Dense Convolutional Neural Network Research Articles

A Novel Approach to Optimizing Convolutional Neural Networks for Improved Digital Image Segmentation

To divide a digital image into individual parts that share similar characteristics is known as digital image segmentation, and it is a vital research subject in the field of computer vision. Object recognition, medical imaging, surveillance, and video processing are just a few of the many real-world contexts where this study could prove useful. While digital image segmentation research has come a long way, there are still certain obstacles to overcome. Segmentation algorithms frequently encounter challenges in achieving both accuracy and efficiency when confronted with intricate settings, noisy pictures, or fluctuating lighting conditions. The absence of established evaluation standards adds complexity to the process of performing equitable comparisons among different segmentation methodologies. Due to the subjective nature of photo segmentation, attaining consistent results among specialists can be challenging. The integration of machine learning and deep neural networks into segmentation algorithms has introduced new challenges, including the need for large amounts of annotated data and the interpretability of the outcomes. Given these challenges, the objective of this study is to enhance the segmentation model. To this end, this research suggests a model of convolutional neural networks that is optimal for digital picture segmentation. The model is based on a dense convolution neural network, and it incorporates a transfer learning technique to significantly boost the model’s robustness and the quality of picture segmentation. The model’s adaptability to new datasets is improved by the incorporation of a transfer learning method. As demonstrated by experimental results on two publicly available datasets, the suggested methodology considerably enhances the resilience of digital picture segmentation.

MODELLING A DENSE NETWORK CONNECTIVITY FOR PANOPTIC TOOTH SEGMENTATION USING LEARNING APPROACHES

By enabling precise diagnoses and assisting in creating successful treatment regimens, teeth segmentation plays a crucial role in dentistry. The segmentation of teeth has been the primary emphasis of previous approaches, but they frequently ignore the context of the oral tissue as a whole. According to this study, background semantic and foreground instance-based segmentation results are combined in a panoptic-segmentation-based approach. This work provides a tailored architecture for segmenting using a Super Adaptive Dense Convolutional Neural Network () with a panoptic quality (PQ) loss function. The PQ loss function speeds up learning and enables the model to predict masks and the classes that go with them instantly. In our suggested design, enables connectivity between the memory path and the pixel route. A stacked network block integrating multi-scale properties from several decoding resolutions is also included. The network block's primary duties involve integrating various mechanisms. The output heads analyze the memory path and pixel route data to predict the mask classes used to create the final mask. The proposed model outperforms the most recent panoptic segmentation on the UFBA-UESC Dental Image dataset, notably in performance and resilience. Our study represents a significant advancement in teeth segmentation and advances our knowledge of oral anatomy.

EVALUATING HYBRID NEURAL NETWORK ARCHITECTURES FOR PREDICTING SLEEP DISORDERS FROM STRUCTURED DATA

The accurate diagnosis of sleep disorders is crucial for effective treatment and management, yet current methods often rely on subjective assessments and are not always reliable. This research examines the efficacy of various neural network architectures, including dense networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and innovative hybrid models, in predicting sleep disorders from structured health data. Our study focuses on comparing the performance of these models using metrics such as accuracy, precision, recall, and F1 score across a dataset comprising 400 individuals with detailed sleep and lifestyle data. Our findings demonstrate that while traditional models like dense networks and CNNs for structured data yield robust results, hybrid models, particularly the CNN-Transformer, significantly outperform others. This model effectively integrates convolutional layers with Transformer’s attention mechanisms, excelling in handling complex data interactions and providing superior predictive accuracy with an F1 score and accuracy reaching as high as 0.91. Conversely, RNN models, designed to capture temporal data dependencies, showed less efficacy, underscoring the importance of model selection aligned with data characteristics. This suggests that for datasets not exhibiting strong temporal features, models leveraging spatial relationships or advanced attention mechanisms are more suitable. This study not only advances our understanding of neural network applications in medical diagnostics but also highlights the potential of hybrid models in enhancing diagnostic accuracy. These insights could lead to significant improvements in the early detection and treatment of sleep disorders, thereby enhancing patient outcomes and contributing to the broader field of medical informatics.

A Novel Deep Learning Approach for Brain Tumor Segmentation and Classification

Automated brain tumor detection and segmentation are crucial in medical diagnostics as they give details about functional structures and also potential unusual tissue that is required to define surgical strategies. Segmentation of images is one of the most difficult issues in the area of MRI scan analysis research. However, due to low contrast, automatic tumor segmentation, accuracy issues, and ill-defined boundaries remain difficult. For the prevention of brain tumors, an investigation was developed for implementing a novel framework. To overcome the problem faced by traditional existing techniques, this paper proposed an automatic brain tumor segmentation and detection system using the proposed dense convolution neural network without human intervention, where an intrinsic set of features are extracted to perform the classification task. The main aim of this paper is to segment the tumor portion from the affected MRI using a novel clustering approach. Moreover, a lot of scholars have researched the diagnosis of brain tumors, yet the accuracy-based performance metric in diagnosis results is low. A deep learning framework is proposed to evaluate brain disease more accurately using a Black Widow Optimization driven Dense Convolution Neural Network (BW-DCNN). The various performances are assessed, and the results are compared to those of other existing classifiers and approaches.

Diagnosis of skin lesion using shift-invariant network and an improved grey wolf optimizer

The global incidence of skin cancer has been rising, resulting in increased mortality and morbidity if left untreated. Accurate diagnosis of skin malignancies is crucial for early intervention through excision. While various innovative medical imaging techniques, such as dermoscopy, have improved the way we examine skin cancers, the progress in medical imaging for identifying skin lesions has not kept pace. Skin lesions exhibit diverse visual features, including variations in size, shape, boundaries, and artifacts, necessitating an efficient image-processing approach to assist dermatologists in decision-making. In this research, we propose an automated skin lesion classifier called GreyNet, which utilizes optimized convolutional neural networks (CNNs) or shift-invariant networks (SIN). GreyNet comprises three components: (i) a trained fully deep CNN for semantic segmentation, relating input images to manually labeled standard scans; (ii) an enhanced dense CNN with global information exchange and adaptive feature salvaging module to accurately classify each pixel in histopathological scans as benign or malignant; and (iii) a binary grey wolf optimizer (BGWO) to improve the classification process by optimizing the network’s hyperparameters. We evaluate the performance of GreyNet in terms of lesion segmentation and classification on the HAM10000 database. Extensive empirical results demonstrate that GreyNet outperforms existing lesion segmentation methods, achieving improved dice similarity score, volume error, and average processing time of 1.008±0.009, 0.903±0.009%, and 0.079±0.010 s, respectively. Moreover, GreyNet surpasses other skin melanoma classification models, exhibiting improved accuracy, precision, specificity, sensitivity, false negative rate, false positive rate, and Jaccard similarity score (JSS) of 96.5%, 97%, 96.2%, 92.1%, 3.8%, 3%, and 89.5%, respectively. Based on our experimental analysis, we conclude that GreyNet is an efficient tool to aid dermatologists in identifying skin melanoma.

EL-DenseNet: a novel method for identifying the flame state of converter steelmaking based on dense convolutional neural networks

EL-DenseNet: a novel method for identifying the flame state of converter steelmaking based on dense convolutional neural networks

Machine Learning Detection and Characterization of Splenic Injuries on Abdominal Computed Tomography.

Multi-detector contrast-enhanced abdominal computed tomography (CT) allows for the accurate detection and classification of traumatic splenic injuries, leading to improved patient management. Their effective use requires rapid study interpretation, which can be a challenge on busy emergency radiology services. A machine learning system has the potential to automate the process, potentially leading to a faster clinical response. This study aimed to create such a system. Using the American Association for the Surgery of Trauma (AAST), spleen injuries were classified into 3 classes: normal, low-grade (AAST grade I-III) injuries, and high-grade (AAST grade IV and V) injuries. Employing a 2-stage machine learning strategy, spleens were initially segmented from input CT images and subsequently underwent classification via a 3D dense convolutional neural network (DenseNet). This single-centre retrospective study involved trauma protocol CT scans performed between January 1, 2005, and July 31, 2021, totaling 608 scans with splenic injuries and 608 without. Five board-certified fellowship-trained abdominal radiologists utilizing the AAST injury scoring scale established ground truth labels. The model achieved AUC values of 0.84, 0.69, and 0.90 for normal, low-grade injuries, and high-grade splenic injuries, respectively. Our findings demonstrate the feasibility of automating spleen injury detection using our method with potential applications in improving patient care through radiologist worklist prioritization and injury stratification. Future endeavours should concentrate on further enhancing and optimizing our approach and testing its use in a real-world clinical environment.

Hyperspectral Image Classification Based on Atrous Convolution Channel Attention-Aided Dense Convolutional Neural Network

Hyperspectral Image Classification Based on Atrous Convolution Channel Attention-Aided Dense Convolutional Neural Network

Retracted: Dense Convolutional Neural Network for Detection of Cancer from CT Images.

[This retracts the article DOI: 10.1155/2022/1293548.].

Sparse convolutional neural network for high-resolution skull shape completion and shape super-resolution

Traditional convolutional neural network (CNN) methods rely on dense tensors, which makes them suboptimal for spatially sparse data. In this paper, we propose a CNN model based on sparse tensors for efficient processing of high-resolution shapes represented as binary voxel occupancy grids. In contrast to a dense CNN that takes the entire voxel grid as input, a sparse CNN processes only on the non-empty voxels, thus reducing the memory and computation overhead caused by the sparse input data. We evaluate our method on two clinically relevant skull reconstruction tasks: (1) given a defective skull, reconstruct the complete skull (i.e., skull shape completion), and (2) given a coarse skull, reconstruct a high-resolution skull with fine geometric details (shape super-resolution). Our method outperforms its dense CNN-based counterparts in the skull reconstruction task quantitatively and qualitatively, while requiring substantially less memory for training and inference. We observed that, on the 3D skull data, the overall memory consumption of the sparse CNN grows approximately linearly during inference with respect to the image resolutions. During training, the memory usage remains clearly below increases in image resolution—an times 8 increase in voxel number leads to less than times 4 increase in memory requirements. Our study demonstrates the effectiveness of using a sparse CNN for skull reconstruction tasks, and our findings can be applied to other spatially sparse problems. We prove this by additional experimental results on other sparse medical datasets, like the aorta and the heart. Project page at https://github.com/Jianningli/SparseCNN.

Dense Convolution Neural Network for Automated Diabetic Retinopathy Detection

Diabetic Retinopathy is a diabetes complication due to uncontrolled levels of glucose in the body which leads to abnormality in the eyes which owing to distortion in the retina and leading to permanent damage of the eye or vision losses. Hence identification and classification of diabetic retinopathy through manual observation is a challenging process due to composite boundaries and features with a high degree of intraclass variation and a low degree of interclass variation.
 Unsupervised machine learning algorithms have been used to classify diseases automatically based on the appearance of lesions and their characteristics. These models require more processing time and less reliability. It has been proposed that deep learning architecture can overcome these limitations as it is more efficient and accurate at detecting the lesion’s features.
 The novel dense convolution neural network has been proposed with preprocessing, segmentation, feature extraction and classification steps. Laplacian filter and CLAHE techniques have been used in a preprocessing step. The region growing algorithm, Principal Component Analysis and Dense CNN have been used for segmentation, Feature extraction and classification of DR lesions. Furthermore, the proposed model was compared with conventional classifiers in terms of Accuracy parameters. The proposed model achieves 97.88 % of Accuracy. It improves computing efficiency and minimizes network complexity. Hence the proposed model can accurately detect the lesions in the retinal fundus images.

Modelling a stacked dense network model for outlier prediction over medical-based heart prediction data

Recently, deep learning has been used in enormous successful applications, specifically considering medical applications. Especially, a huge number of data is captured through the Internet of Things (IoT) based devices related to healthcare systems. Moreover, the given captured data are real-time and unstructured. However, the existing approaches failed to reach a better accuracy rate, and the processing time needed to be lower. This work considers the medical database for accessing the patient’s record to determine the outliers over the dataset. Based on this successful analysis, a novel approach is proposed where some feasible and robust features are extracted to acquire the emotional variations for various ways of expression. Here, a novel dense-Convolutional Neural Network (CNN) with ResNet (CNN-RN) extracts features from patients’, while for establishing visual modality, deep residual network layers are used. The significance of feature extraction is less sensitive during outlier prediction while modeling the context. To handle these issues, this dense network model is used for training the network in an end-to-end manner by correlating the significance of CNN and RN of every stream and outperforming the overall approach. Here, MATLAB 2020b is used for simulation purposes, and the model outperforms various prevailing methods for consistent prediction. Some performance metrics include detection accuracy, F1-score, recall, MCC, p-value, etc. Based on this evaluation, the experimental results attained are superior to other approaches.

Real Time Asthma Disease Detection and Identification Technique from Speech Signals Using Hybrid Dense Convolutional Neural Network

Recently, asthma patients are severely suffering COVID-19 disease, thus the asthma has become one of the dangerous diseases in the world. Further, asthma is occurring in all age groups, which causing huge loss to patient’s health. The primary way to detect the asthma in humans is done by their speech signals, as the asthma severity is increases, which manipulates the properties of speech signal. The conventional methods are failed to extract the maximum features from the speech signals, which resulted in low classification performance. Thus, this article is focused on implementation of real time asthma disease detection and identification technique from speech signals using Multi-Feature Extraction, Selection with Hybrid Classifiers (MFESHC). Initially, speech signals are preprocessed by using Maximum likelihood estimation based spread spectrum analysis (MLE-SSA) method. Then, Improved prefix Beam Search (IPBS) based natural language processing (NLP) method is used to extract and select the best features from the preprocessed speech signals. Then, hybrid dense convolutional neural networks (HDCNN) are used to classify the type of asthma such as normal, stridor, wheezes and rattle classes. Further, Modified Crow Search (MCS) is used to optimize the losses generated in the HDCNN model. The simulation results shows that the proposed MFESHC method resulted in superior performance as compared to state of art approaches because the MCS effectively reduced the losses in the model.

Brain Tumor Detection and Classification using Deep Learning

Abstract: This paper explores the application of convolutional neural networks (CNNs) in diagnosing brain tumors, focusing on children and the elderly who are most vulnerable to this type of cancer. Brain tumors pose significant health risks due to uncontrolled cell growth within the skull, making accurate classification challenging. The study utilizes CNNs, a popular machine learning approach, to classify 3260 brain magnetic resonance images into glioma, meningioma, pituitary, and no tumor categories. Three algorithms, CNN, VGG, and Densenet, are employed for classification. Early detection is vital for effective treatment, and computer-aided diagnostics show promise in assisting clinicians. This work provides an overview of traditional computer-aided tumor diagnosis and highlights the advantages of using CNNs. It discusses image segmentation, classification techniques based on CNN, Densenet, and VGG16, and serves as a guide for future tumor detection research. Data augmentation and min-max normalization enhance tumor cell contrast. The dense CNN model accurately classifies a small image database, and Densenet demonstrates remarkable performance. Experimental results show CNN achieving 45% accuracy on testing data, VGG achieving 51%, and Densenet achieving an impressive 86.49% during training, with high precision and a good F1 score. Overall, this paper emphasizes the potential of CNNs for brain tumor diagnosis and contributes to the development of computeraided diagnostic systems. It advances the field of medical image analysis and paves the way for further research in tumor detection.

P13.10.A PREDICTING SURVIVAL OF GLIOBLASTOMAAFTER RADIOTHERAPY USING DEEP LEARNING AND NEUROIMAGING IN A MULTI-CENTRE COHORT

Abstract BACKGROUND Glioblastoma is an aggressive brain tumour routinely monitored with MRI. However, the potential to use imaging as a prognostic biomarker predicting survival after treatment starts is unclear. This study aims to predict survival within eight months of completing radiotherapy from MRIs using deep learning. MATERIAL AND METHODS The dataset consists of 206 prospective and retrospective consecutive patients with glioblastoma (WHO 2021) across 11 UK centres (short-term survival: N=64; 31.1%). Models were trained/validated on N=158 (76.7%) retrospective patients (3 centres). Two holdout sets were sampled: retrospective test set (N=19); and external, prospective test set (N=29; 8 separate centres). Dense convolutional neural networks were developed with separate branches for T1c-w and T2-w MR sequences; a third branch concatenates outputs from those branches to predict survival. Dense blocks used pretrained weights for an abnormality detection model. A semi-supervised approach was implemented; patients without known outcomes were added with pseudo-labels during training. Parameter tuning included the number of updated blocks, linear layer sizes, and weighting of pseudo-labels. Imaging models were compared to counterparts that apply non-imaging variables (demographics, MGMT status/%, treatment). Logistic regression, support vector classifier, and decision tree models were fit on non-imaging features alone with feature selection and mean/mode imputation. Combined imaging/non-imaging networks were developed that added a branch for non-imaging inputs. RESULTS The current best-performing imaging model used MR sequences alone (validation weighted-ROC=0.80, 95% CI=0.75-0.84; balanced accuracy=0.70, 95% CI=0.55-0.85). Among non-imaging models, the logistic regression model with feature selection performed best (validation weighted-ROC=0.59, 95% CI=0.56-0.63; balanced accuracy=0.59, 95% CI=0.56-0.63). Combined model development is ongoing. CONCLUSION This is the first known model applying deep learning to MRIs from multiple centres to distinguish patients with failure to respond to chemoradiotherapy, and those who survive the subsequent treatment window. Based on initial results, image-based models performed best at predicting survival. Such models could be used across centres to suggest closer monitoring and trial targeting of patients with expected short-term survival compared to treatment response.

Dense Convolutional Neural Network for Identification of Raman Spectra.

The rapid development of cloud computing and deep learning makes the intelligent modes of applications widespread in various fields. The identification of Raman spectra can be realized in the cloud, due to its powerful computing, abundant spectral databases and advanced algorithms. Thus, it can reduce the dependence on the performance of the terminal instruments. However, the complexity of the detection environment can cause great interferences, which might significantly decrease the identification accuracies of algorithms. In this paper, a deep learning algorithm based on the Dense network has been proposed to satisfy the realization of this vision. The proposed Dense convolutional neural network has a very deep structure of over 40 layers and plenty of parameters to adjust the weight of different wavebands. In the kernel Dense blocks part of the network, it has a feed-forward fashion of connection for each layer to every other layer. It can alleviate the gradient vanishing or explosion problems, strengthen feature propagations, encourage feature reuses and enhance training efficiency. The network's special architecture mitigates noise interferences and ensures precise identification. The Dense network shows more accuracy and robustness compared to other CNN-based algorithms. We set up a database of 1600 Raman spectra consisting of 32 different types of liquid chemicals. They are detected using different postures as examples of interfered Raman spectra. In the 50 repeated training and testing sets, the Dense network can achieve a weighted accuracy of 99.99%. We have also tested the RRUFF database and the Dense network has a good performance. The proposed approach advances cloud-enabled Raman spectra identification, offering improved accuracy and adaptability for diverse identification tasks.

Dense Convolutional Neural Network Based Deep Learning Framework for the Diagnosis of Breast Cancer

Dense Convolutional Neural Network Based Deep Learning Framework for the Diagnosis of Breast Cancer

Flame reconstruction of hydrogen fueled-scramjet combustor based on multi-source information fusion

Using various types of data to extract different features and reconstruct flame spontaneous image, the rapid acquisition of flame propagation data and automatic identification of the combustion state in a scramjet combustion chamber in confined space can be promoted. A reconstruction model based on multi-source information fusion is proposed that can effectively reconstruct a flame self-luminous image based on the combustor wall pressure and schlieren image data. A dense convolutional neural network is used to construct and reconstruct the model and train the network based on the experimental datasets. The ground pulse combustion wind tunnel test is conducted under the condition of hydrogen fuel self-ignition using the variation rules of different injection pressures. The evolution process of the combustor wall pressure, schlieren image, and flame self-luminescence image is obtained over time and a dataset is constructed. The reconstruction accuracy of the flame spontaneous luminescence image using the schlieren image and the fusion of the schlieren image and wall pressure under different injection pressure is comprehensively analyzed. Moreover, both qualitative and quantitative results show that the prediction accuracy of flame spontaneous illumination based on multi-source information fusion well matches the experimental result, and the flame boundary, flame head region, flame area, and burning intensity are all well reconstructed. The average peak signal to noise ratio reached 31.57 dB, average structural similarity was 0.939, average mean square error was 0.979, correlation coefficient was 0.0013, and intersection over union reached 0.876.

Down syndrome markers classification via dense neural network in ultrasound foetal image

Down syndrome is a genetically born disorder among infants that occurs during the development of the foetus. Trisomy 21, a chromosome imbalance disorder is a leading cause of the down syndrome. Numerous machine learning (ML) models have been used to identify down syndrome in ultrasound images of foetuses, but the development of deep learning, offers an enormous advantage over ML models in accuracy. However, the existing models have focused on down syndrome as a nasal bone (NB) length or nuchal translucency (NT). In this paper, a novel automatic dense convolution neural network (DConN) is proposed to isolate and measure the down syndrome marker particularly NB length and NT. It is necessary to extract texture features precisely from ultrasound images to classify them accurately. Initially, the test image is processed using an anisotropic diffusion filter to remove the noise. The pre-processed foetal images are subjected to region of interest extraction to isolate the Down syndrome makers from the ultrasound image. The proposed DConN is used to classify the normal and abnormal foetal based on NT and NB length of the foetal in US images. The performance metrics namely sensitivity, accuracy, specificity, F1 score, and precision are considered for validating the effectiveness of the proposed model. From the experimental the proposed DconN achieves the overall accuracy of 99.01%. The proposed method improves the overall accuracy of 3.9%, 1.6% and 0.41% better than cascaded ML, SIFT + GRNN and Modified AdaBoost, respectively.

DFNet: Dense fusion convolution neural network for plant leaf disease classification

AbstractThe early identification of plant diseases is crucial for preventing the loss of crop production. Recently, the advancement of deep learning has significantly improved the identification of plant leaf diseases. However, most approaches depend on a single convolutional neural network (CNN) to extract the leaf features, ignoring the opportunity to take full advantage of the feature richness available in the images. This paper explores a novel CNN model with multiple automated feature extractors, namely, dense fusion CNN (DFNet), for classifying plant leaf diseases. DFNet aims to increase the diversity of extracted features in order to improve discrimination. Instead of using a single‐CNN model, DFNet relies on a double‐pretrained CNN model, MobileNetV2 and NASNetMobile, as the feature extractor. The features extracted from each CNN are fused in the fusion layer using a fully connected network. The proposed method was evaluated using corn (Zea mays L.) and coffee (Coffea canephora) leaf disease datasets and compared to the existing models. The experiment showed that DFNet is superior and consistent to other CNN methods by achieving an accuracy of 97.53% for corn leaf diseases and 94.65% for coffee leaf diseases.