantic Features and Lung-RADS in Predicting Malignancy of Screen-Detected Lung Nodules in the National Lung Screening Trial

Personalised follow-up and management schema for patients with screen-detected pulmonary nodules: A dynamic modelling study

BACKGROUND

Selecting the time target for follow-up testing in lung cancer screening is challenging. We aim to devise dynamic, personalized lung cancer screening schema for patients with pulmonary nodules detected through low-dose computed tomography.

METHODS

We developed and validated dynamic models using data of pulmonary nodule patients (aged 55-74 years) from the National Lung Screening Trial. We predicted patient-specific risk profiles at baseline (R0) and updated the risk evaluation results in repeated screening rounds (R1 and R2). We used risk cutoffs to optimize time-dependent sensitivity at an early decision point (3 months) and time-dependent specificity at a late decision point (1 year).

RESULTS

In validation, area under receiver operating characteristic curve for predicting 12-month lung cancer onset was 0.867 (95 % confidence interval: 0.827-0.894) and 0.807 (0.765-0.948) at R0 and R1-R2, respectively. The personalized schema, compared with National Comprehensive Cancer Network (NCCN) guideline and Lung-RADS, yielded lower rates of delayed diagnosis (1.7% vs. 1.7% vs. 6.9 %) and over-testing (4.9% vs. 5.6% vs. 5.6 %) at R0, and lower rates of delayed diagnosis (0.0% vs. 18.2% vs. 18.2 %) and over-testing (2.6% vs. 8.3% vs. 7.3 %) at R2. Earlier test recommendation among cancer patients was more frequent using the personalized schema (vs. NCCN: 29.8% vs. 20.9 %, p = 0.0065; vs. Lung-RADS: 33.2% vs. 22.8 %, p = 0.0025), especially for women, patients aged ≥65 years, and part-solid or non-solid nodules.

CONCLUSIONS

The personalized schema is easy-to-implement and more accurate compared with rule-based protocols. The results highlight value of personalized approaches in realizing efficient nodule management.

Perinodular Parenchymal Features Improve Indeterminate Lung Nodule Classification

BACKGROUND

Radiomics, defined as quantitative features extracted from images, provide a non-invasive means of assessing malignant versus benign pulmonary nodules. In this study, we evaluate the consistency with which perinodular radiomics extracted from low-dose computed tomography images serve to identify malignant pulmonary nodules.

MATERIALS AND METHODS

Using the National Lung Screening Trial (NLST), we selected individuals with pulmonary nodules between 4mm to 20mm in diameter. Nodules were segmented to generate four distinct datasets; 1) a Tumor dataset containing tumor-specific features, 2) a 10 mm Band dataset containing parenchymal features between the segmented nodule boundary and 10mm out from the boundary, 3) a 15mm Band dataset, and 4) a Tumor Size dataset containing the maximum nodule diameter. Models to predict malignancy were constructed using support-vector machine (SVM), random forest (RF), and least absolute shrinkage and selection operator (LASSO) approaches. Ten-fold cross validation with 10 repetitions per fold was used to evaluate the performance of each approach applied to each dataset.

RESULTS

With respect to the RF, the Tumor, 10mm Band, and 15mm Band datasets achieved areas under the receiver-operator curve (AUC) of 84.44%, 84.09%, and 81.57%, respectively. Significant differences in performance were observed between the Tumor and 15mm Band datasets (adj. p-value <0.001). However, when combining tumor-specific features with perinodular features, the 10mm Band + Tumor and 15mm Band + Tumor datasets (AUC 87.87% and 86.75%, respectively) performed significantly better than the Tumor Size dataset (66.76%) or the Tumor dataset. Similarly, the AUCs from the SVM and LASSO were 84.71% and 88.91%, respectively, for the 10mm Band + Tumor.

CONCLUSIONS

The combined 10mm Band + Tumor dataset improved the differentiation between benign and malignant lung nodules compared to the Tumor datasets across all methodologies. This demonstrates that parenchymal features capture novel diagnostic information beyond that present in the nodule itself. (data agreement: NLST-163).

How AI Can Help in the Diagnostic Dilemma of Pulmonary Nodules

Simple Summary

Pulmonary nodules are considered a sign of bronchogenic carcinoma, detecting them early will reduce their progression and can save lives. Lung cancer is the second most common type of cancer in both men and women. This manuscript discusses the current applications of artificial intelligence (AI) in lung segmentation as well as pulmonary nodule segmentation and classification using computed tomography (CT) scans, published in the last two decades, in addition to the limitations and future prospects in the field of AI.

Abstract

Pulmonary nodules are the precursors of bronchogenic carcinoma, its early detection facilitates early treatment which save a lot of lives. Unfortunately, pulmonary nodule detection and classification are liable to subjective variations with high rate of missing small cancerous lesions which opens the way for implementation of artificial intelligence (AI) and computer aided diagnosis (CAD) systems. The field of deep learning and neural networks is expanding every day with new models designed to overcome diagnostic problems and provide more applicable and simply used models. We aim in this review to briefly discuss the current applications of AI in lung segmentation, pulmonary nodule detection and classification.

Lung Nodule Malignancy Prediction in Sequential CT Scans: Summary of ISBI 2018 Challenge

Lung cancer is by far the leading cause of cancer death in the US. Recent studies have demonstrated the effectiveness of screening using low dose CT (LDCT) in reducing lung cancer related mortality. While lung nodules are detected with a high rate of sensitivity, this exam has a low specificity rate and it is still difficult to separate benign and malignant lesions. The ISBI 2018 Lung Nodule Malignancy Prediction Challenge, developed by a team from the Quantitative Imaging Network of the National Cancer Institute, was focused on the prediction of lung nodule malignancy from two sequential LDCT screening exams using automated (non-manual) algorithms. We curated a cohort of 100 subjects who participated in the National Lung Screening Trial and had established pathological diagnoses. Data from 30 subjects were randomly selected for training and the remaining was used for testing. Participants were evaluated based on the area under the receiver operating characteristic curve (AUC) of nodule-wise malignancy scores generated by their algorithms on the test set. The challenge had 17 participants, with 11 teams submitting reports with method description, mandated by the challenge rules. Participants used quantitative methods, resulting in a reporting test AUC ranging from 0.698 to 0.913. The top five contestants used deep learning approaches, reporting an AUC between 0.87 - 0.91. The team's predictor did not achieve significant differences from each other nor from a volume change estimate (p =.05 with Bonferroni-Holm's correction).

Value of a deep learning-based algorithm for detecting Lung-RADS category 4 nodules on chest radiographs in a health checkup population: estimation of the sample size for a randomized controlled trial

OBJECTIVE

To explore the value of a deep learning-based algorithm in detecting Lung CT Screening Reporting and Data System category 4 nodules on chest radiographs from an asymptomatic health checkup population.

METHODS

Data from an annual retrospective cohort of individuals who underwent chest radiographs for health checkup purposes and chest CT scanning within 3 months were collected. Among 3073 individuals, 118 with category 4 nodules on CT were selected. A reader performance test was performed using those 118 radiographs and randomly selected 51 individuals without any nodules. Four radiologists independently evaluated the radiographs without and with the results of the algorithm; and sensitivities/specificities were compared. The sample size needed to confirm the difference in detection rates was calculated, i.e., the number of true-positive radiographs divided by the total number of radiographs.

RESULTS

The sensitivity of the radiologists substantially increased aided by the algorithm (38.8% [183/472] to 45.1% [213/472]; p < .001) without significant change in specificity (94.1% [192/204] vs. 92.2% [188/204]; p = .22). Pooled radiologists detected more nodules with the algorithm (32.0% [156/488] vs. 38.9% [190/488]; p < .001), without alteration of false-positive rates (0.09 [62/676], both). Pooled detection rates for the annual cohort were 1.49% (183/12,292) and 1.73% (213/12,292) without and with the algorithm, respectively. A sample size of 41,776 in each arm would be required to demonstrate significant detection rate difference with < 5% type I error and > 80% power.

CONCLUSION

Although readers substantially increased sensitivity in detecting nodules on chest radiographs from a health checkup population aided by the algorithm, detection rate difference was only 0.24%, requiring a sample size >80,000 for a randomized controlled trial.

KEY POINTS

• Aided by a deep learning algorithm, pooled radiologists improved their sensitivity in detecting Lung-RADS category 4 nodules on chest radiographs from a health checkup population (38.8% [183/472] to 45.1% [213/472]; p < .001), without increasing false-positive rate. • The prevalence of the Lung-RADS category 4 nodules was 3.8% (118/3073) on the population, resulting in only 0.24% increase of the detection rate for the radiologists with assistance of the algorithm. • To confirm the significant detection rate increase by a randomized controlled trial, a sample size of 84,000 would be required.

A Novel Nodule Edge Sharpness Radiomic Biomarker Improves Performance of Lung-RADS for Distinguishing Adenocarcinomas from Granulomas on Non-Contrast CT Scans

Simple Summary

The great majority of pulmonary nodules on screening CT scans are benign (95%). Due to inaccurate diagnoses of granulomas from adenocarcinomas on CT scans, many patients with benign nodules are subjected to unnecessary surgical procedures. The aim of this retrospective study is to evaluate the discriminability of a new radiomic feature, nodule edge/interface sharpness (NIS), for distinguishing lung adenocarcinomas from benign granulomas on non-contrast CT scans. Moreover, we aim to evaluate whether NIS can improve the performance of Lung-RADS, by reclassifying benign nodules that were initially assessed as suspicious. In a cohort of 352 patients with diagnostic non-contrast CT scans, NIS radiomics was able to classify nodules with an area under the receiver operating characteristic curve (ROC AUC) of 0.77, and when combined with intra-tumoral textural and shape features, classification performance increased to AUC of 0.84. Additionally, the NIS classifier correctly reclassified 46% of those lesions that were actually benign but deemed suspicious by Lung-RADS. Combining NIS with Lung-RADS has the potential to alter patient management by significantly decreasing unnecessary biopsies/follow up imaging.

Abstract

The aim of this study is to evaluate whether NIS radiomics can distinguish lung adenocarcinomas from granulomas on non-contrast CT scans, and also to improve the performance of Lung-RADS by reclassifying benign nodules that were initially assessed as suspicious. The screening or standard diagnostic non-contrast CT scans of 362 patients was divided into training (S_t, N = 145), validation (S_v, N = 145), and independent validation (S_iv, N = 62) sets from different institutions. Nodules were identified and manually segmented on CT images by a radiologist. A series of 264 features relating to the edge sharpness transition from the inside to the outside of the nodule were extracted. The top 10 features were used to train a linear discriminant analysis (LDA) machine learning classifier on St. In conjunction with the LDA classifier, NIS radiomics classified nodules with an AUC of 0.82 ± 0.04, 0.77, and 0.71 respectively on S_t, S_v, and S_iv. We evaluated the ability of the NIS classifier to determine the proportion of the patients in S_v that were identified initially as suspicious by Lung-RADS but were reclassified as benign by applying the NIS scores. The NIS classifier was able to correctly reclassify 46% of those lesions that were actually benign but deemed suspicious by Lung-RADS alone on S_v.

Optimizing the timing of diagnostic testing after positive findings in lung cancer screening: a proof of concept radiomics study

BACKGROUND

The timeliness of diagnostic testing after positive screening remains suboptimal because of limited evidence and methodology, leading to delayed diagnosis of lung cancer and over-examination. We propose a radiomics approach to assist with planning of the diagnostic testing interval in lung cancer screening.

METHODS

From an institute-based lung cancer screening cohort, we retrospectively selected 92 patients with pulmonary nodules with diameters ≥ 3 mm at baseline (61 confirmed as lung cancer by histopathology; 31 confirmed cancer-free). Four groups of region-of-interest-based radiomic features (n = 310) were extracted for quantitative characterization of the nodules, and eight features were proven to be predictive of cancer diagnosis, noise-robust, phenotype-related, and non-redundant. A radiomics biomarker was then built with the random survival forest method. The patients with nodules were divided into low-, middle- and high-risk subgroups by two biomarker cutoffs that optimized time-dependent sensitivity and specificity for decisions about diagnostic workup within 3 months and about repeat screening after 12 months, respectively. A radiomics-based follow-up schedule was then proposed. Its performance was visually assessed with a time-to-diagnosis plot and benchmarked against lung RADS and four other guideline protocols.

RESULTS

The radiomics biomarker had a high time-dependent area under the curve value (95% CI) for predicting lung cancer diagnosis within 12 months; training: 0.928 (0.844, 0.972), test: 0.888 (0.766, 0.975); the performance was robust in extensive cross-validations. The time-to-diagnosis distributions differed significantly between the three patient subgroups, p < 0.001: 96.2% of high-risk patients (n = 26) were diagnosed within 10 months after baseline screen, whereas 95.8% of low-risk patients (n = 24) remained cancer-free by the end of the study. Compared with the five existing protocols, the proposed follow-up schedule performed best at securing timely lung cancer diagnosis (delayed diagnosis rate: < 5%) and at sparing patients with cancer-free nodules from unnecessary repeat screenings and examinations (false recommendation rate: 0%).

CONCLUSIONS

Timely management of screening-detected pulmonary nodules can be substantially improved with a radiomics approach. This proof-of-concept study's results should be further validated in large programs.

Radiomics in immuno-oncology

With the ongoing advances in imaging techniques, increasing volumes of anatomical and functional data are being generated as part of the routine clinical workflow. This surge of available imaging data coincides with increasing research in quantitative imaging, particularly in the domain of imaging features. An important and novel approach is radiomics, where high-dimensional image properties are extracted from routine medical images. The fundamental principle of radiomics is the hypothesis that biomedical images contain predictive information, not discernible to the human eye, that can be mined through quantitative image analysis. In this review, a general outline of radiomics and artificial intelligence (AI) will be provided, along with prominent use cases in immunotherapy (e.g. response and adverse event prediction) and targeted therapy (i.e. radiogenomics). While the increased use and development of radiomics and AI in immuno-oncology is highly promising, the technology is still in its early stages, and different challenges still need to be overcome. Nevertheless, novel AI algorithms are being constructed with an ever-increasing scope of applications.

Multi-Window CT Based Radiological Traits for Improving Early Detection in Lung Cancer Screening

Rationale and Objectives

Evaluate ability of radiological semantic traits assessed on multi-window computed tomography (CT) to predict lung cancer risk.

Materials and Methods

A total of 199 participants were investigated, including 60 incident lung cancers and 139 benign positive controls. Twenty lung window features and 2 mediastinal window features were extracted and scored on a point scale in three screening rounds. Multivariate logistic regression analysis was used to explore the association of these radiological traits with the risk of developing lung cancer. The areas under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and positive predictive value (PPV) were computed to evaluate the best predictive model.

Results

Combining mediastinal window-specific features with the lung window features-based model significantly improves performance compared to individual window features. Model performance is consistent both at baseline and the first follow-up scan, with an AUROC increased from 0.822 to 0.871 (p = 0.009) and from 0.877 to 0.917 (p = 0.008), respectively, for single to multi-window feature models. We also find that the multi-window CT based model showed better specificity and PPV, with PPV at the second follow-up scan improved to 0.953.

Conclusion

We find combining window semantic features improves model performance in identifying cancerous nodules. We also find that lung window features are more informative compared to mediastinal features in predicting malignancy.

Integration of PET/CT Radiomics and Semantic Features for Differentiation between Active Pulmonary Tuberculosis and Lung Cancer

PURPOSE

We aim to accurately differentiate between active pulmonary tuberculosis (TB) and lung cancer (LC) based on radiomics and semantic features as extracted from pre-treatment positron emission tomography/X-ray computed tomography (PET/CT) images.

PROCEDURES

A total of 174 patients (77/97 pulmonary TB/LC as confirmed by pathology) were retrospectively selected, with 122 in the training cohort and 52 in the validation cohort. Four hundred eighty-seven radiomics features were initially extracted to quantify phenotypic characteristics of the lesion region in both PET and CT images. Eleven semantic features were additionally defined by two experienced nuclear medicine physicians. Feature selection was performed in 5 steps to enable derivation of robust and effective signatures. Multivariable logistic regression analysis was subsequently used to develop a radiomics nomogram. The calibration, discrimination, and clinical usefulness of the nomogram were evaluated in both the training and independent validation cohorts.

RESULTS

The individualized radiomics nomogram, which combined PET/CT radiomics signature with semantic features, demonstrated good calibration and significantly improved the diagnostic performance with respect to the semantic model alone or PET/CT signature alone in training cohort (AUC 0.97 vs. 0.94 or 0.91, p = 0.0392 or 0.0056), whereas did not significantly improve the performance in validation cohort (AUC 0.93 vs. 0.89 or 0.91, p = 0.3098 or 0.3323).

CONCLUSION

The radiomics nomogram showed potential for individualized differential diagnosis between solid active pulmonary TB and solid LC, although the improvement of performance was not significant relative to semantic model.

Peritumoral and intratumoral radiomic features predict survival outcomes among patients diagnosed in lung cancer screening

The National Lung Screening Trial (NLST) demonstrated that screening with low-dose computed tomography (LDCT) is associated with a 20% reduction in lung cancer mortality. One potential limitation of LDCT screening is overdiagnosis of slow growing and indolent cancers. In this study, peritumoral and intratumoral radiomics was used to identify a vulnerable subset of lung patients associated with poor survival outcomes. Incident lung cancer patients from the NLST were split into training and test cohorts and an external cohort of non-screen detected adenocarcinomas was used for further validation. After removing redundant and non-reproducible radiomics features, backward elimination analyses identified a single model which was subjected to Classification and Regression Tree to stratify patients into three risk-groups based on two radiomics features (NGTDM Busyness and Statistical Root Mean Square [RMS]). The final model was validated in the test cohort and the cohort of non-screen detected adenocarcinomas. Using a radio-genomics dataset, Statistical RMS was significantly associated with FOXF2 gene by both correlation and two-group analyses. Our rigorous approach generated a novel radiomics model that identified a vulnerable high-risk group of early stage patients associated with poor outcomes. These patients may require aggressive follow-up and/or adjuvant therapy to mitigate their poor outcomes.

Preoperative diagnosis of malignant pulmonary nodules in lung cancer screening with a radiomics nomogram

Background

Lung cancer is the most commonly diagnosed cancer worldwide. Its survival rate can be significantly improved by early screening. Biomarkers based on radiomics features have been found to provide important physiological information on tumors and considered as having the potential to be used in the early screening of lung cancer. In this study, we aim to establish a radiomics model and develop a tool to improve the discrimination between benign and malignant pulmonary nodules.

Methods

A retrospective study was conducted on 875 patients with benign or malignant pulmonary nodules who underwent computed tomography (CT) examinations between June 2013 and June 2018. We assigned 612 patients to a training cohort and 263 patients to a validation cohort. Radiomics features were extracted from the CT images of each patient. Least absolute shrinkage and selection operator (LASSO) was used for radiomics feature selection and radiomics score calculation. Multivariate logistic regression analysis was used to develop a classification model and radiomics nomogram. Radiomics score and clinical variables were used to distinguish benign and malignant pulmonary nodules in logistic model. The performance of the radiomics nomogram was evaluated by the area under the curve (AUC), calibration curve and Hosmer‐Lemeshow test in both the training and validation cohorts.

Results

A radiomics score was built and consisted of 20 features selected by LASSO from 1288 radiomics features in the training cohort. The multivariate logistic model and radiomics nomogram were constructed using the radiomics score and patients’ age. Good discrimination of benign and malignant pulmonary nodules was obtained from the training cohort (AUC, 0.836; 95% confidence interval [CI]: 0.793‐0.879) and validation cohort (AUC, 0.809; 95% CI: 0.745‐0.872). The Hosmer‐Lemeshow test also showed good performance for the logistic regression model in the training cohort (P = 0.765) and validation cohort (P = 0.064). Good alignment with the calibration curve indicated the good performance of the nomogram.

Conclusions

The established radiomics nomogram is a noninvasive preoperative prediction tool for malignant pulmonary nodule diagnosis. Validation revealed that this nomogram exhibited excellent discrimination and calibration capacities, suggesting its clinical utility in the early screening of lung cancer.

Explaining Deep Features Using Radiologist-Defined Semantic Features and Traditional Quantitative Features

Quantitative features are generated from a tumor phenotype by various data characterization, feature-extraction approaches and have been used successfully as a biomarker. These features give us information about a nodule, for example, nodule size, pixel intensity, histogram-based information, and texture information from wavelets or a convolution kernel. Semantic features, on the other hand, can be generated by an experienced radiologist and consist of the common characteristics of a tumor, for example, location of a tumor, fissure, or pleural wall attachment, presence of fibrosis or emphysema, concave cut on nodule surface. These features have been derived for lung nodules by our group. Semantic features have also shown promise in predicting malignancy. Deep features from images are generally extracted from the last layers before the classification layer of a convolutional neural network (CNN). By training with the use of different types of images, the CNN learns to recognize various patterns and textures. But when we extract deep features, there is no specific naming approach for them, other than denoting them by the feature column number (position of a neuron in a hidden layer). In this study, we tried to relate and explain deep features with respect to traditional quantitative features and semantic features. We discovered that 26 deep features from the Vgg-S neural network and 12 deep features from our trained CNN could be explained by semantic or traditional quantitative features. From this, we concluded that those deep features can have a recognizable definition via semantic or quantitative features.

Research progress of computer aided diagnosis system for pulmonary nodules in CT images

BACKGROUND AND OBJECTIVE

Since CAD (Computer Aided Diagnosis) system can make it easier and more efficient to interpret CT (Computer Tomography) images, it has gained much attention and developed rapidly in recent years. This article reviews recent CAD techniques for pulmonary nodule detection and diagnosis in CT Images.

METHODS

CAD systems can be classified into computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems. This review reports recent researches of both systems, including the database, technique, innovation and experimental results of each work. Multi-task CAD systems, which can handle segmentation, false positive reduction, malignancy prediction and other tasks at the same time. The commercial CAD systems are also briefly introduced.

RESULTS

We have found that deep learning based CAD is the mainstream of current research. The reported sensitivity of deep learning based CADe systems ranged between 80.06% and 94.1% with an average 4.3 false-positive (FP) per scan when using LIDC-IDRI dataset, and between 94.4% and 97.9% with an average 4 FP/scan when using LUNA16 dataset, respectively. The overall accuracy of deep learning based CADx systems ranged between 86.84% and 92.3% with an average AUC of 0.956 reported when using LIDC-IDRI dataset.

CONCLUSIONS

We summarized the current tendency and limitations as well as future challenges in this field. The development of CAD needs to meet the rigid clinical requirements, such as high accuracy, strong robustness, high efficiency, fine-grained analysis and classification, and to provide practical clinical functions. This review provides helpful information for both engineering researchers and radiologists to learn the latest development of CAD systems.

A CAD system for pulmonary nodule prediction based on deep three-dimensional convolutional neural networks and ensemble learning

Background

Detection of pulmonary nodules is an important aspect of an automatic detection system. Incomputer-aided diagnosis (CAD) systems, the ability to detect pulmonary nodules is highly important, which plays an important role in the diagnosis and early treatment of lung cancer. Currently, the detection of pulmonary nodules depends mainly on doctor experience, which varies. This paper aims to address the challenge of pulmonary nodule detection more effectively.

Methods

A method for detecting pulmonary nodules based on an improved neural network is presented in this paper. Nodules are clusters of tissue with a diameter of 3 mm to 30 mm in the pulmonary parenchyma. Because pulmonary nodules are similar to other lung structures and have a low density, false positive nodules often occur. Thus, our team proposed an improved convolutional neural network (CNN) framework to detect nodules. First, a nonsharpening mask is used to enhance the nodules in computed tomography (CT) images; then, CT images of 512×512 pixels are segmented into smaller images of 96×96 pixels. Second, in the 96×96 pixel images which contain or exclude pulmonary nodules, the plaques corresponding to positive and negative samples are segmented. Third, CT images segmented into 96×96 pixels are down-sampled to 64×64 and 32×32 size respectively. Fourth, an improved fusion neural network structure is constructed that consists of three three-dimensional convolutional neural networks, designated as CNN-1, CNN-2, and CNN-3, to detect false positive pulmonary nodules. The networks’ input sizes are 32×32×32, 64×64×64, and 96×96×96 and include 5, 7, and 9 layers, respectively. Finally, we use the AdaBoost classifier to fuse the results of CNN-1, CNN-2, and CNN-3. We call this new neural network framework the Amalgamated-Convolutional Neural Network (A-CNN) and use it to detect pulmonary nodules.

Findings

Our team trained A-CNN using the LUNA16 and Ali Tianchi datasets and evaluated its performance using the LUNA16 dataset. We discarded nodules less than 5mm in diameter. When the average number of false positives per scan was 0.125 and 0.25, the sensitivity of A-CNN reached as high as 81.7% and 85.1%, respectively.

Perinodular and Intranodular Radiomic Features on Lung CT Images Distinguish Adenocarcinomas from Granulomas

Purpose To evaluate ability of radiomic (computer-extracted imaging) features to distinguish non-small cell lung cancer adenocarcinomas from granulomas at noncontrast CT. Materials and Methods For this retrospective study, screening or standard diagnostic noncontrast CT images were collected for 290 patients (mean age, 68 years; range, 18-92 years; 125 men [mean age, 67 years; range, 18-90 years] and 165 women [mean age, 68 years; range, 33-92 years]) from two institutions between 2007 and 2013. Histopathologic analysis was available for one nodule per patient. Corresponding nodule of interest was identified on axial CT images by a radiologist with manual annotation. Nodule shape, wavelet (Gabor), and texture-based (Haralick and Laws energy) features were extracted from intra- and perinodular regions. Features were pruned to train machine learning classifiers with 145 patients. In a test set of 145 patients, classifier results were compared against a convolutional neural network (CNN) and diagnostic readings of two radiologists. Results Support vector machine classifier with intranodular radiomic features achieved an area under the receiver operating characteristic curve (AUC) of 0.75 on the test set. Combining radiomics of intranodular with perinodular regions improved the AUC to 0.80. On the same test set, CNN resulted in an AUC of 0.76. Radiologist readers achieved AUCs of 0.61 and 0.60, respectively. Conclusion Radiomic features from intranodular and perinodular regions of nodules can distinguish non-small cell lung cancer adenocarcinomas from benign granulomas at noncontrast CT. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Nishino in this issue.

Representation of Deep Features using Radiologist defined Semantic Features

Semantic features are common radiological traits used to characterize a lesion by a trained radiologist. These features have been recently formulated, quantified on a point scale in the context of lung nodules by our group. Certain radiological semantic traits have been shown to extremely predictive of malignancy [26]. Semantic traits observed by a radiologist at examination describe the nodules and the morphology of the lung nodule shape, size, border, attachment to vessel or pleural wall, location and texture etc. Deep features are numeric descriptors often obtained from a convolutional neural network (CNN) which are widely used for classification and recognition. Deep features may contain information about texture and shape, primarily. Lately, with the advancement of deep learning, convolutional neural networks (CNN) are also being used to analyze lung nodules. In this study, we relate deep features to semantic features by looking for similarity in ability to classify. Deep features were obtained using a transfer learning approach from both an ImageNet pre-trained CNN and our trained CNN architecture. We found that some of the semantic features can be represented by one or more deep features. In this process, we can infer that some deep feature(s) have similar discriminatory ability as semantic features.

Relationship between Circulating Inflammation Proteins and Lung Cancer Diagnosis in the National Lung Screening Trial

BACKGROUND

Previously, we observed a strong relationship between circulating serum inflammation proteins in relation to lung cancer diagnosis and risk, both in case-control and prospective cohorts. Low-dose computed tomography (LDCT) screening has a high prevalence of false-positive nodules, thus companion noninvasive biomarkers that can distinguish between benign and malignant nodules could have clinical utility and positive impact on patient outcomes.

METHODS

We conducted a nested case-control study within the National Lung Screening Trial. Concentrations of 30 inflammation proteins were measured on plasma samples of 262 cases and 528 controls using a highly sensitive and analytically validated electrochemiluminescence V-PLEX immunoassay.

RESULTS

Comparing the fourth quartile with the first quartile, we found increased IFNγ and IL12/IL23p40 associated with increased odds of a lung cancer diagnosis [OR 1.89, 95% confidence intervals (CI), 1.16-3.09; OR 2.49, 95% CI, 1.46-4.23, respectively]. Confirming our previous observations, we also detected a relationship between increased IL6, IL8, and C-reactive protein (CRP) with lung cancer diagnosis. These relationships were significant after adjustment for age, gender, race, smoking, body mass index (BMI), family history of lung cancer, and previous diagnoses of inflammatory conditions. However, none of these proteins could distinguish between a benign and malignant lung nodule (IL6: OR 1.25, 95% CI, 0.59-2.64; IL8: OR 1.40, 95% CI, 0.70-2.81; CRP: OR 0.98, 95% CI, 0.45-2.12).

CONCLUSIONS

We have discovered new associations for IFNγ and IL12/IL23p40 with lung cancer but have no evidence that these proteins can distinguish between benign and malignant lung nodules.

IMPACT

Circulating inflammation proteins are unlikely to have utility as companion LDCT biomarkers.