RESUMEN
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.
Asunto(s)
Endoscopía Capsular , Aprendizaje Profundo , Humanos , Endoscopía Capsular/métodos , Inteligencia Artificial , Reproducibilidad de los Resultados , Redes Neurales de la ComputaciónRESUMEN
BACKGROUND: capsule endoscopy is increasingly used to obtain images of the gastrointestinal tract, although the best preparation for this type of exploration remains unclear. AIMS: the aim of this study was to compare the results of capsule endoscopy explorations performed after a basic preparation with a clear liquid diet, reduced iron intake and fasting or following preparation with a polyethylene glycol (PEG)/ascorbate solution. METHODS: the results obtained from a prospective intervention group that used a PEG/ascorbate solution to prepare for capsule endoscopy were compared with those from a retrospective group of patients who followed a more basic preparation. The quality of visualization was assessed with the Park score, the visualization of the mucosal surface and the cleanliness of the intestinal lumen were assessed. The capsule transit time in different segments of the gastrointestinal tract was also evaluated. RESULTS: a significant improvement in the quality of small intestine visualization was observed in individuals prepared with the PEG/ascorbate solution as opposed to the basic preparation. In fact, there were significant differences in the two separate components that contribute to the overall visualization score, with better mucosa visualization and lumen content scores in the intervention group, thus reflecting an improved performance. The presence of diabetes appeared to affect the results of these explorations, at least when using the PEG/ascorbate preparation. CONCLUSIONS: preparation with a PEG/ascorbate solution improved the results of capsule endoscopy when compared to a basic preparation, without the inconvenience of the more stringent preparations used for colonoscopies.
Asunto(s)
Endoscopía Capsular , Ácido Ascórbico , Estudios de Casos y Controles , Catárticos , Humanos , Polietilenglicoles , Estudios Prospectivos , Estudios RetrospectivosRESUMEN
Gastroenterology is increasingly moving towards minimally invasive diagnostic modalities. The diagnostic exploration of the colon via capsule endoscopy, both in specific protocols for colon capsule endoscopy and during panendoscopic evaluations, is increasingly regarded as an appropriate first-line diagnostic approach. Adequate colonic preparation is essential for conclusive examinations as, contrary to a conventional colonoscopy, the capsule moves passively in the colon and does not have the capacity to clean debris. Several scales have been developed for the classification of bowel preparation for colon capsule endoscopy. Nevertheless, their applications are limited by suboptimal interobserver agreement. Our group developed a deep learning algorithm for the automatic classification of colonic bowel preparation, according to an easily applicable classification. Our neural network achieved high performance levels, with a sensitivity of 91%, a specificity of 97% and an overall accuracy of 95%. The algorithm achieved a good discriminating capacity, with areas under the curve ranging between 0.92 and 0.97. The development of these algorithms is essential for the widespread adoption of capsule endoscopy for the exploration of the colon, as well as for the adoption of minimally invasive panendoscopy.
RESUMEN
BACKGROUND AND AIMS: Capsule endoscopy is a central element in the management of patients with suspected or known Crohn's disease. In 2017, PillCam™ Crohn's Capsule was introduced and demonstrated to have greater accuracy in the evaluation of extension of disease in these patients. Artificial intelligence [AI] is expected to enhance the diagnostic accuracy of capsule endoscopy. This study aimed to develop an AI algorithm for the automatic detection of ulcers and erosions of the small intestine and colon in PillCam™ Crohn's Capsule images. METHODS: A total of 8085 PillCam™ Crohn's Capsule images were extracted between 2017 and 2020, comprising 2855 images of ulcers and 1975 erosions; the remaining images showed normal enteric and colonic mucosa. This pool of images was subsequently split into training and validation datasets. The performance of the network was subsequently assessed in an independent test set. RESULTS: The model had an overall sensitivity and specificity of 90.0% and 96.0%, respectively. The precision and accuracy of this model were 97.1% and 92.4%, respectively. In particular, the algorithm detected ulcers with a sensitivity of 83% and specificity of 98%, and erosions with sensitivity and specificity of 91% and 93%, respectively. CONCLUSION: A deep learning model capable of automatically detecting ulcers and erosions in PillCam™ Crohn's Capsule images was developed for the first time. These findings pave the way for the development of automatic systems for detection of clinically significant lesions, optimizing the diagnostic performance and efficiency of monitoring Crohn's disease activity.
Asunto(s)
Endoscopía Capsular , Enfermedad de Crohn/patología , Redes Neurales de la Computación , Colon/patología , Humanos , Mucosa Intestinal/patología , Intestino Delgado/patología , Proyectos Piloto , Sensibilidad y Especificidad , Úlcera/patologíaRESUMEN
BACKGROUND/AIMS: The increasing use of capsule endoscopy (CE) to examine the gastrointestinal tract highlights the need to establish intestinal preparations that ensure optimal visualization while maximizing patient adherence. Thus, we assessed whether bowel preparation involving dietary restriction and a booster regimen produces adequate CE visualization in a real-world clinical setting. METHODS: We conducted a randomized, double-blind, prospective study of CE procedures at 2 tertiary-care centers. Patients were allocated to 3 groups: group 1 followed a clear liquid diet and fasting-based bowel preparation for the exploration (n = 55); group 2 followed the same procedure as group 1 and then ingested 1 L of a polyethylene glycol (PEG)/ascorbic acid booster solution when the capsule reached the small intestine (n = 55); and group 3 followed the same procedure but ingesting only 0.5 L of the booster solution (n = 56). The quality of visualization and the average gastric, orocecal and small-bowel transit times were evaluated. RESULTS: A total of 166 patients participated in the study. Significantly higher quality of visualization (Park score) was obtained in group 3 (2.28 ± 0.59) than in group 1 (1.84 ± 0.54, P < .001), while there were no significant differences in the average gastric (range: 36.58- 48.32 min, P = .277), orocecal (range: 322.58-289.45 min, P = .072), and small-bowel transit time (range: 280.71-249.95 min, P = .286) between the 3 groups. CONCLUSIONS: Following a clear liquid diet and fasting-based bowel preparation for CE exploration, administering a booster solution of PEG/ascorbic acid after the capsule had reached the small intestine improves mucosal visualization and cleansing without affecting capsule transit times.
Asunto(s)
Ácido Ascórbico/administración & dosificación , Endoscopía Capsular/métodos , Catárticos/administración & dosificación , Intestino Delgado/diagnóstico por imagen , Polietilenglicoles/farmacología , Adolescente , Adulto , Anciano , Anciano de 80 o más Años , Método Doble Ciego , Ayuno , Femenino , Tránsito Gastrointestinal/efectos de los fármacos , Humanos , Masculino , Persona de Mediana Edad , Estudios Prospectivos , Adulto JovenRESUMEN
OBJECTIVE: Capsule endoscopy (CE) is pivotal for evaluation of small bowel disease. Obscure gastrointestinal bleeding most often originates from the small bowel. CE frequently identifies a wide range of lesions with different bleeding potentials in these patients. However, reading CE examinations is a time-consuming task. Convolutional neural networks (CNNs) are highly efficient artificial intelligence tools for image analysis. This study aims to develop a CNN-based model for identification and differentiation of multiple small bowel lesions with distinct haemorrhagic potential using CE images. DESIGN: We developed, trained, and validated a denary CNN based on CE images. Each frame was labelled according to the type of lesion (lymphangiectasia, xanthomas, ulcers, erosions, vascular lesions, protruding lesions, and blood). The haemorrhagic potential was assessed by Saurin's classification. The entire dataset was divided into training and validation sets. The performance of the CNN was measured by the area under the receiving operating characteristic curve, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). RESULTS: A total of 53 555 CE images were included. The model had an overall accuracy of 99%, a sensitivity of 88%, a specificity of 99%, a PPV of 87%, and an NPV of 99% for detection of multiple small bowel abnormalities and respective classification of bleeding potential. CONCLUSION: We developed and tested a CNN-based model for automatic detection of multiple types of small bowel lesions and classification of the respective bleeding potential. This system may improve the diagnostic yield of CE for these lesions and overall CE efficiency.
Asunto(s)
Endoscopía Capsular , Aprendizaje Profundo , Inteligencia Artificial , Humanos , Intestino Delgado/diagnóstico por imagen , Redes Neurales de la ComputaciónRESUMEN
BACKGROUND: Although linaclotide has been approved to treat moderate to severe IBS-C, no data are available on its effectiveness and tolerability in patients in a real-life setting. METHODS: A prospective single-center study of the effectiveness and tolerability of linaclotide was carried out on patients (n = 40) with moderate to severe IBS-C, all fulfilling the Rome IV criteria. Clinical information was recorded using a dietary questionnaire at baseline, and 3 and 6 months after initiating treatment. The end-points to measure effectiveness included abdominal pain and bloating (11-NRS), the number of bowel movements and patient satisfaction. Tolerability was assessed through the frequency of adverse events. KEY RESULTS: In terms of efficacy, an improvement in abdominal pain and in the intensity of bloating was evident in the cohort after 6 months of linaclotide therapy. The proportion of patients with moderate or severe symptoms of bloating fell from 93.3% to 33.3% and those with pain from 93.4% to 20%. Weekly bowel movements also improved and accordingly, 97% of the patients were moderately or very satisfied with the treatment. At the end of the study, diarrhea was the most frequent adverse event (10%), although it was considered mild in 66.7% of these subjects and moderate in 33.3%. A lack of efficacy (n = 3) and excessive diarrhea (n = 7) were motives for discontinuing the treatment. CONCLUSIONS AND INFERENCES: Linaclotide proved to be a safe and effective drug to reduce the main symptoms of IBS-C in everyday clinical practice, with an improvement comparable to that seen in clinical trials.