Computer-aided diagnostic scheme for the detection of lung nodules on chest radiographs: localized search method based on anatomical classification

Artificial intelligence: A critical review of applications for lung nodule and lung cancer

Artificial intelligence (AI) is a broad concept that usually refers to computer programs that can learn from data and perform certain specific tasks. In the recent years, the growth of deep learning, a successful technique for computer vision tasks that does not require explicit programming, coupled with the availability of large imaging databases fostered the development of multiple applications in the medical imaging field, especially for lung nodules and lung cancer, mostly through convolutional neural networks (CNN). Some of the first applications of AI is this field were dedicated to automated detection of lung nodules on X-ray and computed tomography (CT) examinations, with performances now reaching or exceeding those of radiologists. For lung nodule segmentation, CNN-based algorithms applied to CT images show excellent spatial overlap index with manual segmentation, even for irregular and ground glass nodules. A third application of AI is the classification of lung nodules between malignant and benign, which could limit the number of follow-up CT examinations for less suspicious lesions. Several algorithms have demonstrated excellent capabilities for the prediction of the malignancy risk when a nodule is discovered. These different applications of AI for lung nodules are particularly appealing in the context of lung cancer screening. In the field of lung cancer, AI tools applied to lung imaging have been investigated for distinct aims. First, they could play a role for the non-invasive characterization of tumors, especially for histological subtype and somatic mutation predictions, with a potential therapeutic impact. Additionally, they could help predict the patient prognosis, in combination to clinical data. Despite these encouraging perspectives, clinical implementation of AI tools is only beginning because of the lack of generalizability of published studies, of an inner obscure working and because of limited data about the impact of such tools on the radiologists' decision and on the patient outcome. Radiologists must be active participants in the process of evaluating AI tools, as such tools could support their daily work and offer them more time for high added value tasks.

Segmentation Performance Comparison Considering Regional Characteristics in Chest X-ray Using Deep Learning

Chest radiography is one of the most widely used diagnostic methods in hospitals, but it is difficult to read clearly because several human organ tissues and bones overlap. Therefore, various image processing and rib segmentation methods have been proposed to focus on the desired target. However, it is challenging to segment ribs elaborately using deep learning because they cannot reflect the characteristics of each region. Identifying which region has specific characteristics vulnerable to deep learning is an essential indicator of developing segmentation methods in medical imaging. Therefore, it is necessary to compare the deep learning performance differences based on regional characteristics. This study compares the differences in deep learning performance based on the rib region to verify whether deep learning reflects the characteristics of each part and to demonstrate why this regional performance difference has occurred. We utilized 195 normal chest X-ray datasets with data augmentation for learning and 5-fold cross-validation. To compare segmentation performance, the rib image was divided vertically and horizontally based on the spine, clavicle, heart, and lower organs, which are characteristic indicators of the baseline chest X-ray. Resultingly, we found that the deep learning model showed a 6-7% difference in the segmentation performance depending on the regional characteristics of the rib. We verified that the performance differences in each region cannot be ignored. This study will enable a more precise segmentation of the ribs and the development of practical deep learning algorithms.

Lung Segmentation using Active Shape Model to Detect the Disease from Chest Radiography

Background:

Some parametric models are used to diagnose problems of lung segmentation more easily and effectively.

Objective:

The present study aims to detect lung diseases (nodules and tuberculosis) better using an active shape model (ASM) from chest radiographs.

Material and Methods:

In this analytical study, six grouping methods, including three primary methods such as physicians, Dice similarity, and correlation coefficients) and also three secondary methods using SVM (Support Vector Machine) were used to classify the chest radiographs regarding diaphragm congestion and heart reshaping. The most effective method, based on the evaluation of the results by a radiologist, was found and used as input data for segmenting the images by active shape model (ASM). Several segmentation parameters were evaluated to calculate the accuracy of segmentation. This work was conducted on JSRT (Japanese Society of Radiological Technology) database images and tuberculosis database images were used for validation.

Results:

The results indicated that the ASM can detect 94.12 ± 2.34 % and 94.38 ± 3.74 % (mean± standard deviation) of pulmonary nodules in left and right lungs, respectively, from the JRST radiology datasets. Furthermore, the ASM model detected 88.33 ± 6.72 % and 90.37 ± 5.48 % of tuberculosis in left and right lungs, respectively.

Conclusion:

The ASM segmentation method combined with pre-segmentation grouping can be used as a preliminary step to identify areas with tuberculosis or pulmonary nodules. In addition, this presented approach can be used to measure the size and dimensions of the heart in future studies.

Deep learning applied to automatic disease detection using chest X-rays

Deep learning (DL) has shown rapid advancement and considerable promise when applied to the automatic detection of diseases using CXRs. This is important given the widespread use of CXRs across the world in diagnosing significant pathologies, and the lack of trained radiologists to report them. This review article introduces the basic concepts of DL as applied to CXR image analysis including basic deep neural network (DNN) structure, the use of transfer learning and the application of data augmentation. It then reviews the current literature on how DNN models have been applied to the detection of common CXR abnormalities (e.g. lung nodules, pneumonia, tuberculosis and pneumothorax) over the last few years. This includes DL approaches employed for the classification of multiple different diseases (multi-class classification). Performance of different techniques and models and their comparison with human observers are presented. Some of the challenges facing DNN models, including their future implementation and relationships to radiologists, are also discussed.

The detection of lung cancer using massive artificial neural network based on soft tissue technique

BACKGROUND

A proposed computer aided detection (CAD) scheme faces major issues during subtle nodule recognition. However, radiologists have not noticed subtle nodules in beginning stage of lung cancer while a proposed CAD scheme recognizes non subtle nodules using x-ray images.

METHOD

Such an issue has been resolved by creating MANN (Massive Artificial Neural Network) based soft tissue technique from the lung segmented x-ray image. A soft tissue image recognizes nodule candidate for feature extortion and classification. X-ray images are downloaded using Japanese society of radiological technology (JSRT) image set. This image set includes 233 images (140 nodule x-ray images and 93 normal x-ray images). A mean size for a nodule is 17.8 mm and it is validated with computed tomography (CT) image. Thirty percent (42/140) abnormal represents subtle nodules and it is split into five stages (tremendously subtle, very subtle, subtle, observable, relatively observable) by radiologists.

RESULT

A proposed CAD scheme without soft tissue technique attained 66.42% (93/140) sensitivity and 66.76% accuracy having 2.5 false positives per image. Utilizing soft tissue technique, many nodules superimposed by ribs as well as clavicles have identified (sensitivity is 72.85% (102/140) and accuracy is 72.96% at one false positive rate).

CONCLUSION

In particular, a proposed CAD system determine sensitivity and accuracy in support of subtle nodules (sensitivity is 14/42 = 33.33% and accuracy is 33.66%) is statistically higher than CAD (sensitivity is 13/42 = 30.95% and accuracy is 30.97%) scheme without soft tissue technique. A proposed CAD scheme attained tremendously minimum false positive rate and it is a promising technique in support of cancerous recognition due to improved sensitivity and specificity.

Artificial intelligence evaluating primary thoracic lesions has an overall lower error rate compared to veterinarians or veterinarians in conjunction with the artificial intelligence

To date, deep learning technologies have provided powerful decision support systems to radiologists in human medicine. The aims of this retrospective, exploratory study were to develop and describe an artificial intelligence able to screen thoracic radiographs for primary thoracic lesions in feline and canine patients. Three deep learning networks using three different pretraining strategies to predict 15 types of primary thoracic lesions were created (including tracheal collapse, left atrial enlargement, alveolar pattern, pneumothorax, and pulmonary mass). Upon completion of pretraining, the algorithms were provided with over 22 000 thoracic veterinary radiographs for specific training. All radiographs had a report created by a board-certified veterinary radiologist used as the gold standard. The performances of all three networks were compared to one another. An additional 120 radiographs were then evaluated by three types of observers: the best performing network, veterinarians, and veterinarians aided by the network. The error rates for each of the observers was calculated as an overall and for the 15 labels and were compared using a McNemar's test. The overall error rate of the network was significantly better than the overall error rate of the veterinarians or the veterinarians aided by the network (10.7% vs 16.8% vs17.2%, P = .001). The network's error rate was significantly better to detect cardiac enlargement and for bronchial pattern. The current network only provides help in detecting various lesion types and does not provide a diagnosis. Based on its overall very good performance, this could be used as an aid to general practitioners while waiting for the radiologist's report.

Review: On Segmentation of Nodules from Posterior and Anterior Chest Radiographs

Lung cancer is one of the major types of cancer in the world. Survival rate can be increased if the disease can be identified early. Posterior and anterior chest radiography and computerized tomography scans are the most used diagnosis techniques for detecting tumor from lungs. Posterior and anterior chest radiography requires less radiation dose and is available in most of the diagnostic centers and it costs less compared to the remaining diagnosis techniques. So PA chest radiography became the most commonly used technique for lung cancer detection. Because of superimposed anatomical structures present in the image, sometimes radiologists cannot find abnormalities from the image. To help radiologists in diagnosing tumor from PA chest radiographic images range of CAD scheme has been developed for the past three decades. These computerized tools may be used by radiologists as a second opinion in detecting tumor. Literature survey on detecting tumors from chest graphs is presented in this paper.

Computer-aided detection in chest radiography based on artificial intelligence: a survey

As the most common examination tool in medical practice, chest radiography has important clinical value in the diagnosis of disease. Thus, the automatic detection of chest disease based on chest radiography has become one of the hot topics in medical imaging research. Based on the clinical applications, the study conducts a comprehensive survey on computer-aided detection (CAD) systems, and especially focuses on the artificial intelligence technology applied in chest radiography. The paper presents several common chest X-ray datasets and briefly introduces general image preprocessing procedures, such as contrast enhancement and segmentation, and bone suppression techniques that are applied to chest radiography. Then, the CAD system in the detection of specific disease (pulmonary nodules, tuberculosis, and interstitial lung diseases) and multiple diseases is described, focusing on the basic principles of the algorithm, the data used in the study, the evaluation measures, and the results. Finally, the paper summarizes the CAD system in chest radiography based on artificial intelligence and discusses the existing problems and trends.

Computerized Classification of Pneumoconiosis on Digital Chest Radiography Artificial Neural Network with Three Stages

It is difficult for radiologists to classify pneumoconiosis from category 0 to category 3 on chest radiographs. Therefore, we have developed a computer-aided diagnosis (CAD) system based on a three-stage artificial neural network (ANN) method for classification based on four texture features. The image database consists of 36 chest radiographs classified as category 0 to category 3. Regions of interest (ROIs) with a matrix size of 32 × 32 were selected from chest radiographs. We obtained a gray-level histogram, histogram of gray-level difference, gray-level run-length matrix (GLRLM) feature image, and gray-level co-occurrence matrix (GLCOM) feature image in each ROI. For ROI-based classification, the first ANN was trained with each texture feature. Next, the second ANN was trained with output patterns obtained from the first ANN. Finally, we obtained a case-based classification for distinguishing among four categories with the third ANN method. We determined the performance of the third ANN by receiver operating characteristic (ROC) analysis. The areas under the ROC curve (AUC) of the highest category (severe pneumoconiosis) case and the lowest category (early pneumoconiosis) case were 0.89 ± 0.09 and 0.84 ± 0.12, respectively. The three-stage ANN with four texture features showed the highest performance for classification among the four categories. Our CAD system would be useful for assisting radiologists in classification of pneumoconiosis from category 0 to category 3.

Performance analysis of a computer-aided detection system for lung nodules in CT at different slice thicknesses

We study the performance of a computer-aided detection (CAD) system for lung nodules in computed tomography (CT) as a function of slice thickness. In addition, we propose and compare three different training methodologies for utilizing nonhomogeneous thickness training data (i.e., composed of cases with different slice thicknesses). These methods are (1) aggregate training using the entire suite of data at their native thickness, (2) homogeneous subset training that uses only the subset of training data that matches each testing case, and (3) resampling all training and testing cases to a common thickness. We believe this study has important implications for how CT is acquired, processed, and stored. We make use of 192 CT cases acquired at a thickness of 1.25 mm and 283 cases at 2.5 mm. These data are from the publicly available Lung Nodule Analysis 2016 dataset. In our study, CAD performance at 2.5 mm is comparable with that at 1.25 mm and is much better than at higher thicknesses. Also, resampling all training and testing cases to 2.5 mm provides the best performance among the three training methods compared in terms of accuracy, memory consumption, and computational time.

Overview of deep learning in medical imaging

The use of machine learning (ML) has been increasing rapidly in the medical imaging field, including computer-aided diagnosis (CAD), radiomics, and medical image analysis. Recently, an ML area called deep learning emerged in the computer vision field and became very popular in many fields. It started from an event in late 2012, when a deep-learning approach based on a convolutional neural network (CNN) won an overwhelming victory in the best-known worldwide computer vision competition, ImageNet Classification. Since then, researchers in virtually all fields, including medical imaging, have started actively participating in the explosively growing field of deep learning. In this paper, the area of deep learning in medical imaging is overviewed, including (1) what was changed in machine learning before and after the introduction of deep learning, (2) what is the source of the power of deep learning, (3) two major deep-learning models: a massive-training artificial neural network (MTANN) and a convolutional neural network (CNN), (4) similarities and differences between the two models, and (5) their applications to medical imaging. This review shows that ML with feature input (or feature-based ML) was dominant before the introduction of deep learning, and that the major and essential difference between ML before and after deep learning is the learning of image data directly without object segmentation or feature extraction; thus, it is the source of the power of deep learning, although the depth of the model is an important attribute. The class of ML with image input (or image-based ML) including deep learning has a long history, but recently gained popularity due to the use of the new terminology, deep learning. There are two major models in this class of ML in medical imaging, MTANN and CNN, which have similarities as well as several differences. In our experience, MTANNs were substantially more efficient in their development, had a higher performance, and required a lesser number of training cases than did CNNs. "Deep learning", or ML with image input, in medical imaging is an explosively growing, promising field. It is expected that ML with image input will be the mainstream area in the field of medical imaging in the next few decades.

Computer-Aided Diagnosis for Chest Radiographs in Intensive Care

The chest radiograph is an essential tool for the diagnosis of several lung diseases in intensive care units (ICU). However, several factors make the interpretation of the chest radiograph difficult including the number of X-rays done daily in ICU, the quality of the chest radiograph, and the lack of a standardized interpretation. To overcome these limitations in the interpretation of chest radiographs, researchers have developed computer-aided diagnosis (CAD) systems. In this review, the authors report the methodology used to develop CAD systems including identification of the region of interest, analysis of these regions, and classification. Currently, only a few CAD systems for chest X-ray interpretation are commercially available. Some promising research is ongoing, but the involvement of the pediatric research community is needed for the development and validation of such CAD systems dedicated to pediatric intensive care.

Classification of pulmonary nodules by using hybrid features

Early detection of pulmonary nodules is extremely important for the diagnosis and treatment of lung cancer. In this study, a new classification approach for pulmonary nodules from CT imagery is presented by using hybrid features. Four different methods are introduced for the proposed system. The overall detection performance is evaluated using various classifiers. The results are compared to similar techniques in the literature by using standard measures. The proposed approach with the hybrid features results in 90.7% classification accuracy (89.6% sensitivity and 87.5% specificity).

Machine Learning in Computer-aided Diagnosis of the Thorax and Colon in CT: A Survey

Computer-aided detection (CADe) and diagnosis (CAD) has been a rapidly growing, active area of research in medical imaging. Machine leaning (ML) plays an essential role in CAD, because objects such as lesions and organs may not be represented accurately by a simple equation; thus, medical pattern recognition essentially require "learning from examples." One of the most popular uses of ML is the classification of objects such as lesion candidates into certain classes (e.g., abnormal or normal, and lesions or non-lesions) based on input features (e.g., contrast and area) obtained from segmented lesion candidates. The task of ML is to determine "optimal" boundaries for separating classes in the multidimensional feature space which is formed by the input features. ML algorithms for classification include linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), multilayer perceptrons, and support vector machines (SVM). Recently, pixel/voxel-based ML (PML) emerged in medical image processing/analysis, which uses pixel/voxel values in images directly, instead of features calculated from segmented lesions, as input information; thus, feature calculation or segmentation is not required. In this paper, ML techniques used in CAD schemes for detection and diagnosis of lung nodules in thoracic CT and for detection of polyps in CT colonography (CTC) are surveyed and reviewed.

Computerized detection of lung nodules by means of "virtual dual-energy" radiography

Major challenges in current computer-aided detection (CADe) schemes for nodule detection in chest radiographs (CXRs) are to detect nodules that overlap with ribs and/or clavicles and to reduce the frequent false positives (FPs) caused by ribs. Detection of such nodules by a CADe scheme is very important, because radiologists are likely to miss such subtle nodules. Our purpose in this study was to develop a CADe scheme with improved sensitivity and specificity by use of "virtual dual-energy" (VDE) CXRs where ribs and clavicles are suppressed with massive-training artificial neural networks (MTANNs). To reduce rib-induced FPs and detect nodules overlapping with ribs, we incorporated the VDE technology in our CADe scheme. The VDE technology suppressed rib and clavicle opacities in CXRs while maintaining soft-tissue opacity by use of the MTANN technique that had been trained with real dual-energy imaging. Our scheme detected nodule candidates on VDE images by use of a morphologic filtering technique. Sixty morphologic and gray-level-based features were extracted from each candidate from both original and VDE CXRs. A nonlinear support vector classifier was employed for classification of the nodule candidates. A publicly available database containing 140 nodules in 140 CXRs and 93 normal CXRs was used for testing our CADe scheme. All nodules were confirmed by computed tomography examinations, and the average size of the nodules was 17.8 mm. Thirty percent (42/140) of the nodules were rated "extremely subtle" or "very subtle" by a radiologist. The original scheme without VDE technology achieved a sensitivity of 78.6% (110/140) with 5 (1165/233) FPs per image. By use of the VDE technology, more nodules overlapping with ribs or clavicles were detected and the sensitivity was improved substantially to 85.0% (119/140) at the same FP rate in a leave-one-out cross-validation test, whereas the FP rate was reduced to 2.5 (583/233) per image at the same sensitivity level as the original CADe scheme obtained (Difference between the specificities of the original and the VDE-based CADe schemes was statistically significant). In particular, the sensitivity of our VDE-based CADe scheme for subtle nodules (66.7% = 28/42) was statistically significantly higher than that of the original CADe scheme (57.1% = 24/42). Therefore, by use of VDE technology, the sensitivity and specificity of our CADe scheme for detection of nodules, especially subtle nodules, in CXRs were improved substantially.

A computerized scheme for lung nodule detection in multiprojection chest radiography

PURPOSE

Our previous study indicated that multiprojection chest radiography could significantly improve radiologists' performance for lung nodule detection in clinical practice. In this study, the authors further verify that multiprojection chest radiography can greatly improve the performance of a computer-aided diagnostic (CAD) scheme.

METHODS

Our database consisted of 59 subjects, including 43 subjects with 45 nodules and 16 subjects without nodules. The 45 nodules included 7 real and 38 simulated ones. The authors developed a conventional CAD scheme and a new fusion CAD scheme to detect lung nodules. The conventional CAD scheme consisted of four steps for (1) identification of initial nodule candidates inside lungs, (2) nodule candidate segmentation based on dynamic programming, (3) extraction of 33 features from nodule candidates, and (4) false positive reduction using a piecewise linear classifier. The conventional CAD scheme processed each of the three projection images of a subject independently and discarded the correlation information between the three images. The fusion CAD scheme included the four steps in the conventional CAD scheme and two additional steps for (5) registration of all candidates in the three images of a subject, and (6) integration of correlation information between the registered candidates in the three images. The integration step retained all candidates detected at least twice in the three images of a subject and removed those detected only once in the three images as false positives. A leave-one-subject-out testing method was used for evaluation of the performance levels of the two CAD schemes.

RESULTS

At the sensitivities of 70%, 65%, and 60%, our conventional CAD scheme reported 14.7, 11.3, and 8.6 false positives per image, respectively, whereas our fusion CAD scheme reported 3.9, 1.9, and 1.2 false positives per image, and 5.5, 2.8, and 1.7 false positives per patient, respectively. The low performance of the conventional CAD scheme may be attributed to the high noise level in chest radiography, and the small size and low contrast of most nodules.

CONCLUSIONS

This study indicated that the fusion of correlation information in multiprojection chest radiography can markedly improve the performance of CAD scheme for lung nodule detection.

Pixel-based machine learning in medical imaging

Machine learning (ML) plays an important role in the medical imaging field, including medical image analysis and computer-aided diagnosis, because objects such as lesions and organs may not be represented accurately by a simple equation; thus, medical pattern recognition essentially require “learning from examples.” One of the most popular uses of ML is classification of objects such as lesions into certain classes (e.g., abnormal or normal, or lesions or nonlesions) based on input features (e.g., contrast and circularity) obtained from segmented object candidates. Recently, pixel/voxel-based ML (PML) emerged in medical image processing/analysis, which use pixel/voxel values in images directly instead of features calculated from segmented objects as input information; thus, feature calculation or segmentation is not required. Because the PML can avoid errors caused by inaccurate feature calculation and segmentation which often occur for subtle or complex objects, the performance of the PML can potentially be higher for such objects than that of common classifiers (i.e., feature-based MLs). In this paper, PMLs are surveyed to make clear (a) classes of PMLs, (b) similarities and differences within (among) different PMLs and those between PMLs and feature-based MLs, (c) advantages and limitations of PMLs, and (d) their applications in medical imaging.

Computerized analysis of pneumoconiosis in digital chest radiography: effect of artificial neural network trained with power spectra

It is difficult for radiologists to classify pneumoconiosis with small nodules on chest radiographs. Therefore, we have developed a computer-aided diagnosis (CAD) system based on the rule-based plus artificial neural network (ANN) method for distinction between normal and abnormal regions of interest (ROIs) selected from chest radiographs with and without pneumoconiosis. The image database consists of 11 normal and 12 abnormal chest radiographs. These abnormal cases included five silicoses, four asbestoses, and three other pneumoconioses. ROIs (matrix size, 32 × 32) were selected from normal and abnormal lungs. We obtained power spectra (PS) by Fourier transform for the frequency analysis. A rule-based method using PS values at 0.179 and 0.357 cycles per millimeter, corresponding to the spatial frequencies of nodular patterns, were employed for identification of obviously normal or obviously abnormal ROIs. Then, ANN was applied for classification of the remaining normal and abnormal ROIs, which were not classified as obviously abnormal or normal by the rule-based method. The classification performance was evaluated by the area under the receiver operating characteristic curve (Az value). The Az value was 0.972 ± 0.012 for the rule-based plus ANN method, which was larger than that of 0.961 ± 0.016 for the ANN method alone (P ≤ 0.15) and that of 0.873 for the rule-based method alone. We have developed a rule-based plus pattern recognition technique based on the ANN for classification of pneumoconiosis on chest radiography. Our CAD system based on PS would be useful to assist radiologists in the classification of pneumoconiosis.

A computerized method for automated identification of erect posteroanterior and supine anteroposterior chest radiographs

A computerized scheme was developed for automated identification of erect posteroanterior (PA) and supine anteroposterior (AP) chest radiographs. The method was based on three features, the tilt angle of the scapula superior border, the tilt angle of the clavicle and the extent of radiolucence in lung fields, to identify the view of a chest radiograph. The three indices A(scapula), A(clavicle) and C(lung) were determined from a chest image for the three features. Linear discriminant analysis was used to classify PA and AP chest images based on the three indices. The performance of the method was evaluated by receiver operating characteristic analysis. The proposed method was evaluated using a database of 600 PA and 600 AP chest radiographs. The discriminant performances Az of A(scapula), A(clavicle) and C(lung) were 0.878 ± 0.010, 0.683 ± 0.015 and 0.962 ± 0.006, respectively. The combination of the three indices obtained an Az value of 0.979 ± 0.004. The results indicate that the combination of the three indices could yield high discriminant performance. The proposed method could provide radiologists with information about the view of chest radiographs for interpretation or could be used as a preprocessing step for analyzing chest images.

Improved detection of subtle lung nodules by use of chest radiographs with bone suppression imaging: receiver operating characteristic analysis with and without localization

OBJECTIVE

The purpose of this article is to evaluate radiologists' ability to detect subtle nodules by use of standard chest radiographs alone compared with bone suppression imaging used together with standard radiographs.

MATERIALS AND METHODS

The cases used in this observer study comprised radiographs of 72 patients with a subtle nodule and 79 patients without nodules taken from the Japanese Society of Radiological Technology nodule database. A new image-processing system was applied to the 151 radiographs to create corresponding bone suppression images. Two image reading sets were used with an independent test method. The first reading included half of the patients (a randomly selected subset A) showing only the standard image and the remaining half (subset B) showing the standard image plus bone suppression images. The second reading entailed the same subsets; however, subset A was accompanied by bone suppression images, whereas subset B was shown with only the standard image. The two image sets were read by three experienced radiologists, with an interval of more than 2 weeks between the sessions. Receiver operating characteristic (ROC) curves, with and without localization, were obtained to evaluate the observers' performance.

RESULTS

The mean value of the area under the ROC curve for the three observers was significantly improved, from 0.840 with standard radiographs alone to 0.863 with additional bone suppression images (p = 0.01). The area under the localization ROC curve was also improved with bone suppression imaging.

CONCLUSION

The use of bone suppression images improved radiologists' performance in the detection of subtle nodules on chest radiographs.

Development and evaluation of a computer-aided diagnostic scheme for lung nodule detection in chest radiographs by means of two-stage nodule enhancement with support vector classification

PURPOSE

To develop a computer-aided detection (CADe) scheme for nodules in chest radiographs (CXRs) with a high sensitivity and a low false-positive (FP) rate.

METHODS

The authors developed a CADe scheme consisting of five major steps, which were developed for improving the overall performance of CADe schemes. First, to segment the lung fields accurately, the authors developed a multisegment active shape model. Then, a two-stage nodule-enhancement technique was developed for improving the conspicuity of nodules. Initial nodule candidates were detected and segmented by using the clustering watershed algorithm. Thirty-one shape-, gray-level-, surface-, and gradient-based features were extracted from each segmented candidate for determining the feature space, including one of the new features based on the Canny edge detector to eliminate a major FP source caused by rib crossings. Finally, a nonlinear support vector machine (SVM) with a Gaussian kernel was employed for classification of the nodule candidates.

RESULTS

To evaluate and compare the scheme to other published CADe schemes, the authors used a publicly available database containing 140 nodules in 140 CXRs and 93 normal CXRs. The CADe scheme based on the SVM classifier achieved sensitivities of 78.6% (110/140) and 71.4% (100/140) with averages of 5.0 (1165/233) FPs/image and 2.0 (466/233) FPs/image, respectively, in a leave-one-out cross-validation test, whereas the CADe scheme based on a linear discriminant analysis classifier had a sensitivity of 60.7% (85/140) at an FP rate of 5.0 FPs/image. For nodules classified as "very subtle" and "extremely subtle," a sensitivity of 57.1% (24/42) was achieved at an FP rate of 5.0 FPs/image. When the authors used a database developed at the University of Chicago, the sensitivities was 83.3% (40/48) and 77.1% (37/48) at an FP rate of 5.0 (240/48) FPs/image and 2.0 (96/48) FPs/image, respectively.

CONCLUSIONS

These results compare favorably to those described for other commercial and non-commercial CADe nodule detection systems.

Dual energy subtraction digital radiography improves performance of a next generation computer-aided detection program

PURPOSE

Computer-aided detection (CAD) has shown potential to assist physicians in the detection of lung nodules on chest radiographs, but widespread acceptance has been stymied by high false-positive rates. Few studies have examined the potential for dual energy subtraction (DES) to improve CAD performance.

MATERIALS AND METHODS

Institutional review board approval was obtained, the requirement for informed consent was waived because the study was retrospective, and practices conformed to Health Insurance Portability and Accountability Act regulations. The CAD program was applied retrospectively to dual energy posteroanterior (PA) chest radiographs of 36 patients (17 women, 19 men, mean age 69 y) with 48 pathology proven lung nodules. Results were analyzed to determine the stand-alone CAD program false-positive rates, and sensitivity by nodule subtlety and location. Statistical analysis was performed using the chi(2) or Fisher exact tests for independence of sensitivities between standard PA and DES radiography. Differences in the mean false-positives per image (FPPI) between radiographic modalities were determined using the paired Students t test, and bootstrap confidence intervals were obtained to confirm results.

RESULTS

The sensitivity of the CAD program with the standard PA was 46% (22 of 48 nodules) compared with 67% (32 of 48 nodules) using the DES soft tissue or bone-subtracted view (P=0.064). The average number of FPPI identified by CAD was significantly lower using DES (FPPI(soft tissue) = 1.64) when compared with the standard PA chest radiograph (FPPI(PA) = 2.39) (P<0.01).

CONCLUSIONS

DES has the potential to improve stand-alone CAD performance by both increasing sensitivity for certain subtle lung cancer lesions and decreasing overall CAD false-positive rates.

A new computationally efficient CAD system for pulmonary nodule detection in CT imagery

Early detection of lung nodules is extremely important for the diagnosis and clinical management of lung cancer. In this paper, a novel computer aided detection (CAD) system for the detection of pulmonary nodules in thoracic computed tomography (CT) imagery is presented. The paper describes the architecture of the CAD system and assesses its performance on a publicly available database to serve as a benchmark for future research efforts. Training and tuning of all modules in our CAD system is done using a separate and independent dataset provided courtesy of the University of Texas Medical Branch (UTMB). The publicly available testing dataset is that created by the Lung Image Database Consortium (LIDC). The LIDC data used here is comprised of 84 CT scans containing 143 nodules ranging from 3 to 30mm in effective size that are manually segmented at least by one of the four radiologists. The CAD system uses a fully automated lung segmentation algorithm to define the boundaries of the lung regions. It combines intensity thresholding with morphological processing to detect and segment nodule candidates simultaneously. A set of 245 features is computed for each segmented nodule candidate. A sequential forward selection process is used to determine the optimum subset of features for two distinct classifiers, a Fisher Linear Discriminant (FLD) classifier and a quadratic classifier. A performance comparison between the two classifiers is presented, and based on this, the FLD classifier is selected for the CAD system. With an average of 517.5 nodule candidates per case/scan (517.5+/-72.9), the proposed front-end detector/segmentor is able to detect 92.8% of all the nodules in the LIDC/testing dataset (based on merged ground truth). The mean overlap between the nodule regions delineated by three or more radiologists and the ones segmented by the proposed segmentation algorithm is approximately 63%. Overall, with a specificity of 3 false positives (FPs) per case/patient on average, the CAD system is able to correctly identify 80.4% of the nodules (115/143) using 40 selected features. A 7-fold cross-validation performance analysis using the LIDC database only shows CAD sensitivity of 82.66% with an average of 3 FPs per CT scan/case.

Usefulness of computer-aided diagnosis schemes for vertebral fractures and lung nodules on chest radiographs

OBJECTIVE

We retrospectively evaluated the usefulness of computer-aided diagnosis (CAD) schemes to radiologist performance in the simultaneous detection of vertebral fractures and lung nodules on chest radiographs.

MATERIALS AND METHODS

We evaluated posteroanterior and lateral chest images of 21 patients with vertebral fractures, 31 patients with lung nodules, and 10 persons acting as controls. The total number of subjects was 60 because both lesions were present in four patients. Eighteen radiologists were asked to detect vertebral fractures and nodules simultaneously on posteroanterior and lateral images. The radiologists indicated their confidence level ratings regarding the presence or absence of lesions and the most likely location of each lesion on either posteroanterior or lateral images, first without and then with CAD output. The observers' performance was evaluated with use of receiver operating characteristic (ROC) and jackknife free-response ROC curves.

RESULTS

With the CAD scheme, the average area under the ROC curve for detection of vertebral fractures improved from 0.906 to 0.951 (p = 0.002). That for lung nodules also improved, but the improvement was not statistically significant (0.804-0.816, p = 0.297). The figure-of-merit values obtained with the jackknife free-response ROC program improved from 0.585 to 0.680 (p < 0.001) for vertebral fractures and from 0.622 to 0.650 (p = 0.017) for nodules, both results having statistical significance. Average sensitivity in the detection of lesions improved from 59.8% to 69.3% for vertebral fractures and from 64.9% to 67.6% for nodules.

CONCLUSION

In the detection of vertebral fractures and lung nodules on chest images, diagnostic accuracy among radiologists improves with the use of CAD.

Computer-aided diagnosis for the classification of focal liver lesions by use of contrast-enhanced ultrasonography

The authors developed a computer-aided diagnostic (CAD) scheme for classifying focal liver lesions (FLLs) as liver metastasis, hemangioma, and three histologic differentiation types of hepatocellular carcinoma (HCC), by use of microflow imaging (MFI) of contrast-enhanced ultrasonography. One hundred and three FLLs obtained from 97 cases used in this study consisted of 26 metastases (15 hyper- and 11 hypovascularity types), 16 hemangiomas (five hyper- and 11 hypovascularity types) and 61 HCCs: 24 well differentiated (w-HCC), 28 moderately differentiated (m-HCC), and nine poorly differentiated (p-HCC). Pathologies of all cases were determined based on biopsy or surgical specimens. Locations and contours of FLLs on contrast-enhanced images were determined manually by an experienced physician. MFI was obtained with contrast-enhanced low-mechanical-index (MI) pulse subtraction imaging at a fixed plane which included a distinctive cross section of the FLL. In MFI, the inflow high signals in the plane, which were due to the vascular patterns and the contrast agent, were accumulated following flash scanning with a high-MI ultrasound exposure. In the initial step of our computerized scheme, a series of the MFI images was extracted from the original cine clip (AVI format). We applied a smoothing filter and time-sequential running average techniques in order to reduce signal noise on the single MFI image and cyclic noise on the sequential MFI images, respectively. A kidney, vessels, and a liver parenchyma region were segmented automatically by use of the last image of a series of MFI images. The authors estimated time-intensity curves for an FLL by use of a series of the temporally averaged MFI images in order to determine temporal features such as estimated replenishment times at early and delayed phases, flow rates, and peak times. In addition, they extracted morphologic and gray-level image features which were determined based on the physicians' knowledge of the diagnosis of the FLL, such as the size of lesion, vascular patterns, and the presence of hypoechoic regions. They employed a cascade of six independent artificial neural networks (ANNs) by use of extracted temporal and image features for classifying five types of liver diseases. A total of 16 temporal and image features, which were selected from 43 initially extracted features, were used for six different ANNs for making decisions at each decision in the cascade. The ANNs were trained and tested with a leave-one-lesion-out test method. The classification accuracies for the 103 FLLs were 88.5% for metastasis, 93.8% for hemangioma, and 86.9% for all HCCs. In addition, the classification accuracies for histologic differentiation types of HCCs were 79.2% for w-HCC, 50.0% for m-HCC, and 77.8% for p-HCC. The CAD scheme for classifying FLLs by use of the MFI on contrast-enhanced ultrasonography has the potential to improve the diagnostic accuracy in the histologic diagnosis of HCCs and the other liver diseases.

Performance analysis of a new computer aided detection system for identifying lung nodules on chest radiographs

A new computer aided detection (CAD) system is presented for the detection of pulmonary nodules on chest radiographs. Here, we present the details of the proposed algorithm and provide a performance analysis using a publicly available database to serve as a benchmark for future research efforts. All aspects of algorithm training were done using an independent dataset containing 167 chest radiographs with a total of 181 lung nodules. The publicly available test set was created by the Standard Digital Image Database Project Team of the Scientific Committee of the Japanese Society of Radiological Technology (JRST). The JRST dataset used here is comprised of 154 chest radiographs containing one radiologist confirmed nodule each (100 malignant cases, 54 benign cases). The CAD system uses an active shape model for anatomical segmentation. This is followed by a new weighted-multiscale convergence-index nodule candidate detector. A novel candidate segmentation algorithm is proposed that uses an adaptive distance-based threshold. A set of 114 features is computed for each candidate. A Fisher linear discriminant (FLD) classifier is used on a subset of 46 features to produce the final detections. Our results indicate that the system is able to detect 78.1% of the nodules in the JRST test set with and average of 4.0 false positives per image (excluding 14 cases containing lung nodules in retrocardiac and subdiaphragmatic regions of the lung).

Does computer-aided diagnosis for lung tumors change satisfaction of search in chest radiography?

RATIONALE AND OBJECTIVES

Computer-aided diagnosis (CAD) has been developed to ensure that the radiologist considers suspect focal opacities that may represent cancer in chest radiography. Although CAD was not developed to counteract the satisfaction of search (SOS) effect, it may be an effective intervention to do so. The objective of this study is to determine whether an idealized CAD can reduce SOS effects in chest radiography.

MATERIALS AND METHODS

Fifty-seven chest radiographs, half of which demonstrated diverse, native abnormalities were read twice by 16 observers, once with and once without the addition of a simulated pulmonary nodule. Simulated CAD prompts were provided during the interpretation, which unerringly pointed to the added simulated nodule. Area under the ROC curve for detecting the native abnormalities was estimated for each observer in each treatment condition. In addition to testing for the SOS effect in the presence of CAD prompts, results were compared to those of a previous SOS study.

RESULTS

Significantly more nodules were reported in the SOS with CAD experiment than in the original SOS experiment (49 versus 43, P < .01). An SOS effect was found even when CAD prompts were provided; ROC areas for detecting native abnormalities were reduced with added nodules [0.68 versus 0.65, P (one-tailed) < .05]. Comparison of the current experiment with CAD and the previous SOS experiments failed to show a significant difference of the magnitude of the SOS effect (P = .52). The threshold for reporting was more conservative with CAD prompts than in SOS studies (P = .052).

CONCLUSION

Our results indicate that the CAD prompts, even those that always point to their target lesion without false-positive error, fail to counteract SOS in chest radiography. The stricter decision thresholds with CAD prompts may indicate less visual search for native abnormalities.

Computer-aided diagnosis in medical imaging: historical review, current status and future potential

Computer-aided diagnosis (CAD) has become one of the major research subjects in medical imaging and diagnostic radiology. In this article, the motivation and philosophy for early development of CAD schemes are presented together with the current status and future potential of CAD in a PACS environment. With CAD, radiologists use the computer output as a "second opinion" and make the final decisions. CAD is a concept established by taking into account equally the roles of physicians and computers, whereas automated computer diagnosis is a concept based on computer algorithms only. With CAD, the performance by computers does not have to be comparable to or better than that by physicians, but needs to be complementary to that by physicians. In fact, a large number of CAD systems have been employed for assisting physicians in the early detection of breast cancers on mammograms. A CAD scheme that makes use of lateral chest images has the potential to improve the overall performance in the detection of lung nodules when combined with another CAD scheme for PA chest images. Because vertebral fractures can be detected reliably by computer on lateral chest radiographs, radiologists' accuracy in the detection of vertebral fractures would be improved by the use of CAD, and thus early diagnosis of osteoporosis would become possible. In MRA, a CAD system has been developed for assisting radiologists in the detection of intracranial aneurysms. On successive bone scan images, a CAD scheme for detection of interval changes has been developed by use of temporal subtraction images. In the future, many CAD schemes could be assembled as packages and implemented as a part of PACS. For example, the package for chest CAD may include the computerized detection of lung nodules, interstitial opacities, cardiomegaly, vertebral fractures, and interval changes in chest radiographs as well as the computerized classification of benign and malignant nodules and the differential diagnosis of interstitial lung diseases. In order to assist in the differential diagnosis, it would be possible to search for and retrieve images (or lesions) with known pathology, which would be very similar to a new unknown case, from PACS when a reliable and useful method has been developed for quantifying the similarity of a pair of images for visual comparison by radiologists.

Computer-aided diagnosis in chest radiography

We have developed computer-aided diagnosis (CAD) schemes for the detection of lung nodules, interstitial lung diseases, interval changes, and asymmetric opacities, and also for the differential diagnosis of lung nodules and interstitial lung diseases on chest radiographs. Observer performance studies indicate clearly that radiologists' diagnostic accuracy was improved significantly when radiologists used a computer output in their interpretations of chest radiographs. In addition, the automated recognition methods for the patient and the projection view by use of chest radiographs were useful for integrating the chest CAD schemes into the picture-archiving and communication system (PACS).

Recent progress in computer-aided diagnosis of lung nodules on thin-section CT

Computer-aided diagnosis (CAD) provides a computer output as a "second opinion" in order to assist radiologists in the diagnosis of various diseases on medical images. Currently, a significant research effort is being devoted to the detection and characterization of lung nodules in thin-section computed tomography (CT) images, which represents one of the newest directions of CAD development in thoracic imaging. We describe in this article the current status of the development and evaluation of CAD schemes for the detection and characterization of lung nodules in thin-section CT. We also review a number of observer performance studies in which it was attempted to assess the potential clinical usefulness of CAD schemes for nodule detection and characterization in thin-section CT. Whereas current CAD schemes for nodule characterization have achieved high performance levels and would be able to improve radiologists' performance in the characterization of nodules in thin-section CT, current schemes for nodule detection appear to report many false positives, and, therefore, significant efforts are needed in order further to improve the performance levels of current CAD schemes for nodule detection in thin-section CT.

Computer-aided diagnosis for improved detection of lung nodules by use of posterior-anterior and lateral chest radiographs

RATIONALE AND OBJECTIVES

We developed a computerized scheme for detection of lung nodules in the lateral views of chest radiographs, in order to improve the overall performance in combination with the computer-aided diagnostic (CAD) scheme for posterior-anterior (PA) views.

MATERIALS AND METHODS

We used 106 pairs of PA and lateral views of chest radiographs (122 lung nodules) for development of the CAD scheme. In the CAD scheme for lateral views, initial candidates of lung nodules were identified by use of a nodule enhancement filter based on the edge gradients. Thirty-four image features extracted from the original and the nodule-enhanced images were used for the rule-based scheme and for artificial neural networks (ANNs) for removal of some false-positive candidates. The computer performance was evaluated with a leave-one-case-out test method for ANNs. For PA views, we used the existing CAD scheme, which was trained with one-half of 924 chest images and then tested with the remaining images.

RESULTS

When the CAD scheme was applied only to PA views, the sensitivity in the detection of lung nodules was 70.5%, with 4.9 false positives per image. Although the performance of the computerized scheme for lateral views was relatively low (60.7% sensitivity with 1.7 false positives per image), the overall sensitivity (86.9%) was improved (6.6 false positives per two views), because 20 (16.4%) of the 122 nodules were detected only on lateral views.

CONCLUSIONS

The CAD scheme by use of lateral-view images has the potential to improve the overall performance for detection of lung nodules on chest radiographs when combined with a conventional CAD scheme for standard PA views.