Wireless capsule endoscopy

Classification of pediatric video capsule endoscopy images for small bowel abnormalities using deep learning models

BACKGROUND

Video capsule endoscopy (VCE) is a noninvasive technique used to examine small bowel abnormalities in both adults and children. However, manual review of VCE images is time-consuming and labor-intensive, making it crucial to develop deep learning methods to assist in image analysis.

AIM

To employ deep learning models for the automatic classification of small bowel lesions using pediatric VCE images.

METHODS

We retrospectively analyzed VCE images from 162 pediatric patients who underwent VCE between January 2021 and December 2023 at the Children's Hospital of Nanjing Medical University. A total of 2298 high-resolution images were extracted, including normal mucosa and lesions (erosions/erythema, ulcers, and polyps). The images were split into training and test datasets in a 4:1 ratio. Four deep learning models: DenseNet121, Visual geometry group-16, ResNet50, and vision transformer were trained using 5-fold cross-validation, with hyperparameters adjusted for optimal classification performance. The models were evaluated based on accuracy, precision, recall, F1-score, and area under the receiver operating curve (AU-ROC). Lesion visualization was performed using gradient-weighted class activation mapping.

RESULTS

Abdominal pain was the most common indication for VCE, accounting for 62% of cases, followed by diarrhea, vomiting, and gastrointestinal bleeding. Abnormal lesions were detected in 93 children, with 38 diagnosed with inflammatory bowel disease. Among the deep learning models, DenseNet121 and ResNet50 demonstrated excellent classification performance, achieving accuracies of 90.6% [95% confidence interval (CI): 89.2-92.0] and 90.5% (95%CI: 89.9-91.2), respectively. The AU-ROC values for these models were 93.7% (95%CI: 92.9-94.5) for DenseNet121 and 93.4% (95%CI: 93.1-93.8) for ResNet50.

CONCLUSION

Our deep learning-based diagnostic tool developed in this study effectively classified lesions in pediatric VCE images, contributing to more accurate diagnoses and increased diagnostic efficiency.

Development and Validation of a Multi-Task Artificial Intelligence-Assisted System for Small Bowel Capsule Endoscopy

Objective

To develop a multi-task artificial intelligence-assisted system for small bowel capsule endoscopy (SBCE) based on various Transformer neural network architectures. The system integrates lesion recognition, cumulative time statistics, and progress bar marking functions to enhance the efficiency and accuracy of endoscopic image interpretation while effectively reducing missed diagnoses.

Methods

A dataset comprising 12 annotated categories of images captured by three different brands of capsule endoscopy devices was collected. Transfer learning and fine-tuning were conducted on five pre-trained Transformer models. Performance metrics, including accuracy, sensitivity, specificity, and recognition speed, were evaluated to select the best-performing model. The optimal model was converted from PyTorch to Open Neural Network Exchange (ONNX) format. Using OpenCV and MMCV tools, a multi-task SBCE-assisted reading system was developed.

Results

A total of 34,799 images were included in the study. The best-performing model, FocalNet, achieved a weighted average sensitivity of 85.69%, specificity of 98.58%, accuracy of 85.69%, and an AUC of 0.98 across all categories. Its diagnostic accuracy outperformed junior physicians (χ²=17.26, p<0.05) and showed no statistical difference compared to senior physicians (χ²=0.0716, p>0.05). The multi-task AI-assisted reading system, "FocalCE-Master", developed based on FocalNet, achieved a diagnostic speed of 592.40 frames per second, significantly faster than endoscopists. By integrating cumulative time bar charts with progress bar marking functionality, the system enables rapid localization and review of lesions, effectively streamlining the diagnostic workflow of SBCE.

Conclusion

The multi-task SBCE-assisted reading system developed using Transformer networks demonstrated rapid and accurate classification of various small bowel lesions. It holds significant potential in enhancing diagnostic efficiency and image review speed for endoscopists. However, the AI system has not yet been validated in prospective clinical trials, and further real-world studies are needed to confirm its clinical applicability.

Unmet Needs of Artificial Intelligence in Small Bowel Capsule Endoscopy

Small bowel capsule endoscopy (SBCE) has emerged in the past two decades as the cornerstone for assessing small bowel disorders, and its use is supported by several guidelines. However, there are several limitations, such as the considerable time required for gastroenterologists to review these videos and reach a diagnosis. To address these limitations, researchers have explored the integration of artificial intelligence in the interpretation of these videos. In our review, we explore the evolving and emerging role of artificial intelligence in SBCE and examine the latest advancements and ongoing studies in these areas, aiming at overcoming current limitations.

Multivariate Gaussian Bayes classifier with limited data for segmentation of clean and contaminated regions in the small bowel capsule endoscopy images

A considerable amount of undesirable factors in the wireless capsule endoscopy (WCE) procedure hinder the proper visualization of the small bowel and take gastroenterologists more time to review. Objective quantitative assessment of different bowel preparation paradigms and saving the physician reviewing time motivated us to present an automatic low-cost statistical model for automatically segmenting of clean and contaminated regions in the WCE images. In the model construction phase, only 20 manually pixel-labeled images have been used from the normal and reduced mucosal view classes of the Kvasir capsule endoscopy dataset. In addition to calculating prior probability, two different probabilistic tri-variate Gaussian distribution models (GDMs) with unique mean vectors and covariance matrices have been fitted to the concatenated RGB color pixel intensity values of clean and contaminated regions separately. Applying the Bayes rule, the membership probability of every pixel of the input test image to each of the two classes is evaluated. The robustness has been evaluated using 5 trials; in each round, from the total number of 2000 randomly selected images, 20 and 1980 images have been used for model construction and evaluation modes, respectively. Our experimental results indicate that accuracy, precision, specificity, sensitivity, area under the receiver operating characteristic curve (AUROC), dice similarity coefficient (DSC), and intersection over union (IOU) are 0.89 ±  0.07, 0.91 ±  0.07, 0.73 ±  0.20, 0.90 ±  0.12, 0.92 ± 0.06, 0.92 ±  0.05 and 0.86 ±  0.09, respectively. The presented scheme is easy to deploy for objectively assessing small bowel cleansing score, comparing different bowel preparation paradigms, and decreasing the inspection time. The results from the SEE-AI project dataset and CECleanliness database proved that the proposed scheme has good adaptability.

Capsule endoscopy: Do we still need it after 24 years of clinical use?

In this letter, we comment on a recent article published in the World Journal of Gastroenterology by Xiao et al, where the authors aimed to use a deep learning model to automatically detect gastrointestinal lesions during capsule endoscopy (CE). CE was first presented in 2000 and was approved by the Food and Drug Administration in 2001. The indications of CE overlap with those of regular diagnostic endoscopy. However, in clinical practice, CE is usually used to detect lesions in areas inaccessible to standard endoscopies or in cases of bleeding that might be missed during conventional endoscopy. Since the emergence of CE, many physiological and technical challenges have been faced and addressed. In this letter, we summarize the current challenges and briefly mention the proposed methods to overcome these challenges to answer a central question: Do we still need CE?

Toward automated small bowel capsule endoscopy reporting using a summarizing machine learning algorithm: The SUM UP study

BACKGROUND AND OBJECTIVES

Deep learning (DL) algorithms demonstrate excellent diagnostic performance for the detection of vascular lesions via small bowel (SB) capsule endoscopy (CE), including vascular abnormalities with high (P2), intermediate (P1) or low (P0) bleeding potential, while dramatically decreasing the reading time. We aimed to improve the performance of a DL algorithm by characterizing vascular abnormalities using a machine learning (ML) classifier, and selecting the most relevant images for insertion into reports.

MATERIALS AND METHODS

A training dataset of 75 SB CE videos was created, containing 401 sequences of interest that encompassed 1,525 images of various vascular lesions. Several image classification algorithms were tested, to discriminate "typical angiodysplasia" (P2/P1) and "other vascular lesion" (P0) and to select the most relevant image within sequences with repetitive images. The performances of the best-fitting algorithms were subsequently assessed on an independent test dataset of 73 full-length SB CE video recordings.

RESULTS

Following DL detection, a random forest (RF) method demonstrated a specificity of 91.1 %, an area under the receiving operating characteristic curve of 0.873, and an accuracy of 84.2 % for discriminating P2/P1 from P0 lesions while allowing an 83.2 % reduction in the number of reported images. In the independent testing database, after RF was applied, the output number decreased by 91.6 %, from 216 (IQR 108-432) to 12 (IQR 5-33). The RF algorithm achieved 98.0 % agreement with initial, conventional (human) reporting. Following DL detection, the RF method allowed better characterization and accurate selection of images of relevant (P2/P1) SB vascular abnormalities for CE reporting without impairing diagnostic accuracy. These findings pave the way for automated SB CE reporting.

Image detection method for multi-category lesions in wireless capsule endoscopy based on deep learning models

BACKGROUND

Wireless capsule endoscopy (WCE) has become an important noninvasive and portable tool for diagnosing digestive tract diseases and has been propelled by advancements in medical imaging technology. However, the complexity of the digestive tract structure, and the diversity of lesion types, results in different sites and types of lesions distinctly appearing in the images, posing a challenge for the accurate identification of digestive tract diseases.

AIM

To propose a deep learning-based lesion detection model to automatically identify and accurately label digestive tract lesions, thereby improving the diagnostic efficiency of doctors, and creating significant clinical application value.

METHODS

In this paper, we propose a neural network model, WCE_Detection, for the accurate detection and classification of 23 classes of digestive tract lesion images. First, since multicategory lesion images exhibit various shapes and scales, a multidetection head strategy is adopted in the object detection network to increase the model's robustness for multiscale lesion detection. Moreover, a bidirectional feature pyramid network (BiFPN) is introduced, which effectively fuses shallow semantic features by adding skip connections, significantly reducing the detection error rate. On the basis of the above, we utilize the Swin Transformer with its unique self-attention mechanism and hierarchical structure in conjunction with the BiFPN feature fusion technique to enhance the feature representation of multicategory lesion images.

RESULTS

The model constructed in this study achieved an mAP50 of 91.5% for detecting 23 lesions. More than eleven single-category lesions achieved an mAP50 of over 99.4%, and more than twenty lesions had an mAP50 value of over 80%. These results indicate that the model outperforms other state-of-the-art models in the end-to-end integrated detection of human digestive tract lesion images.

CONCLUSION

The deep learning-based object detection network detects multiple digestive tract lesions in WCE images with high accuracy, improving the diagnostic efficiency of doctors, and demonstrating significant clinical application value.

Capsule robots for the monitoring, diagnosis, and treatment of intestinal diseases

Current evidence suggests that the intestine as the new frontier for human health directly impacts both our physical and mental health. Therefore, it is highly desirable to develop the intelligent tool for the enhanced diagnosis and treatment of intestinal diseases. During the past 20 years, capsule robots have opened new avenues for research and clinical applications, potentially revolutionizing human health monitor, disease diagnosis and treatment. In this review, we summarize the research progress of edible multifunctional capsule robots in intestinal diseases. To begin, we introduce the correlation between the intestinal microbiome, intestinal gas and human diseases. After that, we focus on the technical structure of edible multifunctional robots. Subsequently, the biomedical applications in the monitoring, diagnosis and treatment of intestinal diseases are discussed in detail. Last but not least, the main challenges of multifunctional capsule robots during the development process are summarized, followed by a vision for future development opportunities.

The Role of Small-Bowel Endoscopy in the Diagnosis and Management of Small-Bowel Neuroendocrine Tumours

Neuroendocrine tumours (NETs) are relatively rare neoplasms but represent one of the most frequent types of primary small-bowel tumours. Their incidence is rising, and this is most likely because of their more frequent early-stage detection, physician awareness, and increasing availability and use of imaging and small-bowel endoscopic techniques, such as video capsule endoscopy and device-assisted enteroscopy, which enable the detection, localisation, and histological sampling of previously inaccessible and underdiagnosed small-bowel lesions. This review summarises the role of small-bowel endoscopy in the diagnosis and management of small-bowel NETs to assist clinicians in their practice. Small-bowel endoscopy may play a complementary role in the diagnosis of these tumours alongside other diagnostic tests, such as biomarkers, conventional radiology, and functional imaging. In addition, small-bowel enteroscopy may play a role in the preoperative setting for the identification and marking of these tumours for surgical resection and the management of rare complications, such as small-bowel variceal bleeding, in cases of portal hypertension due to the encasement of mesenteric vessels in fibrotic small-bowel NETs.

Magnetic Actuation for Wireless Capsule Endoscopy in a Large Workspace Using a Mobile-Coil System

Current wireless capsule endoscopy (WCE) is limited in the long examination time and low flexibility since the capsule is passively moved by the natural peristalsis. Efforts have been made to facilitate the active locomotion of WCE using magnetic actuation and localization technologies. This work focuses on the motion control of the robotic capsule under magnetic actuation in a complex gastrointestinal (GI) tract environment in order to improve the efficiency and accuracy of its motion in dynamic, complex environments. Specifically, a magnetic actuation system based on a four-electromagnetic coil module is designed, and a control strategy for the system is proposed. In particular, the proportional-integral-derivative (PID) control parameters and current values are optimized online and in real time using the adaptive particle swarm optimization (APSO) algorithm. In this paper, both simulations and real-world experiments were conducted using acrylic plates with irregular shapes to simulate the GI tract environment for evaluation. The results demonstrate the potential of the proposed control methods to realize the accurate and efficient inspection of the intestine using active WCE. The methods presented in this paper can be integrated with current WCE to improve the diagnostic accuracy and efficiency of the GI tract.

Establishing an AI model and application for automated capsule endoscopy recognition based on convolutional neural networks (with video)

BACKGROUND

Although capsule endoscopy (CE) is a crucial tool for diagnosing small bowel diseases, the need to process a vast number of images imposes a significant workload on physicians, leading to a high risk of missed diagnoses. This study aims to develop an artificial intelligence (AI) model and application based on convolutional neural networks that can automatically recognize various lesions in small bowel capsule endoscopy.

METHODS

Three small bowel capsule endoscopy datasets were used for AI model training, validation, and testing, encompassing 12 categories of images. The model's performance was evaluated using metrics such as AUC, sensitivity, specificity, precision, accuracy, and F1 score to select the best model. A human-machine comparison experiment was conducted using the best model and endoscopists with varying levels of experience. Model interpretability was analyzed using Grad-CAM and SHAP techniques. Finally, a clinical application was developed based on the best model using PyQt5 technology.

RESULTS

A total of 34,303 images were included in this study. The best model, MobileNetv3-large, achieved a weighted average sensitivity of 87.17%, specificity of 98.77%, and an AUC of 0.9897 across all categories. The application developed based on this model performed exceptionally well in comparison with endoscopists, achieving an accuracy of 87.17% and a processing speed of 75.04 frames per second, surpassing endoscopists of varying experience levels.

CONCLUSION

The AI model and application developed based on convolutional neural networks can quickly and accurately identify 12 types of small bowel lesions. With its high sensitivity, this system can effectively assist physicians in interpreting small bowel capsule endoscopy images.Future studies will validate the AI system for video evaluations and real-world clinical integration.

Prolonged video capsule endoscopy examination durations can improve capsule endoscopy completeness

BACKGROUND

Capsule endoscopy (CE) is useful for managing patients with suspected small bowel diseases. However, the effect of prolonged CE examination time on CE performance is unknown.

AIM

To evaluate the completeness and diagnostic yield of prolonged CE imaging in patients with suspected small bowel bleeding.

METHODS

We reviewed consecutive records of adult CE examinations via an overnight protocol from Jan 2016 to Dec 2020 at a tertiary center in Taiwan. We subcategorized the CE records by recording length into within 8 h, within 12 h and throughout the whole procedure and compared the completion rate and diagnostic yield between the groups. Cochran's Q test was used for statistical analysis.

RESULTS

A total of 88 patients were enrolled with 78.4% inpatients (median age 72 years). The small bowel evaluation completion rate was 93.2%, which was significantly greater than the 79.5% rate within 12 h (p = 0.025) and the 58% rate within 8 h (p < 0.001). The diagnostic yield was 83% in the whole-course overnight study, which was significantly greater than the 71.6% diagnostic yield within 8 h (p < 0.001) and similar to the 81.8% diagnostic yield within 12 h.

CONCLUSION

Prolonged overnight CE examination can improve the completion rate and diagnostic yield and should be considered for routine clinical practice.

Yield of capsule endoscopy and subsequent device-assisted enteroscopy: experience at an Australian tertiary centre

BACKGROUND

Small bowel capsule endoscopy (SBCE) and device-assisted enteroscopy (DAE) have an established role in the investigation and management of small bowel pathology. Previous studies have reported on the yield of SBCE (60%) and DAE (57%), but none have been in an Australian setting.

AIMS

To determine the yield of SBCE and any DAE performed as a direct consequence of SBCE in an Australian referral centre.

METHODS

A single-centre retrospective study was conducted at a tertiary hospital in Australia, enrolling consecutive patients between 1 January 2009 and 31 December 2021 undergoing SBCE. Data were collected with respect to demographics, procedural factors and findings, as well as findings and interventions of any DAE procedures performed after the SBCE.

RESULTS

1214 SBCEs were performed, with a median age of 66 years old (60.8% men). The predominant indications were anaemia (n = 853, 70.2%) and overt gastrointestinal bleeding (n = 320, 26.4%). Of the complete small bowel studies (1132/1214, 93.2%), abnormal findings were detected in 588 cases (51.9%), most commonly angioectasias (266/588, 45.2%), erosions (106/588, 18.0%) and ulcers (97/588, 8.6%). 165 patients underwent a DAE (117 antegrade, 48 retrograde). Antegrade DAE had a higher yield than retrograde DAE (77.8% vs 54.2%; P = 0.002) and a higher rate of intervention (69.2% vs 37.5%; P < 0.001).

CONCLUSION

In this largest single-centre cohort of patients undergoing SBCE to date, there is a similar yield of abnormal findings compared to existing literature. DAE, especially with an antegrade approach, had high diagnostic and therapeutic yield when pursued after a positive SBCE study.

An efficient computational framework for gastrointestinal disorder prediction using attention-based transfer learning

Diagnosing gastrointestinal (GI) disorders, which affect parts of the digestive system such as the stomach and intestines, can be difficult even for experienced gastroenterologists due to the variety of ways these conditions present. Early diagnosis is critical for successful treatment, but the review process is time-consuming and labor-intensive. Computer-aided diagnostic (CAD) methods provide a solution by automating diagnosis, saving time, reducing workload, and lowering the likelihood of missing critical signs. In recent years, machine learning and deep learning approaches have been used to develop many CAD systems to address this issue. However, existing systems need to be improved for better safety and reliability on larger datasets before they can be used in medical diagnostics. In our study, we developed an effective CAD system for classifying eight types of GI images by combining transfer learning with an attention mechanism. Our experimental results show that ConvNeXt is an effective pre-trained network for feature extraction, and ConvNeXt+Attention (our proposed method) is a robust CAD system that outperforms other cutting-edge approaches. Our proposed method had an area under the receiver operating characteristic curve of 0.9997 and an area under the precision-recall curve of 0.9973, indicating excellent performance. The conclusion regarding the effectiveness of the system was also supported by the values of other evaluation metrics.

Efficacy and safety of three-dimensional magnetically assisted capsule endoscopy for upper gastrointestinal and small bowel examination

BACKGROUND

Magnetically assisted capsule endoscopy (MACE) showed the feasibility for upper gastrointestinal examination. To further enhance the performance of conventional MACE, it is necessary to provide quality-improved and three-dimensional images. The aim of this clinical study was to determine the efficacy and safety of novel three-dimensional MACE (3D MACE) for upper gastrointestinal and small bowel examination at once.

METHODS

This was a prospective, single-center, non-randomized, and sequential examination study (KCT0007114) at Dongguk University Ilsan Hospital. Adult patients who visited for upper endoscopy were included. The study protocol was conducted in two stages. First, upper gastrointestinal examination was performed using 3D MACE, and a continuous small bowel examination was performed by conventional method of capsule endoscopy. Two hours later, an upper endoscopy was performed for comparison with 3D MACE examination. The primary outcome was confirmation of major gastric structures (esophagogastric junction, cardia/fundus, body, angle, antrum, and pylorus). Secondary outcomes were confirmation of esophagus and duodenal bulb, accuracy for gastric lesions, completion of small bowel examination, 3D image reconstruction of gastric lesion, and safety.

RESULTS

Fifty-five patients were finally enrolled. The examination time of 3D MACE was 14.84 ± 3.02 minutes and upper endoscopy was 5.22 ± 2.39 minutes. The confirmation rate of the six major gastric structures was 98.6% in 3D MACE and 100% in upper endoscopy. Gastric lesions were identified in 43 patients during 3D MACE, and 40 patients during upper endoscopy (Sensitivity 0.97). 3D reconstructed images were acquired for all lesions inspected by 3D MACE. The continuous small bowel examination by 3D MACE was completed in 94.5%. 3D MACE showed better overall satisfaction (3D MACE 9.55 ± 0.79 and upper endoscopy 7.75 ± 2.34, p<0.0001). There were no aspiration or significant adverse event or capsule retention in the 3D MACE examination.

CONCLUSIONS

Novel 3D MACE system is more advanced diagnostic modality than the conventional MACE. And it is possible to perform serial upper gastrointestinal and small bowel examination as a non-invasive and one-step test. It would be also served as a bridge to pan-endoscopy.

Obscure Small Bowel Bleeding Related to a Ventral Hernioplasty Mesh Perforation Visualized With Video Capsule Endoscopy

We report a case of a 76-year-old female presenting with intermittent obscure gastrointestinal (GI) bleeding originating from the small intestine secondary to a delayed complication related to mesh hernioplasty. The mesh was eroding into the small bowel causing intermittent transfusion-dependent GI bleeding. Multiple upper and lower endoscopic investigations were sought over the last two years, but they were noncontributory. Finally, video capsule endoscopy (VCE) revealed mesh invasion into the small bowel wall associated with bleeding. This case emphasizes the significance of an early sufficient differential diagnosis in patients with obscure GI bleeding. Meanwhile, being cognizant of rare causes of GI bleeding in patients who have had hernioplasty is very important.

Could Capsule Endoscopy Be Useful in Detection of Suspected Small Bowel Bleeding and IBD-10 Years of Single Center Experience

A retrospective study in patients who underwent video capsule endoscopy (VCE) between 2006 and 2016 was conducted in the Clinic for gastroenterology and Hepatology, University Clinical Center of Serbia. A total of 245 patients underwent VCE. In 198 patients the indication was obscure gastrointestinal bleeding (OGIB), with 92 patients having overt and the other 106 occult bleeding. The remaining 47 patients underwent VCE due to suspected small bowel (SB) disease (i.e., Von Hippel-Lindau syndrome, familial adenomatous polyposis, Peutz Jeghers syndrome, Crohn's disease, prolonged diarrhea, abdominal pain, congenital lymphangiectasia, protein-losing enteropathy, tumors, refractory celiac disease, etc.). VCE identified a source of bleeding in 38.9% of patients (in the obscure overt group in 48.9% of patients, and in the obscure occult group in 30.2% of patients). The most common findings were angiodysplasias, tumors, Meckel's diverticulum and Crohn's disease. In the smaller group of patients with an indication other than OGIB, 38.3% of patients had positive VCE findings. The most common indication is OGIB, and the best candidates are patients with overt bleeding; patients with IBD should be evaluated in this setting.

Development of a multi-fusion convolutional neural network (MF-CNN) for enhanced gastrointestinal disease diagnosis in endoscopy image analysis

Gastrointestinal (GI) diseases are prevalent medical conditions that require accurate and timely diagnosis for effective treatment. To address this, we developed the Multi-Fusion Convolutional Neural Network (MF-CNN), a deep learning framework that strategically integrates and adapts elements from six deep learning models, enhancing feature extraction and classification of GI diseases from endoscopic images. The MF-CNN architecture leverages truncated and partially frozen layers from existing models, augmented with novel components such as Auxiliary Fusing Layers (AuxFL), Fusion Residual Block (FuRB), and Alpha Dropouts (αDO) to improve precision and robustness. This design facilitates the precise identification of conditions such as ulcerative colitis, polyps, esophagitis, and healthy colons. Our methodology involved preprocessing endoscopic images sourced from open databases, including KVASIR and ETIS-Larib Polyp DB, using adaptive histogram equalization (AHE) to enhance their quality. The MF-CNN framework supports detailed feature mapping for improved interpretability of the model's internal workings. An ablation study was conducted to validate the contribution of each component, demonstrating that the integration of AuxFL, αDO, and FuRB played a crucial part in reducing overfitting and efficiency saturation and enhancing overall model performance. The MF-CNN demonstrated outstanding performance in terms of efficacy, achieving an accuracy rate of 99.25%. It also excelled in other key performance metrics with a precision of 99.27%, a recall of 99.25%, and an F1-score of 99.25%. These metrics confirmed the model's proficiency in accurate classification and its capability to minimize false positives and negatives across all tested GI disease categories. Furthermore, the AUC values were exceptional, averaging 1.00 for both test and validation sets, indicating perfect discriminative ability. The findings of the P-R curve analysis and confusion matrix further confirmed the robust classification performance of the MF-CNN. This research introduces a technique for medical imaging that can potentially transform diagnostics in gastrointestinal healthcare facilities worldwide.

Active distance control in multi-capsule endoscopy via closed loop electromagnetic force between capsules

Capsule endoscopy offers a non-invasive and patient-friendly method for imaging the gastrointestinal tract, boasting superior tissue accessibility compared to traditional endoscopy and colonoscopy. While advances have led to capsules capable of drug delivery, tactile sensing, and biopsy, size constraints often limit a single capsule from having multifunctionality. In response, we introduce multi-capsule endoscopy, where individually ingested capsules, each with unique functionalities, work collaboratively. However, synchronized navigation of these capsules is essential for this approach. In this paper, we present an active distance control strategy using a closed-loop system. This entails equipping one capsule with a sphere permanent magnet and the other with a solenoid. We utilized a Simulink model, incorporating (i) the peristalsis motion on the primary capsule, (ii) a PID controller, (iii) force dynamics between capsules through magnetic dipole approximation, and (iv) position tracking of the secondary capsule. For practical implementation, Hall effect sensors determined the inter-capsule distance, and a PID controller adjusted the solenoid's current to maintain the desired capsule spacing. Our proof-of-concept experiments, conducted on phantoms and ex vivo bovine tissues, pulled the leading capsule mimicking a typical human peristalsis speed of 1 cm/min. Results showcased an inter-capsule distance of 1.94 mm ± 0.097 mm for radii of curvature at 500 mm, 250 mm, and 100 mm, aiming for a 2-mm capsule spacing. For ex vivo bovine tissue, the achieved distance was 0.97 ± 0.28 mm against a target inter-capsule distance of 1 mm. Through the successful demonstration of precise inter-capsule control, this study paves the way for the potential of multi-capsule endoscopy in future research.

Deep learning in negative small-bowel capsule endoscopy improves small-bowel lesion detection and diagnostic yield

OBJECTIVES

Although several studies have shown the usefulness of artificial intelligence to identify abnormalities in small-bowel capsule endoscopy (SBCE) images, few studies have proven its actual clinical usefulness. Thus, the aim of this study was to examine whether meaningful findings could be obtained when negative SBCE videos were reanalyzed with a deep convolutional neural network (CNN) model.

METHODS

Clinical data of patients who received SBCE for suspected small-bowel bleeding at two academic hospitals between February 2018 and July 2020 were retrospectively collected. All SBCE videos read as negative were reanalyzed with the CNN algorithm developed in our previous study. Meaningful findings such as angioectasias and ulcers were finally decided after reviewing CNN-selected images by two gastroenterologists.

RESULTS

Among 202 SBCE videos, 103 (51.0%) were read as negative by humans. Meaningful findings were detected in 63 (61.2%) of these 103 videos after reanalyzing them with the CNN model. There were 79 red spots or angioectasias in 40 videos and 66 erosions or ulcers in 35 videos. After reanalysis, the diagnosis was changed for 10 (10.3%) patients who had initially negative SBCE results. During a mean follow-up of 16.5 months, rebleeding occurred in 19 (18.4%) patients. The rebleeding rate was 23.6% (13/55) for patients with meaningful findings and 16.1% (5/31) for patients without meaningful findings (P = 0.411).

CONCLUSION

Our CNN algorithm detected meaningful findings in negative SBCE videos that were missed by humans. The use of deep CNN for SBCE image reading is expected to compensate for human error.

Deep learning and capsule endoscopy: Automatic multi-brand and multi-device panendoscopic detection of vascular lesions

Background and study aims Capsule endoscopy (CE) is commonly used as the initial exam for suspected mid-gastrointestinal bleeding after normal upper and lower endoscopy. Although the assessment of the small bowel is the primary focus of CE, detecting upstream or downstream vascular lesions may also be clinically significant. This study aimed to develop and test a convolutional neural network (CNN)-based model for panendoscopic automatic detection of vascular lesions during CE. Patients and methods A multicentric AI model development study was based on 1022 CE exams. Our group used 34655 frames from seven types of CE devices, of which 11091 were considered to have vascular lesions (angiectasia or varices) after triple validation. We divided data into a training and a validation set, and the latter was used to evaluate the model's performance. At the time of division, all frames from a given patient were assigned to the same dataset. Our primary outcome measures were sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and an area under the precision-recall curve (AUC-PR). Results Sensitivity and specificity were 86.4% and 98.3%, respectively. PPV was 95.2%, while the NPV was 95.0%. Overall accuracy was 95.0%. The AUC-PR value was 0.96. The CNN processed 115 frames per second. Conclusions This is the first proof-of-concept artificial intelligence deep learning model developed for pan-endoscopic automatic detection of vascular lesions during CE. The diagnostic performance of this CNN in multi-brand devices addresses an essential issue of technological interoperability, allowing it to be replicated in multiple technological settings.

A comprehensive examination of small-bowel capsule endoscopy in Spanish centers to meet European Society of Gastrointestinal Endoscopy standards

Background and study aims In 2019, the European Society of Gastrointestinal Endoscopy (ESGE) created a working group to develop technical and quality standards for small-bowel capsule endoscopy (SBCE) to improve the daily practice of endoscopy services. They developed 10 quality parameters, which have yet to be tested in a real-life setting. Our study aimed to evaluate the accomplishment of the quality standards in SBCE established by the ESGE in several Spanish centers. Materials and methods An online survey of 11 multiple-choice questions related to the ESGE performance measures was sent to Spanish centers with experience in SBCE. In order to participate and obtain reliable data, at least 100 questionnaires had to be answered per center because that is the minimum number established by ESGE. Results 20 centers participated in the study, compiling 2049 SBCEs for the analysis. Only one of 10 performance measures (cecal visualization) reached the minimum standard established by the ESGE. In five of 10 performance measures (Indication, lesion detection rate, terminology, and retention rate) the minimum standard was nearly achieved. Conclusions Our study is the first multicenter study regarding SBCE quality performance measures in a real setting. Our results show that the minimum standard is hardly reached in most procedures, which calls into question their clinical applicability in real life. We suggest performing similar studies in other countries to evaluate whether there is a need for quality improvement programs or a need to reevaluate the minimum and target values published so far.

Reading of small bowel capsule endoscopy after frame reduction using an artificial intelligence algorithm

OBJECTIVES

Poorly visualized images that appear during small bowel capsule endoscopy (SBCE) can confuse the interpretation of small bowel lesions and increase the physician's workload. Using a validated artificial intelligence (AI) algorithm that can evaluate the mucosal visualization, we aimed to assess whether SBCE reading after the removal of poorly visualized images could affect the diagnosis of SBCE.

METHODS

A study was conducted to analyze 90 SBCE cases in which a small bowel examination was completed. Two experienced endoscopists alternately performed two types of readings. They used the AI algorithm to remove poorly visualized images for the frame reduction reading (AI user group) and conducted whole frame reading without AI (AI non-user group) for the same patient. A poorly visualized image was defined as an image with < 50% mucosal visualization. The study outcomes were diagnostic concordance and reading time between the two groups. The SBCE diagnosis was classified as Crohn's disease, bleeding, polyp, angiodysplasia, and nonspecific finding.

RESULTS

The final SBCE diagnoses between the two groups showed statistically significant diagnostic concordance (k = 0.954, p < 0.001). The mean number of lesion images was 3008.5 ± 9964.9 in the AI non-user group and 1401.7 ± 4811.3 in the AI user group. There were no cases in which lesions were completely removed. Compared with the AI non-user group (120.9 min), the reading time was reduced by 35.6% in the AI user group (77.9 min).

CONCLUSIONS

SBCE reading after reducing poorly visualized frames using the AI algorithm did not have a negative effect on the final diagnosis. SBCE reading method integrated with frame reduction and mucosal visualization evaluation will help improve AI-assisted SBCE interpretation.

Automatic detection of small bowel lesions with different bleeding risks based on deep learning models

BACKGROUND

Deep learning provides an efficient automatic image recognition method for small bowel (SB) capsule endoscopy (CE) that can assist physicians in diagnosis. However, the existing deep learning models present some unresolved challenges.

AIM

To propose a novel and effective classification and detection model to automatically identify various SB lesions and their bleeding risks, and label the lesions accurately so as to enhance the diagnostic efficiency of physicians and the ability to identify high-risk bleeding groups.

METHODS

The proposed model represents a two-stage method that combined image classification with object detection. First, we utilized the improved ResNet-50 classification model to classify endoscopic images into SB lesion images, normal SB mucosa images, and invalid images. Then, the improved YOLO-V5 detection model was utilized to detect the type of lesion and its risk of bleeding, and the location of the lesion was marked. We constructed training and testing sets and compared model-assisted reading with physician reading.

RESULTS

The accuracy of the model constructed in this study reached 98.96%, which was higher than the accuracy of other systems using only a single module. The sensitivity, specificity, and accuracy of the model-assisted reading detection of all images were 99.17%, 99.92%, and 99.86%, which were significantly higher than those of the endoscopists' diagnoses. The image processing time of the model was 48 ms/image, and the image processing time of the physicians was 0.40 ± 0.24 s/image (P < 0.001).

CONCLUSION

The deep learning model of image classification combined with object detection exhibits a satisfactory diagnostic effect on a variety of SB lesions and their bleeding risks in CE images, which enhances the diagnostic efficiency of physicians and improves the ability of physicians to identify high-risk bleeding groups.

The Role of Capsule Endoscopy in the Diagnosis and Management of Small Bowel Tumors: A Narrative Review

Small bowel tumors (SBT) are relatively rare, but have had a steadily increasing incidence in the last few decades. Small bowel capsule endoscopy (SBCE) and device-assisted enteroscopy are the main endoscopic techniques for the study of the small bowel, the latter additionally providing sampling and therapeutic options, and hence acting complementary to SBCE in the diagnostic work-up. Although a single diagnostic modality is often insufficient in the setting of SBTs, SBCE is a fundamental tool to drive further management towards a definitive diagnosis. The aim of this paper is to provide a concise narrative review of the role of SBCE in the diagnosis and management of SBTs.

High-Speed and Accurate Diagnosis of Gastrointestinal Disease: Learning on Endoscopy Images Using Lightweight Transformer with Local Feature Attention

In response to the pressing need for robust disease diagnosis from gastrointestinal tract (GIT) endoscopic images, we proposed FLATer, a fast, lightweight, and highly accurate transformer-based model. FLATer consists of a residual block, a vision transformer module, and a spatial attention block, which concurrently focuses on local features and global attention. It can leverage the capabilities of both convolutional neural networks (CNNs) and vision transformers (ViT). We decomposed the classification of endoscopic images into two subtasks: a binary classification to discern between normal and pathological images and a further multi-class classification to categorize images into specific diseases, namely ulcerative colitis, polyps, and esophagitis. FLATer has exhibited exceptional prowess in these tasks, achieving 96.4% accuracy in binary classification and 99.7% accuracy in ternary classification, surpassing most existing models. Notably, FLATer could maintain impressive performance when trained from scratch, underscoring its robustness. In addition to the high precision, FLATer boasted remarkable efficiency, reaching a notable throughput of 16.4k images per second, which positions FLATer as a compelling candidate for rapid disease identification in clinical practice.

Smart Endoscopy Is Greener Endoscopy: Leveraging Artificial Intelligence and Blockchain Technologies to Drive Sustainability in Digestive Health Care

The surge in the implementation of artificial intelligence (AI) in recent years has permeated many aspects of our life, and health care is no exception. Whereas this technology can offer clear benefits, some of the problems associated with its use have also been recognised and brought into question, for example, its environmental impact. In a similar fashion, health care also has a significant environmental impact, and it requires a considerable source of greenhouse gases. Whereas efforts are being made to reduce the footprint of AI tools, here, we were specifically interested in how employing AI tools in gastroenterology departments, and in particular in conjunction with capsule endoscopy, can reduce the carbon footprint associated with digestive health care while offering improvements, particularly in terms of diagnostic accuracy. We address the different ways that leveraging AI applications can reduce the carbon footprint associated with all types of capsule endoscopy examinations. Moreover, we contemplate how the incorporation of other technologies, such as blockchain technology, into digestive health care can help ensure the sustainability of this clinical speciality and by extension, health care in general.

Disease surveillance evaluation of primary small-bowel follicular lymphoma using capsule endoscopy images based on a deep convolutional neural network (with video)

BACKGROUND AND AIMS

Capsule endoscopy (CE) is useful in evaluating disease surveillance for primary small-bowel follicular lymphoma (FL), but some cases are difficult to evaluate objectively. This study evaluated the usefulness of a deep convolutional neural network (CNN) system using CE images for disease surveillance of primary small-bowel FL.

METHODS

We enrolled 26 consecutive patients with primary small-bowel FL diagnosed between January 2011 and January 2021 who underwent CE before and after a watch-and-wait strategy or chemotherapy. Disease surveillance by the CNN system was evaluated by the percentage of FL-detected images among all CE images of the small-bowel mucosa.

RESULTS

Eighteen cases (69%) were managed with a watch-and-wait approach, and 8 cases (31%) were treated with chemotherapy. Among the 18 cases managed with the watch-and-wait approach, the outcome of lesion evaluation by the CNN system was almost the same in 13 cases (72%), aggravation in 4 (22%), and improvement in 1 (6%). Among the 8 cases treated with chemotherapy, the outcome of lesion evaluation by the CNN system was improvement in 5 cases (63%), almost the same in 2 (25%), and aggravation in 1 (12%). The physician and CNN system reported similar results regarding disease surveillance evaluation in 23 of 26 cases (88%), whereas a discrepancy between the 2 was found in the remaining 3 cases (12%), attributed to poor small-bowel cleansing level.

CONCLUSIONS

Disease surveillance evaluation of primary small-bowel FL using CE images by the developed CNN system was useful under the condition of excellent small-bowel cleansing level.

Video Analysis of Small Bowel Capsule Endoscopy Using a Transformer Network

Although wireless capsule endoscopy (WCE) detects small bowel diseases effectively, it has some limitations. For example, the reading process can be time consuming due to the numerous images generated per case and the lesion detection accuracy may rely on the operators' skills and experiences. Hence, many researchers have recently developed deep-learning-based methods to address these limitations. However, they tend to select only a portion of the images from a given WCE video and analyze each image individually. In this study, we note that more information can be extracted from the unused frames and the temporal relations of sequential frames. Specifically, to increase the accuracy of lesion detection without depending on experts' frame selection skills, we suggest using whole video frames as the input to the deep learning system. Thus, we propose a new Transformer-architecture-based neural encoder that takes the entire video as the input, exploiting the power of the Transformer architecture to extract long-term global correlation within and between the input frames. Subsequently, we can capture the temporal context of the input frames and the attentional features within a frame. Tests on benchmark datasets of four WCE videos showed 95.1% sensitivity and 83.4% specificity. These results may significantly advance automated lesion detection techniques for WCE images.

Deep learning-based prediction model for diagnosing gastrointestinal diseases using endoscopy images

BACKGROUND

Gastrointestinal (GI) infections are quite common today around the world. Colonoscopy or wireless capsule endoscopy (WCE) are noninvasive methods for examining the whole GI tract for abnormalities. Nevertheless, it requires a great deal of time and effort for doctors to visualize a large number of images, and diagnosis is prone to human error. As a result, developing automated artificial intelligence (AI) based GI disease diagnosis methods is a crucial and emerging research area. AI-based prediction models may lead to improvements in the early diagnosis of gastrointestinal disorders, assessing severity, and healthcare systems for the benefit of patients as well as clinicians. The focus of this research is on the early diagnosis of gastrointestinal diseases using a convolution neural network (CNN) to enhance diagnosis accuracy.

METHODS

Various CNN models (baseline model and using transfer learning (VGG16, InceptionV3, and ResNet50)) were trained on a benchmark image dataset, KVASIR, containing images from inside the GI tract using n-fold cross-validation. The dataset comprises images of three disease states-polyps, ulcerative colitis, and esophagitis-as well as images of the healthy colon. Data augmentation strategies together with statistical measures were used to improve and evaluate the model's performance. Additionally, the test set comprising 1200 images was used to evaluate the model's accuracy and robustness.

RESULTS

The CNN model using the weights of the ResNet50 pre-trained model achieved the highest average accuracy of approximately 99.80% on the training set (100% precision and approximately 99% recall) and accuracies of 99.50% and 99.16% on the validation and additional test set, respectively, while diagnosing GI diseases. When compared to other existing systems, the proposed ResNet50 model outperforms them all.

CONCLUSION

The findings of this study indicate that AI-based prediction models using CNNs, specifically ResNet50, can improve diagnostic accuracy for detecting gastrointestinal polyps, ulcerative colitis, and esophagitis. The prediction model is available at https://github.com/anjus02/GI-disease-classification.git.

Rotational Platform for Real-Time Localization for Active Implantable Medical Devices

This paper presents a sensor based localization system to localize active implantable medical devices i.e., Wireless Capsule Endoscopy (WCE). The importance of localizing the capsule arises once the images from the capsule detect the abnormalities in the Gastrointestinal tract (GI). A successful system can determine the location that associated with the abnormality for further medical investigation or treatment. The system proposed in this paper comprises a rotational platform that consists of magnetic sensors to detect the position of the embedded magnet in the capsule. The rotational platform provides advantageousness in terms of reducing the number of the sensors and increasing the monitoring accuracy during the real time movement.

Diagnostic yield for video capsule endoscopy in gastrointestinal graft- versus -host disease: a systematic review and metaanalysis

BACKGROUND

The gastrointestinal tract is the second most involved organ for graft-versus-host disease where involvement of the small intestine is present in 50% of the cases. Therefore, the use of a non-invasive investigation i.e., video capsule endoscopy (VCE) seems ideal in the diagnostic work-up, but this has never been systematically evaluated before.

OBJECTIVE

The aim of this systematic review was to determine the efficacy and safety of VCE, in comparison with conventional endoscopy in patients who received hematopoietic stem cell transplantation.

METHOD

Databases searched were PubMed, Scopus, EMBASE, and Cochrane CENTRAL. All databases were searched from their inception date until June 17, 2022. The search identified 792 publications, of which 8 studies were included in our analysis comprising of 232 unique patients. Efficacy was calculated in comparison with the golden standard i.e., histology. Risk of bias assessment was performed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool.

RESULTS

The pooled sensitivity was higher for VCE at 0.77 (95% CI: 0.60-0.89) compared to conventional endoscopy 0.62 (95% CI: 0.47-0.75) but the difference was not statistically significant (p = 0.155, Q = 2.02). Similarly, the pooled specificity was higher for VCE at 0.68 (95% CI: 0.46-0.84) than for conventional endoscopy at 0.58 (95% CI: 0.40-0.74) but not statistically significant (p = 0.457, Q = 0.55). Moreover, concern for adverse events such as intestinal obstruction or perforation was not justified since none of the capsules were retained in the small bowel and no perforations occurred in relation to VCE. A limitation to the study is the retrospective approach seen in 50% of the studies.

CONCLUSION

The role of video capsule endoscopy in diagnosing or dismissing graft-versus-host disease is not yet established and requires further studies. However, the modality appears safe in this cohort.

On the Inheritance of Microbiome-Deficiency: Paediatric Functional Gastrointestinal Disorders, the Immune System and the Gut–Brain Axis

Like the majority of non-communicable diseases that have recently gained attention, functional gastrointestinal (GI) disorders (FGID) in both children and adults are caused by a variety of medical conditions. In general, while it is often thought that common conditions such as obesity may cause other problems, for example, asthma or mental health issues, more consideration needs to be given to the possibility that they could both be brought on by a single underlying problem. Based on the variations in non-communicable disease, in recent years, our group has been revisiting the exact role of the intestinal microbiome within the Vertebrata. While the metabolic products of the microbiome have a role to play in the adult, our tentative conclusion is that the fully functioning, mutualistic microbiome has a primary role: to transfer antigen information from the mother to the neonate in order to calibrate its immune system, allowing it to survive within the microbial environment into which it will emerge. Granted that the microbiome possesses such a function, logic suggests the need for a robust, flexible, mechanism allowing for the partition of nutrition in the mature animal, thus ensuring the continued existence of both the vertebrate host and microbial guest, even under potentially unfavourable conditions. It is feasible that this partition process acts by altering the rate of peristalsis following communication through the gut–brain axis. The final step of this animal–microbiota symbiosis would then be when key microbes are transferred from the female to her progeny, either live offspring or eggs. According to this scheme, each animal inherits twice, once from its parents’ genetic material and once from the mother’s microbiome with the aid of the father’s seminal microbiome, which helps determine the expression of the parental genes. The key point is that the failure of this latter inheritance in humans leads to the distinctive manifestations of functional FGID disorders including inflammation and gut motility disturbances. Furthermore, it seems likely that the critical microbiome–gut association occurs in the first few hours of independent life, in a process that we term handshaking. Note that even if obvious disease in childhood is avoided, the underlying disorders may intrude later in youth or adulthood with immune system disruption coexisting with gut–brain axis issues such as excessive weight gain and poor mental health. In principle, investigating and perhaps supplementing the maternal microbiota provide clinicians with an unprecedented opportunity to intervene in long-term disease processes, even before the child is born.

Design of a Convolutional Neural Network as a Deep Learning Tool for the Automatic Classification of Small-Bowel Cleansing in Capsule Endoscopy

Background and objectives: Capsule endoscopy (CE) is a non-invasive method to inspect the small bowel that, like other enteroscopy methods, requires adequate small-bowel cleansing to obtain conclusive results. Artificial intelligence (AI) algorithms have been seen to offer important benefits in the field of medical imaging over recent years, particularly through the adaptation of convolutional neural networks (CNNs) to achieve more efficient image analysis. Here, we aimed to develop a deep learning model that uses a CNN to automatically classify the quality of intestinal preparation in CE. Methods: A CNN was designed based on 12,950 CE images obtained at two clinical centers in Porto (Portugal). The quality of the intestinal preparation was classified for each image as: excellent, ≥90% of the image surface with visible mucosa; satisfactory, 50-90% of the mucosa visible; and unsatisfactory, <50% of the mucosa visible. The total set of images was divided in an 80:20 ratio to establish training and validation datasets, respectively. The CNN prediction was compared with the classification established by consensus of a group of three experts in CE, currently considered the gold standard to evaluate cleanliness. Subsequently, how the CNN performed in diagnostic terms was evaluated using an independent validation dataset. Results: Among the images obtained, 3633 were designated as unsatisfactory preparation, 6005 satisfactory preparation, and 3312 with excellent preparation. When differentiating the classes of small-bowel preparation, the algorithm developed here achieved an overall accuracy of 92.1%, with a sensitivity of 88.4%, a specificity of 93.6%, a positive predictive value of 88.5%, and a negative predictive value of 93.4%. The area under the curve for the detection of excellent, satisfactory, and unsatisfactory classes was 0.98, 0.95, and 0.99, respectively. Conclusions: A CNN-based tool was developed to automatically classify small-bowel preparation for CE, and it was seen to accurately classify intestinal preparation for CE. The development of such a system could enhance the reproducibility of the scales used for such purposes.

Biocompatible and Long-Term Monitoring Strategies of Wearable, Ingestible and Implantable Biosensors: Reform the Next Generation Healthcare

Sensors enable the detection of physiological indicators and pathological markers to assist in the diagnosis, treatment, and long-term monitoring of diseases, in addition to playing an essential role in the observation and evaluation of physiological activities. The development of modern medical activities cannot be separated from the precise detection, reliable acquisition, and intelligent analysis of human body information. Therefore, sensors have become the core of new-generation health technologies along with the Internet of Things (IoTs) and artificial intelligence (AI). Previous research on the sensing of human information has conferred many superior properties on sensors, of which biocompatibility is one of the most important. Recently, biocompatible biosensors have developed rapidly to provide the possibility for the long-term and in-situ monitoring of physiological information. In this review, we summarize the ideal features and engineering realization strategies of three different types of biocompatible biosensors, including wearable, ingestible, and implantable sensors from the level of sensor designing and application. Additionally, the detection targets of the biosensors are further divided into vital life parameters (e.g., body temperature, heart rate, blood pressure, and respiratory rate), biochemical indicators, as well as physical and physiological parameters based on the clinical needs. In this review, starting from the emerging concept of next-generation diagnostics and healthcare technologies, we discuss how biocompatible sensors revolutionize the state-of-art healthcare system unprecedentedly, as well as the challenges and opportunities faced in the future development of biocompatible health sensors.

Location-aware ingestible microdevices for wireless monitoring of gastrointestinal dynamics

Localization and tracking of ingestible microdevices in the gastrointestinal (GI) tract is valuable for the diagnosis and treatment of GI disorders. Such systems require a large field-of-view of tracking, high spatiotemporal resolution, wirelessly operated microdevices and a non-obstructive field generator that is safe to use in practical settings. However, the capabilities of current systems remain limited. Here, we report three dimensional (3D) localization and tracking of wireless ingestible microdevices in the GI tract of large animals in real time and with millimetre-scale resolution. This is achieved by generating 3D magnetic field gradients in the GI field-of-view using high-efficiency planar electromagnetic coils that encode each spatial point with a distinct magnetic field magnitude. The field magnitude is measured and transmitted by the miniaturized, low-power and wireless microdevices to decode their location as they travel through the GI tract. This system could be useful for quantitative assessment of the GI transit-time, precision targeting of therapeutic interventions and minimally invasive procedures.

Artificial Intelligence-The Rising Star in the Field of Gastroenterology and Hepatology

Artificial intelligence (AI) is a term that covers a multitude of techniques that are used in a manner that tries to reproduce human intelligence. AI is helpful in various medical specialties that use imaging for diagnostic purposes, and gastroenterology is no exception. In this field, AI has several applications, such as detecting and classifying polyps, detecting the malignancy in polyps, diagnosing Helicobacter pylori infection, gastritis, inflammatory bowel disease, gastric cancer, esophageal neoplasia, and pancreatic and hepatic lesions. The aim of this mini-review is to analyze the currently available studies regarding AI in the field of gastroenterology and hepatology and to discuss its main applications as well as its main limitations.

Convolutional neural network-based segmentation network applied to image recognition of angiodysplasias lesion under capsule endoscopy

BACKGROUND

Small intestinal vascular malformations (angiodysplasias) are common causes of small intestinal bleeding. While capsule endoscopy has become the primary diagnostic method for angiodysplasia, manual reading of the entire gastrointestinal tract is time-consuming and requires a heavy workload, which affects the accuracy of diagnosis.

AIM

To evaluate whether artificial intelligence can assist the diagnosis and increase the detection rate of angiodysplasias in the small intestine, achieve automatic disease detection, and shorten the capsule endoscopy (CE) reading time.

METHODS

A convolutional neural network semantic segmentation model with a feature fusion method, which automatically recognizes the category of vascular dysplasia under CE and draws the lesion contour, thus improving the efficiency and accuracy of identifying small intestinal vascular malformation lesions, was proposed. Resnet-50 was used as the skeleton network to design the fusion mechanism, fuse the shallow and depth features, and classify the images at the pixel level to achieve the segmentation and recognition of vascular dysplasia. The training set and test set were constructed and compared with PSPNet, Deeplab3+, and UperNet.

RESULTS

The test set constructed in the study achieved satisfactory results, where pixel accuracy was 99%, mean intersection over union was 0.69, negative predictive value was 98.74%, and positive predictive value was 94.27%. The model parameter was 46.38 M, the float calculation was 467.2 G, and the time length to segment and recognize a picture was 0.6 s.

CONCLUSION

Constructing a segmentation network based on deep learning to segment and recognize angiodysplasias lesions is an effective and feasible method for diagnosing angiodysplasias lesions.

Experimental Research on a Capsule Robot with Spring-Connected Legs

Based on a previous study of a novel capsule robot (CR) with spring-connected legs that could collect intestinal juice for biopsy, in this research, an experiment system is designed, and two experiments are carried out. One of the experiments measures the torque and cutting force of this CR, and the other experiment tests and evaluates the biopsy function of this CR. In the measuring experiment, we analyze how the magnetic torque exerted on this CR changes. In the experiment with a biopsy, we decompose the biopsy actions and select the most effective biopsy action. The result of the experiments shows that this CR can collect and store biopsy samples ideally, and the most effective biopsy action is the rotation with legs extended.

Small bowel cleanliness in capsule endoscopy: a case-control study using validated artificial intelligence algorithm

Small bowel capsule endoscopy (SBCE) may need to be performed immediately after colonoscopy without additional bowel preparation if active small bowel diseases are suspected. However, it is unclear whether the small bowel cleanliness is adequately maintained even after SBCE is performed immediately after colonoscopy. We compared the small bowel cleanliness scores of the study group (SBCE immediately after colonoscopy) and control group (SBCE alone) using a validated artificial intelligence (AI) algorithm (cut-off score > 3.25 for adequate). Cases of SBCE in which polyethylene glycol was used were included retrospectively. Among 85 enrolled cases, 50 cases (58.8%) were the study group. The mean time from the last dose of purgative administration to SBCE was 6.86 ± 0.94 h in the study group and 3.00 ± 0.18 h in the control group. Seventy-five cases (88.2%) were adequate small bowel cleanliness, which was not different between the two groups. The mean small bowel cleanliness score for the study group was 3.970 ± 0.603, and for the control group was 3.937 ± 0.428. In the study group, better colon preparation resulted in a higher small bowel cleanliness score (p = 0.015). Small bowel cleanliness was also adequately maintained in SBCE immediately after colonoscopy. There was no difference between the time and volume of purgative administration and small bowel cleanliness.

Rhode Island gastroenterology video capsule endoscopy data set

Complete endoscopic evaluation of the small bowel is challenging due to its length and anatomy. Although several advances have been made to achieve diagnostic and therapeutic goals, including double-balloon enteroscopy, single-balloon enteroscopy, and spiral enteroscopy, video capsule endoscopy (VCE) remains the least invasive tool for complete visualization of the small bowel and is the preferred method for initial diagnostic evaluation. At present, interpretation of VCE data requires manual annotation of landmarks and abnormalities in recorded videos, which can be time consuming. Computer-assisted diagnostic systems using artificial intelligence may help to optimize VCE reading efficiency by reducing the need for manual annotation. Here we present a large VCE data set compiled from studies performed at two United States hospitals in Providence, Rhode Island, including 424 VCE studies and 5,247,588 total labeled images. In conjunction with existing published data sets, these files may aid in the development of algorithms to further improve VCE.

Measurement(s)	organ
Technology Type(s)	Videocapsule Endoscopy
Sample Characteristic - Organism	Homo sapiens
Sample Characteristic - Location	State of Rhode Island

Automatic detection of crohn disease in wireless capsule endoscopic images using a deep convolutional neural network

The diagnosis of Crohn’s disease (CD) in the small bowel is generally performed by observing a very large number of images captured by capsule endoscopy (CE). This diagnostic technique entails a heavy workload for the specialists in terms of time spent reviewing the images. This paper presents a convolutional neural network capable of classifying the CE images to identify those ones affected by lesions indicative of the disease. The architecture of the proposed network was custom designed to solve this image classification problem. This allowed different design decisions to be made with the aim of improving its performance in terms of accuracy and processing speed compared to other state-of-the-art deep-learning-based reference architectures. The experimentation was carried out on a set of 15,972 images extracted from 31 CE videos of patients affected by CD, 7,986 of which showed lesions associated with the disease. The training, validation/selection and evaluation of the network was performed on 70%, 10% and 20% of the total images, respectively. The ROC curve obtained on the test image set has an area greater than 0.997, with points in a 95-99% sensitivity range associated with specificities of 99-96%. These figures are higher than those achieved by EfficientNet-B5, VGG-16, Xception or ResNet networks which also require an average processing time per image significantly higher than the one needed in the proposed architecture. Therefore, the network outlined in this paper is proving to be sufficiently promising to be considered for integration into tools used by specialists in their diagnosis of CD. In the sample of images analysed, the network was able to detect 99% of the images with lesions, filtering out for specialist review 96% of those with no signs of disease.

Endoscopic capsule robot-based diagnosis, navigation and localization in the gastrointestinal tract

The proliferation of video capsule endoscopy (VCE) would not have been possible without continued technological improvements in imaging and locomotion. Advancements in imaging include both software and hardware improvements but perhaps the greatest software advancement in imaging comes in the form of artificial intelligence (AI). Current research into AI in VCE includes the diagnosis of tumors, gastrointestinal bleeding, Crohn’s disease, and celiac disease. Other advancements have focused on the improvement of both camera technologies and alternative forms of imaging. Comparatively, advancements in locomotion have just started to approach clinical use and include onboard controlled locomotion, which involves miniaturizing a motor to incorporate into the video capsule, and externally controlled locomotion, which involves using an outside power source to maneuver the capsule itself. Advancements in locomotion hold promise to remove one of the major disadvantages of VCE, namely, its inability to obtain targeted diagnoses. Active capsule control could in turn unlock additional diagnostic and therapeutic potential, such as the ability to obtain targeted tissue biopsies or drug delivery. With both advancements in imaging and locomotion has come a corresponding need to be better able to process generated images and localize the capsule’s position within the gastrointestinal tract. Technological advancements in computation performance have led to improvements in image compression and transfer, as well as advancements in sensor detection and alternative methods of capsule localization. Together, these advancements have led to the expansion of VCE across a number of indications, including the evaluation of esophageal and colon pathologies including esophagitis, esophageal varices, Crohn’s disease, and polyps after incomplete colonoscopy. Current research has also suggested a role for VCE in acute gastrointestinal bleeding throughout the gastrointestinal tract, as well as in urgent settings such as the emergency department, and in resource-constrained settings, such as during the COVID-19 pandemic. VCE has solidified its role in the evaluation of small bowel bleeding and earned an important place in the practicing gastroenterologist’s armamentarium. In the next few decades, further improvements in imaging and locomotion promise to open up even more clinical roles for the video capsule as a tool for non-invasive diagnosis of lumenal gastrointestinal pathologies.

Small Bowel Detection for Wireless Capsule Endoscopy Using Convolutional Neural Networks with Temporal Filtering

By automatically classifying the stomach, small bowel, and colon, the reading time of the wireless capsule endoscopy (WCE) can be reduced. In addition, it is an essential first preprocessing step to localize the small bowel in order to apply automated small bowel lesion detection algorithms based on deep learning. The purpose of the study was to develop an automated small bowel detection method from long untrimmed videos captured from WCE. Through this, the stomach and colon can also be distinguished. The proposed method is based on a convolutional neural network (CNN) with a temporal filtering on the predicted probabilities from the CNN. For CNN, we use a ResNet50 model to classify three organs including stomach, small bowel, and colon. The hybrid temporal filter consisting of a Savitzky–Golay filter and a median filter is applied to the temporal probabilities for the “small bowel” class. After filtering, the small bowel and the other two organs are differentiated with thresholding. The study was conducted on dataset of 200 patients (100 normal and 100 abnormal WCE cases), which was divided into a training set of 140 cases, a validation set of 20 cases, and a test set of 40 cases. For the test set of 40 patients (20 normal and 20 abnormal WCE cases), the proposed method showed accuracy of 99.8% in binary classification for the small bowel. Transition time errors for gastrointestinal tracts were only 38.8 ± 25.8 seconds for the transition between stomach and small bowel and 32.0 ± 19.1 seconds for the transition between small bowel and colon, compared to the ground truth organ transition points marked by two experienced gastroenterologists.

Obscure Gastrointestinal Bleeding and Capsule Endoscopy: A Win-Win Situation or Not?

Obscure gastrointestinal bleeding (OGIB) refers to bleeding of uncertain origin that persists or recurs after negative workup using any of the radiologic evaluation modalities. It can be divided into two types based on whether clinically evident bleeding is present, namely, obscure overt and obscure occult bleeding. As the visualization of the bowel mucosa is challenging, capsule endoscopy (CE) is the ideal go-to procedure as the process is wireless, ingestible, small, disposable, and, most importantly, non-invasive. This review article has compiled various studies to shed light on the guidelines for using CE, its structure and procedure, patient preferences, diagnostic yield, cost-effectiveness, and the future. The goal of this review is to show the influence of CE on OGIB on the aspects mentioned earlier.

Diagnostic yield of proximal jejunal lesions with third-generation capsule endoscopy

Objectives

Capsule endoscopy (CE) has been shown to have poor diagnostic performance when the capsule passes quickly through the small bowel, especially the proximal jejunum. This study aimed to evaluate the diagnostic yield of proximal jejunal lesions with third-generation CE technology.

Methods

We retrospectively examined 138 consecutive patients, 76 (55.0%) of whom were men. The patients' median age was 70 years, and proximal jejunal lesions were detected by CE and/or double-balloon endoscopy at Hiroshima University Hospital between January 2011 and June 2021. We analyzed the diagnostic accuracy of CE for proximal jejunal lesions and compared the characteristics of the discrepancy between the use of CE and double-balloon endoscopy with Pillcam SB 2 (SB2) and Pillcam SB 3 (SB3).

Results

SB2 and SB3 were used in 48 (35%) and 90 (65%) patients, respectively. There was no difference in baseline characteristics between these groups. Small-bowel lesions in the proximal jejunum comprised 75 tumors (54%), 50 vascular lesions (36%), and 13 inflammatory lesions (9%). The diagnostic rate was significantly higher in the SB3 group than in the SB2 group for tumors (91% vs. 72%, p < 0.05) and vascular lesions (97% vs. 69%, p < 0.01). For vascular lesions, in particular, the diagnostic rate of angioectasia improved in the SB3 group (100%) compared with that in the SB2 group (69%).

Conclusions

SB3 use improved the detection of proximal jejunal tumors and vascular lesions compared with SB2 use.

Scoping out the future: The application of artificial intelligence to gastrointestinal endoscopy

Artificial intelligence (AI) is a quickly expanding field in gastrointestinal endoscopy. Although there are a myriad of applications of AI ranging from identification of bleeding to predicting outcomes in patients with inflammatory bowel disease, a great deal of research has focused on the identification and classification of gastrointestinal malignancies. Several of the initial randomized, prospective trials utilizing AI in clinical medicine have centered on polyp detection during screening colonoscopy. In addition to work focused on colorectal cancer, AI systems have also been applied to gastric, esophageal, pancreatic, and liver cancers. Despite promising results in initial studies, the generalizability of most of these AI systems have not yet been evaluated. In this article we review recent developments in the field of AI applied to gastrointestinal oncology.