Dataset Information

Increasing Navigation Speed at Endoluminal CT Colonography Reduces Colonic Visualization and Polyp Identification.

ABSTRACT: Purpose To investigate the effect of increasing navigation speed on the visual search and decision making during polyp identification for computed tomography (CT) colonography Materials and Methods Institutional review board permission was obtained to use deidentified CT colonography data for this prospective reader study. After obtaining informed consent from the readers, 12 CT colonography fly-through examinations that depicted eight polyps were presented at four different fixed navigation speeds to 23 radiologists. Speeds ranged from 1 cm/sec to 4.5 cm/sec. Gaze position was tracked by using an infrared eye tracker, and readers indicated that they saw a polyp by clicking a mouse. Patterns of searching and decision making by speed were investigated graphically and by multilevel modeling. Results Readers identified polyps correctly in 56 of 77 (72.7%) of viewings at the slowest speed but in only 137 of 225 (60.9%) of viewings at the fastest speed (P = .004). They also identified fewer false-positive features at faster speeds (42 of 115; 36.5%) of videos at slowest speed, 89 of 345 (25.8%) at fastest, P = .02). Gaze location was highly concentrated toward the central quarter of the screen area at faster speeds (mean gaze points at slowest speed vs fastest speed, 86% vs 97%, respectively). Conclusion Faster navigation speed at endoluminal CT colonography led to progressive restriction of visual search patterns. Greater speed also reduced both true-positive and false-positive colorectal polyp identification. ^© RSNA, 2017 Online supplemental material is available for this article.

SUBMITTER: Plumb AA

PROVIDER: S-EPMC5548448 | biostudies-literature | 2017 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Increasing Navigation Speed at Endoluminal CT Colonography Reduces Colonic Visualization and Polyp Identification.

Plumb Andrew A AA Phillips Peter P Spence Graeme G Mallett Susan S Taylor Stuart A SA Halligan Steve S Fanshawe Thomas T

Radiology 20170310 2

Purpose To investigate the effect of increasing navigation speed on the visual search and decision making during polyp identification for computed tomography (CT) colonography Materials and Methods Institutional review board permission was obtained to use deidentified CT colonography data for this prospective reader study. After obtaining informed consent from the readers, 12 CT colonography fly-through examinations that depicted eight polyps were presented at four different fixed navigation spe ...[more]

PMID: 28281908

Similar Datasets

Project description:Purpose To report the prevalence and characteristics of serrated polyps identified in a large, average-risk population undergoing screening computed tomographic (CT) colonography. Materials and Methods This HIPAA-compliant retrospective study was approved by the institutional review board of the University of Wisconsin School of Medicine and Public Health. The need for informed consent was waived. Nine thousand six hundred examinations from 8289 patients were enrolled in a single-institution CT colonography-based screening program (from 2004 to 2011) and were evaluated for the presence of nondiminutive serrated lesions and advanced adenomas. The prevalence and characteristics of these lesions were tabulated. Generalized estimating equation regressions of polyp characteristics that may contribute to visualization of serrated lesions were investigated, including polyp size, location, and morphologic appearance; histologic findings; and presence or absence of contrast material tagging. Results Nondiminutive serrated lesions (?6 mm) were seen at CT colonography-based screening with a prevalence of 3.1% (254 of 8289 patients). Sessile serrated adenomas (SSAs) and traditional serrated adenomas (TSAs) constituted 36.8% (137 of 372) and 4.3% (16 of 372) of serrated lesions, respectively; hyperplastic polyps (HPs) accounted for 58.9% (219 of 372 lesions). SSA and TSA tended to be large (mean size, 10.6 mm and 14.1 mm, respectively), with size categories and polyp subgroups significantly associated (P < .0001). SSA tended to be proximal in location (91.2%, 125 of 137 lesions) and flat in morphologic appearance (39.4%, 54 of 137 lesions) compared with TSA and HP. The presence of high-grade dysplasia in serrated lesions was uncommon when compared with advanced adenomas (one of 372 lesions vs 22 of 395 lesions, respectively; P < .0001). Multivariate analysis showed that contrast material tagging markedly improved serrated polyp detection with an odds ratio of 40.4 (95% confidence interval: 10.1, 161.4). Conclusion Serrated lesions are seen at CT colonography-based screening with a nondiminutive prevalence of 3.1%. These lesions tend to be large, flat, and proximal in location. Adherent contrast material coating on these polyps aids in their detection, despite an often flat morphologic appearance. (©) RSNA, 2016 Online supplemental material is available for this article.

Project description:ObjectivesThe aim of this study was to compare the morphology, radiological stage, conspicuity, and computer-assisted detection (CAD) characteristics of colorectal cancers (CRC) detected by computed tomographic colonography (CTC) in screening and symptomatic populations.MethodsTwo radiologists independently analyzed CTC images from 133 patients diagnosed with CRC in (a) two randomized trials of symptomatic patients (35 patients with 36 tumours) and (b) a screening program using fecal occult blood testing (FOBt; 98 patients with 100 tumours), measuring tumour length, volume, morphology, radiological stage, and subjective conspicuity. A commercial CAD package was applied to both datasets. We compared CTC characteristics between screening and symptomatic populations with multivariable regression.ResultsScreen-detected CRC were significantly smaller (mean 3.0 vs 4.3 cm, p?<?0.001), of lower volume (median 9.1 vs 23.2 cm3, p?<?0.001) and more frequently polypoid (34/100, 34 % vs. 5/36, 13.9 %, p?=?0.02) than symptomatic CRC. They were of earlier stage than symptomatic tumours (OR?=?0.17, 95 %CI 0.07-0.41, p?<?0.001), and were judged as significantly less conspicuous (mean conspicuity 54.1/100 vs. 72.8/100, p?<?0.001). CAD detection was significantly lower for screen-detected (77.4 %; 95 %CI 67.9-84.7 %) than symptomatic CRC (96.9 %; 95 %CI 83.8-99.4 %, p?=?0.02).ConclusionsScreen-detected CRC are significantly smaller, more frequently polypoid, subjectively less conspicuous, and less likely to be identified by CAD than those in symptomatic patients.Key points• Screen-detected colorectal cancers (CRC) are significantly smaller than symptomatic CRC. • Screening cases are significantly less conspicuous to radiologists than symptomatic tumours. • Screen-detected CRC have different morphology compared to symptomatic tumours (more polypoid, fewer annular). • A commercial computer-aided detection (CAD) system was significantly less likely to note screen-detected CRC.

Project description:ObjectivesTo investigate the differentiation of premalignant from benign colorectal polyps detected by CT colonography using deep learning.MethodsIn this retrospective analysis of an average risk colorectal cancer screening sample, polyps of all size categories and morphologies were manually segmented on supine and prone CT colonography images and classified as premalignant (adenoma) or benign (hyperplastic polyp or regular mucosa) according to histopathology. Two deep learning models SEG and noSEG were trained on 3D CT colonography image subvolumes to predict polyp class, and model SEG was additionally trained with polyp segmentation masks. Diagnostic performance was validated in an independent external multicentre test sample. Predictions were analysed with the visualisation technique Grad-CAM++.ResultsThe training set consisted of 107 colorectal polyps in 63 patients (mean age: 63 ± 8 years, 40 men) comprising 169 polyp segmentations. The external test set included 77 polyps in 59 patients comprising 118 polyp segmentations. Model SEG achieved a ROC-AUC of 0.83 and 80% sensitivity at 69% specificity for differentiating premalignant from benign polyps. Model noSEG yielded a ROC-AUC of 0.75, 80% sensitivity at 44% specificity, and an average Grad-CAM++ heatmap score of ≥ 0.25 in 90% of polyp tissue.ConclusionsIn this proof-of-concept study, deep learning enabled the differentiation of premalignant from benign colorectal polyps detected with CT colonography and the visualisation of image regions important for predictions. The approach did not require polyp segmentation and thus has the potential to facilitate the identification of high-risk polyps as an automated second reader.Key points• Non-invasive deep learning image analysis may differentiate premalignant from benign colorectal polyps found in CT colonography scans. • Deep learning autonomously learned to focus on polyp tissue for predictions without the need for prior polyp segmentation by experts. • Deep learning potentially improves the diagnostic accuracy of CT colonography in colorectal cancer screening by allowing for a more precise selection of patients who would benefit from endoscopic polypectomy, especially for patients with polyps of 6-9 mm size.

Dataset Information

Increasing Navigation Speed at Endoluminal CT Colonography Reduces Colonic Visualization and Polyp Identification.

Publications

Increasing Navigation Speed at Endoluminal CT Colonography Reduces Colonic Visualization and Polyp Identification.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets