Lung cancers missed on chest radiographs: results obtained with a commercial computer-aided detection program

Computer-aided hepatocellular carcinoma detection on the hepatobiliary phase of gadoxetic acid-enhanced magnetic resonance imaging using a convolutional neural network: Feasibility evaluation with multi-sequence data

BACKGROUND AND OBJECTIVES

Diagnosis of hepatocellular carcinoma (HCC) on liver MRI needs analysis of multi-sequence images. However, developing computer-aided detection (CAD) for every single sequence requires considerable time and labor for image segmentation. Therefore, we developed CAD for HCC on the hepatobiliary phase (HBP) of gadoxetic acid-enhanced magnetic resonance imaging (MRI) using a convolutional neural network (CNN) and evaluated its feasibility on multi-sequence, multi-unit, and multi-center data.

METHODS

Patients who underwent gadoxetic acid-enhanced MRI and surgery for HCC in Korea University Anam Hospital (KUAH) and Korea University Guro Hospital (KUGH) were reviewed. Finally, 170 nodules from 155 consecutive patients from KUAH and 28 nodules from 28 patients randomly selected from KUGH were included. Regions of interests were drawn on the whole HCC volume on HBP, T1-weighted (T1WI), T2-weighted (T2WI), and portal venous phase (PVP) images. The CAD was developed from the HBP images of KUAH using customized-nnUNet and post-processed for false-positive reduction. Internal and external validation of the CAD was performed with HBP, T1WI, T2WI, and PVP of KUAH and KUGH.

RESULTS

The figure of merit and recall of the jackknife alternative free-response receiver operating characteristic of the CAD for HBP, T1WI, T2WI, and PVP at false-positive rate 0.5 were (0.87 and 87.0), (0.73 and 73.3), (0.13 and 13.3), and (0.67 and 66.7) in KUAH and (0.86 and 86.0), (0.61 and 53.6), (0.07 and 0.07), and (0.57 and 53.6) in KUGH, respectively.

CONCLUSIONS

The CAD for HCC on gadoxetic acid-enhanced MRI developed by CNN from HBP detected HCCs feasibly on HBP, T1WI, and PVP of gadoxetic acid-enhanced MRI obtained from multiple units and centers. This result imply that the CAD developed using single MRI sequence may be applied to other similar sequences and this will reduce labor and time for CAD development in multi-sequence MRI.

A case report of dermatomyositis with the missed diagnosis of non-small cell lung cancer and concurrence of pulmonary tuberculosis

A 42-year-old man with four months of retrosternal pain and two months of skin rashes and proximal muscle weakness was diagnosed with dermatomyositis (DM) based on muscle enzyme analysis and needle electromyography. Chest computed tomography (CT) showed scattered inflammation nodules in both lungs’ upper lobes with negative sputum smear for lung cancer and pulmonary tuberculosis (TB). A good clinical response to oral prednisone was obtained, except for the retrosternal pain in the preceding two months. Urgent CT pulmonary angiography ruled out pulmonary thromboembolism but revealed squamous cell lung cancer with metastases in the sternum and mediastinal lymph nodes. In retrospect, we found osteolytic destruction consistent with sternal metastasis on CT taken at the initial treatment of DM, which was missed by radiologists. Simultaneously, the man was diagnosed with pulmonary TB based on rapid mycobacterial TB detection. This case report indicates the radiologic errors and highlights the importance of a thorough search for underlying lung cancer and pulmonary TB in patients with DM, especially in countries with a high TB burden.

Optimal number of strong labels for curriculum learning with convolutional neural network to classify pulmonary abnormalities in chest radiographs

BACKGROUND AND OBJECTIVE

It is important to alleviate annotation efforts and costs by efficiently training on medical images. We performed a stress test on several strong labels for curriculum learning with a convolutional neural network to differentiate normal and five types of pulmonary abnormalities in chest radiograph images.

METHODS

The numbers of CXR images of healthy subjects and patients, acquired at Asan Medical Center (AMC), were 6069 and 3465, respectively. The numbers of CXR images of patients with nodules, consolidation, interstitial opacity, pleural effusion, and pneumothorax were 944, 550, 280, 1360, and 331, respectively. The AMC dataset was split into training, tuning, and test, with a ratio of 7:1:2. All lesions were strongly labeled by thoracic expert radiologists, with confirmation of the corresponding CT. For curriculum learning, normal and abnormal patches (N = 26658) were randomly extracted around the normal lung and strongly labeled abnormal lesions, respectively. In addition, 1%, 5%, 20%, 50%, and 100% of strong labels were used to determine an optimal number for them. Each patch dataset was trained with the ResNet-50 architecture, and all CXRs with weak labels were used for fine-tuning them in a transfer-learning manner. A dataset acquired from the Seoul National University Bundang Hospital (SNUBH) was used for external validation.

RESULTS

The detection accuracies of the 1%, 5%, 20%, 50%, and 100% datasets were 90.51, 92.15, 93.90, 94.54, and 95.39, respectively, in the AMC dataset and 90.01, 90.14, 90.97, 91.92, and 93.00 in the SNUBH dataset.

CONCLUSIONS

Our results showed that curriculum learning with over 20% sampling rate for strong labels are sufficient to train a model with relatively high performance, which can be easily and efficiently developed in an actual clinical setting.

Lung nodule detection in chest X-rays using synthetic ground-truth data comparing CNN-based diagnosis to human performance

We present a method to generate synthetic thorax radiographs with realistic nodules from CT scans, and a perfect ground truth knowledge. We evaluated the detection performance of nine radiologists and two convolutional neural networks in a reader study. Nodules were artificially inserted into the lung of a CT volume and synthetic radiographs were obtained by forward-projecting the volume. Hence, our framework allowed for a detailed evaluation of CAD systems' and radiologists' performance due to the availability of accurate ground-truth labels for nodules from synthetic data. Radiographs for network training (U-Net and RetinaNet) were generated from 855 CT scans of a public dataset. For the reader study, 201 radiographs were generated from 21 nodule-free CT scans with altering nodule positions, sizes and nodule counts of inserted nodules. Average true positive detections by nine radiologists were 248.8 nodules, 51.7 false positive predicted nodules and 121.2 false negative predicted nodules. The best performing CAD system achieved 268 true positives, 66 false positives and 102 false negatives. Corresponding weighted alternative free response operating characteristic figure-of-merits (wAFROC FOM) for the radiologists range from 0.54 to 0.87 compared to a value of 0.81 (CI 0.75-0.87) for the best performing CNN. The CNN did not perform significantly better against the combined average of the 9 readers (p = 0.49). Paramediastinal nodules accounted for most false positive and false negative detections by readers, which can be explained by the presence of more tissue in this area.

AI-based improvement in lung cancer detection on chest radiographs: results of a multi-reader study in NLST dataset

OBJECTIVE

Assess if deep learning-based artificial intelligence (AI) algorithm improves reader performance for lung cancer detection on chest X-rays (CXRs).

METHODS

This reader study included 173 images from cancer-positive patients (n = 98) and 346 images from cancer-negative patients (n = 196) selected from National Lung Screening Trial (NLST). Eight readers, including three radiology residents, and five board-certified radiologists, participated in the observer performance test. AI algorithm provided image-level probability of pulmonary nodule or mass on CXRs and a heatmap of detected lesions. Reader performance was compared with AUC, sensitivity, specificity, false-positives per image (FPPI), and rates of chest CT recommendations.

RESULTS

With AI, the average sensitivity of readers for the detection of visible lung cancer increased for residents, but was similar for radiologists compared to that without AI (0.61 [95% CI, 0.55-0.67] vs. 0.72 [95% CI, 0.66-0.77], p = 0.016 for residents, and 0.76 [95% CI, 0.72-0.81] vs. 0.76 [95% CI, 0.72-0.81, p = 1.00 for radiologists), while false-positive findings per image (FPPI) was similar for residents, but decreased for radiologists (0.15 [95% CI, 0.11-0.18] vs. 0.12 [95% CI, 0.09-0.16], p = 0.13 for residents, and 0.24 [95% CI, 0.20-0.29] vs. 0.17 [95% CI, 0.13-0.20], p < 0.001 for radiologists). With AI, the average rate of chest CT recommendation in patients positive for visible cancer increased for residents, but was similar for radiologists (54.7% [95% CI, 48.2-61.2%] vs. 70.2% [95% CI, 64.2-76.2%], p < 0.001 for residents and 72.5% [95% CI, 68.0-77.1%] vs. 73.9% [95% CI, 69.4-78.3%], p = 0.68 for radiologists), while that in cancer-negative patients was similar for residents, but decreased for radiologists (11.2% [95% CI, 9.6-13.1%] vs. 9.8% [95% CI, 8.0-11.6%], p = 0.32 for residents and 16.4% [95% CI, 14.7-18.2%] vs. 11.7% [95% CI, 10.2-13.3%], p < 0.001 for radiologists).

CONCLUSIONS

AI algorithm can enhance the performance of readers for the detection of lung cancers on chest radiographs when used as second reader.

KEY POINTS

• Reader study in the NLST dataset shows that AI algorithm had sensitivity benefit for residents and specificity benefit for radiologists for the detection of visible lung cancer. • With AI, radiology residents were able to recommend more chest CT examinations (54.7% vs 70.2%, p < 0.001) for patients with visible lung cancer. • With AI, radiologists recommended significantly less proportion of unnecessary chest CT examinations (16.4% vs. 11.7%, p < 0.001) in cancer-negative patients.

Added Value of Deep Learning-based Detection System for Multiple Major Findings on Chest Radiographs: A Randomized Crossover Study

Background Previous studies assessing the effects of computer-aided detection on observer performance in the reading of chest radiographs used a sequential reading design that may have biased the results because of reading order or recall bias. Purpose To compare observer performance in detecting and localizing major abnormal findings including nodules, consolidation, interstitial opacity, pleural effusion, and pneumothorax on chest radiographs without versus with deep learning-based detection (DLD) system assistance in a randomized crossover design. Materials and Methods This study included retrospectively collected normal and abnormal chest radiographs between January 2016 and December 2017 (https://cris.nih.go.kr/; registration no. KCT0004147). The radiographs were randomized into two groups, and six observers, including thoracic radiologists, interpreted each radiograph without and with use of a commercially available DLD system by using a crossover design with a washout period. Jackknife alternative free-response receiver operating characteristic (JAFROC) figure of merit (FOM), area under the receiver operating characteristic curve (AUC), sensitivity, specificity, false-positive findings per image, and reading times of observers with and without the DLD system were compared by using McNemar and paired t tests. Results A total of 114 normal (mean patient age ± standard deviation, 51 years ± 11; 58 men) and 114 abnormal (mean patient age, 60 years ± 15; 75 men) chest radiographs were evaluated. The radiographs were randomized to two groups: group A (n = 114) and group B (n = 114). Use of the DLD system improved the observers' JAFROC FOM (from 0.90 to 0.95, P = .002), AUC (from 0.93 to 0.98, P = .002), per-lesion sensitivity (from 83% [822 of 990 lesions] to 89.1% [882 of 990 lesions], P = .009), per-image sensitivity (from 80% [548 of 684 radiographs] to 89% [608 of 684 radiographs], P = .009), and specificity (from 89.3% [611 of 684 radiographs] to 96.6% [661 of 684 radiographs], P = .01) and reduced the reading time (from 10-65 seconds to 6-27 seconds, P < .001). The DLD system alone outperformed the pooled observers (JAFROC FOM: 0.96 vs 0.90, respectively, P = .007; AUC: 0.98 vs 0.93, P = .003). Conclusion Observers including thoracic radiologists showed improved performance in the detection and localization of major abnormal findings on chest radiographs and reduced reading time with use of a deep learning-based detection system. © RSNA, 2021 Online supplemental material is available for this article.

Dual energy imaging in cardiothoracic pathologies: A primer for radiologists and clinicians

Recent advances in dual-energy imaging techniques, dual-energy subtraction radiography (DESR) and dual-energy CT (DECT), offer new and useful additional information to conventional imaging, thus improving assessment of cardiothoracic abnormalities. DESR facilitates detection and characterization of pulmonary nodules. Other advantages of DESR include better depiction of pleural, lung parenchymal, airway and chest wall abnormalities, detection of foreign bodies and indwelling devices, improved visualization of cardiac and coronary artery calcifications helping in risk stratification of coronary artery disease, and diagnosing conditions like constrictive pericarditis and valvular stenosis. Commercially available DECT approaches are classified into emission based (dual rotation/spin, dual source, rapid kilovoltage switching and split beam) and detector-based (dual layer) systems. DECT provide several specialized image reconstructions. Virtual non-contrast images (VNC) allow for radiation dose reduction by obviating need for true non contrast images, low energy virtual mono-energetic images (VMI) boost contrast enhancement and help in salvaging otherwise non-diagnostic vascular studies, high energy VMI reduce beam hardening artifacts from metallic hardware or dense contrast material, and iodine density images allow quantitative and qualitative assessment of enhancement/iodine distribution. The large amount of data generated by DECT can affect interpreting physician efficiency but also limit clinical adoption of the technology. Optimization of the existing workflow and streamlining the integration between post-processing software and picture archiving and communication system (PACS) is therefore warranted.

Undetected Lung Cancer at Posteroanterior Chest Radiography: Potential Role of a Deep Learning-based Detection Algorithm

Purpose

To evaluate the performance of a deep learning-based algorithm in detecting lung cancers not reported on posteroanterior chest radiographs during routine practice.

Materials and Methods

The retrospective test dataset included 168 posteroanterior chest radiographs acquired between March 2017 and December 2018 (168 patients; mean age, 71.9 years ± 9.5 [standard deviation]; age range, 42-91 years) with 187 lung cancers (mean size, 2.3 cm ± 1.2) undetected during initial clinical evaluation, and 50 normal chest radiographs. CT served as the reference standard for ground truth. Four thoracic radiologists independently reevaluated the chest radiographs for lung nodules both without and with the aid of the algorithm. The performances of the algorithm and the radiologists were evaluated and compared on a per-chest radiograph basis and a per-lesion basis, according to the area under the receiver operating characteristic curve (AUROC) and area under the jackknife free-response ROC curve (AUFROC).

Results

The algorithm showed excellent diagnostic performances both in terms of per-chest radiograph classification (AUROC, 0.899) and per-lesion localization (AUFROC, 0.744); both of these values were significantly higher than those of the radiologists (AUROC, 0.634-0.663; AUFROC, 0.619-0.651; P < .001 for all). The algorithm also demonstrated higher sensitivity (69.6% [117 of 168] vs 47.0% [316 of 672]; P < .001) and specificity (94.0% [47 of 50] vs 78.0% [156 of 200]; P = .01). When assisted by the algorithm, the radiologists' AUROC (0.634-0.663 vs 0.685-0.724; P < 0.01 for all) and pooled AUFROC (0.636 vs 0.688; P = .03) substantially improved. The false-positive rate of the algorithm, that is, the total number of false-positive nodules divided by the total number of chest radiographs, was similar to that of pooled radiologists (21.1% [46 of 218] vs 19.0% [166 of 872]; P > .05).

Conclusion

A deep learning-based nodule detection algorithm showed excellent detection performance of lung cancers that were not reported on chest radiographs during routine practice and significantly reduced reading errors when used as a second reader.Supplemental material is available for this article.© RSNA, 2020See also commentary by White in this issue.

Reproducibility of abnormality detection on chest radiographs using convolutional neural network in paired radiographs obtained within a short-term interval

We evaluated the reproducibility of computer-aided detections (CADs) with a convolutional neural network (CNN) on chest radiographs (CXRs) of abnormal pulmonary patterns in patients, acquired within a short-term interval. Anonymized CXRs (n = 9792) obtained from 2010 to 2016 and comprising five types of disease patterns, including the nodule (N), consolidation (C), interstitial opacity (IO), pleural effusion (PLE), and pneumothorax (PN), were included. The number of normal and abnormal CXRs was 6068 and 3724, respectively. The number of CXRs (region of interests, ROIs) of N, C, IO, PLE, and PN was 944 (1092), 550 (721), 280 (538), 1361 (1661), and 589 (622), respectively. CXRs were randomly allocated to training, tuning, and test sets in 70:10:20 ratios. Two thoracic radiologists labeled and delineated the ROIs of each disease pattern. The CAD system was developed using eDenseYOLO. For the reproducibility evaluation of developed CAD, paired CXRs of various diseases (N = 121, C = 28, IO = 12, PLE = 67, and PN = 20), acquired within a short-term interval from the test sets without any changes confirmed by thoracic radiologists, were used to evaluate CAD reproducibility. Percent positive agreement (PPAs) and Chamberlain's percent positive agreement (CPPAs) were used to evaluate CAD reproducibility. The figure of merit (FOM) of five classes based on eDenseYOLO showed N-0.72 (0.68-0.75), C-0.41 (0.33-0.43), IO-0.97 (0.96-0.98), PLE-0.94 (0.92-95), and PN-0.87 (0.76-0.93). The PPAs of the five disease patterns including N, C, IO, PLE, and PN were 83.39%, 74.14%, 95.12%, 96.84%, and 84.58%, respectively, whereas the values of CPPAs were 71.70%, 59.13%, 91.16%, 93.91%, and 74.17%, respectively. The reproducibility of abnormal pulmonary patterns from CXRs, based on deep learning-based CAD, showed different results; this is important for assessing the reproducible performance of CAD in clinical settings.

Reproducibility of abnormality detection on chest radiographs using convolutional neural network in paired radiographs obtained within a short-term interval

We evaluated the reproducibility of computer-aided detections (CADs) with a convolutional neural network (CNN) on chest radiographs (CXRs) of abnormal pulmonary patterns in patients, acquired within a short-term interval. Anonymized CXRs (n = 9792) obtained from 2010 to 2016 and comprising five types of disease patterns, including the nodule (N), consolidation (C), interstitial opacity (IO), pleural effusion (PLE), and pneumothorax (PN), were included. The number of normal and abnormal CXRs was 6068 and 3724, respectively. The number of CXRs (region of interests, ROIs) of N, C, IO, PLE, and PN was 944 (1092), 550 (721), 280 (538), 1361 (1661), and 589 (622), respectively. CXRs were randomly allocated to training, tuning, and test sets in 70:10:20 ratios. Two thoracic radiologists labeled and delineated the ROIs of each disease pattern. The CAD system was developed using eDenseYOLO. For the reproducibility evaluation of developed CAD, paired CXRs of various diseases (N = 121, C = 28, IO = 12, PLE = 67, and PN = 20), acquired within a short-term interval from the test sets without any changes confirmed by thoracic radiologists, were used to evaluate CAD reproducibility. Percent positive agreement (PPAs) and Chamberlain’s percent positive agreement (CPPAs) were used to evaluate CAD reproducibility. The figure of merit (FOM) of five classes based on eDenseYOLO showed N-0.72 (0.68–0.75), C-0.41 (0.33–0.43), IO-0.97 (0.96–0.98), PLE-0.94 (0.92–95), and PN-0.87 (0.76–0.93). The PPAs of the five disease patterns including N, C, IO, PLE, and PN were 83.39%, 74.14%, 95.12%, 96.84%, and 84.58%, respectively, whereas the values of CPPAs were 71.70%, 59.13%, 91.16%, 93.91%, and 74.17%, respectively. The reproducibility of abnormal pulmonary patterns from CXRs, based on deep learning-based CAD, showed different results; this is important for assessing the reproducible performance of CAD in clinical settings.

The Role of the Expert Witness in Radiology: Challenges and Strategies for Overcoming Them

Expert witnesses provide an important service in malpractice cases in the United States because they educate the jury on the standards of care relevant to a particular case. In cases in which the defendant physician is a radiologist, the decision often rests on whether a retrospectively detected abnormality should have been perceived and reported, an "error of omission." Errors of omission are usually termed "perceptual" in the literature and are the most common cause of malpractice suits in radiology. Allegations often hinge on whether these errors represent a breach of duty by the defendant radiologist and whether they resulted in an injury to the plaintiff or patient. In short, jurors are asked to decide if the radiologist performed below the "standard of care," generally defined as that which a minimally competent, reasonable, or ordinary physician in the same field would do under similar circumstances. The authors describe challenges associated with being an expert witness and provide guidance to radiologists on how to address cases involving alleged perceptual errors.

A Bayesian Latent Class Model to Predict Kidney Obstruction in the Absence of Gold Standard

Kidney obstruction, if untreated in a timely manner, can lead to irreversible loss of renal function. A widely used technology for evaluations of kidneys with suspected obstruction is diuresis renography. However, it is generally very challenging for radiologists who typically interpret renography data in practice to build high level of competency due to the low volume of renography studies and insufficient training. Another challenge is that there is currently no gold standard for detection of kidney obstruction. Seeking to develop a computer-aided diagnostic (CAD) tool that can assist practicing radiologists to reduce errors in the interpretation of kidney obstruction, a recent study collected data from diuresis renography, interpretations on the renography data from highly experienced nuclear medicine experts as well as clinical data. To achieve the objective, we develop a statistical model that can be used as a CAD tool for assisting radiologists in kidney interpretation. We use a Bayesian latent class modeling approach for predicting kidney obstruction through the integrative analysis of time-series renogram data, expert ratings, and clinical variables. A nonparametric Bayesian latent factor regression approach is adopted for modeling renogram curves in which the coefficients of the basis functions are parameterized via the factor loadings dependent on the latent disease status and the extended latent factors that can also adjust for clinical variables. A hierarchical probit model is used for expert ratings, allowing for training with rating data from multiple experts while predicting with at most one expert, which makes the proposed model operable in practice. An efficient MCMC algorithm is developed to train the model and predict kidney obstruction with associated uncertainty. We demonstrate the superiority of the proposed method over several existing methods through extensive simulations. Analysis of the renal study also lends support to the usefulness of our model as a CAD tool to assist less experienced radiologists in the field.

Short-term Reproducibility of Pulmonary Nodule and Mass Detection in Chest Radiographs: Comparison among Radiologists and Four Different Computer-Aided Detections with Convolutional Neural Net

To investigate the reproducibility of computer-aided detection (CAD) for detection of pulmonary nodules and masses for consecutive chest radiographies (CXRs) of the same patient within a short-term period. A total of 944 CXRs (Chest PA) with nodules and masses, recorded between January 2010 and November 2016 at the Asan Medical Center, were obtained. In all, 1092 regions of interest for the nodules and mass were delineated using an in-house software. All CXRs were randomly split into 6:2:2 sets for training, development, and validation. Furthermore, paired follow-up CXRs (n = 121) acquired within one week in the validation set, in which expert thoracic radiologists confirmed no changes, were used to evaluate the reproducibility of CAD by two radiologists (R1 and R2). The reproducibility comparison of four different convolutional neural net algorithms and two chest radiologists (with 13- and 14-years' experience) was conducted. Model performances were evaluated by figure-of-merit (FOM) analysis of the jackknife free-response receiver operating curve and reproducibility rates were evaluated in terms of percent positive agreement (PPA) and Chamberlain's percent positive agreement (CPPA). Reproducibility analysis of the four CADs and R1 and R2 showed variations in the PPA and CPPA. Model performance of YOLO (You Only Look Once) v2 based eDenseYOLO showed a higher FOM (0.89; 0.85-0.93) than RetinaNet (0.89; 0.85-0.93) and atrous spatial pyramid pooling U-Net (0.85; 0.80-0.89). eDenseYOLO showed higher PPAs (97.87%) and CPPAs (95.80%) than Mask R-CNN, RetinaNet, ASSP U-Net, R1, and R2 (PPA: 96.52%, 94.23%, 95.04%, 96.55%, and 94.98%; CPPA: 93.18%, 89.09%, 90.57%, 93.33%, and 90.43%). There were moderate variations in the reproducibility of CAD with different algorithms, which likely indicates that measurement of reproducibility is necessary for evaluating CAD performance in actual clinical environments.

Missed lung cancer: when, where, and why?

Missed lung cancer is a source of concern among radiologists and an important medicolegal challenge. In 90% of the cases, errors in diagnosis of lung cancer occur on chest radiographs. It may be challenging for radiologists to distinguish a lung lesion from bones, pulmonary vessels, mediastinal structures, and other complex anatomical structures on chest radiographs. Nevertheless, lung cancer can also be overlooked on computed tomography (CT) scans, regardless of the context, either if a clinical or radiologic suspect exists or for other reasons. Awareness of the possible causes of overlooking a pulmonary lesion can give radiologists a chance to reduce the occurrence of this eventuality. Various factors contribute to a misdiagnosis of lung cancer on chest radiographs and on CT, often very similar in nature to each other. Observer error is the most significant one and comprises scanning error, recognition error, decision-making error, and satisfaction of search. Tumor characteristics such as lesion size, conspicuity, and location are also crucial in this context. Even technical aspects can contribute to the probability of skipping lung cancer, including image quality and patient positioning and movement. Albeit it is hard to remove missed lung cancer completely, strategies to reduce observer error and methods to improve technique and automated detection may be valuable in reducing its likelihood.

The imaging of small pulmonary nodules

Lung cancer is the leading cause of cancer death worldwide. The major goal in lung cancer research is the improvement of long-term survival. Pulmonary nodules have high clinical importance, they may not only prove to be an early manifestation of lung cancer, but decide to choose the right therapy. This review will introduce the development and current situation of several imaging examination methods: computed tomography (CT), positron emission tomography/computed tomography (PET/CT), endobronchial ultrasound (EBUS).

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.

Computer-aided detection system for chest radiography: reducing report turnaround times of examinations with abnormalities

BACKGROUND

The ability to give high priority to examinations with pathological findings could be very useful to radiologists with large work lists who wish to first evaluate the most critical studies. A computer-aided detection (CAD) system for identifying chest examinations with abnormalities has therefore been developed.

PURPOSE

To evaluate the effectiveness of a CAD system on report turnaround times of chest examinations with abnormalities.

MATERIAL AND METHODS

The CAD system was designed to automatically mark chest examinations with possible abnormalities in the work list of radiologists interpreting chest examinations. The system evaluation was performed in two phases: two radiologists interpreted the chest examinations without CAD in phase 1 and with CAD in phase 2. The time information recorded by the radiology information system was then used to calculate the turnaround times. All chest examinations were reviewed by two other radiologists and were divided into normal and abnormal groups. The turnaround times for the examinations with pathological findings with and without the CAD system assistance were compared.

RESULTS

The sensitivity and specificity of the CAD for chest abnormalities were 0.790 and 0.697, respectively, and use of the CAD system decreased the turnaround time for chest examinations with abnormalities by 44%.

CONCLUSION

The turnaround times required for radiologists to identify chest examinations with abnormalities could be reduced by using the CAD system. This system could be useful for radiologists with large work lists who wish to first evaluate the most critical studies.

Potential clinical impact of advanced imaging and computer-aided diagnosis in chest radiology: importance of radiologist's role and successful observer study

This review paper is based on our research experience in the past 30 years. The importance of radiologists' role is discussed in the development or evaluation of new medical images and of computer-aided detection (CAD) schemes in chest radiology. The four main topics include (1) introducing what diseases can be included in a research database for different imaging techniques or CAD systems and what imaging database can be built by radiologists, (2) understanding how radiologists' subjective judgment can be combined with technical objective features to improve CAD performance, (3) sharing our experience in the design of successful observer performance studies, and (4) finally, discussing whether the new images and CAD systems can improve radiologists' diagnostic ability in chest radiology. In conclusion, advanced imaging techniques and detection/classification of CAD systems have a potential clinical impact on improvement of radiologists' diagnostic ability, for both the detection and the differential diagnosis of various lung diseases, in chest radiology.

Computer-aided nodule detection system: results in an unselected series of consecutive chest radiographs

RATIONALE AND OBJECTIVES

To evaluate the performance of a computer-aided detection (CAD) system with bone suppression imaging when applied to unselected consecutive chest radiographs (CXRs) with computed tomography (CT) correlation.

MATERIALS AND METHODS

This study included 586 consecutive patients with standard or portable CXRs who had a chest CT scan on the same day. Among the 586 CXRs, 438 had various abnormalities, including 46 CXRs with 66 lung nodules, and 148 CXRs had no significant abnormalities. A commercially available CAD system was applied to all 586 CXRs. True nodules and false positives (FPs) marked on CXRs by the CAD system were evaluated based on the corresponding chest CT findings.

RESULTS

The CAD system marked 47 of 66 (71%) lung nodules in this consecutive series of CXRs. The mean FP rate per image was 1.3 across all 586 CXRs, with 1.5 FPs per image on the 438 abnormal CXRs and 0.8 FPs per image on the 148 normal CXRs. A total of 41% of the 752 FP marks were related to non-nodule pathologic findings.

CONCLUSIONS

A currently available CAD system marked 71% of radiologist-identified lung nodules in a large consecutive series of CXRs, and 41% of "false" marks were caused by pathologic findings.

[Detection of lung nodules. New opportunities in chest radiography]

BACKGROUND

Chest radiography still represents the most commonly performed X-ray examination because it is readily available, requires low radiation doses and is relatively inexpensive. However, as previously published, many initially undetected lung nodules are retrospectively visible in chest radiographs.

STANDARD RADIOLOGICAL METHODS

The great improvements in detector technology with the increasing dose efficiency and improved contrast resolution provide a better image quality and reduced dose needs.

METHODICAL INNOVATIONS

The dual energy acquisition technique and advanced image processing methods (e.g. digital bone subtraction and temporal subtraction) reduce the anatomical background noise by reduction of overlapping structures in chest radiography. Computer-aided detection (CAD) schemes increase the awareness of radiologists for suspicious areas.

RESULTS

The advanced image processing methods show clear improvements for the detection of pulmonary lung nodules in chest radiography and strengthen the role of this method in comparison to 3D acquisition techniques, such as computed tomography (CT).

ASSESSMENT

Many of these methods will probably be integrated into standard clinical treatment in the near future. Digital software solutions offer advantages as they can be easily incorporated into radiology departments and are often more affordable as compared to hardware solutions.

Comparison of dual-energy subtraction and electronic bone suppression combined with computer-aided detection on chest radiographs: effect on human observers' performance in nodule detection

OBJECTIVE

The objective of our study was to compare the effect of dual-energy subtraction and bone suppression software alone and in combination with computer-aided detection (CAD) on the performance of human observers in lung nodule detection.

MATERIALS AND METHODS

One hundred one patients with from one to five lung nodules measuring 5-29 mm and 42 subjects with no nodules were retrospectively selected and randomized. Three independent radiologists marked suspicious-appearing lesions on the original chest radiographs, dual-energy subtraction images, and bone-suppressed images before and after postprocessing with CAD. Marks of the observers and CAD marks were compared with CT as the reference standard. Data were analyzed using nonparametric tests and the jackknife alternative free-response receiver operating characteristic (JAFROC) method.

RESULTS

Using dual-energy subtraction alone (p = 0.0198) or CAD alone (p = 0.0095) improved the detection rate compared with using the original conventional chest radiograph. The combination of bone suppression and CAD provided the highest sensitivity (51.6%) and the original nonenhanced conventional chest radiograph alone provided the lowest (46.9%; p = 0.0049). Dual-energy subtraction and bone suppression provided the same false-positive (p = 0.2702) and true-positive (p = 0.8451) rates. Up to 22.9% of lesions were found only by the CAD program and were missed by the readers. JAFROC showed no difference in the performance between modalities (p = 0.2742-0.5442).

CONCLUSION

Dual-energy subtraction and the electronic bone suppression program used in this study provided similar detection rates for pulmonary nodules. Additionally, CAD alone or combined with bone suppression can significantly improve the sensitivity of human observers for pulmonary nodule detection.

Missed lung cancer on chest radiography and computed tomography

Missed lung cancer raises an important medicolegal issue and contributes to one of the most common causes for malpractice actions against radiologists. Lung cancer may be missed on either chest radiography or computed tomography. Although most malpractice cases involve lesions overlooked on the former, a small and increasing portion of cases are related to chest computed tomography scan. Factors contributing to overlooked lung cancer can be attributed to observer performance, lesion characteristics, and technical considerations.

Automatic detection of lesions in lung regions that are segmented using spatial relations

This article presents a novel approach for the automatic detection of lesions and selection of features on chest radiographs. We have illustrated the importance of accurate segmentation, which is based on spatial relationships between the lung structures, as a preprocessing step in a Computer Aided Diagnosis (CAD) scheme. Then, three suitable combinations of features have been identified using the forward stepwise selection method from the original images and their transformed ones. Experimental results show that our segmentation approach and the suppression of skeletal structures improve the detection accuracy. The selected features can describe efficiently different kinds of chest lesions.

Computer-aided detection of malignant lung nodules on chest radiographs: effect on observers' performance

Objective

To evaluate the effect of computer-aided detection (CAD) system on observer performance in the detection of malignant lung nodules on chest radiograph.

Materials and Methods

Two hundred chest radiographs (100 normal and 100 abnormal with malignant solitary lung nodules) were evaluated. With CT and histological confirmation serving as a reference, the mean nodule size was 15.4 mm (range, 7-20 mm). Five chest radiologists and five radiology residents independently interpreted both the original radiographs and CAD output images using the sequential testing method. The performances of the observers for the detection of malignant nodules with and without CAD were compared using the jackknife free-response receiver operating characteristic analysis.

Results

Fifty-nine nodules were detected by the CAD system with a false positive rate of 1.9 nodules per case. The detection of malignant lung nodules significantly increased from 0.90 to 0.92 for a group of observers, excluding one first-year resident (p = 0.04). When lowering the confidence score was not allowed, the average figure of merit also increased from 0.90 to 0.91 (p = 0.04) for all observers after a CAD review. On average, the sensitivities with and without CAD were 87% and 84%, respectively; the false positive rates per case with and without CAD were 0.19 and 0.17, respectively. The number of additional malignancies detected following true positive CAD marks ranged from zero to seven for the various observers.

Conclusion

The CAD system may help improve observer performance in detecting malignant lung nodules on chest radiographs and contribute to a decrease in missed lung cancer.

Potential of computer-aided diagnosis to improve CT lung cancer screening

The development of low-dose spiral computed tomography (CT) has rekindled hope that effective lung cancer screening might yet be found. Screening is justified when there is evidence that it will extend lives at reasonable cost and acceptable levels of risk. A screening test should detect all extant cancers while avoiding unnecessary workups. Thus optimal screening modalities have both high sensitivity and specificity. Due to the present state of technology, radiologists must opt to increase sensitivity and rely on follow-up diagnostic procedures to rule out the incurred false positives. There is evidence in published reports that computer-aided diagnosis technology may help radiologists alter the benefit-cost calculus of CT sensitivity and specificity in lung cancer screening protocols. This review will provide insight into the current discussion of the effectiveness of lung cancer screening and assesses the potential of state-of-the-art computer-aided design developments.

Observer training for computer-aided detection of pulmonary nodules in chest radiography

OBJECTIVES

To assess whether short-term feedback helps readers to increase their performance using computer-aided detection (CAD) for nodule detection in chest radiography.

METHODS

The 140 CXRs (56 with a solitary CT-proven nodules and 84 negative controls) were divided into four subsets of 35; each were read in a different order by six readers. Lesion presence, location and diagnostic confidence were scored without and with CAD (IQQA-Chest, EDDA Technology) as second reader. Readers received individual feedback after each subset. Sensitivity, specificity and area under the receiver-operating characteristics curve (AUC) were calculated for readings with and without CAD with respect to change over time and impact of CAD.

RESULTS

CAD stand-alone sensitivity was 59 % with 1.9 false-positives per image. Mean AUC slightly increased over time with and without CAD (0.78 vs. 0.84 with and 0.76 vs. 0.82 without CAD) but differences did not reach significance. The sensitivity increased (65 % vs. 70 % and 66 % vs. 70 %) and specificity decreased over time (79 % vs. 74 % and 80 % vs. 77 %) but no significant impact of CAD was found.

CONCLUSION

Short-term feedback does not increase the ability of readers to differentiate true- from false-positive candidate lesions and to use CAD more effectively.

KEY POINTS

• Computer-aided detection (CAD) is increasingly used as an adjunct for many radiological techniques. • Short-term feedback does not improve reader performance with CAD in chest radiography. • Differentiation between true- and false-positive CAD for low conspicious possible lesions proves difficult. • CAD can potentially increase reader performance for nodule detection in chest radiography.

Content-based image-retrieval system in chest computed tomography for a solitary pulmonary nodule: method and preliminary experiments

PURPOSE

The aim of this study was to develop a new diagnostic support system using content-based image-retrieval technology. In this article, we describe the mechanism and preliminary evaluation of this system for use with CT images of solitary pulmonary nodules.

MATERIALS AND METHODS

With the approval of the institutional review board of Shizuoka Cancer Center, we built a database that included CT images of 461 solitary pulmonary nodules. With this database, we developed a system that automatically extracts the pulmonary nodule when the nodule area is clicked, retrieves previous cases based on an image analysis of the extracted lesion, and generates reports of the pulmonary nodule semi-automatically. We compared the percentage of correct diagnoses with and without the system using 30 solitary pulmonary nodules, which were not included in the database, with one radiologist and two residents. As a per-user evaluation, the number of clicks required to extract the nodule region and the extracted regions was compared, and presented candidate cases were evaluated. As an evaluation of the retrieval results, the presented candidate cases were evaluated by comparing the number of diagnostic matches (benign/malignant) between the queries and four presented cases. Additionally, to evaluate the validity of the retrieval technology, the radiologist selected the most similar cases presented by the system and evaluated the visual similarity on a five-point scale.

RESULTS

With this system, the percentage of correct diagnoses for the radiologist improved from 80 to 93%. For the two residents, the diagnostic accuracy improved from 66.7 to 80% and from 76.7 to 90%, respectively. The evaluation of the number of clicks required indicated that for 19 cases with the radiologist and 12 and 11 cases with the two residents, respectively, only one click was required to extract the region. When the extracted regions were compared between the radiologist and the residents, 22 and 19 cases had a Dice's Coefficient of 0.85 or higher, respectively. For the radiologist, the number of cases that matched the diagnosis (benign/malignant) averaged 3.7 ± 0.5 among 23 malignant cases and 1.7 ± 1.4 among 7 benign cases, while for the residents, these values were 3.6 ± 0.5 and 1.1 ± 0.9, and 3.4 ± 0.8 and 1.1 ± 1.3, respectively. With regard to visual evaluations by the radiologist, there were 15 similar cases and 11 somewhat similar cases.

CONCLUSION

These results suggest that, despite some differences in the search results among the users, this system has been confirmed that it can improve the accuracy of diagnosis as it displays similar cases at high probability. In addition, with the use of this system, past cases and their reports can be effectively referred to. Therefore, this diagnostic-assistant system has the potential to improve the efficiency of the CT image-reading workflow.

Computer-aided detection of small pulmonary nodules in chest radiographs: an observer study

RATIONALE AND OBJECTIVES

To evaluate the impact of computer-aided detection (CAD, IQQA-Chest; EDDA Technology, Princeton Junction, NJ) used as second reader on the detection of small pulmonary nodules in chest radiography (CXR).

MATERIALS AND METHODS

A total of 113 patients (mean age 62 years) with CT and CXR within 6 weeks were selected. Fifty-nine patients showed 101 pulmonary nodules (diameter 5-15mm); the remaining 54 patients served as negative controls. Six readers of varying experience individually evaluated the CXR without and with CAD as second reader in two separate reading sessions. The sensitivity per lesion, figure of merit (FOM), and mean false positive per image (mFP) were calculated. Institutional review board approval was waived.

RESULTS

With CAD, the sensitivity increased for inexperienced readers (39% vs. 45%, P < .05) and remained unchanged for experienced readers (50% vs. 51%). The mFP nonsignificantly increased for both inexperienced and experienced readers (0.27 vs. 0.34 and 0.16 vs. 0.21). The mean FOM did not significantly differ for readings without and with CAD irrespective of reader experience (0.71 vs. 0.71 and 0.84 vs. 0.87). All readers together dismissed 33% of true-positive CAD candidates. False-positive candidates by CAD provoked 40% of all false-positive marks made by the readers.

CONCLUSION

CAD improves the sensitivity of inexperienced readers for the detection of small nodules at the expense of loss of specificity. Overall performance by means of FOM was therefore not affected. To use CAD more beneficial, readers need to improve their ability to differentiate true from false-positive CAD candidates.

Small lung cancers: improved detection by use of bone suppression imaging--comparison with dual-energy subtraction chest radiography

PURPOSE

To determine whether use of bone suppression (BS) imaging, used together with a standard radiograph, could improve radiologists' performance for detection of small lung cancers compared with use of standard chest radiographs alone and whether BS imaging would provide accuracy equivalent to that of dual-energy subtraction (DES) radiography.

MATERIALS AND METHODS

Institutional review board approval was obtained. The requirement for informed consent was waived. The study was HIPAA compliant. Standard and DES chest radiographs of 50 patients with 55 confirmed primary nodular cancers (mean diameter, 20 mm) as well as 30 patients without cancers were included in the observer study. A new BS imaging processing system that can suppress the conspicuity of bones was applied to the standard radiographs to create corresponding BS images. Ten observers, including six experienced radiologists and four radiology residents, indicated their confidence levels regarding the presence or absence of a lung cancer for each lung, first by using a standard image, then a BS image, and finally DES soft-tissue and bone images. Receiver operating characteristic (ROC) analysis was used to evaluate observer performance.

RESULTS

The average area under the ROC curve (AUC) for all observers was significantly improved from 0.807 to 0.867 with BS imaging and to 0.916 with DES (both P < .001). The average AUC for the six experienced radiologists was significantly improved from 0.846 with standard images to 0.894 with BS images (P < .001) and from 0.894 to 0.945 with DES images (P = .001).

CONCLUSION

Use of BS imaging together with a standard radiograph can improve radiologists' accuracy for detection of small lung cancers on chest radiographs. Further improvements can be achieved by use of DES radiography but with the requirement for special equipment and a potential small increase in radiation dose.

Computer-aided diagnosis of renal obstruction: utility of log-linear modeling versus standard ROC and kappa analysis

Background

The accuracy of computer-aided diagnosis (CAD) software is best evaluated by comparison to a gold standard which represents the true status of disease. In many settings, however, knowledge of the true status of disease is not possible and accuracy is evaluated against the interpretations of an expert panel. Common statistical approaches to evaluate accuracy include receiver operating characteristic (ROC) and kappa analysis but both of these methods have significant limitations and cannot answer the question of equivalence: Is the CAD performance equivalent to that of an expert? The goal of this study is to show the strength of log-linear analysis over standard ROC and kappa statistics in evaluating the accuracy of computer-aided diagnosis of renal obstruction compared to the diagnosis provided by expert readers.

Methods

Log-linear modeling was utilized to analyze a previously published database that used ROC and kappa statistics to compare diuresis renography scan interpretations (non-obstructed, equivocal, or obstructed) generated by a renal expert system (RENEX) in 185 kidneys (95 patients) with the independent and consensus scan interpretations of three experts who were blinded to clinical information and prospectively and independently graded each kidney as obstructed, equivocal, or non-obstructed.

Results

Log-linear modeling showed that RENEX and the expert consensus had beyond-chance agreement in both non-obstructed and obstructed readings (both p < 0.0001). Moreover, pairwise agreement between experts and pairwise agreement between each expert and RENEX were not significantly different (p = 0.41, 0.95, 0.81 for the non-obstructed, equivocal, and obstructed categories, respectively). Similarly, the three-way agreement of the three experts and three-way agreement of two experts and RENEX was not significantly different for non-obstructed (p = 0.79) and obstructed (p = 0.49) categories.

Conclusion

Log-linear modeling showed that RENEX was equivalent to any expert in rating kidneys, particularly in the obstructed and non-obstructed categories. This conclusion, which could not be derived from the original ROC and kappa analysis, emphasizes and illustrates the role and importance of log-linear modeling in the absence of a gold standard. The log-linear analysis also provides additional evidence that RENEX has the potential to assist in the interpretation of diuresis renography studies.

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.

Performance of radiologists in detection of small pulmonary nodules on chest radiographs: effect of rib suppression with a massive-training artificial neural network

OBJECTIVE

A massive-training artificial neural network is a nonlinear pattern recognition tool used to suppress rib opacity on chest radiographs while soft-tissue contrast is maintained. We investigated the effect of rib suppression with a massive-training artificial neural network on the performance of radiologists in the detection of pulmonary nodules on chest radiographs.

MATERIALS AND METHODS

We used 60 chest radiographs; 30 depicted solitary pulmonary nodules, and 30 showed no nodules. A stratified random-sampling scheme was used to select the images from the standard digital image database developed by the Japanese Society of Radiologic Technology. The mean diameter of the 30 pulmonary nodules was 14.7 +/- 4.1 (SD) mm. Receiver operating characteristic analysis was used to evaluate observer performance in the detection of pulmonary nodules first on the chest radiographs without and then on the radiographs with rib suppression. Seven board-certified radiologists and five radiology residents participated in this observer study.

RESULTS

For all 12 observers, the mean values of the area under the best-fit receiver operating characteristic curve for images without and with rib suppression were 0.816 +/- 0.077 and 0.843 +/- 0.074; the difference was statistically significant (p = 0.019). The mean areas under the curve for images without and with rib suppression were 0.848 +/- 0.059 and 0.883 +/- 0.050 for the seven board-certified radiologists (p = 0.011) and 0.770 +/- 0.081 and 0.788 +/- 0.074 for the five radiology residents (p = 0.310).

CONCLUSION

In the detection of pulmonary nodules, evaluation of a combination of rib-suppressed and original chest radiographs significantly improved the diagnostic performance of radiologists over the use of chest radiographs alone.

Improved detection of pulmonary nodules on energy-subtracted chest radiographs with a commercial computer-aided diagnosis software: comparison with human observers

OBJECTIVE

To retrospectively analyze the performance of a commercial computer-aided diagnosis (CAD) software in the detection of pulmonary nodules in original and energy-subtracted (ES) chest radiographs.

METHODS

Original and ES chest radiographs of 58 patients with 105 pulmonary nodules measuring 5-30 mm and images of 25 control subjects with no nodules were randomized. Five blinded readers evaluated firstly the original postero-anterior images alone and then together with the subtracted radiographs. In a second phase, original and ES images were analyzed by a commercial CAD program. CT was used as reference standard. CAD results were compared to the readers' findings. True-positive (TP) and false-positive (FP) findings with CAD on subtracted and non-subtracted images were compared.

RESULTS

Depending on the reader's experience, CAD detected between 11 and 21 nodules missed by readers. Human observers found three to 16 lesions missed by the CAD software. CAD used with ES images produced significantly fewer FPs than with non-subtracted images: 1.75 and 2.14 FPs per image, respectively (p = 0.029). The difference for the TP nodules was not significant (40 nodules on ES images and 34 lesions in non-subtracted radiographs, p = 0.142).

CONCLUSION

CAD can improve lesion detection both on energy subtracted and non-subtracted chest images, especially for less experienced readers. The CAD program marked less FPs on energy-subtracted images than on original chest radiographs.

Computer-aided detection (CAD) of lung nodules and small tumours on chest radiographs

Detection of focal pulmonary lesions is limited by quantum and anatomic noise and highly influenced by variable perception capacity of the reader. Multiple studies have proven that lesions - missed at time of primary interpretation - were visible on the chest radiographs in retrospect. Computer-aided diagnosis (CAD) schemes do not alter the anatomic noise but aim at decreasing the intrinsic limitations and variations of human perception by alerting the reader to suspicious areas in a chest radiograph when used as a 'second reader'. Multiple studies have shown that the detection performance can be improved using CAD especially for less experienced readers at a variable amount of decreased specificity. There seem to be a substantial learning process for both, experienced and inexperienced readers, to be able to optimally differentiate between false positive and true positive lesions and to build up sufficient trust in the capabilities of these systems to be able to use them at their full advantage. Studies so far focussed on stand-alone performance of the CAD schemes to reveal the magnitude of potential impact or on retrospective evaluation of CAD as a second reader for selected study groups. Further research is needed to assess the performance of these systems in clinical routine and to determine the trade-off between performance increase in terms of increased sensitivity and decreased inter-reader variability and loss of specificity and secondary indicated follow-up examinations for further diagnostic workup.

Use of a computer-aided detection system to detect missed lung cancer at chest radiography

PURPOSE

To study the ability of a computer-aided detection (CAD) system to detect lung cancer overlooked at initial interpretation by the radiologist.

MATERIALS AND METHODS

Institutional review board approval was given for this study. Patient consent was not required; a HIPAA waiver was granted because of the retrospective nature of the data collection. In patients with lung cancer diagnosed from 1995 to 2006 at two institutions, each chest radiograph obtained prior to tumor discovery was evaluated by two radiologists for an overlooked lesion. The size and location of the nodules were documented and graded for subtlety (grades 1-4, 1 = very subtle). Each radiograph with a missed lesion was analyzed by a commercial CAD system, as was the follow-up image at diagnosis. An age- and sex-matched control group was used to assess CAD false-positive rates.

RESULTS

Missed lung cancer was found in 89 patients (age range, 51-86 years; mean age, 65 years; 80 men, nine women) on 114 radiographs. Lesion size ranged from 0.4 to 5.5 cm (mean, 1.8 cm). Lesions were most commonly peripheral (n = 63, 71%) and in upper lobes (n = 67, 75%). Lesion subtlety score was 1, 2, 3, or 4 on 43, 49, 17, and five radiographs, respectively. CAD identified 53 (47%) and 46 (52%) undetected lesions on a per-image and per-patient basis, respectively. The average size of lesions detected with CAD was 1.73 cm compared with 1.85 cm for lesions that were undetected (P = .47). A significant difference (P = .017) was found in the average subtlety score between detected lesions (score, 2.06) and undetected lesions (score, 1.68). An average of 3.9 false-positive results occurred per radiograph; an average of 2.4 false-positive results occurred per radiograph for the control group.

CONCLUSION

CAD has the potential to detect approximately half of the lesions overlooked by human readers at chest radiography.

Temporal subtraction chest radiography

Radiologist are commonly required to compare a sequence of two or more chest radiographs of a given patient obtained over a period of time, which may range from a few hours to many years. In such cases, the task is one of detecting interval change. In the case of patients who have had a previous chest radiograph, an opportunity exists to enhance selectively areas of interval change, including regions with new or altered pathology, by using the previous radiographs as a subtraction mask. With temporal subtraction, the previous image is superimposed and registered with the current image, using automated two-dimensional warping to compensate for any differences in positioning. A "difference image" is then created, by subtracting the previous from the current radiograph. In this temporal subtraction image, areas that are unchanged appear as uniform gray, while regions of new opacity, such as due to pneumonia or cancer, appear as prominent dark foci on a lighter background. By cancelling out the complex anatomical background, temporal subtraction can provide dramatically enhanced visibility of new areas of disease.

True detection versus "accidental" detection of small lung cancer by a computer-aided detection (CAD) program on chest radiographs

To evaluate the number of actual detections versus "accidental" detections by a computer-aided detection (CAD) system for small nodular lung cancers (<or=30 mm) on chest radiographs, using two different criteria for measuring performance. A Food-and-Drug-Administration-approved CAD program (version 1.0; Riverain Medical) was applied to 34 chest radiographs with a "radiologist-missed" nodular cancer and 36 radiographs with a radiologist-mentioned nodule (a newer version 3.0 was also applied to the 36-case database). The marks applied by this CAD system consisted of 5-cm-diameter circles. A strict "nodule-in-center" criterion and a generous "nodule-in-circle" criterion were compared as methods for the calculation of CAD sensitivity. The increased sensitivities by the nodule-in-circle criterion were considered as nodules detected by chance. The number of false-positive (FP) marks was also analyzed. For the 34 radiologist-missed cancers, the nodule-in-circle criterion caused eight more cancers (24%) to be detected by chance, as compared to the nodule-in-center criterion, when using the version 1.0 results. For the 36 radiologist-mentioned nodules, the nodule-in-circle criterion caused seven more lesions (19%) to be detected by chance, as compared to the nodule-in-center criterion, when using the version 1.0 results, and three more lesions (8%) to be detected by chance when using the version 3.0 results. Version 1.0 yielded a mean of six FP marks per image, while version 3.0 yielded only three FP marks per image. The specific criteria used to define true- and false-positive CAD detections can substantially influence the apparent accuracy of a CAD system.

Design and Development of a New Multi-Projection X-Ray System for Chest Imaging

Overlapping anatomical structures may confound the detection of abnormal pathology, including lung nodules, in conventional single-projection chest radiography. To minimize this fundamental limiting factor, a dedicated digital multi-projection system for chest imaging was recently developed at the Radiology Department of Duke University. We are reporting the design of the multi-projection imaging system and its initial performance in an ongoing clinical trial. The system is capable of acquiring multiple full-field projections of the same patient along both the horizontal and vertical axes at variable speeds and acquisition frame rates. These images acquired in rapid succession from slightly different angles about the posterior-anterior (PA) orientation can be correlated to minimize the influence of overlying anatomy. The developed system has been tested for repeatability and motion blur artifacts to investigate its robustness for clinical trials. Excellent geometrical consistency was found in the tube motion, with positional errors for clinical settings within 1%. The effect of tube-motion on the image quality measured in terms of impact on the Modulation Transfer Function (MTF) was found to be minimal. The system was deemed clinic-ready and a clinical trial was subsequently launched. The flexibility of image acquisition built into the system provides a unique opportunity to easily modify it for different clinical applications, including tomosynthesis, correlation imaging (CI), and stereoscopic imaging.

Improved detection of small lung cancers with dual-energy subtraction chest radiography

OBJECTIVE

The objective of our study was to retrospectively evaluate whether the use of dual-energy subtraction chest radiographs can improve radiologists' performance for the detection of small previously missed lung cancers.

MATERIALS AND METHODS

Dual-energy subtraction chest radiographs of 19 patients with previously missed nodular cancers, in which the radiology report did not mention a nodule that was visible in retrospect, were selected. Dual-energy subtraction radiographs of 19 patients with cancer and 16 patients without cancer were used for an observer study. Six radiologists indicated their confidence level regarding the presence of a lung cancer and, if they thought a cancer was present, also marked the most likely position for each lung, first using standard posteroanterior and lateral chest radiographs and then using both soft-tissue and bone dual-energy subtraction images along with standard radiographs. Receiver operating characteristic (ROC) curves were used to evaluate the observers' performance. The indicated locations of cancers and false-positives were also analyzed.

RESULTS

The average area under the ROC curve (A(z)) value for the six radiologists was improved from 0.718 to 0.816, a statistically significant amount (p = 0.004), and the average sensitivity (correct localizations) for 19 previously missed cancers was also significantly improved from 40% to 59% (p = 0.008) with the aid of dual-energy subtraction images. The average number of false-positive (incorrect) localizations on 70 lungs was 10 without and nine with dual-energy subtraction images (p = 0.785).

CONCLUSION

Dual-energy subtraction chest radiography has the potential to improve radiologists' performance for the detection of small missed lung cancers.