RESUMEN
Background: Capsule endoscopy (CE) is a valuable tool for assessing inflammation in patients with Crohn's disease (CD). The current standard for evaluating inflammation are validated scores (and clinical laboratory values) like Lewis score (LS), Capsule Endoscopy Crohn's Disease Activity Index (CECDAI), and ELIAKIM. Recent advances in artificial intelligence (AI) have made it possible to automatically select the most relevant frames in CE. Objectives: In this proof-of-concept study, our objective was to develop an automated scoring system using CE images to objectively grade inflammation. Design: Pan-enteric CE videos (PillCam Crohn's) performed in CD patients between 09/2020 and 01/2023 were retrospectively reviewed and LS, CECDAI, and ELIAKIM scores were calculated. Methods: We developed a convolutional neural network-based automated score consisting of the percentage of positive frames selected by the algorithm (for small bowel and colon separately). We correlated clinical data and the validated scores with the artificial intelligence-generated score (AIS). Results: A total of 61 patients were included. The median LS was 225 (0-6006), CECDAI was 6 (0-33), ELIAKIM was 4 (0-38), and SB_AIS was 0.5659 (0-29.45). We found a strong correlation between SB_AIS and LS, CECDAI, and ELIAKIM scores (Spearman's r = 0.751, r = 0.707, r = 0.655, p = 0.001). We found a strong correlation between LS and ELIAKIM (r = 0.768, p = 0.001) and a very strong correlation between CECDAI and LS (r = 0.854, p = 0.001) and CECDAI and ELIAKIM scores (r = 0.827, p = 0.001). Conclusion: Our study showed that the AI-generated score had a strong correlation with validated scores indicating that it could serve as an objective and efficient method for evaluating inflammation in CD patients. As a preliminary study, our findings provide a promising basis for future refining of a CE score that may accurately correlate with prognostic factors and aid in the management and treatment of CD patients.
Artificial intelligence in Crohn's disease: the development of an automated score for disease activity evaluation This study introduces an innovative AI-based approach to evaluate Crohn's Disease. The AI system automatically analyzes images from capsule endoscopy, focusing on finding ulcers and erosions to measure disease activity. The research reveals a robust correlation between the AI-generated score assessing inflammation in the small bowel and traditional clinical scores. This suggests that the AI solution could be a quicker and more consistent way to evaluate Crohn's Disease, speeding up the evaluation process and reducing manual scoring variability. While promising, the study acknowledges limitations and emphasizes the need for further validation with larger groups of patients. Overall, it represents a crucial step toward integrating AI into gastroenterology, offering a glimpse into a future of more objective and personalized Crohn's Disease evaluation.
RESUMEN
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.
RESUMEN
Artificial intelligence has yielded remarkably promising results in several medical fields, namely those with a strong imaging component. Gynecology relies heavily on imaging since it offers useful visual data on the female reproductive system, leading to a deeper understanding of pathophysiological concepts. The applicability of artificial intelligence technologies has not been as noticeable in gynecologic imaging as in other medical fields so far. However, due to growing interest in this area, some studies have been performed with exciting results. From urogynecology to oncology, artificial intelligence algorithms, particularly machine learning and deep learning, have shown huge potential to revolutionize the overall healthcare experience for women's reproductive health. In this review, we aim to establish the current status of AI in gynecology, the upcoming developments in this area, and discuss the challenges facing its clinical implementation, namely the technological and ethical concerns for technology development, implementation, and accountability.
RESUMEN
Device-assisted enteroscopy (DAE) is capable of evaluating the entire gastrointestinal tract, identifying multiple lesions. Nevertheless, DAE's diagnostic yield is suboptimal. Convolutional neural networks (CNN) are multi-layer architecture artificial intelligence models suitable for image analysis, but there is a lack of studies about their application in DAE. Our group aimed to develop a multidevice CNN for panendoscopic detection of clinically relevant lesions during DAE. In total, 338 exams performed in two specialized centers were retrospectively evaluated, with 152 single-balloon enteroscopies (Fujifilm®, Porto, Portugal), 172 double-balloon enteroscopies (Olympus®, Porto, Portugal) and 14 motorized spiral enteroscopies (Olympus®, Porto, Portugal); then, 40,655 images were divided in a training dataset (90% of the images, n = 36,599) and testing dataset (10% of the images, n = 4066) used to evaluate the model. The CNN's output was compared to an expert consensus classification. The model was evaluated by its sensitivity, specificity, positive (PPV) and negative predictive values (NPV), accuracy and area under the precision recall curve (AUC-PR). The CNN had an 88.9% sensitivity, 98.9% specificity, 95.8% PPV, 97.1% NPV, 96.8% accuracy and an AUC-PR of 0.97. Our group developed the first multidevice CNN for panendoscopic detection of clinically relevant lesions during DAE. The development of accurate deep learning models is of utmost importance for increasing the diagnostic yield of DAE-based panendoscopy.
RESUMEN
INTRODUCTION: High-resolution anoscopy (HRA) is the gold standard for detecting anal squamous cell carcinoma (ASCC) precursors. Preliminary studies on the application of artificial intelligence (AI) models to this modality have revealed promising results. However, the impact of staining techniques and anal manipulation on the effectiveness of these algorithms has not been evaluated. We aimed to develop a deep learning system for automatic differentiation of high-grade squamous intraepithelial lesion vs low-grade squamous intraepithelial lesion in HRA images in different subsets of patients (nonstained, acetic acid, lugol, and after manipulation). METHODS: A convolutional neural network was developed to detect and differentiate high-grade and low-grade anal squamous intraepithelial lesions based on 27,770 images from 103 HRA examinations performed in 88 patients. Subanalyses were performed to evaluate the algorithm's performance in subsets of images without staining, acetic acid, lugol, and after manipulation of the anal canal. The sensitivity, specificity, accuracy, positive and negative predictive values, and area under the curve were calculated. RESULTS: The convolutional neural network achieved an overall accuracy of 98.3%. The algorithm had a sensitivity and specificity of 97.4% and 99.2%, respectively. The accuracy of the algorithm for differentiating high-grade squamous intraepithelial lesion vs low-grade squamous intraepithelial lesion varied between 91.5% (postmanipulation) and 100% (lugol) for the categories at subanalysis. The area under the curve ranged between 0.95 and 1.00. DISCUSSION: The introduction of AI to HRA may provide an accurate detection and differentiation of ASCC precursors. Our algorithm showed excellent performance at different staining settings. This is extremely important because real-time AI models during HRA examinations can help guide local treatment or detect relapsing disease.
Asunto(s)
Neoplasias del Ano , Carcinoma de Células Escamosas , Aprendizaje Profundo , Lesiones Intraepiteliales Escamosas , Humanos , Neoplasias del Ano/diagnóstico , Neoplasias del Ano/patología , Neoplasias del Ano/diagnóstico por imagen , Femenino , Masculino , Persona de Mediana Edad , Lesiones Intraepiteliales Escamosas/patología , Lesiones Intraepiteliales Escamosas/diagnóstico , Carcinoma de Células Escamosas/patología , Carcinoma de Células Escamosas/diagnóstico , Carcinoma de Células Escamosas/diagnóstico por imagen , Coloración y Etiquetado/métodos , Proctoscopía/métodos , Anciano , Algoritmos , Redes Neurales de la Computación , Ácido Acético , Adulto , Sensibilidad y Especificidad , Lesiones Precancerosas/patología , Lesiones Precancerosas/diagnóstico , Lesiones Precancerosas/diagnóstico por imagen , Canal Anal/patología , Canal Anal/diagnóstico por imagen , Valor Predictivo de las PruebasRESUMEN
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
Ingestion of foreign bodies (IFB) and ingestion of caustic agents are frequent non-hemorrhagic causes of endoscopic urgencies, with the potential for severe complications. This study aimed to evaluate the predicting factors of the clinical outcomes of patients hospitalized as a result of IFB or ingestion of caustics (IC). This was a retrospective single-center study of patients admitted for IFB or IC between 2000 and 2019 at a tertiary center. Demographic and clinical data, as well as preliminary exams, were evaluated. Also, variables of the clinical outcomes, including the length of stay (LS) and other inpatient complications, were assessed. Sixty-six patients were included (44 IFB and 22 IC). The median LS was 7 days, with no differences between the groups (p = 0.07). The values of C-reactive protein (CRP) upon admission correlated with the LS in the IFB group (p < 0.01) but not with that of those admitted after IC. In the IFB patients, a diagnosis of perforation on both an endoscopy (p = 0.02) and CT scan (p < 0.01) was correlated with the LS. The Zargar classification was not correlated with the LS in the IC patients (p = 0.36). However, it was correlated with antibiotics, nosocomial pneumonia and an increased need for intensive care treatment. CT assessment of the severity of the caustic lesions did not correlate with the LS. In patients admitted for IFB, CRP values may help stratify the probability of complications. In patients admitted due to IC, the Zargar classification may help to predict inpatient complications, but it does not correlate with the LS.
RESUMEN
INTRODUCTION: Capsule endoscopy (CE) is a minimally invasive examination for evaluating the gastrointestinal tract. However, its diagnostic yield for detecting gastric lesions is suboptimal. Convolutional neural networks (CNNs) are artificial intelligence models with great performance for image analysis. Nonetheless, their role in gastric evaluation by wireless CE (WCE) has not been explored. METHODS: Our group developed a CNN-based algorithm for the automatic classification of pleomorphic gastric lesions, including vascular lesions (angiectasia, varices, and red spots), protruding lesions, ulcers, and erosions. A total of 12,918 gastric images from 3 different CE devices (PillCam Crohn's; PillCam SB3; OMOM HD CE system) were used from the construction of the CNN: 1,407 from protruding lesions; 994 from ulcers and erosions; 822 from vascular lesions; and 2,851 from hematic residues and the remaining images from normal mucosa. The images were divided into a training (split for three-fold cross-validation) and validation data set. The model's output was compared with a consensus classification by 2 WCE-experienced gastroenterologists. The network's performance was evaluated by its sensitivity, specificity, accuracy, positive predictive value and negative predictive value, and area under the precision-recall curve. RESULTS: The trained CNN had a 97.4% sensitivity; 95.9% specificity; and positive predictive value and negative predictive value of 95.0% and 97.8%, respectively, for gastric lesions, with 96.6% overall accuracy. The CNN had an image processing time of 115 images per second. DISCUSSION: Our group developed, for the first time, a CNN capable of automatically detecting pleomorphic gastric lesions in both small bowel and colon CE devices.
Asunto(s)
Endoscopía Capsular , Aprendizaje Profundo , Humanos , Endoscopía Capsular/métodos , Inteligencia Artificial , Úlcera , Redes Neurales de la ComputaciónRESUMEN
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
Introduction: Small bowel adenocarcinoma is a rare but well-known complication of Crohn's disease. Diagnosis can be challenging, as clinical presentation may mimic an exacerbation of Crohn's disease and imaging findings may be indistinguishable from benign strictures. The result is that the majority of cases are diagnosed at the time of operation or postoperatively at an advanced stage. Case Presentation: A 48-year-old male with a previous 20-year history of ileal stenosing Crohn's disease presented with iron deficiency anemia. The patient reported melena approximately 1 month earlier but was currently asymptomatic. There were no other laboratory abnormalities. Anemia was refractory to intravenous iron replacement. The patient underwent computerized tomography enterography, which revealed multiple ileal strictures with features suggesting underlying inflammation and an area of sacculation with circumferential thickening of adjacent bowel loops. Therefore, the patient underwent retrograde balloon-assisted small bowel enteroscopy, where an area of irregular mucosa and ulceration was found at the region of ileo-ileal anastomosis. Biopsies were performed and histopathological examination revealed tubular adenocarcinoma infiltrating the muscularis mucosae. The patient underwent right hemicolectomy plus segmental enterectomy of the anastomotic region where the neoplasia was located. After 2 months, he is asymptomatic and there is no evidence of recurrence. Discussion: This case demonstrates that small bowel adenocarcinoma may have a subtle clinical presentation and that computed tomography enterography may not be accurate enough to distinguish benign from malignant strictures. Clinicians must, therefore, maintain a high index of suspicion for this complication in patients with long-standing small bowel Crohn's disease. In this setting, balloon-assisted enteroscopy may be a useful tool when there is raised concern for malignancy, and it is expected that its more widespread use could contribute to an earlier diagnosis of this severe complication.
Introdução: O adenocarcinoma do intestino delgado é uma complicação rara mas bem estabelecida da doença de Crohn. O seu diagnóstico pode ser desafiante, na medida em que a apresentação clínica pode mimetizar uma agudização da doença de Crohn e os achados imagiológicos podem ser indistinguíveis de estenoses benignas. Em consequência, a maioria dos casos são diagnosticados durante ou após a cirurgia em estadio avançado. Descrição do caso: Um homem de 48 anos com antecedentes de doença de Crohn ileal estenosante, com 20 anos de evolução, apresentou-se com anemia ferropénica. O doente referia melenas aproximadamente um mês antes, mas encontrava-se atualmente assintomático. Não apresentava outras alterações laboratoriais de relevo. A anemia era refratária a suplementação com ferro endovenoso. Foi submetido a enterografia por tomografia computorizada, que revelou múltiplas estenoses ileais com caraterísticas sugestivas de atividade inflamatória e uma área de saculação com espessamento circunferencial das ansas de intestino delgado adjacentes. Assim, foi submetido a enteroscopia assistida por balão, onde se identificou uma área de mucosa irregular e ulceração na região da anastomose ileo-ileal. Biópsias desta área revelaram a presença de adenocarcinoma tubular com infiltração até à muscularis mucosae. O doente foi submetido a hemicolectomia direita com enterectomia segmentar da região da anastomose onde a neoplasia se encontrava localizada. Ao fim de 2 meses, o doente encontra-se assintomático e sem evidência de recorrência. Discussão: Este caso demonstra que o adenocarcinoma do intestino delgado pode ter uma apresentação clínica subtil e que a enterografia por tomografia computorizada pode não ter precisão suficiente para distinguir estenoses benignas de neoplasias malignas. Os clínicos devem, portanto, manter um elevado índice de suspeição diagnóstica para esta complicação em doentes com doença de Crohn ileal de longa duração. Neste contexto, a enteroscopia assistida por balão pode ser uma ferramenta útil em casos de suspeita de neoplasia maligna, esperando- se que possa contribuir para um diagnóstico mais precoce desta complicação severa.
RESUMEN
INTRODUCTION: Dysphagia is a prevalent condition (20%), and occurs more frequently in women and in older people. It negatively impacts innumerous aspects of patient's personal and professional lives. Patient-reported outcomes allow patients to directly quantify their experience regarding dysphagia and evaluate its true impact on quality of life. Among the scales available, Patient-Reported Outcomes Measurement Information System Gastrointestinal (PROMIS GI) Disrupted Swallowing stands out because it is a robust instrument that can be applied regardless of the type and etiology of dysphagia. The aim of this study was to translate, culturally adapt and validate PROMIS GI Disrupted Swallowing scale for the Portuguese-speaking population. MATERIAL AND METHODS: Firstly, the seven items of the scale were translated and transculturally reviewed following the systematic method proposed by the Functional Assessment of Chronic Illness Therapy (FACIT). Afterwards, the pre-test version of the questionnaire was administered to a convenience sample (n = 6) for semantic evaluation, with the aim of detection and subsequent correction of possible problems in the translation. The final translated and certified version of the scale was administered to 200 voluntary adult participants (n = 123 healthy; n = 77 dysphagia) in Portugal, for evaluation of reliability and validity. RESULTS: The Portuguese version of PROMIS GI Disrupted Swallowing presented acceptable internal consistency (coefficient of Cronbach's α of 0.919) and adequate test-retest reliability (intraclass correlation coefficient of 0.941). The translated version of the scale revealed a strong correlation with both Eckardt score (p < 0.001; ρ = 0.782) and the quality-of-life questionnaire EuroQol-5D (p < 0.001; ρ = -0.551), demonstrating evidence of convergent validity. CONCLUSION: The Portuguese version of PROMIS GI Disrupted Swallowing scale presented conceptual, semantic, cultural and measurement equivalence relatively to the original items. The results attained demonstrated that the translation of this scale to Portuguese is reliable and valid for use both in clinical practice and for research purposes.
Asunto(s)
Trastornos de Deglución , Calidad de Vida , Adulto , Humanos , Femenino , Anciano , Portugal , Trastornos de Deglución/diagnóstico , Reproducibilidad de los Resultados , Deglución , Traducciones , Encuestas y Cuestionarios , Lenguaje , Psicometría/métodosRESUMEN
BACKGROUND AND AIMS: capsule endoscopy (CE) revolutionized the study of the small intestine. Nevertheless, reviewing CE images is time-consuming and prone to error. Artificial intelligence algorithms, particularly convolutional neural networks (CNN), are expected to overcome these drawbacks. Protruding lesions of the small intestine exhibit enormous morphological diversity in CE images. This study aimed to develop a CNN-based algorithm for the automatic detection small bowel protruding lesions. METHODS: a CNN was developed using a pool of CE images containing protruding lesions or normal mucosa from 1,229 patients. A training dataset was used for the development of the model. The performance of the network was evaluated using an independent dataset, by calculating its sensitivity, specificity, accuracy, positive and negative predictive values. RESULTS: a total of 18,625 CE images (2,830 showing protruding lesions and 15,795 normal mucosa) were included. Training and validation datasets were built with an 80 %/20 % distribution, respectively. After optimizing the architecture of the network, our model automatically detected small-bowel protruding lesions with an accuracy of 92.5 %. CNN had a sensitivity and specificity of 96.8 % and 96.5 %, respectively. The CNN analyzed the validation dataset in 53 seconds, at a rate of approximately 70 frames per second. CONCLUSIONS: we developed an accurate CNN for the automatic detection of enteric protruding lesions with a wide range of morphologies. The development of these tools may enhance the diagnostic efficiency of CE.
Asunto(s)
Inteligencia Artificial , Endoscopía Capsular , Humanos , Endoscopía Capsular/métodos , Redes Neurales de la Computación , Algoritmos , Intestino Delgado/diagnóstico por imagen , Intestino Delgado/patologíaRESUMEN
BACKGROUND AND AIM: Colon capsule endoscopy (CCE) has become a minimally invasive alternative for conventional colonoscopy. Nevertheless, each CCE exam produces between 50 000 and 100 000 frames, making its analysis time-consuming and prone to errors. Convolutional neural networks (CNNs) are a type of artificial intelligence (AI) architecture with high performance in image analysis. This study aims to develop a CNN model for the identification of colonic ulcers and erosions in CCE images. METHODS: A CNN model was designed using a database of CCE images. A total of 124 CCE exams performed between 2010 and 2020 in two centers were reviewed. For CNN development, a total of 37 319 images were extracted, 33 749 showing normal colonic mucosa and 3570 showing colonic ulcers and erosions. Datasets for CNN training, validation, and testing were created. The performance of the algorithm was evaluated regarding its sensitivity, specificity, positive and negative predictive values, accuracy, and area under the curve. RESULTS: The network had a sensitivity of 96.9% and a specificity of 99.9% specific for the detection of colonic ulcers and erosions. The algorithm had an overall accuracy of 99.6%. The area under the curve was 1.00. The CNN had an image processing capacity of 90 frames per second. CONCLUSIONS: The developed algorithm is the first CNN-based model to accurately detect ulcers and erosions in CCE images, also providing a good image processing performance. The development of these AI systems may contribute to improve both the diagnostic and time efficiency of CCE exams, facilitating CCE adoption to routine clinical practice.
Asunto(s)
Endoscopía Capsular , Humanos , Inteligencia Artificial , Redes Neurales de la Computación , ColonRESUMEN
Introduction: Capsule endoscopy has revolutionized the management of patients with obscure gastrointestinal bleeding. Nevertheless, reading capsule endoscopy images is time-consuming and prone to overlooking significant lesions, thus limiting its diagnostic yield. We aimed to create a deep learning algorithm for automatic detection of blood and hematic residues in the enteric lumen in capsule endoscopy exams. Methods: A convolutional neural network was developed based on a total pool of 22,095 capsule endoscopy images (13,510 images containing luminal blood and 8,585 of normal mucosa or other findings). A training dataset comprising 80% of the total pool of images was defined. The performance of the network was compared to a consensus classification provided by 2 specialists in capsule endoscopy. Subsequently, we evaluated the performance of the network using an independent validation dataset (20% of total image pool), calculating its sensitivity, specificity, accuracy, and precision. Results: Our convolutional neural network detected blood and hematic residues in the small bowel lumen with an accuracy and precision of 98.5 and 98.7%, respectively. The sensitivity and specificity were 98.6 and 98.9%, respectively. The analysis of the testing dataset was completed in 24 s (approximately 184 frames/s). Discussion/Conclusion: We have developed an artificial intelligence tool capable of effectively detecting luminal blood. The development of these tools may enhance the diagnostic accuracy of capsule endoscopy when evaluating patients presenting with obscure small bowel bleeding.
Introdução: A endoscopia por cápsula revolucionou a abordagem a doentes com hemorragia digestiva obscura. No entanto, a leitura de imagens de endoscopia por cápsula é morosa, havendo suscetibilidade para a perda de lesões significativas, limitando desta forma a sua eficácia diagnóstica. Este estudo visou a criação de um algoritmo de deep learning para deteção automática de sangue e resíduos hemáticos no lúmen entérico usando imagens de endoscopia por cápsula. Métodos: Foi desenvolvida uma rede neural convolucional com base num conjunto de 22,095 imagens de endoscopia de cápsula (13,510 imagens contendo sangue e 8,585 mucosa normal ou outros achados). Foi construído um grupo de imagens para treino, compreendendo 80% do total de imagens. O desempenho da rede foi comparado com a classificação consenso de dois especialistas em endoscopia por cápsula. Posteriormente, o desempenho da rede foi avaliado usando os restantes 20% de imagens. Foi calculada a sua sensibilidade, especificidade, exatidão e precisão. Resultados: O algoritmo detetou sangue e resíduos hemáticos no lúmen do intestino delgado com uma exatidão e precisão de 98.5% e 98.7%, respetivamente. A sensibilidade e especificidade foram 98.6% e 98.9%, respetivamente. A análise do conjunto de usado para teste da rede foi concluída em 24 segundos (aproximadamente 184 frames/s). Discussão/Conclusão: Foi desenvolvida uma ferramenta de inteligência artificial capaz de detetar efetivamente o sangue luminal. O desenvolvimento dessas ferramentas pode aumentar a precisão do diagnóstico da endoscopia por cápsula ao avaliar pacientes que apresentam sangramento obscuro do intestino delgado.
RESUMEN
Endoscopic ultrasound (EUS) morphology can aid in the discrimination between mucinous and non-mucinous pancreatic cystic lesions (PCLs) but has several limitations that can be overcome by artificial intelligence. We developed a convolutional neural network (CNN) algorithm for the automatic diagnosis of mucinous PCLs. Images retrieved from videos of EUS examinations for PCL characterization were used for the development, training, and validation of a CNN for mucinous cyst diagnosis. The performance of the CNN was measured calculating the area under the receiving operator characteristic curve (AUC), sensitivity, specificity, and positive and negative predictive values. A total of 5505 images from 28 pancreatic cysts were used (3725 from mucinous lesions and 1780 from non-mucinous cysts). The model had an overall accuracy of 98.5%, sensitivity of 98.3%, specificity of 98.9% and AUC of 1. The image processing speed of the CNN was 7.2 ms per frame. We developed a deep learning algorithm that differentiated mucinous and non-mucinous cysts with high accuracy. The present CNN may constitute an important tool to help risk stratify PCLs.
RESUMEN
Background and study aims Colon capsule endoscopy (CCE) is a minimally invasive alternative to conventional colonoscopy. However, CCE produces long videos, making its analysis time-consuming and prone to errors. Convolutional neural networks (CNN) are artificial intelligence (AI) algorithms with high performance levels in image analysis. We aimed to develop a deep learning model for automatic identification and differentiation of significant colonic mucosal lesions and blood in CCE images. Patients and methods A retrospective multicenter study including 124 CCE examinations was conducted for development of a CNN model, using a database of CCE images including anonymized images of patients with normal colon mucosa, several mucosal lesions (erosions, ulcers, vascular lesions and protruding lesions) and luminal blood. For CNN development, 9005 images (3,075 normal mucosa, 3,115 blood and 2,815 mucosal lesions) were ultimately extracted. Two image datasets were created and used for CNN training and validation. Results The mean (standard deviation) sensitivity and specificity of the CNN were 96.3â% (3.9â%) and 98.2â% (1.8â%) Mucosal lesions were detected with a sensitivity of 92.0â% and a specificity of 98.5â%. Blood was detected with a sensitivity and specificity of 97.2â% and 99.9â%, respectively. The algorithm was 99.2â% sensitive and 99.6â% specific in distinguishing blood from mucosal lesions. The CNN processed 65 frames per second. Conclusions This is the first CNN-based algorithm to accurately detect and distinguish colonic mucosal lesions and luminal blood in CCE images. AI may improve diagnostic and time efficiency of CCE exams, thus facilitating CCE adoption to routine clinical practice.
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: capsule enteroscopy (CE) and 99mTc red blood cell (RBC) scintigraphy are frequently used in the investigation of obscure gastrointestinal bleeding (OGIB). There are few data comparing both diagnostic modalities. This study aimed to assess the performance of CE and scintigraphy for the diagnosis of OGIB. METHODS: patients who underwent CE and scintigraphy for OGIB were selected and analyzed retrospectively. The hemorrhagic potential of CE findings was rated using Saurin's classification. The concordance between both diagnostic techniques for bleeding detection and localization was analyzed. RESULTS: eighty-five patients (62 % female), with a median age of 63 years, were included in the study. Capsule enteroscopy identified 37 patients (43 %) with high hemorrhagic potential (P2) lesions. Most scintigraphy exams were positive for gastrointestinal bleeding (82 %). No concordance was found in the detection of lesions with hemorrhagic potential between CE and scintigraphy (kappa < 0). The distribution of P0, P1 and P2 findings was similar in patients with positive or negative scintigraphy (p = 0.526). There was no agreement regarding the location of P2 findings in CE and the bleeding detected by scintigraphy (kappa < 0). Patients with P2 lesions had significantly lower median levels of hemoglobin (p = 0.002) at presentation. No significant differences were found in hemoglobin values between patients with positive and negative scintigraphy (p = 0.058). CONCLUSION: significant diagnostic discrepancy was observed between CE and scintigraphy. The findings of CE correlated better with hemoglobin values at presentation than scintigraphy results. Therefore, scintigraphy does not appear to be useful in the diagnostic workup of OGIB.
Asunto(s)
Endoscopía Capsular , Hemorragia Gastrointestinal/diagnóstico por imagen , Endoscopía Capsular/métodos , Femenino , Hemoglobinas , Humanos , Masculino , Persona de Mediana Edad , Radioisótopos , Estudios RetrospectivosRESUMEN
Drug-induced liver injury is an important cause of acute liver injury. Immunomodulatory therapies, such as vedolizumab (VDZ), are being increasingly used for the treatment of several diseases, most importantly inflammatory bowel disease. Several studies have demonstrated the safety of this substance. To date, only one post-marketing study has reported a case of hepatotoxicity attributable to VDZ. The authors present the case of a 41-year-old woman followed at the gastroenterology outpatient clinic for ulcerative colitis (UC) and autoimmune hepatitis (AIH). This patient was being treated with low-dose glucocorticoids for AIH (prednisolone 10 mg), with adequate disease control. Additionally, she was being treated with oral salicylates (mesalamine 3 g/day) and oral budesonide (9 mg/day) for her UC. For uncontrolled UC, she was started on VDZ. Two weeks after the first infusion of VDZ, the patient developed a clinical and analytical phenotype compatible with acute hepatitis. Diagnostic workup for causes of hepatocellular liver injury retrieved no results. A liver biopsy corroborated the diagnosis of toxic hepatitis overlapping chronic liver disease. VDZ was withdrawn and the patient experienced complete recovery of liver tests over the following weeks. In this case report, we present the first post-marketing case of hepatocellular liver injury in probable relation to VDZ.
A hepatotoxicidade induzida por fármacos é uma causa importante de lesão hepática aguda. As terapêuticas imunomoduladoras, como o vedolizumab (VDZ), são cada vez mais utilizadas para o tratamento de diversas patologias, particularmente a doença inflamatória do intestino. Vários estudos comprovaram o perfil de segurança favorável do VDZ. Até à data, apenas foi relatado um caso de hepatotoxicidade atribuída ao VDZ em estudos de farmacovigilância pós comercialização. Os autores apresentam o caso de uma mulher de 41 anos, seguida em Gastrenterologia por colite ulcerosa (CU) e hepatite autoimune (HAI). A doença hepática desta doente encontrava-se eficazmente controlada com corticoterapia em baixa dose (prednisolona 10 mg). Concomitantemente, a terapêutica dirigida à CU incluía salicilatos (messalazina 3 g/dia) e budesonido (9 mg/dia) orais. Por apresentar CU não controlada com o esquema referido, iniciou VDZ. Duas semanas após a primeira infusão de VDZ, a doente desenvolve manifestações clínicas e analíticas compatíveis com quadro de hepatite. Do estudo etiológico realizado, nenhuma causa foi identificada como responsável pela lesão hepatocelular. Foi realizada uma biópsia hepática que corroborou o diagnóstico de hepatite tóxica a sobreporse a características de doença hepática crónica. A terapêutica com VDZ foi interrompida e a doente apresentou recuperação de valores normais do perfil hepático durante as semanas que se sucederam. Com este trabalho, os autores expõem o primeiro caso pós-comercialização de lesão hepatocelular em provável relação com VDZ.