Deep learning system improved detection efficacy of fetal intracranial malformations in a randomized controlled trial

Congenital malformations of the central nervous system are among the most common major congenital malformations. Deep learning systems have come to the fore in prenatal diagnosis of congenital malformation, but the impact of deep learning-assisted detection of congenital intracranial malformations from fetal neurosonographic images has not been evaluated. Here we report a three-way crossover, randomized control trial (Trial Registration: ChiCTR2100048233) that assesses the efficacy of a deep learning system, the Prenatal Ultrasound Diagnosis Artificial Intelligence Conduct System (PAICS), in assisting fetal intracranial malformation detection. A total of 709 fetal neurosonographic images/videos are read interactively by 36 sonologists of different expertise levels in three reading modes: unassisted mode (without PAICS assistance), concurrent mode (using PAICS at the beginning of the assessment) and second mode (using PAICS after a fully unaided interpretation). Aided by PAICS, the average accuracy of the unassisted mode (73%) is increased by the concurrent mode (80%; P < 0.001) and the second mode (82%; P < 0.001). Correspondingly, the AUC is increased from 0.85 to 0.89 and to 0.90, respectively (P < 0.001 for all). The median read time per data is slightly increased in concurrent mode but substantially prolonged in the second mode, from 6 s to 7 s and to 11 s (P < 0.001 for all). In conclusion, PAICS in both concurrent and second modes has the potential to improve sonologists' performance in detecting fetal intracranial malformations from neurosonographic data. PAICS is more efficient when used concurrently for all readers.

Colorectal Cancer: Performance and Evaluation for CT Colonography Screening- A Multicenter Cluster-randomized Controlled Trial

Background Most radiologists reporting CT colonography (CTC) do not undergo compulsory performance accreditation, potentially lowering diagnostic sensitivity. Purpose To determine whether 1-day individualized training in CTC reporting improves diagnostic sensitivity of experienced radiologists for 6-mm or larger lesions, the durability of any improvement, and any associated factors. Materials and Methods This prospective, multicenter cluster-randomized controlled trial was performed in National Health Service hospitals in England and Wales between April 2017 and January 2020. CTC services were cluster randomized into intervention (1-day training plus feedback) or control (no training or feedback) arms. Radiologists in the intervention arm attended a 1-day workshop focusing on CTC reporting pitfalls with individualized feedback. Radiologists in the control group received no training. Sensitivity for 6-mm or larger lesions was tested at baseline and 1, 6, and 12 months thereafter via interpretation of 10 CTC scans at each time point. The primary outcome was the mean difference in per-lesion sensitivity between arms at 1 month, analyzed using multilevel regression after adjustment for baseline sensitivity. Secondary outcomes included per-lesion sensitivity at 6- and 12-month follow-up, sensitivity for flat neoplasia, and effect of prior CTC experience. Results A total of 69 hospitals were randomly assigned to the intervention (31 clusters, 80 radiologists) or control (38 clusters, 59 radiologists) arm. Radiologists were experienced (median, 500-999 CTC scans interpreted) and reported CTC scans routinely (median, 151-200 scans per year). One-month sensitivity improved after intervention (66.4% [659 of 992]) compared with sensitivity in the control group (42.4% [278 of 655]; difference = 20.8%; 95% CI: 14.6, 27.0; P < .001). Improvements were maintained at 6 (66.4% [572 of 861] vs 50.5% [283 of 560]; difference = 13.0%; 95% CI: 7.4, 18.5; P < .001) and 12 (63.7% [310 of 487] vs 44.4% [187 of 421]; difference = 16.7%; 95% CI: 10.3, 23.1; P < .001) months. This beneficial effect applied to flat lesions (difference = 22.7%; 95% CI: 15.5, 29.9; P < .001) and was independent of career experience (≥1500 CTC scans: odds ratio = 1.09; 95% CI: 0.88, 1.36; P = .22). Conclusion For radiologists evaluating CT colonography studies, a 1-day training intervention yielded sustained improvement in detection of clinically relevant colorectal neoplasia, independent of previous career experience. Clinical trial registration no. NCT02892721 © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Pickhardt in this issue.

Deep learning in CT colonography: differentiating premalignant from benign colorectal polyps

Objectives

To investigate the differentiation of premalignant from benign colorectal polyps detected by CT colonography using deep learning.

Methods

In 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++.

Results

The 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.

Conclusions

In 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.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-021-08532-2.

Opportunities in cancer imaging: a review of oesophageal, gastric and colorectal malignancies

The incidence of gastrointestinal (GI) malignancy is increasing worldwide. In particular, there is a concerning rise in incidence of GI cancer in younger adults. Direct endoscopic visualisation of luminal tumour sites requires invasive procedures, which are associated with certain risks, but remain necessary because of limitations in current imaging techniques and the continuing need to obtain tissue for diagnosis and genetic analysis; however, management of GI cancer is increasingly reliant on non-invasive, radiological imaging to diagnose, stage, and treat these malignancies. Oesophageal, gastric, and colorectal malignancies require specialist investigation and treatment due to the complex nature of the anatomy, biology, and subsequent treatment strategies. As cancer imaging techniques develop, many opportunities to improve tumour detection, diagnostic accuracy and treatment monitoring present themselves. This review article aims to report current imaging practice, advances in various radiological modalities in relation to GI luminal tumour sites and describes opportunities for GI radiologists to improve patient outcomes.

How to Read Articles That Use Machine Learning: Users' Guides to the Medical Literature

In recent years, many new clinical diagnostic tools have been developed using complicated machine learning methods. Irrespective of how a diagnostic tool is derived, it must be evaluated using a 3-step process of deriving, validating, and establishing the clinical effectiveness of the tool. Machine learning-based tools should also be assessed for the type of machine learning model used and its appropriateness for the input data type and data set size. Machine learning models also generally have additional prespecified settings called hyperparameters, which must be tuned on a data set independent of the validation set. On the validation set, the outcome against which the model is evaluated is termed the reference standard. The rigor of the reference standard must be assessed, such as against a universally accepted gold standard or expert grading.

Performance and Reading Time of Automated Breast US with or without Computer-aided Detection

BackgroundComputer-aided detection (CAD) systems may be used to help radiologists interpret automated breast (AB) US images. However, the optimal use of CAD with AB US has, to the knowledge of the authors, not been determined.PurposeTo compare the performance and reading time of different readers by using AB US CAD system to detect breast cancer in different reading modes.Materials and MethodsIn this retrospective study, 1485 AB US images (282 with malignant lesions, 695 with benign lesions, and 508 healthy) in 1452 women (mean age, 43.7 years; age range, 19-82 years) including 529 (36.4%) women who were asymptomatic were collected between 2016 and 2017. A CAD system was used to interpret the images. Three novice readers with 1-3 years of US experience and three experienced readers with 5-10 years of US experience were assigned to read AB US images without CAD, at a second reading (after the reader completed a full unaided interpretation), and at concurrent reading (use of CAD at the start of the assessment). Diagnostic performances and reading times were compared by using analysis of variance.ResultsFor all readers, the mean area under the receiver operating characteristic curve improved from 0.88 (95% confidence interval [CI]: 0.85, 0.91) at without-CAD mode to 0.91 (95% CI: 0.89, 0.92; P < .001) at the second-reading mode and 0.90 (95% CI: 0.89, 0.92; P = .002) at the concurrent-reading mode. The mean sensitivity of novice readers in women who were asymptomatic improved from 67% (95% CI: 63%, 74%) at without-CAD mode to 88% (95% CI: 84%, 89%) at both the second-reading mode and the concurrent-reading mode (P = .003). Compared with the without-CAD and second-reading modes, the mean reading time per volume of concurrent reading was 16 seconds (95% CI: 11, 22; P < .001) and 27 seconds (95% CI: 21, 32; P < .001) shorter, respectively.ConclusionComputer-aided detection (CAD) was helpful for novice readers to improve cancer detection at automated breast US in women who were asymptomatic. CAD was more efficient when used concurrently for all readers.© RSNA, 2019Online supplemental material is available for this article.See also the editorial by Slanetz in this issue.

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.

Virtual monoenergetic imaging in rapid kVp-switching dual-energy CT (DECT) of the abdomen: impact on CT texture analysis

PURPOSE

To study the impact of keV levels of virtual monoenergetic images generated from rapid kVp-switching dual-energy CT (rsDECT) on CT texture analysis (CTTA).

METHODS

This study included 30 consecutive patients (59.3 ± 12 years; range 34-77 years; 17M:13F) who underwent portal venous phase abdominal CT on a rsDECT scanner. Axial 5-mm monoenergetic images at 5 energy levels (40/50/60/70/80 keV) were created and CTTA of liver was performed. CTTA comprised a filtration-histogram technique with different spatial scale filter (SSF) values (0-6). CTTA quantification at each SSF value included histogram-based statistical parameters such as mean intensity, standard deviation (SD), entropy, mean of positive pixels (MPP), skewness, and kurtosis. The values were compared using repeated measures ANOVA.

RESULTS

Among the different CTTA metrics, mean intensity (at SSF > 0), skewness, and kurtosis did not show variability whereas entropy, MPP, and SD varied with different keV levels. There was no change in skewness and kurtosis values for all 6 filters (p > 0.05). Mean intensity showed no change for filters 2-6 (p > 0.05). Mean intensity at SSF = 0 i.e., mean attenuations were 91.2 ± 2.9, 108.7 ± 3.6, 136.1 ± 4.7, 179.8 ± 6.9, and 250.5 ± 10.1 HU for 80, 70, 60, 50, and 40 keV images, respectively demonstrating significant variability (decrease) with increasing keV levels (p < 0.001). Entropy, MPP, and SD values showed a statistically significant decrease with increasing keV of monoenergetic images on all 6 filters (p < 0.001).

CONCLUSION

The energy levels of monoenergetic images have variable impact on the different CTTA parameters, with no significant change in skewness, kurtosis, and filtered mean intensity whereas significant decrease in mean attenuation, entropy, MPP, and SD values with increasing energy levels.

Fecal Matrix Metalloprotease-9 and Lipocalin-2 as Biomarkers in Detecting Endoscopic Activity in Patients With Inflammatory Bowel Diseases

BACKGROUND

Fecal biomarkers are emerging tools in the assessment of mucosal healing in inflammatory bowel diseases (IBD).

GOALS

We aimed to evaluate the accuracy of fecal matrix metalloprotease-9 (MMP-9) and fecal lipocalin-2 (LCN-2) compared with calprotectin in detecting endoscopic activity in IBD STUDY:: Overall, 86 IBD adults underwent colonoscopy consecutively and prospectively, with Crohn's disease Endoscopic Index of Severity (CDEIS) in Crohn's disease (CD) patients or Mayo endoscopic subscore calculation for ulcerative colitis (UC) patients, and stool collection. Fecal calprotectin was measured using quantitative immunochromatographic testing. Fecal MMP-9 and LCN-2 was quantified by enzyme-linked immunosorbent assay. MMP-9 and LCN-2 thresholds were determined using receiver operating curves.

RESULTS

In 54 CD patients, fecal calprotectin, MMP-9 and LCN-2 correlated with CDEIS and were significantly increased in patients with endoscopic ulcerations. MMP-9 >350 ng/g detected endoscopic ulceration in CD with a sensitivity of 90.0% and a specificity of 63.6%, compared with fecal calprotectin >250 μg/g (sensitivity=90.5% and specificity=59.1%). Fecal LCN-2 demonstrated lower performances than the 2 other biomarkers (sensitivity=85.7% and specificity=45.5%).In 32 UC patients, fecal MMP-9, LCN-2, and calprotectin levels were significantly increased in patients with endoscopic activity. In UC patients, fecal MMP-9 >900 ng/g had the best efficacy to detect endoscopic activity (sensitivity=91.0% and specificity=80.0%, compared with fecal calprotectin >250 μg/g (sensitivity=86.4% and specificity=80.0%) and LCN-2 >6700 ng/g (sensitivity=82.0% and specificity=80.0%).

CONCLUSIONS

Fecal MMP-9 is a reliable biomarker in detecting endoscopic activity in both UC and CD patients.

Post-imaging colorectal cancer or interval cancer rates after CT colonography: a systematic review and meta-analysis

BACKGROUND

CT colonography is highly sensitive for colorectal cancer, but interval or post-imaging colorectal cancer rates (diagnosis of cancer after initial negative CT colonography) are unknown, as are their underlying causes. We did a systematic review and meta-analysis of post-CT colonography and post-imaging colorectal cancer rates and causes to address this gap in understanding.

METHODS

We systematically searched MEDLINE, Embase, and the Cochrane Central Register of Controlled Trials. We included randomised, cohort, cross-sectional, or case-control studies published between Jan 1, 1994, and Feb 28, 2017, using CT colonography done according to international consensus standards with the aim of detecting cancer or polyps, and reporting post-imaging colorectal cancer rates or sufficient data to allow their calculation. We excluded studies in which all CT colonographies were done because of incomplete colonoscopy or if CT colonography was done with knowledge of colonoscopy findings. We contacted authors of component studies for additional data where necessary for retrospective CT colonography image review and causes for each post-imaging colorectal cancer. Two independent reviewers extracted data from the study reports. Our primary outcome was prevalence of post-imaging colorectal cancer 36 months after CT colonography. We used random-effects meta-analysis to estimate pooled post-imaging colorectal cancer rates, expressed using the total number of cancers and total number of CT colonographies as denominators, and per 1000 person-years. This study is registered with PROSPERO, number CRD42016042437.

FINDINGS

2977 articles were screened and 12 studies were eligible for analysis. These studies reported data for 19 867 patients (aged 18-96 years; of 11 590 with sex data available, 6532 [56%] were female) between March, 2002, and May, 2015. At a mean of 34 months' follow-up (range 3-128·4 months), CT colonography detected 643 colorectal cancers. 29 post-imaging colorectal cancers were subsequently diagnosed. The pooled post-imaging colorectal cancer rate was 4·42 (95% CI 3·03-6·42) per 100 cancers detected, corresponding to 1·61 (1·11-2·33) post-imaging colorectal cancers per 1000 CT colonographies or 0·64 (0·44-0·92) post-imaging colorectal cancers per 1000 person-years. Heterogeneity was low (I²=0%). 17 (61%) of 28 post-imaging colorectal cancers were attributable to perceptual error and were visible in retrospect.

INTERPRETATION

CT colonography does not lead to an excess of post-test cancers relative to colonoscopy within 3-5 years, and the low 5-year post-imaging colorectal cancer rate confirms that the recommended screening interval of 5 years is safe. Since most post-imaging colorectal cancers arise from perceptual errors, radiologist training and quality assurance could help to reduce post-imaging colorectal cancer rates.

FUNDING

St Mark's Hospital Foundation and the UK National Institute for Health Research via the UCL/UCLH Biomedical Research Centre.

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

As navigation speed increases, gaze of the reader becomes more central and polyp identification rates fall.

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.

Faecal chitinase 3-like 1 is a reliable marker as accurate as faecal calprotectin in detecting endoscopic activity in adult patients with inflammatory bowel diseases

BACKGROUND

Faecal biomarkers are emerging tools in the assessment of mucosal healing in inflammatory bowel diseases (IBDs).

AIM

To evaluate the accuracy of faecal chitinase 3-like 1(CHI3L1) compared to calprotectin in detecting endoscopic activity in IBD.

METHODS

Overall, 86 IBD adults underwent colonoscopy consecutively and prospectively, with Crohn's disease Endoscopic Index of Severity (CDEIS) or Mayo endoscopic subscore calculation for ulcerative colitis, and stool collection. Faecal calprotectin was measured using quantitative immunochromatographic testing. Faecal CHI3L1 was quantified by ELISA. CHI3L1 cut-off value was determined using a receiver-operating curve.

RESULTS

In 54 Crohn's disease patients, faecal CHI3L1 (ρ = 0.70, P < 0.001) and calprotectin (ρ = 0.74, P < 0.001) levels correlated with CDEIS and were significantly increased in patients with endoscopic ulceration. In patients with ileal Crohn's disease, faecal CHI3L1 seemed to be better correlated with CDEIS than faecal calprotectin (ρ = 0.78 vs. ρ = 0.62, P < 0.001 for both). CHI3L1 > 15 ng/g detected endoscopic ulceration in Crohn's disease with a sensitivity of 100% and a specificity of 63.6%, compared to faecal calprotectin > 250 μg/g showing a sensitivity of 90.5% and a specificity of 59.1%. In 32 ulcerative colitis patients, faecal CHI3L1 and calprotectin levels correlated with Mayo endoscopic subscore (ρ = 0.44 and 0.61, respectively, P < 0.001 for both) and were significantly increased in ulcerative colitis patients with endoscopic activity. In ulcerative colitis patients, faecal CHI3L1 > 15 ng/g predicted endoscopic activity with a sensitivity of 81.8% and a specificity of 80.0%, compared to faecal calprotectin>250 μg/g showing a sensitivity of 86.4% and a specificity of 80.0%.

CONCLUSION

Faecal CHI3L1 is a reliable biomarker in detecting endoscopic activity in IBD.

Progress in Fully Automated Abdominal CT Interpretation

OBJECTIVE

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

CONCLUSION

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

Do prevalence expectations affect patterns of visual search and decision-making in interpreting CT colonography endoluminal videos?

OBJECTIVE

To assess the effect of expected abnormality prevalence on visual search and decision-making in CT colonography (CTC).

METHODS

13 radiologists interpreted endoluminal CTC fly-throughs of the same group of 10 patient cases, 3 times each. Abnormality prevalence was fixed (50%), but readers were told, before viewing each group, that prevalence was either 20%, 50% or 80% in the population from which cases were drawn. Infrared visual search recording was used. Readers indicated seeing a polyp by clicking a mouse. Multilevel modelling quantified the effect of expected prevalence on outcomes.

RESULTS

Differences between expected prevalence were not statistically significant for time to first pursuit of the polyp (median 0.5 s, each prevalence), pursuit rate when no polyp was on screen (median 2.7 s(-1), each prevalence) or number of mouse clicks [mean 0.75/video (20% prevalence), 0.93 (50%), 0.97 (80%)]. There was weak evidence of increased tendency to look outside the central screen area at 80% prevalence and reduction in positive polyp identifications at 20% prevalence.

CONCLUSION

This study did not find a large effect of prevalence information on most visual search metrics or polyp identification in CTC. Further research is required to quantify effects at lower prevalence and in relation to secondary outcome measures.

ADVANCES IN KNOWLEDGE

Prevalence effects in evaluating CTC have not previously been assessed. In this study, providing expected prevalence information did not have a large effect on diagnostic decisions or patterns of visual search.

Developments in Screening Tests and Strategies for Colorectal Cancer

BACKGROUND

Worldwide, colorectal cancer (CRC) is the third most common cancer in men and second most common in women. It is the fourth most common cause of cancer mortality. In the United States, CRC is the third most common cause of cancer and second most common cause of cancer mortality. Incidence and mortality rates have steadily fallen, primarily due to widespread screening.

METHODS

We conducted keyword searches on PubMed in four categories of CRC screening: stool, endoscopic, radiologic, and serum, as well as news searches in Medscape and Google News.

RESULTS

Colonoscopy is the gold standard for CRC screening and the most common method in the United States. Technological improvements continue to be made, including the promising "third-eye retroscope." Fecal occult blood remains widely used, particularly outside the United States. The first at-home screen, a fecal DNA screen, has also recently been approved. Radiological methods are effective but seldom used due to cost and other factors. Serum tests are largely experimental, although at least one is moving closer to market.

CONCLUSIONS

Colonoscopy is likely to remain the most popular screening modality for the immediate future, although its shortcomings will continue to spur innovation in a variety of modalities.

Assessment of the Incremental Benefit of Computer-Aided Detection (CAD) for Interpretation of CT Colonography by Experienced and Inexperienced Readers

OBJECTIVES

To quantify the incremental benefit of computer-assisted-detection (CAD) for polyps, for inexperienced readers versus experienced readers of CT colonography.

METHODS

10 inexperienced and 16 experienced radiologists interpreted 102 colonography studies unassisted and with CAD utilised in a concurrent paradigm. They indicated any polyps detected on a study sheet. Readers' interpretations were compared against a ground-truth reference standard: 46 studies were normal and 56 had at least one polyp (132 polyps in total). The primary study outcome was the difference in CAD net benefit (a combination of change in sensitivity and change in specificity with CAD, weighted towards sensitivity) for detection of patients with polyps.

RESULTS

Inexperienced readers' per-patient sensitivity rose from 39.1% to 53.2% with CAD and specificity fell from 94.1% to 88.0%, both statistically significant. Experienced readers' sensitivity rose from 57.5% to 62.1% and specificity fell from 91.0% to 88.3%, both non-significant. Net benefit with CAD assistance was significant for inexperienced readers but not for experienced readers: 11.2% (95%CI 3.1% to 18.9%) versus 3.2% (95%CI -1.9% to 8.3%) respectively.

CONCLUSIONS

Concurrent CAD resulted in a significant net benefit when used by inexperienced readers to identify patients with polyps by CT colonography. The net benefit was nearly four times the magnitude of that observed for experienced readers. Experienced readers did not benefit significantly from concurrent CAD.

The effect of computer-aided detection markers on visual search and reader performance during concurrent reading of CT colonography

OBJECTIVE

We aimed to identify the effect of computer-aided detection (CAD) on visual search and performance in CT Colonography (CTC) of inexperienced and experienced readers.

METHODS

Fifteen endoluminal CTC examinations were recorded, each with one polyp, and two videos were generated, one with and one without a CAD mark. Forty-two readers (17 experienced, 25 inexperienced) interpreted the videos during infrared visual search recording. CAD markers and polyps were treated as regions of interest in data processing. This multi-reader, multi-case study was analysed using multilevel modelling.

RESULTS

CAD drew readers' attention to polyps faster, accelerating identification times: median 'time to first pursuit' was 0.48 s (IQR 0.27 to 0.87 s) with CAD, versus 0.58 s (IQR 0.35 to 1.06 s) without. For inexperienced readers, CAD also held visual attention for longer. All visual search metrics used to assess visual gaze behaviour demonstrated statistically significant differences when "with" and "without" CAD were compared. A significant increase in the number of correct polyp identifications across all readers was seen with CAD (74 % without CAD, 87 % with CAD; p < 0.001).

CONCLUSIONS

CAD significantly alters visual search and polyp identification in readers viewing three-dimensional endoluminal CTC. For polyp and CAD marker pursuit times, CAD generally exerted a larger effect on inexperienced readers.

KEY POINTS

• Visual gaze is attracted by computer-assisted detection (CAD) marks on polyps • Inexperienced readers' gaze is affected more by CAD than experienced readers. • CAD marks could mean that the unannotated endoluminal surface is relatively neglected. • Correct polyp identification is increased significantly by CAD.

Disadvantages of using the area under the receiver operating characteristic curve to assess imaging tests: a discussion and proposal for an alternative approach

OBJECTIVES

The objectives are to describe the disadvantages of the area under the receiver operating characteristic curve (ROC AUC) to measure diagnostic test performance and to propose an alternative based on net benefit.

METHODS

We use a narrative review supplemented by data from a study of computer-assisted detection for CT colonography.

RESULTS

We identified problems with ROC AUC. Confidence scoring by readers was highly non-normal, and score distribution was bimodal. Consequently, ROC curves were highly extrapolated with AUC mostly dependent on areas without patient data. AUC depended on the method used for curve fitting. ROC AUC does not account for prevalence or different misclassification costs arising from false-negative and false-positive diagnoses. Change in ROC AUC has little direct clinical meaning for clinicians. An alternative analysis based on net benefit is proposed, based on the change in sensitivity and specificity at clinically relevant thresholds. Net benefit incorporates estimates of prevalence and misclassification costs, and it is clinically interpretable since it reflects changes in correct and incorrect diagnoses when a new diagnostic test is introduced.

CONCLUSIONS

ROC AUC is most useful in the early stages of test assessment whereas methods based on net benefit are more useful to assess radiological tests where the clinical context is known. Net benefit is more useful for assessing clinical impact.

KEY POINTS

• The area under the receiver operating characteristic curve (ROC AUC) measures diagnostic accuracy. • Confidence scores used to build ROC curves may be difficult to assign. • False-positive and false-negative diagnoses have different misclassification costs. • Excessive ROC curve extrapolation is undesirable. • Net benefit methods may provide more meaningful and clinically interpretable results than ROC AUC.

The ribs unfolded - a CT visualization algorithm for fast detection of rib fractures: effect on sensitivity and specificity in trauma patients

OBJECTIVE

To assess a radiologist's detection rate of rib fractures in trauma CT when reading curved planar reformats (CPRs) of the ribs compared to reading standard MPRs.

METHODS

Two hundred and twenty trauma CTs (146 males, 74 females) were retrospectively subjected to a software algorithm to generate CPRs of the ribs. Patients were split into two equal groups. Sixteen patients were excluded due to insufficient segmentation, leaving 107 patients in group A and 97 patients in group B. Two radiologists independently evaluated group A using CPRs and group B using standard MPRs. Two different radiologists reviewed both groups with the inverse methods setting. Results were compared to a standard of reference created by two senior radiologists.

RESULTS

The reference standard identified 361 rib fractures in 61 patients. Reading CPRs showed a significantly higher overall sensitivity (P < 0.001) for fracture detection than reading standard MPRs, with 80.9% (584/722) and 71.5% (516/722), respectively. Mean reading time was significantly shorter for CPRs (31.3 s) compared to standard MPRs (60.7 s; P < 0.001).

CONCLUSION

Using CPRs for the detection of rib fractures accelerates the reading of trauma patient chest CTs, while offering an increased overall sensitivity compared to conventional standard MPRs.

KEY POINTS

• In major blunt trauma, rib fractures are diagnosed with Computed Tomography. • Image processing can unfold all ribs into a single plane. • Unfolded ribs can be read twice as fast as axial images. • Unfolding the ribs allows a more accurate diagnosis of rib fractures.

History, evolution, and current status of radiologic imaging tests for colorectal cancer screening

Colorectal cancer screening is thought to be an effective tool with which to reduce the mortality from colorectal cancer through early detection and removal of colonic adenomas and early colon cancers. In this article, we review the history, evolution, and current status of imaging tests of the colon-including single-contrast barium enema, double-contrast barium enema, computed tomographic (CT) colonography, and magnetic resonance (MR) colonography-for colorectal cancer screening. Despite its documented value in the detection of colonic polyps, the double-contrast barium enema has largely disappeared as a screening test because it is widely perceived as a labor-intensive, time-consuming, and technically demanding procedure. In the past decade, the barium enema has been supplanted by CT colonography as the major imaging test in colorectal cancer screening in the United States, with MR colonography emerging as another viable option in Europe. Although MR colonography does not require ionizing radiation, the radiation dose for CT colonography has decreased substantially, and regular screening with this technique has a high benefit-to-risk ratio. In recent years, CT colonography has been validated as an effective tool for use in colorectal cancer screening that is increasingly being disseminated.

Tracking eye gaze during interpretation of endoluminal three-dimensional CT colonography: visual perception of experienced and inexperienced readers

PURPOSE

To identify and compare key stages of the visual process in experienced and inexperienced readers and to examine how these processes are used to search a moving three-dimensional ( 3D three-dimensional ) image and their relationship to false-negative errors.

MATERIALS AND METHODS

Institutional review board research ethics approval was granted to use anonymized computed tomographic (CT) colonographic data from previous studies and to obtain eye-tracking data from volunteers. Sixty-five radiologists (27 experienced, 38 inexperienced) interpreted 23 endoluminal 3D three-dimensional CT colonographic videos. Eye movements were recorded by using eye tracking with a desk-mounted tracker. Readers indicated when they saw a polyp by clicking a computer mouse. Polyp location and boundary on each video frame were quantified and gaze data were related to the polyp boundary for each individual reader and case. Predefined metrics were quantified and used to describe and compare visual search patterns between experienced and inexperienced readers by using multilevel modeling.

RESULTS

Time to first pursuit was significantly shorter in experienced readers (hazard ratio, 1.22 [95% confidence interval: 1.04, 1.44]; P = .017) but other metrics were not significantly different. Regardless of expertise, metrics such as assessment, identification period, and pursuit times were extended in videos where polyps were visible on screen for longer periods of time. In 97% (760 of 787) of observations, readers correctly pursued polyps.

CONCLUSION

Experienced readers had shorter time to first eye pursuit, but many other characteristics of eye tracking were similar between experienced and inexperienced readers. Readers pursued polyps in 97% of observations, which indicated that errors during interpretation of 3D three-dimensional CT colonography in this study occurred in either the discovery or the recognition phase, but rarely in the scanning phase of radiologic image inspection.

Exploration of analysis methods for diagnostic imaging tests: problems with ROC AUC and confidence scores in CT colonography

BACKGROUND

Different methods of evaluating diagnostic performance when comparing diagnostic tests may lead to different results. We compared two such approaches, sensitivity and specificity with area under the Receiver Operating Characteristic Curve (ROC AUC) for the evaluation of CT colonography for the detection of polyps, either with or without computer assisted detection.

METHODS

In a multireader multicase study of 10 readers and 107 cases we compared sensitivity and specificity, using radiological reporting of the presence or absence of polyps, to ROC AUC calculated from confidence scores concerning the presence of polyps. Both methods were assessed against a reference standard. Here we focus on five readers, selected to illustrate issues in design and analysis. We compared diagnostic measures within readers, showing that differences in results are due to statistical methods.

RESULTS

Reader performance varied widely depending on whether sensitivity and specificity or ROC AUC was used. There were problems using confidence scores; in assigning scores to all cases; in use of zero scores when no polyps were identified; the bimodal non-normal distribution of scores; fitting ROC curves due to extrapolation beyond the study data; and the undue influence of a few false positive results. Variation due to use of different ROC methods exceeded differences between test results for ROC AUC.

CONCLUSIONS

The confidence scores recorded in our study violated many assumptions of ROC AUC methods, rendering these methods inappropriate. The problems we identified will apply to other detection studies using confidence scores. We found sensitivity and specificity were a more reliable and clinically appropriate method to compare diagnostic tests.

Sequential Monte Carlo tracking of the marginal artery by multiple cue fusion and random forest regression

Given the potential importance of marginal artery localization in automated registration in computed tomography colonography (CTC), we have devised a semi-automated method of marginal vessel detection employing sequential Monte Carlo tracking (also known as particle filtering tracking) by multiple cue fusion based on intensity, vesselness, organ detection, and minimum spanning tree information for poorly enhanced vessel segments. We then employed a random forest algorithm for intelligent cue fusion and decision making which achieved high sensitivity and robustness. After applying a vessel pruning procedure to the tracking results, we achieved statistically significantly improved precision compared to a baseline Hessian detection method (2.7% versus 75.2%, p<0.001). This method also showed statistically significantly improved recall rate compared to a 2-cue baseline method using fewer vessel cues (30.7% versus 67.7%, p<0.001). These results demonstrate that marginal artery localization on CTC is feasible by combining a discriminative classifier (i.e., random forest) with a sequential Monte Carlo tracking mechanism. In so doing, we present the effective application of an anatomical probability map to vessel pruning as well as a supplementary spatial coordinate system for colonic segmentation and registration when this task has been confounded by colon lumen collapse.

Towards a framework for analysis of eye-tracking studies in the three dimensional environment: a study of visual search by experienced readers of endoluminal CT colonography

OBJECTIVE

Eye tracking in three dimensions is novel, but established descriptors derived from two-dimensional (2D) studies are not transferable. We aimed to develop metrics suitable for statistical comparison of eye-tracking data obtained from readers of three-dimensional (3D) "virtual" medical imaging, using CT colonography (CTC) as a typical example.

METHODS

Ten experienced radiologists were eye tracked while observing eight 3D endoluminal CTC videos. Subsequently, we developed metrics that described their visual search patterns based on concepts derived from 2D gaze studies. Statistical methods were developed to allow analysis of the metrics.

RESULTS

Eye tracking was possible for all readers. Visual dwell on the moving region of interest (ROI) was defined as pursuit of the moving object across multiple frames. Using this concept of pursuit, five categories of metrics were defined that allowed characterization of reader gaze behaviour. These were time to first pursuit, identification and assessment time, pursuit duration, ROI size and pursuit frequency. Additional subcategories allowed us to further characterize visual search between readers in the test population.

CONCLUSION

We propose metrics for the characterization of visual search of 3D moving medical images. These metrics can be used to compare readers' visual search patterns and provide a reproducible framework for the analysis of gaze tracking in the 3D environment.

ADVANCES IN KNOWLEDGE

This article describes a novel set of metrics that can be used to describe gaze behaviour when eye tracking readers during interpretation of 3D medical images. These metrics build on those established for 2D eye tracking and are applicable to increasingly common 3D medical image displays.

Population screening for colorectal cancer by flexible sigmoidoscopy or CT colonography: study protocol for a multicenter randomized trial

BACKGROUND

Colorectal cancer (CRC) is the second most prevalent type of cancer in Europe. A single flexible sigmoidoscopy (FS) screening at around the age of 60 years prevents about one-third of CRC cases. However, FS screens only the distal colon, and thus mortality from proximal CRC is unaffected. Computed tomography colonography (CTC) is a highly accurate examination that allows assessment of the entire colon. However, the benefit of CTC testing as a CRC screening test is uncertain. We designed a randomized trial to compare participation rate, detection rates, and costs between CTC (with computer-aided detection) and FS as primary tests for population-based screening.

METHODS/DESIGN

An invitation letter to participate in a randomized screening trial comparing CTC versus FS will be mailed to a sample of 20,000 people aged 58 or 60 years, living in the Piedmont region and the Verona district of Italy. Individuals with a history of CRC, adenomas, inflammatory bowel disease, or recent colonoscopy, or with two first-degree relatives with CRC will be excluded from the study by their general practitioners. Individuals responding positively to the invitation letter will be then randomized to the intervention group (CTC) or control group (FS), and scheduled for the screening procedure. The primary outcome parameter of this part of the trial is the difference in advanced neoplasia detection between the two screening tests. Secondary outcomes are cost-effectiveness analysis, referral rates for colonoscopy induced by CTC versus FS, and the expected and perceived burden of the procedures. To compare participation rates for CTC versus FS, 2,000 additional eligible subjects will be randomly assigned to receive an invitation for screening with CTC or FS. In the CTC arm, non-responders will be offered fecal occult blood test (FOBT) as alternative screening test, while in the FS arm, non-responders will receive an invitation letter to undergo screening with either FOBT or CTC. Data on reasons for participation and non-participation will also be collected.

DISCUSSION

This study will provide reliable information concerning benefits and risks of the adoption of CTC as a mass screening intervention in comparison with FS. The trial will also evaluate the role of computer-aided detection in a screening setting.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT01739608.

Patients' & healthcare professionals' values regarding true- & false-positive diagnosis when colorectal cancer screening by CT colonography: discrete choice experiment

Purpose

To establish the relative weighting given by patients and healthcare professionals to gains in diagnostic sensitivity versus loss of specificity when using CT colonography (CTC) for colorectal cancer screening.

Materials and Methods

Following ethical approval and informed consent, 75 patients and 50 healthcare professionals undertook a discrete choice experiment in which they chose between “standard” CTC and “enhanced” CTC that raised diagnostic sensitivity 10% for either cancer or polyps in exchange for varying levels of specificity. We established the relative increase in false-positive diagnoses participants traded for an increase in true-positive diagnoses.

Results

Data from 122 participants were analysed. There were 30 (25%) non-traders for the cancer scenario and 20 (16%) for the polyp scenario. For cancer, the 10% gain in sensitivity was traded up to a median 45% (IQR 25 to >85) drop in specificity, equating to 2250 (IQR 1250 to >4250) additional false-positives per additional true-positive cancer, at 0.2% prevalence. For polyps, the figure was 15% (IQR 7.5 to 55), equating to 6 (IQR 3 to 22) additional false-positives per additional true-positive polyp, at 25% prevalence. Tipping points were significantly higher for patients than professionals for both cancer (85 vs 25, p<0.001) and polyps (55 vs 15, p<0.001). Patients were willing to pay significantly more for increased sensitivity for cancer (p = 0.021).

Conclusion

When screening for colorectal cancer, patients and professionals believe gains in true-positive diagnoses are worth much more than the negative consequences of a corresponding rise in false-positives. Evaluation of screening tests should account for this.

CT colonography: external clinical validation of an algorithm for computer-assisted prone and supine registration

PURPOSE

To perform external validation of a computer-assisted registration algorithm for prone and supine computed tomographic (CT) colonography and to compare the results with those of an existing centerline method.

MATERIALS AND METHODS

All contributing centers had institutional review board approval; participants provided informed consent. A validation sample of CT colonographic examinations of 51 patients with 68 polyps (6-55 mm) was selected from a publicly available, HIPAA compliant, anonymized archive. No patients were excluded because of poor preparation or inadequate distension. Corresponding prone and supine polyp coordinates were recorded, and endoluminal surfaces were registered automatically by using a computer algorithm. Two observers independently scored three-dimensional endoluminal polyp registration success. Results were compared with those obtained by using the normalized distance along the colonic centerline (NDACC) method. Pairwise Wilcoxon signed rank tests were used to compare gross registration error and McNemar tests were used to compare polyp conspicuity.

RESULTS

Registration was possible in all 51 patients, and 136 paired polyp coordinates were generated (68 polyps) to test the algorithm. Overall mean three-dimensional polyp registration error (mean ± standard deviation, 19.9 mm ± 20.4) was significantly less than that for the NDACC method (mean, 27.4 mm ± 15.1; P = .001). Accuracy was unaffected by colonic segment (P = .76) or luminal collapse (P = .066). During endoluminal review by two observers (272 matching tasks, 68 polyps, prone to supine and supine to prone coordinates), 223 (82%) polyp matches were visible (120° field of view) compared with just 129 (47%) when the NDACC method was used (P < .001). By using multiplanar visualization, 48 (70%) polyps were visible after scrolling ± 15 mm in any multiplanar axis compared with 16 (24%) for NDACC (P < .001).

CONCLUSION

Computer-assisted registration is more accurate than the NDACC method for mapping the endoluminal surface and matching the location of polyps in corresponding prone and supine CT colonographic acquisitions.

Development and evaluation of a software tool for the generation of virtual liver lesions in multidetector-row CT datasets

RATIONALE AND OBJECTIVES

Development and evaluation of a software tool for the insertion of simulated hypodense liver lesions in multidetector-row computed tomography (CT) datasets.

MATERIALS AND METHODS

Forty software-generated hypodense liver lesions were inserted at random locations in 20 CT datasets by using the "alpha blending" technique and compared with 40 real metastatic lesions. The location, diameter (5-20 mm) and density of the simulated lesions were individually adjusted to closely resemble real lesions in each patient. Three blinded readers evaluated all 80 lesions twice in a 2-week interval using a five-point Likert confidence scale under standardized conditions. Nonparametric tests were used to statistically evaluate possible differences in scoring between real and simulated lesions. The correctness of the observer rating for real and simulated lesions was compared to chance distribution using the chi-squared statistics. The inter- and intraobserver variability was determined using Kendall's coefficient of concordance.

RESULTS

The observer study did not reveal significant differences between the scoring for real versus simulated lesions for any of the readers (P > .05). The distribution of correct and false scoring of the lesions was not significantly different from chance distribution (P > .05). Inter- and intraobserver agreement was poor (Kendall W coefficient = 0.12/0.13).

CONCLUSION

The proposed algorithm is suitable for creating realistic virtual liver lesions in CT datasets.

Quantifying tumour heterogeneity with CT

Heterogeneity is a key feature of malignancy associated with adverse tumour biology. Quantifying heterogeneity could provide a useful non-invasive imaging biomarker. Heterogeneity on computed tomography (CT) can be quantified using texture analysis which extracts spatial information from CT images (unenhanced, contrast-enhanced and derived images such as CT perfusion) that may not be perceptible to the naked eye. The main components of texture analysis can be categorized into image transformation and quantification. Image transformation filters the conventional image into its basic components (spatial, frequency, etc.) to produce derived subimages. Texture quantification techniques include structural-, model- (fractal dimensions), statistical- and frequency-based methods. The underlying tumour biology that CT texture analysis may reflect includes (but is not limited to) tumour hypoxia and angiogenesis. Emerging studies show that CT texture analysis has the potential to be a useful adjunct in clinical oncologic imaging, providing important information about tumour characterization, prognosis and treatment prediction and response.

Advances in CT Colonography for Colorectal Cancer Screening and Diagnosis

CT colonography (CTC) is a validated colorectal cancer test that provides an additional minimally-invasive screening option which is likely to be preferred by some patients. Important examination prerequisites include adequate colonic cleansing and distention. Tagging of residual material aids in the differentiation of true polyps from stool. Low radiation dose technique should be employed routinely for screening studies. Readers must be skilled in the use of both 2D and 3D interpretation methods.

How to read and report CTC

Owing to encouraging results achieved in the clinical practice, CT colonography (CTC) is being increasingly employed for the examination of the whole colon and rectum and is quickly becoming a widely accepted diagnostic technique that is replacing double contrast barium enema and appears a promising tool for colorectal cancer screening as well. The increasing number of symptomatic and asymptomatic patients undergoing CTC for both evaluation of symptoms and colorectal cancer screening, along with the growing availability of CTC facilities in most healthcare departments and imaging centres, requires that a sufficient number of radiologists be adequately trained in performing and interpreting CTC studies. Indeed, optimal performance of CTC depends on a number of factors, including the quality of colonic preparation (e.g. laxative bowel cleansing and optimised colonic distension), the CTC image acquisition protocol used, and reading approach and specific skills of radiologists for correct detection and interpretation of colonic findings. Consequently, dedicated training and expertise is key to obtain high sensitivity in lesion detection and reduce the number of false positives, thus ensuring an optimal clinical management of patients. To this purpose, dedicated training programmes are essential to teach and standardise not only the approach to CTC reading, but also reporting of colonic findings.

The second ESGAR consensus statement on CT colonography

Objective

To update quality standards for CT colonography based on consensus among opinion leaders within the European Society of Gastrointestinal and Abdominal Radiology (ESGAR).

Material and methods

A multinational European panel of nine members of the ESGAR CT colonography Working Group (representing six EU countries) used a modified Delphi process to rate their level of agreement on a variety of statements pertaining to the acquisition, interpretation and implementation of CT colonography. Four Delphi rounds were conducted, each at 2 months interval.

Results

The panel elaborated 86 statements.

In the final round the panelists achieved complete consensus in 71 of 86 statements (82 %). Categories including the highest proportion of statements with excellent Cronbach's internal reliability were colon distension, scan parameters, use of intravenous contrast agents, general guidelines on patient preparation, role of CAD and lesion measurement.

Lower internal reliability was achieved for the use of a rectal tube, spasmolytics, decubitus positioning and number of CT data acquisitions, faecal tagging, 2D vs. 3D reading, and reporting.

Conclusion

The recommendations of the consensus should be useful for both the radiologist who is starting a CTC service and for those who have already implemented the technique but whose practice may need updating.

Key Points

• Computed tomographic colonography is the optimal radiological method of assessing the colon

• This article reviews ESGAR quality standards for CT colonography

• This article is aimed to provide CT-colonography guidelines for practising radiologists

• The recommendations should help radiologists who are starting/updating their CTC services

The future developments in gastrointestinal radiology

The last decade has witnessed great advances in abdominal imaging with technological developments and diagnostic improvements in CT, MRI and positron emission tomography-CT. Over the next decade, gastrointestinal imaging is set to rapidly evolve. Fluoroscopic techniques will be left behind and we will develop beyond simply anatomical imaging, embracing increasingly functional and quantitative techniques. Dose reduction and radiation-free modalities will take centre stage as imaging goes mobile, allowing clinicians at the bedside and remote subspecialty radiologists to review radiology from electronic devices. The authors discuss some of the key trends set to define the next decade in gastrointestinal radiology.

Computer-aided detection of colorectal polyps in CT colonography with and without fecal tagging: a stand-alone evaluation

PURPOSE

To evaluate the stand-alone performance of a computer-aided detection (CAD) algorithm for colorectal polyps in a large heterogeneous CT colonography (CTC) database that included both tagged and untagged datasets.

METHODS

Written, informed consent was waived for this institutional review board-approved, HIPAA-compliant retrospective study. CTC datasets from 2063 patients were assigned to training (n = 374) and testing (n = 1689). The test set consisted of 836 untagged and 853 tagged examinations not used for CAD training. Examinations were performed at 15 sites in the United States, Asia, and Europe, using 4- to 64-multidetector-row computed tomography and various acquisition parameters. CAD sensitivities were calculated on a per-patient and per-polyp basis for polyps measuring ≥6 mm. The reference standard was colonoscopy in 1588 (94%) and consensus interpretation by expert radiologists in 101 (6%) patients. Statistical testing employed χ, logistic regression, and Mann-Whitney U tests.

RESULTS

In 383 of 1689 individuals, 564 polyps measuring ≥6 mm were identified by the reference standard (347 polyps: 6-9 mm and 217 polyps: ≥10 mm). Overall, CAD per-patient sensitivity was 89.6% (343/383), with 89.0% (187/210) for untagged and 90.2% (156/173) for tagged datasets (P = 0.72). Overall, per-polyp sensitivity was 86.9% (490/564), with 84.4% (270/320) for untagged and 90.2% (220/244) for tagged examinations (P = 068). The mean false-positive rate per patient was 5.14 (median, 4) in untagged and 4.67 (median, 4) in tagged patient datasets (P = 0.353).

CONCLUSION

Stand-alone CAD can be applied to both tagged and untagged CTC studies without significant performance differences. Detection rates are comparable to human readers at a relatively low false-positive rate, making CAD a useful tool in clinical practice.

Does CT colonography have a role for population-based colorectal cancer screening?

Colorectal cancer (CRC) is the second most common cancer and second most common cause of cancer-related deaths in Europe. CRC screening has been proven to reduce disease-specific mortality and several European countries employ national screening programmes. These almost exclusively rely on stool tests, with endoscopy used as an adjunct in some countries. Computed tomographic colonography (CTC) is a potential screening test, with an estimated sensitivity of 88 % for advanced neoplasia ≥10 mm. Recent randomised studies have shown that CTC and colonoscopy have similar yields of advanced neoplasia per screened invitee, indicating that CTC is potentially viable as a primary screening test. However, the evidence is not fully elaborated. It is unclear whether CTC screening is cost-effective and the impact of extracolonic findings, both medical and economic, remains unknown. Furthermore, the effect of CTC screening on CRC-related mortality is unknown, as it is also unknown for colonoscopy. It is plausible that both techniques could lead to decreased mortality, as for sigmoidoscopy and gFOBT. Although radiation exposure is a drawback, this disadvantage may be over-emphasised. In conclusion, the detection characteristics and acceptability of CTC suggest it is a viable screening investigation. Implementation will depend on detection of extracolonic disease and health-economic impact. Key Points • Meta-analysis of CT colonographic screening showed high sensitivity for advanced neoplasia ≥10mm. • CTC, colonoscopy and sigmoidoscopy screening all have similar yields for advanced neoplasia. • Good quality information regarding the cost-effectiveness of CTC screening is lacking. • There is little good quality data regarding the impact of extracolonic findings. • CTC triage is not clinically effective in first round gFOBT/FIT positives.

Predicting readers' diagnostic accuracy with a new CAD algorithm

RATIONALE AND OBJECTIVES

Before computer-aided detection (CAD) algorithms can be used in clinical practice, they must be shown to improve readers' diagnostic accuracy over their unaided performance. This is usually accomplished through a large multireader, multicase (MRMC) clinical trial. It is burdensome, however, for an MRMC study to be performed with each new release of a CAD algorithm. The aim of this report is to present an approach for building models to predict readers' accuracy with a new CAD algorithm.

MATERIALS AND METHODS

A modeling approach for predicting readers' results with a new CAD algorithm is described. Multiple-variable logistic regression was used to build models for readers' sensitivity and false-positive rate, given the results of an MRMC study with an older CAD algorithm and the stand-alone performance results of a new CAD algorithm. Data from a large lung MRMC CAD trial are used to illustrate the modeling approach and test the ability of the models to predict readers' accuracy with the new CAD algorithm.

RESULTS

The model overestimated the readers' actual sensitivity with the new CAD algorithm, but this did not reach statistical significance (0.621 vs 0.603, P = .147). The observed and predicted false-positive rates also did not differ significantly (0.275 vs 0.285, P = .250).

CONCLUSIONS

Using one clinical study as a test case, it is shown that the modeling approach is feasible. More testing of the approach is needed to determine if and under what circumstances it can be used as an alternative to a full-scale MRMC study. Meanwhile, the approach can be used to determine if a new CAD algorithm is likely to improve readers' accuracy before embarking on a full-scale MRMC study.

Evidence review and status update on computed tomography colonography

Computed tomographic (CT) colonography is being implemented increasingly in the USA and Europe, and in many centers it has become the radiological technique of choice for imaging the whole colorectum. Although high diagnostic accuracy has been demonstrated in both screening and symptomatic populations, controversy persists regarding implementation, who should interpret the examination, and its cost effectiveness, particularly in the context of primary colorectal cancer screening. Published research in recent years has demonstrated efficacy in a wide range of patient groups, striking technical improvements, and high levels of patient acceptability. New developments continue in the fields of computer aided detection, digital cleansing, and integration into positron emission tomography. The purpose of this review is to bring the reader up-to-date with the latest developments in CT colonography, in particular, those of the last year.