Automated measurement of colorectal polyp height at CT colonography: hyperplastic polyps are flatter than adenomatous polyps

Severe grade of melanosis coli is associated with a higher detection rate of colorectal adenoma

The severity and distribution of melanosis coli differ among individuals, and the related factors remain unknown. Additionally, their clinical implications have not been sufficiently demon-strated. Thus, we aimed to detect clinical factors related to the severity and range of melanosis coli and elucidate the associations between the grade, location, and detection rate of colorectal neoplasms. Colonoscopy cases performed at our institution from January 2011 to February 2021 were included. Melanosis coli was classified into mild and severe grades. Clinical characteristics and neoplasm detection rates were compared between the mild and severe MC groups and between the right-sided and whole-colon melanosis coli groups. Overall, 236 MC (mild, n = 143; severe, n = 93) cases, of which 50 were right-sided, 5 were left-sided, and 181 were whole-colon melanosis coli cases, were enrolled. The proportion of anthranoid users was higher in the severe melanosis coli group than in the mild melanosis coli group. The adenoma detection rate was higher in the severe melanosis coli and whole-colon melanosis coli groups. The prevalence of neoplasms measuring 5-9 mm and >9 mm was higher in the severe melanosis coli group (p<0.01 and p = 0.04). Severe melanosis coli due to anthranoid usage is associated with colorectal adenoma development.

Machine Learning-based Differentiation of Benign and Premalignant Colorectal Polyps Detected with CT Colonography in an Asymptomatic Screening Population: A Proof-of-Concept Study

Background CT colonography does not enable definite differentiation between benign and premalignant colorectal polyps. Purpose To perform machine learning-based differentiation of benign and premalignant colorectal polyps detected with CT colonography in an average-risk asymptomatic colorectal cancer screening sample with external validation using radiomics. Materials and Methods In this secondary analysis of a prospective trial, colorectal polyps of all size categories and morphologies were manually segmented on CT colonographic images and were classified as benign (hyperplastic polyp or regular mucosa) or premalignant (adenoma) according to the histopathologic reference standard. Quantitative image features characterizing shape (n = 14), gray level histogram statistics (n = 18), and image texture (n = 68) were extracted from segmentations after applying 22 image filters, resulting in 1906 feature-filter combinations. Based on these features, a random forest classification algorithm was trained to predict the individual polyp character. Diagnostic performance was validated in an external test set. Results The random forest model was fitted using a training set consisting of 107 colorectal polyps in 63 patients (mean age, 63 years ± 8 [standard deviation]; 40 men) comprising 169 segmentations on CT colonographic images. The external test set included 77 polyps in 59 patients comprising 118 segmentations. Random forest analysis yielded an area under the receiver operating characteristic curve of 0.91 (95% CI: 0.85, 0.96), a sensitivity of 82% (65 of 79) (95% CI: 74%, 91%), and a specificity of 85% (33 of 39) (95% CI: 72%, 95%) in the external test set. In two subgroup analyses of the external test set, the area under the receiver operating characteristic curve was 0.87 in the size category of 6-9 mm and 0.90 in the size category of 10 mm or larger. The most important image feature for decision making (relative importance of 3.7%) was quantifying first-order gray level histogram statistics. Conclusion In this proof-of-concept study, machine learning-based image analysis enabled noninvasive differentiation of benign and premalignant colorectal polyps with CT colonography. © RSNA, 2021 Online supplemental material is available for this article.

Domain-Based Analysis of Colon Polyp in CT Colonography Using Image-Processing Techniques

Background: The purpose of the research was to improve the polyp detection accuracy in CT Colonography (CTC) through effective colon segmentation, removal of tagged fecal matter through Electronic Cleansing (EC), and measuring the smaller polyps. Methods: An improved method of boundary-based semi-automatic colon segmentation with the knowledge of colon distension, an adaptive multistep method for the virtual cleansing of segmented colon based on the knowledge of Hounsfield Units, and an automated method of smaller polyp measurement using skeletonization technique have been implemented. Results: The techniques were evaluated on 40 CTC dataset. The segmentation method was able to delineate the colon wall accurately. The submerged colonic structures were preserved without soft tissue erosion, pseudo enhanced voxels were corrected, and the air-contrast layer was removed without losing the adjacent tissues. The smaller polyp of size less than <10mm was detected correctly. The results were statistically validated qualitatively and quantitatively. Segmented colons were validated through volumetric overlap computation, and accuracy of 95.826±0.6854% was achieved. In polyp measurement, the paired t-test method was applied to compare the difference with ground truth and at α=5%, t=0.9937 and p=0.098 was achieved. The statistical values of TPR=90%, TNR=82.3% and accuracy=88.31% were achieved. Conclusion: An automated system of polyp measurement has been developed starting from colon segmentation to improve the existing CTC solutions. The analysis of domain-based approach of polyp has given good results. A prototype software, which can be used as a low-cost polyp diagnosis tool, has been developed.

Flat Serrated Polyps at CT Colonography: Relevance, Appearance, and Optimizing Interpretation

Serrated polyps are a recently recognized family of colonic polyps with subgroups that harbor future malignant potential. In the past, the significance of these lesions to the colorectal cancer carcinogenesis pathway was not recognized nor well understood. It is now known that serrated polyps account for approximately one-fourth of all sporadic colorectal cancers. The sessile serrated polyp (SSP) (also known as a sessile serrated adenoma [SSA]) is the main lesion of interest given its prevalence and subtle presentation. These lesions are often flat-only minimally raised from the colonic surface-and occur in the right colon. These lesions have been a likely common cause of screening failure at colonoscopy, although detection has improved with improved recognition over time. Although detection is difficult with image-based screening, serrated lesions can be detected at CT colonography. The prevalence in CT colonography screening populations mirrors the rates at colonoscopy for similar size categories. CT colonography allows identification of SSPs despite their minimally raised profile owing to the phenomenon of lesional contrast material coating. This contrast material coat aids in lesion detection by highlighting the subtle morphologic changes as well as increasing confidence that a true lesion exists despite a flat morphology. It is important to optimize contrast material coating with specific bowel preparations and other technical parameters. Radiologists should be aware of these technical and interpretation issues. Armed with this knowledge, radiologists should expect excellent results in detection of these subtle but important lesions. ^©RSNA, 2017.

Measurement of smaller colon polyp in CT colonography images using morphological image processing

PURPOSE

Automated measurement of the size and shape of colon polyps is one of the challenges in Computed tomography colonography (CTC). The objective of this retrospective study was to improve the sensitivity and specificity of smaller polyp measurement in CTC using image processing techniques.

METHODS

A domain knowledge-based method has been implemented with hybrid method of colon segmentation, morphological image processing operators for detecting the colonic structures, and the decision-making system for delineating the smaller polyp-based on a priori knowledge.

RESULTS

The method was applied on 45 CTC dataset. The key finding was that the smaller polyps were accurately measured. In addition to 6-9 mm range, polyps of even <5 mm were also detected. The results were validated qualitatively and quantitatively using both 2D MPR and 3D view. Implementation was done on a high-performance computer with parallel processing. It takes [Formula: see text] min for measuring the smaller polyp in a dataset of 500 CTC images. With this method, [Formula: see text] and [Formula: see text] were achieved.

CONCLUSIONS

The domain-based approach with morphological image processing has given good results. The smaller polyps were measured accurately which helps in making right clinical decisions. Qualitatively and quantitatively the results were acceptable when compared to the ground truth at [Formula: see text].

Nanomaterials for In Vivo Imaging

In vivo imaging, which enables us to peer deeply within living subjects, is producing tremendous opportunities both for clinical diagnostics and as a research tool. Contrast material is often required to clearly visualize the functional architecture of physiological structures. Recent advances in nanomaterials are becoming pivotal to generate the high-resolution, high-contrast images needed for accurate, precision diagnostics. Nanomaterials are playing major roles in imaging by delivering large imaging payloads, yielding improved sensitivity, multiplexing capacity, and modularity of design. Indeed, for several imaging modalities, nanomaterials are now not simply ancillary contrast entities, but are instead the original and sole source of image signal that make possible the modality's existence. We address the physicochemical makeup/design of nanomaterials through the lens of the physical properties that produce contrast signal for the cognate imaging modality-we stratify nanomaterials on the basis of their (i) magnetic, (ii) optical, (iii) acoustic, and/or (iv) nuclear properties. We evaluate them for their ability to provide relevant information under preclinical and clinical circumstances, their in vivo safety profiles (which are being incorporated into their chemical design), their modularity in being fused to create multimodal nanomaterials (spanning multiple different physical imaging modalities and therapeutic/theranostic capabilities), their key properties, and critically their likelihood to be clinically translated.

Feasibility of computed tomography colonography as a diagnostic procedure in colon cancer screening in India

Computed Tomography Colonography (CTC) is a medical imaging technology used in identifying polyps and colon cancer masses in the large intestine. The technique has evolved a great deal since its invention and has become a routine diagnostic procedure in Western countries due to its non invasiveness and ease of use. The objective of our study was to explore the possibility of CTC application in Indian hospitals. This paper gives an overview of the procedure and its commercial viability. The explanation begins with the domain aspects from gastroenterologist perspective, the new way of thinking in polyp classification, the technical components of CTC procedure, and how engineering solutions have helped clinicians in solving the complexities involved in colon diagnosis. The colon cancer statistics in India and the results of single institution study we carried out with retrospective data is explained. By considering the increasing number of patients developing colon malignancies, the practicality of CTC in Indian hospitals is discussed. This paper does not reveal any technical aspects (algorithms) of engineering solutions implemented in CTC.

Colorectal laterally spreading tumors by computed tomographic colonography

To date, few reports focused primarily on detecting colorectal laterally spreading tumors (LSTs) have been published. The aim of this study was to determine the visibility of LSTs on computed tomographic colonography (CTC) compared with that on colonoscopy as a standard. We retrospectively reviewed and matched data on endoscopic and CTC reports in 157 patients (161 LSTs) who received a multidetector CT scan using contrast media immediately after total colonoscopy at the National Cancer Center Hospital in Tokyo, Japan, between December 2005 and August 2010. The results of the total colonoscopy were known at the time of the CTC procedure and reading. Of the 161 LSTs detected on colonoscopy, 138 were observed and matched by CTC (86%). Of the 91 granular type LSTs (LST-Gs), 88 (97%) were observed and matched, while of the 70 non-granular type LSTs (LST-NGs), 50 (71%) were observed and matched by CTC (p < 0.0001). CTC enabled observation of 73% (22/30) of 20–29 mm, 83% (35/42) of 30–39 mm, 88% (49/56) of 40–59 mm, and 97% (32/33) of ≥60 mm tumors. The rate of observed LSTs by CTC was 86% (97% of LST-G, 71% of LST-NG) of the LSTs found during total colonoscopy.

CT colonography: pitfalls in interpretation

As with any radiologic imaging test, there are several potential interpretive pitfalls at CT colonography that need to be recognized and handled appropriately. Perhaps the single most important step in learning to avoid most of these diagnostic traps is simply to be aware of their existence. With a little experience, most of these potential pitfalls are easily recognized. This article systematically covers the key pitfalls confronting the radiologist at CT colonography interpretation, primarily dividing them into those related to technique and those related to underlying anatomy. Tips and pointers for how to effectively handle these potential pitfalls are included.

Computed tomography colonography: emerging evidence to further support clinical effectiveness

PURPOSE OF REVIEW

Computed tomography colonography (CTC) continues to mature and evolve as a noninvasive imaging test of the large intestine. The aim of this review is to provide an update on the recent and emerging data that further supports the clinical effectiveness of CTC.

RECENT FINDINGS

The diagnostic performance of CTC for detecting colorectal polyps and masses is well established, but its precise clinical role is yet to be determined. Recent data on test performance, patient acceptance, and study technique may help to clarify the role of CTC and accelerate its clinical implementation.

SUMMARY

Recent advances and refinements in CTC should help to clarify and expand its clinical role, both as a screening and diagnostic test. High patient acceptance for CTC could lead to increased adherence rates. Ultimately, the complementary nature of CTC and optical colonoscopy should result in improved patient care.

Fecal-tagging CT colonography with structure-analysis electronic cleansing for detection of colorectal flat lesions

PURPOSE

To evaluate the feasibility and sensitivity of the 3D-reading of fecal-tagging CT colonography (CTC) with a novel structure-analysis electronic cleansing (SAEC) in detecting colorectal flat lesions in comparison with a cleansed 3D reading with Viatronix V3D Colon system (V3D) and primary uncleansed 2D reading (2D).

MATERIALS AND METHODS

Forty CTC cases with flat lesions were retrospectively observed. The Subjects from a multicenter clinical trial underwent cathartic bowel preparation with orally administrated barium-based fecal-tagging. Sixty-nine flat lesions were confirmed using colonoscopy and histopathology as a reference standard. The results from SAEC reading were compared with those of prospective V3D and 2D readings.

RESULTS

Overall detection sensitivity with SAEC was 52% (36/69), which was statistically higher than that of 32% (22/69) and 29% (20/69) with V3D and 2D readings, respectively (p<0.05). The sensitivities in detecting not-on-fold flat lesions were 63% (24/38), 45% (17/38), and 42% (16/38) with SAEC, V3D, and 2D readings, respectively; whereas those of on-fold flat lesions were 39% (12/31), 16% (5/31), and 13% (4/31), respectively. None of the eight flat lesions (2-9mm) at cecum was detected by any of the three reading methods. Excluding the flat lesions at cecum, the sensitivity with SAEC for detecting flat lesion ≥4mm increased to 84% (31/37).

CONCLUSIONS

The fecal-tagging CTC with structure-analysis electronic cleansing could yield a high sensitivity for detecting flat lesions ≥4mm. The not-on-fold flat lesions were detected with higher sensitivity than on-fold flat lesions.

Flat (nonpolypoid) colorectal lesions identified at CT colonography in a U.S. screening population

RATIONALE AND OBJECTIVES

The aim of this study was to investigate the clinical importance and height definition of flat (nonpolypoid) colorectal lesions detected on screening computed tomographic colonography (CTC).

MATERIALS AND METHODS

Results from prospective screening CTC in 5107 consecutive asymptomatic adults (mean age, 56.9 years) at a single center were analyzed. All detected colorectal lesions > or = 6 mm were prospectively categorized as polypoid or flat (nonpolypoid). The maximal height of all flat lesions was measured to assess the suggested 3-mm threshold definition.

RESULTS

Of 954 polyps measuring > or = 6 mm identified on screening CTC, 125 lesions (13.1%) in 106 adults were prospectively categorized as flat, with a mean size of 12.7 mm (range, 6-80 mm), including 73 lesions 6 to 9 mm, 42 lesions 10 to 29 mm, and 10 lesions > or = 3 cm (carpet lesions). For polyps between 6 and 30 mm in size, flat lesions were less likely than polypoid lesions to be neoplastic (25.0% vs 60.3%, P < .001), histologically advanced (5.4% vs 12.1%, P = .07) or malignant (0% vs 0.5%, P = NS). Two of 10 carpet lesions (20%) were malignant, compared to 50% of polypoid masses > or = 3 cm. Of nine flat lesions seen only on colonoscopy (false-negatives on CTC), two were neoplastic (tubular adenomas), and none was histologically advanced. For all flat lesions between 6 and 30 mm, the maximal height averaged 2.2 mm and was < or =3 mm in 86.1%, including 93.2% of small 6-mm to 9-mm flat lesions.

CONCLUSION

In a US screening population, flat colorectal lesions detected on CTC demonstrated less aggressive histologic features compared to polypoid lesions. Excluding carpet lesions, a maximal height of 3 mm appears to be a reasonable definition.

Polyp size measurement at CT colonography: what do we know and what do we need to know?

Polyp size is a critical biomarker for clinical management. Larger polyps have a greater likelihood of being or of becoming an adenocarcinoma. To balance the referral rate for polypectomy against the risk of leaving potential cancers in situ, sizes of 6 and 10 mm are increasingly being discussed as critical thresholds for clinical decision making (immediate polypectomy versus polyp surveillance) and have been incorporated into the consensus CT Colonography Reporting and Data System (C-RADS). Polyp size measurement at optical colonoscopy, pathologic examination, and computed tomographic (CT) colonography has been studied extensively but the reported precision, accuracy, and relative sizes have been highly variable. Sizes measured at CT colonography tend to lie between those measured at optical colonoscopy and pathologic evaluation. The size measurements are subject to a variety of sources of error associated with image acquisition, display, and interpretation, such as partial volume averaging, two- versus three-dimensional displays, and observer variability. This review summarizes current best practices for polyp size measurement, describes the role of automated size measurement software, discusses how to manage the measurement uncertainties, and identifies areas requiring further research.

Improving the accuracy of CTC interpretation: computer-aided detection

Computer-aided polyp detection aims to improve the accuracy of the colonography interpretation. The computer searches the colonic wall to look for polyplike protrusions and presents a list of suspicious areas to a physician for further analysis. Computer-aided polyp detection has developed rapidly in the past decade in the laboratory setting and has sensitivities comparable with those of experts. Computer-aided polyp detection tends to help inexperienced readers more than experienced ones and may also lead to small reductions in specificity. In its currently proposed use as an adjunct to standard image interpretation, computer-aided polyp detection serves as a spellchecker rather than an efficiency enhancer.