Fig 8 - uploaded by Clifford K. Yang
Content may be subject to copyright.
Illustration of the network architecture of VGG-19 model: conv means convolution, FC means fully connected

Illustration of the network architecture of VGG-19 model: conv means convolution, FC means fully connected

Context in source publication

Context 1
... and Zisserman of the University of Oxford created a 19-layer (16 conv., 3 fully-connected) CNN that strictly used 3×3 filters with stride and pad of 1, along with 2×2 max-pooling layers with stride 2, called VGG-19 model. 28,29 Compared to AlexNet, the VGG-19 (see Fig. 8) is a deeper CNN with more layers. To reduce the number of parameters in such deep networks, it uses small 3×3 filters in all convolutional layers and best utilized with its 7.3% error rate. The VGG-19 model was not the winner of ILSVRC 30 2014, however, the VGG Net is one of the most influential papers because it reinforced the notion ...

Similar publications

Article
Full-text available
The radiation dose delivered to patients undergoing mammography examination is of utmost importance because of the risk of cancer induction due to the process. In this work, we analyze the dose to 109 patients (214 images) who underwent mammographic examinations with a full-field digital mammography (FFDM) system. Quality control assessment was fir...
Preprint
Full-text available
Deep learning models designed for visual classification tasks on natural images have become prevalent in medical image analysis. However, medical images differ from typical natural images in many ways, such as significantly higher resolutions and smaller regions of interest. Moreover, both the global structure and local details play important roles...
Article
Full-text available
There is uncertainty about the magnitude of the effect of screening mammography on breast‐cancer mortality. The relevance and validity of evidence from dated RCTs has been questioned, while observational studies often lack a valid comparison group. There is no estimate of the effect of one screening invitation only. We exploited the geographic roll...
Article
Full-text available
To investigate the value of contrast-enhanced mammography (CEM) compared to full-field digital mammography (FFDM) in screening breast cancer patients after breast-conserving surgery (BCS), this Health Insurance Portability and Accountability Act-compliant, institutional review board-approved retrospective, single-institution study included 971 CEM...

Citations

... Deep learning has attracted significant attention since 2018. Kooi and Karssemeijer and Zheng et al. proposed DL algorithms for the detection of breast masses using temporal analysis (Figure 4) [52,53]. Both studies exploited deep CNNs. ...
... (a,b) Right CC (1051 × 1521 pixels) and MLO (1069 × 1746 pixels) views of the recent mammogram with a mass present and marked by a yellow rectangle. (c,d) Right CC and MLO from a prior exam 1 year earlier (not aligned yet), which was normal (reprint with permission from[52]). ...
Article
Full-text available
Radiologists assess the results of mammography, the key screening tool for the detection of breast cancer, to determine the presence of malignancy. They, routinely, compare recent and prior mammographic views to identify changes between the screenings. In case a new lesion appears in a mammogram, or a region is changing rapidly, it is more likely to be suspicious, compared to a lesion that remains unchanged and it is usually benign. However, visual evaluation of mammograms is challenging even for expert radiologists. For this reason, various Computer-Aided Diagnosis (CAD) algorithms are being developed to assist in the diagnosis of abnormal breast findings using mammograms. Most of the current CAD systems do so using only the most recent mammogram. This paper provides a review of the development of methods to emulate the radiological approach and perform automatic segmentation and/or classification of breast abnormalities using sequential mammogram pairs. It begins with demonstrating the importance of utilizing prior views in mammography, through the review of studies where the performance of expert and less-trained radiologists was compared. Following, image registration techniques and their application to mammography are presented. Subsequently, studies that implemented temporal analysis or subtraction of temporally sequential mammograms are summarized. Finally, a description of the open access mammography datasets is provided. This comprehensive review can serve as a thorough introduction to the use of prior information in breast cancer CAD systems but also provides indicative directions to guide future applications.
... VGG-19 consists of 19 layers which use convolutional layers with a 3×3 size core with max-pooling layers. It has two fully connected layers, each with 4096 nodes, which are then followed by a Softmax layer which together form the classifier (Zheng et al., 2018). ...
... Features are extracted from recent and prior images and, then, subtracted for the creation of a temporal feature vector that is used in the classification. The effectiveness of temporal analysis for the diagnosis of breast masses has been assessed thoroughly [13,14,15,16,17,18]. Despite the fact that the findings are promising, temporal analysis offers no benefit, compared to using only the most recent mammographic view, when the findings are new with no traces of abnormality in the prior screening. ...
Article
Full-text available
Objective: Cancer remains a major cause of morbidity and mortality globally, with 1 in 5 of all new cancers arising in the breast. The introduction of mammography for the radiological diagnosis of breast abnormalities, significantly decreased their mortality rates. Accurate detection and classification of breast masses in mammograms is especially challenging for various reasons, including low contrast and the normal variations of breast tissue density. Various Computer-Aided Diagnosis (CAD) systems are being developed to assist radiologists with the accurate classification of breast abnormalities. Methods: In this study, subtraction of temporally sequential digital mammograms and machine learning are proposed for the automatic segmentation and classification of masses. The performance of the algorithm was evaluated on a dataset created especially for the purposes of this study, with 320 images from 80 patients (two time points and two views of each breast) with precisely annotated mass locations by two radiologists. Results: Ninety-six features were extracted and ten classifiers were tested in a leave-one-patient-out and k-fold cross-validation process. Using Neural Networks, the detection of masses was 99.9% accurate. The classification accuracy of the masses as benign or suspicious increased from 92.6%, using the state-of-the-art temporal analysis, to 98%, using the proposed methodology. The improvement was statistically significant (p-value < 0.05). Conclusion: These results demonstrate the effectiveness of the subtraction of temporally consecutive mammograms for the diagnosis of breast masses. Clinical and Translational Impact Statement: The proposed algorithm has the potential to substantially contribute to the development of automated breast cancer Computer-Aided Diagnosis systems with significant impact on patient prognosis.
... The first step of the algorithm: the image passes through the underlying network of the convolutional neural network and extracts feature maps of the input data. For this, the first 10 layers of the popular VGG-19 network [16] are used. Next, the feature map is processed in a multi-stage convolutional network pipeline to create detail confidence maps and a detail similarity field. ...
... VGG 19 architecture[22]. ...
Article
This study investigated the effect of the class number on the prediction performance of the convolutional neural network (CNN) classification model that is applied in fire detectors to reduce nuisance fire alarms by appropriately recognizing fire images including those of flames and smoke. A CNN model trained by transfer learning using five image datasets of flame, smoke, normal, haze, and light was realized and trained by altering the class number to generate the classification model. A total of three classification models were generated as follows: classification model 1 was trained using normal and fire images including flames and smoke; classification model 2 was trained using flame, smoke, and normal images; and classification model 3 was trained using flames, smoke, normal, and haze, and light images. A test image dataset independent of training was used to assess the prediction performance of the three classification models. The results indicate that the prediction accuracy for classification models 1, 2, and 3 were approximately 93.0%, 94.2%, and 97.3%, respectively. The performance of the predicted classification improved as the class number increased, because the model could learn with greater precision the features of the normal images that are similar to those of the fire images.
... Convolutional Neural Networks (CNNs) are a powerful combination of math, biology, and computer science. These neural networks have been one of the most effective innovations in the fields of AI and CV [30]. CNN enables learning and obtaining large quantities of information from raw data abstraction levels [31]. ...
Article
Intelligent systems can be used to build systems that simulate human behavior. One such system is lip reading. Hence, lip reading is considered one of the hardest problems in image analysis, and thus machine learning is used to solve this problem, which achieves remarkable results, especially when using a deep neural network, in which it dives deeply into the texture of any input. Microlearning is the new trend in E-learning. It is based on small pieces of information to make the learning process easier and more productive. In this paper, a proposed system for multi-layer lip reading is presented. The proposed system is based on micro content (letters) to achieve the lip reading process using deep learning and auto-correction models for error detection and correction of the accumulated words spelled by the lip reading system.The proposed system was implemented on a proposed dataset gathered using 20 persons of different ages and genders. The model achieved 98% accuracy in micro content recognition and 73.6% accuracy in accumulated word lip reading.
... There are 19.6 billion FLOPs in VGG19. The VGG-19 model becomes simpler and more useful as 3 x 3 convolutional layers are layered on top of each other to increase with depth level [18,19]. In VGG-19, Max pooling layers were utilized as a handler to minimize the volume size. ...
Preprint
Full-text available
Deep learning is currently the most important branch of machine learning, with applications in speech recognition, computer vision, image classification, and medical imaging analysis. Plant recognition is one of the areas where image classification can be used to identify plant species through their leaves. Botanists devote a significant amount of time to recognizing plant species by personally inspecting. This paper describes a method for dissecting color images of Swedish leaves and identifying plant species. To achieve higher accuracy, the task is completed using transfer learning with the help of pre-trained classifier VGG-19. The four primary processes of classification are image preprocessing, image augmentation, feature extraction, and recognition, which are performed as part of the overall model evaluation. The VGG-19 classifier grasps the characteristics of leaves by employing pre-defined hidden layers such as convolutional layers, max pooling layers, and fully connected layers, and finally uses the soft-max layer to generate a feature representation for all plant classes. The model obtains knowledge connected to aspects of the Swedish leaf dataset, which contains fifteen tree classes, and aids in predicting the proper class of an unknown plant with an accuracy of 99.70% which is higher than previous research works reported.
... Up to 1000 items can be classified using this pre-trained network. The network was trained using colorful images with a resolution of 224 × 224 pixels ( Figure 3 [118]). ...
Article
Full-text available
Recycling tasks are the most effective method for reducing waste generation, protecting the environment, and boosting the overall national economy. The productivity and effectiveness of the recycling process are strongly dependent on the cleanliness and precision of processed primary sources. However, recycling operations are often labor intensive, and computer vision and deep learning (DL) techniques aid in automatically detecting and classifying trash types during recycling chores. Due to the dimensional challenge posed by pre-trained CNN networks, the scientific community has developed numerous techniques inspired by biology, swarm intelligence theory, physics, and mathematical rules. This research applies a new meta-heuristic algorithm called the artificial hummingbird algorithm (AHA) to solving the waste classification problem based on feature selection. However, the performance of the AHA is barely satisfactory; it may be stuck in optimal local regions or have a slow convergence. To overcome these limitations, this paper develops two improved versions of the AHA called the AHA-ROBL and the AHA-OBL. These two versions enhance the exploitation stage by using random opposition-based learning (ROBL) and opposition-based learning (OBL) to prevent local optima and accelerate the convergence. The main purpose of this paper is to apply the AHA-ROBL and AHA-OBL to select the relevant deep features provided by two pre-trained models of CNN (VGG19 & ResNet20) to recognize a waste classification. The TrashNet dataset is used to verify the performance of the two proposed approaches (the AHA-ROBL and AHA-OBL). The effectiveness of the suggested methods (the AHA-ROBL and AHA-OBL) is compared with that of 12 modern and competitive optimizers, namely the artificial hummingbird algorithm (AHA), Harris hawks optimizer (HHO), Salp swarm algorithm (SSA), aquila optimizer (AO), Henry gas solubility optimizer (HGSO), particle swarm optimizer (PSO), grey wolf optimizer (GWO), Archimedes optimization algorithm (AOA), manta ray foraging optimizer (MRFO), sine cosine algorithm (SCA), marine predators algorithm (MPA), and rescue optimization algorithm (SAR). A fair evaluation of the proposed algorithms’ performance is achieved using the same dataset. The performance analysis of the two proposed algorithms is applied in terms of different measures. The experimental results confirm the two proposed algorithms’ superiority over other comparative algorithms. The AHA-ROBL and AHA-OBL produce the optimal number of selected features with the highest degree of precision.
... VGG19 Architecture[121] ...
Article
Recycling tasks are the most effective method for reducing waste generation, protecting the environment, and boosting the overall national economy. Productivity and effectiveness of the recycling process are strongly dependent on the cleanliness and precision of the processed primary sources. On the other hand, recycling operations are often labor-intensive, and computer vision and deep learning (DL) techniques aid in automatically detecting and classifying trash types during recycling chores. Due to the dimensional challenge posed by pre-trained CNN networks, the scientific community has developed numerous techniques inspired by biology, swarm intelligence theory, physics, and mathematical rules. This research applies a new meta-heuristic algorithm called Artificial Hummingbird Algorithm (AHA) for solving the Waste classification Problem based on Feature Selection. However, the performance of AHA is barely satisfactory; it may be stuck in optimal local regions or has a slow convergence. To overcome these limitations, this paper develops two improved versions of AHA called AHA-ROBL \& AHA-OBL. \textcolor{red}{These two versions enhance the exploitation stage by using Random Opposition-based Learning(ROBL) and Opposition-based Learning(OBL) to prevent local optima and accelerate the convergence}. The main purpose of this paper is to apply AHA-ROBL and AHA-OBL to select the relevant deep features provided by two pre-trained models of CNN (VGG19 \& ResNet20) to recognize the Waste Classification. The TrashNet dataset verifies the performance of the two proposed approaches (AHA-ROBL and AHA-OBL). The effectiveness of the suggested methods (AHA-ROBL and AHA-OBL) are compared with twelve modern and competitive optimizers such as Artificial Hummingbird Algorithm (AHA), Harris Hawks Optimization (HHO), Salp Swarm Algorithm (SSA), Aquila Optimizer (AO), Henry Gas Solubility Optimization (HGSO), Particle swarm optimization (PSO), Grey Wolf Optimizer (GWO), and Archimedes Optimization Algorithm (AOA), Manta Ray Foraging Optimization (MRFO), Sine Cosine Algorithm (SCA), Marine predators algorithm (MPA),\textcolor{red}{and} Rescue optimization algorithm (SAR). A fair evaluation of the algorithm's performance is achieved using the same dataset. The performance analysis of the two proposed algorithms is applied in terms of different measures . The experimental results confirm the two proposed algorithm's superiority over other comparative algorithms. AHA-ROBL \& AHA-OBL produce the optimal number of selected features with the highest degree of precision.