Deep Neural Networks approaches for detecting and classifying colorectal polyps

Nogueira-Rodríguez, Alba; Domínguez-Carbajales, Rubén; López-Fernández, Hugo; Iglesias, Águeda; Cubiella, Joaquín; Fdez-Riverola, Florentino; Reboiro-Jato, Miguel; Glez-Peña, Daniel

doi:10.1016/j.neucom.2020.02.123

Cited by 70 publications

(42 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Current novel technologies have been applied in order to aid adenoma detection by using deep learning techniques. With the intent of improving ADRs, computer algorithms driven by CNNs may accurately detect and localize the presence of premalignant lesions [46]. A CNN represents a particular type of artificial neural network and deep learning technique that is highly effective at performing medical image analysis [47] (Figure 2).…”

Section: Colonoscopymentioning

confidence: 99%

“…Information from a complete blood count (CBC), including findings indicative of either microcytic iron deficiency anemia or a combination of anemia and elevated red cell distribution width (RDW), may help physicians estimate the cancer risk [62][63][64]. In fact, previous research revealed that RDW showed a sensitivity of 84% and a specificity of 88% for right-sided colon cancer [46]. In a binational retrospective study, Kinar et al [63] used electronic medical records of two independent (unrelated) groups of individuals (Israeli and UK datasets) and designed an AI-assisted prediction model (MeScore ® , Calgary, Alberta, Canada) for identifying people at high risk for CRC.…”

Section: Blood Testsmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence in Colorectal Cancer Screening, Diagnosis and Treatment. A New Era

et al. 2021

View full text Add to dashboard Cite

The development of artificial intelligence (AI) algorithms has permeated the medical field with great success. The widespread use of AI technology in diagnosing and treating several types of cancer, especially colorectal cancer (CRC), is now attracting substantial attention. CRC, which represents the third most commonly diagnosed malignancy in both men and women, is considered a leading cause of cancer-related deaths globally. Our review herein aims to provide in-depth knowledge and analysis of the AI applications in CRC screening, diagnosis, and treatment based on current literature. We also explore the role of recent advances in AI systems regarding medical diagnosis and therapy, with several promising results. CRC is a highly preventable disease, and AI-assisted techniques in routine screening represent a pivotal step in declining incidence rates of this malignancy. So far, computer-aided detection and characterization systems have been developed to increase the detection rate of adenomas. Furthermore, CRC treatment enters a new era with robotic surgery and novel computer-assisted drug delivery techniques. At the same time, healthcare is rapidly moving toward precision or personalized medicine. Machine learning models have the potential to contribute to individual-based cancer care and transform the future of medicine.

show abstract

Section: Colonoscopymentioning

confidence: 99%

Section: Blood Testsmentioning

confidence: 99%

Artificial Intelligence in Colorectal Cancer Screening, Diagnosis and Treatment. A New Era

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Polyp classification is a widely researched problem in the medical image analysis community [ 12 ], [ 13 ]. Previous work has used traditional methods for hand-crafted feature extraction using color, texture, and 3D features for polyp classification in videos [ 14 ].…”

Section: Background and Previous Workmentioning

confidence: 99%

Improving Colonoscopy Lesion Classification Using Semi-Supervised Deep Learning

et al. 2021

View full text Add to dashboard Cite

While data-driven approaches excel at many image analysis tasks, the performance of these approaches is often limited by a shortage of annotated data available for training. Recent work in semi-supervised learning has shown that meaningful representations of images can be obtained from training with large quantities of unlabeled data, and that these representations can improve the performance of supervised tasks. Here, we demonstrate that an unsupervised jigsaw learning task, in combination with supervised training, results in up to a 9.8% improvement in correctly classifying lesions in colonoscopy images when compared to a fully-supervised baseline. We additionally benchmark improvements in domain adaptation and out-of-distribution detection, and demonstrate that semi-supervised learning outperforms supervised learning in both cases. In colonoscopy applications, these metrics are important given the skill required for endoscopic assessment of lesions, the wide variety of endoscopy systems in use, and the homogeneity that is typical of labeled datasets.

show abstract

“…In this study, we utilized YOLOv3 as a processing library, because it has a good performance in both speed and accuracy [45]. Therefore, YOLOv3 was applied and adapted to detect colorectal polyp in other works [43,46,47]. Basically, the deep neural network feeds the input images through feature extractor blocks followed by a detector; if a polyp was detected, a bounding box surrounding it was overlaid on the input as shown in Figure 5.…”

Section: Deep-learning-based Automated Intestinal Polyp Detectionmentioning

confidence: 99%

“…These systems have demonstrated promising results with high sensitivity and specificity for obscure gastrointestinal bleeding (OGIB) [35][36][37], Crohn disease lesions [38,39], polyps [40][41][42], and so on. Especially for colorectal polyp detection, deep learning models show remarkable performances as summarized in [43]. However, due to the lack of CE motion controllability and position information, tracking the target during diagnostic procedures and marking suspicious regions for post-procedure have not been addressed yet.…”

Section: Introductionmentioning

confidence: 99%

Automated Bowel Polyp Detection Based on Actively Controlled Capsule Endoscopy: Feasibility Study

Hoang

Nguyen²,

Kim³

et al. 2021

Diagnostics

View full text Add to dashboard Cite

This paper presents an active locomotion capsule endoscope system with 5D position sensing and real-time automated polyp detection for small-bowel and colon applications. An electromagnetic actuation system (EMA) consisting of stationary electromagnets is utilized to remotely control a magnetic capsule endoscope with multi-degree-of-freedom locomotion. For position sensing, an electronic system using a magnetic sensor array is built to track the position and orientation of the magnetic capsule during movement. The system is integrated with a deep learning model, named YOLOv3, which can automatically identify colorectal polyps in real-time with an average precision of 85%. The feasibility of the proposed method concerning active locomotion and localization is validated and demonstrated through in vitro experiments in a phantom duodenum. This study provides a high-potential solution for automatic diagnostics of the bowel and colon using an active locomotion capsule endoscope, which can be applied for a clinical site in the future.

show abstract

Deep Neural Networks approaches for detecting and classifying colorectal polyps

Cited by 70 publications

References 54 publications

Artificial Intelligence in Colorectal Cancer Screening, Diagnosis and Treatment. A New Era

Artificial Intelligence in Colorectal Cancer Screening, Diagnosis and Treatment. A New Era

Improving Colonoscopy Lesion Classification Using Semi-Supervised Deep Learning

Automated Bowel Polyp Detection Based on Actively Controlled Capsule Endoscopy: Feasibility Study

Contact Info

Product

Resources

About