Introduction

Early detection and removal of colorectal adenomatous lesions is effective in reducing the incidence and mortality of colorectal cancer. To achieve this, it is important to improve the detection of colorectal lesions. Newly endoscopy technology, texture and color enhancement imaging (TXI) is expected to enhance visibility of lesion by adjusting the color, structure, and brightness of images taken with white-light imaging (WLI) using EVIS X1 system (Olympus Medical Systems Co., Tokyo, Japan). Our previous retrospective study indicated that TXI improve the detection of colorectal neoplastic lesions. However, it is unclear that ability of detection in TXI is superior to that of WLI.

Aims & Methods

We conducted a prospective multicenter randomized controlled trial to verify the efficacy of TXI in the detection of colorectal neoplastic lesions, when compared with WLI (jRCT1032230089).This trial was conducted at 8 institutions in Japan between May and November 2023. The eligibility criteria included patients aged 20–80 years who were scheduled for screening, post-endoscopic surveillance, or work-up for a positive fecal immunochemical test or abdominal symptoms. Patients were randomly assigned (1:1) to TXI or WLI (control group). In all colonoscopies, EVIS X1 system and CF-EZ1500DI were used. The primary endpoint was mean adenoma per procedure (MAP) in per protocol set (PPS). Other endpoints included adenoma detection rate (ADR), advanced ADR (advanced adenoma: more than 10 mm in diameter, villous or tubulovillous in histology, or high-grade dysplasia), polyp detection rate (PDR), and flat polyp detection rate (FDR). We assumed the TXI mode observations to have an improvement effect of MAP with a difference of δ=0.3 on WLI and the standard deviations of MAP in TXI and WLI were expected to be 1.8 and 1.3, respectively. The required number of subjects for analysis was calculated to be 960, considering an expected dropout rate of 10%, when the two-sided significance level was set at 0.05 and power at 0.8.

Results

A total of 960 patients were enrolled. In PPS, 896 patients were analyzed (451 in TXI and 445 in WLI). In MAP, there was no statistically significant difference between the groups (TXI: 1.4 [95% CI: 1.2-1.6] vs. WLI: 1.5 [1.3-1.7]). ADR was similar in the groups (57.21% [52.49-61.82] vs. 55.96 [51.20-60.63]). Advanced ADR tend to be higher in TXI than WLI (11.09% [8.34-14.35] vs. 8.54[6.11-11.53]). PDR was significantly higher in TXI than WLI (82.48% [78.65-85.88] vs. 74.38 [70.06-78.38]. FDR was significantly higher in TXI than WLI (76.50% [72.31-80.34] vs. 70.34 [65.86-74.55]).

Conclusion

This trial could not show the superiority of TXI over WLI in MAP and ADR. However, it showed that of TXI over WLI in PDR and FDR, indicating that TXI may have ability to detect more flat colorectal lesions which have malignant potential or are difficult to detect.

Introduction

Approximately 10% of patients diagnosed with pancreatic ductal adenocarcinoma (PDAC) carry a pathogenic variant in a PDAC susceptibility gene. Current guidelines recommend offering germline cancer susceptibility testing for all individuals with PDAC regardless of family history. Previous studies have shown moderate rates of uptake of gene testing, highlighting the need for efficient and accessible clinical pathways for delivering gene testing education and counseling. We evaluated the uptake of gene testing when offered at the point-of-care by an oncology nurse specialist in an outpatient setting.

Aims & Methods

We undertook a retrospective chart review of PDAC patients treated at the Johns Hopkins Hospital between January 2021 and December 2023. Patients were educated about germline testing by an oncology nurse specialist during their initial clinic visit, and provided with instructional handouts, links to videos, instructions on kit ordering and given time to consider testing. “MyChart” reminders are sent as needed. Patients who desired testing were sent a saliva kit to their home that they had to send back to the testing lab. Results were communicated by the oncology nurse to the patients, and those with pathogenic variants or variants of uncertain significance (VUS) are referred to formal genetic counseling.

Results

Of 1022 patients seen by the oncology and surgery teams, all but 2 were seen by oncology, 377 underwent surgery, 52% were male, 74.9% were White, 15.8% African American (AA), 6% were Asian, 3% were Hispanic, and 17.5% had a family history of pancreatic cancer. At diagnosis, median age was 67.1 +/- 10.6 years; 51.9% of cases had resectable-stage disease.
Among the 87.5% of patients offered gene testing, 77.6% completed testing. Completion rates among those offered testing increased from 72.4% (2021) to 78.5% (2022) and 82.2% (2023).
Factors significantly associated with reduced gene testing uptake included African American patients, those that were single, had advanced-stage disease, did not receive chemotherapy and of older age at diagnosis (Table 1).
Among tested individuals, 55 (7.9%) involving PDAC susceptibility genes, with BRCA2, ATM and PALB2 being the most common. 50 out of these 55 patients (91%) were referred to genetic counseling, with 76% completing their counseling visit to date. Germline testing results led to a change in the treatment regimen in 23 of the 55 patients.

Conclusion

The implementation of point-of-care encounters for cancer susceptibility gene testing by an oncology nurse specialist in the outpatient setting yielded a high uptake of testing. African American, older-age, single and advanced-stage disease individuals had lower rates of completing gene testing.

Introduction

Non-expert endoscopists’ optical diagnosis (OD) of colorectal polyps falls short of ‘resect and discard’ and ‘diagnose and leave’ thresholds. Previous CADx studies are limited to locally deployed hardware AI systems and are mainly evaluated in expert endoscopists. CADDIE is a cloud-based CADx system that receives the live image stream from the endoscopy screen via the hospital’s internet network, where the AI algorithm processes the images and outputs its diagnosis (adenoma, non-adenoma or uncertain) on the endoscopy screen.

We aimed to assess the performance of the real-time cloud-based CADDIE system when colonoscopy is undertaken by non-expert endoscopists (adenoma detection rate below 30%).

Aims & Methods

We enrolled 739 patients between April 2021 - Dec 2022, scoped by 32 endoscopists in 9 UK hospitals. Each endoscopist was limited to a maximum of 60 procedures and required to perform more than 20% of this target. Patients were block randomised in a 1:1 ratio to standard of care (SOC) or intervention (CADDIE), stratified by endoscopist and indication. OD accuracy of humans alone (SOC arm) and humans aided by CADDIE (CADDIE arm) were compared to the CADDIE system’s stand-alone performance in the CADDIE arm.

Results

There were 615 evaluable patients after exclusions as pre-defined in the study protocol. There were 523 eligible polyps (270 SOC arm, 253 CADDIE arm). The CADDIE system diagnosed 17.8% of polyps (45/253) as “uncertain”.

Human alone (SOC) OD accuracy was 75.9%, human OD aided by CADDIE was 80.2%, whilst the stand-alone CADDIE system was significantly higher than both at 87.5% (p=0.005 and p=0.04, respectively). Similarly, in the sub-analysis of small/diminutive polyps (≤10mm), human alone OD accuracy was 73.8%, human OD aided by CADDIE was 79.0%, whilst the CADDIE system was significantly higher than both at 87.9% (p=0.001 and p=0.02). Although results were not significant for diminutive polyps (≤5mm), the trend was towards higher accuracy in the CADDIE system (86.6%) compared to humans alone and human OD aided by CADDIE (77.3%;p=0.05).

In sub-analyses of high-confidence (HC) OD, the CADDIE system’s accuracy for ≤10mm polyps was significantly higher (87.9%) than humans alone (78.4%;p=0.04), with no difference to humans aided by CADDIE (83.3%;p=0.18). For HC OD of ≤5mm polyps, where the sample size is smaller, the CADDIE system’s accuracy was higher (86.6%) but not significant compared to humans alone (82.7%,p=0.46) and humans aided by CADDIE (81.4%,p=0.28).

The OD-derived colonoscopy surveillance interval accuracy was 87.2% in humans alone (SOC), 86.8% in humans aided by CADDIE and 90.9% for the CADDIE system.

Conclusion

We demonstrate proof of concept and robust results for a cloud-based CADx system. Further research is warranted in the human-computer interaction to optimise non-expert endoscopists’ OD performance to that of CADx systems.

Disclosure

Dr Rawen Kader and Professor Laurence Lovat have received medical consultancy fees from Odin Vision