A Comparative Analysis of Deep Learning-Based Approaches for Classifying Dental Implants Decision Support System.

This study aims to provide an effective solution for the autonomous identification of dental implant brands through a deep learning-based computer diagnostic system. It also seeks to ascertain the system's potential in clinical practices and to offer a strategic framework for improving diagnosis and treatment processes in implantology. This study employed a total of 28 different deep learning models, including 18 convolutional neural network (CNN) models (VGG, ResNet, DenseNet, EfficientNet, RegNet, ConvNeXt) and 10 vision transformer models (Swin and Vision Transformer). The dataset comprises 1258 panoramic radiographs from patients who received implant treatments at Erciyes University Faculty of Dentistry between 2012 and 2023. It is utilized for the training and evaluation process of deep learning models and consists of prototypes from six different implant systems provided by six manufacturers. The deep learning-based dental implant system provided high classification accuracy for different dental implant brands using deep learning models. Furthermore, among all the architectures evaluated, the small model of the ConvNeXt architecture achieved an impressive accuracy rate of 94.2%, demonstrating a high level of classification success.This study emphasizes the effectiveness of deep learning-based systems in achieving high classification accuracy in dental implant types. These findings pave the way for integrating advanced deep learning tools into clinical practice, promising significant improvements in patient care and treatment outcomes.

A robust deep learning model for the classification of dental implant brands.

OBJECTIVE: In cases where the brands of implants are not known, treatment options can be significantly limited in potential complications arising from implant procedures. This research aims to explore the application of deep learning techniques for the classification of dental implant systems using panoramic radiographs. The primary objective is to assess the superiority of the proposed model in achieving accurate and efficient dental implant classification. MATERIAL AND METHODS: A comprehensive analysis was conducted using a diverse set of 25 convolutional neural network (CNN) models, including popular architectures such as VGG16, ResNet-50, EfficientNet, and ConvNeXt. The dataset of 1258 panoramic radiographs from patients who underwent implant treatment at faculty of dentistry was utilized for training and evaluation. Six different dental implant systems were employed as prototypes for the classification task. The precision, recall, F1 score, and support scores for each class have included in the classification accuracy report to ensure accurate and reliable results from the model. RESULTS: The experimental results demonstrate that the proposed model consistently outperformed the other evaluated CNN architectures in terms of accuracy, precision, recall, and F1-score. With an impressive accuracy of 95.74 % and high precision and recall rates, the ConvNeXt model showcased its superiority in accurately classifying dental implant systems. Notably, the model's performance was achieved with a relatively smaller number of parameters, indicating its efficiency and speed during inference. CONCLUSION: The findings highlight the effectiveness of deep learning techniques, particularly the proposed model, in accurately classifying dental implant systems from panoramic radiographs.

An efficient real-time colonic polyp detection with YOLO algorithms trained by using negative samples and large datasets.

Colorectal cancer (CRC) is one of the common types of cancer with a high mortality rate. Colonoscopy is the gold standard for CRC screening and significantly reduces CRC mortality. However, due to many factors, the rate of missed polyps, which are the precursors of colorectal cancer, is high in practice. Therefore, many artificial intelligence-based computer-aided diagnostic systems have been presented to increase the detection rate of missed polyps. In this article, we present deep learning-based methods for reliable computer-assisted polyp detection. The proposed methods differ from state-of-the-art methods as follows. First, we improved the performances of YOLOv3 and YOLOv4 object detection algorithms by integrating Cross Stage Partial Network (CSPNet) for real-time and high-performance automatic polyp detection. Then, we utilized advanced data augmentation techniques and transfer learning to improve the performance of polyp detection. Next, for further improving the performance of polyp detection using negative samples, we substituted the Sigmoid-weighted Linear Unit (SiLU) activation functions instead of the Leaky ReLU and Mish activation functions, and Complete Intersection over Union (CIoU) as the loss function. In addition, we present a comparative analysis of these activation functions for polyp detection. We applied the proposed methods on the recently published novel datasets, which are the SUN polyp database and the PICCOLO database. Additionally, we investigated the proposed models for MICCAI Sub-Challenge on Automatic Polyp Detection in Colonoscopy dataset. The proposed methods outperformed the other studies in both real-time performance and polyp detection accuracy.

A comprehensive review of deep learning in colon cancer.

Deep learning has emerged as a leading machine learning tool in object detection and has attracted attention with its achievements in progressing medical image analysis. Convolutional Neural Networks (CNNs) are the most preferred method of deep learning algorithms for this purpose and they have an essential role in the detection and potential early diagnosis of colon cancer. In this article, we hope to bring a perspective to progress in this area by reviewing deep learning practices for colon cancer analysis. This study first presents an overview of popular deep learning architectures used in colon cancer analysis. After that, all studies related to colon cancer analysis are collected under the field of colon cancer and deep learning, then they are divided into five categories that are detection, classification, segmentation, survival prediction, and inflammatory bowel diseases. Then, the studies collected under each category are summarized in detail and listed. We conclude our work with a summary of recent deep learning practices for colon cancer analysis, a critical discussion of the challenges faced, and suggestions for future research. This study differs from other studies by including 135 recent academic papers, separating colon cancer into five different classes, and providing a comprehensive structure. We hope that this study is beneficial to researchers interested in using deep learning techniques for the diagnosis of colon cancer.