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.

Colon capsule endoscopy for colonic surveillance

AIM

Resources used in surveillance colonoscopies are taking up an increasing proportion of colonoscopy capacity. Colon capsule endoscopy (CCE) is a promising technique for noninvasive investigation of the colon. We aimed to investigate CCE as a possible filter in colonic surveillance with the primary outcome of reducing the number of colonoscopies.

METHOD

Patients scheduled for follow-up colonoscopy were subjected to a primary CCE and only supplemental conventional endoscopy if significant pathology was detected or if the CCE examination was incomplete. Significant pathology was defined as more than two small polyps, or one polyp greater than 9 mm or any polyp in patients with hereditary nonpolyposis colorectal cancer. Supplemental endoscopy was carried out to the extent needed to resect the detected polyps and investigate the parts of the colon that were not sufficiently visualized by the capsule.

RESULTS

A total of 180 patients were included. Seventy-seven patients (43%) had a complete CCE with no significant findings. A complete colonoscopy was carried out in 67 patients (37%) and 36 patients (20%) underwent a sigmoidoscopy. In the 103 patients undergoing endoscopy, 59 (57%) had no adenomas detected, 33 (32%) had 'low-risk' adenomas and 11 (11%) had 'high-risk' adenomas.

CONCLUSION

The introduction of CCE as filter test in colonic surveillance reduced colonoscopies by 43%, but this implies that untreated polyps are left behind and is not cost-effective. The CCE completion rate must be improved.

Back-to-back colon capsule endoscopy and optical colonoscopy in colorectal cancer screening individuals

AIM

The aim was to determine the polyp detection rate and per-patient sensitivity for polyps > 9 mm of colon capsule endoscopy (CCE) compared with colonoscopy as well as the diagnostic accuracy of CCE.

METHOD

Individuals who had a positive immunochemical faecal occult blood test during screening had investigator blinded CCE and colonoscopy. Participants underwent repeat endoscopy if significant lesions detected by CCE were considered to have been missed by colonoscopy.

RESULTS

There were 253 participants. The polyp detection rate was significantly higher in CCE compared with colonoscopy (P = 0.02). The per-patient sensitivity for > 9 mm polyps for CCE and colonoscopy was 87% (95% CI: 83-91%) and 88% (95% CI: 84-92%) respectively. In participants with complete CCE and colonoscopy examinations (N = 126), per-patient sensitivity of > 9 mm polyps in CCE (97%; 95% CI: 94-100%) was superior to colonoscopy (89%; 95% CI: 84-94%). A complete capsule endoscopy examination (N = 134) could detect patients with intermediate or greater risk (according to the European guidelines) with an accuracy, sensitivity, specificity and positivity rate of 79%, 93%, 69% and 58% respectively, using a cut-off of at least one polyp > 10 mm or more than two polyps.

CONCLUSION

CCE is superior to colonoscopy in polyp detection rate and per-patient sensitivity to > 9 mm polyps, but only in complete CCE examinations. The rate of incomplete CCE examinations must be improved.

Review of colorectal cancer and its metastases in rodent models: comparative aspects with those in humans

BACKGROUND AND PURPOSE

Colorectal cancer (CRC) remains one of the most common cancer forms developing in industrialized countries, and its incidence appears to be rising. Studies of human population groups provide insufficient information about carcinogenesis, pathogenesis, and treatment of CRC. To study these phenomena in detail, a number of animal models of human CRC have been developed. The hypothetical ideal animal model should mimic the human disease in terms of morphology, biochemical alterations, and biological behavior. No existing model replicates the disease as an entity, but available models approximate many of the characteristics of human colonic carcinogenesis and metastasis. So far few comparative evaluations of the various animal models of CRC have been made.

CONCLUSION

Animal studies cannot replace human clinical trials, but they can be used as a pre-screening tool, so that human trials become more directed, with greater chances of success. The orthotopic transplantation of colon cancer cells into the cecum of syngeneic animals or intraportal inoculation appears to resemble the human metastatic disease most closely, providing a model for study of the treatment of metastases. Which model(s) to choose depends on the goal(s) of the experiment(s). The review published here can provide help in selecting the most optimal CRC model(s) for a certain purpose and in preventing unnecessary duplication of animal experimentation.