Computer-aided diagnosis for lung cancer

Performance of an Artificial Intelligence-Based Platform Against Clinical Radiology Reports for the Evaluation of Noncontrast Chest CT

RATIONALE AND OBJECTIVES

Research on implementation of artificial intelligence (AI) in radiology workflows and its impact on reports remains scarce. In this study, we aim to assess if an AI platform would perform better than clinical radiology reports in evaluating noncontrast chest computed tomography (CT) scans.

MATERIALS AND METHODS

Consecutive patients who had undergone noncontrast chest CT were retrospectively identified. The radiology reports were reviewed in a binary fashion for reporting of pulmonary lesions, pulmonary emphysema, aortic dilatation, coronary artery calcifications (CAC), and vertebral compression fractures (VCF). CT scans were then processed using an AI platform. The reports' findings and the AI results were subsequently compared to a consensus read by two board-certificated radiologists as reference.

RESULTS

A total of 100 patients (mean age: 64.2 ± 14.8 years; 57% males) were included in this study. Aortic segmentation and calcium quantification failed to be processed by AI in 2 and 3 cases, respectively. AI showed superior diagnostic performance in identifying aortic dilatation (AI: sensitivity: 96.3%, specificity: 81.4%, AUC: 0.89) vs (Reports: sensitivity: 25.9%, specificity: 100%, AUC: 0.63), p <0.001; and CAC (AI: sensitivity: 89.8%, specificity: 100, AUC: 0.95) vs (Reports: sensitivity: 75.4%, specificity: 94.9%, AUC: 0.85), p = 0.005. Reports had better performance than AI in identifying pulmonary lesions (Reports: sensitivity: 97.6%, specificity: 100%, AUC: 0.99) vs (AI: sensitivity: 92.8%, specificity: 82.4%, AUC: 0.88), p = 0.024; and VCF (Reports: sensitivity:100%, specificity: 100%, AUC: 1.0) vs (AI: sensitivity: 100%, specificity: 63.7%, AUC: 0.82), p <0.001. A comparable diagnostic performance was noted in identifying pulmonary emphysema on AI (sensitivity: 80.6%, specificity: 66.7%. AUC: 0.74) and reports (sensitivity: 74.2%, specificity: 97.1%, AUC: 0.86), p = 0.064.

CONCLUSION

Our results demonstrate that incorporating AI support platforms into radiology workflows can provide significant added value to clinical radiology reporting.

Lungs nodule detection framework from computed tomography images using support vector machine

The emergence of cloud infrastructure has the potential to provide significant benefits in a variety of areas in the medical imaging field. The driving force behind the extensive use of cloud infrastructure for medical image processing is the exponential increase in the size of computed tomography (CT) and magnetic resonance imaging (MRI) data. The size of a single CT/MRI image has increased manifold since the inception of these imagery techniques. This demand for the introduction of effective and efficient frameworks for extracting relevant and most suitable information (features) from these sizeable images. As early detection of lungs cancer can significantly increase the chances of survival of a lung scanner patient, an effective and efficient nodule detection system can play a vital role. In this article, we have proposed a novel classification framework for lungs nodule classification with less false positive rates (FPRs), high accuracy, sensitivity rate, less computationally expensive and uses a small set of features while preserving edge and texture information. The proposed framework comprises multiple phases that include image contrast enhancement, segmentation, feature extraction, followed by an employment of these features for training and testing of a selected classifier. Image preprocessing and feature selection being the primary steps-playing their vital role in achieving improved classification accuracy. We have empirically tested the efficacy of our technique by utilizing the well-known Lungs Image Consortium Database dataset. The results prove that the technique is highly effective for reducing FPRs with an impressive sensitivity rate of 97.45%.

The UK Lung Cancer Screening Trial: a pilot randomised controlled trial of low-dose computed tomography screening for the early detection of lung cancer

BACKGROUND

Lung cancer kills more people than any other cancer in the UK (5-year survival < 13%). Early diagnosis can save lives. The USA-based National Lung Cancer Screening Trial reported a 20% relative reduction in lung cancer mortality and 6.7% all-cause mortality in low-dose computed tomography (LDCT)-screened subjects.

OBJECTIVES

To (1) analyse LDCT lung cancer screening in a high-risk UK population, determine optimum recruitment, screening, reading and care pathway strategies; and (2) assess the psychological consequences and the health-economic implications of screening.

DESIGN

A pilot randomised controlled trial comparing intervention with usual care. A population-based risk questionnaire identified individuals who were at high risk of developing lung cancer (≥ 5% over 5 years).

SETTING

Thoracic centres with expertise in lung cancer imaging, respiratory medicine, pathology and surgery: Liverpool Heart & Chest Hospital, Merseyside, and Papworth Hospital, Cambridgeshire.

PARTICIPANTS

Individuals aged 50-75 years, at high risk of lung cancer, in the primary care trusts adjacent to the centres.

INTERVENTIONS

A thoracic LDCT scan. Follow-up computed tomography (CT) scans as per protocol. Referral to multidisciplinary team clinics was determined by nodule size criteria.

MAIN OUTCOME MEASURES

Population-based recruitment based on risk stratification; management of the trial through web-based database; optimal characteristics of CT scan readers (radiologists vs. radiographers); characterisation of CT-detected nodules utilising volumetric analysis; prevalence of lung cancer at baseline; sociodemographic factors affecting participation; psychosocial measures (cancer distress, anxiety, depression, decision satisfaction); and cost-effectiveness modelling.

RESULTS

A total of 247,354 individuals were approached to take part in the trial; 30.7% responded positively to the screening invitation. Recruitment of participants resulted in 2028 in the CT arm and 2027 in the control arm. A total of 1994 participants underwent CT scanning: 42 participants (2.1%) were diagnosed with lung cancer; 36 out of 42 (85.7%) of the screen-detected cancers were identified as stage 1 or 2, and 35 (83.3%) underwent surgical resection as their primary treatment. Lung cancer was more common in the lowest socioeconomic group. Short-term adverse psychosocial consequences were observed in participants who were randomised to the intervention arm and in those who had a major lung abnormality detected, but these differences were modest and temporary. Rollout of screening as a service or design of a full trial would need to address issues of outreach. The health-economic analysis suggests that the intervention could be cost-effective but this needs to be confirmed using data on actual lung cancer mortality.

CONCLUSIONS

The UK Lung Cancer Screening (UKLS) pilot was successfully undertaken with 4055 randomised individuals. The data from the UKLS provide evidence that adds to existing data to suggest that lung cancer screening in the UK could potentially be implemented in the 60-75 years age group, selected via the Liverpool Lung Project risk model version 2 and using CT volumetry-based management protocols.

FUTURE WORK

The UKLS data will be pooled with the NELSON (Nederlands Leuvens Longkanker Screenings Onderzoek: Dutch-Belgian Randomised Lung Cancer Screening Trial) and other European Union trials in 2017 which will provide European mortality and cost-effectiveness data. For now, there is a clear need for mortality results from other trials and further research to identify optimal methods of implementation and delivery. Strategies for increasing uptake and providing support for underserved groups will be key to implementation.

TRIAL REGISTRATION

Current Controlled Trials ISRCTN78513845.

FUNDING

This project was funded by the National Institute for Health Research (NIHR) Health Technology Assessment programme and will be published in full in Health Technology Assessment; Vol. 20, No. 40. See the NIHR Journals Library website for further project information.

Barriers to uptake among high-risk individuals declining participation in lung cancer screening: a mixed methods analysis of the UK Lung Cancer Screening (UKLS) trial

OBJECTIVE

The current study aimed to identify the barriers to participation among high-risk individuals in the UK Lung Cancer Screening (UKLS) pilot trial.

SETTING

The UKLS pilot trial is a randomised controlled trial of low-dose CT (LDCT) screening that has recruited high-risk people using a population approach in the Cambridge and Liverpool areas.

PARTICIPANTS

High-risk individuals aged 50-75 years were invited to participate in UKLS. Individuals were excluded if a LDCT scan was performed within the last year, if they were unable to provide consent, or if LDCT screening was unable to be carried out due to coexisting comorbidities.

OUTCOME MEASURES

Statistical associations between individual characteristics and UKLS uptake were examined using multivariable regression modelling. In those who completed a non-participation questionnaire (NPQ), thematic analysis of free-text data was undertaken to identify reasons for not taking part, with subsequent exploratory linkage of key themes to risk factors for non-uptake.

RESULTS

Comparative data were available from 4061 high-risk individuals who consented to participate in the trial and 2756 who declined participation. Of those declining participation, 748 (27.1%) completed a NPQ. Factors associated with non-uptake included: female gender (OR=0.64, p<0.001), older age (OR=0.73, p<0.001), current smoking (OR=0.70, p<0.001), lower socioeconomic group (OR=0.56, p<0.001) and higher affective risk perception (OR=0.52, p<0.001). Among non-participants who provided a reason, two main themes emerged reflecting practical and emotional barriers. Smokers were more likely to report emotional barriers to participation.

CONCLUSIONS

A profile of risk factors for non-participation in lung screening has emerged, with underlying reasons largely relating to practical and emotional barriers. Strategies for engaging high-risk, hard-to-reach groups are critical for the equitable uptake of a potential future lung cancer screening programme.

TRIAL REGISTRATION NUMBER

The UKLS trial was registered with the International Standard Randomised Controlled Trial Register under the reference 78513845.

Data analysis of the Lung Imaging Database Consortium and Image Database Resource Initiative

RATIONALE AND OBJECTIVES

The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI) is the largest publicly available computed tomography (CT) image reference data set of lung nodules. In this article, a comprehensive data analysis of the data set and a uniform data model are presented with the purpose of facilitating potential researchers to have an in-depth understanding to and efficient use of the data set in their lung cancer-related investigations.

MATERIALS AND METHODS

A uniform data model was designed for representation and organization of various types of information contained in different source data files. A software tool was developed for the processing and analysis of the database, which 1) automatically aligns and graphically displays the nodule outlines marked manually by radiologists onto the corresponding CT images; 2) extracts diagnostic nodule characteristics annotated by radiologists; 3) calculates a variety of nodule image features based on the outlines of nodules, including diameter, volume, and degree of roundness, and so forth; 4) integrates all the extracted nodule information into the uniform data model and stores it in a common and easy-to-access data format; and 5) analyzes and summarizes various feature distributions of nodules in several different categories. Using this data processing and analysis tool, all 1018 CT scans from the data set were processed and analyzed for their statistical distribution.

RESULTS

The information contained in different source data files with different formats was extracted and integrated into a new and uniform data model. Based on the new data model, the statistical distributions of nodules in terms of nodule geometric features and diagnostic characteristics were summarized. In the LIDC/IDRI data set, 2655 nodules ≥3 mm, 5875 nodules <3 mm, and 7411 non-nodules are identified, respectively. Among the 2655 nodules, 1) 775, 488, 481, and 911 were marked by one, two, three, or four radiologists, respectively; 2) most of nodules ≥3 mm (85.7%) have a diameter <10.0 mm with the mean value of 6.72 mm; and 3) 10.87%, 31.4%, 38.8%, 16.4%, and 2.6% of nodules were assessed with a malignancy score of 1, 2, 3, 4, and 5, respectively.

CONCLUSIONS

This study demonstrates the usefulness of the proposed software tool to the potential users for an in-depth understanding of the LIDC/IDRI data set, therefore likely to be beneficial to their future investigations. The analysis results also demonstrate the distribution diversity of nodules characteristics, therefore being useful as a reference resource for assessing the performance of a new and existing nodule detection and/or segmentation schemes.

Development of a personalized training system using the Lung Image Database Consortium and Image Database resource Initiative Database

RATIONALE AND OBJECTIVES

The aim of this study was to develop a personalized training system using the Lung Image Database Consortium (LIDC) and Image Database resource Initiative (IDRI) Database, because collecting, annotating, and marking a large number of appropriate computed tomography (CT) scans, and providing the capability of dynamically selecting suitable training cases based on the performance levels of trainees and the characteristics of cases are critical for developing a efficient training system.

MATERIALS AND METHODS

A novel approach is proposed to develop a personalized radiology training system for the interpretation of lung nodules in CT scans using the Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI) database, which provides a Content-Boosted Collaborative Filtering (CBCF) algorithm for predicting the difficulty level of each case of each trainee when selecting suitable cases to meet individual needs, and a diagnostic simulation tool to enable trainees to analyze and diagnose lung nodules with the help of an image processing tool and a nodule retrieval tool.

RESULTS

Preliminary evaluation of the system shows that developing a personalized training system for interpretation of lung nodules is needed and useful to enhance the professional skills of trainees.

CONCLUSIONS

The approach of developing personalized training systems using the LIDC/IDRL database is a feasible solution to the challenges of constructing specific training program in terms of cost and training efficiency.

Evaluation and management of pulmonary nodules: state-of-the-art and future perspectives

INTRODUCTION

The imaging evaluation of pulmonary nodules, often incidentally detected on imaging examinations performed for other clinical reasons, is a frequently encountered clinical circumstance. With advances in imaging modalities, both the detection and characterization of pulmonary nodules continue to evolve and improve.

AREAS COVERED

This article will review the imaging modalities used to detect and diagnose benign and malignant pulmonary nodules, with a focus on computed tomography (CT), which continues to be the mainstay for evaluation. The authors discuss recent advances in the lung nodule management, and an algorithm for the management of indeterminate pulmonary nodules.

EXPERT OPINION

There are set of criteria that define a benign nodule, the most important of which are the lack of temporal change for 2 years or more, and certain benign imaging criteria, including specific patterns of calcification or the presence of fat. Although some indeterminate pulmonary nodules are immediately actionable, generally those approaching 1 cm or larger in diameter, at which size the diagnostic accuracy of tools such as positron emission tomography (PET)/CT, single photon emission CT (SPECT) and biopsy techniques are sufficient to warrant their use. The majority of indeterminate pulmonary nodules are under 1 cm, for which serial CT examinations through at least 2 years for solid nodules and 3 years for ground-glass nodules, are used to demonstrate either benign biologic behavior or otherwise. The management of incidental pulmonary nodules involves a multidisciplinary approach in which radiology plays a pivotal role. Newer imaging and postprocessing techniques have made this a more accurate technique eliminating ambiguity and unnecessary follow-up.

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.

Sensitivity and specificity of a CAD solution for lung nodule detection on chest radiograph with CTA correlation

The objective of this research was to determine the sensitivity and specificity of a commercially available computer-aided detection (CAD) system for detection of lung nodule on posterior-anterior (PA) chest radiograph in a varied patient population who are referred to computed tomographic angiogram (CTA) of the chest as a reference standard. Patients who had a PA chest radiograph with concomitant CTA of the chest were included in this retrospective study. The PA chest radiograph was analyzed by a CAD device, and results were recorded. A qualitative assessment of the CAD results was performed using a 5-point Likert scale. The CTA was then reviewed to determine if there were correlative nodules. The presence of a correlative nodule between 0.5 cm and 1.5 cm was considered a positive result. The baseline sensitivity of the system was determined to be 0.707 (95% CI = 0.52-0.86), with a specificity of 0.50 (95% CI = 0.38-0.76). Positive predictive value was 0.30 (95% CI = 0.24-0.49), with a negative predictive value of 0.858 (95% CI = 0.82-0.95), and accuracy of 0.555 (95% CI = 0.40-0.66). When excluding nodules that were qualitatively determined by a thoracic radiologist to be false positives, the specificity was 0.781 (95% CI = 0.764-0.839), the positive predictive value was 0.564 (95% CI = 0.491-0.654), the negative predictive value was 0.829 (95% CI = 0.819-0.878), and the accuracy was 0.737 (95% CI = 0.721-0.801). The use of CAD for lung nodule detection on chest radiograph, when used in conjunction with an experienced radiologist, has a very good sensitivity, specificity, and accuracy.

Effect of CAD on radiologists' detection of lung nodules on thoracic CT scans: analysis of an observer performance study by nodule size

RATIONALE AND OBJECTIVES

To retrospectively investigate the effect of a computer-aided detection (CAD) system on radiologists' performance for detecting small pulmonary nodules in computed tomography (CT) examinations, with a panel of expert radiologists serving as the reference standard.

MATERIALS AND METHODS

Institutional review board approval was obtained. Our dataset contained 52 CT examinations collected by the Lung Image Database Consortium, and 33 from our institution. All CTs were read by multiple expert thoracic radiologists to identify the reference standard for detection. Six other thoracic radiologists read the CT examinations first without and then with CAD. Performance was evaluated using free-response receiver operating characteristics (FROC) and the jackknife FROC analysis methods (JAFROC) for nodules above different diameter thresholds.

RESULTS

A total of 241 nodules, ranging in size from 3.0 to 18.6 mm (mean, 5.3 mm) were identified as the reference standard. At diameter thresholds of 3, 4, 5, and 6 mm, the CAD system had a sensitivity of 54%, 64%, 68%, and 76%, respectively, with an average of 5.6 false positives (FPs) per scan. Without CAD, the average figures of merit (FOMs) for the six radiologists, obtained from JAFROC analysis, were 0.661, 0.729, 0.793, and 0.838 for the same nodule diameter thresholds, respectively. With CAD, the corresponding average FOMs improved to 0.705, 0.763, 0.810, and 0.862, respectively. The improvement achieved statistical significance for nodules at the 3 and 4 mm thresholds (P = .002 and .020, respectively), and did not achieve significance at 5 and 6 mm (P = .18 and .13, respectively). At a nodule diameter threshold of 3 mm, the radiologists' average sensitivity and FP rate were 0.56 and 0.67, respectively, without CAD, and 0.67 and 0.78 with CAD.

CONCLUSION

CAD improves thoracic radiologists' performance for detecting pulmonary nodules smaller than 5 mm on CT examinations, which are often overlooked by visual inspection alone.

Automatic segmentation and recognition of lungs and lesion from CT scans of thorax

In this study, a fully automated texture-based segmentation and recognition system for lesion and lungs from CT of thorax is presented. For the segmentation part, we have extracted texture features by Gabor filtering the images, and, then combined these features to segment the target volume by using Fuzzy C Means (FCM) clustering. Since clustering is sensitive to initialization of cluster prototypes, optimal initialization of the cluster prototypes was done by using a Genetic Algorithm. For the recognition stage, we have used cortex like mechanism for extracting statistical features in addition to shape-based features. The segmented regions showed a high degree of imbalance between positive and negative samples, so we employed over and under sampling for balancing the data. Finally, the balanced and normalized data was subjected to Support Vector Machine (SimpleSVM) for training and testing. Results reveal an accuracy of delineation to be 94.06%, 94.32% and 89.04% for left lung, right lung and lesion, respectively. Average sensitivity of the SVM classifier was seen to be 89.48%.

Lung cancer screening: the way forward

To take lung cancer screening into national programmes, we first have to answer the question whether low-dose computed tomography (LDCT) screening and treatment of early lesions will decrease lung cancer mortality compared with a control group, to accurately estimate the balance of benefits and harms, and to determine the cost-effectiveness of the intervention.

Performance of a computer-aided program for automated matching of metastatic pulmonary nodules detected on follow-up chest CT

OBJECTIVE

The purpose of this study was to evaluate the performance of a computer-aided program that allows automated matching of metastatic pulmonary nodules imaged with two serial clinical chest CT studies.

MATERIALS AND METHODS

The cases of 30 patients with metastatic pulmonary nodules depicted on two serial clinical MDCT scans (16- or 64-MDCT, 5-mm section thickness) were studied. The number of nodules per patient varied from a minimum of two to innumerable. A maximum of 10 well-defined solid nodules per patient, a total of 210 nodules, were selected from each baseline CT scan and were evaluated for matching detection in follow-up CT by means of an automated program. Substantial changes in lung findings and lung volumes between serial scans were visually assessed. The effects on matching rate of interval lung changes and location, size, and total number of nodules in the lung were analyzed with contingency tables. Chi-square tests were used to evaluate patterns for statistical significance.

RESULTS

The nodule-matching rate per patient ranged from 0 to 100% (median, 87.5%). By nodule, the overall matching rate was 140 of 210 (66.7%). Matching rate was highly associated with changes in lung quality between serial studies. Matching of 122 of 148 nodules (82.4%) occurred in 23 patients with relatively unchanged lung findings, compared with 18 of 62 nodules (29.0%) in seven patients with substantial interval changes (p < 0.001). The matching rate decreased with an increased total number of nodules per lung. For 10 or fewer nodules per lung, matching was successful for 31 of 36 nodules; for 11-50 nodules per lung, 60 of 73 nodules; for 51-100 nodules per lung, 33 of 47 nodules; and for more than 100 nodules per lung, 16 of 54 nodules (p < 0.001). The matching rate was not significantly different with location or size of nodules.

CONCLUSION

The rate of automated matching of metastatic pulmonary nodules on clinical serial CT scans was high (82.4%) when the lung findings and lung expansion between the serial scans were relatively unchanged. The rate decreased significantly, however, with substantial interval changes in the lung and a larger number of nodules.

Computer-aided detection (CAD) in lung cancer screening at chest MDCT: ROC analysis of CAD versus radiologist performance

To evaluate the performance of a computer-aided detection (CAD) algorithm in the detection of pulmonary nodules on high-resolution multidetector row computed tomography images in a large, homogeneous screening population, and to evaluate the effect of the system output on the performance of radiologists, using receiver operating characteristic analysis. Three radiologists with variable experience (1 to 7 y), independently read the 200 computed tomography scans and assigned each nodule candidate a confidence score (1-2-3: unlikely, probably, and definitely a nodule). CAD was applied to all scans; successively readers reevaluated all findings of the CAD, assigning, in consensus, a confidence score (1 to 3). The reference standard was established by the consensus of 2 experienced radiologists with 30 and 15 years of experience. Results were used to generate an free-response receiver operating characteristic analysis. The reference standard showed 125 nodules. Sensitivity for readers I-II-III was 57%, 68%, and 46%. A double reading resulted in an increase in sensitivity up to 75%. With CAD, sensitivity was increased to 94%, 96%, and 94% for readers I, II, and III. The area under the free-response receiver operating characteristic curve (Az) was 0.72, 0.82, 0.55, and 0.84 for readers I, II, III, and the CAD, when considering all nodules. Differences between readers I-II and CAD were not significant (P=0.9). There was a significant difference between reader III and the CAD. For nodules <6-mm Az was 0.40, 0.47, 0.14, and 0.72 for readers I, II, III, and the CAD. Differences between all readers and the CAD were significant (P<0.05). CAD can aid in daily radiologic routine detecting a substantial number of nodules unseen by radiologists. This is true for both board-certified radiologists and for less experienced readers especially in the detection of small nodules.

Registration of lung nodules using a semi-rigid model: method and preliminary results

The tracking of lung nodules across computed tomography (CT) scans acquired at different times for the same patient is helpful for the determination of malignancy. We are developing a nodule registration system to facilitate this process. We propose to use a semi-rigid method that considers principal structures surrounding the nodule and allows relative movements among the structures. The proposed similarity metric, which evaluates both the image correlation and the degree of elastic deformation amongst the structures, is maximized by a two-layered optimization method, employing a simulated annealing framework. We tested our method by simulating five cases that represent physiological deformation as well as different nodule shape/size changes with time. Each case is made up of a source and target scan, where the source scan consists of a nodule-free patient CT volume into which we inserted ten simulated lung nodules, and the target scan is the result of applying a known, physiologically based nonrigid transformation to the nodule-free source scan, into which we inserted modified versions of the corresponding nodules at the same, known locations. Five different modification strategies were used, one for each of the five cases: (1) nodules maintain size and shape, (2) nodules disappear, (3) nodules shrink uniformly by a factor of 2, (4) nodules grow uniformly by a factor of 2, and (5) nodules grow nonuniformly. We also matched 97 real nodules in pairs of scans (acquired at different times) from 12 patients and compared our registration to a radiologist's visual determination. In the simulation experiments, the mean absolute registration errors were 1.0+/-0.8 mm (s.d.), 1.1+/-0.7 mm (s.d.), 1.0+/-0.7 mm (s.d.), 1.0+/-0.6 mm (s.d.), and 1.1+/- 0.9 mm (s.d.) for the five cases, respectively. For the 97 nodule pairs in 12 patient scans, the mean absolute registration error was 1.4+/-0.8 mm (s.d.).

Pulmonary Nodules Detected at Lung Cancer Screening: Interobserver Variability of Semiautomated Volume Measurements

PURPOSE

To retrospectively determine interobserver variability of semiautomated volume measurements of pulmonary nodules and the potential reasons for variability.

MATERIALS AND METHODS

The Dutch-Belgian lung cancer screening trial (NELSON) is a lung cancer screening study that includes men between the ages of 50 and 75 years who are current or former heavy smokers. The NELSON project was approved by the Dutch Ministry of Health and the ethics committee of each participating hospital. Informed consent was obtained from all participants. For this study, the authors evaluated 1200 consecutive low-dose computed tomographic (CT) scans of the chest obtained during the NELSON project and identified subjects who had at least one 50-500-mm(3) nodule. One local and one central observer independently evaluated the scans and measured the volume of any detected nodule by using semiautomated software. Noncalcified solid nodules with volumes of 15-500 mm(3) were included in this study if they were fully surrounded by air (intraparenchymal) and were detected by both observers. The mean volume and the difference between both measurements were calculated for all nodules. Intermeasurement agreement was assessed with the Spearman correlation coefficient. Potential reasons for discrepancies were assessed.

RESULTS

There were 232 men (mean age, 60 years; age range, 52-73 years) with 430 eligible nodules (mean volume, 77.8 mm(3); range, 15.3-499.5 mm(3)). Interobserver correlation was high (r = 0.99). No difference in volume was seen for 383 nodules (89.1%). Discrepant results were obtained for 47 nodules (10.9%); in 16 cases (3.7%), the discrepancy was larger than 10%. The most frequent cause of variability was incomplete segmentation due to an irregular shape or irregular margins.

CONCLUSION

In a minority (approximately 11%) of small solid intraparenchymal nodules, semiautomated measurements are not completely reproducible and, thus, may cause errors in the assessment of nodule growth. For small or irregularly shaped nodules, an observer should check the segmentation shown by the program.

Diagnosis of hepatic tumors with texture analysis in nonenhanced computed tomography images

RATIONALE AND OBJECTIVES

Computed tomography (CT) after iodinated contrast agent injection is highly accurate for diagnosis of hepatic tumors. However, iodinating may have problems of renal toxicity and allergic reaction. We aimed to evaluate the potential role of the computer-aided diagnosis (CAD) with texture analysis in the differential of hepatic tumors on nonenhanced CT.

MATERIALS AND METHODS

This study evaluated 164 liver lesions (80 malignant tumors and 84 hemangiomas). The suspicious tumor region in the digitized CT image was manually selected and extracted as a circular subimage. Proposed preprocessing adjustments for subimages were used to equalize the information needed for a differential diagnosis. The autocovariance texture features of subimage were extracted and a support vector machine classifier identified the tumor as benign or malignant.

RESULTS

The accuracy of the proposed diagnosis system for classifying malignancies is 81.7%, the sensitivity is 75.0%, the specificity is 88.1%, the positive predictive value is 85.7%, and the negative predictive value is 78.7%.

CONCLUSIONS

This system differentiates benign from malignant hepatic tumors with relative high accuracy and is therefore clinically useful to reduce patients needed for iodinated contrast agent injection in CT examination. Because the support vector machine is trainable, it could be further optimized if a larger set of tumor images is to be supplied.

Lung Cancer Screening

Advances in imaging technology have ushered in a new era for lung cancer screening in high-risk individuals using computed tomographic (CT) scans. Although most published studies are nonrandomized observational cohorts of volunteers, the ability of CT scans to detect early stage lung cancer is undisputable. What is unresolved is the ability of spiral CT screening to affect lung cancer-related mortality. A large randomized trial sponsored by the National Cancer Institute to address this question is currently under way. Genomic and proteomic approaches promise to complement the ability of spiral CT to detect early lung cancer in the next few years. Currently, the decision to screen for lung cancer should involve a careful discussion with the individuals involved about the potential advantages, costs, and drawbacks of the approach.

Computer technology in detection and staging of prostate carcinoma: A review

After two decades of increasing interest and research activity, computer-assisted diagnostic approaches are reaching the stage where more routine deployment in clinical practice is becoming a possibility [Kruppinski, E.A., 2004. Computer-aided detection in clinical environment: Benefits and challenges for radiologists. Radiology 231, 7-9]. This is particularly the case in the analysis of mammographic images [Helvie, M.A., Hadjiiski, L., Makariou, E., Chan, H.P., Petrick, N., Sahiner, B., Lo, S.C., Freedman, M., Adler, D., Bailey, J., Blane, C., Hoff, D., Hunt, K., Joynt, L., Klein, K., Paramagul, C., Patterson, S.K., Roubidoux, M.A., 2004. Sensitivity of noncommercial computer-aided detection system for mammographic breast cancer detection: pilot clinical trial. Radiology 231, 208-214] and in the detection of pulmonary nodules [Reeves, A.P., Kostis, W.J., 2000. Computer-aided diagnosis for lung cancer. Radiol. Clin. North Am. 38, 497-509]. However, similar approaches can be applied more widely with the promise of increasing clinical utility in other areas. We review how computer-aided approaches may be applied in the diagnosis and staging of prostatic cancer. The current status of computer technology is reviewed, covering artificial neural networks for detection and staging, computerised biopsy simulation and computer-assisted analysis of ultrasound and magnetic resonance images.

Computer-aided kidney segmentation on abdominal CT images

In this paper, an effective model-based approach for computer-aided kidney segmentation of abdominal CT images with anatomic structure consideration is presented. This automatic segmentation system is expected to assist physicians in both clinical diagnosis and educational training. The proposed method is a coarse to fine segmentation approach divided into two stages. First, the candidate kidney region is extracted according to the statistical geometric location of kidney within the abdomen. This approach is applicable to images of different sizes by using the relative distance of the kidney region to the spine. The second stage identifies the kidney by a series of image processing operations. The main elements of the proposed system are: 1) the location of the spine is used as the landmark for coordinate references; 2) elliptic candidate kidney region extraction with progressive positioning on the consecutive CT images; 3) novel directional model for a more reliable kidney region seed point identification; and 4) adaptive region growing controlled by the properties of image homogeneity. In addition, in order to provide different views for the physicians, we have implemented a visualization tool that will automatically show the renal contour through the method of second-order neighborhood edge detection. We considered segmentation of kidney regions from CT scans that contain pathologies in clinical practice. The results of a series of tests on 358 images from 30 patients indicate an average correlation coefficient of up to 88% between automatic and manual segmentation.

Autonomous detection of pulmonary nodules on CT images with a neural network-based fuzzy system

In this paper, a novel extension of neural network-based fuzzy model has been proposed to detect lung nodules. The proposed model can automatically identify a set of appropriate fuzzy inference rules, and refine the membership functions through the steepest gradient descent-learning algorithm. Twenty-nine clinical cases involving 583 thick section CT images were tested in this study. Receiver operating characteristic (ROC) analysis was used to evaluate the proposed autonomous pulmonary nodules detection system and yielded an area under the ROC curve of Azs=0.963. The overall detection sensitivity of the proposed method was 89.3% (with p-value less than 0.001), and the false positive was as low as 0.2 per image. This result demonstrates that the proposed neural network-based fuzzy system resolves the most suitable fuzzy rules, improves the detection rate, and reduces false positives compared to other approaches. The proposed system is fully automated with fast processing speed. The studies have shown a high potential for implementation of this system in clinical practice as a CAD tool.

Clinical Issues in the Management of Early Lung Cancer

Lung cancer is commonly diagnosed after metastatic spread, when therapies are rarely curative, providing an impetus for continued research directed at exploring approaches for cost-effective early lung cancer detection. Recently published pilot studies across three continents support a benefit of spiral computed tomography (CT) in detecting earlier stage non-small cell lung cancer. Improved resolution of early lung cancer is a result of significant changes in CT imaging hardware and software. The status and implications of these developments are reviewed. Many aspects of the management of screening for early lung cancer could be informed by optimizing the downstream clinical management of potential lung cancers identified by CT screening. The first and most critical issue is whether or not this improved detection rate is clearly associated with a reduction in lung cancer-related mortality. However, other related issues such as cost-benefit evaluations are also considered. If smaller, truly localized primary cancer can be routinely detected, then options for less morbid interventions would also be desirable. The rapid improvement in resolution and cost of spiral CT has provided a powerful impetus to reconsider the possibilities for achieving safe, economical, and meaningful early lung cancer detection.

Diagnosis of lung nodule using semivariogram and geometric measures in computerized tomography images

This paper uses the geostatistical function - semivariogram and a set of 3D geometric measures - sphericity index, convexity index, extrinsic and intrinsic curvature index and surface type, to characterize lung nodules as malignant or benign in computerized tomography images. Based on a sample of 31 nodules, 25 benign and 6 malignant, these methods are first analyzed individually and then jointly, with techniques for classification and analysis (stepwise discriminant analysis, leave-one-out and ROC curve). We have concluded that the individual measures and their combinations produce good results in the diagnosis of lung nodules.

Pulmonary nodules: automated detection on CT images with morphologic matching algorithm--preliminary results

Institutional review board approval was obtained. Informed patient consent was not required for this retrospective study, which involved review of previously obtained image data. Patient confidentiality was protected; the study was compliant with the Health Insurance Portability and Accountability Act. An automated pulmonary nodule detection program that takes advantage of three-dimensional volumetric data was developed and tested with multi-detector row computed tomographic (CT) images from 20 patients (13 men, seven women; age range, 40-75 years) with pulmonary nodules. A total of 164 nodules 3 mm in diameter and larger were detected by two radiologists in consensus and were used as a reference standard to evaluate the computer-aided detection (CAD) program. The CAD algorithm was structured to process nodules that were categorized into three types: isolated, juxtapleural, and juxtavascular. Overall sensitivity for nodule detection with the CAD program was 95.1% (156 of 164 nodules). The sensitivity according to nodule size was 91.2% (52 of 57 nodules) for nodules 3 mm to less than 5 mm and 97.2% (104 of 107 nodules) for nodules 5 mm and larger. The number of false-positive detections per patient was 6.9 for false nodule structures 3 mm and larger and 4.0 for false nodule structures 5 mm and larger.

New Developments in Lung Cancer Screening

Lung cancer is the most lethal cancer in our society. Late diagnosis of this disease is a major problem and so recent favorable reports with spiral computed tomography screening of high-risk populations have rekindled interest in improving early lung cancer detections. The process of lung cancer screening is a complicated process that involves many component activities. Interest to date has heavily focused on the initial case identification, but more recent reports have suggested that the issues with case work-up and surgical management also bear closer consideration. Given the dynamic nature of spiral computed tomography scan development and the remarkable improvements in imaging resolution over the last decade, there is an urgent need for research to establish optimal clinical management of early lung cancer detected in a screening setting.

Computer-aided diagnosis in high resolution CT of the lungs

A computer-aided diagnosis (CAD) system is presented to automatically distinguish normal from abnormal tissue in high-resolution CT chest scans acquired during daily clinical practice. From high-resolution computed tomography scans of 116 patients, 657 regions of interest are extracted that are to be classified as displaying either normal or abnormal lung tissue. A principled texture analysis approach is used, extracting features to describe local image structure by means of a multi-scale filter bank. The use of various classifiers and feature subsets is compared and results are evaluated with ROC analysis. Performance of the system is shown to approach that of two expert radiologists in diagnosing the local regions of interest, with an area under the ROC curve of 0.862 for the CAD scheme versus 0.877 and 0.893 for the radiologists.

Population screening for lung cancer

The feasibility of diagnosing small stage 1 lung cancers using low-dose chest computed tomography in asymptomatic at-risk individuals has been demonstrated in multiple studies. However, it has yet to be proved that the introduction of a chest computed tomography screening programme would do more good than harm at an acceptable cost.

Improved detection of lung nodules on chest radiographs using a commercial computer-aided diagnosis system

OBJECTIVE

The aim of this study was to evaluate the usefulness of a new commercially available computer-aided diagnosis (CAD) system with an automated method of detecting nodules due to lung cancers on chest radiograph.

MATERIALS AND METHODS

For patients with cancer, 45 cases with solitary lung nodules up to 25 mm in diameter (nodule size range, 8-25 mm in diameter; mean, 18 mm; median, 20 mm) were used. For healthy patients, 45 cases were selected on the basis of confirmation on chest CT. All chest radiographs were obtained with a computed radiography system. The CAD output images were produced with a newly developed CAD system, which consisted of an image server including CAD software called EpiSight/XR. Eight radiologists (four board-certified radiologists and four radiology residents) participated in observer performance studies and interpreted both the original radiographs and CAD output images using a sequential testing method. The observers' performance was evaluated with receiver operating characteristic analysis.

RESULTS

The average area under the curve value increased significantly from 0.924 without to 0.986 with CAD output images. Individually, the use of CAD output images was more beneficial to radiology residents than to board-certified radiologists.

CONCLUSION

This CAD system for digital chest radiographs can assist radiologists and has the potential to improve the detection of lung nodules due to lung cancer.

Pulmonary nodules at chest CT: effect of computer-aided diagnosis on radiologists' detection performance

PURPOSE

To evaluate the effect of computer-aided diagnosis (CAD) on radiologists' detection of pulmonary nodules.

MATERIALS AND METHODS

Fifty chest computed tomographic (CT) examination cases were used. The mean nodule size was 0.81 cm +/- 0.60 (SD) (range, 0.3-2.9 cm). Alternative free-response receiver operating characteristic (ROC) analysis with a continuous rating scale was used to compare the observers' performance in detecting nodules with and without use of CAD. Five board-certified radiologists and five radiology residents participated in an observer performance study. First they were asked to rate the probability of nodule presence without using CAD; then they were asked to rate the probability of nodule presence by using CAD.

RESULTS

For all radiologists, the mean areas under the best-fit alternative free-response ROC curves (Az) without and with CAD were 0.64 +/- 0.08 and 0.67 +/- 0.09, respectively, indicating a significant difference (P <.01). For the five board-certified radiologists, the mean Az values without and with CAD were 0.63 +/- 0.08 and 0.66 +/- 0.09, respectively, indicating a significant difference (P <.01). For the five resident radiologists, the mean Az values without and with CAD were 0.66 +/- 0.04 and 0.68 +/- 0.04, respectively, indicating a significant difference (P =.02). At observer performance analyses, there were no significant differences in Az values obtained either without (P =.61) or with (P =.88) CAD between the board-certified radiologists and the residents. For all radiologists, in the detection of pulmonary nodules 1.0 cm in diameter or smaller, the mean Az values without and with CAD were 0.60 +/- 0.11 and 0.64 +/- 0.11, respectively, indicating a significant difference (P <.01).

CONCLUSION

Use of the CAD system improved the board-certified radiologists' and residents' detection of pulmonary nodules at chest CT.

Landmark detection in the chest and registration of lung surfaces with an application to nodule registration

We developed an automated system for registering computed tomography (CT) images of the chest temporally. Our system detects anatomical landmarks, in particular, the trachea, sternum and spine, using an attenuation-based template matching approach. It computes the optimal rigid-body transformation that aligns the corresponding landmarks in two CT scans of the same patient. This transformation then provides an initial registration of the lung surfaces segmented from the two scans. The initial surface alignment is refined step by step in an iterative closest-point (ICP) process. To establish the correspondence of lung surface points, Elias' nearest neighbor algorithm was adopted. Our method improves the processing time of the original ICP algorithm from O(kn log n) to O(kn), where k is the number of iterations and n the number of surface points. The surface transformation is applied to align nodules in the initial CT scan with nodules in the follow-up scan. For 56 out of 58 nodules in the initial CT scans of 10 patients, nodule correspondences in the follow-up scans are established correctly. Our methods can therefore potentially facilitate the radiologist's evaluation of pulmonary nodules on chest CT for interval growth.

Lung nodule detection and characterization with multislice CT

The ability to identify and characterize pulmonary nodules has been dramatically increased by the introduction of multislice CT (MSCT) technology. Using high-resolution sections, MSCT allows considerable improvement in assessing nodule morphology, enhancement patterns, and growth. MSCT also has facilitated the development and potential of clinical application of computer-assisted diagnosis.

Screening for lung cancer: in pursuit of pre-metastatic disease

One reason for the high death rate of lung cancer is that tumours are not usually detected until the disease is at a late stage, at which point the cancer is non-curable. Spiral computerized tomography is a highly sensitive imaging method that could be used to screen high-risk populations, such as current or former smokers, for early-stage tumours. Trials to validate this tool are just underway, but beyond the imaging tools, population-based care of pre-metastatic lung cancer requires considerable evolution in clinical management approaches. More sensitive imaging tools might also provide a window into earlier biology, enabling the molecular dynamics of lung cancer progression to be elucidated.

Computer-aided diagnosis in chest radiography: a survey

The traditional chest radiograph is still ubiquitous in clinical practice, and will likely remain so for quite some time. Yet, its interpretation is notoriously difficult. This explains the continued interest in computer-aided diagnosis for chest radiography. The purpose of this survey is to categorize and briefly review the literature on computer analysis of chest images, which comprises over 150 papers published in the last 30 years. Remaining challenges are indicated and some directions for future research are given.

Computed tomography screening for lung cancer: back to basics

After some years in the doldrums, interest in screening for lung cancer is resurging. Conflicting evidence from previous lung cancer screening trials, based on plain chest radiography, has been the subject of much debate: the failure to demonstrate a reduction in mortality has led to the widely held conclusion that screening for lung cancer is ineffective. The validity of this assumption has been questioned sporadically and a large study currently under way in the U.S.A. should help settle the issue. Recently, there has been interest in the use of computed tomography to screen for lung cancer; radiation doses have been reduced to 'acceptable' levels and the superiority of computed tomography (CT) over chest radiography for the identification of pulmonary nodules is unquestioned. However, whether improved nodule detection will result in a reduction in mortality has not yet been demonstrated. The present review provides a historical background to the current interest in low-dose CT screening, explains the arguments that previous studies have provoked, and discusses the recent and evolving status of lung cancer screening with CT. Ellis, S. M. et al. (2001).

Virtual tools for imaging of the thorax

Helical computed tomography (HCT) allows for volume acquisition of the entire thorax during a single apnoea. Combination of HCT acquisition with synchronous vascular enhancement gives rise to HCT angiography (HCTA). In the last decade, HCT and HCTA have revolutionized the diagnosis of thoracic diseases, modifying many diagnostic algorithms. Because HCT provides for a true volume acquisition free of respiratory misregistration, three-dimensional (3D) rendering techniques can be applied to HCT acquisitions. As these 3D rendering techniques present the HCT information in a different format to the conventional transaxial CT slices, they can be summarized as virtual tools. The purpose of this review is to give the readers the most important technical aspects of virtual tools, to report their application to the thorax, to answer clinical and scientific questions, and to stress their importance for patient management, clinical decision making, and research.

Computer-aided diagnosis of small pulmonary nodules

Computer-aided methods are now being developed for the detection and characterization of pulmonary nodules found in CT images, based on techniques from computer vision, image processing, and pattern classification. With the increasing resolution of modern CT scanners, computer methods provide continually improving accuracy, reproducibility, and utility in analyzing the larger numbers of images acquired in a lung screening exam or diagnostic study. This article describes the fundamental tools and issues involved in computer-aided nodule detection and characterization, as we move from two-dimensional toward three-dimensional automated methods. In particular, we focus on the new domain of "small" pulmonary nodules.