CAD techniques, challenges, and controversies in computed tomographic colonography

Emara AH, Al-Sarem M, Kurdi NA. Toward Robust Lung Cancer Diagnosis: Integrating Multiple CT Datasets, Curriculum Learning, and Explainable AI

Background and Objectives: Computer-aided diagnostic systems have achieved remarkable success in the medical field, particularly in diagnosing malignant tumors, and have done so at a rapid pace. However, the generalizability of the results remains a challenge for researchers and decreases the credibility of these models, which represents a point of criticism by physicians and specialists, especially given the sensitivity of the field. This study proposes a novel model based on deep learning to enhance lung cancer diagnosis quality, understandability, and generalizability. Methods: The proposed approach uses five computed tomography (CT) datasets to assess diversity and heterogeneity. Moreover, the mixup augmentation technique was adopted to facilitate the reliance on salient characteristics by combining features and CT scan labels from datasets to reduce their biases and subjectivity, thus improving the model's generalization ability and enhancing its robustness. Curriculum learning was used to train the model, starting with simple sets to learn complicated ones quickly. Results: The proposed approach achieved promising results, with an accuracy of 99.38%; precision, specificity, and area under the curve (AUC) of 100%; sensitivity of 98.76%; and F1-score of 99.37%. Additionally, it scored a 00% false positive rate and only a 1.23% false negative rate. An external dataset was used to further validate the proposed method's effectiveness. The proposed approach achieved optimal results of 100% in all metrics, with 00% false positive and false negative rates. Finally, explainable artificial intelligence (XAI) using Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to better understand the model. Conclusions: This research proposes a robust and interpretable model for lung cancer diagnostics with improved generalizability and validity. Incorporating mixup and curriculum training supported by several datasets underlines its promise for employment as a diagnostic device in the medical industry.

Interobserver Variation of Colonic Polyp Measurement at Computed Tomography Colonography

BACKGROUND

The concept of "advanced polyps" is well accepted and is defined as polyps ≥10 mm and/or those having a villous component and/or demonstrating areas of dysplasia. Of these parameters, computed tomography colonography (CTC) can only document size. The accepted management of CTC-detected "advanced polyps" is to recommend excision if feasible, whereas the management of "intermediate" (6-9 mm) polyps is more controversial, and interval surveillance may be acceptable. Therefore, distinction between 6-9 mm and ≥10 mm is important.

METHODS

Datasets containing 26 polyps originally reported as between 8-12 mm in diameter were reviewed independently by 4 CTC-accredited radiologists. Observers tabulated the largest measurement for each polyp on axial, coronal, sagittal, and endoluminal views at lung-window settings. These measurements were also compared to those determined by the computer-aided detection (CAD) software.

RESULTS

The interobserver reliability intra-class correlation coefficient (ICC) for sagittal projection was 0.80 ("excellent" category of Hosmer and Lemeshow [2004]), 0.71 for axial ("acceptable"), 0.69 for coronal, and 0.41 for endoluminal ("unacceptable"). The largest of sagittal/axial/coronal measurement gave the best reliability with the smallest variance (ICC = 0.80; 95% CI 0.67-0.89). For 8 of 26 polyps, at least one radiologist's measurement placed the polyp in a different category compared to a colleague. For the majority of the polyps, the CAD significantly overestimated the readings compared to the largest of the manual measurements with an average difference of 1.6 mm (P < .0001 for sagittal/axial/coronal). This resulted in 33% of polyps falling into a different category-10% were lower and 23% were higher (P < .034).

CONCLUSION

It is apparent that around the cutoff point of 10 mm between "advanced" and "intermediate" polyps, interobserver performance is variable.

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.

Cloud-Based Evaluation of Anatomical Structure Segmentation and Landmark Detection Algorithms: VISCERAL Anatomy Benchmarks

Variations in the shape and appearance of anatomical structures in medical images are often relevant radiological signs of disease. Automatic tools can help automate parts of this manual process. A cloud-based evaluation framework is presented in this paper including results of benchmarking current state-of-the-art medical imaging algorithms for anatomical structure segmentation and landmark detection: the VISCERAL Anatomy benchmarks. The algorithms are implemented in virtual machines in the cloud where participants can only access the training data and can be run privately by the benchmark administrators to objectively compare their performance in an unseen common test set. Overall, 120 computed tomography and magnetic resonance patient volumes were manually annotated to create a standard Gold Corpus containing a total of 1295 structures and 1760 landmarks. Ten participants contributed with automatic algorithms for the organ segmentation task, and three for the landmark localization task. Different algorithms obtained the best scores in the four available imaging modalities and for subsets of anatomical structures. The annotation framework, resulting data set, evaluation setup, results and performance analysis from the three VISCERAL Anatomy benchmarks are presented in this article. Both the VISCERAL data set and Silver Corpus generated with the fusion of the participant algorithms on a larger set of non-manually-annotated medical images are available to the research community.

Comparison of 64-Detector CT Colonography and Conventional Colonoscopy in the Detection of Colorectal Lesions

Background:

Colon cancer is a leading cause of morbidity and mortality in developed countries. The early detection of colorectal cancer using screening programs is important for managing early-stage colorectal cancers and polyps. Modalities that allow examination of the entire colon are conventional colonoscopy, double contrast barium enema examination and multi-detector computed tomography (MDCT) colonography.

Objectives:

To compare CT colonography and conventional colonoscopy results and to evaluate the accuracy of CT colonography for detecting colorectal lesions.

Patients and Methods:

In a prospective study performed at Gastroenterology and Radiology Departments of Medical Faculty of Eskisehir Osmangazi University, CT colonography and colonoscopy results of 31 patients with family history of colorectal carcinoma, personal or family history of colorectal polyps, lower gastrointestinal tract bleeding, change in bowel habits, iron deficiency anemia and abdominal pain were compared. Regardless of the size, CT colonography and conventional colonoscopy findings for all the lesions were cross - tabulated and the sensitivity, specificity, and positive and negative predictive values were calculated. To assess the agreement between CT colonography and conventional colonoscopy examinations, the Kappa coefficient of agreementt was used. Statistical analysis was performed by SPSS ver 15.0.

Results:

Regardless of the size, MDCT colonography showed 83% sensitivity and 95% specificity, with a positive predictive value of 95% and a negative predictive value of 83% for the detection of colorectal polyps and masses. MDCT colonography displayed 92% sensitivity and 95% specificity, with a positive predictive value of 92% and a negative predictive value of 95% for polyps ≥ 10 mm. For polyps between 6mm and 9 mm, MDCT colonography displayed 75% sensitivity and 100% specificity, with a positive predictive value of 100% and a negative predictive value of 90%. For polyps ≤ 5 mm MDCT colonography displayed 88% sensitivity and 100% specificity with a positive predictive value of 100% and a negative predictive value of 95%.

Conclusions:

CT colonography is a safe and minimally invasive technique, a valuable diagnostic tool for examining the entire colon and a good alternative compared to other colorectal cancer screening tests because of its high sensitivity values in colorectal lesions over 1 cm.

Smart Colonography for Distributed Medical Databases with Group Kernel Feature Analysis

Computer-Aided Detection (CAD) of polyps in Computed Tomographic (CT) colonography is currently very limited since a single database at each hospital/institution doesn't provide sufficient data for training the CAD system's classification algorithm. To address this limitation, we propose to use multiple databases, (e.g., big data studies) to create multiple institution-wide databases using distributed computing technologies, which we call smart colonography. Smart colonography may be built by a larger colonography database networked through the participation of multiple institutions via distributed computing. The motivation herein is to create a distributed database that increases the detection accuracy of CAD diagnosis by covering many true-positive cases. Colonography data analysis is mutually accessible to increase the availability of resources so that the knowledge of radiologists is enhanced. In this article, we propose a scalable and efficient algorithm called Group Kernel Feature Analysis (GKFA), which can be applied to multiple cancer databases so that the overall performance of CAD is improved. The key idea behind the proposed GKFA method is to allow the feature space to be updated as the training proceeds with more data being fed from other institutions into the algorithm. Experimental results show that GKFA achieves very good classification accuracy.

Colorectal polyp segmentation using front propagation on surfaces guided by shape

Polyp size is a biomarker of colon cancer. Manual size measurements are subject to a variety of sources of error. We present an automatic method for segmenting a polyp from a user clicked point. The method is based on front propagation on surface mesh, guided by features that characterize the local protrudedness, its thickness, its resemblance to wall like structures and ridge measures. These measures are designed to characterize growths in the colonic lumen and differentiate polyp growth from other protrusions such as haustral folds. These measures are aggregated and smoothed. Fast marching guided by these features extracts the polyps. Empirical observation suggests that the method successfully segments a variety of polyp shapes in less than 2 s.

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.

The role of informatics in health care reform

Improving health care quality while simultaneously reducing cost has become a high priority of health care reform. Informatics is crucial in tackling this challenge. The American Recovery and Reinvestment Act of 2009 mandates adaptation and "meaningful use " of health information technology. In this review, we will highlight several areas in which informatics can make significant contributions, with a focus on radiology. We also discuss informatics related to the increasing imperatives of state and local regulations (such as radiation dose tracking) and quality initiatives.

Machine learning and radiology

In this paper, we give a short introduction to machine learning and survey its applications in radiology. We focused on six categories of applications in radiology: medical image segmentation, registration, computer aided detection and diagnosis, brain function or activity analysis and neurological disease diagnosis from fMR images, content-based image retrieval systems for CT or MRI images, and text analysis of radiology reports using natural language processing (NLP) and natural language understanding (NLU). This survey shows that machine learning plays a key role in many radiology applications. Machine learning identifies complex patterns automatically and helps radiologists make intelligent decisions on radiology data such as conventional radiographs, CT, MRI, and PET images and radiology reports. In many applications, the performance of machine learning-based automatic detection and diagnosis systems has shown to be comparable to that of a well-trained and experienced radiologist. Technology development in machine learning and radiology will benefit from each other in the long run. Key contributions and common characteristics of machine learning techniques in radiology are discussed. We also discuss the problem of translating machine learning applications to the radiology clinical setting, including advantages and potential barriers.

Medical decision-making system of ultrasound carotid artery intima-media thickness using neural networks

The objective of this work is to develop and implement a medical decision-making system for an automated diagnosis and classification of ultrasound carotid artery images. The proposed method categorizes the subjects into normal, cerebrovascular, and cardiovascular diseases. Two contours are extracted for each and every preprocessed ultrasound carotid artery image. Two types of contour extraction techniques and multilayer back propagation network (MBPN) system have been developed for classifying carotid artery categories. The results obtained show that MBPN system provides higher classification efficiency, with minimum training and testing time. The outputs of decision support system are validated with medical expert to measure the actual efficiency. MBPN system with contour extraction algorithms and preprocessing scheme helps in developing medical decision-making system for ultrasound carotid artery images. It can be used as secondary observer in clinical decision making.

Massive-training support vector regression and Gaussian process for false-positive reduction in computer-aided detection of polyps in CT colonography

PURPOSE

A massive-training artificial neural network (MTANN) has been developed for the reduction of false positives (FPs) in computer-aided detection (CADe) of polyps in CT colonography (CTC). A major limitation of the MTANN is the long training time. To address this issue, the authors investigated the feasibility of two state-of-the-art regression models, namely, support vector regression (SVR) and Gaussian process regression (GPR) models, in the massive-training framework and developed massive-training SVR (MTSVR) and massive-training GPR (MTGPR) for the reduction of FPs in CADe of polyps.

METHODS

The authors applied SVR and GPR as volume-processing techniques in the distinction of polyps from FP detections in a CTC CADe scheme. Unlike artificial neural networks (ANNs), both SVR and GPR are memory-based methods that store a part of or the entire training data for testing. Therefore, their training is generally fast and they are able to improve the efficiency of the massive-training methodology. Rooted in a maximum margin property, SVR offers excellent generalization ability and robustness to outliers. On the other hand, GPR approaches nonlinear regression from a Bayesian perspective, which produces both the optimal estimated function and the covariance associated with the estimation. Therefore, both SVR and GPR, as the state-of-the-art nonlinear regression models, are able to offer a performance comparable or potentially superior to that of ANN, with highly efficient training. Both MTSVR and MTGPR were trained directly with voxel values from CTC images. A 3D scoring method based on a 3D Gaussian weighting function was applied to the outputs of MTSVR and MTGPR for distinction between polyps and nonpolyps. To test the performance of the proposed models, the authors compared them to the original MTANN in the distinction between actual polyps and various types of FPs in terms of training time reduction and FP reduction performance. The authors' CTC database consisted of 240 CTC data sets obtained from 120 patients in the supine and prone positions. The training set consisted of 27 patients, 10 of which had 10 polyps. The authors selected 10 nonpolyps (i.e., FP sources) from the training set. These ten polyps and ten nonpolyps were used for training the proposed models. The testing set consisted of 93 patients, including 19 polyps in 7 patients and 86 negative patients with 474 FPs produced by an original CADe scheme.

RESULTS

With the MTSVR, the training time was reduced by a factor of 190, while a FP reduction performance [by-polyp sensitivity of 94.7% (18/19) with 2.5 (230/93) FPs/patient] comparable to that of the original MTANN [the same sensitivity with 2.6 (244/93) FPs/patient] was achieved. The classification performance in terms of the area under the receiver-operating-characteristic curve value of the MTGPR (0.82) was statistically significantly higher than that of the original MTANN (0.77), with a two-sided p-value of 0.03. The MTGPR yielded a 94.7% (18/19) by-polyp sensitivity at a FP rate of 2.5 (235/93) per patient and reduced the training time by a factor of 1.3.

CONCLUSIONS

Both MTSVR and MTGPR improve the efficiency of the training in the massive-training framework while maintaining a comparable performance.

Colonic polyps: inheritance, susceptibility, risk evaluation, and diagnostic management

Colorectal cancer (CRC) is the third-ranked neoplasm in order of incidence and mortality, worldwide, and the second cause of cancer death in industrialized countries. One of the most important environmental risk factors for CRC is a Western-type diet, which is characterized by a low-fiber and high-fat content. Up to 25% of patients with CRC have a family history for CRC, and a fraction of these patients are affected by hereditary syndromes, such as familial adenomatous polyposis, Gardner or Turcot syndromes, or hereditary nonpolyposis colorectal cancer. The onset of CRC is triggered by a well-defined combination of genetic alterations, which form the bases of the adenoma-carcinoma sequence hypothesis and justify the set-up of CRC screening techniques. Several screening and diagnostic tests for CRC are illustrated, including rectosigmoidoscopy, optical colonoscopy (OC), double contrast barium enema (DCBE), and computed tomography colonography (CTC). The strengths and weaknesses of each technique are discussed. Particular attention is paid to CTC, which has evolved from an experimental technique to an accurate and mature diagnostic approach, and gained wide acceptance and clinical validation for CRC screening. This success of CTC is due mainly to its ability to provide cross-sectional analytical images of the entire colon and secondarily detect extracolonic findings, with minimal invasiveness and lower cost than OC, and with greater detail and diagnostic accuracy than DCBE. Moreover, especially with the advent and widespread availability of modern multidetector CT scanners, excellent quality 2D and 3D reconstructions of the large bowel can be obtained routinely with a relatively low radiation dose. Computer-aided detection systems have also been developed to assist radiologists in reading CTC examinations, improving overall diagnostic accuracy and potentially speeding up the clinical workflow of CTC image interpretation.

CT colonography: computer-assisted detection of colorectal cancer

OBJECTIVES

Computer-aided detection (CAD) for CT colonography (CTC) has been developed to detect benign polyps in asymptomatic patients. We aimed to determine whether such a CAD system can also detect cancer in symptomatic patients.

METHODS

CTC data from 137 symptomatic patients subsequently proven to have colorectal cancer were analysed by a CAD system at 4 different sphericity settings: 0, 50, 75 and 100. CAD prompts were classified by an observer as either true-positive if overlapping a cancer or false-positive if elsewhere. Colonoscopic data were used to aid matching.

RESULTS

Of 137 cancers, CAD identified 124 (90.5%), 122 (89.1%), 119 (86.9%) and 102 (74.5%) at a sphericity of 0, 50, 75 and 100, respectively. A substantial proportion of cancers were detected on either the prone or supine acquisition alone. Of 125 patients with prone and supine acquisitions, 39.3%, 38.3%, 43.2% and 50.5% of cancers were detected on a single acquisition at a sphericity of 0, 50, 75 and 100, respectively. CAD detected three cancers missed by radiologists at the original clinical interpretation. False-positive prompts decreased with increasing sphericity value (median 65, 57, 45, 24 per patient at values of 0, 50, 75, 100, respectively) but many patients were poorly prepared.

CONCLUSION

CAD can detect symptomatic colorectal cancer but must be applied to both prone and supine acquisitions for best performance.

Massive-training artificial neural network coupled with Laplacian-eigenfunction-based dimensionality reduction for computer-aided detection of polyps in CT colonography

A major challenge in the current computer-aided detection (CAD) of polyps in CT colonography (CTC) is to reduce the number of false-positive (FP) detections while maintaining a high sensitivity level. A pattern-recognition technique based on the use of an artificial neural network (ANN) as a filter, which is called a massive-training ANN (MTANN), has been developed recently for this purpose. The MTANN is trained with a massive number of subvolumes extracted from input volumes together with the teaching volumes containing the distribution for the "likelihood of being a polyp;" hence the term "massive training." Because of the large number of subvolumes and the high dimensionality of voxels in each input subvolume, the training of an MTANN is time-consuming. In order to solve this time issue and make an MTANN work more efficiently, we propose here a dimension reduction method for an MTANN by using Laplacian eigenfunctions (LAPs), denoted as LAP-MTANN. Instead of input voxels, the LAP-MTANN uses the dependence structures of input voxels to compute the selected LAPs of the input voxels from each input subvolume and thus reduces the dimensions of the input vector to the MTANN. Our database consisted of 246 CTC datasets obtained from 123 patients, each of whom was scanned in both supine and prone positions. Seventeen patients had 29 polyps, 15 of which were 5-9 mm and 14 were 10-25 mm in size. We divided our database into a training set and a test set. The training set included 10 polyps in 10 patients and 20 negative patients. The test set had 93 patients including 19 polyps in seven patients and 86 negative patients. To investigate the basic properties of a LAP-MTANN, we trained the LAP-MTANN with actual polyps and a single source of FPs, which were rectal tubes. We applied the trained LAP-MTANN to simulated polyps and rectal tubes. The results showed that the performance of LAP-MTANNs with 20 LAPs was advantageous over that of the original MTANN with 171 inputs. To test the feasibility of the LAP-MTANN, we compared the LAP-MTANN with the original MTANN in the distinction between actual polyps and various types of FPs. The original MTANN yielded a 95% (18/19) by-polyp sensitivity at an FP rate of 3.6 (338/93) per patient, whereas the LAP-MTANN achieved a comparable performance, i.e., an FP rate of 3.9 (367/93) per patient at the same sensitivity level. With the use of the dimension reduction architecture, the time required for training was reduced from 38 h to 4 h. The classification performance in terms of the area under the receiver-operating-characteristic curve of the LAP-MTANN (0.84) was slightly higher than that of the original MTANN (0.82) with no statistically significant difference (p-value =0.48).

Improving Polyp Detection Algorithms for CT Colonography: Pareto Front Approach

We investigated a Pareto front approach to improving polyp detection algorithms for CT colonography (CTC). A dataset of 56 CTC colon surfaces with 87 proven positive detections of 53 polyps sized 4 to 60 mm was used to evaluate the performance of a one-step and a two-step curvature-based region growing algorithm. The algorithmic performance was statistically evaluated and compared based on the Pareto optimal solutions from 20 experiments by evolutionary algorithms. The false positive rate was lower (p<0.05) by the two-step algorithm than by the one-step for 63% of all possible operating points. While operating at a suitable sensitivity level such as 90.8% (79/87) or 88.5% (77/87), the false positive rate was reduced by 24.4% (95% confidence intervals 17.9-31.0%) or 45.8% (95% confidence intervals 40.1-51.0%) respectively. We demonstrated that, with a proper experimental design, the Pareto optimization process can effectively help in fine-tuning and redesigning polyp detection algorithms.

Computer-aided detection of prostate cancer on tissue sections

We report an automated computer technique for detection of prostate cancer in prostate tissue sections processed with immunohistochemistry. Two sets of color optical images were acquired from prostate tissue sections stained with a double-chromogen triple-antibody cocktail combining alpha-methylacyl-CoA racemase, p63, and high-molecular-weight cytokeratin. The first set of images consisted of 20 training images (10 malignant) used for developing the computer technique and 15 test images (7 malignant) used for testing and optimizing the technique. The second set of images consisted of 299 images (114 malignant) used for evaluation of the performance of the computer technique. The computer technique identified image segments of alpha-methylacyl-CoA racemase-labeled malignant epithelial cells (red), p63, and high-molecular-weight cytokeratin-labeled benign basal cells (brown), and secretory and stromal cells (blue) for identifying prostate cancer automatically. The sensitivity and specificity of the computer technique were 94% (16/17) and 94% (17/18), respectively, on the first (training and test) set of images, and 88% (79/90) and 97% (136/140), respectively, on the second (validation) set of images. If high-grade prostatic intraepithelial neoplasia, which is a precursor of cancer, and atypical cases were included, the sensitivity and specificity were 85% (97/114) and 89% (165/185), respectively. These results show that the novel automated computer technique can accurately identify prostatic adenocarcinoma in the triple-antibody cocktail-stained prostate sections.

Computed tomographic colonography: current perspectives and future directions

Computed tomographic (CT) colonography, also known as virtual colonoscopy or CT colography, is capable of detecting colon polyps and cancers. It is emerging rapidly and has gained great momentum over the past several years, to the point where it has been proposed to be a viable primary colon cancer screening option. Despite the current publicity, many issues concerning CT colonography remain. As of 2009, the following topics are of paramount importance: (1) accuracy, including both sensitivity and specificity, (2) bowel preparation, (3) safety, (4) extracolonic findings, (5) patient acceptability, (6) training and standardization, and (7) implementation of CT colonography. Although much about CT colonography has already been learned, more remains to be learned in the future.

Influence of computer-aided detection false-positives on reader performance and diagnostic confidence for CT colonography

OBJECTIVE

The objective of our study was to investigate whether an increasing number of computer-aided detection (CAD) false-positives decreases reader sensitivity, specificity, and confidence for nonexpert readers of CT colonography (CTC).

MATERIALS AND METHODS

Fifty CTC data sets (29 men; mean age, 65 years), 25 of which contained 35 polyps > or = 5 mm, were selected in which CAD had 100% polyp sensitivity at two sphericity settings (0 and 75) but differed in the number of false-positives. The data sets were read by five readers twice: once at each sphericity setting. Sensitivity, specificity, report time, and confidence before and after second-read CAD were compared using the paired exact and Student's t test, respectively. Receiver operating characteristic (ROC) curves were generated using reader confidence (1-100) in correct case classification (normal or abnormal).

RESULTS

CAD generated a mean of 42 (range, 3-118) and 15 (range, 1-36) false-positives at a sphericity of 0 and 75, respectively. CAD at both settings increased per-patient sensitivity from 82% to 87% (p = 0.03) and per-polyp sensitivity by 8% and 10% for a sphericity of 0 and 75, respectively (p < 0.001). Specificity decreased from 84% to 79% (sphericity 0 and 75, p = 0.03 and 0.07). There was no difference in sensitivity, specificity, or reader confidence between sphericity settings (p = 1.0, 1.0, 0.11, respectively). The area under the ROC curve was 0.78 (95% CI, 0.70-0.86) and 0.77 (0.68-0.85) for a sphericity of 0 and 75, respectively. CAD added a median of 4.4 minutes (interquartile range [IQR], 2.7-6.5 minutes) and 2.2 minutes (IQR, 1.2-4.0 minutes) for a sphericity of 0 and 75, respectively (p < 0.001). CONCLUSION. CAD has the potential to increase the sensitivity of readers inexperienced with CTC, although specificity may be reduced. An increased number of CAD-generated false-positives does not negate any beneficial effect but does reduce efficiency.

Optimizing computer-aided colonic polyp detection for CT colonography by evolving the Pareto fronta

A multiobjective genetic algorithm is designed to optimize a computer-aided detection (CAD) system for identifying colonic polyps. Colonic polyps appear as elliptical protrusions on the inner surface of the colon. Curvature-based features for colonic polyp detection have proved to be successful in several CT colonography (CTC) CAD systems. Our CTC CAD program uses a sequential classifier to form initial polyp detections on the colon surface. The classifier utilizes a set of thresholds on curvature-based features to cluster suspicious colon surface regions into polyp candidates. The thresholds were previously chosen experimentally by using feature histograms. The chosen thresholds were effective for detecting polyps sized 10 mm or larger in diameter. However, many medium-sized polyps, 6-9 mm in diameter, were missed in the initial detection procedure. In this paper, the task of finding optimal thresholds as a multiobjective optimization problem was formulated, and a genetic algorithm to solve it was utilized by evolving the Pareto front of the Pareto optimal set. The new CTC CAD system was tested on 792 patients. The sensitivities of the optimized system improved significantly, from 61.68% to 74.71% with an increase of 13.03% (95% CI [6.57%, 19.5%], p = 7.78 x 10(-5)) for the size category of 6-9 mm polyps, from 65.02% to 77.4% with an increase of 12.38% (95% CI [6.23%, 18.53%], p = 7.95 x 10(-5)) for polyps 6 mm or larger, and from 82.2% to 90.58% with an increase of 8.38% (95% CI [0.75%, 16%], p = 0.03) for polyps 8 mm or larger at comparable false positive rates. The sensitivities of the optimized system are nearly equivalent to those of expert radiologists.

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.

Computed tomographic colonography: clinical value

Computed tomographic colonography (CTC) has the potential to reliably detect polyps in the colon. Its clinical value is accepted for several indications. The main target is screening asymptomatic people for colorectal cancer (CRC). As in large multi-centre trials controversial results were obtained, acceptance of this indication on a large scale is still pending. Agreement exists that in experienced hands screening can be performed with CTC. This emphasizes the importance of adequate and intensive training. Besides this, other problems have to be solved. A low complication profile is mandatory. Perforation rate is very low. Ultra-low dose radiation should be used. When screening large patient cohorts, CTC will need a time-efficient and cost-effective management without too many false positives and additional exploration. Can therefore a cut-off size of polyp detection safely be installed? Is the flat lesion an issue? Can extra-colonic findings be treated efficiently? A positive relationship with the gastro-enterologists will improve the act of screening. Improvements of scanning technique and software with dose reduction, improved 3D visualisation methods and CAD are steps in the good direction. Finally, optimisation of laxative-free CTC could be invaluable in the development of CTC as a screening tool for CRC.

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.

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.

CT colonography: false-negative interpretations

PURPOSE

To retrospectively evaluate if false-negative interpretations at computed tomographic (CT) colonography are due to observer error.

MATERIALS AND METHODS

This study was HIPAA compliant and had institutional review board approval, with waiver of informed consent. An initial unblinded review of CT colonographic image data was used to generate reconciliation reports for all false-negative polyp candidates 6.0 mm or larger. These findings were then verified by two experienced readers. After reports from the original study and reconciliation reports were reviewed, errors were classified as observer (measurement or perceptual) errors, technical errors (eg, those caused by insufficient distention, fluid), or not reconcilable. Per-polyp and per-patient sensitivity values were calculated for adenomas 6.0 mm or larger in the original data set and again by assuming elimination of technical and observer errors.

RESULTS

Of the original data set of 228 available polyps, 147 were adenomas; for this subgroup, the per-patient sensitivity was 70% and 68% at 10.0- and 6.0-mm thresholds, respectively. When all histologic types were considered, 114 polyps were false-negative findings. Of these, 53% (60 of 114) were attributed to observer-related errors, and 26% were attributed to errors classified as technical. After detailed retrospective reconciliation of individual polyps (so as to exclude any potentially correctable observer error), the per-polyp sensitivity of CT colonography for adenomas 10.0 mm or larger increased to 93%, and the per-patient sensitivity increased to 91%. When observer and technical errors were accounted for, eight (5.4%) of 147 adenomas 6.0 mm or larger could not be detected. If all technical errors and observer errors were scored as true-positive findings, the sensitivity for adenomas 6.0 mm or larger would have been 95% on both a per-polyp and a per-patient basis.

CONCLUSION

The major contributor to error at CT colonography was observer perceptual error, while observer measurement error played a smaller role.

CAD in CT colonography without and with oral contrast agents: progress and challenges

Computed tomographic colonography (CTC), also known as virtual colonoscopy, is an emerging alternative technique for screening of colon cancers. CTC uses CT to provide a series of cross-sectional images of the colon for detection of polyps and masses. Fecal tagging is a means of labeling of residual feces by an oral contrast agent for improving the accuracy in the detection of polyps. Computer-aided diagnosis (CAD) for CTC automatically determines the locations of suspicious polyps and masses in CTC and presents them to radiologists, typically as a second opinion. Despite its relatively short history, CAD has become one of the mainstream techniques that could make CTC prime time for screening of colorectal cancer. Rapid technical developments have advanced CAD substantially during the last several years, and a fundamental scheme for the detection of polyps has been established, in which sophisticated 3D image processing, analysis, and display techniques play a pivotal role. The latest CAD systems indicate a clinically acceptable high sensitivity and a low false-positive rate, and observer studies have demonstrated the benefits of these systems in improving radiologists' detection performance. Some technical and clinical challenges, however, remain unresolved before CAD can become a truly useful tool for clinical practice. Also, new challenges are facing CAD as the methods for bowel preparation and image acquisition, such as tagging of fecal residue with oral contrast agents, and interpretation of CTC images evolve. This article reviews the current status and future challenges in CAD for CTC without and with fecal tagging.

Effect of computer-aided detection as a second reader in multidetector-row CT colonography

Our purpose was to assess the effect of computer-aided detection (CAD) on lesion detection as a second reader in computed tomographic colonography, and to compare the influence of CAD on the performance of readers with different levels of expertise. Fifty-two CT colonography patient data-sets (37 patients: 55 endoscopically confirmed polyps > or =0.5 cm, seven cancers; 15 patients: no abnormalities) were retrospectively reviewed by four radiologists (two expert, two nonexpert). After primary data evaluation, a second reading augmented with findings of CAD (polyp-enhanced view, Siemens) was performed. Sensitivities and reading time were calculated for each reader without CAD and supported by CAD findings. The sensitivity of expert readers was 91% each, and of nonexpert readers, 76% and 75%, respectively, for polyp detection. CAD increased the sensitivity of expert readers to 96% (P = 0.25) and 93% (P = 1), and that of nonexpert readers to 91% (P = 0.008) and 95% (P = 0.001), respectively. All four readers diagnosed 100% of cancers, but CAD alone only 43%. CAD increased reading time by 2.1 min (mean). CAD as a second reader significantly improves sensitivity for polyp detection in a high disease prevalence population for nonexpert readers. CAD causes a modest increase in reading time. CAD is of limited value in the detection of cancer.

Fully automated three-dimensional detection of polyps in fecal-tagging CT colonography

RATIONALE AND OBJECTIVES

The presence of opacified materials presents several technical challenges for automated detection of polyps in fecal-tagging computed tomography colonography (ftCTC), such as pseudo-enhancement and the distortion of the density, size, and shape of the observed lesions. We developed a fully automated computer-aided detection (CAD) scheme that addresses these issues in automated detection of polyps in ftCTC.

MATERIALS AND METHODS

Pseudo-enhancement was minimized by use of an adaptive density correction (ADC) method. The presence of tagging was minimized by use of an adaptive density mapping (ADM) method. We also developed a new method for automated extraction of the colonic wall within air-filled and tagged regions. The ADC and ADM parameters were optimized by use of an anthropomorphic phantom. The CAD scheme was evaluated with 32+32 cases from two types of clinical ftCTC databases. The cases in database I had full cathartic cleansing and 40 polyps > or =6 mm, and the cases in database II had reduced cathartic cleansing and 44 polyps > or =6 mm. The by-polyp detection performance of the CAD scheme was evaluated by use of a leave-one-patient-out method with five features, and the results were compared with those of a conventional CAD scheme by use of free-response receiver operating characteristic curves.

RESULTS

The CAD scheme detected 95% and 86% of the polyps > or =6 mm with 3.6 and 4.2 false positives per scan on average in databases I and II, respectively. For polyps > or =10 mm, the detection sensitivity was 94% in database I (with one missed hyperplastic polyp) and 100% in database II at the same false-positive rate. The detection sensitivity of the new CAD scheme was approximately 20% higher than that of the conventional CAD scheme.

CONCLUSIONS

The results show that the CAD scheme developed in this study resolves the technical challenges introduced by fecal tagging, is applicable to a variety of colon preparation regimens, and provides a performance superior to that of conventional CAD schemes.

Computer-aided detection in CT colonography: initial clinical experience using a prototype system

Computer-aided detection (CAD) algorithms help to detect colonic polyps at CT colonography (CTC). The purpose of this study was to evaluate the accuracy of CAD versus an expert reader in CTC. One hundred forty individuals (67 men, 73 women; mean age, 59 years) underwent screening 64-MDCT colonography after full cathartic bowel cleansing without fecal tagging. One expert reader interpreted supine and prone scans using a 3D workstation with integrated CAD used as "second reader." The system's sensitivity for the detection of polyps, the number of false-positive findings, and its running time were evaluated. Polyps were classified as small (< or =5 mm), medium (6-9 mm), and large (> or =10 mm). A total of 118 polyps (small, 85; medium, 19; large, 14) were found in 56 patients. CAD detected 72 polyps (61%) with an average of 2.2 false-positives. Sensitivity was 51% (43/85) for small, 90% (17/19) for medium, and 86% (12/14) for large polyps. For all polyps, per-patient sensitivity was 89% (50/56) for the radiologist and 73% (41/56) for CAD. For large and medium polyps, per-patient sensitivity was 100% for the radiologist, and 96% for CAD. In conclusion, CAD shows high sensitivity in the detection of clinically significant polyps with acceptable false-positive rates.

CT colonography: techniques, indications, findings

Computed tomographic colonography (CTC) is a minimally invasive technique for imaging the entire colon. Based on a helical thin-section CT of the cleansed and air-distended colon, two-dimensional and three-dimensional projections are used for image interpretation. Several clinical improvements in patient preparation, technical advances in CT, and new developments in evaluation software have allowed CTC to develop into a powerful diagnostic tool. It is already well established as a reliable diagnostic tool in symptomatic patients. Many experts currently consider CTC a comparable alternative to conventional colonoscopy, although there is still debate about its sensitivity for the detection of colonic polyps in a screening population. This article summarizes the main indications, the current techniques in patient preparation, data acquisition and data analysis as well as imaging features for common benign and malignant colorectal lesions.

Massive-training artificial neural network (MTANN) for reduction of false positives in computer-aided detection of polyps: Suppression of rectal tubes

One of the limitations of the current computer-aided detection (CAD) of polyps in CT colonography (CTC) is a relatively large number of false-positive (FP) detections. Rectal tubes (RTs) are one of the typical sources of FPs because a portion of a RT, especially a portion of a bulbous tip, often exhibits a cap-like shape that closely mimics the appearance of a small polyp. Radiologists can easily recognize and dismiss RT-induced FPs; thus, they may lose their confidence in CAD as an effective tool if the CAD scheme generates such "obvious" FPs due to RTs consistently. In addition, RT-induced FPs may distract radiologists from less common true positives in the rectum. Therefore, removal RT-induced FPs as well as other types of FPs is desirable while maintaining a high sensitivity in the detection of polyps. We developed a three-dimensional (3D) massive-training artificial neural network (MTANN) for distinction between polyps and RTs in 3D CTC volumetric data. The 3D MTANN is a supervised volume-processing technique which is trained with input CTC volumes and the corresponding "teaching" volumes. The teaching volume for a polyp contains a 3D Gaussian distribution, and that for a RT contains zeros for enhancement of polyps and suppression of RTs, respectively. For distinction between polyps and nonpolyps including RTs, a 3D scoring method based on a 3D Gaussian weighting function is applied to the output of the trained 3D MTANN. Our database consisted of CTC examinations of 73 patients, scanned in both supine and prone positions (146 CTC data sets in total), with optical colonoscopy as a reference standard for the presence of polyps. Fifteen patients had 28 polyps, 15 of which were 5-9 mm and 13 were 10-25 mm in size. These CTC cases were subjected to our previously reported CAD scheme that included centerline-based segmentation of the colon, shape-based detection of polyps, and reduction of FPs by use of a Bayesian neural network based on geometric and texture features. Application of this CAD scheme yielded 96.4% (27/28) by-polyp sensitivity with 3.1 (224/73) FPs per patient, among which 20 FPs were caused by RTs. To eliminate the FPs due to RTs and possibly other normal structures, we trained a 3D MTANN with ten representative polyps and ten RTs, and applied the trained 3D MTANN to the above CAD true- and false-positive detections. In the output volumes of the 3D MTANN, polyps were represented by distributions of bright voxels, whereas RTs and other normal structures partly similar to RTs appeared as darker voxels, indicating the ability of the 3D MTANN to suppress RTs as well as other normal structures effectively. Application of the 3D MTANN to the CAD detections showed that the 3D MTANN eliminated all RT-induced 20 FPs, as well as 53 FPs due to other causes, without removal of any true positives. Overall, the 3D MTANN was able to reduce the FP rate of the CAD scheme from 3.1 to 2.1 FPs per patient (33% reduction), while the original by-polyp sensitivity of 96.4% was maintained.

Computer-assisted detection for CT colonography: external validation

AIM

To externally validate a computer-assisted detection (CAD) system for computed tomography (CT) colonography, using data from a single centre uninvolved with the software development.

MATERIALS AND METHODS

Twenty-five multi-detector CT colonography examinations of patients with validated polyps accumulated at a single centre were examined by two readers who used endoscopic and histopathological data to identify polyp coordinates. A CAD system that had been developed using data from elsewhere, and had not previously encountered the present data, was then applied to the data at sphericity filter settings of 0.75 and 0.50 and identified potential polyps. True-positive, false-negative, and false-positive counts were determined by comparison with the known polyp coordinates.

RESULTS

Twenty-five patients had 57 polyps, median size 6mm (range 1-15mm). Per-patient sensitivity for the CAD system was 96% (24 of 25). The CAD system detected 44 (77%) polyps at sphericity setting 0.75 and 49 (86%) polyps at sphericity 0.50: the additional five polyps detected all measured 5mm or less. Sphericity of 0.75 resulted in a median of 10 (one to 34) easily dismissed false-positive prompts per patient and a median of 4 (zero to 15) that needed three-dimensional rendering before dismissal. This rose to 32 (16 to 99) and 11 (three to 35), respectively, at sphericity 0.5.

CONCLUSIONS

A per-patient sensitivity of 96% was found for the CAD system (in patients with a median polyp diameter of 6mm) using external validation, a more stringent test than either internal cross-validation or temporal validation. Decreasing sphericity increases sensitivity for small polyps at the expense of decreased specificity.

Comparison of routine and unprepped CT colonography augmented by low fiber diet and stool tagging: a pilot study

BACKGROUND

We performed a pilot study examining the feasibility of a new unprepped CT colonography (CTC) strategy: low fiber diet and tagging (unprepped) vs. low fiber diet, tagging and a magnesium citrate cleansing preparation (prepped). Prior reports of tagging were limited in that the residual stool was neither measured and stratified by size nor did prior reports subjectively evaluate the ease of interpretation by a reader experienced in interpreting CTC examinations.

METHODS

Prospective randomized to unprepped n = 14 and prepped n = 14. Colonic segments were subjectively evaluated for residual stool that would potentially interfere with interpretation. Scores were given in the following categories: percentage of residual stool that was touching or nearly touching mucosa, the largest piece of retained stool, effectiveness of tagging, height of residual fluid, degree of distention, ease of interpretation, and reading time.

RESULTS

Ease of the CT read (scale where 4 = optimal read) averaged 1.3 for the unprepped group and 2.3 for the prepped group. The mean read time averaged 17.5 min for unprepped and 17.9 min for prepped. The degree of distention (scale where 4 = well distended) averaged 3.7 for unprepped and 3.6 for prepped. Supine and prone images combined, the unprepped group had 160 segments with stool; prepped group had 58 segments. The amount of stool covering the mucosa in all segments averaged 1.6 (33%-66% coverage) in the unprepped group and 0.35 (<33% mucosal coverage) in the prepped group. The mean size of the largest piece of stool was 33.67 mm for unprepped and 4.01 mm for prepped. Percentage of tagged stool was not significantly different between the groups (range of 94-98%). The height of residual fluid averaged 8.37 mm for unprepped and 13.4 mm for prepped. Three polyps in three patients were found during optical colonoscopy (OC) in the unprepped group (5, 6, and 10 mm), none of which were prospectively detected at CTC. Three polyps in three patients were detected during OC in the prepped group (5, 10, and 15 mm), two of which were prospectively detected at CTC. Two false-positive lesions were observed at CTC in one patient in the prepped group.

CONCLUSION

There was more stool in the unprepped group and while this factor did not slow down the reading time, it made the examination subjectively harder to interpret and likely caused the three polyps in this group to be missed. We conclude that a truly unprepped strategy that leaves significant residual stool, even if well tagged, is not desirable.