Efficacy of Real-Time Computer-Aided Detection of Colorectal Neoplasia in a Randomized Trial

Negative Samples for Improving Object Detection-A Case Study in AI-Assisted Colonoscopy for Polyp Detection

Deep learning object-detection models are being successfully applied to develop computer-aided diagnosis systems for aiding polyp detection during colonoscopies. Here, we evidence the need to include negative samples for both (i) reducing false positives during the polyp-finding phase, by including images with artifacts that may confuse the detection models (e.g., medical instruments, water jets, feces, blood, excessive proximity of the camera to the colon wall, blurred images, etc.) that are usually not included in model development datasets, and (ii) correctly estimating a more realistic performance of the models. By retraining our previously developed YOLOv3-based detection model with a dataset that includes 15% of additional not-polyp images with a variety of artifacts, we were able to generally improve its F1 performance in our internal test datasets (from an average F1 of 0.869 to 0.893), which now include such type of images, as well as in four public datasets that include not-polyp images (from an average F1 of 0.695 to 0.722).

Unassisted Clinicians Versus Deep Learning-Assisted Clinicians in Image-Based Cancer Diagnostics: Systematic Review With Meta-analysis

BACKGROUND

A number of publications have demonstrated that deep learning (DL) algorithms matched or outperformed clinicians in image-based cancer diagnostics, but these algorithms are frequently considered as opponents rather than partners. Despite the clinicians-in-the-loop DL approach having great potential, no study has systematically quantified the diagnostic accuracy of clinicians with and without the assistance of DL in image-based cancer identification.

OBJECTIVE

We systematically quantified the diagnostic accuracy of clinicians with and without the assistance of DL in image-based cancer identification.

METHODS

PubMed, Embase, IEEEXplore, and the Cochrane Library were searched for studies published between January 1, 2012, and December 7, 2021. Any type of study design was permitted that focused on comparing unassisted clinicians and DL-assisted clinicians in cancer identification using medical imaging. Studies using medical waveform-data graphics material and those investigating image segmentation rather than classification were excluded. Studies providing binary diagnostic accuracy data and contingency tables were included for further meta-analysis. Two subgroups were defined and analyzed, including cancer type and imaging modality.

RESULTS

In total, 9796 studies were identified, of which 48 were deemed eligible for systematic review. Twenty-five of these studies made comparisons between unassisted clinicians and DL-assisted clinicians and provided sufficient data for statistical synthesis. We found a pooled sensitivity of 83% (95% CI 80%-86%) for unassisted clinicians and 88% (95% CI 86%-90%) for DL-assisted clinicians. Pooled specificity was 86% (95% CI 83%-88%) for unassisted clinicians and 88% (95% CI 85%-90%) for DL-assisted clinicians. The pooled sensitivity and specificity values for DL-assisted clinicians were higher than for unassisted clinicians, at ratios of 1.07 (95% CI 1.05-1.09) and 1.03 (95% CI 1.02-1.05), respectively. Similar diagnostic performance by DL-assisted clinicians was also observed across the predefined subgroups.

CONCLUSIONS

The diagnostic performance of DL-assisted clinicians appears better than unassisted clinicians in image-based cancer identification. However, caution should be exercised, because the evidence provided in the reviewed studies does not cover all the minutiae involved in real-world clinical practice. Combining qualitative insights from clinical practice with data-science approaches may improve DL-assisted practice, although further research is required.

TRIAL REGISTRATION

PROSPERO CRD42021281372; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=281372.

Complementary Effect of the Proportion of Overspeed Frames of Withdrawal and Withdrawal Time on Reflecting Colonoscopy Quality: A Retrospective, Observational Study

INTRODUCTION

Constructing quality indicators that reflect the defect of colonoscopy operation for quality audit and feedback is very important. Previously, we have established a real-time withdrawal speed monitoring system to control withdrawal speed below the safe speed. We aimed to explore the relationship between the proportion of overspeed frames (POF) of withdrawal and the adenoma detection rate (ADR) and to conjointly analyze the influence of POF and withdrawal time on ADR to evaluate the feasibility of POF combined with withdrawal time as a quality control indicator.

METHODS

The POF was defined as the proportion of frames with instantaneous speed ≥44 in the whole colonoscopy video. First, we developed a system for the POF of withdrawal based on a perceptual hashing algorithm. Next, we retrospectively collected 1,804 colonoscopy videos to explore the relationship between POF and ADR. According to withdrawal time and POF cutoff, we conducted a complementary analysis on the effects of POF and withdrawal time on ADR.

RESULTS

There was an inverse correlation between the POF and ADR (Pearson correlation coefficient -0.836). When withdrawal time was >6 minutes, the ADR of the POF ≤10% was significantly higher than that of POF >10% (25.30% vs 16.50%; odds ratio 0.463, 95% confidence interval 0.296-0.724, P < 0.01). When the POF was ≤10%, the ADR of withdrawal time >6 minutes was higher than that of withdrawal time ≤6 minutes (25.30% vs 21.14%; odds ratio 0.877, 95% confidence interval 0.667-1.153, P = 0.35).

DISCUSSION

The POF was strongly correlated with ADR. The combined assessment of the POF and withdrawal time has profound significance for colonoscopy quality control.

Computer-aided detection, mucosal exposure device, their combination, and standard colonoscopy for adenoma detection: a randomized controlled trial

BACKGROUND AND AIMS

Computer-aided detection (CADe) and a mucosal exposure device can improve adenoma detection rate (ADR). Potential benefits of combining the 2 modalities have never been studied. This study aimed to compare ADR differences among CADe alone, endocuff-assisted colonoscopy (EAC) alone, and the combination of CADe and EAC (CADe+EAC) with standard colonoscopy.

METHODS

This prospective randomized controlled study included 1245 participants who underwent screening colonoscopy. Participants were randomized to CADe, EAC, CADe+EAC, and standard colonoscopy as a control. The primary outcome was ADR. Secondary outcomes were proximal ADR (pADR), advanced ADR (AADR), and the number of adenomas per colonoscopy (APCs).

RESULTS

ADRs from the control, CADe, EAC, and CADe+EAC groups were 41.9%, 52.2%, 54.0%, and 58.8%, respectively; pADRs were 25.2%, 33.3%, 34.9%, and 37.0%, respectively; AADRs were 7.7%, 8.3%, 8.3%, and 13.6%, respectively; and APCs were .76, 1.11, 1.18, and 1.31, respectively. Significant increases in ADR and pADR were observed between the intervention and control groups (P < .05 in all comparisons). The AADR was significantly higher only in the CADe+EAC group than in the control group (P = .02). The adjusted incidence rate ratios of APCs were significantly higher in the intervention groups versus the control group (P < .01 in all comparisons).

CONCLUSIONS

CADe+EAC significantly improve ADR and AADR over standard colonoscopy. However, although CADe or EAC alone can substantially increase the detection of adenomas, they do not lead to increased detection of advanced adenomas unless used in combination. (Clinical trial registration number: TCTR20200929003.).

Performance evaluation methods for improvements at post-market of artificial intelligence/machine learning-based computer-aided detection/diagnosis/triage in the United States

Computer-aided detection (CADe), computer-aided diagnosis (CADx), and computer-aided simple triage (CAST), which incorporate artificial intelligence (AI) and machine learning (ML), are continually undergoing post-market improvement. Therefore, understanding the evaluation and approval process of improved products is important. This study intended to conduct a comprehensive survey of AI/ML-based CAD products approved by the U.S. Food and Drug Administration (FDA) that had been improved post-market to gain insights into the efficacy and safety required for market approval. A survey of the product code database published by the FDA identified eight products that were improved post-market. The methods used to evaluate the performance of improvements were analysed, and post-market improvements were approved with retrospective data. Reader study testing (RT) or software standalone testing (SA) procedures were conducted retrospectively. Six RT procedures were conducted because of modifications to the intended use. An average of 17.3 readers (minimum 14, maximum 24) participated, and the area under the curve (AUC) was considered the primary endpoint. The addition of study learning data that did not change the intended use and changes in the analysis algorithm were evaluated by SA. The average sensitivity, specificity, and AUC were 93% (minimum 91.1, maximum 97), 89.6% (minimum 85.9, maximum 96), and 0.96 (minimum 0.96, maximum 0.97), respectively. The average interval between applications was 348 days (minimum -18, maximum 975), which showed that the improvements were implemented within approximately one year. This is the first comprehensive study on AI/ML-based CAD products that have been improved post-market to elucidate evaluation points for post-market improvements. The findings will be informative for the industry and academia in developing and improving AI/ML-based CAD.

Deep Learning-Based Model for Identifying Tumors in Endoscopic Images From Patients With Locally Advanced Rectal Cancer Treated With Total Neoadjuvant Therapy

BACKGROUND

A barrier to the widespread adoption of watch-and-wait management for locally advanced rectal cancer is the inaccuracy and variability of identifying tumor response endoscopically in patients who have completed total neoadjuvant therapy (chemoradiotherapy and systemic chemotherapy).

OBJECTIVE

This study aimed to develop a novel method of identifying the presence or absence of a tumor in endoscopic images using deep convolutional neural network-based automatic classification and to assess the accuracy of the method.

DESIGN

In this prospective pilot study, endoscopic images obtained before, during, and after total neoadjuvant therapy were grouped on the basis of tumor presence. A convolutional neural network was modified for probabilistic classification of tumor versus no tumor and trained with an endoscopic image set. After training, a testing endoscopic imaging set was applied to the network.

SETTINGS

The study was conducted at a comprehensive cancer center.

PATIENTS

Images were analyzed from 109 patients who were diagnosed with locally advanced rectal cancer between December 2012 and July 2017 and who underwent total neoadjuvant therapy.

MAIN OUTCOME MEASURES

The main outcomes were accuracy of identifying tumor presence or absence in endoscopic images measured as area under the receiver operating characteristic for the training and testing image sets.

RESULTS

A total of 1392 images were included; 1099 images (468 of no tumor and 631 of tumor) were for training and 293 images (151 of no tumor and 142 of tumor) for testing. The area under the receiver operating characteristic for training and testing was 0.83.

LIMITATIONS

The study had a limited number of images in each set and was conducted at a single institution.

CONCLUSIONS

The convolutional neural network method is moderately accurate in distinguishing tumor from no tumor. Further research should focus on validating the convolutional neural network on a large image set. See Video Abstract at http://links.lww.com/DCR/B959 .

MODELO BASADO EN APRENDIZAJE PROFUNDO PARA IDENTIFICAR TUMORES EN IMGENES ENDOSCPICAS DE PACIENTES CON CNCER DE RECTO LOCALMENTE AVANZADO TRATADOS CON TERAPIA NEOADYUVANTE TOTAL

ANTECEDENTES:Una barrera para la aceptación generalizada del tratamiento de Observar y Esperar para el cáncer de recto localmente avanzado, es la imprecisión y la variabilidad en la identificación de la respuesta tumoral endoscópica, en pacientes que completaron la terapia neoadyuvante total (quimiorradioterapia y quimioterapia sistémica).OBJETIVO:Desarrollar un método novedoso para identificar la presencia o ausencia de un tumor en imágenes endoscópicas utilizando una clasificación automática basada en redes neuronales convolucionales profundas y evaluar la precisión del método.DISEÑO:Las imágenes endoscópicas obtenidas antes, durante y después de la terapia neoadyuvante total se agruparon en base de la presencia del tumor. Se modificó una red neuronal convolucional para la clasificación probabilística de tumor versus no tumor y se entrenó con un conjunto de imágenes endoscópicas. Después del entrenamiento, se aplicó a la red un conjunto de imágenes endoscópicas de prueba.ENTORNO CLINICO:El estudio se realizó en un centro oncológico integral.PACIENTES:Analizamos imágenes de 109 pacientes que fueron diagnosticados de cáncer de recto localmente avanzado entre diciembre de 2012 y julio de 2017 y que se sometieron a terapia neoadyuvante total.PRINCIPALES MEDIDAS DE VALORACION:La precisión en la identificación de la presencia o ausencia de tumores en imágenes endoscópicas medidas como el área bajo la curva de funcionamiento del receptor para los conjuntos de imágenes de entrenamiento y prueba.RESULTADOS:Se incluyeron mil trescientas noventa y dos imágenes: 1099 (468 sin tumor y 631 con tumor) para entrenamiento y 293 (151 sin tumor y 142 con tumor) para prueba. El área bajo la curva operativa del receptor para entrenamiento y prueba fue de 0,83.LIMITACIONES:El estudio tuvo un número limitado de imágenes en cada conjunto y se realizó en una sola institución.CONCLUSIÓN:El método de la red neuronal convolucional es moderadamente preciso para distinguir el tumor de ningún tumor. La investigación adicional debería centrarse en validar la red neuronal convolucional en un conjunto de imágenes mayor. Consulte Video Resumen en http://links.lww.com/DCR/B959 . (Traducción -Dr. Fidel Ruiz Healy ).

Usefulness of a novel computer-aided detection system for colorectal neoplasia: a randomized controlled trial

BACKGROUND AND AIMS

Artificial intelligence-based computer-aid detection (CADe) devices have been recently tested in colonoscopies, increasing the adenoma detection rate (ADR), mainly in Asian populations. However, evidence for the benefit of these devices in the occidental population is still low. We tested a new CADe device, namely, ENDO-AID (OIP-1) (Olympus, Tokyo, Japan), in clinical practice.

METHODS

This randomized controlled trial included 370 consecutive patients who were randomized 1:1 to CADe (n = 185) versus standard exploration (n = 185) from November 2021 to January 2022. The primary endpoint was the ADR. Advanced adenoma was defined as ≥10 mm, harboring high-grade dysplasia, or with a villous pattern. Otherwise, the adenoma was nonadvanced. ADR was assessed in both groups stratified by endoscopist ADR and colon cleansing.

RESULTS

In the intention-to-treat analysis, the ADR was 55.1% (102/185) in the CADe group and 43.8% (81/185) in the control group (P = .029). Nonadvanced ADRs (54.8% vs 40.8%, P = .01) and flat ADRs (39.4 vs 24.8, P = .006), polyp detection rate (67.1% vs 51%; P = .004), and number of adenomas per colonoscopy were significantly higher in the CADe group than in the control group (median [25th-75th percentile], 1 [0-2] vs 0 [0-1.5], respectively; P = .014). No significant differences were found in serrated ADR. After stratification by endoscopist and bowel cleansing, no statistically significant differences in ADR were found.

CONCLUSIONS

Colonoscopy assisted by ENDO-AID (OIP-1) increases ADR and number of adenomas per colonoscopy, suggesting it may aid in the detection of colorectal neoplastic lesions, especially because of its detection of diminutive and flat adenomas. (Clinical trial registration number: NCT04945044.).

The Impacts of Computer-Aided Detection of Colorectal Polyps on Subsequent Colonoscopy Surveillance Intervals: Simulation Study

BACKGROUND

Computer-aided detection (CADe) of colorectal polyps has been shown to increase adenoma detection rates, which would potentially shorten subsequent surveillance intervals.

OBJECTIVE

The purpose of this study is to simulate the potential changes in subsequent colonoscopy surveillance intervals after the application of CADe in a large cohort of patients.

METHODS

We simulated the projected increase in polyp and adenoma detection by universal CADe application in our patients who had undergone colonoscopy with complete endoscopic and histological findings between 2016 and 2020. The simulation was based on bootstrapping the published performance of CADe. The corresponding changes in surveillance intervals for each patient, as recommended by the US Multi-Society Task Force on Colorectal Cancer (USMSTF) or the European Society of Gastrointestinal Endoscopy (ESGE), were determined after the CADe was determined.

RESULTS

A total of 3735 patients who had undergone colonoscopy were included. Based on the simulated CADe effect, the application of CADe would result in 19.1% (n=714) and 1.9% (n=71) of patients having shorter surveillance intervals, according to the USMSTF and ESGE guidelines, respectively. In particular, all (or 2.7% (n=101) of the total) patients who were originally scheduled to have 3-5 years of surveillance would have their surveillance intervals shortened to 3 years, following the USMSTF guidelines. The changes in this group of patients were largely attributed to an increase in the number of adenomas (n=75, 74%) rather than serrated lesions being detected.

CONCLUSIONS

Widespread adoption of CADe would inevitably increase the demand for surveillance colonoscopies with the shortening of original surveillance intervals, particularly following the current USMSTF guideline.

A bibliometric and visual analysis of publications on artificial intelligence in colorectal cancer (2002-2022)

Background

Colorectal cancer (CRC) has the third-highest incidence and second-highest mortality rate of all cancers worldwide. Early diagnosis and screening of CRC have been the focus of research in this field. With the continuous development of artificial intelligence (AI) technology, AI has advantages in many aspects of CRC, such as adenoma screening, genetic testing, and prediction of tumor metastasis.

Objective

This study uses bibliometrics to analyze research in AI in CRC, summarize the field's history and current status of research, and predict future research directions.

Method

We searched the SCIE database for all literature on CRC and AI. The documents span the period 2002-2022. we used bibliometrics to analyze the data of these papers, such as authors, countries, institutions, and references. Co-authorship, co-citation, and co-occurrence analysis were the main methods of analysis. Citespace, VOSviewer, and SCImago Graphica were used to visualize the results.

Result

This study selected 1,531 articles on AI in CRC. China has published a maximum number of 580 such articles in this field. The U.S. had the most quality publications, boasting an average citation per article of 46.13. Mori Y and Ding K were the two authors with the highest number of articles. Scientific Reports, Cancers, and Frontiers in Oncology are this field's most widely published journals. Institutions from China occupy the top 9 positions among the most published institutions. We found that research on AI in this field mainly focuses on colonoscopy-assisted diagnosis, imaging histology, and pathology examination.

Conclusion

AI in CRC is currently in the development stage with good prospects. AI is currently widely used in colonoscopy, imageomics, and pathology. However, the scope of AI applications is still limited, and there is a lack of inter-institutional collaboration. The pervasiveness of AI technology is the main direction of future housing development in this field.

An Evaluation of Critical Factors for the Cost-Effectiveness of Real-Time Computer-Aided Detection: Sensitivity and Threshold Analyses Using a Microsimulation Model

BACKGROUND

The use of computer-aided detection (CAD) increases the adenoma detection rates (ADRs) during colorectal cancer (CRC) screening/surveillance. This study aimed to evaluate the requirements for CAD to be cost-effective and the impact of CAD on adenoma detection by endoscopists with different ADRs.

METHODS

We developed a semi-Markov microsimulation model to compare the effectiveness of traditional colonoscopy (mean ADR, 26%) to colonoscopy with CAD (mean ADR, 37%). CAD was modeled as having a $75 per-procedure cost. Extensive 1-way sensitivity and threshold analysis were performed to vary cost and ADR of CAD. Multiple scenarios evaluated the potential effect of CAD on endoscopists' ADRs. Outcome measures were reported in incremental cost-effectiveness ratios, with a willingness-to-pay threshold of $100,000/quality-adjusted life year.

RESULTS

When modeling CAD improved ADR for all endoscopists, the CAD cohort had 79 and 34 fewer lifetime CRC cases and deaths, respectively, per 10,000 persons. This scenario was dominant with a cost savings of $143 and incremental effectiveness of 0.01 quality-adjusted life years. Threshold analysis demonstrated that CAD would be cost-effective up to an additional cost of $579 per colonoscopy, or if it increases ADR from 26% to at least 30%. CAD reduced CRC incidence and mortality when limited to improving ADRs for low-ADR endoscopists (ADR <25%), with 67 fewer CRC cases and 28 CRC deaths per 10,000 persons compared with traditional colonoscopy.

CONCLUSIONS

As CAD is implemented clinically, it needs to improve mean ADR from 26% to at least 30% or cost less than $579 per colonoscopy to be cost-effective when compared with traditional colonoscopy. Further studies are needed to understand the impact of CAD on community practice.

Computer-assisted detection versus conventional colonoscopy for proximal colonic lesions: a multicenter, randomized, tandem-colonoscopy study

BACKGROUND AND AIMS

Computer-assisted detection (CADe) is a promising technologic advance that enhances adenoma detection during colonoscopy. However, the role of CADe in reducing missed colonic lesions is uncertain. The aim of this study was to determine the miss rates of proximal colonic lesions by CADe and conventional colonoscopy.

METHODS

This was a prospective, multicenter, randomized, tandem-colonoscopy study conducted in 3 Asian centers. Patients were randomized to receive CADe or conventional white-light colonoscopy during the first withdrawal of the proximal colon (cecum to splenic flexure), immediately followed by tandem examination of the proximal colon with white light in both groups. The primary outcome was adenoma/polyp miss rate, which was defined as any adenoma/polyp detected during the second examination.

RESULTS

Of 223 patients (48.6% men; median age, 63 years) enrolled, 7 patients did not have tandem examination, leaving 108 patients in each group. There was no difference in the miss rate for proximal adenomas (CADe vs conventional: 20.0% vs 14.0%, P = .07) and polyps (26.7% vs 19.6%, P = .06). The CADe group, however, had significantly higher proximal polyp (58.0% vs 46.7%, P = .03) and adenoma (44.7% vs 34.6%, P = .04) detection rates than the conventional group. The mean number of proximal polyps and adenomas detected per patient during the first examination was also significantly higher in the CADe group (polyp: 1.20 vs .86, P = .03; adenoma, .91 vs .61, P = .03). Subgroup analysis showed that CADe enhanced proximal adenoma detection in patients with fair bowel preparation, shorter withdrawal time, and endoscopists with lower adenoma detection rate.

CONCLUSIONS

This multicenter trial from Asia confirmed that CADe can further enhance proximal adenoma and polyp detection but may not be able to reduce the number of missed proximal colonic lesions. (Clinical trial registration number: NCT04294355.).

Automation: A revolutionary vision of artificial intelligence in theranostics

The last two decades have witnessed an extraordinary evolution of automation and artificial intelligence (AI), which has become an integral part of our daily lives. Lately, AI has also been assimilated in the field of medicine to upgrade overall healthcare system and encourage personalized treatment. Theranostics literally meaning combination of diagnosis and therapeutics, is a targeted pharmacotherapy, based on specific targeted diagnostic tests. Numerous theranostic agents/biomarkers are available which can identify the most beneficial treatment, correct dose or predict response to a medicine, thus, maximizing drug efficacy, minimizing toxicity and providing informed treatment choice. For instance, a statistics based Cluster-FLIM technology provides precise data on drug-receptor binding behavior in biological tissues using fluorescence real experimental imaging. Automated Idylla™ qPCR System is another approach in oncology to determine the EGFR mutations at initial stage as well as during the treatment and also assists the oncologist in designing the treatment protocol. Recent incorporation of automation and AI in theranostics has brought a drastic change in early detection and treatment protocols for various diseases such as cancer and diabetes. Also, it leads to quick analysis of number of diverse experimental datum with accuracy. The approach mainly uses computer algorithms to unveil relevant and significant information from clinical data, thereby assisting in making accurate, logical and pertinent decisions. This review highlights the emerging uses/role of automation and AI in theranostics, technical difficulties and focuses on its future prospects to facilitate a patient specific, reliable and efficient pharmacotherapy.

Effect of computer-aided colonoscopy on adenoma miss rates and polyp detection: A systematic review and meta-analysis

BACKGROUND AND AIM

Multiple computer-aided techniques utilizing artificial intelligence (AI) have been created to improve the detection of polyps during colonoscopy and thereby reduce the incidence of colorectal cancer. While adenoma detection rates (ADR) and polyp detection rates (PDR) are important colonoscopy quality indicators, adenoma miss rates (AMR) may better quantify missed lesions, which can ultimately lead to interval colorectal cancer. The purpose of this systematic review and meta-analysis was to determine the efficacy of computer-aided colonoscopy (CAC) with respect to AMR, ADR, and PDR in randomized controlled trials.

METHODS

A comprehensive, systematic literature search was performed across multiple databases in September of 2022 to identify randomized, controlled trials that compared CAC with traditional colonoscopy. Primary outcomes were AMR, ADR, and PDR.

RESULTS

Fourteen studies totaling 10 928 patients were included in the final analysis. There was a 65% reduction in the adenoma miss rate with CAC (OR, 0.35; 95% CI, 0.25-0.49, P < 0.001, I²  = 50%). There was a 78% reduction in the sessile serrated lesion miss rate with CAC (OR, 0.22; 95% CI, 0.08-0.65, P < 0.01, I²  = 0%). There was a 52% increase in ADR in the CAC group compared with the control group (OR, 1.52; 95% CI, 1.39-1.67, P = 0.04, I²  = 47%). There was 93% increase in the number of adenomas > 10 mm detected per colonoscopy with CAC (OR 1.93; 95% CI, 1.18-3.16, P < 0.01, I²  = 0%).

CONCLUSIONS

The results of the present study demonstrate the promise of CAC in improving AMR, ADR, PDR across a spectrum of size and morphological lesion characteristics.

Comprehensive review of publicly available colonoscopic imaging databases for artificial intelligence research: availability, accessibility, and usability

BACKGROUND AND AIMS

Publicly available databases containing colonoscopic imaging data are valuable resources for artificial intelligence (AI) research. Currently, little is known regarding the available number and content of these databases. This review aimed to describe the availability, accessibility, and usability of publicly available colonoscopic imaging databases, focusing on polyp detection, polyp characterization, and quality of colonoscopy.

METHODS

A systematic literature search was performed in MEDLINE and Embase to identify AI studies describing publicly available colonoscopic imaging databases published after 2010. Second, a targeted search using Google's Dataset Search, Google Search, GitHub, and Figshare was done to identify databases directly. Databases were included if they contained data about polyp detection, polyp characterization, or quality of colonoscopy. To assess accessibility of databases, the following categories were defined: open access, open access with barriers, and regulated access. To assess the potential usability of the included databases, essential details of each database were extracted using a checklist derived from the Checklist for Artificial Intelligence in Medical Imaging.

RESULTS

We identified 22 databases with open access, 3 databases with open access with barriers, and 15 databases with regulated access. The 22 open access databases contained 19,463 images and 952 videos. Nineteen of these databases focused on polyp detection, localization, and/or segmentation; 6 on polyp characterization, and 3 on quality of colonoscopy. Only half of these databases have been used by other researcher to develop, train, or benchmark their AI system. Although technical details were in general well reported, important details such as polyp and patient demographics and the annotation process were under-reported in almost all databases.

CONCLUSIONS

This review provides greater insight on public availability of colonoscopic imaging databases for AI research. Incomplete reporting of important details limits the ability of researchers to assess the usability of current databases.

Variability in adenoma detection rate in control groups of randomized colonoscopy trials: a systematic review and meta-analysis

BACKGROUND AND AIMS

Adenoma detection rate (ADR) is still the main surrogate outcome parameter of screening colonoscopy, but most studies include mixed indications, and basic ADR is quite variable. We therefore looked at the control groups in randomized ADR trials using advanced imaging or mechanical methods to find out whether indications or other factors influence ADR levels.

METHODS

Patients in the control groups of randomized controlled trials (RCTs) on ADR increase using various methods were collected based on a systematic review; this control group had to use high-definition white-light endoscopy performed between 2008 and 2021. Random-effects meta-analysis was used to pool ADR in control groups and its 95% confidence interval (CI) according to clinical (indication and demographic), study setting (tandem/parallel, number of centers, sample size), and technical (type of intervention, withdrawal time) parameters. Interstudy heterogeneity was reported with the I² statistic. Multivariable mixed-effects meta-regression was performed for potentially relevant variables.

RESULTS

From 80 studies, 25,304 patients in the respective control groups were included. ADR in control arms varied between 8.2% and 68.1% with a high degree of heterogeneity (I² = 95.1%; random-effect pooled value, 37.5%; 95% CI, 34.6‒40.5). There was no difference in ADR levels between primary colonoscopy screening (12 RCTs, 15%) and mixed indications including screening/surveillance and diagnostic colonoscopy; however, fecal immunochemical testing as an indication for colonoscopy was an independent predictor of ADR (odds ratio [OR], 1.6; 95% CI, 1.1-2.4). Other well-known parameters were confirmed by our analysis such as age (OR, 1.038; 95% CI, 1.004-1.074), sex (male sex: OR, 1.02; 95% CI, 1.01-1.03), and withdrawal time (OR, 1.1; 95% CI, 1.0-1.1). The type of intervention (imaging vs mechanical) had no influence, but methodologic factors did: More recent year of publication and smaller sample size were associated with higher ADR.

CONCLUSIONS

A high level of variability was found in the level of ADR in the control groups of RCTs. With regards to indications, only fecal immunochemical test-based colonoscopy studies influenced basic ADR, and primary colonoscopy screening appeared to be similar to other indications. Standardization for variables related to clinical, methodologic, and technical parameters is required to achieve generalizability and reproducibility.

Artificial intelligence empowers the second-observer strategy for colonoscopy: a randomized clinical trial

Background

In colonoscopy screening for colorectal cancer, human vision limitations may lead to higher miss rate of lesions; artificial intelligence (AI) assistance has been demonstrated to improve polyp detection. However, there still lacks direct evidence to demonstrate whether AI is superior to trainees or experienced nurses as a second observer to increase adenoma detection during colonoscopy. In this study, we aimed to compare the effectiveness of assistance from AI and human observer during colonoscopy.

Methods

A prospective multicenter randomized study was conducted from 2 September 2019 to 29 May 2020 at four endoscopy centers in China. Eligible patients were randomized to either computer-aided detection (CADe)-assisted group or observer-assisted group. The primary outcome was adenoma per colonoscopy (APC). Secondary outcomes included polyp per colonoscopy (PPC), adenoma detection rate (ADR), and polyp detection rate (PDR). We compared continuous variables and categorical variables by using R studio (version 3.4.4).

Results

A total of 1,261 (636 in the CADe-assisted group and 625 in the observer-assisted group) eligible patients were analysed. APC (0.42 vs 0.35, P = 0.034), PPC (1.13 vs 0.81, P < 0.001), PDR (47.5% vs 37.4%, P < 0.001), ADR (25.8% vs 24.0%, P = 0.464), the number of detected sessile polyps (683 vs 464, P < 0.001), and sessile adenomas (244 vs 182, P = 0.005) were significantly higher in the CADe-assisted group than in the observer-assisted group. False detections of the CADe system were lower than those of the human observer (122 vs 191, P < 0.001).

Conclusions

Compared with the human observer, the CADe system may improve the clinical outcome of colonoscopy and reduce disturbance to routine practice (Chictr.org.cn No.: ChiCTR1900025235).

Deep-Learning and Device-Assisted Enteroscopy: Automatic Panendoscopic Detection of Ulcers and Erosions

Background and Objectives: Device-assisted enteroscopy (DAE) has a significant role in approaching enteric lesions. Endoscopic observation of ulcers or erosions is frequent and can be associated with many nosological entities, namely Crohn's disease. Although the application of artificial intelligence (AI) is growing exponentially in various imaged-based gastroenterology procedures, there is still a lack of evidence of the AI technical feasibility and clinical applicability of DAE. This study aimed to develop and test a multi-brand convolutional neural network (CNN)-based algorithm for automatically detecting ulcers and erosions in DAE. Materials and Methods: A unicentric retrospective study was conducted for the development of a CNN, based on a total of 250 DAE exams. A total of 6772 images were used, of which 678 were considered ulcers or erosions after double-validation. Data were divided into a training and a validation set, the latter being used for the performance assessment of the model. Our primary outcome measures were sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and an area under the curve precision-recall curve (AUC-PR). Results: Sensitivity, specificity, PPV, and NPV were respectively 88.5%, 99.7%, 96.4%, and 98.9%. The algorithm's accuracy was 98.7%. The AUC-PR was 1.00. The CNN processed 293.6 frames per second, enabling AI live application in a real-life clinical setting in DAE. Conclusion: To the best of our knowledge, this is the first study regarding the automatic multi-brand panendoscopic detection of ulcers and erosions throughout the digestive tract during DAE, overcoming a relevant interoperability challenge. Our results highlight that using a CNN to detect this type of lesion is associated with high overall accuracy. The development of binary CNN for automatically detecting clinically relevant endoscopic findings and assessing endoscopic inflammatory activity are relevant steps toward AI application in digestive endoscopy, particularly for panendoscopic evaluation.

Extent of use of artificial intelligence & machine learning protocols in cancer diagnosis: A scoping review

Background & objectives

Artificial intelligence (AI) and machine learning (ML) have shown promising results in cancer diagnosis in validation tests involving retrospective patient databases. This study was aimed to explore the extent of actual use of AI/ML protocols for diagnosing cancer in prospective settings.

Methods

PubMed was searched for studies reporting usage of AI/ML protocols for cancer diagnosis in prospective (clinical trial/real world) setting with the AI/ML diagnosis aiding clinical decision-making, from inception till May 17, 2021. Data pertaining to the cancer, patients and the AI/ML protocol were extracted. Comparison of AI/ML protocol diagnosis with human diagnosis was recorded. Through a post hoc analysis, data from studies describing validation of various AI/ML protocols were extracted.

Results

Only 18/960 initial hits (1.88%) utilized AI/ML protocols for diagnostic decision-making. Most protocols used artificial neural network and deep learning. AI/ML protocols were utilized for cancer screening, pre-operative diagnosis and staging and intra-operative diagnosis of surgical specimens. The reference standard for 17/18 studies was histology. AI/ML protocols were used to diagnose cancers of the colorectum, skin, uterine cervix, oral cavity, ovaries, prostate, lungs and brain. AI/ML protocols were found to improve human diagnosis, and had either similar or better performance than the human diagnosis, especially made by the less experienced clinician. Validation of AI/ML protocols was described by 223 studies of which only four studies were from India. Also there was a huge variation in the number of items used for validation.

Interpretation & conclusions

The findings of this review suggest that a meaningful translation from the validation of AI/ML protocols to their actual usage in cancer diagnosis is lacking. Development of regulatory framework specific for AI/ML usage in healthcare is essential.

Risk of Metachronous Advanced Colorectal Neoplasia After Removal of Diminutive Versus Small Nonadvanced Adenomas: A Multicenter Study

BACKGROUND

Current postpolypectomy guidelines treat 1-9 mm nonadvanced adenomas (NAAs) as carrying the same level of risk for metachronous advanced colorectal neoplasia (ACRN).

AIMS

To evaluate whether small (6-9 mm) NAAs are associated with a greater risk of metachronous ACRN than diminutive (1-5 mm) NAAs.

METHODS

We retrospectively evaluated 10,060 index colonoscopies performed from July 2011 to June 2019. A total of 1369 patients aged ≥ 40 years with index NAAs and having follow-up examinations were categorized into 5 groups based on size and number of index findings: Group 1, ≤ 2 diminutive NAAs (n = 655); Group 2, ≤ 2 small NAAs (n = 529); Group 3, 3-4 diminutive NAAs (n = 78); Group 4, 3-4 small NAAs (n = 65); and Group 5, 5-10 NAAs (n = 42). Size was classified based on the largest NAA. ACRN was defined as finding an advanced adenoma or colorectal cancer at follow-up.

RESULTS

The absolute risk of metachronous ACRN increased from 7.2% in patients with all diminutive NAAs to 12.2% in patients with at least 1 small NAA (P = 0.002). Patients in Group 2 (adjusted odds ratio [AOR] 1.89; 95% confidence interval [CI], 1.21-2.95), Group 3 (AOR 2.40; 95% CI 1.78-4.90), Group 4 (AOR 2.77; 95% CI 1.35-5.66), and Group 5 (AOR 3.71; 95% CI 1.65-8.37) were associated with an increased risk of metachronous ACRN compared with Group 1.

CONCLUSIONS

Patients with small NAAs have an increased risk of metachronous ACRN. Postpolypectomy guidelines should consider including risk stratification between small and diminutive adenomas.

Artificial intelligence in gastroenterology: A narrative review

Artificial intelligence (AI) is a complex concept, broadly defined in medicine as the development of computer systems to perform tasks that require human intelligence. It has the capacity to revolutionize medicine by increasing efficiency, expediting data and image analysis and identifying patterns, trends and associations in large datasets. Within gastroenterology, recent research efforts have focused on using AI in esophagogastroduodenoscopy, wireless capsule endoscopy (WCE) and colonoscopy to assist in diagnosis, disease monitoring, lesion detection and therapeutic intervention. The main objective of this narrative review is to provide a comprehensive overview of the research being performed within gastroenterology on AI in esophagogastroduodenoscopy, WCE and colonoscopy.

Mucosal imaging in colon polyps: New advances and what the future may hold

An expanding range of advanced mucosal imaging technologies have been developed with the goal of improving the detection and characterization of lesions in the gastrointestinal tract. Many technologies have targeted colorectal neoplasia given the potential for intervention prior to the development of invasive cancer in the setting of widespread surveillance programs. Improvement in adenoma detection reduces miss rates and prevents interval cancer development. Advanced imaging technologies aim to enhance detection without significantly increasing procedural time. Accurate polyp characterisation guides resection techniques for larger polyps, as well as providing the platform for the “resect and discard” and “do not resect” strategies for small and diminutive polyps. This review aims to collate and summarise the evidence regarding these technologies to guide colonoscopic practice in both interventional and non-interventional endoscopists.

An interpretable artificial intelligence system for detecting risk factors of gastroesophageal variceal bleeding

Bleeding risk factors for gastroesophageal varices (GEV) detected by endoscopy in cirrhotic patients determine the prophylactical treatment patients will undergo in the following 2 years. We propose a methodology for measuring the risk factors. We create an artificial intelligence system (ENDOANGEL-GEV) containing six models to segment GEV and to classify the grades (grades 1-3) and red color signs (RC, RC0-RC3) of varices. It also summarizes changes in the above results with region in real time. ENDOANGEL-GEV is trained using 6034 images from 1156 cirrhotic patients across three hospitals (dataset 1) and validated on multicenter datasets with 11009 images from 141 videos (dataset 2) and in a prospective study recruiting 161 cirrhotic patients from Renmin Hospital of Wuhan University (dataset 3). In dataset 1, ENDOANGEL-GEV achieves intersection over union values of 0.8087 for segmenting esophageal varices and 0.8141 for gastric varices. In dataset 2, the system maintains fairly accuracy across images from three hospitals. In dataset 3, ENDOANGEL-GEV surpasses attended endoscopists in detecting RC of GEV and classifying grades (p < 0.001). When ranking the risk of patients combined with the Child‒Pugh score, ENDOANGEL-GEV outperforms endoscopists for esophageal varices (p < 0.001) and shows comparable performance for gastric varices (p = 0.152). Compared with endoscopists, ENDOANGEL-GEV may help 12.31% (16/130) more patients receive the right intervention. We establish an interpretable system for the endoscopic diagnosis and risk stratification of GEV. It will assist in detecting the first bleeding risk factors accurately and expanding the scope of quantitative measurement of diseases.

Evaluation of a real-time computer-aided polyp detection system during screening colonoscopy: AI-DETECT study

BACKGROUND

Polyp detection and resection during colonoscopy significantly reduce long-term colorectal cancer risk. Computer-aided detection (CADe) may increase polyp identification but has undergone limited clinical evaluation. Our aim was to assess the effectiveness of CADe at colonoscopy within a bowel cancer screening program (BCSP).

METHODS

This prospective, randomized controlled trial involved all eight screening-accredited colonoscopists at an English National Health Service (NHS) BCSP center (February 2020 to December 2021). Patients were randomized to CADe or standard colonoscopy. Patients meeting NHS criteria for bowel cancer screening were included. The primary outcome of interest was polyp detection rate (PDR).

RESULTS

658 patients were invited and 44 were excluded. A total of 614 patients were randomized to CADe (n = 308) or standard colonoscopy (n = 306); 35 cases were excluded from the per-protocol analysis due to poor bowel preparation (n = 10), an incomplete procedure (n = 24), or a data issue (n = 1). Endocuff Vision was frequently used and evenly distributed (71.7 % CADe and 69.2 % standard). On intention-to-treat (ITT) analysis, there was a borderline significant difference in PDR (85.7 % vs. 79.7 %; P = 0.05) but no significant difference in adenoma detection rate (ADR; 71.4 % vs. 65.0 %; P = 0.09) for CADe vs. standard groups, respectively. On per-protocol analysis, no significant difference was observed in these rates. There was no significant difference in procedure times.

CONCLUSIONS

In high-performing colonoscopists in a BCSP who routinely used Endocuff Vision, CADe improved PDR but not ADR. CADe appeared to have limited benefit in a BCSP setting where procedures are performed by experienced colonoscopists.

Artificial Intelligence and Advanced Melanoma: Treatment Management Implications

Artificial intelligence (AI), a field of research in which computers are applied to mimic humans, is continuously expanding and influencing many aspects of our lives. From electric cars to search motors, AI helps us manage our daily lives by simplifying functions and activities that would be more complex otherwise. Even in the medical field, and specifically in oncology, many studies in recent years have highlighted the possible helping role that AI could play in clinical and therapeutic patient management. In specific contexts, clinical decisions are supported by "intelligent" machines and the development of specific softwares that assist the specialist in the management of the oncology patient. Melanoma, a highly heterogeneous disease influenced by several genetic and environmental factors, to date is still difficult to manage clinically in its advanced stages. Therapies often fail, due to the establishment of intrinsic or secondary resistance, making clinical decisions complex. In this sense, although much work still needs to be conducted, numerous evidence shows that AI (through the processing of large available data) could positively influence the management of the patient with advanced melanoma, helping the clinician in the most favorable therapeutic choice and avoiding unnecessary treatments that are sure to fail. In this review, the most recent applications of AI in melanoma will be described, focusing especially on the possible finding of this field in the management of drug treatments.

Artificial intelligence and colon capsule endoscopy: Automatic detection of ulcers and erosions using a convolutional neural network

BACKGROUND AND AIM

Colon capsule endoscopy (CCE) has become a minimally invasive alternative for conventional colonoscopy. Nevertheless, each CCE exam produces between 50 000 and 100 000 frames, making its analysis time-consuming and prone to errors. Convolutional neural networks (CNNs) are a type of artificial intelligence (AI) architecture with high performance in image analysis. This study aims to develop a CNN model for the identification of colonic ulcers and erosions in CCE images.

METHODS

A CNN model was designed using a database of CCE images. A total of 124 CCE exams performed between 2010 and 2020 in two centers were reviewed. For CNN development, a total of 37 319 images were extracted, 33 749 showing normal colonic mucosa and 3570 showing colonic ulcers and erosions. Datasets for CNN training, validation, and testing were created. The performance of the algorithm was evaluated regarding its sensitivity, specificity, positive and negative predictive values, accuracy, and area under the curve.

RESULTS

The network had a sensitivity of 96.9% and a specificity of 99.9% specific for the detection of colonic ulcers and erosions. The algorithm had an overall accuracy of 99.6%. The area under the curve was 1.00. The CNN had an image processing capacity of 90 frames per second.

CONCLUSIONS

The developed algorithm is the first CNN-based model to accurately detect ulcers and erosions in CCE images, also providing a good image processing performance. The development of these AI systems may contribute to improve both the diagnostic and time efficiency of CCE exams, facilitating CCE adoption to routine clinical practice.

Efficacy of a computer-aided detection system in a fecal immunochemical test-based organized colorectal cancer screening program: a randomized controlled trial (AIFIT study)

BACKGROUND

Computer-aided detection (CADe) increases adenoma detection in primary screening colonoscopy. The potential benefit of CADe in a fecal immunochemical test (FIT)-based colorectal cancer (CRC) screening program is unknown. This study assessed whether use of CADe increases the adenoma detection rate (ADR) in a FIT-based CRC screening program.

METHODS

In a multicenter, randomized trial, FIT-positive individuals aged 50-74 years undergoing colonoscopy, were randomized (1:1) to receive high definition white-light (HDWL) colonoscopy, with or without a real-time deep-learning CADe by endoscopists with baseline ADR > 25 %. The primary outcome was ADR. Secondary outcomes were mean number of adenomas per colonoscopy (APC) and advanced adenoma detection rate (advanced-ADR). Subgroup analysis according to baseline endoscopists' ADR (≤ 40 %, 41 %-45 %, ≥ 46 %) was also performed.

RESULTS

800 individuals (median age 61.0 years [interquartile range 55-67]; 409 men) were included: 405 underwent CADe-assisted colonoscopy and 395 underwent HDWL colonoscopy alone. ADR and APC were significantly higher in the CADe group than in the HDWL arm: ADR 53.6 % (95 %CI 48.6 %-58.5 %) vs. 45.3 % (95 %CI 40.3 %-50.45 %; RR 1.18; 95 %CI 1.03-1.36); APC 1.13 (SD 1.54) vs. 0.90 (SD 1.32; P  = 0.03). No significant difference in advanced-ADR was found (18.5 % [95 %CI 14.8 %-22.6 %] vs. 15.9 % [95 %CI 12.5 %-19.9 %], respectively). An increase in ADR was observed in all endoscopist groups regardless of baseline ADR.

CONCLUSIONS

Incorporating CADe significantly increased ADR and APC in the framework of a FIT-based CRC screening program. The impact of CADe appeared to be consistent regardless of endoscopist baseline ADR.

Expected value of artificial intelligence in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement

This ESGE Position Statement defines the expected value of artificial intelligence (AI) for the diagnosis and management of gastrointestinal neoplasia within the framework of the performance measures already defined by ESGE. This is based on the clinical relevance of the expected task and the preliminary evidence regarding artificial intelligence in artificial or clinical settings. MAIN RECOMMENDATIONS:: (1) For acceptance of AI in assessment of completeness of upper GI endoscopy, the adequate level of mucosal inspection with AI should be comparable to that assessed by experienced endoscopists. (2) For acceptance of AI in assessment of completeness of upper GI endoscopy, automated recognition and photodocumentation of relevant anatomical landmarks should be obtained in ≥90% of the procedures. (3) For acceptance of AI in the detection of Barrett's high grade intraepithelial neoplasia or cancer, the AI-assisted detection rate for suspicious lesions for targeted biopsies should be comparable to that of experienced endoscopists with or without advanced imaging techniques. (4) For acceptance of AI in the management of Barrett's neoplasia, AI-assisted selection of lesions amenable to endoscopic resection should be comparable to that of experienced endoscopists. (5) For acceptance of AI in the diagnosis of gastric precancerous conditions, AI-assisted diagnosis of atrophy and intestinal metaplasia should be comparable to that provided by the established biopsy protocol, including the estimation of extent, and consequent allocation to the correct endoscopic surveillance interval. (6) For acceptance of artificial intelligence for automated lesion detection in small-bowel capsule endoscopy (SBCE), the performance of AI-assisted reading should be comparable to that of experienced endoscopists for lesion detection, without increasing but possibly reducing the reading time of the operator. (7) For acceptance of AI in the detection of colorectal polyps, the AI-assisted adenoma detection rate should be comparable to that of experienced endoscopists. (8) For acceptance of AI optical diagnosis (computer-aided diagnosis [CADx]) of diminutive polyps (≤5 mm), AI-assisted characterization should match performance standards for implementing resect-and-discard and diagnose-and-leave strategies. (9) For acceptance of AI in the management of polyps ≥ 6 mm, AI-assisted characterization should be comparable to that of experienced endoscopists in selecting lesions amenable to endoscopic resection.

The optimal use of colon capsule endoscopes in clinical practice

Colon capsule endoscopy (CCE) has been available for nearly two decades but has grappled with being an equal diagnostic alternative to optical colonoscopy (OC). Due to the COVID-19 pandemic, CCE has gained more foothold in clinical practice. In this cutting-edge review, we aim to present the existing knowledge on the pros and cons of CCE and discuss whether the modality is ready for a larger roll-out in clinical settings. We have included clinical trials and reviews with the most significant impact on the current position of CCE in clinical practice and discuss the challenges that persist and how they could be addressed to make CCE a more sustainable imaging modality with an adenoma detection rate equal to OC and a low re-investigation rate by a proper preselection of suitable populations. CCE is embedded with a very low risk of severe complications and can be performed in the patient's home as a pain-free procedure. The diagnostic accuracy is found to be equal to OC. However, a significant drawback is low completion rates eliciting a high re-investigation rate. Furthermore, the bowel preparation before CCE is extensive due to the high demand for clean mucosa. CCE is currently not suitable for large-scale implementation in clinical practice mainly due to high re-investigation rates. By a better preselection before CCE and the implantation of artificial intelligence for picture and video analysis, CCE could be the alternative to OC needed to move away from in-hospital services and relieve long-waiting lists for OC.

Effects of ai-assisted colonoscopy on adenoma miss rate/adenoma detection rate: A protocol for systematic review and meta-analysis

BACKGROUND

Colonoscopy can detect colorectal adenomas and reduce the incidence of colorectal cancer, but there are still many missing diagnoses. Artificial intelligence-assisted colonoscopy (AIAC) can effectively reduce the rate of missed diagnosis and improve the detection rate of adenoma, but its clinical application is still unclear. This systematic review and meta-analysis assessed the adenoma missed detection rate (AMR) and the adenoma detection rate (ADR) by artificial colonoscopy.

METHODS

Conduct a comprehensive literature search using the PubMed, Medline database, Embase, and the Cochrane Library. This meta-analysis followed the direction of the preferred reporting items for systematic reviews and meta-analyses, the preferred reporting item for systematic review and meta-analysis. The random effect model was used for meta-analysis.

RESULTS

A total of 12 articles were eventually included in the study. Computer aided detection (CADe) significantly decreased AMR compared with the control group (137/1039, 13.2% vs 304/1054, 28.8%; OR,0.39; 95% CI, 0.26-0.59; P < .05). Similarly, there was statistically significant difference in ADR between the CADe group and control group, respectively (1835/5041, 36.4% vs 1309/4553, 28.7%; OR, 1.54; 95% CI, 1.39-1.71; P < .05). The advanced adenomas missed rate and detection rate in CADe group was not statistically significant when compared with the control group.

CONCLUSIONS

AIAC can effectively reduce AMR and improve ADR, especially small adenomas. Therefore, this method is worthy of clinical application. However, due to the limitations of the number and quality of the included studies, more in-depth studies are needed in the field of AIAC in the future.

Reduced detection rate of artificial intelligence in images obtained from untrained endoscope models and improvement using domain adaptation algorithm

A training dataset that is limited to a specific endoscope model can overfit artificial intelligence (AI) to its unique image characteristics. The performance of the AI may degrade in images of different endoscope model. The domain adaptation algorithm, i.e., the cycle-consistent adversarial network (cycleGAN), can transform the image characteristics into AI-friendly styles. We attempted to confirm the performance degradation of AIs in images of various endoscope models and aimed to improve them using cycleGAN transformation. Two AI models were developed from data of esophagogastroduodenoscopies collected retrospectively over 5 years: one for identifying the endoscope models, Olympus CV-260SL, CV-290 (Olympus, Tokyo, Japan), and PENTAX EPK-i (PENTAX Medical, Tokyo, Japan), and the other for recognizing the esophagogastric junction (EGJ). The AIs were trained using 45,683 standardized images from 1,498 cases and validated on 624 separate cases. Between the two endoscope manufacturers, there was a difference in image characteristics that could be distinguished without error by AI. The accuracy of the AI in recognizing gastroesophageal junction was >0.979 in the same endoscope-examined validation dataset as the training dataset. However, they deteriorated in datasets from different endoscopes. Cycle-consistent adversarial network can successfully convert image characteristics to ameliorate the AI performance. The improvements were statistically significant and greater in datasets from different endoscope manufacturers [original → AI-trained style, increased area under the receiver operating characteristic (ROC) curve, P-value: CV-260SL → CV-290, 0.0056, P = 0.0106; CV-260SL → EPK-i, 0.0182, P = 0.0158; CV-290 → CV-260SL, 0.0134, P < 0.0001; CV-290 → EPK-i, 0.0299, P = 0.0001; EPK-i → CV-260SL, 0.0215, P = 0.0024; and EPK-i → CV-290, 0.0616, P < 0.0001]. In conclusion, cycleGAN can transform the diverse image characteristics of endoscope models into an AI-trained style to improve the detection performance of AI.

A video based benchmark data set (ENDOTEST) to evaluate computer-aided polyp detection systems

BACKGROUND AND AIMS

Computer-aided polyp detection (CADe) may become a standard for polyp detection during colonoscopy. Several systems are already commercially available. We report on a video-based benchmark technique for the first preclinical assessment of such systems before comparative randomized trials are to be undertaken. Additionally, we compare a commercially available CADe system with our newly developed one.

METHODS

ENDOTEST consisted in the combination of two datasets. The validation dataset contained 48 video-snippets with 22,856 manually annotated images of which 53.2% contained polyps. The performance dataset contained 10 full-length screening colonoscopies with 230,898 manually annotated images of which 15.8% contained a polyp. Assessment parameters were accuracy for polyp detection and time delay to first polyp detection after polyp appearance (FDT). Two CADe systems were assessed: a commercial CADe system (GI-Genius, Medtronic), and a self-developed new system (ENDOMIND). The latter being a convolutional neuronal network trained on 194,983 manually labeled images extracted from colonoscopy videos recorded in mainly six different gastroenterologic practices.

RESULTS

On the ENDOTEST, both CADe systems detected all polyps in at least one image. The per-frame sensitivity and specificity in full colonoscopies was 48.1% and 93.7%, respectively for GI-Genius; and 54% and 92.7%, respectively for ENDOMIND. Median FDT of ENDOMIND with 217 ms (Inter-Quartile Range(IQR)8-1533) was significantly faster than GI-Genius with 1050 ms (IQR 358-2767, p = 0.003).

CONCLUSIONS

Our benchmark ENDOTEST may be helpful for preclinical testing of new CADe devices. There seems to be a correlation between a shorter FDT with a higher sensitivity and a lower specificity for polyp detection.

Polyp detection on video colonoscopy using a hybrid 2D/3D CNN

Colonoscopy is the gold standard for early diagnosis and pre-emptive treatment of colorectal cancer by detecting and removing colonic polyps. Deep learning approaches to polyp detection have shown potential for enhancing polyp detection rates. However, the majority of these systems are developed and evaluated on static images from colonoscopies, whilst in clinical practice the treatment is performed on a real-time video feed. Non-curated video data remains a challenge, as it contains low-quality frames when compared to still, selected images often obtained from diagnostic records. Nevertheless, it also embeds temporal information that can be exploited to increase predictions stability. A hybrid 2D/3D convolutional neural network architecture for polyp segmentation is presented in this paper. The network is used to improve polyp detection by encompassing spatial and temporal correlation of the predictions while preserving real-time detections. Extensive experiments show that the hybrid method outperforms a 2D baseline. The proposed architecture is validated on videos from 46 patients and on the publicly available SUN polyp database. A higher performance and increased generalisability indicate that real-world clinical implementations of automated polyp detection can benefit from the hybrid algorithm and the inclusion of temporal information.

Artificial Intelligence-Aided Colonoscopy Does Not Increase Adenoma Detection Rate in Routine Clinical Practice

The performance of artificial intelligence-aided colonoscopy (AIAC) in a real-world setting has not been described. We compared adenoma and polyp detection rates (ADR/PDR) in a 6-month period before (pre-AIAC) and after introduction of AIAC (GI Genius, Medtronic) in all endoscopy suites in our large-volume center. The ADR and PDR in the AIAC group was lower compared with those in the pre-AIAC group (30.3% vs 35.2%, P < 0.001; 36.5% vs 40.9%, P = 0.004, respectively); procedure time was significantly shorter in the AIAC group. In summary, introduction of AIAC did not result in performance improvement in our large-center cohort, raising important questions on AI-human interactions in medicine.

Artificial Intelligence Allows Leaving-In-Situ Colorectal Polyps

BACKGROUND & AIMS

Artificial Intelligence (AI) could support cost-saving strategies for colonoscopy because of its accuracy in the optical diagnosis of colorectal polyps. However, AI must meet predefined criteria to be implemented in clinical settings.

METHODS

An approved computer-aided diagnosis (CADx) module for differentiating between adenoma and nonadenoma in unmagnified white-light colonoscopy was used in a consecutive series of colonoscopies. For each polyp, CADx output and subsequent endoscopist diagnosis with advanced imaging were matched against the histology gold standard. The primary outcome was the negative predictive value (NPV) of CADx for adenomatous histology for ≤5-mm rectosigmoid lesions. We also calculated the NPV for AI-assisted endoscopist predictions, and agreement between CADx and histology-based postpolypectomy surveillance intervals according to European and American guidelines.

RESULTS

Overall, 544 polyps were removed in 162 patients, of which 295 (54.2%) were ≤5-mm rectosigmoid histologically verified lesions. CADx diagnosis was feasible in 291 of 295 (98.6%), and the NPV for ≤5-mm rectosigmoid lesions was 97.6% (95% CI, 94.1%-99.1%). There were 242 of 295 (82%) lesions that were amenable for a leave-in-situ strategy. Based on CADx output, 212 of 544 (39%) would be amenable to a resect-and-discard strategy, resulting in a 95.6% (95% CI, 90.8%-98.0%) and 95.9% (95% CI, 89.8%-98.4%) agreement between CADx- and histology-based surveillance intervals according to European and American guidelines, respectively. A similar NPV (97.6%; 95% CI, 94.8%-99.1%) for ≤5-mm rectosigmoids was achieved by AI-assisted endoscopists assessing polyps with electronic chromoendoscopy, with a CADx-concordant diagnosis in 97.2% of cases.

CONCLUSIONS

In this study, CADx without advanced imaging exceeded the benchmarks required for optical diagnosis of colorectal polyps. CADx could help implement cost-saving strategies in colonoscopy by reducing the burden of polypectomy and/or pathology.

CLINICALTRIALS

gov registration number: NCT04884581.

Key research questions for implementation of artificial intelligence in capsule endoscopy

BACKGROUND

Artificial intelligence (AI) is rapidly infiltrating multiple areas in medicine, with gastrointestinal endoscopy paving the way in both research and clinical applications. Multiple challenges associated with the incorporation of AI in endoscopy are being addressed in recent consensus documents.

OBJECTIVES

In the current paper, we aimed to map future challenges and areas of research for the incorporation of AI in capsule endoscopy (CE) practice.

DESIGN

Modified three-round Delphi consensus online survey.

METHODS

The study design was based on a modified three-round Delphi consensus online survey distributed to a group of CE and AI experts. Round one aimed to map out key research statements and challenges for the implementation of AI in CE. All queries addressing the same questions were merged into a single issue. The second round aimed to rank all generated questions during round one and to identify the top-ranked statements with the highest total score. Finally, the third round aimed to redistribute and rescore the top-ranked statements.

RESULTS

Twenty-one (16 gastroenterologists and 5 data scientists) experts participated in the survey. In the first round, 48 statements divided into seven themes were generated. After scoring all statements and rescoring the top 12, the question of AI use for identification and grading of small bowel pathologies was scored the highest (mean score 9.15), correlation of AI and human expert reading-second (9.05), and real-life feasibility-third (9.0).

CONCLUSION

In summary, our current study points out a roadmap for future challenges and research areas on our way to fully incorporating AI in CE reading.

Systematic analysis of the test design and performance of AI/ML-based medical devices approved for triage/detection/diagnosis in the USA and Japan

The development of computer-aided detection (CAD) using artificial intelligence (AI) and machine learning (ML) is rapidly evolving. Submission of AI/ML-based CAD devices for regulatory approval requires information about clinical trial design and performance criteria, but the requirements vary between countries. This study compares the requirements for AI/ML-based CAD devices approved by the US Food and Drug Administration (FDA) and the Pharmaceuticals and Medical Devices Agency (PMDA) in Japan. A list of 45 FDA-approved and 12 PMDA-approved AI/ML-based CAD devices was compiled. In the USA, devices classified as computer-aided simple triage were approved based on standalone software testing, whereas devices classified as computer-aided detection/diagnosis were approved based on reader study testing. In Japan, however, there was no clear distinction between evaluation methods according to the category. In the USA, a prospective randomized controlled trial was conducted for AI/ML-based CAD devices used for the detection of colorectal polyps, whereas in Japan, such devices were approved based on standalone software testing. This study indicated that the different viewpoints of AI/ML-based CAD in the two countries influenced the selection of different evaluation methods. This study’s findings may be useful for defining a unified global development and approval standard for AI/ML-based CAD.

Trial protocol for COLO-DETECT: A randomized controlled trial of lesion detection comparing colonoscopy assisted by the GI Genius™ artificial intelligence endoscopy module with standard colonoscopy

AIM

Colorectal cancer is the second commonest cause of cancer death worldwide. Colonoscopy plays a key role in the control of colorectal cancer and, in that regard, maximizing detection (and removal) of pre-cancerous adenomas at colonoscopy is imperative. GI Genius™ (Medtronic Ltd) is a computer-aided detection system that integrates with existing endoscopy systems and improves adenoma detection during colonoscopy. COLO-DETECT aims to assess the clinical and cost effectiveness of GI Genius™ in UK routine colonoscopy practice.

METHODS AND ANALYSIS

Participants will be recruited from patients attending for colonoscopy at National Health Service sites in England, for clinical symptoms, surveillance or within the national Bowel Cancer Screening Programme. Randomization will involve a 1:1 allocation ratio (GI Genius™-assisted colonoscopy:standard colonoscopy) and will be stratified by age category (<60 years, 60-<74 years, ≥74 years), sex, hospital site and indication for colonoscopy. Demographic data, procedural data, histology and post-procedure patient experience and quality of life will be recorded. COLO-DETECT is designed and powered to detect clinically meaningful differences in mean adenomas per procedure and adenoma detection rate between GI Genius™-assisted colonoscopy and standard colonoscopy groups. The study will close when 1828 participants have had a complete colonoscopy. An economic evaluation will be conducted from the perspective of the National Health Service. A patient and public representative is contributing to all stages of the trial. Registered at ClinicalTrials.gov (NCT04723758) and ISRCTN (10451355). WHAT WILL THIS TRIAL ADD TO THE LITERATURE?: COLO-DETECT will be the first multi-centre randomized controlled trial evaluating GI Genius™ in real world colonoscopy practice and will, uniquely, evaluate both clinical and cost effectiveness.

Artificial intelligence in gastrointestinal endoscopy - Evolution to a new era

Artificial intelligence (AI) systems based on machine learning have evolved in the last few years with an increasing applicability in gastrointestinal endoscopy. Thanks to AI, an image (input) can be transformed into a clinical decision (output). Although AI systems have been initially studied to improve detection (CADe) and characterization of colorectal lesions (CADx), other indications are being currently investigated as detection of blind spots, scope guidance, or delineation/measurement of lesions. The objective of these review is to summarize the current evidence on applicability of AI systems in gastrointestinal endoscopy, highlight strengths and limitations of the technology and review regulatory and ethical aspects for its general implementation in gastrointestinal endoscopy.

The role of artificial intelligence based systems for cost optimization in colorectal cancer prevention programs

Colorectal Cancer (CRC) has seen a dramatic increase in incidence globally. In 2019, colorectal cancer accounted for 1.15 million deaths and 24.28 million disability-adjusted life-years (DALYs) worldwide. In India, the annual incidence rates (AARs) for colon cancer was 4.4 per 100,000. There has been a steady rise in the prevalence of CRC in India which may be attributed to urbanization, mass migration of population, westernization of diet and lifestyle practices and a rise of obesity and metabolic risk factors that place the population at a higher risk of CRC. Moreoever, CRC in India differs from that described in the Western countries, with a higher proportion of young patients and more patients presenting with an advanced stage. This may be due to poor access to specialized healthcare and socio-economic factors. Early identification of adenomatous colonic polyps, which are well-recognized pre-cancerous lesions, at the time of screening colonoscopy has been shown to be the most effective measure used for CRC prevention. However, colonic polyps are frequently missed during colonoscopy and moreover, these screening programs necessitate man-power, time and resources for processing resected polyps, that may hamper penetration and efficacy in mid- to low-income countries. In the last decade, there has been significant progress made in the automatic detection of colonic polyps by multiple AI-based systems. With the advent of better AI methodology, the focus has shifted from mere detection to accurate discrimination and diagnosis of colonic polyps. These systems, once validated, could usher in a new era in Colorectal Cancer (CRC) prevention programs which would center around “Leave in-situ” and “Resect and discard” strategies. These new strategies hinge around the specificity and accuracy of AI based systems in correctly identifying the pathological diagnosis of the polyps, thereby providing the endoscopist with real-time information in order to make a clinical decision of either leaving the lesion in-situ (mucosal polyps) or resecting and discarding the polyp (hyperplastic polyps). The major advantage of employing these strategies would be in cost optimization of CRC prevention programs while ensuring good clinical outcomes. The adoption of these AI-based systems in the national cancer prevention program of India in accordance with the mandate to increase technology integration could prove to be cost-effective and enable implementation of CRC prevention programs at the population level. This level of penetration could potentially reduce the incidence of CRC and improve patient survival by enabling early diagnosis and treatment. In this review, we will highlight key advancements made in the field of AI in the identification of polyps during colonoscopy and explore the role of AI based systems in cost optimization during the universal implementation of CRC prevention programs in the context of mid-income countries like India.

Future of Endoscopy in Inflammatory Bowel Diseases (IBDs)

Gastrointestinal (GI) endoscopy has transformed over the years in scope, safety, accuracy, acceptability, and cost effectiveness of the clinical practice. There has been a reduction in the superiority of the endoscopic devices as innovations have taken place and increased the diagnostic values with certain limitations. There are particular difficulties in striking a balance between the development of new technology and the device's acceptance. The wide use of endoscopy for investigating GI lesions and diagnosis has led to an increase in more advanced methods and their broad application. It can simultaneously diagnose pre-malignant and malignant lesions, and newer interventions have made the biopsy specimen uptake possible. In this review article, we focus on the more recent roles, indications, applications, and usage of the innovative methods of endoscopy.

Key factors for improving adenoma detection rate

INTRODUCTION

Colonoscopy is a fundamental tool in colorectal cancer (CRC) prevention. Nevertheless, one-fourth of colorectal neoplasms are still missed during colonoscopy, potentially being the main reason for post-colonoscopy colorectal cancer (PCCRC). Adenoma detection rate (ADR) is currently known as the best quality indicator correlating with PCCRC incidence.

AREAS COVERED

We performed a literature review in order to summarize evidences investigating key factors affecting ADR: endoscopists education and training, patient management, endoscopic techniques, improved navigation (exposition defect), and enhanced lesions recognition (vision defect) were considered.

EXPERT OPINION

'Traditional' factors, such as split dose bowel preparation, adequate withdrawal time, and right colon second view, held a significant impact on ADR. Several devices and technologies have been developed to promote high-quality colonoscopy, however artificial intelligence may be considered the most promising tool for ADR improvement, provided that endoscopists education and recording are guaranteed.

Randomized Clinical Trials of Machine Learning Interventions in Health Care: A Systematic Review

IMPORTANCE

Despite the potential of machine learning to improve multiple aspects of patient care, barriers to clinical adoption remain. Randomized clinical trials (RCTs) are often a prerequisite to large-scale clinical adoption of an intervention, and important questions remain regarding how machine learning interventions are being incorporated into clinical trials in health care.

OBJECTIVE

To systematically examine the design, reporting standards, risk of bias, and inclusivity of RCTs for medical machine learning interventions.

EVIDENCE REVIEW

In this systematic review, the Cochrane Library, Google Scholar, Ovid Embase, Ovid MEDLINE, PubMed, Scopus, and Web of Science Core Collection online databases were searched and citation chasing was done to find relevant articles published from the inception of each database to October 15, 2021. Search terms for machine learning, clinical decision-making, and RCTs were used. Exclusion criteria included implementation of a non-RCT design, absence of original data, and evaluation of nonclinical interventions. Data were extracted from published articles. Trial characteristics, including primary intervention, demographics, adherence to the CONSORT-AI reporting guideline, and Cochrane risk of bias were analyzed.

FINDINGS

Literature search yielded 19 737 articles, of which 41 RCTs involved a median of 294 participants (range, 17-2488 participants). A total of 16 RCTS (39%) were published in 2021, 21 (51%) were conducted at single sites, and 15 (37%) involved endoscopy. No trials adhered to all CONSORT-AI standards. Common reasons for nonadherence were not assessing poor-quality or unavailable input data (38 trials [93%]), not analyzing performance errors (38 [93%]), and not including a statement regarding code or algorithm availability (37 [90%]). Overall risk of bias was high in 7 trials (17%). Of 11 trials (27%) that reported race and ethnicity data, the median proportion of participants from underrepresented minority groups was 21% (range, 0%-51%).

CONCLUSIONS AND RELEVANCE

This systematic review found that despite the large number of medical machine learning-based algorithms in development, few RCTs for these technologies have been conducted. Among published RCTs, there was high variability in adherence to reporting standards and risk of bias and a lack of participants from underrepresented minority groups. These findings merit attention and should be considered in future RCT design and reporting.

Artificial intelligence in gastroenterology and hepatology: how to advance clinical practice while ensuring health equity

Artificial intelligence (AI) and machine learning (ML) systems are increasingly used in medicine to improve clinical decision-making and healthcare delivery. In gastroenterology and hepatology, studies have explored a myriad of opportunities for AI/ML applications which are already making the transition to bedside. Despite these advances, there is a risk that biases and health inequities can be introduced or exacerbated by these technologies. If unrecognised, these technologies could generate or worsen systematic racial, ethnic and sex disparities when deployed on a large scale. There are several mechanisms through which AI/ML could contribute to health inequities in gastroenterology and hepatology, including diagnosis of oesophageal cancer, management of inflammatory bowel disease (IBD), liver transplantation, colorectal cancer screening and many others. This review adapts a framework for ethical AI/ML development and application to gastroenterology and hepatology such that clinical practice is advanced while minimising bias and optimising health equity.