Missed lesions at CT colonography: lessons learned

MM-GLCM-CNN: A multi-scale and multi-level based GLCM-CNN for polyp classification

Distinguishing malignant from benign lesions has significant clinical impacts on both early detection and optimal management of those early detections. Convolutional neural network (CNN) has shown great potential in medical imaging applications due to its powerful feature learning capability. However, it is very challenging to obtain pathological ground truth, addition to collected in vivo medical images, to construct objective training labels for feature learning, leading to the difficulty of performing lesion diagnosis. This is contrary to the requirement that CNN algorithms need a large number of datasets for the training. To explore the ability to learn features from small pathologically-proven datasets for differentiation of malignant from benign polyps, we propose a Multi-scale and Multi-level based Gray-level Co-occurrence Matrix CNN (MM-GLCM-CNN). Specifically, instead of inputting the lesions' medical images, the GLCM, which characterizes the lesion heterogeneity in terms of image texture characteristics, is fed into the MM-GLCN-CNN model for the training. This aims to improve feature extraction by introducing multi-scale and multi-level analysis into the construction of lesion texture characteristic descriptors (LTCDs). To learn and fuse multiple sets of LTCDs from small datasets for lesion diagnosis, we further propose an adaptive multi-input CNN learning framework. Furthermore, an Adaptive Weight Network is used to highlight important information and suppress redundant information after the fusion of the LTCDs. We evaluated the performance of MM-GLCM-CNN by the area under the receiver operating characteristic curve (AUC) merit on small private lesion datasets of colon polyps. The AUC score reaches 93.99% with a gain of 1.49% over current state-of-the-art lesion classification methods on the same dataset. This gain indicates the importance of incorporating lesion characteristic heterogeneity for the prediction of lesion malignancy using small pathologically-proven datasets.

Nanotechnology for colorectal cancer detection and treatment

Colorectal cancer (CRC) is the third most diagnosed cancer and the second leading cause of cancer-related mortality in the United States. Across the globe, people in the age group older than 50 are at a higher risk of CRC. Genetic and environmental risk factors play a significant role in the development of CRC. If detected early, CRC is preventable and treatable. Currently, available screening methods and therapies for CRC treatment reduce the incidence rate among the population, but the micrometastasis of cancer may lead to recurrence. Therefore, the challenge is to develop an alternative therapy to overcome this complication. Nanotechnology plays a vital role in cancer treatment and offers targeted chemotherapies directly and selectively to cancer cells, with enhanced therapeutic efficacy. Additionally, nanotechnology elevates the chances of patient survival in comparison to traditional chemotherapies. The potential of nanoparticles includes that they may be used simultaneously for diagnosis and treatment. These exciting properties of nanoparticles have enticed researchers worldwide to unveil their use in early CRC detection and as effective treatment. This review discusses contemporary methods of CRC screening and therapies for CRC treatment, while the primary focus is on the theranostic approach of nanotechnology in CRC treatment and its prospects. In addition, this review aims to provide knowledge on the advancement of nanotechnology in CRC and as a starting point for researchers to think about new therapeutic approaches using nanotechnology.

Nanotechnology in Colorectal Cancer for Precision Diagnosis and Therapy

Colorectal cancer (CRC) is the third most frequently occurring tumor in the human population. CRCs are usually adenocarcinomatous and originate as a polyp on the inner wall of the colon or rectum which may become malignant in the due course of time. Although the therapeutic options of CRC are limited, the early diagnosis of CRC may play an important role in preventive and therapeutic interventions to decrease the mortality rate. The CRC-affected tissues exhibit several molecular markers that may be exploited as the novel strategy to develop newer approaches for the treatment of the disease. Nanotechnology consists of a wide array of innovative and astonishing nanomaterials with both diagnostics and therapeutic potential. Several nanomaterials and nano formulations such as Carbon nanotubes, Dendrimer, Liposomes, Silica Nanoparticles, Gold nanoparticles, Metal-organic frameworks, Core-shell polymeric nano-formulations, Nano-emulsion System, etc can be used to targeted anticancer drug delivery and diagnostic purposes in CRC. The light-sensitive photosensitizer drugs loaded gold and silica nanoparticles can be used to diagnose as well as the killing of CRC cells by the targeted delivery of anticancer drugs to cancer cells. This review is focused on the recent advancement of nanotechnology in the diagnosis and treatment of CRC.

Colon Capsule Endoscopy vs. CT Colonography Following Incomplete Colonoscopy: A Systematic Review with Meta-Analysis

Following incomplete colonoscopy (IC) patients often undergo computed tomography colonography (CTC), but colon capsule endoscopy (CCE) may be an alternative. We compared the completion rate, sensitivity and diagnostic yield for polyp detection from CCE and CTC following IC. A systematic literature search resulted in twenty-six studies. Extracted data included inter alia, complete/incomplete investigations and polyp findings. Pooled estimates of completion rates of CCE and CTC and complete colonic view rates (CCE reaching the most proximal point of IC) of CCE were calculated. Per patient diagnostic yields of CCE and CTC were calculated stratified by polyp sizes. CCE completion rate and complete colonic view rate were 76% (CI 95% 68-84%) and 90% (CI 95% 83-95%). CTC completion rate was 98% (CI 95% 96-100%). Diagnostic yields of CTC and CCE were 10% (CI 95% 7-15%) and 37% (CI 95% 30-43%) for any size, 13% (CI 95% 9-18%) and 21% (CI 95% 12-32%) for >5-mm and 4% (CI 95% 2-7%) and 9% (CI 95% 3-17%) for >9-mm polyps. No study performed a reference standard follow-up after CCE/CTC in individuals without findings, rendering sensitivity calculations unfeasible. The increased diagnostic yield of CCE could outweigh its slightly lower complete colonic view rate compared to the superior CTC completion rate. Hence, CCE following IC appears feasible for an introduction to clinical practice. Therefore, randomized studies investigating CCE and/or CTC following incomplete colonoscopy with a golden standard reference for the entire population enabling estimates for sensitivity and specificity are needed.

Colon capsule endoscopy versus CT colonography after incomplete colonoscopy. Application of artificial intelligence algorithms to identify complete colonic investigations

BACKGROUND

Guidelines suggest computed tomography colonography (CTC) following incomplete optical colonoscopy (OC). Colon capsule endoscopies (CCE) have been suggested as an alternative, although completion rates have been unsatisfactory. Introduction of artificial intelligence (AI)-based localization algorithms of the camera capsules may enable identification of incomplete CCE investigations overlapping with incomplete OCs.

OBJECTIVE

The study aims to investigate relative sensitivity of CCE compared with CTC following incomplete OC, investigate the completion rate when combining results from the incomplete OC and CCE, and develop a forward-tracking algorithm ensuring a safe completeness of combined investigations.

METHODS

In this prospective paired study, patients with indication for CTC following incomplete OC were included for CCE and CTC. Location of CCE abortion and OC abortion were registered to identify complete combined investigations. AI-based algorithm for localization of capsules were developed reconstructing the passage of the colon.

RESULTS

In 237 individuals with CTC indication; 105 were included, of which 97 underwent both a CCE and CTC. CCE was complete in 66 (68%). Including CCEs which reached most oral point of incomplete OC, 73 (75%) had complete colonic investigations; 78 (80%) had conclusive investigations. Relative sensitivity of CCE compared with CTC was 2.67 (95% confidence interval (CI) 1.76;4.04) for polyps >5 mm and 1.91 (95% CI 1.18;3.09) for polyps >9 mm. An AI-based algorithm was developed.

CONCLUSION

Sensitivity of CCE following incomplete OC was superior to CTC. Introducing and improving algorithm-based localization of capsule abortion may increase identification of overall complete investigation rates following incomplete OC.ClinicalTrials.gov identifier: NCT02826993.

Multi-scale characterizations of colon polyps via computed tomographic colonography

Texture features have played an essential role in the field of medical imaging for computer-aided diagnosis. The gray-level co-occurrence matrix (GLCM)-based texture descriptor has emerged to become one of the most successful feature sets for these applications. This study aims to increase the potential of these features by introducing multi-scale analysis into the construction of GLCM texture descriptor. In this study, we first introduce a new parameter - stride, to explore the definition of GLCM. Then we propose three multi-scaling GLCM models according to its three parameters, (1) learning model by multiple displacements, (2) learning model by multiple strides (LMS), and (3) learning model by multiple angles. These models increase the texture information by introducing more texture patterns and mitigate direction sparsity and dense sampling problems presented in the traditional Haralick model. To further analyze the three parameters, we test the three models by performing classification on a dataset of 63 large polyp masses obtained from computed tomography colonoscopy consisting of 32 adenocarcinomas and 31 benign adenomas. Finally, the proposed methods are compared to several typical GLCM-texture descriptors and one deep learning model. LMS obtains the highest performance and enhances the prediction power to 0.9450 with standard deviation 0.0285 by area under the curve of receiver operating characteristics score which is a significant improvement.

Anorectal pitfalls in computed tomography colonography

There is a wide array of pathological lesions seen in the anorectal region with CT colonography (CTC), much of which is unique to this location. Many relatively common findings in the anorectal region are typically benign, but can be misinterpreted as malignant. There are also technique-related pitfalls that can impede accurate diagnosis of anorectal findings at CTC. Understanding common and uncommon lesions in the anorectal region as well as recognizing technical pitfalls will optimize interpretation of CTC and decrease the number of missed cancers and false positives. This review will systematically cover that they key pitfalls confronting the radiologist at CTC interpretation of the anorectal region, primarily dividing them into those related to underlying anatomy and those related to technique. Tips for how to effectively handle these potential pitfalls will also be discussed.

CT colonography interpretation: how to maximize polyp detection and minimize overcalling

This article outlines how to achieve maximum accuracy in interpreting CT colonography (CTC) regarding colonic findings. Interpreting extracolonic findings seen on CTC is a separate diagnostic task and will not be addressed in this article. While many interpretive pitfalls are in fact related to CTC techniques, this article focuses on issues that are related to interpretive knowledge and skills, avoiding in-depth discussions on CTC techniques. Principal methods and further tips for detecting possible polyp candidates and for confirming true soft-tissue polyps will be discussed. Specific points about optimizing interpretation strategies for difficult flat polyps including sessile serrated polyp will be raised. There are numerous interpretive pitfalls regarding the colonic interpretation of CTC. Knowledge of these pitfalls will shorten the learning curve and help achieve accurate reads.

Computed Tomography Colonography vs Colonoscopy for Colorectal Cancer Surveillance After Surgery

BACKGROUND & AIMS

Recommendations for surveillance after curative surgery for colorectal cancer (CRC) include a 1-year post-resection abdominal-pelvic computed tomography (CT) scan and optical colonoscopy (OC). CT colonography (CTC), when used in CRC screening, effectively identifies colorectal polyps ≥10 mm and cancers. We performed a prospective study to determine whether CTC, concurrent with CT, could substitute for OC in CRC surveillance.

METHODS

Our study enrolled 231 patients with resected stage 0-III CRC, identified at 5 tertiary care academic centers. Approximately 1 year after surgery, participants underwent outpatient CTC plus CT, followed by same-day OC. CTC results were revealed after endoscopic visualization of sequential colonic segments, which were re-examined for discordant findings. The primary outcome was performance of CTC in the detection of colorectal adenomas and cancers using endoscopy as the reference standard.

RESULTS

Of the 231 participants, 116 (50.2%) had polyps of any size or histology identified by OC, and 15.6% had conventional adenomas and/or serrated polyps ≥6 mm. No intra-luminal cancers were detected. CTC detected patients with polyps of ≥6 mm with 44.0% sensitivity (95% CI, 30.2-57.8) and 93.4% specificity (95% CI, 89.7-97.0). CTC detected polyps ≥10 mm with 76.9% sensitivity (95% CI, 54.0-99.8) and 89.0% specificity (95% CI, 84.8-93.1). Similar values were found when only adenomatous polyps were considered. The negative predictive value of CTC for adenomas ≥6 mm was 90.7% (95% CI, 86.7-94.5) and for adenomas ≥10 mm the negative predictive value was 98.6% (95% CI, 97.0-100).

CONCLUSIONS

In a CRC surveillance population 1 year following resection, CTC was inferior to OC for detecting patients with polyps ≥6 mm. Clinical Trials.gov Registration Number: NCT02143115.

TC Rectal Pathology: Findings at CT-Colonography

OBJECTIVE

To review the spectrum of benign and malignant rectal diseases, their findings on CT colonography, and their management.

CONCLUSION

Although CT colonography is not the first choice for the study of rectal disease, it is indicated in cases where optical colonoscopy is contraindicated or cannot be completed. Rectal lesions can go undetected because this anatomic area is difficult to evaluate; for this reason, it is essential to ensure optimal preparation and distension, moderate balloon insufflation, and careful 2D and 3D navigation with knowledge of the spectrum of rectal disease and its CT colonography signs.

Serrated polyps - a concealed but prevalent precursor of colorectal cancer

Serrated polyps have long been considered to lack malignant potential but accumulating data suggest that these lesions may cause up to one-third of all sporadic colorectal cancer. Serrated polyps are classified into three subtypes, including sessile serrated adenomas/polyps (SSA/Ps), traditional serrated adenomas (TSAs), and hyperplastic polyps (HPs). SSA/P and TSA harbour malignant potential but TSA represents only 1-2%, wheras SSA/P constitute up to 20% of all serrated lesions. HPs are most common (80%) of all serrated polyps but are considered to have a low potential of developing colorectal cancer. Due to their subtle appearence, detection and removal of serrated polyps pose a major challenge to endoscopists. Considering that precancerous serrated polyps are predominately located in the right colon could explain why interval cancers most frequently appear in the proximal colon and why colonoscopy is less protective against colon cancer in the proximal compared to the distal colon. Despite the significant impact on colorectal cancer incidence, the aetiology, incidence, prevalence, and natural history of serrated polyps is incompletely known. To effectively detect, remove, and follow-up serrated polyps, endoscopists and pathologists should be well-informed about serrated polyps. This review highlights colorectal serrated polyps in terms of biology, types, diagnosis, therapy, and follow-up.

Colonoscopy Surveillance After Colorectal Cancer Resection: Recommendations of the US Multi-Society Task Force on Colorectal Cancer

The US Multi-Society Task Force has developed updated recommendations to guide health care providers with the surveillance of patients after colorectal cancer (CRC) resection with curative intent. This document is based on a critical review of the literature regarding the role of colonoscopy, flexible sigmoidoscopy, endoscopic ultrasound, fecal testing and CT colonography in this setting. The document addresses the effect of surveillance, with focus on colonoscopy, on patient survival after CRC resection, the appropriate use and timing of colonoscopy for perioperative clearing and for postoperative prevention of metachronous CRC, specific considerations for the detection of local recurrence in the case of rectal cancer, as well as the place of CT colonography and fecal tests in post-CRC surveillance.

Colonoscopy Surveillance after Colorectal Cancer Resection: Recommendations of the US Multi-Society Task Force on Colorectal Cancer

The US Multi-Society Task Force has developed updated recommendations to guide health care providers with the surveillance of patients after colorectal cancer (CRC) resection with curative intent. This document is based on a critical review of the literature regarding the role of colonoscopy, flexible sigmoidoscopy, endoscopic ultrasound, fecal testing and CT colonography in this setting. The document addresses the effect of surveillance, with focus on colonoscopy, on patient survival after CRC resection, the appropriate use and timing of colonoscopy for perioperative clearing and for postoperative prevention of metachronous CRC, specific considerations for the detection of local recurrence in the case of rectal cancer, as well as the place of CT colonography and fecal tests in post-CRC surveillance.

Prognostic Value of the Diverticular Disease Severity Score Based on CT Colonography: Follow-up in Patients Recovering from Acute Diverticulitis

RATIONALE AND OBJECTIVES

To assess the prognostic value of a diverticular disease severity score (DDSS) based on computed tomography colonography (CTC) after acute diverticulitis (AD).

MATERIALS AND METHODS

Of 252 patients who had an AD episode, we finally selected 46 patients who underwent both conventional CT at the acute event and CTC after 9 ± 7 weeks. Of these 46 patients, 17 underwent elective surgery after CTC. Disease severity was assessed with a 0-4 modified Hinchey CT-based score and a 1-4 CTC-based DDSS. A phone survey was performed 27 months later (range 4-52) for the 29 patients not surgically treated.

RESULTS

Significant correlation was found between CTC-based DDSS and clinical follow-up (P = 0.022) or elective surgery (P = 0.007), but not between clinical follow-up and CT-based score, extraluminal gas, C-reactive protein serum level, age, gender, or first versus recurrent AD episode. CTC demonstrated relevant additional findings in five of 46 (11%) patients: two AD complications (enterocolic and enterotubal fistulae), two colon cancers, and one extracolonic (lung) cancer.

CONCLUSIONS

The CTC-based DDSS showed a prognostic value and correlated with the risk of undergoing surgery, and clinically relevant additional findings were found in more than 10% of patients. CTC could be the preferred test in patients recovering after AD.

Errors in multidetector row computed tomography

Multidetector row computed tomography (MDCT) represents the technique of choice for the majority of pathologies today and is responsible for the majority of diagnoses. However, despite the low number of studies dedicated to errors in MDCT, CT reporting seems especially prone to generating errors and errors are an inevitable part of MDCT practice. Most of these arise during image interpretation but, differently from other radiological techniques, the awareness of radiologists regarding technical CT aspects and pathologies substantially contribute in generating errors, in particular because CT technology expands rapidly and radiologists do not routinely receive specific and appropriate training for its use and because CT examinations are not the same for each patient and each pathology and the choice of the most appropriate CT examination (including the dose exposure to the patient) presumes a very large awareness from radiologists. This review is aimed at increasing awareness regarding the type of errors in MDCT and in particular to also highlight technical and procedural errors.

Recent developments in colorectal imaging

PURPOSE OF REVIEW

The aim of this review is to provide an update on important recent advances in radiologic colorectal imaging, with emphasis on detection, staging, and surveillance of colorectal neoplasia.

RECENT FINDINGS

Colorectal imaging advances with magnetic resonance (MR), computed tomography colonography (CTC), and positron emission tomography (PET) over the past year or so have been substantial. Progress in MRI for rectal cancer was most notable in terms of assessment of response to neoadjuvant therapy. Continued maturation and clinical validation of CTC was observed for the evaluation of advanced neoplasia, among other areas. Multimodality approaches to colorectal imaging that incorporate functional PET data have also made impressive strides forward.

SUMMARY

Recent advances in cross-sectional and functional radiologic imaging of the colorectum will positively impact the clinical capabilities for noninvasive evaluation of colorectal neoplasia.

Sessile serrated adenomas: an evidence-based guide to management

The concept of serrated colorectal neoplasia and a serrated pathway to colorectal cancer (CRC) is relatively new and continuing to evolve, but it has become highly relevant to gastroenterologists, pathologist, and oncologists alike. Sessile serrated adenomas (SSA) are now thought to be the major precursor lesion of serrated pathway cancers, which represent up to one-third of all sporadic CRC cases. However, despite their increasingly recognized importance, relatively little is known about the epidemiology and natural history of SSAs, and the molecular and epigenetic aspects are incompletely understood. Endoscopists must be aware of the unique features of SSAs so that the practice of colonoscopic screening for CRC can include optimized detection, removal, and appropriate surveillance of SSAs and other serrated precursor lesions. In this review, we discuss the history, epidemiology, and pathologic aspects of SSAs, as well as a recommended management approach and a discussion of uncertainties and opportunities for future research.

Carpet lesions detected at CT colonography: clinical, imaging, and pathologic features

PURPOSE

To describe carpet lesions (laterally spreading tumors ≥ 3 cm) detected at computed tomographic (CT) colonography, including their clinical, imaging, and pathologic features.

MATERIALS AND METHODS

The imaging reports for 9152 consecutive adults undergoing initial CT colonography at a tertiary center were reviewed in this HIPAA-compliant, institutional review board-approved retrospective study to identify all potential carpet lesions detected at CT colonography. Carpet lesions were defined as morphologically flat, laterally spreading tumors 3 cm or larger. For those patients with neoplastic carpet lesions, CT colonography studies were analyzed to determine maximal lesion width and height, oral contrast material coating, segmental location, and computer-aided detection (CAD) findings. Demographic data and details of clinical treatment in these patients were reviewed.

RESULTS

Eighteen carpet lesions in 18 patients (0.2%; mean age, 67.1 years; eight men, 10 women) were identified and were subsequently confirmed at colonoscopy and pathologic examination among 20 potential flat masses (≥3 cm) prospectively identified at CT colonography (there were two nonneoplastic rectal false-positive findings). No additional neoplastic carpet lesions were found in the cohort undergoing colonoscopy after CT colonography and/or surgery (there were no false-negatives). Mean lesion width was 46.5 mm (range, 30-80 mm); mean lesion height was 7.9 mm (range, 4-14 mm). Surface retention of oral contrast material was noted in all 18 cases. All but two lesions were located in the distal rectosigmoid or proximal right colon. At CAD, 17 (94.4%) lesions were detected (mean, 6.2 CAD marks per lesion). Sixteen lesions (88.9%) demonstrated advanced histologic features, including a villous component (n = 11), high-grade dysplasia (n = 4), and invasive cancer (n = 5). Sixteen patients (88.9%) required surgical treatment for complete excision.

CONCLUSION

CT colonography can effectively depict carpet lesions. Common features in this series included older patient age, rectal or cecal location, surface coating with oral contrast material, multiple CAD hits, advanced yet typically benign histologic features, and surgical treatment.

Diverticular disease severity score based on CT colonography

OBJECTIVE

We propose a diverticular disease severity score (DDSS) based on CT colonography (CTC) findings.

METHODS

Seventy-nine patients (62 ± 14.5 years) underwent CTC after recovering from an episode of acute diverticulitis. Two independent readers classified each case using a four-point scale (DDSS), based on maximum sigmoid colon wall thickness (MSCWT) and minimum lumen diameter at CTC: 1 = MSCWT <3 mm, lumen diameter ≥15 mm; 2 = MSCWT 3-8 mm, lumen diameter ≥5 mm; 3 = MSCWT ≥8 mm, lumen diameter ≥5 mm; 4 = MSCWT ≥8 mm, lumen diameter <5 mm. Intra- and interobserver reproducibility was evaluated. Of 79 patients, 32 (40 %) underwent surgery after CTC; MSCWT was directly measured on the pathological specimen.

RESULTS

Intra- and interobserver reproducibility of DDSS were almost perfect (k = 0.90-0.84). DDSS significantly correlated with the probability of surgery (P = 0.001). After surgery, histopathology revealed acute/chronic diverticular inflammation only in 29 cases, and superimposed sigmoid cancer (n = 2) or Crohn's disease (n = 1) in 3 patients with a DDSS of 4. MSCWT at histopathology correlated with DDSS (P = 0.008).

CONCLUSION

DDSS is highly reproducible and correlates with pathological MSCWT. Nearly 1 in 3 patients with a DDSS of 4 had significant superimposed histopathology. CTC with DDSS can provide colorectal surgeons with valuable information.

KEY POINTS

• A diverticular disease severity score (DDSS) based on CT colonography is proposed. • This DDSS is based on sigmoid colon wall thickness and lumen diameter. • High scores may be associated with relevant coexisting lesions. • A CTC-based DDSS may influence therapeutic decision-making.

Computed tomography colonography for colorectal cancer screening

Colorectal cancer screening has been shown to help prevent cancer-related death. Concerns about suboptimal adherence to conventional colonoscopy has led to the search for alternative screening modalities. Computed tomography colono-graphy (CTC) is a highly sensitive and minimally invasive alternative modality. The American College of Radiology has established a standardized reporting system for CTC. The advantages of CTC include complete colonic examination and extraluminal imaging in a single breath hold time. Lack of sensitivity in the evaluation of flat lesions and radiation exposure are the main concerns with this modality. Although the usefulness of CTC has been demonstrated in academic centers, larger studies in community settings are needed to facilitate its adoption by healthcare services.