An automatic gastric polyp detection technique using deep learning

Mushtaq, Dania; Madni, Tahir Mustafa; Janjua, Uzair Iqbal; Anwar, Fareeha; Kakakhail, Ahmad

doi:10.1002/ima.22850

Cited by 11 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, when comparing the performance of recent research papers on object detection in gastrointestinal endoscopy, a study conducted by using the InVNorm model [31] achieved an mAP of 84.2% by applying interpretable style normalization, without compromising the reliability of medical data augmentation. Another study proposed the ASSD-GPNet model [32], which achieved an mAP of 94.2% for gastrointestinal endoscopy videos and 76.9% for the Pascal VOC dataset. This model demonstrated outstanding performance by generating intricate feature maps that focus on specific information, aiding in the detection of small polyps.…”

Section: Results Of the Proposed Modelmentioning

confidence: 99%

YOLO-MR: Meta-Learning-Based Lesion Detection Algorithm for Resolving Data Imbalance

Lee,

Kim,

Park

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The early detection and precise diagnosis of gastrointestinal diseases, particularly gastric cancer, play a vital role in improving patient survival rates and treatment outcomes. However, diagnosing these conditions can be challenging when symptoms are mild or absent. Endoscopy is commonly used for diagnosis, but it requires endoscopists with a high level of specialized knowledge to accurately identify diseases. By integrating artificial intelligence (AI) with endoscopic imaging, AI can assist in diagnosis, reduce missed cases, and enable early treatment, thereby improving patient survival rates. Previous studies have mainly focused on improving disease classification and accuracy, often overlooking disproportionate and limited medical data reliability issues. In this study, we propose a solution to address the challenges posed by imbalanced and sparse medical image data by introducing model-agnostic meta-learning (MAML).To accomplish this, we employ the YOLO-MR model, which incorporates the concept of meta-recognition into the You Only Look Once (YOLO) model. Experimental results demonstrate that the mean average precision (mAP) of the conventional YOLO model is low at 41.7, indicating a significant impact of data imbalance. Traditional data augmentation methods provide a low mAP of 65.2, while the proposed YOLO-MR model achieves an impressive mAP of 96. This is significantly higher than the conventional YOLO model by 54.3, reducing accuracy disparities between different disease classes and addressing the issue of data imbalance. Furthermore, this research showcases the effectiveness of innovative techniques such as MAML and residual blocks in addressing data imbalance in medical image recognition. These findings hold substantial potential for tackling the challenges posed by limited and imbalanced medical data in the healthcare field.INDEX TERMS Endoscopy, you only look once (YOLO), meta-learning, model-agnostic meta-learning (MAML), residual block

show abstract

Section: Results Of the Proposed Modelmentioning

confidence: 99%

YOLO-MR: Meta-Learning-Based Lesion Detection Algorithm for Resolving Data Imbalance

Lee,

Kim,

Park

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Risk factors for stomach cancer include chronic superficial gastritis. It is crucial to conduct fast and accurate stomach cancer screenings [34]. Other risk factors include recurrent Helicobacter pylori infection, pernicious anemia, and consuming too much salt.…”

Section: Input Variables and Predicting Gastric Cancermentioning

confidence: 99%

Diagnosis of gastric cancer in role of endoscopic imaging techniques in artificial intelligence and machine learning applications: An overview

K.,

Kanna R.

2024

E3S Web Conf.

View full text Add to dashboard Cite

Gastric cancer is a serious medical issue because its occurrence and death rates are increasing all over the world. Furthermore, obesity, tobacco use, alcohol consumption, and a few dietary defense elements are known cancer-causing agents. In some nations, early detection strategies have been shown to reduce GC-related morbidity and mortality. It offers therapies that are minimally invasive like most effective procedure is endoscopic resection. The most appropriate standard for using a procedure that is typically secure to precisely evaluate the lesions region. It is simple method and it can be expected difficult techniques can be viewed as in early stage of tumour in accurate diagnosis. A few uses of computerized method have arisen in the field of gastric malignant growth. For example, image diagnosis-based prediction conclusion and guess expectation, because of its viable computational power and learning capabilities. As a result, a detailed outline of how artificial intelligence can be used to treat gastric cancer through image-based endoscopic diagnosis and machine learning analysis applications this review, which demonstrates the future developments in this field for the early prediction of gastric cancer, it was also thoroughly discussed the possibility of AI models being over fitted, their accuracy, and their usefulness to clinical research in this field of image processing. In addition, in this review article was been detailed about synopsis of the therapy choices of malignant growth.

show abstract

“…Zoom‐in‐Net underscores the critical role of localized high‐resolution areas in lesion detection [35]. To address feature loss in gastric polyps, Mushtaq et al developed a novel model for polyp detection: the Attention‐based SSD for Gastric Polyps (ASSD‐GPNet) [36]. YOLO‐SG, a deep learning model, enhances the detection of minuscule lesions through saliency maps [37].…”

Section: Related Workmentioning

confidence: 99%

SOCR‐YOLO: Small Objects Detection Algorithm in Medical Images

Liu,

Li,

Jiang

et al. 2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

In the field of medical image analysis, object detection plays a crucial role by providing interpretable diagnostic information to healthcare professionals. Although current object detection models have achieved remarkable success in conventional images, their performance in detecting abnormalities in medical images has not been as satisfactory. This is primarily due to the complexity of anatomical structures in medical images, and the fact that some lesions may have subtle features, particularly in the case of early‐stage, small‐scale abnormalities. To address this challenge, we introduce SOCR‐YOLO, a novel lesion detection model with online convolutional reparameterization based on channel shuffling. First, it employs the SOCR (Shuffled Channel with Online Convolutional Re‐parameterization) module to establish a connection between feature concatenation and computational efficiency, aiming to extract more comprehensive information while reducing time consumption. Second, it incorporates the Bi‐FPN structure to achieve multiscale feature fusion. Lastly, the loss function has been optimized to improve the model training process. We evaluated two datasets, chest x‐ray (Vindr‐CXR) and brain tumor (Br35H), provided by the Kaggle competition. Experimental results show that the proposed method has outperformed several state‐of‐the‐art models, including YOLOv8, YOLO‐NAS, and RT‐DETR, in both speed and accuracy. Notably, in the context of chest x‐ray anomaly detection, SOCR‐YOLO exhibits a 1.8% enhancement in accuracy over YOLOv8 while simultaneously reducing floating‐point operations by 26.3%. Additionally, a similar 1.8% improvement in accuracy is observed in the detection of brain tumors. The results indicate the superior ability of our model to detect multiscale variations and small lesions.

show abstract

An automatic gastric polyp detection technique using deep learning

Cited by 11 publications

References 41 publications

YOLO-MR: Meta-Learning-Based Lesion Detection Algorithm for Resolving Data Imbalance

YOLO-MR: Meta-Learning-Based Lesion Detection Algorithm for Resolving Data Imbalance

Diagnosis of gastric cancer in role of endoscopic imaging techniques in artificial intelligence and machine learning applications: An overview

SOCR‐YOLO: Small Objects Detection Algorithm in Medical Images

Contact Info

Product

Resources

About