Early Detection Of Colorectal Polyps Research Articles

Automated Colorectal Polyps Detection from Endoscopic Images using MultiResUNet Framework with Attention Guided Segmentation

AbstractThe early detection of colorectal polyps is crucial for the reduction of mortality rates. However, manually identifying polyps is time-consuming and expensive, increasing the risk of missing them. Our paper aims to address this issue by presenting an automated segmentation approach for colorectal polyps. This paper proposes a method that combines a skip connection with hybrid attention guidance (AG) using attention guidance (AG) and residual path frameworks to identify salient features. Furthermore, we augment test samples using original, horizontal flip, and vertical flip transformations to enhance model robustness through Test Time Augmentation (TTA). The model was trained with Kvasir-seg samples and evaluated on Kvasir-seg and CVC-ClinicDB datasets to gauge generalizability. A significant accuracy (0.9546), a Dice Similarity Coefficient (DSC) of 0.8557, a Cross-section over Union (IoU) of 0.8824, a Recall (0.8221), a Precision (0.8922), an area under Receiver Operating Characteristics (ROC-AUC) of 0.9454, and an area under Precision-Recall (AUC-PR) of 0.8717 were achieved without TTA. Through TTA integration, accuracy (0.9993), DSC (0.8663), IoU (0.8277), Recall (0.8060), Precision (0.9364), and ROC-AUC (0.9587) have been improved. A comparison of our framework with state-of-the-art models demonstrated its effectiveness and segmentation capabilities. Additionally, the proposed model contains only 0.47 million parameters and a weight size of 6.71 MB, illustrating its potential for clinical diagnostics. A computer-aided diagnosis (CAD) system improves patient outcomes by detecting colorectal polyps early and improving segmentation accuracy.

UPolySeg: A U-Net-Based Polyp Segmentation Network Using Colonoscopy Images

Colonoscopy is a gold standard procedure for tracking the lower gastrointestinal region. A colorectal polyp is one such condition that is detected through colonoscopy. Even though technical advancements have improved the early detection of colorectal polyps, there is still a high percentage of misses due to various factors. Polyp segmentation can play a significant role in the detection of polyps at the early stage and can thus help reduce the severity of the disease. In this work, the authors implemented several image pre-processing techniques such as coherence transport and contrast limited adaptive histogram equalization (CLAHE) to handle different challenges in colonoscopy images. The processed image was then segmented into a polyp and normal pixel using a U-Net-based deep learning segmentation model named UPolySeg. The main framework of UPolySeg has an encoder–decoder section with feature concatenation in the same layer as the encoder–decoder along with the use of dilated convolution. The model was experimentally verified using the publicly available Kvasir-SEG dataset, which gives a global accuracy of 96.77%, a dice coefficient of 96.86%, an IoU of 87.91%, a recall of 95.57%, and a precision of 92.29%. The new framework for the polyp segmentation implementing UPolySeg improved the performance by 1.93% compared with prior work.

Lectin-functionalized mesoporous silica nanoparticles for endoscopic detection of premalignant colonic lesions

Colorectal cancer (CRC) is one of the leading causes of cancer-deaths worldwide. Methods for the early in situ detection of colorectal adenomatous polyps and their precursors – prior to their malignancy transformation into CRC – are urgently needed. Unfortunately at present, the primary diagnostic method, colonoscopy, can only detect polyps and carcinomas by shape/morphology; with sessile polyps more likely to go unnoticed than polypoid lesions. Here we describe our development of polyp-targeting, fluorescently-labeled mesoporous silica nanoparticles (MSNs) that serve as targeted endoscopic contrast agents for the early detection of colorectal polyps and cancer. In vitro cell studies, ex vivo histopathological analysis, and in vivo colonoscopy and endoscopy of murine colorectal cancer models, demonstrate significant binding specificity of our nanoconstructs to pathological lesions via targeting aberrant α-L-fucose expression. Our findings strongly suggest that lectin-functionalized fluorescent MSNs could serve as a promising endoscopic contrast agent for in situ diagnostic imaging of premalignant colonic lesions.

Colon Cancer Screening in 2005: Status and Challenges

The field of colon cancer screening has evolved dramatically in the last 15 years regarding evidence, guidelines, and practice. In 1990, no evidence from a randomized controlled clinical trial (RCT) existed to show that colorectal cancer (CRC) screening was effective in reducing CRC mortality. In 1990, although some guidelines endorsed screening, there was disagreement among recommending organizations about which tests to recommend or whether to recommend any screening tests at all. The US Preventive Services Task Force (USPSTF), arguably the most influential of the recommending organizations and the most rigorously evidence based, said that evidence was insufficient to recommend either for or against CRC screening.1Knight K.K. Fielding J.E. Battista R.N. US Preventive Services Task ForceRecommendations for fecal occult blood screening.JAMA. 1989; 261: 586-593Crossref PubMed Scopus (81) Google Scholar In this environment, CRC screening was not widely practiced, much less reimbursed by payers. If screening was performed at all, fecal occult blood testing (FOBT) was the most common test. Sigmoidoscopy was performed less frequently, and colonoscopy, rarely performed for screening, was used mainly for workup of a positive FOBT or sigmoidoscopy and for postpolypectomy surveillance. The primary questions facing academics, recommending organizations, and practicing clinicians in 1990 were (1) does CRC screening—of any kind—work to reduce CRC mortality, and (2) should it be implemented and reimbursed? In 2005, the situation is dramatically different. We now know that CRC screening works, and it is now being implemented and reimbursed. Colonoscopy has become popular as a primary screening test, and new tests, such as virtual colonoscopy, are being developed. The purpose of this article is to identify current challenges in light of the evolution of evidence, guidelines, and practice and to anticipate the next phase of development and implementation. In 1990, no strong evidence existed from an RCT showing that screening reduces CRC mortality. Some recommending organizations had supported it, but screening was not reimbursed or widely practiced. However, after 3 RCTs in the mid 1990s provided evidence of efficacy, a broad consensus developed among recommending organizations about performing screening and about which testing programs to recommend.2US Preventive Services Task ForceChapter 8 screening for colorectal cancer.in: Guide to clinical preventive services. 2nd ed. US Government Printing Office, Washington, DC1996: 89-103Google Scholar, 3Byers T. Levin B. Rothenberger D. Dodd G.D. Smith R.A. American Cancer Society guidelines for screening and surveillance for early detection of colorectal polyps and cancer update 1997.CA Cancer J Clin. 1997; 47: 154-160Crossref PubMed Scopus (448) Google Scholar, 4Winawer S.J. Fletcher R.H. Miller L. Godlee F. Stolar M.H. Mulrow C.D. et al.Colorectal cancer screening clinical guidelines and rationale.Gastroenterology. 1997; 112: 594-642Abstract Full Text Full Text PDF PubMed Scopus (1829) Google Scholar Particularly important were the USPSTF’s decision in 1996 to endorse screening2US Preventive Services Task ForceChapter 8 screening for colorectal cancer.in: Guide to clinical preventive services. 2nd ed. US Government Printing Office, Washington, DC1996: 89-103Google Scholar and Medicare’s decision in 2001 to reimburse for it. The first strong evidence that screening reduces CRC mortality came not from an RCT but from an unusually well done case-control study about sigmoidoscopy. Published in the New England Journal of Medicine in 1992, this study showed that CRC mortality was reduced by approximately 60% for lesions within reach of the instrument among persons who had had screening sigmoidoscopy.5Selby J.V. Friedman G.D. Quesenberry Jr, C.P. Weiss N.S. A case-control study of screening sigmoidoscopy and mortality from colorectal cancer.N Engl J Med. 1992; 326: 653-657Crossref PubMed Scopus (1573) Google Scholar Although case-control studies are generally regarded as providing weak evidence about efficacy because bias is so hard to account for compared with RCTs, this study used an unusual kind of “control group”6Ransohoff D.F. Lang C.A. Sigmoidoscopic screening in the 1990s.JAMA. 1993; 269: 1278-1281Crossref PubMed Scopus (75) Google Scholar that, along with results from another study,7Newcomb P.A. Norfleet R.G. Storer B.E. Surawicz T.S. Marcus P.M. Screening sigmoidoscopy and colorectal cancer mortality.J Natl Cancer Inst. 1992; 84: 1572-1575Crossref PubMed Scopus (867) Google Scholar provided the rationale for the USPSTF to modify its recommendations in 1996 to include sigmoidoscopy.2US Preventive Services Task ForceChapter 8 screening for colorectal cancer.in: Guide to clinical preventive services. 2nd ed. US Government Printing Office, Washington, DC1996: 89-103Google Scholar In 1993 and 1996, 3 landmark RCTs provided evidence that FOBT screening reduces CRC mortality. Mortality reduction was 33% among subjects who had every-year rehydrated FOBT in the US trial8Mandel J.S. Bond J.H. Church T.R. Snover D.C. Bradley G.M. Schuman L.M. et al.Reducing mortality from colorectal cancer by screening for fecal occult blood.N Engl J Med. 1993; 328: 1365-1371Crossref PubMed Scopus (2908) Google Scholar and was approximately 15% in 2 European studies for every-other-year nonrehydrated FOBT.9Kronborg O. Fenger C. Olsen J. Jorgensen O.D. Sondergaard O. Randomised study of screening for colorectal cancer with faecal-occult-blood test.Lancet. 1996; 348: 1467-1471Abstract Full Text Full Text PDF PubMed Scopus (2186) Google Scholar, 10Hardcastle J.D. Chamberlain J.O. Robinson M.H.E. Moss S.M. Amar S.S. Balfour T.W. et al.Randomised controlled trial of faecal-occult-blood screening for colorectal cancer.Lancet. 1996; 348: 1472-1477Abstract Full Text Full Text PDF PubMed Scopus (2428) Google Scholar Although by 1996 no study had assessed the efficacy of colonoscopy screening in reducing CRC mortality (and none has now), support for colonoscopy evolved on the basis of evidence from studies about FOBT and sigmoidoscopy. One line of reasoning is that, because colonoscopy is the means by which FOBT or sigmoidoscopy screening reduces mortality (because colonoscopy is performed to work up a positive primary screening test), then colonoscopy is the mechanism by which CRC mortality is reduced and should plausibly be effective as a primary screening test. A second line of reasoning is that if endoscopic screening works in the sigmoid colon, it should also work for the rest of the colon; this argument might be incorrect if the right colon behaves differently, biologically, compared with the left. Overall these arguments have been taken to indicate that colonoscopy works. Further consideration must be given to how well it works in comparison to other tests and programs, as will be discussed below. Guidelines followed evidence. In 1990, some guidelines had recommended screening, although, as noted, the USPSTF did not. In 1992, the US Congress decided not to reimburse for CRC screening for Medicare patients, declining to follow recommendations based on the cost-effectiveness analysis that Congress had commissioned from the Office of Technology Assessment.11US Congress Office of Technology AssessmentCosts and effectiveness of colorectal cancer screening in the elderly—background paper, OTA-BP-H-74. US Government Printing Office, Washington, DC1990Google Scholar, 12Wagner J.L. Herdman R.C. Wadhwa S. Cost effectiveness of colorectal cancer screening in the elderly.Ann Intern Med. 1991; 115: 807-817Crossref PubMed Scopus (105) Google Scholar That analysis concluded, on the basis of available evidence before RCTs, that CRC screening was cost-effective compared with other medical and screening practices. However, lacking both RCT evidence and popular support for what would be a costly (even if cost-effective) program, Congress declined to support screening. By 1996, however, evidence from 3 RCTs and the case-control study dramatically changed guidelines when the USPSTF decided to endorse CRC screening.2US Preventive Services Task ForceChapter 8 screening for colorectal cancer.in: Guide to clinical preventive services. 2nd ed. US Government Printing Office, Washington, DC1996: 89-103Google Scholar That evolution of evidence and recommendations set the stage for the events of the year 2000, when CRC screening became popular. By 2000, evidence about efficacy was already several years old, as was the 1996 USPSTF endorsement. However, screening was not widely practiced, and—importantly—Medicare had not decided to fully reimburse it. The events of 2000 changed the situation and provided lessons about how public policy gets made. March 2000 became the nation’s first colon cancer awareness month when Katie Couric, host of NBC’s Today Show, promoted CRC screening after her husband’s death from CRC. Couric was featured in a cover story in Time Magazine and produced a 5-part series on the Today Show, including a broadcast of her own screening colonoscopy. These events affected practice in the United States.13Dobson R. Broadcast of star’s colonoscopy boosts screening.Br Med J. 2002; 324: 1118Crossref PubMed Scopus (5) Google Scholar, 14Cram P. Fendrick A.M. Inadomi J. Cowen M.E. Carpenter D. Vijan S. The impact of a celebrity promotional campaign on the use of colon cancer screening the Katie Couric effect.Arch Intern Med. 2003; 163: 1601-1605Crossref PubMed Scopus (328) Google Scholar In July 2000, two reports in the New England Journal of Medicine—and their interpretation in an accompanying editorial and the media—dramatically affected the popularity and practice of CRC screening, particularly colonoscopy. The studies were the first reports of the yield of screening colonoscopy in an asymptomatic average-risk population. Before this time, information about the prevalence of colonic neoplasms (ie, cancer and adenomas) had come from autopsy studies. Although knowing the prevalence, or yield, of screening for such lesions is related only indirectly to the outcome of CRC mortality reduction, such lesions may be considered strong surrogate outcomes because of other evidence about CRC, for example, from the RCTs of FOBT. One goal of the studies was to compare sigmoidoscopy with colonoscopy by assessing how many lesions would be missed by sigmoidoscopy. Because the expected prevalence of CRC, the most important outcome, would be too low to provide a useful comparison even in groups involving several thousand subjects, the studies also assessed (as had some previous studies) a lesion that would be more common: advanced adenomas,15Lieberman D.A. Weiss D.G. Bond J.H. Ahnen D.H. Garewal H. Chejfec G. et al.Use of colonoscopy to screen asymptomatic adults for colorectal cancer.N Engl J Med. 2000; 343: 162-168Crossref PubMed Scopus (1609) Google Scholar, 16Imperiale T.F. Wagner D.R. Lin C.Y. Larkin G.N. Rogge J.D. Ransohoff D.F. Risk of advanced proximal neoplasms in asymptomatic adults according to the distal colorectal findings.N Engl J Med. 2000; 343: 169-174Crossref PubMed Scopus (698) Google Scholar generally defined as a tubular adenoma ≥1 cm, with villous histology, or with advanced histology. They were included as outcomes not because their natural history is known to be ominous (ie, how often and how rapidly they become incurable cancer); their natural history is unknown. Rather, they were included as possibly useful surrogates that would provide a bigger sample size for research studies to measure. Advanced adenomas have taken on a kind of life of their own in terms of becoming important targets for CRC screening.17Imperiale T.F. Wagner D.R. Lin C.Y. Larkin G.N. Rogge J.D. Ransohoff D.F. Results of screening colonoscopy among persons 40 to 49 years of age.N Engl J Med. 2002; 346: 1781-1785Crossref PubMed Scopus (314) Google Scholar The studies found, as was widely expected, that sigmoidoscopy, which examines approximately half of the colon, misses roughly half of the lesions in the colon.15Lieberman D.A. Weiss D.G. Bond J.H. Ahnen D.H. Garewal H. Chejfec G. et al.Use of colonoscopy to screen asymptomatic adults for colorectal cancer.N Engl J Med. 2000; 343: 162-168Crossref PubMed Scopus (1609) Google Scholar, 16Imperiale T.F. Wagner D.R. Lin C.Y. Larkin G.N. Rogge J.D. Ransohoff D.F. Risk of advanced proximal neoplasms in asymptomatic adults according to the distal colorectal findings.N Engl J Med. 2000; 343: 169-174Crossref PubMed Scopus (698) Google Scholar Sigmoidoscopy detects a few right-sided lesions indirectly when it discovers a lesion in the left colon considered to be a sentinel lesion that provokes a full colonoscopy. The number of right-sided lesions detected in this manner depends on what is considered a sentinel lesion, whether it is a large or advanced adenoma, an adenoma of any size, or a hyperplastic polyp. Because small adenomas and hyperplastic polyps are so common,18UK Flexible Sigmoidoscopy Screening Trial InvestigatorsSingle flexible sigmoidoscopy screening to prevent colorectal cancer baseline findings of a UK multicentre randomised trial.Lancet. 2002; 359: 1291-1300Abstract Full Text Full Text PDF PubMed Scopus (458) Google Scholar, 19Ransohoff D.F. Lessons from the UK sigmoidoscopy screening trial.Lancet. 2002; 359: 1266-1267Abstract Full Text Full Text PDF PubMed Scopus (23) Google Scholar the decision about what is a sentinel lesion has substantial implications for workup at sigmoidoscopy screening. The 2 New England Journal of Medicine studies found that many right-sided CRCs and advanced adenomas were not accompanied by sentinel lesions and would be missed by sigmoidoscopy.15Lieberman D.A. Weiss D.G. Bond J.H. Ahnen D.H. Garewal H. Chejfec G. et al.Use of colonoscopy to screen asymptomatic adults for colorectal cancer.N Engl J Med. 2000; 343: 162-168Crossref PubMed Scopus (1609) Google Scholar, 16Imperiale T.F. Wagner D.R. Lin C.Y. Larkin G.N. Rogge J.D. Ransohoff D.F. Risk of advanced proximal neoplasms in asymptomatic adults according to the distal colorectal findings.N Engl J Med. 2000; 343: 169-174Crossref PubMed Scopus (698) Google Scholar This finding was not a surprise to clinicians or policy makers in the field. Sigmoidoscopy had been recommended by the USPSTF in 1996 and by other recommending organizations despite this deficiency, and it was to be recommended again in 2002, after these articles. However, in 2000, the finding was considered important “news” when an accompanying editorial, entitled “Going the distance—the case for true colorectal-cancer screening,”20Podolsky D.K. Going the distance—the case for true colorectal-cancer screening.N Engl J Med. 2000; 343 (editorial): 207-208Crossref PubMed Scopus (144) Google Scholar said that performing sigmoidoscopy screening was like performing mammography screening of only one breast—ie, unsatisfactory. A report on the front page of the New York Times said that “The test most commonly recommended to screen healthy adults for colorectal cancer misses too many precancerous growths and should be replaced by a more extensive procedure that examines the entire colon, doctors are reporting today.”21Grady D. More extensive test needed for colon cancer, studies say. New York Times July 20, 2000;A1, A20.Google Scholar The news article went on to say that sigmoidoscopy had “been used for screening on the optimistic theory that if no abnormalities were seen in the lower colon, none were likely to be found higher up.”21Grady D. More extensive test needed for colon cancer, studies say. New York Times July 20, 2000;A1, A20.Google Scholar The problem with the news report, based on the editorial, was that recommending organizations had not relied on an optimistic theory that right-sided lesions would be found. To recommend sigmoidoscopy, guidelines organizations had used other considerations, such as effectiveness, cost-effectiveness, and availability, whereas the editorial considered mainly the thoroughness of a test at one examination. Although colonoscopy may be the best test at any one application, that does not necessarily translate to the best test in a program of repeated applications of tests over time, as will be discussed below. These more complicated considerations22Imperiale T.F. Ransohoff D.F. Screening for colorectal cancer.N Engl J Med. 2000; 343: 1651-1653Crossref Scopus (922) Google Scholar were lost in the attention given to the thoroughness of the examination and what was missed. The interpretation of these 2 studies, along with other events in 2000, had a dramatic effect on CRC screening in general and on colonoscopy in particular. By the end of 2000, Medicare had decided to reimburse for colonoscopy screening, and colonoscopy as the best primary screening test began to be discussed and to be advocated by some gastroenterology organizations. Since 2000, evidence and guidelines have not substantially evolved regarding tests recommended as options for average-risk persons, but practice has evolved. Medicare’s decision to reimburse for screening colonoscopy has had a ripple effect among other payers. Now that guidelines are generally supportive and make little preference among available tests, the field has moved into a kind of “postguideline” environment that involves other forces beyond guidelines, as will be discussed below. Evidence about screening efficacy has not evolved substantially since 2000. Two important RCTs about sigmoidoscopy screening, initiated in the 1990s, will provide results about CRC incidence and mortality.18UK Flexible Sigmoidoscopy Screening Trial InvestigatorsSingle flexible sigmoidoscopy screening to prevent colorectal cancer baseline findings of a UK multicentre randomised trial.Lancet. 2002; 359: 1291-1300Abstract Full Text Full Text PDF PubMed Scopus (458) Google Scholar, 23Prorok P.C. Andriole G.L. Bresalier R.S. Buys S.S. Chia D. Crawford E.D. et al.Design of the Prostate, Lung, Colorectal and Ovarian (PLCO) Cancer Screening Trial.Control Clin Trials. 2000; 21: 273S-309SAbstract Full Text PDF PubMed Google Scholar These studies are expected to provide critical data that will likely have implications also for colonoscopy. Because such RCTs are so costly and time consuming, even for a cancer as common as CRC, these may well be the last RCTs to include CRC incidence and mortality as an outcome. Guidelines since 2000 have also been basically stable regarding average-risk persons. Any of several CRC screening programs is recommended, including FOBT alone, sigmoidoscopy alone, a combination of FOBT and sigmoidoscopy, and colonoscopy.24Ransohoff D.F. Sandler R.S. Clinical practice. Screening for colorectal cancer.N Engl J Med. 2002; 346: 40-44Crossref PubMed Scopus (176) Google Scholar, 25Woolf S.H. The best screening test for colorectal cancer a personal choice.N Engl J Med. 2000; 343 (editorial): 1641-1643Crossref PubMed Scopus (117) Google Scholar With several choices recommended and none preferred (with one exception, as discussed below), other events and forces in the postguideline environment are becoming important. The current broad consensus has been achieved in part because of a deliberate effort on the part of major guidelines organizations to coordinate recommendations. Guidelines have discussed but not made recommendations about newer technologies such as virtual colonoscopy or stool DNA testing, in part because of the need to accumulate sufficient evidence and because of the time lag after publication of evidence; such new modalities will likely be considered in detail over time. Practice has evolved, although details of how it is evolving are not clear. Gastroenterologists now report, at least anecdotally, performing many more colonoscopies than before. Some spend up to 50% or even 80% of their practice time simply performing colonoscopy; this is a dramatic increase from 5 years ago. In the United States, there is no ongoing systematic approach to describe practice patterns over time, although useful snapshots are available.26Janes G.R. Blackman D.K. Bolen J.C. Kamimoto L.A. Rhodes L. Caplan L.S. et al.Surveillance for use of preventive health-care services by older adults, 1995–1997.MMWR CDC Surveill Summ. 1999; 48: 51-88PubMed Google Scholar, 27Seeff L. Nadel M. Blackman D. Colorectal cancer test use among persons aged >50 years—United States, 2001.MMWR Morb Mortal Wkly Rep. 2003; 52: 193-196PubMed Google Scholar, 28Klabunde C.N. Frame P.S. Meadow A. Jones E. Nadel M. Vernon S.W. A national survey of primary care physicians’ colorectal cancer screening recommendations and practices.Prev Med. 2003; 36: 352-362Crossref PubMed Scopus (194) Google Scholar, 29Mysliwiec P.A. Brown M.L. Klabunde C.N. Ransohoff D.F. Are physicians doing too much colonoscopy? A national survey of colorectal surveillance after polypectomy.Ann Intern Med. 2004; 141: 264-271Crossref PubMed Scopus (285) Google Scholar, 30Nadel M.R. Shapiro J.A. Klabunde C.N. Seeff L.C. Uhler R. Smith R.A. et al.A national survey of primary care physicians’ methods for screening for fecal occult blood.Ann Intern Med. 2005; 142: 86-94Crossref PubMed Scopus (157) Google Scholar One lesson from this evolution is that implementation of CRC screening has required not only evidence, but also strong popular support. On the one hand, this should not be unexpected. Widespread implementation of breast cancer screening was achieved long after evidence was available from RCTs, boosted by endorsement of public figures such as Happy Rockefeller and Betty Ford. Prostate cancer screening has become widely practiced on the basis of popular support, along with some guidelines organizations’ endorsement, even without evidence from an RCT of mortality reduction. Public perception and support, a necessary ingredient for any degree of implementation, may also take on a kind of life of its own, as discussed below. Such issues need to be considered in anticipating and planning for the future. Achieving implementation of any kind of CRC screening is a major challenge in 2005. The reasons that screening rates are low compared with those for breast cancer or cervical cancer screening are critical to understand and address, and they are receiving detailed attention from the research and policy communities; they are not discussed further here.28Klabunde C.N. Frame P.S. Meadow A. Jones E. Nadel M. Vernon S.W. A national survey of primary care physicians’ colorectal cancer screening recommendations and practices.Prev Med. 2003; 36: 352-362Crossref PubMed Scopus (194) Google Scholar, 31Vernon S.W. Participation in colorectal cancer screening a review.J Natl Cancer Inst. 1997; 89: 1406-1422Crossref PubMed Scopus (675) Google Scholar, 32Wender R.C. Barriers to screening for colorectal cancer.Gastrointest Endosc Clin North Am. 2002; 12: 145-170Abstract Full Text Full Text PDF PubMed Scopus (50) Google Scholar, 33Swan J. Breen N. Coates R.J. Rimer B.K. Lee N.C. Progress in cancer screening practices in the United States results from the 2000 National Health Interview Survey.Cancer. 2003; 97: 1528-1540Crossref PubMed Scopus (674) Google Scholar, 34Meissner H.I. Vernon S.W. Rimer B.K. Wilson K.M. Rakowski W. Briss P.A. et al.The future of research that promotes cancer screening.Cancer. 2004; 101: 1251-1259Crossref PubMed Scopus (21) Google Scholar, 35Hiatt R. Wardle J. Vernon S. Austoker J. Bistanti L. Fox S. et al.Workgroup IV: public education. UICC International Workshop on Facilitating Screening for Colorectal Cancer, Oslo, Norway (29 and 30 June 2002).Ann Oncol. 2005; 16: 38-41Crossref PubMed Scopus (8) Google Scholar, 36Vernon S.W. Briss P.A. Tiro J.A. Warnecke R.B. Some methodologic lessons learned from cancer screening research.Cancer. 2004; 101: 1131-1145Crossref PubMed Scopus (71) Google Scholar, 37Vernon S.W. Meissner H. Klabunde C. Rimer B.K. Ahnen D.J. Bastani R. et al.Measures for ascertaining use of colorectal cancer screening in behavioral, health services, and epidemiologic research.Cancer Epidemiol Biomarkers Prev. 2004; 13: 898-905PubMed Google Scholar, 38Levin B. Smith R.A. Feldman G.E. Colditz G.A. Fletcher R.H. Nadel M. et al.Promoting early detection tests for colorectal carcinoma and adenomatous polyps a framework for action—the strategic plan of the National Colorectal Cancer Roundtable.Cancer. 2002; 95: 1618-1628Crossref PubMed Scopus (74) Google Scholar It seems likely that the current low rates will improve over time,27Seeff L. Nadel M. Blackman D. Colorectal cancer test use among persons aged >50 years—United States, 2001.MMWR Morb Mortal Wkly Rep. 2003; 52: 193-196PubMed Google Scholar building in part on lessons learned from implementation of mammography screening. FOBT and sigmoidoscopy, historically the primary screening tests, are still recommended as mainstream tests and may improve individually or in combinations that may make them more attractive, as discussed below. FOBT, specifically Hemoccult II (Beckman Coulter, Inc, Fullerton, CA), has been the most widely used test in practice and has potential for future improvement. Use of a program of FOBT screening (in which screening is performed yearly or every other year) may result in a cumulative sensitivity of the program that is competitive with a program of a more sensitive test (such as colonoscopy) performed less frequently. Specifically, a combined program of FOBT plus sigmoidoscopy may be as effective as or more effective than a program of colonoscopy screening every 10 years, as discussed below. For this reason, and because improved FOBT tests such as that based on immunoassay of human hemoglobin may be more sensitive than the widely used Hemoccult II based on the peroxidase-like activity of hemoglobin, FOBT screening should not be excluded from consideration by physicians, patients, and policy makers. One important problem is that proper testing with FOBT using Hemoccult II involves examining 3 different bowel movements. Physicians in practice often use a 1-card (in-office) test,30Nadel M.R. Shapiro J.A. Klabunde C.N. Seeff L.C. Uhler R. Smith R.A. et al.A national survey of primary care physicians’ methods for screening for fecal occult blood.Ann Intern Med. 2005; 142: 86-94Crossref PubMed Scopus (157) Google Scholar perhaps in part because of the difficulty of arranging office logistics and systems to keep track of home-based collection. The single-card approach is considered inadequate because of low sensitivity and specificity.39Collins J.F. Lieberman D.A. Durbin T.E. Weiss D.G. Accuracy of screening for fecal occult blood on a single stool sample obtained by digital rectal examination a comparison with recommended sampling practice.Ann Intern Med. 2005; 142: 81-85Crossref PubMed Scopus (194) Google Scholar Furthermore, positive results often are not worked up by a whole-colon examination, as recommended.40Ransohoff D.F. Lang C.A. American College of PhysiciansScreening for colorectal cancer with the fecal occult blood test a background paper.Ann Intern Med. 1997; 126: 811-822Crossref PubMed Scopus (166) Google Scholar Part of the problem may be that FOBT screening involves a system that is complicated (and is not reimbursed) and that, if not fully implemented, can cause substantially reduced effectiveness of screening compared with that obtained in clinical trials. Sigmoidoscopy, the other historical or traditional test, is supported by all recommending organizations as an acceptable option and may be particularly effective when combined with FOBT, as noted previously. One practical problem in implementation is that many primary care physicians, who have traditionally performed the test in screening, have never received the hands-on supervised training required to gain proficiency.41Ashley O.S. Nadel M. Ransohoff D.F. Achieving quality in flexible sigmoidoscopy screening for colorectal cancer.Am J Med. 2001; 111: 643-653Abstract Full Text Full Text PDF PubMed Scopus (17) Google Scholar From a practical standpoint, the procedure may be reimbursed at a rate that is too low to justify the required equipment, staff time, and dedicated space.42Lewis J.D. Asch D.A. Barriers to office-based screening sigmoidoscopy does reimbursement cover costs?.Ann Intern Med. 1999; 130: 525-530Crossref PubMed Scopus (75) Google Scholar, 43Shaheen N.J. Ransohoff D.F. Sigmoidoscopy costs and the limits of altruism.Am J Med. 1999; 107: 286-287Abstract Full Text PDF PubMed Scopus (11) Google Scholar Although sigmoidoscopy screening is not particularly popular in the United States,28Klabunde C.N. Frame P.S. Meadow A. Jones E. Nadel M. Vernon S.W. A national survey of primary care physicians’ colorectal cancer screening recommendations and practices.Prev Med. 2003; 36: 352-362Crossref PubMed Scopus (194) Google Scholar the fact that it is being studied in the United Kingdom as a possible once-in-a-lifetime test18UK Flexible Sigmoidoscopy Screening Trial InvestigatorsSingle flexible sigmoidoscopy screening to prevent colorectal cancer baseline findings of a UK multicentre randomised trial.Lancet. 2002; 359: 1291-1300Abstract Full Text Full Text PDF PubMed Scopus (458) Google Scholar suggests that it should at least remain as a consideration. Before 2000, colonoscopy was seldom used as a primary screening test. Since 2000, colonoscopy has become a popular primary screening test, and questions are being discussed about whether there is sufficient capacity to satisfy demand44Kolata G. 50 and ready for a colonoscopy? Doctors say there is often a wait. New York Times, December 8, 2003:A1, A23.Google Scholar, 45Maguire P. Colonoscopy screening gains momentum, but problems remain.ACP-ASIM Observer. 2002; 22 (16, 17): 1Google Scholar, 46Rex D.K. Rationale for colonoscopy screening and estimated effectiveness in clinical practice.Gastrointest Endosc Clin North Am

Efficacy of automatic path tracking in virtual colonoscopy

Virtual colonoscopy is a minimally invasive technique allowing early detection of colorectal polyps. Several visualization techniques exist to inspect this large amount of data on the presence of lesions. The most common ones are slice-by-slice viewing, multiplanar reformatting and perspective volume rendering of the inner colon wall (virtual endoscopy). A path or centerline through the colon can be very useful to perform virtual endoscopy. Frequently, this path has to be tracked manually. Unfortunately, manual path tracking is a very time-consuming task and the resulting path depends a lot on the experience of the operator. This severely limits the applicability of the path-based visualization and inspection methods. We have developed an automatic path tracker for virtual endoscopy based on the minimal cost path algorithm described in Deschamps and Cohen [1]. In this paper, we briefly summarize the minimal cost path method and its implementation into an automatic path tracker tool. We also describe the results of a multiuser study, where we measured the speed and operator dependence of the automated path tracker.

Automatic segmentation of the colon for virtual colonoscopy

Virtual colonoscopy is a minimally invasive technique that enables early detection of colorectal polyps and cancer. Normally, a patient's bowel is prepared with colonic lavage and gas insufflation prior to computed tomography scanning. An important step for 3D analysis of the image volume is segmentation of the colon. The high-contrast gas/tissue interface that exists in the colon lumen makes segmentation of the majority of the colon relatively easy; however, two factors inhibit automatic segmentation of the entire colon. First, the colon is not the only gas-filled organ in the data volume: lungs, small bowel, and stomach also meet this criterion. User-defined seed points placed in the colon lumen have previously been required to spatially isolate the colon. Second, portions of the colon lumen may be obstructed by peristalsis, large masses, and/or residual feces. These complicating factors require increased user interaction during the segmentation process to isolate additional colonic segments. To automate the segmentation of the colon, we have developed a method to locate seed points and segment the gas-filled lumen sections without user supervision. We have also developed an automated approach to improve lumen segmentation by digitally removing residual contrast-enhanced fluid. Experimental results with 20 patient volumes show that our method is accurate and reliable.