https://www.gastrojournal.org/article/S0016-5085(06)00561-0/pdf

Guidelines for colonoscopy surveillance after polypectomy: a consensus update by the US Multi-Society Task Force on Colorectal Cancer and the American Cancer Society.

The use of machine learning (ML) has been increasing rapidly in the medical imaging field, including computer-aided diagnosis (CAD), radiomics, and medical image analysis. Recently, an ML area called deep learning emerged in the computer vision field and became very popular in many fields. It started from an event in late 2012, when a deep-learning approach based on a convolutional neural network (CNN) won an overwhelming victory in the best-known worldwide computer vision competition, ImageNet Classification. Since then, researchers in virtually all fields, including medical imaging, have started actively participating in the explosively growing field of deep learning. In this paper, the area of deep learning in medical imaging is overviewed, including (1) what was changed in machine learning before and after the introduction of deep learning, (2) what is the source of the power of deep learning, (3) two major deep-learning models: a massive-training artificial neural network (MTANN) and a convolutional neural network (CNN), (4) similarities and differences between the two models, and (5) their applications to medical imaging. This review shows that ML with feature input (or feature-based ML) was dominant before the introduction of deep learning, and that the major and essential difference between ML before and after deep learning is the learning of image data directly without object segmentation or feature extraction; thus, it is the source of the power of deep learning, although the depth of the model is an important attribute. The class of ML with image input (or image-based ML) including deep learning has a long history, but recently gained popularity due to the use of the new terminology, deep learning. There are two major models in this class of ML in medical imaging, MTANN and CNN, which have similarities as well as several differences. In our experience, MTANNs were substantially more efficient in their development, had a higher performance, and required a lesser number of training cases than did CNNs. “Deep learning”, or ML with image input, in medical imaging is an explosively growing, promising field. It is expected that ML with image input will be the mainstream area in the field of medical imaging in the next few decades.

Overview of deep learning in medical imaging

Adenomatous polyps are the most common neoplastic findings uncovered in people who undergo colorectal screening or have a diagnostic workup for symptoms. It was common practice in the 1970s for these patients to have annual follow-up surveillance examinations to detect additional new adenomas as well as missed synchronous adenomas. As a result of the National Polyp Study report in 1993, which demonstrated clearly in a randomized design that the first postpolypectomy examination could be deferred for 3 years, guidelines published by a gastrointestinal consortium in 1997 recommended that the first follow-up surveillance be 3 years after polypectomy for most patients. In 2003, these guidelines were updated, colonoscopy was recommended as the only follow-up examination, and stratification at baseline into lower and higher risk for subsequent adenomas was suggested. The 1997 and 2003 guidelines dealt with both screening and surveillance. However, it has become increasingly clear that postpolypectomy surveillance is now a large part of endoscopic practice, draining resources from screening and diagnosis. In addition, surveys have demonstrated that a large proportion of endoscopists are conducting surveillance examinations at shorter intervals than recommended in the guidelines. In the present paper, a careful analytic approach was designed addressing all evidence available in the literature to delineate predictors of advanced pathology, both cancer and advanced adenomas, so that patients can be more definitely stratified at their baseline colonoscopy into those at lower or increased risk for a subsequent advanced neoplasia. People at increased risk have either three or more adenomas, or high-grade dysplasia, or villous features, or an adenoma ≥1 cm in size. It is recommended that they have a 3-year follow-up colonoscopy. People at lower risk who have one or two small (<1 cm) tubular adenomas with no high-grade dysplasia can have a follow up in 5 to 10 years, whereas people with hyperplastic polyps only should have a 10-year follow up as average-risk people. Recent papers have reported a significant number of missed cancers by colonoscopy. However, high-quality baseline colonoscopy with excellent patient preparation and adequate withdrawal time should minimize this and reduce clinicians' concerns. These guidelines were developed jointly by the US Multi-Society Task Force on Colorectal Cancer and the American Cancer Society to provide a broader consensus and thereby increase utilization of the recommendations by endoscopists. Adoption of these guidelines nationally can have a dramatic impact on shifting available resources from intensive surveillance to screening. It has been shown that the first screening colonoscopy and polypectomy produces the greatest effects on reducing the incidence of colorectal cancer in patients with adenomatous polyps.

https://onlinelibrary.wiley.com/doi/pdf/10.3322/canjclin.56.3.143

Guidelines for colonoscopy surveillance after polypectomy: A consensus update by the US Multi-Society Task Force on Colorectal Cancer and the American Cancer Society

BACKGROUND Computer-aided detection identifies suspicious findings on mammograms to assist radiologists. Since the Food and Drug Administration approved the technology in 1998, it has been disseminated into practice, but its effect on the accuracy of interpretation is unclear. METHODS We determined the association between the use of computer-aided detection at mammography facilities and the performance of screening mammography from 1998 through 2002 at 43 facilities in three states. We had complete data for 222,135 women (a total of 429,345 mammograms), including 2351 women who received a diagnosis of breast cancer within 1 year after screening. We calculated the specificity, sensitivity, and positive predictive value of screening mammography with and without computer-aided detection, as well as the rates of biopsy and breast-cancer detection and the overall accuracy, measured as the area under the receiver-operating-characteristic (ROC) curve. RESULTS Seven facilities (16%) implemented computer-aided detection during the study period. Diagnostic specificity decreased from 90.2% before implementation to 87.2% after implementation (P<0.001), the positive predictive value decreased from 4.1% to 3.2% (P=0.01), and the rate of biopsy increased by 19.7% (P<0.001). The increase in sensitivity from 80.4% before implementation of computer-aided detection to 84.0% after implementation was not significant (P=0.32). The change in the cancer-detection rate (including invasive breast cancers and ductal carcinomas in situ) was not significant (4.15 cases per 1000 screening mammograms before implementation and 4.20 cases after implementation, P=0.90). Analyses of data from all 43 facilities showed that the use of computer-aided detection was associated with significantly lower overall accuracy than was nonuse (area under the ROC curve, 0.871 vs. 0.919; P=0.005). CONCLUSIONS The use of computer-aided detection is associated with reduced accuracy of interpretation of screening mammograms. The increased rate of biopsy with the use of computer-aided detection is not clearly associated with improved detection of invasive breast cancer.

/pdf/influence-of-computer-aided-detection-on-performance-of-57pj972nws.pdf

Influence of computer-aided detection on performance of screening mammography.

Machine learning and radiology

Computed tomographic virtual colonoscopy computer-aided polyp detection in a screening population.

PURPOSE: To apply a computer-aided detection (CAD) algorithm to supine and prone multisection helical computed tomographic (CT) colonographic images to confirm if there is any added benefit provided by CAD over that of standard clinical interpretation. MATERIALS AND METHODS: CT colonography (with patients in both supine and prone positions) was performed with a multisection helical CT scanner in 40 asymptomatic high-risk patients. There were two consecutive series of patients, 20 of whom had at least one polyp 1.0 cm in size or larger and 20 of whom had normal colons at conventional colonoscopy performed the same day. The CT colonographic images were interpreted with an automated CAD algorithm and by two radiologists who were blinded to colonoscopy findings. RESULTS: For 25 polyps at least 1.0 cm in size (“large” polyps), sensitivity for detection by at least one radiologist was 48% (12 of 25). The sensitivity of CAD for detecting large polyps was also 48% (12 of 25), but the CAD algorithm detected four o...

Colonic polyps: complementary role of computer-aided detection in CT colonography.

An automatic method to segment colonic polyps in computed tomography (CT) colonography is presented in this paper. The method is based on a combination of knowledge-guided intensity adjustment, fuzzy c-mean clustering, and deformable models. The computer segmentations were compared with manual segmentations to validate the accuracy of our method. An average 76.3% volume overlap percentage among 105 polyp detections was reported in the validation, which was very good considering the small polyp size. Several experiments were performed to investigate the intraoperator and interoperator repeatability of manual colonic polyp segmentation. The investigation demonstrated that the computer-human repeatability was as good as the interoperator repeatability. The polyp segmentation was also applied in computer-aided detection (CAD) to reduce the number of false positive (FP) detections and provide volumetric features for polyp classification. Our segmentation method was able to eliminate 30% of FP detections. The volumetric features computed from the segmentation can further reduce FP detections by 50% at 80% sensitivity.

Colonic polyp segmentation in CT colonography-based on fuzzy clustering and deformable models

Reliable segmentation of the colon is a requirement for three-dimensional visualization programs and automatic detection of polyps on computed tomography (CT) colonography. There is an evolving clinical consensus that giving patients positive oral contrast to tag out remnants of stool and residual fluids is mandatory. The presence of positive oral contrast in the colon adds an additional challenge for colonic segmentation but ultimately is beneficial to the patient because the enhanced fluid helps reveal polyps in otherwise hidden areas. Therefore, we developed a new segmentation procedure which can handle both air- and fluid-filled parts of the colon. The procedure organizes individual air- and fluid-filled regions into a graph that enables identification and removal of undesired leakage outside the colon. In addition, the procedure provides a risk assessment of possible leakage to assist the user prior to the tedious task of visual verification. The proposed hybrid algorithm uses modified region growing, fuzzy connectedness and level set segmentation. We tested our algorithm on 160 CT colonography scans containing 183 known polyps. All 183 polyps were in segmented regions. In addition, visual inspection of 24 CT colonography scans demonstrated good performance of our procedure: the reconstructed colonic wall appeared smooth even at the interface between air and fluid and there were no leaked regions.

Hybrid segmentation of colon filled with air and opacified fluid for CT colonography

Detection of colonic polyps in CT colonography is problematic due to complexities of polyp shape and the surface of the normal colon. Published results indicate the feasibility of computer-aided detection of polyps but better classifiers are needed to improve specificity. In this paper we compare the classification results of two approaches: neural networks and recursive binary trees. As our starting point we collect surface geometry information from three-dimensional reconstruction of the colon, followed by a filter based on selected variables such as region density, Gaussian and average curvature and sphericity. The filter returns sites that are candidate polyps, based on earlier work using detection thresholds, to which the neural nets or the binary trees are applied. A data set of 39 polyps from 3 to 25 mm in size was used in our investigation. For both neural net and binary trees we use tenfold cross-validation to better estimate the true error rates. The backpropagation neural net with one hidden layer trained with Levenberg-Marquardt algorithm achieved the best results: sensitivity 90% and specificity 95% with 16 false positives per study.

Marek Franaszek

Papers

Computed tomographic virtual colonoscopy computer-aided polyp detection in a screening population.

Colonic polyps: complementary role of computer-aided detection in CT colonography.

Colonic polyp segmentation in CT colonography-based on fuzzy clustering and deformable models

Hybrid segmentation of colon filled with air and opacified fluid for CT colonography

Computer-assisted detection of colonic polyps with CT colonography using neural networks and binary classification trees.