Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis

Endoscopic prediction of deeply submucosal invasive carcinoma with use of artificial intelligence

Background and study aims  We evaluated use of artificial intelligence (AI) assisted image classifier in determining the feasibility of curative endoscopic resection of large colonic lesion based on non-magnified endoscopic images Methods  AI image classifier was trained by 8,000 endoscopic images of large (≥ 2 cm) colonic lesions. The independent validation set consisted of 567 endoscopic images from 76 colonic lesions. Histology of the resected specimens was used as gold standard. Curative endoscopic resection was defined as histology no more advanced than well-differentiated adenocarcinoma, ≤ 1 mm submucosal invasion and without lymphovascular invasion, whereas non-curative resection was defined as any lesion that could not meet the above requirements. Performance of the trained AI image classifier was compared with that of endoscopists. Results  In predicting endoscopic curative resection, AI had an overall accuracy of 85.5 %. Images from narrow band imaging (NBI) had significantly higher accuracy (94.3 % vs 76.0 %; P  < 0.00001) and area under the ROC curve (AUROC) (0.934 vs 0.758; P  = 0.002) than images from white light imaging (WLI). AI was superior to two junior endoscopists in terms of accuracy (85.5 % vs 61.9 % or 82.0 %, P  < 0.05), AUROC (0.837 vs 0.638 or 0.717, P  < 0.05) and confidence level (90.1 % vs 83.7 % or 78.3 %, P  < 0.05). However, there was no statistical difference in accuracy and AUROC between AI and a senior endoscopist. Conclusions  The trained AI image classifier based on non-magnified images can accurately predict probability of curative resection of large colonic lesions and is better than junior endoscopists. NBI images have better accuracy than WLI for AI prediction.

Computer-aided diagnosis of colorectal polyps using linked color imaging colonoscopy to predict histology

We developed a computer-aided diagnosis (CAD) system based on linked color imaging (LCI) images to predict the histological results of polyps by analyzing the colors of the lesions. A total of 139 images of adenomatous polyps and 69 images of non-adenomatous polyps obtained from our hospital were collected and used to train the CAD system. A test set of LCI images, including both adenomatous and non-adenomatous polyps, was prospectively collected from patients who underwent colonoscopies between Oct and Dec 2017; this test set was used to assess the diagnostic abilities of the CAD system compared to those of human endoscopists (two experts and two novices). The accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of this novel CAD system for the training set were 87.0%, 87.1%, 87.0%, 93.1%, and 76.9%, respectively. The test set included 115 adenomatous polyps and 66 non-adenomatous polyps that were prospectively collected. The CAD system identified adenomatous or non-adenomatous polyps in the test set with an accuracy of 78.4%, a sensitivity of 83.3%, a specificity of 70.1%, a PPV of 82.6%, and an NPV of 71.2%. The accuracy of the CAD system was comparable to that of the expert endoscopists (78.4% vs 79.6%; p = 0.517). In addition, the diagnostic accuracy of the novices was significantly lower to the performance of the experts (70.7% vs 79.6%; p = 0.018). A novel CAD system based on LCI could be a rapid and powerful decision-making tool for endoscopists.

Early detection and therapeutics

Early detection, including cancer screening and surveillance, is emerging as one of the most important topics in modern oncology. Because symptomatic presentation remains the predominant route to cancer diagnosis, there is a growing interest in developing techniques to detect the disease at an early, curative stage. Moreover, growing understanding of cancer biology has paved the way for prevention studies with the focus on therapeutic interventions for premalignant conditions. Where there is a recognisable precursor stage, such as a colorectal adenoma or Barrett's metaplasia, the removal of abnormal tissue prevents the development of cancer and enables stratification of the patient to a high-risk group requiring further surveillance. Here, we provide a review of the available technologies for early diagnosis and minimally-invasive treatment.

Study on detection rate of polyps and adenomas in artificial-intelligence-aided colonoscopy

BACKGROUND/AIM

To study the impact of computer-aided detection (CADe) system on the detection rate of polyps and adenomas in colonoscopy.

MATERIALS AND METHODS

A total of 1026 patients were prospectively randomly scheduled for colonoscopy with (the CADe group, CADe) or without (the control group, CON) the aid of the CADe system, together with visual notification and voice alarm, so as to compare the detection rate of polyp.

RESULTS

Compared with group CON, the detection rate of adenomas increased in group CADe, the average number of adenomas increased, the number of small adenomas increased, the number of proliferative polyps increased, and the differences were statistically significant (P < 0.001), but the comparison for the number of larger adenomas showed no significant difference between the groups (P> 0.05).

CONCLUSIONS

The CADe system is feasible for increasing the detection of polyps and adenomas in colonoscopy.

Optical Diagnosis of Colorectal Polyps: Recent Developments

PURPOSE OF REVIEW

Optical diagnosis of diminutive colorectal polyps has been recently proposed as an alternative to histopathologic diagnosis. Recent developments in imaging techniques, new classification systems, and the use of artificial intelligence have allowed for increased viability of optical diagnosis. This review provides an up-to-date overview of optical diagnosis recommendations, classifications, outcomes, and recent developments.

RECENT FINDINGS

There are currently seven major classification systems and three major society recommendations for quality benchmarks for optical diagnosis of diminutive polyps. The NICE classification has been extensively studied and meets quality benchmarks for most imaging techniques but does not allow for the diagnosis of sessile serrated polyps (SSPs). The SIMPLE classification has met quality benchmarks for NBI and i-Scan and allows for the diagnosis of SSPs. Other classification systems need to be further studied to validate effectiveness. Computer-assisted diagnosis of colorectal polyps is a very promising recent development with first studies showing that society-recommended quality benchmarks for real-time colonoscopies on patients are being met. Limitations include a non-negligible percentage of failure to diagnose, low specificity, and low number of real-time diagnostic studies. More research needs to be performed to further understand the value of artificial intelligence for optical polyp diagnosis. Optical diagnosis of diminutive colorectal polyps is currently a viable strategy for experienced endoscopists using validated classifications and imaging-enhanced endoscopy. Artificial intelligence-based diagnosis could make optical diagnosis widely applicable but is currently in its early developmental stage.

Application of convolutional neural networks for evaluating Helicobacter pylori infection status on the basis of endoscopic images

BACKGROUND AND AIM

We recently reported the role of artificial intelligence in the diagnosis of Helicobacter pylori (H. pylori) gastritis on the basis of endoscopic images. However, that study included only H. pylori-positive and -negative patients, excluding patients after H. pylori-eradication. In this study, we constructed a convolutional neural network (CNN) and evaluated its ability to ascertain all H. pylori infection statuses.

METHODS

A deep CNN was pre-trained and fine-tuned on a dataset of 98,564 endoscopic images from 5236 patients (742 H. pylori-positive, 3649 -negative, and 845 -eradicated). A separate test data set (23,699 images from 847 patients; 70 positive, 493 negative, and 284 eradicated) was evaluated by the CNN.

RESULTS

The trained CNN outputs a continuous number between 0 and 1 as the probability index for H. pylori infection status per image (Pp, H. pylori-positive; Pn, negative; Pe, eradicated). The most probable (largest number) of the three infectious statuses was selected as the 'CNN diagnosis'. Among 23,699 images, the CNN diagnosed 418 images as positive, 23,034 as negative, and 247 as eradicated. Because of the large number of H. pylori negative findings, the probability of H. pylori-negative was artificially re-defined as Pn -0.9, after which 80% (465/582) of negative diagnoses were accurate, 84% (147/174) eradicated, and 48% (44/91) positive. The time needed to diagnose 23,699 images was 261 seconds.

CONCLUSION

We used a novel algorithm to construct a CNN for diagnosing H. pylori infection status on the basis of endoscopic images very quickly.

ABBREVIATIONS

H. pylori: Helicobacter pylori; CNN: convolutional neural network; AI: artificial intelligence; EGD: esophagogastroduodenoscopies.

Should We Resect and Discard Low Risk Diminutive Colon Polyps

Diminutive colorectal polyps <5 mm are very common and almost universally benign. The current strategy of resection with histological confirmation of all colorectal polyps is costly and may increase the risk of colonoscopy. Accurate, optical diagnosis without histology can be achieved with currently available endoscopic technologies. The American Society of Gastrointestinal Endoscopy Preservation and Incorporation of Valuable endoscopic Innovations supports strategies for optical diagnosis of small non neoplastic polyps as long as two criteria are met. For hyperplastic appearing polyps <5 mm in recto-sigmoid colon, the negative predictive value should be at least 90%. For diminutive low grade adenomatous appearing polyps, a resect and discard strategy should be sufficiently accurate such that post-polypectomy surveillance recommendations based on the optical diagnosis, agree with a histologically diagnosis at least 90% of the time. Although the resect and discard as well as diagnose and leave behind approach has major benefits with regard to both safety and cost, it has yet to be used widely in practice. To fully implement such as strategy, there is a need for better-quality training, quality assurance, and patient acceptance. In the article, we will review the current state of the science on optical diagnose of colorectal polyps and its implications for colonoscopy practice.

Use of image-enhanced endoscopy in the characterization of colorectal polyps: Still some ways to go

BACKGROUND/AIM

Instrument-based image-enhanced endoscopy (IEE) is of benefit in detecting and characterizing lesions during colonoscopy. We aimed to study the ability of community-based gastroenterologists to differentiate between neoplastic and non-neoplastic lesions using IEE modalities and to identify predictors of correct classification and the confidence of the optical diagnosis made.

MATERIALS AND METHODS:

An electronic survey was sent to practicing gastroenterologists using electronic tablets during a gastroenterology meeting. Demographic and professional information was gathered and endoscopic images of various colonic lesions were shown and they were requested to classify the images based in white light, flexible spectral imaging color enhancement (FICE), iScan, and narrow band imaging (NBI).

RESULTS:

Overall, 71 gastroenterologists responded to the survey, 76% were males and the majority were aged between 36 and 45 years (44%). Most of the respondents practiced both hepatology and gastroenterology (56%) and most of them had never received any training on IEE (66%). Correct identification of lesions using regular white light endoscopy was low (range 28%-84%). None of the IEE modalities increased the percentage of correct diagnoses apart from one NBI image where it increased from 28% (95%CI: 17%-38%) to 56% (95%CI: 44%-68%) (P < 0.01). Those who identified themselves as practicing mainly luminal gastroenterology were more confident 72% (95%CI: 60%-84%) compared with hepatologists 36% (95%CI: 25%-48%), or those who practiced both 48% (95%CI: 39%-56%) despite no difference in the percentage in correct answers.

CONCLUSION:

There remain areas of improvement in the performance of endoscopists in practice and would recommend more dedicated training programs, which could make use of asynchronous technological platforms.

A neural network algorithm for detection of GI angiectasia during small-bowel capsule endoscopy

BACKGROUND AND AIMS

GI angiectasia (GIA) is the most common small-bowel (SB) vascular lesion, with an inherent risk of bleeding. SB capsule endoscopy (SB-CE) is the currently accepted diagnostic procedure. The aim of this study was to develop a computer-assisted diagnosis tool for the detection of GIA.

METHODS

Deidentified SB-CE still frames featuring annotated typical GIA and normal control still frames were selected from a database. A semantic segmentation images approach associated with a convolutional neural network (CNN) was used for deep-feature extractions and classification. Two datasets of still frames were created and used for machine learning and for algorithm testing.

RESULTS

The GIA detection algorithm yielded a sensitivity of 100%, a specificity of 96%, a positive predictive value of 96%, and a negative predictive value of 100%. Reproducibility was optimal. The reading process for an entire SB-CE video would take 39 minutes.

CONCLUSIONS

The developed CNN-based algorithm had high diagnostic performances, allowing detection of GIA in SB-CE still frames. This study paves the way for future automated CNN-based SB-CE reading softwares.

Artificial intelligence and computer-aided diagnosis in colonoscopy: current evidence and future directions

Computer-aided diagnosis offers a promising solution to reduce variation in colonoscopy performance. Pooled miss rates for polyps are as high as 22%, and associated interval colorectal cancers after colonoscopy are of concern. Optical biopsy, whereby in-vivo classification of polyps based on enhanced imaging replaces histopathology, has not been incorporated into routine practice because it is limited by interobserver variability and generally only meets accepted standards in expert settings. Real-time decision-support software has been developed to detect and characterise polyps, and also to offer feedback on the technical quality of inspection. Some of the current algorithms, particularly with recent advances in artificial intelligence techniques, match human expert performance for optical biopsy. In this Review, we summarise the evidence for clinical applications of computer-aided diagnosis and artificial intelligence in colonoscopy.

Glioma Grading on Conventional MR Images: A Deep Learning Study With Transfer Learning

Background: Accurate glioma grading before surgery is of the utmost importance in treatment planning and prognosis prediction. But previous studies on magnetic resonance imaging (MRI) images were not effective enough. According to the remarkable performance of convolutional neural network (CNN) in medical domain, we hypothesized that a deep learning algorithm can achieve high accuracy in distinguishing the World Health Organization (WHO) low grade and high grade gliomas.

Methods: One hundred and thirteen glioma patients were retrospectively included. Tumor images were segmented with a rectangular region of interest (ROI), which contained about 80% of the tumor. Then, 20% data were randomly selected and leaved out at patient-level as test dataset. AlexNet and GoogLeNet were both trained from scratch and fine-tuned from models that pre-trained on the large scale natural image database, ImageNet, to magnetic resonance images. The classification task was evaluated with five-fold cross-validation (CV) on patient-level split.

Results: The performance measures, including validation accuracy, test accuracy and test area under curve (AUC), averaged from five-fold CV of GoogLeNet which trained from scratch were 0.867, 0.909, and 0.939, respectively. With transfer learning and fine-tuning, better performances were obtained for both AlexNet and GoogLeNet, especially for AlexNet. Meanwhile, GoogLeNet performed better than AlexNet no matter trained from scratch or learned from pre-trained model.

Conclusion: In conclusion, we demonstrated that the application of CNN, especially trained with transfer learning and fine-tuning, to preoperative glioma grading improves the performance, compared with either the performance of traditional machine learning method based on hand-crafted features, or even the CNNs trained from scratch.

Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy

The detection and removal of precancerous polyps via colonoscopy is the gold standard for the prevention of colon cancer. However, the detection rate of adenomatous polyps can vary significantly among endoscopists. Here, we show that a machine-learning algorithm can detect polyps in clinical colonoscopies, in real time and with high sensitivity and specificity. We developed the deep-learning algorithm by using data from 1,290 patients, and validated it on newly collected 27,113 colonoscopy images from 1,138 patients with at least one detected polyp (per-image-sensitivity, 94.38%; per-image-specificity, 95.92%; area under the receiver operating characteristic curve, 0.984), on a public database of 612 polyp-containing images (per-image-sensitivity, 88.24%), on 138 colonoscopy videos with histologically confirmed polyps (per-image-sensitivity of 91.64%; per-polyp-sensitivity, 100%), and on 54 unaltered full-range colonoscopy videos without polyps (per-image-specificity, 95.40%). By using a multi-threaded processing system, the algorithm can process at least 25 frames per second with a latency of 76.80 ± 5.60 ms in real-time video analysis. The software may aid endoscopists while performing colonoscopies, and help assess differences in polyp and adenoma detection performance among endoscopists.

GTCreator: a flexible annotation tool for image-based datasets

PURPOSE

Methodology evaluation for decision support systems for health is a time-consuming task. To assess performance of polyp detection methods in colonoscopy videos, clinicians have to deal with the annotation of thousands of images. Current existing tools could be improved in terms of flexibility and ease of use.

METHODS

We introduce GTCreator, a flexible annotation tool for providing image and text annotations to image-based datasets. It keeps the main basic functionalities of other similar tools while extending other capabilities such as allowing multiple annotators to work simultaneously on the same task or enhanced dataset browsing and easy annotation transfer aiming to speed up annotation processes in large datasets.

RESULTS

The comparison with other similar tools shows that GTCreator allows to obtain fast and precise annotation of image datasets, being the only one which offers full annotation editing and browsing capabilites.

CONCLUSION

Our proposed annotation tool has been proven to be efficient for large image dataset annotation, as well as showing potential of use in other stages of method evaluation such as experimental setup or results analysis.

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

BACKGROUND

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

OBJECTIVE

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

DESIGN

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

SETTING

University hospital.

PARTICIPANTS

791 consecutive patients undergoing colonoscopy and 23 endoscopists.

INTERVENTION

Real-time use of CAD during colonoscopy.

MEASUREMENTS

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

RESULTS

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

LIMITATION

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

CONCLUSION

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

PRIMARY FUNDING SOURCE

Japan Society for the Promotion of Science.

Connecting Technological Innovation in Artificial Intelligence to Real-world Medical Practice through Rigorous Clinical Validation: What Peer-reviewed Medical Journals Could Do

Artificial intelligence (AI) is projected to substantially influence clinical practice in the foreseeable future. However, despite the excitement around the technologies, it is yet rare to see examples of robust clinical validation of the technologies and, as a result, very few are currently in clinical use. A thorough, systematic validation of AI technologies using adequately designed clinical research studies before their integration into clinical practice is critical to ensure patient benefit and safety while avoiding any inadvertent harms. We would like to suggest several specific points regarding the role that peer-reviewed medical journals can play, in terms of study design, registration, and reporting, to help achieve proper and meaningful clinical validation of AI technologies designed to make medical diagnosis and prediction, focusing on the evaluation of diagnostic accuracy efficacy. Peer-reviewed medical journals can encourage investigators who wish to validate the performance of AI systems for medical diagnosis and prediction to pay closer attention to the factors listed in this article by emphasizing their importance. Thereby, peer-reviewed medical journals can ultimately facilitate translating the technological innovations into real-world practice while securing patient safety and benefit.