Identifying EGFR mutations in lung adenocarcinoma by noninvasive imaging using radiomics features and random forest modeling.

OBJECTIVES: The tyrosine kinase inhibitor (TKI)-sensitive mutations of the epidermal growth factor receptor (EGFR) gene is essential in the treatment of lung adenocarcinoma. To overcome the difficulty of EGFR gene test in situations where surgery and biopsy samples are too risky to obtain, we tried a noninvasive imaging method using radiomics features and random forest models. METHODS: Five hundred three lung adenocarcinoma patients who received surgery-based treatment were included in this study. The diagnosis and EGFR gene test were based on resections. TKI-sensitive mutations were found in 60.8% of the patients. CT scans before any invasive operation were gathered and analyzed to extract quantitative radiomics features and build random forest classifiers to identify EGFR mutants from wild types. Clinical features (sex and smoking history) were added to the image-based model. The model was trained on a set of 345 patients and validated on an independent test group (n = 158) using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. RESULTS: The performance of the random forest model with 94 radiomics features reached an AUC of 0.802. Its AUC was further improved to 0.828 by adding sex and smoking history. The sensitivity and specificity are 60.6% and 85.1% at the best diagnostic decision point. CONCLUSION: Our results showed that radiomics could not only reflect the genetic differences among tumors but also have diagnostic value and the potential to be a diagnostic tool. KEY POINTS: • Radiomics provides a potential noninvasive method for the prediction of EGFR mutation status. • In situations where surgeries and biopsy are not available, CT image-based radiomics models could help to make treatment decisions. • The accuracy, sensitivity, and specificity still need to be improved before the image-based EGFR identifier could be used in clinics.

Improved False Positive Reduction by Novel Morphological Features for Computer-Aided Polyp Detection in CT Colonography.

Computer-aided detection (CAD) systems can assist radiologists in reducing the interpretation time and improving the detection results in computed tomographic colonography (CTC). However, existing false positives (FPs) impair the advantages of CAD systems. This study aims to develop new morphological features for the FP reduction while maintaining high detection sensitivity. Volumetric feature maps are computed for each polyp candidate by using three-dimensional (3-D) geodesic distance transformation, circular transformation (CcT), and quantized convergence index (QCI) filters. Then, new morphological features are developed based on the curvature, fractal dimension, and volumetric feature maps. To the best of our knowledge, we are also the first to develop 3-D CcT and QCI filters specifically for colonic polyps. The new morphological features were evaluated to reduce the FPs by using 456 oral contrast-enhanced CT scans from 228 patients with 130 polyps ≥5 mm. For comparison, the well-defined features from our previous work were used to generate a baseline reference. The additional use of the new morphological features reduced the FP rate from 4.2 to 2.0 FPs per scan (i.e., 52.4% FP reduction percentage) at 96.2% by-polyp sensitivity and from 4.5 to 2.1 FPs per scan (i.e., 53.3% FP reduction percentage) at 93.9% per-scan sensitivity for polyps ≥5 mm. Experimental results indicate that the new morphological features can effectively reduce the FP rate without sacrificing detection sensitivity. We believe that the newly developed morphological features would advance the CAD systems to assist radiologists in interpreting CTC images.

The Role of PET-Based Radiomic Features in Predicting Local Control of Esophageal Cancer Treated with Concurrent Chemoradiotherapy.

This study was designed to evaluate the predictive performance of 18F-fluorodeoxyglucose positron emission tomography (PET)-based radiomic features for local control of esophageal cancer treated with concurrent chemoradiotherapy (CRT). For each of the 30 patients enrolled, 440 radiomic features were extracted from both pre-CRT and mid-CRT PET images. The top 25 features with the highest areas under the receiver operating characteristic curve for identifying local control status were selected as discriminative features. Four machine-learning methods, random forest (RF), support vector machine, logistic regression, and extreme learning machine, were used to build predictive models with clinical features, radiomic features or a combination of both. An RF model incorporating both clinical and radiomic features achieved the best predictive performance, with an accuracy of 93.3%, a specificity of 95.7%, and a sensitivity of 85.7%. Based on risk scores of local failure predicted by this model, the 2-year local control rate and PFS rate were 100.0% (95% CI 100.0-100.0%) and 52.2% (31.8-72.6%) in the low-risk group and 14.3% (0.0-40.2%) and 0.0% (0.0-40.2%) in the high-risk group, respectively. This model may have the potential to stratify patients with different risks of local failure after CRT for esophageal cancer, which may facilitate the delivery of personalized treatment.

A 3D Convolutional Neural Network Framework for Polyp Candidates Detection on the Limited Dataset of CT Colonography.

Proper training of convolutional neural networks (CNNs) requires annotated training datasets oflarge size, which are not currently available in CT colonography (CTC). In this paper, we propose a well-designed framework to address the challenging problem of data shortage in the training of 3D CNN for the detection of polyp candidates, which is the first and crucial part of the computer-aided diagnosis (CAD) of CTC. Our scheme relies on the following two aspects to reduce overfitting: 1) mass data augmentation, and 2) a flat 3D residual fully convolutional network (FCN). In the first aspect, we utilize extensive rotation, translation, and scaling with continuous value to provide numerous data samples. In the second aspect, we adapt the well-known V-Net to a flat residual FCN to resolve the problem of detection other than segmentation. Our proposed framework does not rely on accurate colon segmentation nor any electrical cleansing of tagged fluid, and experimental results show that it can still achieve high sensitivity with much fewer false positives. Code has been made available at: http://github.com/chenyzstju/ctc_screening_cnn.

Lung field segmentation using weighted sparse shape composition with robust initialization.

PURPOSE: Lung field segmentation for chest radiography is critical to pulmonary disease diagnosis. In this paper, we propose a new deformable model using weighted sparse shape composition with robust initialization to achieve robust and accurate lung field segmentation. METHODS: Our method consists of three steps: initialization, deformation and regularization. The steps of deformation and regularization are iteratively employed until convergence. First, since a deformable model is sensitive to the initial shape, a robust initialization is obtained by using a novel voting strategy, which allows the reliable patches on the image to vote for each landmark of the initial shape. Then, each point of the initial shape independently deforms to the lung boundary under the guidance of the appearance model, which can distinguish lung tissues from nonlung tissues near the boundary. Finally, the deformed shape is regularized by weighted sparse shape composition (SSC) model, which is constrained by both boundary information and the correlations between each point of the deformed shape. RESULTS: Our method has been evaluated on 247 chest radiographs from well-known dataset Japanese Society of Radiological Technology (JSRT) and achieved high overlap scores (0.955 ± 0.021). CONCLUSIONS: The experimental results show that the proposed deformable segmentation model is more robust and accurate than the traditional appearance and shape model on the JSRT database. Our method also shows higher accuracy than most state-of-the-art methods.

High-Performance CAD-CTC Scheme Using Shape Index, Multiscale Enhancement Filters, and Radiomic Features.

OBJECTIVE: Computer-aided detection (CAD) systems for computed tomography colonography (CTC) can automatically detect colorectal polyps. The main problem of currently developed CAD-CTC systems is the numerous false positives (FPs) caused by the existence of complicated colon structures (e.g., haustral fold, residual fecal material, inflation tube, and ileocecal valve). This study proposes a CAD-CTC scheme using shape index, multiscale enhancement filters, and radiomic features to address the FP issue. METHODS: Shape index and multiscale enhancement filter calculated in the Gaussian smoothed geodesic distance field are combined to generate the polyp candidates. A total of 440 well-defined radiomic features collected from previous radiomic studies and 200 newly developed radiomic features are used to construct a supervised classification model to reduce the numerous FPs. RESULTS: The proposed CAD-CTC scheme was evaluated on 152 oral contrast-enhanced CT datasets from 76 patients with 103 polyps ≥5 mm. The detection results were 98.1% and 95.3% by-polyp sensitivity and per-scan sensitivity, respectively, with the same FP rate of 1.3 FPs per dataset for polyps ≥5 mm. CONCLUSION: Experimental results indicate that the proposed CAD-CTC scheme can achieve high sensitivity while maintaining a low FP rate. SIGNIFICANCE: The proposed CAD-CTC scheme would be a beneficial tool in clinical colon examination.

Computerized detection of lung nodules through radiomics.

PURPOSE: Lung cancer is a major cause of cancer deaths, and the 5-year survival rate of stage IV lung cancer patients is only 2%. However, the 5-year survival rate of stage I lung cancer patients significantly increases to 50%. As such, spiral computed tomography (CT) scans are necessary to diagnose high-risk lung cancer patients in early stages. In this study, a computer-aided detection (CAD) system with radiomics was proposed. This system could automatically detect pulmonary nodules and reduce radiologists' workloads and human errors. METHODS: In the proposed scheme, a nodular enhancement filter was used to segment nodule candidates and extract radiomic features. A synthetic minority over-sampling technique was also applied to balance the samples, and a random forest method was utilized to distinguish between real nodules and false positive detections. The radiomics approach quantified intratumor heterogeneity and multifrequency information, which are highly correlated with lung nodules. RESULTS: The proposed method was used to evaluate 1004 CT cases from the well-known Lung Image Database Consortium, and 88.9% sensitivity with four false positive detections per CT scan was obtained by randomly selecting 502 cases for training and 502 other cases for testing. CONCLUSIONS: The proposed scheme yielded a high performance on the LIDC database. Therefore, the proposed scheme is possibly effective for various CT configurations used in routine diagnosis and lung cancer screening.