Observer agreement for diagnosis of colorectal lesions with analysis of the vascular pattern by image-enhanced endoscopy

Performance of artificial intelligence in the characterization of colorectal lesions

Background

Image-enhanced endoscopy (IEE) has been used in the differentiation between neoplastic and non-neoplastic colorectal lesions through microvasculature analysis. This study aimed to evaluate the computer-aided diagnosis (CADx) mode of the CAD EYE system for the optical diagnosis of colorectal lesions and compare it with the performance of an expert, in addition to evaluating the computer-aided detection (CADe) mode in terms of polyp detection rate (PDR) and adenoma detection rate (ADR).

Methods

A prospective study was conducted to evaluate the performance of CAD EYE using blue light imaging (BLI), dichotomizing lesions into hyperplastic and neoplastic, and of an expert based on the Japan Narrow-Band Imaging Expert Team (JNET) classification for the characterization of lesions. After white light imaging (WLI) diagnosis, magnification was used on all lesions, which were removed and examined histologically. Diagnostic criteria were evaluated, and PDR and ADR were calculated.

Results

A total of 110 lesions (80 (72.7%) dysplastic lesions and 30 (27.3%) nondysplastic lesions) were evaluated in 52 patients, with a mean lesion size of 4.3 mm. Artificial intelligence (AI) analysis showed 81.8% accuracy, 76.3% sensitivity, 96.7% specificity, 98.5% positive predictive value (PPV), and 60.4% negative predictive value (NPV). The kappa value was 0.61, and the area under the receiver operating characteristic curve (AUC) was 0.87. Expert analysis showed 93.6% accuracy, 92.5% sensitivity, 96.7% specificity, 98.7% PPV, and 82.9% NPV. The kappa value was 0.85, and the AUC was 0.95. Overall, PDR was 67.6% and ADR was 45.9%.

Conclusions

The CADx mode showed good accuracy in characterizing colorectal lesions, but the expert assessment was superior in almost all diagnostic criteria. PDR and ADR were high.

Effect of Linked-color Imaging on the Detection of Adenomas in Screening Colonoscopies

OBJECTIVES

Linked-color imaging (LCI) is a new image-enhancement option that emphasizes mucosal surface contrast, facilitating the differentiation between colorectal lesions and normal mucosa. This study aimed to evaluate the potential of LCI to increase the detection of colorectal adenomas in screening colonoscopies.

METHODS

A prospective randomized study was conducted using white-light imaging (WLI), blue-laser imaging (BLI)-bright and LCI. The outcome measures were adenoma detection rate (ADR), mean number of adenomas per patient, and withdrawal time. Lesion characteristics such as size, morphology, location, and histology were also evaluated.

RESULTS

A total of 205 patients were randomized, and 251 adenomas were detected. The overall ADR was 62%. The ADR was 52.9% for WLI, 62.1% for BLI-bright, and 71% for LCI, and was significantly higher in the LCI group than in the WLI group (P=0.04). No significant difference was observed between LCI and BLI-bright (P=0.28) or BLI-bright and WLI (P=0.30). The mean number of adenomas per patient was 1.01, 1.03, and 1.62 for WLI, BLI-bright, and LCI, respectively, with a significant difference (P=0.02). Withdrawal time did not differ among the groups. A total of 71 adenomas were detected by WLI, 68 by BLI-bright, and 112 by LCI. There was no difference in the size and morphology of the adenomas detected, nor in the diagnosis of sessile serrated adenomas/polyps.

CONCLUSION

LCI significantly increased the detection of adenomas in screening colonoscopies.

Advanced endoscopy technologies to improve the detection and characterisation of colorrectal polyps

Colorectal cancer is a major health problem. An improvement to its survival has been demonstrated by performing colonoscopy screenings and removing its precursor lesions: polyps. However, colonoscopy is not infallible and multiple strategies have been proposed aimed at improving the quality thereof. This report describes the endoscopic systems available to improve the detection and characterization of polyps, the different classifications for histological prediction and the current indications of advanced endoscopic diagnostic techniques.

Impact of linked-color imaging on colorectal adenoma detection

BACKGROUND AND AIMS

Linked-color imaging (LCI) is a new technology that emphasizes changes in mucosal color by providing clearer and brighter images, thus allowing red and white areas to be visualized more clearly. We investigated whether LCI increases the detection of colorectal adenomas compared with white-light imaging (WLI) and blue-laser imaging (BLI)-bright.

METHODS

Consecutive patients undergoing colonoscopy were randomized (1:1:1) into examination by WLI, BLI-bright, or LCI during withdrawal of the colonoscope. The adenoma detection rate (ADR), mean number of adenomas per patient, and withdrawal time were evaluated. The lesions were evaluated according to size, morphology, location, and histology.

RESULTS

A total of 379 patients were randomized, and 412 adenomas were detected. The ADR was 43.2%, 54.0%, and 56.9% for WLI, BLI-bright, and LCI, respectively, and was significantly higher in the LCI group than in the WLI group (P = .03). No significant difference was observed between LCI and BLI-bright (P = .71) or BLI-bright and WLI (P = .09). The mean number of adenomas per patient was 0.82, 1.06, and 1.38 for WLI, BLI-bright, and LCI, respectively, with a significant difference between LCI and WLI (P = .03). Withdrawal time did not differ among the groups. A total of 102 adenomas were detected by WLI, 131 by BLI-bright, and 179 by LCI. LCI provided a higher rate of detection of adenomas ≤5 mm in size than WLI (P = .02), with a borderline significance for a higher detection of sessile serrated adenomas (P = .05). Nonpolypoid adenomas were more commonly located in the right colon segment and polypoid adenomas in the left colon segment, with a significant difference only between BLI-bright (P < .01) and LCI (P = .03).

CONCLUSIONS

Our findings show that LCI increases the detection of colorectal adenomas during colonoscopy. (Clinical trial registration number: RBR-9xg6dx.).

Blue laser imaging: a new image-enhanced endoscopy for the diagnosis of colorectal lesions

BACKGROUND

Image-enhanced endoscopy enables real-time differential diagnosis of colorectal lesions through the observation of microvascular architecture.

PURPOSE

To evaluate the efficacy of using blue laser imaging (BLI) for capillary pattern analysis in the differential diagnosis of neoplastic and non-neoplastic lesions.

PATIENTS AND METHODS

This prospective study included 920 consecutive superficial lesions diagnosed in 457 patients. The capillary pattern was analysed using BLI-bright magnification on the basis of the Teixeira classification. Histopathology was used as the reference standard.

RESULTS

The adenoma detection rate was 42.3%, with a mean of 0.95 adenomas per patient. Neoplastic lesions were predominant (70.3%), of which 33 (5.1%) had advanced histology. Neoplastic progression was significantly increased in patients aged at least 50 years, in lesions at least 10 mm and in lesions located in the right colon (P<0.01). BLI-based capillary pattern analysis showed 95.5% accuracy, 95.7% sensitivity, 95.2% specificity, 97.9% positive predictive value and 90.3% negative predictive value in the diagnosis of neoplastic lesions. For 672 diminutive lesions (≤5 mm), BLI-based capillary pattern analysis showed 95.7% accuracy, 96.6% sensitivity, 93.6% specificity, 97.2% positive predictive value and 92.2% negative predictive value. Analysing only lesions up to 5 mm in the rectum and sigmoid colon, the values were 95.2, 93.9, 96.5, 95.8 and 94.8%, respectively.

CONCLUSION

BLI associated with magnification yielded excellent results for the real-time predictive histological diagnosis of colorectal lesions.

Application of image-enhanced endoscopy in diagnosis of colorectal cancer

Colorectal cancer (CRC) is one of the most common malignancies, and in China the incidence and mortality of CRC are among the top in the world. Early diagnosis of CRC can improve the prognosis significantly. Image enhancement techniques have already been applied to endoscopy, including narrow band imaging, flexible spectral imaging, i-Scan, and blue laser imaging endoscopy system. These techniques, combined with image pre-processing or post-processing method, might improve the detection of lesions by enhancing the color contrast between lesions and their surrounding mucosa. Nowadays, several classification systems for colorectal tumors have been established based on the surface pattern and microvascular morphology of lesions. Image enhancement technology might display the microvascular structures more clearly and determine the malignancy and infiltrating depth of lesions more accurately.

Hyoscine butylbromide for colorectal polyp detection: prospective, randomized, placebo-controlled trial

OBJECTIVES:

The removal of pre-malignant colorectal lesions prevents cancer. Hyoscine has been proposed as a means of improving diagnosis by reducing colonic movements. The aim of this study was to analyze whether this anti-spasmodic enhances the detection of pre-malignant colorectal lesions.

METHODS:

In a randomized, double-blinded fashion patients received hyoscine or a saline solution in all consecutive colonoscopies in which the cecum was reached. Lesions were analysed with respect to number, size, location, histology and capillary pattern.

RESULTS:

A total of 440 colonoscopies were randomized. The overall polyp detection rate (PDR) and the adenoma detection rate (ADR) were 65.2% and 49.3%, respectively. In the hyoscine group, non-polypoid lesions were detected significantly more often (p=0.01). In the placebo group 281 lesions were diagnosed (202 adenomas) and in the hyoscine group 282 lesions were detected (189 adenomas) (p=0.23). The PDR and ADR were similar between the placebo and hyoscine groups (64% vs 66% and 50% vs 47%, respectively). No differences were observed between the two groups in the advanced-ADR or advanced neoplasia detection rate, as well the mean numbers of polyps, adenomas, advanced adenomas and advanced neoplasias detected per patient. The administration of hyoscine also did not improve the diagnostic accuracy of digital chromoendoscopy. The presence of adenomatous polyps in the right colon was detected significantly more frequently in the hyoscine group (OR 5.41 95% CI 2.7 - 11; p<0.01 vs OR 2.3 95% CI 1.1 - 4.6; p=0.02).

CONCLUSION:

The use of hyoscine before beginning the withdrawal of the colonoscope does not seem to enhance the PDR and the ADR.