MobileNetV2 Ensemble for Cervical Precancerous Lesions Classification

An extensive investigation of convolutional neural network designs for the diagnosis of lumpy skin disease in dairy cows

Cow diseases are a major source of concern for people. Some diseases in animals that are discovered in their early stages can be treated while they are still treatable. If lumpy skin disease (LSD) is not properly treated, it can result in significant financial losses for the farm animal industry. Animals like cows that sign this disease have their skin seriously affected. A reduction in milk production, reduced fertility, growth retardation, miscarriage, and occasionally death are all detrimental effects of this disease in cows. Over the past three months, LSD has affected thousands of cattle in nearly fifty districts across Bangladesh, causing cattle farmers to worry about their livelihood. Although the virus is very contagious, after receiving the right care for a few months, the affected cattle can be cured. The goal of this study was to use various deep learning and machine learning models to determine whether or not cows had lumpy disease. To accomplish this work, a Convolution neural network (CNN) based novel architecture is proposed for detecting the illness. The lumpy disease-affected area has been identified using image preprocessing and segmentation techniques. After the extraction of numerous features, our proposed model has been evaluated to classify LSD. Four CNN models, DenseNet, MobileNetV2, Xception, and InceptionResNetV2 were used to classify the framework, and evaluation metrics were computed to determine how well the classifiers worked. MobileNetV2 has been able to achieve 96% classification accuracy and an AUC score of 98% by comparing results with recently published relevant works, which seems both good and promising.

Classification of cervical lesions based on multimodal features fusion

Cervical cancer is a severe threat to women's health worldwide with a long cancerous cycle and a clear etiology, making early screening vital for the prevention and treatment. Based on the dataset provided by the Obstetrics and Gynecology Hospital of Fudan University, a four-category classification model for cervical lesions including Normal, low-grade squamous intraepithelial lesion (LSIL), high-grade squamous intraepithelial lesion (HSIL) and cancer (Ca) is developed. Considering the dataset characteristics, to fully utilize the research data and ensure the dataset size, the model inputs include original and acetic colposcopy images, lesion segmentation masks, human papillomavirus (HPV), thinprep cytologic test (TCT) and age, but exclude iodine images that have a significant overlap with lesions under acetic images. Firstly, the change information between original and acetic images is introduced by calculating the acetowhite opacity to mine the correlation between the acetowhite thickness and lesion grades. Secondly, the lesion segmentation masks are utilized to introduce prior knowledge of lesion location and shape into the classification model. Lastly, a cross-modal feature fusion module based on the self-attention mechanism is utilized to fuse image information with clinical text information, revealing the features correlation. Based on the dataset used in this study, the proposed model is comprehensively compared with five excellent models over the past three years, demonstrating that the proposed model has superior classification performance and a better balance between performance and complexity. The modules ablation experiments further prove that each proposed improved module can independently improve the model performance.

Development of a multi-fusion convolutional neural network (MF-CNN) for enhanced gastrointestinal disease diagnosis in endoscopy image analysis

Gastrointestinal (GI) diseases are prevalent medical conditions that require accurate and timely diagnosis for effective treatment. To address this, we developed the Multi-Fusion Convolutional Neural Network (MF-CNN), a deep learning framework that strategically integrates and adapts elements from six deep learning models, enhancing feature extraction and classification of GI diseases from endoscopic images. The MF-CNN architecture leverages truncated and partially frozen layers from existing models, augmented with novel components such as Auxiliary Fusing Layers (AuxFL), Fusion Residual Block (FuRB), and Alpha Dropouts (αDO) to improve precision and robustness. This design facilitates the precise identification of conditions such as ulcerative colitis, polyps, esophagitis, and healthy colons. Our methodology involved preprocessing endoscopic images sourced from open databases, including KVASIR and ETIS-Larib Polyp DB, using adaptive histogram equalization (AHE) to enhance their quality. The MF-CNN framework supports detailed feature mapping for improved interpretability of the model's internal workings. An ablation study was conducted to validate the contribution of each component, demonstrating that the integration of AuxFL, αDO, and FuRB played a crucial part in reducing overfitting and efficiency saturation and enhancing overall model performance. The MF-CNN demonstrated outstanding performance in terms of efficacy, achieving an accuracy rate of 99.25%. It also excelled in other key performance metrics with a precision of 99.27%, a recall of 99.25%, and an F1-score of 99.25%. These metrics confirmed the model's proficiency in accurate classification and its capability to minimize false positives and negatives across all tested GI disease categories. Furthermore, the AUC values were exceptional, averaging 1.00 for both test and validation sets, indicating perfect discriminative ability. The findings of the P-R curve analysis and confusion matrix further confirmed the robust classification performance of the MF-CNN. This research introduces a technique for medical imaging that can potentially transform diagnostics in gastrointestinal healthcare facilities worldwide.

MFEM-CIN: A Lightweight Architecture Combining CNN and Transformer for the Classification of Pre-Cancerous Lesions of the Cervix

Goal: Cervical cancer is one of the most common cancers in women worldwide, ranking among the top four. Unfortunately, it is also the fourth leading cause of cancer-related deaths among women, particularly in developing countries where incidence and mortality rates are higher compared to developed nations. Colposcopy can aid in the early detection of cervical lesions, but its effectiveness is limited in areas with limited medical resources and a lack of specialized physicians. Consequently, many cases are diagnosed at later stages, putting patients at significant risk. Methods: This paper proposes an automated colposcopic image analysis framework to address these challenges. The framework aims to reduce the labor costs associated with cervical precancer screening in undeserved regions and assist doctors in diagnosing patients. The core of the framework is the MFEM-CIN hybrid model, which combines Convolutional Neural Networks (CNN) and Transformer to aggregate the correlation between local and global features. This combined analysis of local and global information is scientifically useful in clinical diagnosis. In the model, MSFE and MSFF are utilized to extract and fuse multi-scale semantics. This preserves important shallow feature information and allows it to interact with the deep feature, enriching the semantics to some extent. Conclusions: The experimental results demonstrate an accuracy rate of 89.2% in identifying cervical intraepithelial neoplasia while maintaining a lightweight model. This performance exceeds the average accuracy achieved by professional physicians, indicating promising potential for practical application. Utilizing automated colposcopic image analysis and the MFEM-CIN model, this research offers a practical solution to reduce the burden on healthcare providers and improve the efficiency and accuracy of cervical cancer diagnosis in resource-constrained areas.

Exploiting Sparse Self-Representation and Particle Swarm Optimization for CNN Compression

Structured pruning has received ever-increasing attention as a method for compressing convolutional neural networks. However, most existing methods directly prune the network structure according to the statistical information of the parameters. Besides, these methods differentiate the pruning rates only in each pruning stage or even use the same pruning rate across all layers, rather than using learnable parameters. In this article, we propose a network redundancy elimination approach guided by the pruned model. Our proposed method can easily tackle multiple architectures and is scalable to the deeper neural networks because of the use of joint optimization during the pruning procedure. More specifically, we first construct a sparse self-representation for the filters or neurons of the well-trained model, which is useful for analyzing the relationship among filters. Then, we employ particle swarm optimization to learn pruning rates in a layerwise manner according to the performance of the pruned model, which can determine optimal pruning rates with the best performance of the pruned model. Under this criterion, the proposed pruning approach can remove more parameters without undermining the performance of the model. Experimental results demonstrate the effectiveness of our proposed method on different datasets and different architectures. For example, it can reduce 58.1% FLOPs for ResNet50 on ImageNet with only a 1.6% top-five error increase and 44.1% FLOPs for FCN_ResNet50 on COCO2017 with a 3% error increase, outperforming most state-of-the-art methods.

Adapted Deep Ensemble Learning-Based Voting Classifier for Osteosarcoma Cancer Classification

The study utilizes osteosarcoma hematoxylin and the Eosin-stained image dataset, which is unevenly dispersed, and it raises concerns about the potential impact on the overall performance and reliability of any analyses or models derived from the dataset. In this study, a deep-learning-based convolution neural network (CNN) and adapted heterogeneous ensemble-learning-based voting classifier have been proposed to classify osteosarcoma. The proposed methods can also resolve the issue and develop unbiased learning models by introducing an evenly distributed training dataset. Data augmentation is employed to boost the generalization abilities. Six different pre-trained CNN models, namely MobileNetV1, Mo-bileNetV2, ResNetV250, InceptionV2, EfficientNetV2B0, and NasNetMobile, are applied and evaluated in frozen and fine-tuned-based phases. In addition, a novel CNN model and adapted heterogeneous ensemble-learning-based voting classifier developed from the proposed CNN model, fine-tuned NasNetMobile model, and fine-tuned Efficient-NetV2B0 model are also introduced to classify osteosarcoma. The proposed CNN model outperforms other pre-trained models. The Kappa score obtained from the proposed CNN model is 93.09%. Notably, the proposed voting classifier attains the highest Kappa score of 96.50% and outperforms all other models. The findings of this study have practical implications in telemedicine, mobile healthcare systems, and as a supportive tool for medical professionals.

UNet and MobileNet CNN-based model observers for CT protocol optimization: comparative performance evaluation by means of phantom CT images

Purpose

The aim of this work is the development and characterization of a model observer (MO) based on convolutional neural networks (CNNs), trained to mimic human observers in image evaluation in terms of detection and localization of low-contrast objects in CT scans acquired on a reference phantom. The final goal is automatic image quality evaluation and CT protocol optimization to fulfill the ALARA principle.

Approach

Preliminary work was carried out to collect localization confidence ratings of human observers for signal presence/absence from a dataset of 30,000 CT images acquired on a PolyMethyl MethAcrylate phantom containing inserts filled with iodinated contrast media at different concentrations. The collected data were used to generate the labels for the training of the artificial neural networks. We developed and compared two CNN architectures based respectively on Unet and MobileNetV2, specifically adapted to achieve the double tasks of classification and localization. The CNN evaluation was performed by computing the area under localization-ROC curve (LAUC) and accuracy metrics on the test dataset.

Results

The mean of absolute percentage error between the LAUC of the human observer and MO was found to be below 5% for the most significative test data subsets. An elevated inter-rater agreement was achieved in terms of S-statistics and other common statistical indices.

Conclusions

Very good agreement was measured between the human observer and MO, as well as between the performance of the two algorithms. Therefore, this work is highly supportive of the feasibility of employing CNN-MO combined with a specifically designed phantom for CT protocol optimization programs.

Visual Detection of Water Content Range of Seabuckthorn Fruit Based on Transfer Deep Learning

To realize the classification of sea buckthorn fruits with different water content ranges, a convolution neural network (CNN) detection model of sea buckthorn fruit water content ranges was constructed. In total, 900 images of seabuckthorn fruits with different water contents were collected from 720 seabuckthorn fruits. Eight classic network models based on deep learning were used as feature extraction for transfer learning. A total of 180 images were randomly selected from the images of various water content ranges for testing. Finally, the identification accuracy of the network model for the water content range of seabuckthorn fruit was 98.69%, and the accuracy on the test set was 99.4%. The program in this study can quickly identify the moisture content range of seabuckthorn fruit by collecting images of the appearance and morphology changes during the drying process of seabuckthorn fruit. The model has a good detection effect for seabuckthorn fruits with different moisture content ranges with slight changes in characteristics. The migration deep learning can also be used to detect the moisture content range of other agricultural products, providing technical support for the rapid nondestructive testing of moisture contents of agricultural products.

Tobacco shred varieties classification using Multi-Scale-X-ResNet network and machine vision

The primary task in calculating the tobacco shred blending ratio is identifying the four tobacco shred types: expanded tobacco silk, cut stem, tobacco silk, and reconstituted tobacco shred. The classification precision directly affects the subsequent determination of tobacco shred components. However, the tobacco shred types, especially expanded tobacco silk and tobacco silk, have no apparent differences in macro-scale characteristics. The tobacco shreds have small size and irregular shape characteristics, creating significant challenges in their recognition and classification based on machine vision. This study provides a complete set of solutions aimed at this problem for screening tobacco shred samples, taking images, image preprocessing, establishing datasets, and identifying types. A block threshold binarization method is used for image preprocessing. Parameter setting and method performance are researched to obtain the maximum number of complete samples with acceptable execution time. ResNet50 is used as the primary classification and recognition network structure. By increasing the multi-scale structure and optimizing the number of blocks and loss function, a new tobacco shred image classification method is proposed based on the MS-X-ResNet (Multi-Scale-X-ResNet) network. Specifically, the MS-ResNet network is obtained by fusing the multi-scale Stage 3 low-dimensional and Stage 4 high-dimensional features to reduce the overfitting risk. The number of blocks in Stages 1-4 are adjusted from the original 3:4:6:3 to 3:4:N:3 (A-ResNet) and 3:3:N:3 (B-ResNet) to obtain the X-ResNet network, which improves the model's classification performance with lower complexity. The focal loss function is selected to reduce the impact of identification difficulty for different sample types on the network and improve its performance. The experimental results show that the final classification accuracy of the network on a tobacco shred dataset is 96.56%. The image recognition of a single tobacco shred requires 103 ms, achieving high classification accuracy and efficiency. The image preprocessing and deep learning algorithms for tobacco shred classification and identification proposed in this study provide a new implementation approach for the actual production and quality detection of tobacco and a new way for online real-time type identification of other agricultural products.

Convolutional Neural Network for Object Detection in Garlic Root Cutting Equipment

Traditional manual garlic root cutting is inefficient and can cause food safety problems. To develop food processing equipment, a novel and accurate object detection method for garlic using deep learning—a convolutional neural network—is proposed in this study. The you-only-look-once (YOLO) algorithm, which is based on lightweight and transfer learning, is the most advanced computer vision method for single large object detection. To detect the bulb, the YOLOv2 model was modified using an inverted residual module and residual structure. The modified model was trained based on images of bulbs with varied brightness, surface attachment, and shape, which enabled sufficient learning of the detector. The optimum minibatches and epochs were obtained by comparing the test results of different training parameters. Research shows that IRM-YOLOv2 is superior to the SqueezeNet, ShuffleNet, and YOLOv2 models of classical neural networks, as well as the YOLOv3 and YOLOv4 algorithm models. The confidence score, average accuracy, deviation, standard deviation, detection time, and storage space of IRM-YOLOv2 were 0.98228, 99.2%, 2.819 pixels, 4.153, 0.0356 s, and 24.2 MB, respectively. In addition, this study provides an important reference for the application of the YOLO algorithm in food research.

Human Gait Analysis: A Sequential Framework of Lightweight Deep Learning and Improved Moth-Flame Optimization Algorithm

Human gait recognition has emerged as a branch of biometric identification in the last decade, focusing on individuals based on several characteristics such as movement, time, and clothing. It is also great for video surveillance applications. The main issue with these techniques is the loss of accuracy and time caused by traditional feature extraction and classification. With advances in deep learning for a variety of applications, particularly video surveillance and biometrics, we proposed a lightweight deep learning method for human gait recognition in this work. The proposed method includes sequential steps–pretrained deep models selection of features classification. Two lightweight pretrained models are initially considered and fine-tuned in terms of additional layers and freezing some middle layers. Following that, models were trained using deep transfer learning, and features were engineered on fully connected and average pooling layers. The fusion is performed using discriminant correlation analysis, which is then optimized using an improved moth-flame optimization algorithm. For final classification, the final optimum features are classified using an extreme learning machine (ELM). The experiments were carried out on two publicly available datasets, CASIA B and TUM GAID, and yielded an average accuracy of 91.20 and 98.60%, respectively. When compared to recent state-of-the-art techniques, the proposed method is found to be more accurate.

Steel Plate Surface Defect Detection Based on Dataset Enhancement and Lightweight Convolution Neural Network

In the production and manufacturing industry, factors such as rolling equipment and processes may cause various defects on the surface of the steel plate, which greatly affect the performance and subsequent machining accuracy. Therefore, it is essential to identify defects in time and improve the quality of production. An intelligent detection system was constructed, and some improved algorithms such as dataset enhancement, annotation and lightweight convolution neural network are proposed in this paper. (1) Compared with the original YOLOV5 (You Only Look Once), the precision is 0.924, and the inference time is 29.8 ms, which is 13.8 ms faster than the original model. Additionally, the parameters and calculations are also far less than YOLOV5. (2) Ablation experiments were designed to verify the effectiveness of the proposed algorithms. The overall accuracy was improved by 0.062; meanwhile, the inference time was reduced by 21.7 ms. (3) Compared with other detection models, although RetinaNet has the highest accuracy, it takes the longest time. The overall performance of the proposed method is better than other methods. This research can better meet the requirements of the industry for precision and real-time performance. It can also provide ideas for industrial detection and lay the foundation for industrial automation.

Colposcopic multimodal fusion for the classification of cervical lesions

Objective: Cervical cancer is one of the two biggest killers of women and early detection of cervical precancerous lesions can effectively improve the survival rate of patients. Manual diagnosis by combining colposcopic images and clinical examination results is the main clinical diagnosis method at present. Developing an intelligent diagnosis algorithm based on artificial intelligence is an inevitable trend to solve the objectification of diagnosis and improve the quality and efficiency of diagnosis.Approach: A colposcopic multimodal fusion convolutional neural network (CMF-CNN) was proposed for the classification of cervical lesions. Mask region convolutional neural network was used to detect the cervical region while the encoding network EfficientNet-B3 was introduced to extract the multimodal image features from the acetic image and iodine image. Finally, Squeeze-and-Excitation, Atrous Spatial Pyramid Pooling, and convolution block were also adopted to encode and fuse the patient's clinical text information.Main results: The experimental results showed that in 7106 cases of colposcopy, the accuracy, macro F1-score, macro-areas under the curve of the proposed model were 92.70%, 92.74%, 98.56%, respectively. They are superior to the mainstream unimodal image classification models.Significance: CMF-CNN proposed in this paper combines multimodal information, which has high performance in the classification of cervical lesions in colposcopy, so it can provide comprehensive diagnostic aid.

Transfer Learning-Based Automatic Hurricane Damage Detection Using Satellite Images

After the occurrence of a hurricane, assessing damage is extremely important for the emergency managers so that relief aid could be provided to afflicted people. One method of assessing the damage is to determine the damaged and the undamaged buildings post-hurricane. Normally, damage assessment is performed by conducting ground surveys, which are time-consuming and involve immense effort. In this paper, transfer learning techniques have been used for determining damaged and undamaged buildings in post-hurricane satellite images. Four different transfer learning techniques, which include VGG16, MobileNetV2, InceptionV3 and DenseNet121, have been applied to 23,000 Hurricane Harvey satellite images, which occurred in the Texas region. A comparative analysis of these models has been performed on the basis of the number of epochs and the optimizers used. The performance of the VGG16 pre-trained model was better than the other models and achieved an accuracy of 0.75, precision of 0.74, recall of 0.95 and F1-score of 0.83 when the Adam optimizer was used. When the comparison of the best performing models was performed in terms of various optimizers, VGG16 produced the best accuracy of 0.78 for the RMSprop optimizer.

A Study of Text Vectorization Method Combining Topic Model and Transfer Learning

With the development of Internet cloud technology, the scale of data is expanding. Traditional processing methods find it difficult to deal with the problem of information extraction of big data. Therefore, it is necessary to use machine-learning-assisted intelligent processing to extract information from data in order to solve the optimization problem in complex systems. There are many forms of data storage. Among them, text data is an important data type that directly reflects semantic information. Text vectorization is an important concept in natural language processing tasks. Because text data can not be directly used for model parameter training, it is necessary to vectorize the original text data and make it numerical, and then the feature extraction operation can be carried out. The traditional text digitization method is often realized by constructing a bag of words, but the vector generated by this method can not reflect the semantic relationship between words, and it also easily causes the problems of data sparsity and dimension explosion. Therefore, this paper proposes a text vectorization method combining a topic model and transfer learning. Firstly, the topic model is selected to model the text data and extract its keywords, to grasp the main information of the text data. Then, with the help of the bidirectional encoder representations from transformers (BERT) model, which belongs to the pretrained model, model transfer learning is carried out to generate vectors, which are applied to the calculation of similarity between texts. By setting up a comparative experiment, this method is compared with the traditional vectorization method. The experimental results show that the vector generated by the topic-modeling- and transfer-learning-based text vectorization (TTTV) proposed in this paper can obtain better results when calculating the similarity between texts with the same topic, which means that it can more accurately judge whether the contents of the given two texts belong to the same topic.

Special Issue on “Big Data in Biology, Life Sciences and Healthcare”

In the past few decades, we have witnessed tremendous advancements in biology, life sciences and healthcare [...]

Discriminative Cervical Lesion Detection in Colposcopic Images with Global Class Activation and Local Bin Excitation

Accurate cervical lesion detection (CLD) methods using colposcopic images are highly demanded in computer-aided diagnosis (CAD) for automatic diagnosis of High-grade Squamous Intraepithelial Lesions (HSIL). However, compared to natural scene images, the specific characteristics of colposcopic images, such as low contrast, visual similarity, and ambiguous lesion boundaries, pose difficulties to accurately locating HSIL regions and also significantly impede the performance improvement of existing CLD approaches. To tackle these difficulties and better capture cervical lesions, we develop novel feature enhancing mechanisms from both global and local perspectives, and propose a new discriminative CLD framework, called CervixNet, with a Global Class Activation (GCA) module and a Local Bin Excitation (LBE) module. Specifically, the GCA module learns discriminative features by introducing an auxiliary classifier, and guides our model to focus on HSIL regions while ignoring noisy regions. It globally facilitates the feature extraction process and helps boost feature discriminability. Further, our LBE module excites lesion features in a local manner, and allows the lesion regions to be more fine-grained enhanced by explicitly modelling the inter-dependencies among bins of proposal feature. Extensive experiments on a number of 9888 clinical colposcopic images verify the superiority of our method (AP _.75=20.45) over state-of-the-art models on four widely used metrics.

Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Deep learning models are efficient in learning the features that assist in understanding complex patterns precisely. This study proposed a computerized process of classifying skin disease through deep learning based MobileNet V2 and Long Short Term Memory (LSTM). The MobileNet V2 model proved to be efficient with a better accuracy that can work on lightweight computational devices. The proposed model is efficient in maintaining stateful information for precise predictions. A grey-level co-occurrence matrix is used for assessing the progress of diseased growth. The performance has been compared against other state-of-the-art models such as Fine-Tuned Neural Networks (FTNN), Convolutional Neural Network (CNN), Very Deep Convolutional Networks for Large-Scale Image Recognition developed by Visual Geometry Group (VGG), and convolutional neural network architecture that expanded with few changes. The HAM10000 dataset is used and the proposed method has outperformed other methods with more than 85% accuracy. Its robustness in recognizing the affected region much faster with almost 2× lesser computations than the conventional MobileNet model results in minimal computational efforts. Furthermore, a mobile application is designed for instant and proper action. It helps the patient and dermatologists identify the type of disease from the affected region's image at the initial stage of the skin disease. These findings suggest that the proposed system can help general practitioners efficiently and effectively diagnose skin conditions, thereby reducing further complications and morbidity.

Using Dynamic Features for Automatic Cervical Precancer Detection

Cervical cancer remains a major public health concern in developing countries due to financial and human resource constraints. Visual inspection with acetic acid (VIA) of the cervix was widely promoted and routinely used as a low-cost primary screening test in low- and middle-income countries. It can be performed by a variety of health workers and the result is immediate. VIA provides a transient whitening effect which appears and disappears differently in precancerous and cancerous lesions, as compared to benign conditions. Colposcopes are often used during VIA to magnify the view of the cervix and allow clinicians to visually assess it. However, this assessment is generally subjective and unreliable even for experienced clinicians. Computer-aided techniques may improve the accuracy of VIA diagnosis and be an important determinant in the promotion of cervical cancer screening. This work proposes a smartphone-based solution that automatically detects cervical precancer from the dynamic features extracted from videos taken during VIA. The proposed solution achieves a sensitivity and specificity of 0.9 and 0.87 respectively, and could be a solution for screening in countries that suffer from the lack of expensive tools such as colposcopes and well-trained clinicians.