Recent advances to improve the endoscopic detection and differentiation of early colorectal neoplasia

Intraprocedure Artificial Intelligence Alert System for Colonoscopy Examination

Colonoscopy is a valuable tool for preventing and reducing the incidence and mortality of colorectal cancer. Although several computer-aided colorectal polyp detection and diagnosis systems have been proposed for clinical application, many remain susceptible to interference problems, including low image clarity, unevenness, and low accuracy for the analysis of dynamic images; these drawbacks affect the robustness and practicality of these systems. This study proposed an intraprocedure alert system for colonoscopy examination developed on the basis of deep learning. The proposed system features blurred image detection, foreign body detection, and polyp detection modules facilitated by convolutional neural networks. The training and validation datasets included high-quality images and low-quality images, including blurred images and those containing folds, fecal matter, and opaque water. For the detection of blurred images and images containing folds, fecal matter, and opaque water, the accuracy rate was 96.2%. Furthermore, the study results indicated a per-polyp detection accuracy of 100% when the system was applied to video images. The recall rates for high-quality image frames and polyp image frames were 95.7% and 92%, respectively. The overall alert accuracy rate and the false-positive rate of low quality for video images obtained through per-frame analysis were 95.3% and 0.18%, respectively. The proposed system can be used to alert colonoscopists to the need to slow their procedural speed or to perform flush or lumen inflation in cases where the colonoscope is being moved too rapidly, where fecal residue is present in the intestinal tract, or where the colon has been inadequately distended.

Multicentre randomised controlled trial comparing standard and high resolution optical technologies in colorectal cancer screening

BACKGROUND AND OBJECTIVES

The UK bowel cancer screening programme (BCSP) has been established for the early detection of colorectal cancer offering colonoscopy to patients screened positive by faecal occult blood tests. In this multisite, prospective, randomised controlled trial, we aimed to compare the performance of Standard Definition Olympus Lucera (SD-OL) with Scope Guide and the High Definition Pentax HiLine (HD-PHL).

PATIENTS AND METHODS

Subjects undergoing a colonoscopy as part of the UK National BCSP at four UK sites were randomised to an endoscopy list run using either SD-OL or HD-PHL. Primary endpoints were polyp and adenoma detection rate (PDR and ADR, respectively) as well as polyp size, morphology and histology characteristics.

RESULTS

262 subjects (168 males, mean age 66.3±4.3 years) were colonoscoped (133 patients with HD-PHL while 129 with SD-OL). PDR and ADR were comparable within the two optical systems. The HD-PHL group resulted in a PDR 55.6% and ADR 43.6%; the SD-OL group had PDR 56.6% and ADR 45.7%. HD-PHL was significantly superior to SD-OL in detection of flat adenomas (18.6% vs 5.2%, p<0.001), but not detection of pedunculated or sessile polyps. Patient comfort, use of sedation and endoscopist perception of procedural difficulty resulted similar despite the use of Scope Guide with SD-OL.

CONCLUSION

PDR and ADR were not significantly different between devices. The high-resolution colonoscopy system HD-PHL may improve polyp detection as compared with standard resolution technology in detecting flat adenomas. This advantage may have clinically significant implications for missed lesion rates and post-colonoscopy interval colorectal cancer rates.

Evolving Therapeutic Strategies to Exploit Chromosome Instability in Cancer

Cancer is a devastating disease that claims over 8 million lives each year. Understanding the molecular etiology of the disease is critical to identify and develop new therapeutic strategies and targets. Chromosome instability (CIN) is an abnormal phenotype, characterized by progressive numerical and/or structural chromosomal changes, which is observed in virtually all cancer types. CIN generates intratumoral heterogeneity, drives cancer development, and promotes metastatic progression, and thus, it is associated with highly aggressive, drug-resistant tumors and poor patient prognosis. As CIN is observed in both primary and metastatic lesions, innovative strategies that exploit CIN may offer therapeutic benefits and better outcomes for cancer patients. Unfortunately, exploiting CIN remains a significant challenge, as the aberrant mechanisms driving CIN and their causative roles in cancer have yet to be fully elucidated. The development and utilization of CIN-exploiting therapies is further complicated by the associated risks for off-target effects and secondary cancers. Accordingly, this review will assess the strengths and limitations of current CIN-exploiting therapies, and discuss emerging strategies designed to overcome these challenges to improve outcomes and survival for patients diagnosed with cancer.

Assessment of colon polyp morphology: Is education effective?

AIM

To determine the inter-observer variability for colon polyp morphology and to identify whether education can improve agreement among observers.

METHODS

For purposes of the tests, we recorded colonoscopy video clips that included scenes visualizing the polyps. A total of 15 endoscopists and 15 nurses participated in the study. Participants watched 60 video clips of the polyp morphology scenes and then estimated polyp morphology (pre-test). After education for 20 min, participants performed a second test in which the order of 60 video clips was changed (post-test). To determine if the effectiveness of education was sustained, four months later, a third, follow-up test was performed with the same participants.

RESULTS

The overall Fleiss' kappa value of the inter-observer agreement was 0.510 in the pre-test, 0.618 in the post-test, and 0.580 in the follow-up test. The overall diagnostic accuracy of the estimation for polyp morphology in the pre-, post-, and follow-up tests was 0.662, 0.797, and 0.761, respectively. After education, the inter-observer agreement and diagnostic accuracy of all participants improved. However, after four months, the inter-observer agreement and diagnostic accuracy of expert groups were markedly decreased, and those of beginner and nurse groups remained similar to pre-test levels.

CONCLUSION

The education program used in this study can improve inter-observer agreement and diagnostic accuracy in assessing the morphology of colon polyps; it is especially effective when first learning endoscopy.

Efficacy Evaluation of SAVE for the Diagnosis of Superficial Neoplastic Lesion

The detection of non-polypoid superficial neoplastic lesions using current standard of white light endoscopy surveillance and random biopsy is associated with high miss rate. The subtle changes in mucosa caused by the flat and depressed neoplasms often go undetected and do not qualify for further investigation, e.g., biopsy and resection, thus increasing the risk of cancer advancement. This paper presents a screening tool named the saliency-aided visual enhancement (SAVE) method, with an objective of highlighting abnormalities in endoscopic images to detect early lesions. SAVE is a hybrid system combining image enhancement and saliency detection. The method provides both qualitative enhancement and quantitative suspicion index for endoscopic image regions. A study to evaluate the efficacy of SAVE to localize superficial neoplastic lesion was performed. Experimental results for average overlap index >0.7 indicated that SAVE was successful to localize the lesion areas. The area under the receiver-operating characteristic curve obtained for SAVE was 94.91%. A very high sensitivity (100%) was achieved with a moderate specificity (65.45%). Visual inspection showed a comparable performance of SAVE with chromoendoscopy to highlight mucosal irregularities. This paper suggests that SAVE could be a potential screening tool that can substitute the application of burdensome chromoendoscopy technique. SAVE method, as a simple, easy-to-use, highly sensitive, and consistent red flag technology, will be useful for early detection of neoplasm in clinical applications.