Deep Learning Classification Model Research Articles

Deep Learning Models for Classification of Deciduous and Permanent Teeth From Digital Panoramic Images.

Dental radiographs are essential in the diagnostic process in dentistry. They serve various purposes, including determining age, analyzing patterns of tooth eruption/shedding, and treatment planning and prognosis. The emergence of digital radiography technology has piqued interest in using artificial intelligence systems to assist and guide dental professionals. These cutting-edge technologies assist in streamlining decision-making processes by enabling entity classification and localization tasks. With the integration of artificial Intelligence algorithms tailored for pediatric dentistry applications and utilizing automated tools, there is an optimistic outlook on improving diagnostic capabilities while reducing stress and fatigue among clinicians. The dataset comprised 620 images (mixed dentition: 314, permanent dentition: 306). Panoramic radiographs taken were within the age range of 4-16 years. The classification of deciduous and permanent teeth involved training CNN-based models using different architectures such as Resnet, AlexNet, and EfficientNet, among others. A ratio of 70:15:15 was utilized for training, validation, and testing, respectively. The findings indicated that among the models proposed, EfficientNetB0 and EfficientNetB3 exhibited superior performance. Both EfficientNetB0 and EfficientNetB3 achieved an accuracy rate, precision, recall, and F1 scores of 98% in classifying teeth as either deciduous or permanent. This implies that these models were highly accurate in identifying patterns/features within the dataset used for evaluation.

Deep learning-assisted development and validation of an algorithm for predicting the growth of persistent pure ground-glass nodules.

The prediction of the persistent pure ground-glass nodule (pGGN) growth is challenging and limited by subjective assessment and variation across radiologists. A chest computed tomography (CT) image-based deep learning classification model (DLCM) may provide a more accurate growth prediction. This retrospective study enrolled consecutive patients with pGGNs from January 2010 to December 2020 from two independent medical institutions. Four DLCM algorithms were built to predict the growth of pGGNs, which were extracted from the nodule areas of chest CT images annotated by two radiologists. All nodules were assigned to either the study, the inner validation, or the external validation cohort. Accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curves, and areas under the ROC curve (AUROCs) were analyzed to evaluate our models. A total of 286 patients were included, with 419 pGGN. In total, 197 (68.9%) of the patients were female and the average age was 59.5±12.0 years. The number of pGGN assigned to the study, the inner validation, and the external validation cohort were 193, 130, and 96, respectively. The follow-up time of stable pGGNs for the primary and external validation cohorts were 3.66 (range, 2.01-10.08) and 4.63 (range, 2.00-9.91) years, respectively. Growth of the pGGN occurred in 166 nodules [83 (43%), 39 (30%), and 44 (45%) in the study, inner and external validation cohorts respectively]. The best-performing DLCM algorithm was DenseNet_DR, which achieved AUROCs of 0.79 [95% confidence interval (CI): 0.70, 0.86] in predicting pGGN growth in the inner validation cohort and 0.70 (95% CI: 0.60, 0.79) in the external validation cohort. DLCM algorithms that use chest CT images can help predict the growth of pGGNs.

Skin Cancer Classification using Multiple Convolutional Neural Networks

Skin cancer is a significant threat to the global health, with over 2.1 million new cases diagnosed annually worldwide. Timely detection and treatment are vital for improving survival rates, yet the limited availability of dermatologists in remote regions poses a significant barrier. The utilization of Artificial Intelligence (AI) and Deep Learning (DL) has seen a remarkable surge in recent years for skin cancer prediction. This study conducts an in-depth review of advanced skin cancer prediction methods employing deep learning techniques and explores the diverse array of machine learning algorithms applied in this context. Skin cancer comprises seven distinct diagnoses, presenting a formidable challenge for dermatologists due to the overlapping phenotypic traits. Conventional diagnostic accuracy typically ranges from 62% to 80%, underscoring the potential of machine learning to enhance diagnosis and treatment. While some researchers have created binary skin cancer classification models, extending this to multiple classes with superior performance has been elusive. A deep learning classification model for various skin cancer types, yielding promising results that highlight the superiority of deep learning in classification tasks is developed. The experimental outcomes demonstrate that the individual accuracy of Sequential, ResNet50, DenseNet201, VGG-16 and EfficientNetB0 models are aggregated and yields the maximum occurring output value from all the models. Furthermore, a comparative analysis with the latest skin classification models underscores the superior performance of the proposed multi-type skin cancer classification model.

Comparison of Different Machine Learning Algorithms for the Prediction of the Wheat Grain Filling Stage Using RGB Images

Grain filling is essential for wheat yield formation, but is very susceptible to environmental stresses, such as high temperatures, especially in the context of global climate change. Grain RGB images include rich color, shape, and texture information, which can explicitly reveal the dynamics of grain filling. However, it is still challenging to further quantitatively predict the days after anthesis (DAA) from grain RGB images to monitor grain development. Results: The WheatGrain dataset revealed dynamic changes in color, shape, and texture traits during grain development. To predict the DAA from RGB images of wheat grains, we tested the performance of traditional machine learning, deep learning, and few-shot learning on this dataset. The results showed that Random Forest (RF) had the best accuracy of the traditional machine learning algorithms, but it was far less accurate than all deep learning algorithms. The precision and recall of the deep learning classification model using Vision Transformer (ViT) were the highest, 99.03% and 99.00%, respectively. In addition, few-shot learning could realize fine-grained image recognition for wheat grains, and it had a higher accuracy and recall rate in the case of 5-shot, which were 96.86% and 96.67%, respectively. Materials and Methods: In this work, we proposed a complete wheat grain dataset, WheatGrain, which covers thousands of wheat grain images from 6 DAA to 39 DAA, which can characterize the complete dynamics of grain development. At the same time, we built different algorithms to predict the DAA, including traditional machine learning, deep learning, and few-shot learning, in this dataset, and evaluated the performance of all models. Conclusions: To obtain wheat grain filling dynamics promptly, this study proposed an RGB dataset for the whole growth period of grain development. In addition, detailed comparisons were conducted between traditional machine learning, deep learning, and few-shot learning, which provided the possibility of recognizing the DAA of the grain timely. These results revealed that the ViT could improve the performance of deep learning in predicting the DAA, while few-shot learning could reduce the need for a number of datasets. This work provides a new approach to monitoring wheat grain filling dynamics, and it is beneficial for disaster prevention and improvement of wheat production.

Deep Learning for Circulating Multiple Myeloma Cell (CMMC) Enumeration with the Cellsearch System

Background Circulating Multiple Myeloma Cell (CMMC) enumeration in blood samples with the CELLSEARCH® system is a minimally invasive assay used to quantify plasma cells in patients with Multiple Myeloma (MM) and in precursor stages MGUS and SMM 1 particularly during disease stages when a bone marrow aspirate is not desirable (Foulk et al. 2017). Currently, CMMC identification is performed by human reviewers through visual assessment, which is a time-consuming procedure that could be affected by subjective interpretations. Modern Deep Learning (DL) methods can provide a solution by automating the process of CMMC identification, thus eliminating subjectivity and producing faster and more reproducible results. The purpose of this study was to train and test an automated algorithm (for research use only) based on DL models for CMMC identification in CELLSEARCH® fluorescent images. Methods The DL algorithm was designed to analyze images using a segmentation and a classification network as presented in recent studies (Zeune et al. Nature MI 2020; Coumans et al. ACTC 2021). The DL classification model was trained on 5139 CMMC and 16235 non-CMMC images (training set) of fully anonymized blood samples from the CoMMpass study (NCT01454297 sponsored by the Multiple Myeloma Research Foundation) scanned by CELLTRACKS ANALYZER II® (CTAII). The test set was composed of 75 samples from the CoMMpass study with 1000 images per sample reviewed by an operator (with training and experience of reviewing CTAII images) and processed by the algorithm, for a total of 75000 images. The algorithm was compared with the human reviewer in terms of overall agreement and Cohen's Kappa of the image classification results and of correlation for the CMMC enumeration results per sample. Results In the test dataset, out of 75000 images in total the reviewer identified 32403 CMMCs and the algorithm 32842 CMMCs. The DL algorithm and the reviewer provided the same classification for 71711 images, thus showing very high agreement = 95.6% (Cohen's Kappa = 0.91). CMMC counts per sample and linear regression are shown in the figure: slope = 0.95 (95% CI = 0.02), intercept = 26.99 (95% CI = 11.56) and coefficient of determination R 2 = 0.99. Conclusion These preliminary results show the potential of applying automated algorithms to CMMC identification with the CELLSEARCH® system in order to remove human subjectivity from the review process, thus maximizing standardization among different research centers. 1) The CMMC assay is run in a CLIA/CAP certified laboratory in the US and is also New York State CLEP approved. In the EU, the CMMC assay is research use only (RUO).

Diagnosis of Cardiovascular Diseases by Ensemble Optimization Deep Learning Techniques

Cardiovascular disease (CVD) is a variety of diseases that affect the blood vessels and the heart. The authors propose a set of deep learning inspired by the approach used in CVD support centers for the early diagnosis of CVD using deep learning techniques. Data were collected from patients who received CVD screening. The authors propose a prediction model to diagnose whether people have CVD or not and to provide awareness or diagnosis on that. The performance of each algorithm is compared with that of long-, short-time memory, feedforward, and cascade forward neural networks, and Elman neural networks. The results show that the ensemble deep learning classification and prediction model achieved 98.45% accuracy. Using the proposed early diagnosis model for CVD can help simplify the diagnosis of CVD by medical professionals.

Utilizing Deep Learning Algorithms for Signal Processing in Electrochemical Biosensors: From Data Augmentation to Detection and Quantification of Chemicals of Interest.

Nanomaterial-based aptasensors serve as useful instruments for detecting small biological entities. This work utilizes data gathered from three electrochemical aptamer-based sensors varying in receptors, analytes of interest, and lengths of signals. Our ultimate objective was the automatic detection and quantification of target analytes from a segment of the signal recorded by these sensors. Initially, we proposed a data augmentation method using conditional variational autoencoders to address data scarcity. Secondly, we employed recurrent-based networks for signal extrapolation, ensuring uniform signal lengths. In the third step, we developed seven deep learning classification models (GRU, unidirectional LSTM (ULSTM), bidirectional LSTM (BLSTM), ConvGRU, ConvULSTM, ConvBLSTM, and CNN) to identify and quantify specific analyte concentrations for six distinct classes, ranging from the absence of analyte to 10 μM. Finally, the second classification model was created to distinguish between abnormal and normal data segments, detect the presence or absence of analytes in the sample, and, if detected, identify the specific analyte and quantify its concentration. Evaluating the time series forecasting showed that the GRU-based network outperformed two other ULSTM and BLSTM networks. Regarding classification models, it turned out signal extrapolation was not effective in improving the classification performance. Comparing the role of the network architectures in classification performance, the result showed that hybrid networks, including both convolutional and recurrent layers and CNN networks, achieved 82% to 99% accuracy across all three datasets. Utilizing short-term Fourier transform (STFT) as the preprocessing technique improved the performance of all datasets with accuracies from 84% to 99%. These findings underscore the effectiveness of suitable data preprocessing methods in enhancing neural network performance, enabling automatic analyte identification and quantification from electrochemical aptasensor signals.

Improving biosensor accuracy and speed using dynamic signal change and theory-guided deep learning

False results and time delay are longstanding challenges in biosensing. While classification models and deep learning may provide new opportunities for improving biosensor performance, such as measurement confidence and speed, it remains a challenge to ensure that predictions are explainable and consistent with domain knowledge. Here, we show that consistency of deep learning classification model predictions with domain knowledge in biosensing can be achieved by cost function supervision and enables rapid and accurate biosensing using the biosensor dynamic response. The impact and utility of the methodology were validated by rapid and accurate quantification of microRNA (let-7a) across the nanomolar (nM) to femtomolar (fM) concentration range using the dynamic response of cantilever biosensors. Data augmentation and cost function supervision based on the consistency of model predictions and experimental observations with the theory of surface-based biosensors improved the F1 score, precision, and recall of a recurrent neural network (RNN) classifier by an average of 13.8%. The theory-guided RNN (TGRNN) classifier enabled quantification of target analyte concentration and false results with an average prediction accuracy, precision, and recall of 98.5% using the initial transient or entire dynamic response, which is indicative of high prediction accuracy and low probability of false-negative and false-positive results. Classification scores were used to establish new relationships among biosensor performance characteristics (e.g., measurement confidence) and design parameters (e.g., inputs and hyperparameters of classification models and data acquisition parameters) that may be used for characterizing biosensor performance.

Taming the data deluge: A novel end‐to‐end deep learning system for classifying marine biological and environmental images

AbstractUnderwater imaging enables nondestructive plankton sampling at frequencies, durations, and resolutions unattainable by traditional methods. These systems necessitate automated processes to identify organisms efficiently. Early underwater image processing used a standard approach: binarizing images to segment targets, then integrating deep learning models for classification. While intuitive, this infrastructure has limitations in handling high concentrations of biotic and abiotic particles, rapid changes in dominant taxa, and highly variable target sizes. To address these challenges, we introduce a new framework that starts with a scene classifier to capture large within‐image variation, such as disparities in the layout of particles and dominant taxa. After scene classification, scene‐specific Mask regional convolutional neural network (Mask R‐CNN) models are trained to separate target objects into different groups. The procedure allows information to be extracted from different image types, while minimizing potential bias for commonly occurring features. Using in situ coastal plankton images, we compared the scene‐specific models to the Mask R‐CNN model encompassing all scene categories as a single full model. Results showed that the scene‐specific approach outperformed the full model by achieving a 20% accuracy improvement in complex noisy images. The full model yielded counts that were up to 78% lower than those enumerated by the scene‐specific model for some small‐sized plankton groups. We further tested the framework on images from a benthic video camera and an imaging sonar system with good results. The integration of scene classification, which groups similar images together, can improve the accuracy of detection and classification for complex marine biological images.

Annotating otoliths with a deep generative model

Abstract Otoliths are a central information source for fish ecology and stock management, conveying important data about age and other life history for individual fish. Traditionally, interpretation of otoliths has required skilled expert readers, but recently deep learning classification and regression models have been trained to extract fish age from images of otoliths from a variety of species. Despite high accuracy in many cases, the adoption of such models in fisheries management has been slow. One reason may be that the underlying mechanisms the model uses to derive its results from the data are opaque, and this lack of legibility makes it challenging to build sufficient trust in the results. Here, we implement a deep learning model that instead of age predicts the location of annotation marks for each of the annuli. This allows an expert to evaluate the model’s performance in detail. The quality of the annotations was judged by a panel of four expert otolith readers in a double-blinded randomized survey. Using a scale from 1 to 5, the generated marks received an average quality score of 4.22, whereas expert annotations received an average score of 4.33. By counting the marks to determine fish age, we obtained an agreement between expert and model annotations of 64% on our test set, which running the model stochastically increased to 69%. Stochastic sampling yields further benefits, including an explicit measure of the model’s uncertainty, the post hoc likelihood of the different age classes for each otolith, and a set of alternative annotation sequences that highlight the structure of the annuli.

Breast cancer classification based on convolutional neural network and image fusion approaches using ultrasound images

Deep learning and image processing are used to classify and segment breast tumor images, specifically in ultrasound (US) modalities, to support clinical decisions and improve healthcare quality. However, directly using US images can be challenging due to noise and diverse imaging modalities. In this study, we developed a three-step image processing scheme involving speckle noise filtering using a block-matching three-dimensional filtering technique, region of interest highlighting, and RGB fusion. This method enhances the generalization of deep-learning models and achieves better performance. We used a deep learning model (VGG19) to perform transfer learning on three datasets: BUSI (780 images), Dataset B (162 images), and KAIMRC (5693 images). When tested on the BUSI and KAIMRC datasets using a fivefold cross-validation mechanism, the model with the proposed preprocessing step performed better than without preprocessing for each dataset. The proposed image processing approach improves the performance of the breast cancer deep learning classification model. Multiple diverse datasets (private and public) were used to generalize the model for clinical application.

Can Perceptual Guidance Lead to Semantically Explainable Adversarial Perturbations?

It is well known that carefully crafted imperceptible perturbations can cause state-of-the-art deep learning classification models to misclassify. Understanding and analyzing these adversarial perturbations play a crucial role in the design of robust convolutional neural networks. However, their mechanics are not well understood. In this work, we investigate the following question: Is there any relationship between the imperceptibility and semantic significance of adversarial perturbations? In other words, can adversarial perturbations change only the regions of the image that are important for classification, while still being imperceptible? To address this, we consider generating adversarial perturbations by explicitly incorporating a “perceptual quality ball” constraint in our formulation. We pose this adversarial example generation problem as a tractable convex optimization problem, with constraints taken from a mathematically amenable variant of the popular SSIM index. We also provide a fast approximation algorithm to solve the proposed convex optimization problem, bringing our technique in line with other <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$l_{p}$</tex-math></inline-formula> based techniques like PGD, both in form and computational complexity. We use the MobileNetV2 network trained on the ImageNet dataset for our experiments. By comparing the SSIM maps generated by our method with class activation maps, we observe that the perceptually guided perturbations generated by the proposed technique introduce changes specifically in the regions that contribute to classification decisions i.e., the proposed method induces changes that are semantic.

BCI-AMSH: A MATLAB based open-source brain computer interface assistive application for mental stress healing

Numerous Brain computer interface (BCI) assistive software applications or toolboxes help to monitor the status of brain through Electroencephalogram (EEG); however, currently there is no application available to alleviate mental stress along with EEG analysis. In this paper, a new MATLAB-based assistive application called BCI-AMSH (Brain-Computer Interface-Assistive Mental Stress Healing) is developed. This application includes EEG signal offline analysis and stress healing techniques, such as guided meditation and singing bowl sound therapy, combined with real-time EEG analysis using the Enobio-8 device. The EEG offline analysis and stress healing modules are designed to be platform-independent.EEG offline analysis module offers signal preprocessing methods, diverse EEG signal analysis techniques, feature extraction methods, such as time and frequency domain analysis, and a range of machine learning and deep learning models for classification, various performance evaluation metrics. Additionally, it generates comprehensive EEG report about the user's mental states such as focus, relax and stress both in real-time and offline analysis. Furthermore, the stress healing module provides a variety of guided breathing practices and singing bowl sound therapy practices to effectively reduce stress levels. This new application is designed to be very simple and user-friendly, making it accessible to users without prior experience. Its potential applications are significant, particularly in the clinical industry for mental health purposes, as well as for novice researchers seeking to explore new possibilities in BCI.

Combined deep-learning MRI-based radiomic models for preoperative risk classification of endometrial endometrioid adenocarcinoma.

Differences exist between high- and low-risk endometrial cancer (EC) in terms of whether lymph node dissection is performed. Factors such as tumor grade, myometrial invasion (MDI), and lymphovascular space invasion (LVSI) in the European Society for Medical Oncology (ESMO), European SocieTy for Radiotherapy & Oncology (ESTRO) and European Society of Gynaecological Oncology (ESGO) guidelines risk classification can often only be accurately assessed postoperatively. The aim of our study was to estimate the risk classification of patients with endometrial endometrioid adenocarcinoma before surgery and offer individualized treatment plans based on their risk classification. Clinical information and last preoperative pelvic magnetic resonance imaging (MRI) of patients with postoperative pathologically determined endometrial endometrioid adenocarcinoma were collected retrospectively. The region of interest (ROI) was subsequently plotted in T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI) MRI scans, and the traditional radiomics features and deep-learning image features were extracted. A final radiomics nomogram model integrating traditional radiomics features, deep learning image features, and clinical information was constructed to distinguish between low- and high-risk patients (based on the 2020 ESMO-ESGO-ESTRO guidelines). The efficacy of the model was evaluated in the training and validation sets of the model. We finally included 168 patients from January 1, 2020 to July 29, 2021, of which 95 patients in 2021 were classified as the training set and 73 patients in 2020 were classified as the validation set. In the training set, the area under the curve (AUC) of the radiomics nomogram was 0.923 (95%CI: 0.865-0.980) and in the validation set, the AUC of the radiomics nomogram was 0.842 (95%CI: 0.762-0.923). The nomogram had better predictions than both the traditional radiomics model and the deep-learning radiomics model. MRI-based radiomics models can be useful for preoperative risk classification of patients with endometrial endometrioid adenocarcinoma.

Artificial Intelligence based real-time automatic detection and classification of skin lesion in dermoscopic samples using DenseNet-169 architecture

The most common challenge faced by dermoscopy images is the automatic detection of lesion features. All the existing solutions focus on complex algorithms to provide accurate detections. In this research work, proposed Online Tigerclaw Fuzzy Region Segmentation with Deep Learning Classification model, an intellectual model is proposed that provides discrimination of features with classification even in fine-grained samples. This model works on four different stages, which include the Boosted Anisotropic Diffusion filter with Recursive Pixel Histogram Equalization (BADF-RPHE) in the preprocessing stage. The next step is the proposed Online Tigerclaw Fuzzy Region Segmentation (OTFRS) algorithm for lesion area segmentation of dermoscopic images, which can achieve 98.9% and 97.4% accuracy for benign and malignant lesions, respectively. In the proposed OTFRS, an accuracy improvement of 1.4% is achieved when compared with previous methods. Finally, the increased robustness of lesion classification is achieved using Deep Learning Classification –DenseNet 169 with 500 images. The proposed approach was evaluated with accuracy classifications of 100% and 98.86% for benign and malignant lesions, respectively, and a processing time of less than 18 sec. In the proposed DensetNet-169 classification technique, an accuracy improvement of 3% is achieved when compared with other state-of-art methods. A higher range of true positive values is obtained for the Region of Convergence (ROC) curve, which indicates that the proposed work ensures better performance in clinical diagnosis for accurate feature visualization analysis. The methodology has been validated to prove its effectiveness and throw light on the lives of affected patients so they can resume normalcy and live long. The research work was tested in real-time clinical samples, which delivered promising and encouraging results in skin cell detection procedures.

Video-Based Activity Recognition for Automated Motor Assessment of Parkinson's Disease.

Over the last decade, video-enabled mobile devices have become ubiquitous, while advances in markerless pose estimation allow an individual's body position to be tracked accurately and efficiently across the frames of a video. Previous work by this and other groups has shown that pose-extracted kinematic features can be used to reliably measure motor impairment in Parkinson's disease (PD). This presents the prospect of developing an asynchronous and scalable, video-based assessment of motor dysfunction. Crucial to this endeavour is the ability to automatically recognise the class of an action being performed, without which manual labelling is required. Representing the evolution of body joint locations as a spatio-temporal graph, we implement a deep-learning model for video and frame-level classification of activities performed according to part 3 of the Movement Disorder Society Unified PD Rating Scale (MDS-UPDRS). We train and validate this system using a dataset of n = 7310 video clips, recorded at 5 independent sites. This approach reaches human-level performance in detecting and classifying periods of activity within monocular video clips. Our framework could support clinical workflows and patient care at scale through applications such as quality monitoring of clinical data collection, automated labelling of video streams, or a module within a remote self-assessment system.

Deep Learning to Predict the Cell Proliferation and Prognosis of Non-Small Cell Lung Cancer Based on FDG-PET/CT Images.

(1) Background: Cell proliferation (Ki-67) has important clinical value in the treatment and prognosis of non-small cell lung cancer (NSCLC). However, current detection methods for Ki-67 are invasive and can lead to incorrect results. This study aimed to explore a deep learning classification model for the prediction of Ki-67 and the prognosis of NSCLC based on FDG-PET/CT images. (2) Methods: The FDG-PET/CT scan results of 159 patients with NSCLC confirmed via pathology were analyzed retrospectively, and the prediction models for the Ki-67 expression level based on PET images, CT images and PET/CT combined images were constructed using Densenet201. Based on a Ki-67 high expression score (HES) obtained from the prediction model, the survival rate of patients with NSCLC was analyzed using Kaplan-Meier and univariate Cox regression. (3) Results: The statistical analysis showed that Ki-67 expression was significantly correlated with clinical features of NSCLC, including age, gender, differentiation state and histopathological type. After a comparison of the three models (i.e., the PET model, the CT model, and the FDG-PET/CT combined model), the combined model was found to have the greatest advantage in Ki-67 prediction in terms of AUC (0.891), accuracy (0.822), precision (0.776) and specificity (0.902). Meanwhile, our results indicated that HES was a risk factor for prognosis and could be used for the survival prediction of NSCLC patients. (4) Conclusions: The deep-learning-based FDG-PET/CT radiomics classifier provided a novel non-invasive strategy with which to evaluate the malignancy and prognosis of NSCLC.

Chagas parasite classification in blood sample images using different machine learning architectures.

Chagas disease is a life-threatening illness mainly found in Latin America. Early identification and diagnosis of Chagas disease are critical for reducing the death rate of individuals since cures and treatments are available at the acute stage. In this work, we test and compare several deep learning classification models on smear blood sample images for the task of Chagas parasite classification. Our experiments showed that the best classification model is a deep learning architecture based on a residual network together with separable convolution blocks as feature extractors and using a support vector machine algorithm as the classifier in the final layer. This optimized model, we named Res2_SVM, with a reduced number of parameters, achieved an accuracy of [Formula: see text], precision of [Formula: see text], recall of [Formula: see text], and F1-score of [Formula: see text] on our test dataset, overcoming other machine learning models.

Evaluation of thermal damages of concrete subjected to high temperatures using recurrent neural networks for ultrasonic pulse waves

This study aims to propose the use of deep learning methods to classify the thermal damage of concrete cylinder specimens based on ultrasonic pulse wave data. Data are collected from laboratory experiments using concrete specimens with three different water-to-binder ratios (0.54, 0.46, and 0.35). The specimens are subjected to different target temperatures (100 °C, 200 °C, 300 °C, 400 °C and 600 °C) and another set of cylinders are subjected to just the room temperature to represent the normal temperature condition (20 °C). Thermal damages are classified using deep learning classification models based on three recurrent neural networks (long short-term memory, gated recurrent unit, and bidirectional long short-term memory) of the ultrasonic pulse wave data. It is demonstrated that deep learning yields a high accuracy in classifying thermal damage of concrete with a value of 88.24% based on the combination of instantaneous frequency and spectral entropy of ultrasonic times series with a sampling frequency of 1 MHz, as an input of the gated recurrent unit. The performance of the deep learning classification model is superior to models based on two conventional ultrasonic parameters (ultrasonic pulse velocity and signal coherence).

Comparison of deep learning classification models for facial image age estimation in digital forensic investigations

There has been a significant rise in digital forensic investigations containing Indecent Images of Children (IIoC), and one of the major challenges faced by investigators is the time-consuming task of manually investigating images for illicit content. In the UK, law enforcement maintains and uses a standard national repository of IIoC, known as CAID (Child Abuse Image Database), to identify known illegal images by matching their image hashes and metadata. The CAID plays a significant role in making IIoC investigations faster and more effective. However, all images that are not matched through using CAID require manual analysis. Every image has to be viewed and verified as IIoC by investigators. The victim age estimation in the images (i.e., determining whether they are juvenile or adult as this would change the course of the investigation) is a crucial part of this verification process and takes time due to a large number of images to inspect, therefore impacting the speed of the investigation, and consequently victims. This is a time-consuming and challenging task for human investigators.Previous work has demonstrated that deep learning has the capability to estimate age with high accuracy in images. This reduces the number of images that will need to be manually processed, thereby finishing the investigation faster. However, in terms of practical implementation in IIoC investigations, there is an absence of a comparative study using the same datasets to establish the most appropriate deep learning model and classification approach to use. This is important as different models have different capabilities and previous works utilise various binary, multi-class, and regression approaches. It is not yet known which is the most accurate for use in digital forensic investigations. In this paper, we construct an extensive dataset before experimenting with four pre-trained deep learning models: VGG16, ResNet50, Xception, and InceptionV3. We have identified that binary classification works best for the identification of images as a child or adult, with the ResNet50 obtaining the best results in terms of accuracy (91.70%) on unseen images.