Artificial intelligence-based measurement outperforms current methods for colorectal polyp size measurement

Effect of an online educational module incorporating real-time feedback on accuracy of polyp sizing in trainees: a randomized controlled trial

BACKGROUND

Although polyp size dictates surveillance intervals, endoscopists often estimate polyp size inaccurately. We hypothesized that an intervention providing didactic instruction and real-time feedback could significantly improve polyp size classification.

METHODS

We conducted a multicenter randomized controlled trial to evaluate the impact of different components of an online educational module on polyp sizing. Participants were randomized to control (no video, no feedback), video only, feedback only, or video + feedback. The primary outcome was accuracy of polyp size classification into clinically relevant categories (diminutive [1-5mm], small [6-9mm], large [≥10mm]). Secondary outcomes included accuracy of exact polyp size (inmm), learning curves, and directionality of inaccuracy (over- vs. underestimation).

RESULTS

36 trainees from five training programs provided 1360 polyp size assessments. The feedback only (80.1%, P=0.01) and video + feedback (78.9%, P=0.02) groups had higher accuracy of polyp size classification compared with controls (71.6%). There was no significant difference in accuracy between the video only group (74.4%) and controls (P=0.42). Groups receiving feedback had higher accuracy of exact polyp size (inmm) and higher peak learning curves. Polyps were more likely to be overestimated than underestimated, and 29.3% of size inaccuracies impacted recommended surveillance intervals.

CONCLUSIONS

Our online educational module significantly improved polyp size classification. Real-time feedback appeared to be a critical component in improving accuracy. This scalable and no-cost educational module could significantly decrease under- and overutilization of colonoscopy, improving patient outcomes while increasing colonoscopy access.

Enhancing endoscopic measurement: validating a quantitative method for polyp size and location estimation in upper gastrointestinal endoscopy

BACKGROUND

Accurate measurement of polyps size is crucial in predicting malignancy, planning relevant intervention strategies and surveillance schedules. Endoscopists' visual estimations can lack precision. This study builds on our prior research, with the aim to evaluate a recently developed quantitative method to measure the polyp size and location accurately during a simulated endoscopy session.

METHODS

The quantitative method merges information about endoscopic positions obtained from an electromagnetic tracking sensor, with corresponding points on the images of the segmented polyp border. This yields real-scale 3D coordinates of the border of the polyp. By utilising the sensor, positions of any anatomical landmarks are attainable, enabling the estimation of a polyp's location relative to them. To verify the method's reliability and accuracy, simulated endoscopies were conducted in pig stomachs, where polyps were artificially created and assessed in a test-retest manner. The polyp measurements were subsequently compared against clipper measurements.

RESULTS

The average size of the fifteen polyps evaluated was approximately 12 ± 4.3 mm, ranging from 5 to 20 mm. The test-retest reliability, measured by the Intraclass Correlation Coefficient (ICC) for polyp size estimation, demonstrated an absolute agreement of 0.991 (95% CI 0.973-0.997, p < 0.05). Bland & Altman analysis revealed a mean estimation difference of - 0.17 mm (- 2.03%) for polyp size and, a mean difference of - 0.4 mm (- 0.21%) for polyp location. Both differences were statistically non-significant (p > 0.05). When comparing the proposed method with calliper measurements, the Bland & Altman plots showed 95% of size estimation differences between - 1.4 and 1.8 mm (- 13 to 17.4%) which was not significant (p > 0.05).

CONCLUSIONS

The proposed method of measurements of polyp size and location was found to be highly accurate, offering great potential for clinical implementation to improve polyp assessment. This level of performance represents a notable improvement over visual estimation technique used in clinical practice.

As how artificial intelligence is revolutionizing endoscopy

With incessant advances in information technology and its implications in all domains of our lives, artificial intelligence (AI) has emerged as a requirement for improved machine performance. This brings forth the query of how this can benefit endoscopists and improve both diagnostic and therapeutic endoscopy in each part of the gastrointestinal tract. Additionally, it also raises the question of the recent benefits and clinical usefulness of this new technology in daily endoscopic practice. There are two main categories of AI systems: computer-assisted detection (CADe) for lesion detection and computer-assisted diagnosis (CADx) for optical biopsy and lesion characterization. Quality assurance is the next step in the complete monitoring of high-quality colonoscopies. In all cases, computer-aided endoscopy is used, as the overall results rely on the physician. Video capsule endoscopy is a unique example in which a computer operates a device, stores multiple images, and performs an accurate diagnosis. While there are many expectations, we need to standardize and assess various software packages. It is important for healthcare providers to support this new development and make its use an obligation in daily clinical practice. In summary, AI represents a breakthrough in digestive endoscopy. Screening for gastric and colonic cancer detection should be improved, particularly outside expert centers. Prospective and multicenter trials are mandatory before introducing new software into clinical practice.

A real-time deep learning-based system for colorectal polyp size estimation by white-light endoscopy: development and multicenter prospective validation

BACKGROUND

The choice of polypectomy device and surveillance intervals for colorectal polyps are primarily decided by polyp size. We developed a deep learning-based system (ENDOANGEL-CPS) to estimate colorectal polyp size in real time.

METHODS

ENDOANGEL-CPS calculates polyp size by estimating the distance from the endoscope lens to the polyp using the parameters of the lens. The depth estimator network was developed on 7297 images from five virtually produced colon videos and tested on 730 images from seven virtual colon videos. The performance of the system was first evaluated in nine videos of a simulated colon with polyps attached, then tested in 157 real-world prospective videos from three hospitals, with the outcomes compared with that of nine endoscopists over 69 videos. Inappropriate surveillance recommendations caused by incorrect estimation of polyp size were also analyzed.

RESULTS

The relative error of depth estimation was 11.3% (SD 6.0%) in successive virtual colon images. The concordance correlation coefficients (CCCs) between system estimation and ground truth were 0.89 and 0.93 in images of a simulated colon and multicenter videos of 157 polyps. The mean CCC of ENDOANGEL-CPS surpassed all endoscopists (0.89 vs. 0.41 [SD 0.29]; P<0.001). The relative accuracy of ENDOANGEL-CPS was significantly higher than that of endoscopists (89.9% vs. 54.7%; P<0.001). Regarding inappropriate surveillance recommendations, the system's error rate is also lower than that of endoscopists (1.5% vs. 16.6%; P<0.001).

CONCLUSIONS

ENDOANGEL-CPS could potentially improve the accuracy of colorectal polyp size measurements and size-based surveillance intervals.

Endoscopic measurement of the size of gastrointestinal polyps using an electromagnetic tracking system and computer vision-based algorithm

PURPOSE

Polyp size is an important factor that may influence diagnosis and clinical management decision, but estimation by visual inspection during endoscopy is often difficult and subject to error. The purpose of this study is to develop a quantitative approach that enables an accurate and objective measurement of polyp size and to study the feasibility of the method.

METHODS

We attempted to estimate polyp size and location relative to the gastro-oesophageal junction by integrating data from an electromagnetic tracking sensor and endoscopic images. This method is based on estimation of the three-dimensional coordinates of the borders of the polyp by combining the endoscope camera position and the corresponding points along the polyp border in endoscopic images using a computer vision-based algorithm. We evaluated the proposed method using a simulated upper gastrointestinal endoscopy model.

RESULTS

The difference between the mean of ten measurements of one artificial polyp and its actual size (10 mm in diameter) was 0.86 mm. Similarly, the difference between the mean of ten measurements of the polyp distance from the gastroesophageal junction and its actual distance (~ 22 cm) was 1.28 mm. Our results show that the changes in camera positions in which the images were taken and the quality of the polyp segmentation have the most impact on the accuracy of polyp size estimation.

CONCLUSION

This study demonstrated an innovative approach to endoscopic measurements using motion tracking technologies and computer vision and demonstrated its accuracy in determining the size and location of the polyp. The observed magnitude of error is clinically acceptable, and the measurements are available immediately after the images captured. To enhance accuracy, it is recommended to avoid identical images and instead utilise control wheels on the endoscope for capturing different views. Future work should further evaluate this innovative method during clinical endoscopic procedures.

Surveillance after colorectal polyp resection

Post-polypectomy surveillance has proven to reduce colorectal cancer (CRC) incidence in patients with high-risk polyps, but it implies a major burden on colonoscopy units. Therefore, it should be targeted to individuals with a higher risk. Different societies have published guidelines on surveillance after resection of polyps, with notable discrepancies among them, and many recommendations come from low-quality evidence based on surrogate measures, such as risk of advanced adenoma, and not CRC risk. In this review, we aimed to summarize the evidence supporting post-polypectomy surveillance, compare the recently updated major guidelines, and discuss the existing discrepancies on this topic. Briefly, patients with adenomas ≥10 mm or high-grade dysplasia and patients with serrated polyps ≥10 mm or dysplasia are generally considered to have an increased risk of metachronous CRC and require surveillance, whereas the indication of surveillance is not clearly established in patients without these high-risk features.

Artificial intelligence-based polyp size measurement in gastrointestinal endoscopy using the auxiliary waterjet as a reference

BACKGROUND

Measurement of colorectal polyp size during endoscopy is mainly performed visually. In this work, we propose a novel polyp size measurement system (Poseidon) based on artificial intelligence (AI) using the auxiliary waterjet as a measurement reference.

METHODS

Visual estimation, biopsy forceps-based estimation, and Poseidon were compared using a computed tomography colonography-based silicone model with 28 polyps of defined sizes. Four experienced gastroenterologists estimated polyp sizes visually and with biopsy forceps. Furthermore, the gastroenterologists recorded images of each polyp with the waterjet in proximity for the application of Poseidon. Additionally, Poseidon's measurements of 29 colorectal polyps during routine clinical practice were compared with visual estimates.

RESULTS

In the silicone model, visual estimation had the largest median percentage error of 25.1 % (95 %CI 19.1 %-30.4 %), followed by biopsy forceps-based estimation: median 20.0 % (95 %CI 14.4 %-25.6 %). Poseidon gave a significantly lower median percentage error of 7.4 % (95 %CI 5.0 %-9.4 %) compared with other methods. During routine colonoscopies, Poseidon presented a significantly lower median percentage error (7.7 %, 95 %CI 6.1 %-9.3 %) than visual estimation (22.1 %, 95 %CI 15.1 %-26.9 %).

CONCLUSION

In this work, we present a novel AI-based method for measuring colorectal polyp size with significantly higher accuracy than other common sizing methods.

Multi-head deep learning framework for pulmonary disease detection and severity scoring with modified progressive learning

Chest X-rays (CXR) are the most commonly used imaging methodology in radiology to diagnose pulmonary diseases with close to 2 billion CXRs taken every year. The recent upsurge of COVID-19 and its variants accompanied by pneumonia and tuberculosis can be fatal in some cases and lives could be saved through early detection and appropriate intervention for the advanced cases. Thus CXRs can be used for an automated severity grading of pulmonary diseases that can aid radiologists in making better and informed diagnoses. In this article, we propose a single framework for disease classification and severity scoring produced by segmenting the lungs into six regions. We present a modified progressive learning technique in which the amount of augmentations at each step is capped. Our base network in the framework is first trained using modified progressive learning and can then be tweaked for new data sets. Furthermore, the segmentation task makes use of an attention map generated within and by the network itself. This attention mechanism allows to achieve segmentation results that are on par with networks having an order of magnitude or more parameters. We also propose severity score grading for 4 thoracic diseases that can provide a single-digit score corresponding to the spread of opacity in different lung segments with the help of radiologists. The proposed framework is evaluated using the BRAX data set for segmentation and classification into six classes with severity grading for a subset of the classes. On the BRAX validation data set, we achieve F1 scores of 0.924 and 0.939 without and with fine-tuning, respectively. A mean matching score of 80.8% is obtained for severity score grading while an average area under receiver operating characteristic curve of 0.88 is achieved for classification.

Artificial intelligence in digestive endoscopy: recent advances

PURPOSE OF REVIEW

With the incessant advances in information technology and its implications in all domains of our life, artificial intelligence (AI) started to emerge as a need for better machine performance. How it can help endoscopists and what are the areas of interest in improving both diagnostic and therapeutic endoscopy in each part of the gastrointestinal (GI) tract. What are the recent benefits and clinical usefulness of this new technology in daily endoscopic practice.

RECENT FINDINGS

The two main AI systems categories are computer-assisted detection 'CADe' for lesion detection and computer-assisted diagnosis 'CADx' for optical biopsy and lesion characterization. Multiple softwares are now implemented in endoscopy practice. Other AI systems offer therapeutic assistance such as lesion delineation for complete endoscopic resection or prediction of possible lymphanode after endoscopic treatment. Quality assurance is the coming step with complete monitoring of high-quality colonoscopy. In all cases it is a computer-aid endoscopy as the overall result rely on the physician. Video capsule endoscopy is the unique example were the computer conduct the device, store multiple images, and perform accurate diagnosis.

SUMMARY

AI is a breakthrough in digestive endoscopy. Screening gastric and colonic cancer detection should be improved especially outside of expert's centers. Prospective and multicenter trials are mandatory before introducing new software in clinical practice.

Effectiveness and application of artificial intelligence for endoscopic screening of colorectal cancer: the future is now

INTRODUCTION

Artificial intelligence (AI) in gastrointestinal endoscopy includes systems designed to interpret medical images and increase sensitivity during examination. This may be a promising solution to human biases and may provide support during diagnostic endoscopy.

AREAS COVERED

This review aims to summarize and evaluate data supporting AI technologies in lower endoscopy, addressing their effectiveness, limitations, and future perspectives.

EXPERT OPINION

Computer-aided detection (CADe) systems have been studied with promising results, allowing for an increase in adenoma detection rate (ADR), adenoma per colonoscopy (APC), and a reduction in adenoma miss rate (AMR). This may lead to an increase in the sensitivity of endoscopic examinations and a reduction in the risk of interval-colorectal cancer. In addition, computer-aided characterization (CADx) has also been implemented, aiming to distinguish adenomatous and non-adenomatous lesions through real-time assessment using advanced endoscopic imaging techniques. Moreover, computer-aided quality (CADq) systems have been developed with the aim of standardizing quality measures in colonoscopy (e.g. withdrawal time and adequacy of bowel cleansing) both to improve the quality of examinations and set a reference standard for randomized controlled trials.

Artificial Intelligence in Colonoscopy

PURPOSE OF REVIEW

Artificial intelligence (AI) is a rapidly growing field in gastrointestinal endoscopy, and its potential applications are virtually endless, with studies demonstrating use of AI for early gastric cancer, inflammatory bowel disease, Barrett's esophagus, capsule endoscopy, as well as other areas in gastroenterology. Much of the early studies and applications of AI in gastroenterology have revolved around colonoscopy, particularly with regards to real-time polyp detection and characterization. This review will cover much of the existing data on computer-aided detection (CADe), computer-aided diagnosis (CADx), and briefly discuss some other interesting applications of AI for colonoscopy, while also considering some of the challenges and limitations that exist around the use of AI for colonoscopy.

RECENT FINDINGS

Multiple randomized controlled trials have now been published which show a statistically significant improvement when using AI to improve adenoma detection and reduce adenoma miss rates during colonoscopy. There is also a growing pool of literature showing that AI can be helpful for characterizing/diagnosing colorectal polyps in real time. AI has also shown promise in other areas of colonoscopy, including polyp sizing and automated measurement and monitoring of quality metrics during colonoscopy. AI is a promising tool that has the ability to shape the future of gastrointestinal endoscopy, with much of the early data showing significant benefits to use of AI during colonoscopy. However, there remain several challenges that may delay or hamper the widespread use of AI in the field.

Artificial Intelligence Applied to Colonoscopy: Is It Time to Take a Step Forward?

Growing evidence indicates that artificial intelligence (AI) applied to medicine is here to stay. In gastroenterology, AI computer vision applications have been stated as a research priority. The two main AI system categories are computer-aided polyp detection (CADe) and computer-assisted diagnosis (CADx). However, other fields of expansion are those related to colonoscopy quality, such as methods to objectively assess colon cleansing during the colonoscopy, as well as devices to automatically predict and improve bowel cleansing before the examination, predict deep submucosal invasion, obtain a reliable measurement of colorectal polyps and accurately locate colorectal lesions in the colon. Although growing evidence indicates that AI systems could improve some of these quality metrics, there are concerns regarding cost-effectiveness, and large and multicentric randomized studies with strong outcomes, such as post-colonoscopy colorectal cancer incidence and mortality, are lacking. The integration of all these tasks into one quality-improvement device could facilitate the incorporation of AI systems in clinical practice. In this manuscript, the current status of the role of AI in colonoscopy is reviewed, as well as its current applications, drawbacks and areas for improvement.

Comparing size measurement of colorectal polyps using a novel virtual scale endoscope, endoscopic ruler or forceps: A preclinical randomized trial

Background and study aims  Accurate polyp size measurement is important for guideline conforming choice of polypectomy techniques and subsequent surveillance interval assignments. Some endoscopic tools (biopsy forceps [BF] or endoscopic rulers [ER]) exist to help with visual size estimation. A virtual scale endoscope (VSE) has been developed that allows superimposing a virtual measurement scale during live endoscopies. Our aim was to evaluate the performance of VSE when compared to ER and BF-based measurement. Methods  We conducted a preclinical randomized trial to evaluate the relative accuracy of size measurement of simulated colorectal polyps when using: VSE, ER, and BF. Six endoscopists performed 60 measurements randomized at a 1:1:1 ratio using each method. Primary outcome was relative accuracy in polyp size measurement. Secondary outcomes included misclassification of sizes at the 5-, 10-, and 20-mm thresholds. Results  A total of 360 measurements were performed. The relative accuracy of BF, ER, and VSE was 78.9 % (95 %CI = 76.2-81.5), 78.4 % (95 %CI = 76.0-80.8), and 82.7 % (95 %CI = 80.8-84.8). VSE had significantly higher accuracy compared to BF ( P  = 0.02) and ER ( P  = 0.006). VSE misclassified a lower percentage of polyps > 5 mm as ≤ 5 mm (9.4 %) compared to BF (15.7 %) and ER (20.9 %). VSE misclassified a lower percentage of ≥ 20 mm polyps as < 20 mm (8.3 %) compared with BF (66.7 %) and ER (75.0 %). Of polyps ≥10mm, 25.6 %, 25.5 %, and 22.5 % were misclassified as <10 mm with ER, BF, and VSE, respectively. Conclusions  VSE had significantly higher relative accuracy in measuring polyps compared to ER or BF assisted measurement. VSE improves correct classification of polyps at clinically important size thresholds.

Evaluation of the competence of an artificial intelligence-assisted colonoscopy system in clinical practice: A post hoc analysis

Background

Artificial intelligence-assisted colonoscopy (AIAC) has been proposed and validated in recent years, but the effectiveness of clinic application remains unclear since it was only validated in some clinical trials rather than normal conditions. In addition, previous clinical trials were mostly concerned with colorectal polyp identification, while fewer studies are focusing on adenoma identification and polyps size measurement. In this study, we validated the effectiveness of AIAC in the clinical environment and further investigated its capacity for adenoma identification and polyps size measurement.

Methods

The information of 174 continued patients who went for coloscopy in Chongqing Rongchang District People's hospital with detected colon polyps was retrospectively collected, and their coloscopy images were divided into three validation datasets, polyps dataset, polyps/adenomas dataset (all containing narrow band image, NBI images), and polyp size measurement dataset (images with biopsy forceps and polyps) to assess the competence of the artificial intelligence system, and compare its diagnostic ability with endoscopists with different experiences.

Results

A total of 174 patients were included, and the sensitivity of the colorectal polyp recognition model was 99.40%, the accuracy of the colorectal adenoma diagnostic model was 93.06%, which was higher than that of endoscopists, and the mean absolute error of the polyp size measurement model was 0.62 mm and the mean relative error was 10.89%, which was lower than that of endoscopists.

Conclusion

Artificial intelligence-assisted model demonstrated higher competence compared with endoscopists and stable diagnosis ability in clinical use.