Endoscopic approach to polyp recognition

Diagnostic accuracy of endocytoscopy via artificial intelligence in colorectal lesions: A systematic review and meta‑analysis

BACKGROUND

Endocytoscopy (EC) is a nuclei and micro-vessels visualization in real-time and can facilitate "optical biopsy" and "virtual histology" of colorectal lesions. This study aimed to investigate the significance of employing artificial intelligence (AI) in the field of endoscopy, specifically in diagnosing colorectal lesions. The research was conducted under the supervision of experienced professionals and trainees.

METHODS

EMBASE, PubMed, Cochrane Library, Web of Science, Chinese National Knowledge Infrastructure (CNKI) database, and other potential databases were surveyed for articles related to the EC with AI published before September 2023. RevMan (5.40), Stata (14.0), and R software (4.1.0) were used for statistical assessment. Studies that measured the accuracy of EC using AI for colorectal lesions were included. Two authors independently assessed the selected studies and their extracted data. This included information such as the country, literature, total study population, study design, characteristics of the fundamental study and control groups, sensitivity, number of samples, assay methodology, specificity, true positives or negatives, and false positives or negatives. The diagnostic accuracy of EC by AI was determined by a bivariate random-effects model, avoiding a high heterogeneity effect. The ANOVA model was employed to determine the more effective approach.

RESULTS

A total of 223 studies were reviewed; 8 articles were selected that included 2984 patients (4241 lesions) for systematic review and meta-analysis. AI assessed 4069 lesions; experts diagnosed 3165 and 5014 by trainees. AI demonstrated high accuracy, sensitivity, and specificity levels in detecting colorectal lesions, with values of 0.93 (95% CI: 0.90, 0.95) and 0.94 (95% CI: 0.73, 0.99). Expert diagnosis was 0.90 (95% CI: 0.85, 0.94), 0.87 (95% CI: 0.78, 0.93), and trainee diagnosis was 0.74 (95% CI: 0.67, 0.79), 0.72 (95% CI: 0.62, 0.80). With the EC by AI, the AUC from SROC was 0.95 (95% CI: 0.93, 0.97), therefore classified as excellent category, expert showed 0.95 (95% CI: 0.93, 0.97), and the trainee had 0.79 (95% CI: 0.75, 0.82). The superior index from the ANOVA model was 4.00 (1.15,5.00), 2.00 (1.15,5.00), and 0.20 (0.20,0.20), respectively. The examiners conducted meta-regression and subgroup analyses to evaluate the presence of heterogeneity. The findings of these investigations suggest that the utilization of NBI technology was correlated with variability in sensitivity and specificity. There was a lack of solid evidence indicating the presence of publishing bias.

CONCLUSIONS

The present findings indicate that using AI in EC can potentially enhance the efficiency of diagnosing colorectal abnormalities. As a valuable instrument, it can enhance prognostic outcomes in ordinary EC procedures, exhibiting superior diagnostic accuracy compared to trainee-level endoscopists and demonstrating comparability to expert endoscopists. The research is subject to certain constraints, namely a limited number of clinical investigations and variations in the methodologies used for identification. Consequently, it is imperative to conduct comprehensive and extensive research to enhance the precision of diagnostic procedures.

Wide-field endoscope accessory for multiplexed fluorescence imaging

A wide-field endoscope that is sensitive to fluorescence can be used as an adjunct to conventional white light endoscopy by detecting multiple molecular targets concurrently. We aim to demonstrate a flexible fiber-coupled accessory that can pass forward through the instrument channel of standard medical endoscopes for clinical use to collect fluorescence images. A miniature scan mirror with reflector dimensions of 1.30 × 0.45  mm2 was designed, fabricated, and placed distal to collimated excitation beams at λex = 488, 660, and 785 nm. The mirror was driven at resonance for wide angular deflections in the X and Y-axes. A large image field-of-view (FOV) was generated in real time. The optomechanical components were packaged in a rigid distal tip with dimensions of 2.6 mm diameter and 12 mm length. The scan mirror was driven at 27.6 and 9.04 kHz in the fast (X) and slow (Y) axes, respectively, using a square wave with 50% duty cycle at 60 Vpp to collect fluorescence images at 10 frames per sec. Maximum total divergence angles of ± 27.4° and ± 22.8° were generated to achieve a FOV of 10.4 and 8.4 mm, respectively, at a working distance of 10 mm. Multiplexed fluorescence images were collected in vivo from the rectum of live mice using 3 fluorescently-labeled peptides that bind to unique cell surface targets. The fluorescence images collected were separated into 3 channels. Target-to-background ratios of 2.6, 3.1, and 3.9 were measured. This instrument demonstrates potential for broad clinical use to detect heterogeneous diseases in hollow organs.

Artificial Intelligence-Assisted Optical Diagnosis: A Comprehensive Review of Its Role in Leave-In-Situ and Resect-and-Discard Strategies in Colonoscopy

Colorectal cancer screening plays a vital role in early detection and removal of precancerous adenomas, contributing to decreased mortality rates. Most polyps found during colonoscopies are small and unlikely to harbor advanced neoplasia or invasive cancer, leading to the development of "leave-in-situ" and "resect-and-discard" approaches. These strategies could lead to significant cost savings and efficiencies, but their implementation has been hampered by concerns around financial incentives, medical-legal risks, and local rules for tissue handling. This article reviews the potential of artificial intelligence to enhance the accuracy of polyp diagnosis through computer-aided diagnosis (CADx). While the adoption of CADx in optical biopsy has shown mixed results, it has the potential to significantly improve the management of colorectal polyps. Several studies reviewed in this article highlight the varied results of CADx in optical biopsy for colorectal polyps. Although artificial intelligence does not consistently outperform expert endoscopists, it has the potential to serve as a beneficial secondary reader, aiding in accurate optical diagnosis and increasing the confidence of the endoscopist. These studies indicate that although CADx holds great potential, it is yet to fully meet the performance thresholds necessary for clinical implementation.

Evaluation of Performance in Colon Capsule Endoscopy Reading by Endoscopy Nurses

BACKGROUND

Although there are papers reporting on the accuracy of colon capsule endoscopy (CCE) compared with colonoscopy (CS), there are few reports on the detection rates of significant lesions by endoscopy nurses. We previously reported no significant difference in the detection rates for small bowel capsule endoscopy (SBCE) images among two well-trained physicians and one expert nurse.

OBJECTIVE

To evaluate the reading time and detection rate of the significant lesions of CCE images among novice and trained expert endoscopy nurses and novice physicians.

METHODS

CCE videos of 20 consecutive patients who performed both CCE and CS with clinically significant localized lesions were selected. Two trained expert endoscopy nurses, untrained two novice physicians, and novice three endoscopy nurses reviewed CCE videos. The detection rate of the lesions and reading time were compared among the three groups and were evaluated by comparison between the first and the second 10 videos.

RESULTS

The median reading time was the shortest (19 min) in the trained expert endoscopy nurses and the longest (45 min) in the novice nurses. The number of thumbnails tended to be more in the trained expert endoscopy nurses in the first 10-video reading. Although the detection rates of small polyps (<5 mm) were significantly lower (46.5%, p=0.025) in the novice nurses compared to the others, they were improved (35.2% to 63.5%, p=0.015) in the second 10 videos. The detection rates of tumor lesions by either one of two trained expert endoscopy nurses were higher compared to those by each novice physician.

CONCLUSIONS

The trained expert endoscopy nurses for CCE reading can reduce physician's time and improve the diagnostic yield.

Ultra-Compact Microsystems-Based Confocal Endomicroscope

Point-of-care medical diagnosis demands immediate feedback on tissue pathology. Confocal endomicroscopy can provide real-time in vivo images with histology-like features. The working channel in medical endoscopes are becoming smaller in dimension. Microsystems methods can produce tiny mechanical scanners. We demonstrate a flexible fiber instrument for in vivo imaging as an endoscope accessory. The optical path is folded on-axis to reduce length while allowing the beam to expand and achieve a numerical aperture of 0.41. A high-speed parametric resonance mirror produces large deflection angles > 13°, and is mounted on a 2 mm diameter chip designed with clamp structures for reduced space. A compact lens assembly provides diffraction-limited lateral and axial resolution of 1.5 and [Formula: see text], respectively. A working distance of [Formula: see text] and field-of-view of [Formula: see text] m are achieved. Miniature apparatus is fabricated to assemble and align the scanhead components. The optics and scanner are packaged in a distal tip with 2.4 mm diameter and 10 mm rigid length. These dimensions allow the endomicroscope to pass forward easily through the 2.8 mm diameter working channel in medical endoscopes commonly used in clinical practice. Fluorescence images are collected in vivo at 10 frames per second in the colon of genetically-engineered mice that spontaneously develop adenomas. A FITC-labeled peptide heterodimer is administered intravenously to provide specific contrast. Sub-cellular structures are visualized to distinguish pre-malignant from normal mucosa. These results demonstrate use of microsystems methods to produce an ultra-compact instrument with sufficiently small dimensions for broad use.

Real-Time Use of Artificial Intelligence in Identification of Diminutive Polyps During Colonoscopy: A Prospective Study

BACKGROUND

Computer-aided diagnosis (CAD) for colonoscopy may help endoscopists distinguish neoplastic polyps (adenomas) requiring resection from nonneoplastic polyps not requiring resection, potentially reducing cost.

OBJECTIVE

To evaluate the performance of real-time CAD with endocytoscopes (×520 ultramagnifying colonoscopes providing microvascular and cellular visualization of colorectal polyps after application of the narrow-band imaging [NBI] and methylene blue staining modes, respectively).

DESIGN

Single-group, open-label, prospective study. (UMIN [University hospital Medical Information Network] Clinical Trial Registry: UMIN000027360).

SETTING

University hospital.

PARTICIPANTS

791 consecutive patients undergoing colonoscopy and 23 endoscopists.

INTERVENTION

Real-time use of CAD during colonoscopy.

MEASUREMENTS

CAD-predicted pathology (neoplastic or nonneoplastic) of detected diminutive polyps (≤5 mm) on the basis of real-time outputs compared with pathologic diagnosis of the resected specimen (gold standard). The primary end point was whether CAD with the stained mode produced a negative predictive value (NPV) of 90% or greater for identifying diminutive rectosigmoid adenomas, the threshold required to "diagnose-and-leave" nonneoplastic polyps. Best- and worst-case scenarios assumed that polyps lacking either CAD diagnosis or pathology were true- or false-positive or true- or false-negative, respectively.

RESULTS

Overall, 466 diminutive (including 250 rectosigmoid) polyps from 325 patients were assessed by CAD, with a pathologic prediction rate of 98.1% (457 of 466). The NPVs of CAD for diminutive rectosigmoid adenomas were 96.4% (95% CI, 91.8% to 98.8%) (best-case scenario) and 93.7% (CI, 88.3% to 97.1%) (worst-case scenario) with stained mode and 96.5% (CI, 92.1% to 98.9%) (best-case scenario) and 95.2% (CI, 90.3% to 98.0%) (worst-case scenario) with NBI.

LIMITATION

Two thirds of the colonoscopies were conducted by experts who had each experienced more than 200 endocytoscopies; 186 polyps not assessed by CAD were excluded.

CONCLUSION

Real-time CAD can achieve the performance level required for a diagnose-and-leave strategy for diminutive, nonneoplastic rectosigmoid polyps.

PRIMARY FUNDING SOURCE

Japan Society for the Promotion of Science.