Computer-aided diagnosis scheme for detection of polyps at CT colonography

Review of artificial intelligence clinical applications in Nuclear Medicine

This paper provides an in-depth analysis of the clinical applications of artificial intelligence (AI) in Nuclear Medicine, focusing on three key areas: neurology, cardiology, and oncology. Beginning with neurology, specifically Alzheimer's disease and Parkinson's disease, the paper examines reviews on diagnosis and treatment planning. The same pattern is followed in cardiology studies. In the final section on oncology, the paper explores the various AI applications in multiple cancer types, including lung, head and neck, lymphoma, and pancreatic cancer.

Rapid Polyp Classification in Colonoscopy Using Textural and Convolutional Features

Colorectal cancer is the leading cause of cancer-associated morbidity and mortality worldwide. One of the causes of developing colorectal cancer is untreated colon adenomatous polyps. Clinically, polyps are detected in colonoscopy and the malignancies are determined according to the biopsy. To provide a quick and objective assessment to gastroenterologists, this study proposed a quantitative polyp classification via various image features in colonoscopy. The collected image database was composed of 1991 images including 1053 hyperplastic polyps and 938 adenomatous polyps and adenocarcinomas. From each image, textural features were extracted and combined in machine learning classifiers and machine-generated features were automatically selected in deep convolutional neural networks (DCNN). The DCNNs included AlexNet, Inception-V3, ResNet-101, and DenseNet-201. AlexNet trained from scratch achieved the best performance of 96.4% accuracy which is better than transfer learning and textural features. Using the prediction models, the malignancy level of polyps can be evaluated during a colonoscopy to provide a rapid treatment plan.

Quantitative Analysis of Melanosis Coli Colonic Mucosa Using Textural Patterns

Melanosis coli (MC) is a disease related to long-term use of anthranoid laxative agents. Patients with clinical constipation or obesity are more likely to use these drugs for long periods. Moreover, patients with MC are more likely to develop polyps, particularly adenomatous polyps. Adenomatous polyps can transform to colorectal cancer. Recognizing multiple polyps from MC is challenging due to their heterogeneity. Therefore, this study proposed a quantitative assessment of MC colonic mucosa with texture patterns. In total, the MC colonoscopy images of 1092 person-times were included in this study. At the beginning, the correlations among carcinoembryonic antigens, polyp texture, and pathology were analyzed. Then, 181 patients with MC were extracted for further analysis while patients having unclear images were excluded. By gray-level co-occurrence matrix, texture patterns in the colorectal images were extracted. Pearson correlation analysis indicated five texture features were significantly correlated with pathological results (p < 0.001). This result should be used in the future to design an instant help software to help the physician. The information of colonoscopy and image analystic data can provide clinicians with suggestions for assessing patients with MC.

A comparison of computer-assisted detection (CAD) programs for the identification of colorectal polyps: performance and sensitivity analysis, current limitations and practical tips for radiologists

AIM

To directly compare the accuracy and speed of analysis of two commercially available computer-assisted detection (CAD) programs in detecting colorectal polyps.

MATERIALS AND METHOD

In this retrospective single-centre study, patients who had colorectal polyps identified on computed tomography colonography (CTC) and subsequent lower gastrointestinal endoscopy, were analysed using two commercially available CAD programs (CAD1 and CAD2). Results were compared against endoscopy to ascertain sensitivity and positive predictive value (PPV) for colorectal polyps. Time taken for CAD analysis was also calculated.

RESULTS

CAD1 demonstrated a sensitivity of 89.8%, PPV of 17.6% and mean analysis time of 125.8 seconds. CAD2 demonstrated a sensitivity of 75.5%, PPV of 44.0% and mean analysis time of 84.6 seconds.

CONCLUSION

The sensitivity and PPV for colorectal polyps and CAD analysis times can vary widely between current commercially available CAD programs. There is still room for improvement. Generally, there is a trade-off between sensitivity and PPV, and so further developments should aim to optimise both. Information on these factors should be made routinely available, so that an informed choice on their use can be made. This information could also potentially influence the radiologist's use of CAD results.

A Study of Multilevel Banded Graph Cuts for Three-Dimensional Colon Tissue Segmentation

Graph cuts is an image segmentation method by which the region and boundary information of objects can be revolved comprehensively. Because of the complex spatial characteristics of high-dimensional images, time complexity and segmentation accuracy of graph cuts methods for high-dimensional images need to be improved. This paper proposes a new three-dimensional multilevel banded graph cuts model to increase its accuracy and reduce its complexity. Firstly, three-dimensional image is viewed as a high-dimensional space to construct three-dimensional network graphs. A pyramid image sequence is created by Gaussian pyramid downsampling procedure. Then, a new energy function is built according to the spatial characteristics of the three-dimensional image, in which the adjacent points are expressed by using a 26-connected system. At last, the banded graph is constructed on a narrow band around the object/background. The graph cuts method is performed on the banded graph layer by layer to obtain the object region sequentially. In order to verify the proposed method, we have performed an experiment on a set of three-dimensional colon CT images, and compared the results with local region active contour and Chan–Vese model. The experimental results demonstrate that the proposed method can segment colon tissues from three-dimensional abdominal CT images accurately. The segmentation accuracy can be increased to 95.1% and the time complexity is reduced by about 30% of the other two methods.

A CAD of fully automated colonic polyp detection for contrasted and non-contrasted CT scans

PURPOSE

Computer-aided detection (CAD) systems are developed to help radiologists detect colonic polyps over CT scans. It is possible to reduce the detection time and increase the detection accuracy rates by using CAD systems. In this paper, we aimed to develop a fully integrated CAD system for automated detection of polyps that yields a high polyp detection rate with a reasonable number of false positives.

METHODS

The proposed CAD system is a multistage implementation whose main components are: automatic colon segmentation, candidate detection, feature extraction and classification. The first element of the algorithm includes a discrete segmentation for both air and fluid regions. Colon-air regions were determined based on adaptive thresholding, and the volume/length measure was used to detect air regions. To extract the colon-fluid regions, a rule-based connectivity test was used to detect the regions belong to the colon. Potential polyp candidates were detected based on the 3D Laplacian of Gaussian filter. The geometrical features were used to reduce false-positive detections. A 2D projection image was generated to extract discriminative features as the inputs of an artificial neural network classifier.

RESULTS

Our CAD system performs at 100% sensitivity for polyps larger than 9 mm, 95.83% sensitivity for polyps 6-10 mm and 85.71% sensitivity for polyps smaller than 6 mm with 5.3 false positives per dataset. Also, clinically relevant polyps ([Formula: see text]6 mm) were identified with 96.67% sensitivity at 1.12 FP/dataset.

CONCLUSIONS

To the best of our knowledge, the novel polyp candidate detection system which determines polyp candidates with LoG filters is one of the main contributions. We also propose a new 2D projection image calculation scheme to determine the distinctive features. We believe that our CAD system is highly effective for assisting radiologist interpreting CT.

Progress in Fully Automated Abdominal CT Interpretation

OBJECTIVE

Automated analysis of abdominal CT has advanced markedly over just the last few years. Fully automated assessment of organs, lymph nodes, adipose tissue, muscle, bowel, spine, and tumors are some examples where tremendous progress has been made. Computer-aided detection of lesions has also improved dramatically.

CONCLUSION

This article reviews the progress and provides insights into what is in store in the near future for automated analysis for abdominal CT, ultimately leading to fully automated interpretation.

CT colonography with computer-aided detection: recognizing the causes of false-positive reader results

Computed tomography (CT) colonography is a screening modality used to detect colonic polyps before they progress to colorectal cancer. Computer-aided detection (CAD) is designed to decrease errors of detection by finding and displaying polyp candidates for evaluation by the reader. CT colonography CAD false-positive results are common and have numerous causes. The relative frequency of CAD false-positive results and their effect on reader performance on the basis of a 19-reader, 100-case trial shows that the vast majority of CAD false-positive results were dismissed by readers. Many CAD false-positive results are easily disregarded, including those that result from coarse mucosa, reconstruction, peristalsis, motion, streak artifacts, diverticulum, rectal tubes, and lipomas. CAD false-positive results caused by haustral folds, extracolonic candidates, diminutive lesions (<6 mm), anal papillae, internal hemorrhoids, varices, extrinsic compression, and flexural pseudotumors are almost always recognized and disregarded. The ileocecal valve and tagged stool are common sources of CAD false-positive results associated with reader false-positive results. Nondismissable CAD soft-tissue polyp candidates larger than 6 mm are another common cause of reader false-positive results that may lead to further evaluation with follow-up CT colonography or optical colonoscopy. Strategies for correctly evaluating CAD polyp candidates are important to avoid pitfalls from common sources of CAD false-positive results.

Ischemic stroke detection system with a computer-aided diagnostic ability using an unsupervised feature perception enhancement method

We propose an ischemic stroke detection system with a computer-aided diagnostic ability using a four-step unsupervised feature perception enhancement method. In the first step, known as preprocessing, we use a cubic curve contrast enhancement method to enhance image contrast. In the second step, we use a series of methods to extract the brain tissue image area identified during preprocessing. To detect abnormal regions in the brain images, we propose using an unsupervised region growing algorithm to segment the brain tissue area. The brain is centered on a horizontal line and the white matter of the brain's inner ring is split into eight regions. In the third step, we use a coinciding regional location method to find the hybrid area of locations where a stroke may have occurred in each cerebral hemisphere. Finally, we make corrections and mark the stroke area with red color. In the experiment, we tested the system on 90 computed tomography (CT) images from 26 patients, and, with the assistance of two radiologists, we proved that our proposed system has computer-aided diagnostic capabilities. Our results show an increased stroke diagnosis sensitivity of 83% in comparison to 31% when radiologists use conventional diagnostic images.

Automated assessment of renal cortical surface roughness from computerized tomography images and its association with age

RATIONALE AND OBJECTIVES

Nephrosclerosis occurs with aging and is characterized by increased kidney subcapsular surface irregularities at autopsy. Assessments of cortical roughness in vivo could provide an important measure of nephrosclerosis. The purpose of this study was to develop and validate an image-processing algorithm for quantifying renal cortical surface roughness in vivo and determine its association with age.

MATERIALS AND METHODS

Renal cortical surface roughness was measured on contrast-enhanced abdominal computed tomography (CT) images of potential living kidney donors. A roughness index was calculated based on geometric curvature of each kidney from three-dimensional images and compared to visual observation scores. Cortical roughness was compared between the oldest and youngest donors, and its interaction with cortical volume and age assessed.

RESULTS

The developed quantitative roughness index identified significant differences in kidneys with visual surface roughness scores of 0 (minimal), 1 (mild), and 2 (moderate; P < .001) in a random sample of 200 potential kidney donors. Cortical roughness was significantly higher in the 94 oldest (64-75 years) versus 91 youngest (18-25 years) potential kidney donors (P < .001). Lower cortical volume was associated with older age but not with roughness (r = -0.03, P = .75). The association of oldest age group with roughness (odds ratio [OR] = 1.8 per standard deviation [SD] of roughness index) remained significant after adjustment for total cortex volume (OR = 2.0 per SD of roughness index).

CONCLUSIONS

A new algorithm to measure renal cortical surface roughness from CT scans detected rougher surface in older compared to younger kidneys, independent of cortical volume loss. This novel index may allow quantitative evaluation of nephrosclerosis in vivo using contrast-enhanced CT.

Quantification of heterogeneity as a biomarker in tumor imaging: a systematic review

BACKGROUND

Many techniques are proposed for the quantification of tumor heterogeneity as an imaging biomarker for differentiation between tumor types, tumor grading, response monitoring and outcome prediction. However, in clinical practice these methods are barely used. This study evaluates the reported performance of the described methods and identifies barriers to their implementation in clinical practice.

METHODOLOGY

The Ovid, Embase, and Cochrane Central databases were searched up to 20 September 2013. Heterogeneity analysis methods were classified into four categories, i.e., non-spatial methods (NSM), spatial grey level methods (SGLM), fractal analysis (FA) methods, and filters and transforms (F&T). The performance of the different methods was compared.

PRINCIPAL FINDINGS

Of the 7351 potentially relevant publications, 209 were included. Of these studies, 58% reported the use of NSM, 49% SGLM, 10% FA, and 28% F&T. Differentiation between tumor types, tumor grading and/or outcome prediction was the goal in 87% of the studies. Overall, the reported area under the curve (AUC) ranged from 0.5 to 1 (median 0.87). No relation was found between the performance and the quantification methods used, or between the performance and the imaging modality. A negative correlation was found between the tumor-feature ratio and the AUC, which is presumably caused by overfitting in small datasets. Cross-validation was reported in 63% of the classification studies. Retrospective analyses were conducted in 57% of the studies without a clear description.

CONCLUSIONS

In a research setting, heterogeneity quantification methods can differentiate between tumor types, grade tumors, and predict outcome and monitor treatment effects. To translate these methods to clinical practice, more prospective studies are required that use external datasets for validation: these datasets should be made available to the community to facilitate the development of new and improved methods.

Computer-aided detection of exophytic renal lesions on non-contrast CT images

Renal lesions are important extracolonic findings on computed tomographic colonography (CTC). They are difficult to detect on non-contrast CTC images due to low image contrast with surrounding objects. In this paper, we developed a novel computer-aided diagnosis system to detect a subset of renal lesions, exophytic lesions, by (1) exploiting efficient belief propagation to segment kidneys, (2) establishing an intrinsic manifold diffusion on kidney surface, (3) searching for potential lesion-caused protrusions with local maximum diffusion response, and (4) exploring novel shape descriptors, including multi-scale diffusion response, with machine learning to classify exophytic renal lesions. Experimental results on the validation dataset with 167 patients revealed that manifold diffusion significantly outperformed conventional shape features (p<1e-3) and resulted in 95% sensitivity with 15 false positives per patient for detecting exophytic renal lesions. Fivefold cross-validation also demonstrated that our method could stably detect exophytic renal lesions. These encouraging results demonstrated that manifold diffusion is a key means to enable accurate computer-aided diagnosis of renal lesions.

Development and evaluation of statistical shape modeling for principal inner organs on torso CT images

The shapes of the inner organs are important information for medical image analysis. Statistical shape modeling provides a way of quantifying and measuring shape variations of the inner organs in different patients. In this study, we developed a universal scheme that can be used for building the statistical shape models for different inner organs efficiently. This scheme combines the traditional point distribution modeling with a group-wise optimization method based on a measure called minimum description length to provide a practical means for 3D organ shape modeling. In experiments, the proposed scheme was applied to the building of five statistical shape models for hearts, livers, spleens, and right and left kidneys by use of 50 cases of 3D torso CT images. The performance of these models was evaluated by three measures: model compactness, model generalization, and model specificity. The experimental results showed that the constructed shape models have good "compactness" and satisfied the "generalization" performance for different organ shape representations; however, the "specificity" of these models should be improved in the future.

A review of computer-aided diagnosis in thoracic and colonic imaging

Medical imaging has been indispensable in medicine since the discovery of x-rays. Medical imaging offers useful information on patients' medical conditions and on the causes of their symptoms and diseases. As imaging technologies advance, a large number of medical images are produced which physicians/radiologists must interpret. Thus, computer aids are demanded and become indispensable in physicians' decision making based on medical images. Consequently, computer-aided detection and diagnosis (CAD) has been investigated and has been an active research area in medical imaging. CAD is defined as detection and/or diagnosis made by a radiologist/physician who takes into account the computer output as a "second opinion". In CAD research, detection and diagnosis of lung and colorectal cancer in thoracic and colonic imaging constitute major areas, because lung and colorectal cancers are the leading and second leading causes, respectively, of cancer deaths in the U.S. and also in other countries. In this review, CAD of the thorax and colon, including CAD for detection and diagnosis of lung nodules in thoracic CT, and that for detection of polyps in CT colonography, are reviewed.

CAD-associated reader error in CT colonography

RATIONALE AND OBJECTIVES

Computed tomographic colonographic interpretation with computer-aided detection (CAD) may be superior to unaided viewing, although polyp characteristics may influence accuracy. Reader error due to polyp characteristics was evaluated in a multiple-case, multiple-reader trial of computed tomographic colonography with CAD.

MATERIALS AND METHODS

Two experts retrospectively reviewed 52 positive cases (74 polyps) and categorized them as hard, moderate, or easy to detect. Each case was evaluated without and with CAD. Features that may influence a reader's ability to detect a polyp or to accept or reject a CAD mark were tabulated. The association between polyp characteristics and detection rates in the trial was assessed. The difference in detection rates (CAD vs unassisted) was calculated, and regression analysis was performed.

RESULTS

Of 64 polyps found by CAD, experts categorized 20 as hard, 28 as moderate, and 16 as easy to detect. Reader characterization errors predominated (47.3%) over other errors. Factors associated with lower detection rates included small size, flat morphology, and resemblance to a thickened fold. CAD was superior for polyps resembling lipomas compared to those that did not resemble lipomas (average increase in detection rate with CAD, 12.8% vs 5.5%; P < .05).

CONCLUSIONS

Polyp characteristic may impair computed tomographic colonographic interpretation augmented by CAD. Readers can avoid errors of measurement by evaluating diminutive polyp candidates with sample measurements. Caution should be taken when evaluating focally thick folds and when using visual impression to dismiss a polyp candidate as a lipoma when it is submerged in densely tagged fluid.

Sources of false positives in computer-assisted CT colonography

The application of computer-aided detection (CAD) is expected to improve reader sensitivity and to reduce inter-observer variance in computed tomographic (CT) colonography. However, current CAD systems display a large number of false-positive (FP) detections. The reviewing of a large number of FP CAD detections increases interpretation time, and it may also reduce the specificity and/or sensitivity of a computer-assisted reader. Therefore, it is important to be aware of the patterns and pitfalls of FP CAD detections. This pictorial essay reviews common sources of FP CAD detections that have been observed in the literature and in our experiments in computer-assisted CT colonography. Also the recommended computer-assisted reading technique is described.

Improving the accuracy of CTC interpretation: computer-aided detection

Computer-aided polyp detection aims to improve the accuracy of the colonography interpretation. The computer searches the colonic wall to look for polyplike protrusions and presents a list of suspicious areas to a physician for further analysis. Computer-aided polyp detection has developed rapidly in the past decade in the laboratory setting and has sensitivities comparable with those of experts. Computer-aided polyp detection tends to help inexperienced readers more than experienced ones and may also lead to small reductions in specificity. In its currently proposed use as an adjunct to standard image interpretation, computer-aided polyp detection serves as a spellchecker rather than an efficiency enhancer.

Comparison of polyp size and volume at CT colonography: implications for follow-up CT colonography

OBJECTIVE

The purpose of this study was to evaluate the reliability of polyp measurements at CT colonography and the factors that affect the measurements.

MATERIALS AND METHODS

Fifty colonoscopically proven cases of polyps 6 mm in diameter or larger were analyzed by two observers who measured each polyp in supine and prone views. Manual measurements of 2D volume by summation of areas, 2D maximum diameter, and 3D maximum diameter and automated measurements of 3D maximum diameter and volume were recorded for each observer and were repeated for one of the observers. Intraobserver and interobserver agreement was calculated. Analysis was performed to determine the measurement parameter that correlated most with summation-of-areas volume. Supine and prone measurements as a surrogate for tracking change in polyp size over time were analyzed to determine the measurement parameter with the least variation.

RESULTS

Maximum diameter measured manually on 3D images had the highest correlation with summation-of-areas volume. Manual summation-of-areas volume was found to have the least variation between supine and prone measurements.

CONCLUSION

Linear polyp measurement in the 3D endoluminal view appears to be the most reliable parameter for use in the decision to excise a polyp according to current guidelines. In our study, manual calculation of volume with summation of areas was found to be the most reliable measurement parameter for observing polyp growth over serial examinations. High reliability of polyp measurements is essential for adequate assessment of change in polyp size over serial examinations because many patients with intermediate-size polyps are expected to choose surveillance.

Computer-aided detection of polyps in CT colonography using logistic regression

We present a computer-aided detection (CAD) system for computed tomography colonography that orders the polyps according to clinical relevance. The CAD system consists of two steps: candidate detection and supervised classification. The characteristics of the detection step lead to specific choices for the classification system. The candidates are ordered by a linear logistic classifier (logistic regression) based on only three features: the protrusion of the colon wall, the mean internal intensity, and a feature to discard detections on the rectal enema tube. This classifier can cope with a small number of polyps available for training, a large imbalance between polyps and non-polyp candidates, a truncated feature space, unbalanced and unknown misclassification costs, and an exponential distribution with respect to candidate size in feature space. Our CAD system was evaluated with data sets from four different medical centers. For polyps larger than or equal to 6 mm we achieved sensitivities of respectively 95%, 85%, 85%, and 100% with 5, 4, 5, and 6 false positives per scan over 86, 48, 141, and 32 patients. A cross-center evaluation in which the system is trained and tested with data from different sources showed that the trained CAD system generalizes to data from different medical centers and with different patient preparations. This is essential to application in large-scale screening for colorectal polyps.

Pleural nodule identification in low-dose and thin-slice lung computed tomography

A completely automated system for the identification of pleural nodules in low-dose and thin-slice computed tomography (CT) of the lung has been developed. The directional-gradient concentration method has been applied to the pleura surface and combined with a morphological opening-based procedure to generate a list of nodule candidates. Each nodule candidate is characterized by 12 morphological and textural features, which are analyzed by a rule-based filter and a neural classifier. This detection system has been developed and validated on a dataset of 42 annotated CT scans. The k-fold cross validation has been used to evaluate the neural classifier performance. The system performance variability due to different ground truth agreement levels is discussed. In particular, the poor 44% sensitivity obtained on the ground truth with agreement level 1 (nodules annotated by only one radiologist) with six FP per scan grows up to the 72% if the underlying ground truth is changed to the agreement level 2 (nodules annotated by two radiologists).

Computer-aided detection (CAD) as a second reader using perspective filet view at CT colonography: effect on performance of inexperienced readers

AIM

To evaluate whether computer-aided detection (CAD) as a second reader using perspective filet view [three-dimensional (3D) filet] improves the performance of inexperienced readers at computed tomography colonography (CTC) compared with unassisted 3D filet and unassisted two-dimensional (2D) CTC.

MATERIAL AND METHODS

Fifty symptomatic patients underwent CTC and same-day colonoscopy with segmental unblinding. Two inexperienced readers read the CTC studies on 3D filet and 2D several weeks apart. Four months later, readers re-read the cases only evaluating CAD marks using 3D filet. Suspicious CAD marks not previously described on 3D filet were recorded. Jackknife free-response receiver operating characteristic (JAFROC-1) analysis was used to compare the observers' performances in detecting lesions with 3D filet, 2D and 3D filet with CAD.

RESULTS

One hundred and three lesions > or =3mm were detected at colonoscopy with segmental unblinding. CAD alone had a sensitivity of 73% (75/103) at a mean false-positive rate per patient of 12.8 in supine and 11.4 in prone. For inexperienced readers sensitivities with 3D filet with CAD were 58% (60/103) and 48% (50/103) with an improvement of 14-16 percentage points (p<0.05) compared with 2D and of 10-11 percentage points (p<0.05) compared with 3D filet. For inexperienced readers, the false-positive rate was 25-41% and 71-200% higher with 3D filet with CAD compared with 3D filet and 2D, respectively. JAFROC-1 analysis showed no significant differences in per-lesion overall performance among reading modes (p=0.8).

CONCLUSION

CAD applied as a second reader using 3D filet increased both sensitivity and the number of false positives by inexperienced readers compared with 3D filet and 2D, thus not improving overall performance, i.e., the ability to distinguish between lesions and non-lesions.

Virtual colonoscopy in paediatric patients Usefulness of a colon dissection technique

OBJECTIVE

To determine the usefulness of perspective-filet view for polypoid lesions in paediatric patients in comparison with conventional virtual colonoscopy (VC) analysis and optical colonoscopy.

METHODS

Sixty-one patients (mean age 5 years old) with a previous episode of rectal bleeding were studied using a 16 slices CT scanner. All patients underwent a colonic preparation. Two acquisitions were done in supine and prone positions with slices of 2mm thickness; increment 1mm, 30-50mA; 90-120kV. In a workstation an experienced radiologist reviewed images twice. The first read was done using the conventional virtual colonoscopy technique with the evaluation of two-dimensional (2D), three-dimensional (3D) and endoscopical images. Later, in a second session, perspective-filet view was used. It shows a 360 degrees unrolled visualization of the inner colon. The presence, size and location of the lesions were determined. A record of the reading time was made.

RESULTS

At per patient evaluation the conventional virtual colonoscopy analysis obtained a sensitivity of 86% and a specificity of 98%. The perspective-filet view obtained a sensitivity of 91% and a specificity of 99%. In the evaluation on a per lesion basis the conventional analysis had a sensitivity of 81% and a specificity of 88%. Perspective-filet view, had a sensitivity of 82% and specificity of 90%. The average total reading time using conventional colonoscopy technique was 18+/-3min, versus 4+/-1min using the perspective-filet view.

CONCLUSION

Virtual colon dissection with perspective-filet view is more time-efficient than conventional virtual colonoscopy evaluation with correct correlation in results.

Anniversary paper: History and status of CAD and quantitative image analysis: the role of Medical Physics and AAPM

The roles of physicists in medical imaging have expanded over the years, from the study of imaging systems (sources and detectors) and dose to the assessment of image quality and perception, the development of image processing techniques, and the development of image analysis methods to assist in detection and diagnosis. The latter is a natural extension of medical physicists' goals in developing imaging techniques to help physicians acquire diagnostic information and improve clinical decisions. Studies indicate that radiologists do not detect all abnormalities on images that are visible on retrospective review, and they do not always correctly characterize abnormalities that are found. Since the 1950s, the potential use of computers had been considered for analysis of radiographic abnormalities. In the mid-1980s, however, medical physicists and radiologists began major research efforts for computer-aided detection or computer-aided diagnosis (CAD), that is, using the computer output as an aid to radiologists-as opposed to a completely automatic computer interpretation-focusing initially on methods for the detection of lesions on chest radiographs and mammograms. Since then, extensive investigations of computerized image analysis for detection or diagnosis of abnormalities in a variety of 2D and 3D medical images have been conducted. The growth of CAD over the past 20 years has been tremendous-from the early days of time-consuming film digitization and CPU-intensive computations on a limited number of cases to its current status in which developed CAD approaches are evaluated rigorously on large clinically relevant databases. CAD research by medical physicists includes many aspects-collecting relevant normal and pathological cases; developing computer algorithms appropriate for the medical interpretation task including those for segmentation, feature extraction, and classifier design; developing methodology for assessing CAD performance; validating the algorithms using appropriate cases to measure performance and robustness; conducting observer studies with which to evaluate radiologists in the diagnostic task without and with the use of the computer aid; and ultimately assessing performance with a clinical trial. Medical physicists also have an important role in quantitative imaging, by validating the quantitative integrity of scanners and developing imaging techniques, and image analysis tools that extract quantitative data in a more accurate and automated fashion. As imaging systems become more complex and the need for better quantitative information from images grows, the future includes the combined research efforts from physicists working in CAD with those working on quantitative imaging systems to readily yield information on morphology, function, molecular structure, and more-from animal imaging research to clinical patient care. A historical review of CAD and a discussion of challenges for the future are presented here, along with the extension to quantitative image analysis.

Does a computer-aided detection algorithm in a second read paradigm enhance the performance of experienced computed tomography colonography readers in a population of increased risk?

We prospectively determined whether computer-aided detection (CAD) could improve the performance characteristics of computed tomography colonography (CTC) in a population of increased risk for colorectal cancer. Therefore, we included 170 consecutive patients that underwent both CTC and colonoscopy. All findings >or=6 mm were evaluated at colonoscopy by segmental unblinding. We determined per-patient sensitivity and specificity for polyps >or=6 mm and >or=10 mm without and with computer-aided detection (CAD). The McNemar test was used for comparison the results without and with CAD. Unblinded colonoscopy detected 50 patients with lesions >or=6 mm and 25 patients with lesions >or=10 mm. Sensitivity of CTC without CAD for these size categories was 80% (40/50, 95% CI: 69-81%) and 64% (16/25, 95% CI: 45-83%), respectively. CTC with CAD detected one additional patient with a lesion >or=6 mm and two with a lesion >or=10 mm, resulting in a sensitivity of 82% (41/50, 95% CI: 71-93%) (p = 0.50) and 72% (18/25, 95% CI: 54-90%) (p = 1.0), respectively. Specificity without CAD for polyps >or=6 mm and >or=10 mm was 84% (101/120, 95% CI: 78-91%) and 94% (136/145, 95% CI: 90-98%), respectively. With CAD, the specificity remained (nearly) unchanged: 83% (99/120, 95% CI: 76-89%) and 94% (136/145, 95% CI: 90-98%), respectively. Thus, although CTC with CAD detected a few more patients than CTC without CAD, it had no statistically significant positive influence on CTC performance.

Volume-based Feature Analysis of Mucosa for Automatic Initial Polyp Detection in Virtual Colonoscopy

In this paper, we present a volume-based mucosa-based polyp candidate determination scheme for automatic polyp detection in computed colonography. Different from most of the existing computer-aided detection (CAD) methods where mucosa layer is a one-layer surface, a thick mucosa of 3-5 voxels wide fully reflecting partial volume effect is intentionally extracted, which excludes the direct applications of the traditional geometrical features. In order to address this dilemma, fast marching-based adaptive gradient/curvature and weighted integral curvature along normal directions (WICND) are developed for volume-based mucosa. In doing so, polyp candidates are optimally determined by computing and clustering these fast marching-based adaptive geometrical features. By testing on 52 patients datasets in which 26 patients were found with polyps of size 4-22 mm, both the locations and number of polyp candidates detected by WICND and previously developed linear integral curvature (LIC) were compared. The results were promising that WICND outperformed LIC mainly in two aspects: (1) the number of detected false positives was reduced from 706 to 132 on average, which significantly released our burden of machine learning in the feature space, and (2) both the sensitivity and accuracy of polyp detection have been slightly improved, especially for those polyps smaller than 5mm.

Mixture of expert 3D massive-training ANNs for reduction of multiple types of false positives in CAD for detection of polyps in CT colonography

One of the major challenges in computer-aided detection (CAD) of polyps in CT colonography (CTC) is the reduction of false-positive detections (FPs) without a concomitant reduction in sensitivity. A large number of FPs is likely to confound the radiologist's task of image interpretation, lower the radiologist's efficiency, and cause radiologists to lose their confidence in CAD as a useful tool. Major sources of FPs generated by CAD schemes include haustral folds, residual stool, rectal tubes, the ileocecal valve, and extra-colonic structures such as the small bowel and stomach. Our purpose in this study was to develop a method for the removal of various types of FPs in CAD of polyps while maintaining a high sensitivity. To achieve this, we developed a "mixture of expert" three-dimensional (3D) massive-training artificial neural networks (MTANNs) consisting of four 3D MTANNs that were designed to differentiate between polyps and four categories of FPs: (1) rectal tubes, (2) stool with bubbles, (3) colonic walls with haustral folds, and (4) solid stool. Each expert 3D MTANN was trained with examples from a specific non-polyp category along with typical polyps. The four expert 3D MTANNs were combined with a mixing artificial neural network (ANN) such that different types of FPs could be removed. Our database consisted of 146 CTC datasets obtained from 73 patients whose colons were prepared by standard pre-colonoscopy cleansing. Each patient was scanned in both supine and prone positions. Radiologists established the locations of polyps through the use of optical-colonoscopy reports. Fifteen patients had 28 polyps, 15 of which were 5-9 mm and 13 were 10-25 mm in size. The CTC cases were subjected to our previously reported CAD method consisting of centerline-based extraction of the colon, shape-based detection of polyp candidates, and a Bayesian-ANN-based classification of polyps. The original CAD method yielded 96.4% (27/28) by-polyp sensitivity with an average of 3.1 (224/73) FPs per patient. The mixture of expert 3D MTANNs removed 63% (142/224) of the FPs without the loss of any true positive; thus, the FP rate of our CAD scheme was improved to 1.1 (82/73) FPs per patient while the original sensitivity was maintained. By use of the mixture of expert 3D MTANNs, the specificity of a CAD scheme for detection of polyps in CTC was substantially improved while a high sensitivity was maintained.

Computer-aided detection for CT colonography: update 2007

Computed tomographic colonography (CTC) is an emerging technique for polyp detection in the colon. However, lesion detection can be challenging due to insufficient patient preparation, chosen CT technique or reader imperfection. The primary goal of computer-aided detection (CAD) for CTC is locating possible polyps, and presenting the reader with these polyp candidates. Other goals are sensitivity improvement and reduction of reading time and inter-observer variability. The multistep CAD procedure typically consists of segmentation of the colonic wall (e.g. region growing); selection of intermediate polyp candidates (curvature analysis, sphere fitting, normal analysis, slope density function ...); classification of final candidates for detection and listing suspicious polyps (location, size and volume). Remaining task for the radiologist is the validation or rejection of the polyp candidates. State-of-the-art CAD systems should require minimal or even no user interaction for the extraction of the colonic wall, offer a computation time less than 10-20 min and high sensitivity and specificity for different polyp sizes and shapes, with a low number of false positives. These systems have the potential to increase radiologist's performance and to decrease inter-reader variability. Besides CAD key techniques we also discuss new developments in CAD and describe recent applications facilitating CTC.

CT colonography: computer-aided detection of morphologically flat T1 colonic carcinoma

The purpose was to evaluate the ability of computer-aided detection (CAD) software to detect morphologically flat early colonic carcinoma using CT colonography (CTC). Twenty-four stage T1 colonic carcinomas endoscopically classified as flat (width over twice height) were accrued from patients undergoing staging CTC. Tumor location was annotated by three experienced radiologists in consensus aided by the endosocpic report. CAD software was then applied at three settings of sphericity (0, 0.75, and 1). Computer prompts were categorized as either true positive (overlapping tumour boundary) or false positive. True positives were subclassified as focal or non focal. The 24 cancers were endoscopically classified as type IIa (n=11) and type IIa+IIc (n=13). Mean size (range) was 27 mm (7-70 mm). CAD detected 20 (83.3%), 17 (70.8%), and 13 (54.1%) of the 24 cancers at filter settings of 0, 0.75, and 1, respectively with 3, 4, and 8 missed cancers of type IIa, respectively. The mean total number of false-positive CAD marks per patient at each filter setting was 36.5, 21.1, and 9.5, respectively, excluding polyps. At all settings, >96.1% of CAD true positives were classified as focal. CAD may be effective for the detection of morphologically flat cancer, although minimally raised laterally spreading tumors remain problematic.

CT colonography and computer-aided detection: effect of false-positive results on reader specificity and reading efficiency in a low-prevalence screening population

PURPOSE

To retrospectively evaluate the effect of increasing numbers of computer-aided detection (CAD)-generated false-positive (FP) marks on reader specificity and reporting times by using computed tomographic (CT) colonography in a low-prevalence screening population.

MATERIALS AND METHODS

Ethics committee approval and informed consent were obtained for this HIPAA-compliant study. Four readers each read 48 data sets (26 men, 22 women; mean age, 57 years) from a screening population (three containing polyps) without CAD application, followed by review of the CAD output and recorded findings and diagnostic confidence. The 45 data sets that were designated as normal were chosen such that 22 generated 15 or fewer FP CAD marks and 23 generated more than 15 FP CAD marks. Sensitivity, specificity, and receiver operating characteristic (ROC) curves were calculated with and without CAD. The relationships between the number of CAD FP marks and reader confidence, reporting times, and correct data set classification were analyzed by using linear and logistic regression.

RESULTS

Across all readers, CAD resulted in four additional FP detections. Overall reader sensitivity and specificity (6-mm polyp threshold) before and after CAD application were 0.75 (95% confidence interval [CI]: 0.43, 0.95) versus 0.83 (95% CI: 0.52, 0.98) and 0.96 (95% CI: 0.91, 0.98) versus 0.93 (95% CI: 0.88, 0.96), respectively. The area under the ROC curve increased from 0.57 (95% CI: 0.34, 0.80) to 0.61 (95% CI: 0.42, 0.80). There was no correlation between an increasing number of CAD FP marks and reader confidence (P = .71) or correct study classification (P = .23), but there was a positive correlation with CAD-assisted reading times (0.06 [95% CI: 0.02, 0.10], P = .002).

CONCLUSION

Increasing numbers of CAD FP marks did not adversely influence correct reader study classification or diagnostic confidence, although reporting times did increase.

Critical analysis of the performance of double-contrast barium enema for detecting colorectal polyps > or = 6 mm in the era of CT colonography

OBJECTIVE

The purpose of our study was to perform a meta-analysis comparing the performance of double-contrast barium enema (DCBE) with CT colonography (CTC) for the detection of colorectal polyps > or = 6 mm using endoscopy as the gold standard.

MATERIALS AND METHODS

Prospective DCBE and CTC studies were identified. Percentages of polyps and of patients with polyps > or = 10 mm and 6-9 mm were abstracted. The performance of DCBE versus CTC was determined by separately evaluating each technique's performance versus that of endoscopy, and contrasting the techniques. The I-squared statistic and Fisher's exact test were used for heterogeneity, the Cochran-Mantel-Haenszel and the Kruskal-Wallis tests for correlation, and the A(z) test for comparing pooled weighted estimates of performance.

RESULTS

Eleven studies of DCBE (5,995 patients, 1,548 polyps) and 30 studies of CTC (6,573 patients, 2,348 polyps) fulfilled inclusion criteria. For polyps > or = 10 mm, a 0.121-per-patient sensitivity difference favored CTC (p < 0.0001; DCBE, 0.702 [95% CI, 0.687-0.715]; CTC, 0.823 [0.809-0.836]). For polyps > or = 10 mm, a 0.031-per-polyp sensitivity difference favored CTC (p < 0.0001; DCBE, 0.715 [0.703-0.726]; CTC, 0.746 [0.735-0.757]). For polyps > or = 10 mm, a specificity difference of 0.104 favored CTC (p = 0.001; DCBE, 0.850 [0.847-0.855]; CTC, 0.954 [0.952-0.955]). DCBE was also significantly less sensitive for 6- to 9-mm polyps (p < 0.001).

CONCLUSION

DCBE has statistically lower sensitivity and specificity than CTC for detecting colorectal polyps > or = 6 mm.

Manual and automated polyp measurement comparison of CT colonography with optical colonoscopy

RATIONALE AND OBJECTIVES

The purpose of this study was to assess (1) the agreement of two-dimensional (2D) and three-dimensional (3D) manual and automated polyp linear diameter measurements at CT colonography (CTC), with optical colonoscopic equivalents and (2) intraobserver and interobserver agreement of the CTC measurements.

MATERIALS AND METHODS

Using the same CTC system, two radiologists independently measured the maximum linear diameter of 44 polyps (reference size 3-15 mm) matched on CTC and optical colonoscopy: manual 2D optimized multiplanar reformatted planes with standard window settings (level 1500 HU, width -200 HU), manual 3D measurement with software calipers and automated 3D measurement with software. After 2 weeks, polyps were measured again. Compatibility of CTC measurement with that of optical colonoscopy and measurement reproducibility was assessed statistically.

RESULTS

In the manual measurement, 44 polyps were analyzed and 41 in automated measurement; three polyps could not be extracted. Although the measurement difference was noted for automated, manual 3D, and manual 2D measurements, statistically supported agreement with optical colonoscopic measurement was noted only with manual 2D measurement for both observers. However, 95% limits of agreement were wide for all the measurement methods. When categorized according to the optical colonoscopic measurement, manual 2D, 3D, and automated measurements showed "good" agreement. Although intraobserver and interobserver agreement was good with manual measurement, intraobserver and interobserver agreement was excellent with automated measurement.

CONCLUSION

Manual 2D measurements demonstrated trends of better approximation to optical colonoscopy measurements than manual 3D or automated measurements. And automated measurement eliminated intraobserver and interobserver variability. For noninvasive CTC surveillance, manual 2D measurements are expected to measure medium-sized polyps with sufficient agreement with optical colonoscopic measurements and excellent intraobserver and interobserver variability, especially if combined with automated measurement.

Computer-aided detection for CT colonography: incremental benefit of observer training

The purpose of this study was to investigate the incremental effect of focused training on observer performance when using computer-assisted detection (CAD) software to interpret CT colonography (CTC). Six radiologists who were relatively inexperienced with CTC interpretation underwent 1 day of focused training before reading 20 patient datasets with the assistance of CAD software (ColonCAR 1.3, Medicsight PLC). Sensitivity, specificity and interpretation times were determined and compared with previous performance when reading the same datasets but without the benefit of focused training, using the binomial exact test and Wilcoxon's signed rank test. Per-polyp sensitivity improved after training by 18% overall (95% confidence interval (CI): 14-24%, p<0.001) and was greatest for polyps of 6-9 mm (26%, 95% CI: 18-34%, p<0.001). Absolute sensitivity was 23% (9-36%), 51% (33-71%) and 74% (44-100%) for polyps of <or=5 mm, 6-9 mm and >or=10 mm, respectively. Specificity fell significantly after focused training (median of 5.5 false positives per 20 datasets (interquartile range (IQR): 4-6) post-training vs median of 2.5 (IQR: 1-5) pre-training, p = 0.03). Interpretation time also increased significantly after training (from a median of 9.3 min (IQR: 9.3-14.5 min) to a median of 17.1 min (IQR: 15.4-19.4 min), p = 0.03). In conclusion, one day of training increases observer polyp sensitivity when using CAD for CTC at the expense of increased reporting time and reduction in specificity.

Computer-aided detection of colorectal polyps: can it improve sensitivity of less-experienced readers? Preliminary findings

PURPOSE

To determine whether computer-aided detection (CAD) applied to computed tomographic (CT) colonography can help improve sensitivity of polyp detection by less-experienced radiologist readers, with colonoscopy or consensus used as the reference standard.

MATERIALS AND METHODS

The release of the CT colonographic studies was approved by the individual institutional review boards of each institution. Institutions from the United States were HIPAA compliant. Written informed consent was waived at all institutions. The CT colonographic studies in 30 patients from six institutions were collected; 24 images depicted at least one confirmed polyp 6 mm or larger (39 total polyps) and six depicted no polyps. By using an investigational software package, seven less-experienced readers from two institutions evaluated the CT colonographic images and marked or scored polyps by using a five-point scale before and after CAD. The time needed to interpret the CT colonographic findings without CAD and then to re-evaluate them with CAD was recorded. For each reader, the McNemar test, adjusted for clustered data, was used to compare sensitivities for readers without and with CAD; a Wilcoxon signed-rank test was used to analyze the number of false-positive results per patient.

RESULTS

The average sensitivity of the seven readers for polyp detection was significantly improved with CAD-from 0.810 to 0.908 (P=.0152). The number of false-positive results per patient without and with CAD increased from 0.70 to 0.96 (95% confidence interval for the increase: -0.39, 0.91). The mean total time for the readings was 17 minutes 54 seconds; for interpretation of CT colonographic findings alone, the mean time was 14 minutes 16 seconds; and for review of CAD findings, the mean time was 3 minutes 38 seconds.

CONCLUSION

Results of this feasibility study suggest that CAD for CT colonography significantly improves per-polyp detection for less-experienced readers.

Volume CT: State-of-the-Art Reporting

OBJECTIVE

CT has undergone generational change that has led to true volume imaging. Interpretation of volume images requires interaction between the radiologist and the volume data sets. The aim of this review is to examine postprocessing options and the evidence in the literature for changing the process of reporting to digital volume reporting.

CONCLUSION

Diagnostic confidence and the accuracy of interpretation of volume CT images have increased with improvements in postprocessing techniques.