RESUMEN
The rapidly expanding Internet of Medical Things (IoMT) landscape fosters enormous opportunities for personalized healthcare, yet it also exposes patients and healthcare systems to diverse security threats. Heterogeneous IoMT devices present challenges that need comprehensive risk assessment due to their varying functionality, protocols, and vulnerabilities. Hence, to achieve the goal of having risk-free IoMT devices, the authors used a hybrid approach using fuzzy logic and the Fuzzy Analytical Hierarchy Process (FAHP) to evaluate risks, providing effective and useful results for developers and researchers. The presented approach specifies qualitative descriptors such as the frequency of occurrence, consequence severity, weight factor, and risk level. A case study with risk events in three different IoMT devices was carried out to illustrate the proposed method. We performed a Bluetooth Low Energy (BLE) attack on an oximeter, smartwatch, and smart peak flow meter to discover their vulnerabilities. Using the FAHP method, we calculated fuzzy weights and risk levels, which helped us to prioritize criteria and alternatives in decision-making. Smartwatches were found to have a risk level of 8.57 for injection attacks, which is of extreme importance and needs immediate attention. Conversely, jamming attacks registered the lowest risk level of 1, with 9 being the maximum risk level and 1 the minimum. Based on this risk assessment, appropriate security measures can be implemented to address the severity of potential threats. The findings will assist healthcare industry decision-makers in evaluating the relative importance of risk factors, aiding informed decisions through weight comparison.
RESUMEN
The privacy and security of patients' health records have been an ongoing issue, and researchers are in a race against technology to design a system that can help stop the compromising of patient data. Many researchers have proposed solutions; however, most solutions have not incorporated potential parameters that can ensure private and secure personal health records management, which is the focus of this study. To design and develop a solution, this research thoroughly investigated existing solutions and identified potential key contexts. These include IOTA Tangle, Distributed Ledger Technology (DLT), IPFS protocols, Application Programming Interface (API), Proxy Re-encryption (PRE), and access control, which are analysed and integrated to secure patient medical records, and Internet of Things (IoT) medical devices, to develop a patient-based access management system that gives patients full control of their health records. This research developed four prototype applications to demonstrate the proposed solution: the web appointment application, the patient application, the doctor application, and the remote medical IoT device application. The results indicate that the proposed framework can improve healthcare services by providing immutable, secure, scalable, trusted, self-managed, and traceable patient health records while giving patients full control of their own medical records.
Asunto(s)
Seguridad Computacional , Registros de Salud Personal , Humanos , Registros Electrónicos de Salud , Programas Informáticos , TecnologíaRESUMEN
Electronic Health Records (EHR) are the healthcare sector's core digital strategy meant to improve the quality of care provided to patients. Despite the benefits afforded by this digital transformation initiative, adoption among healthcare organizations has been slower than desired. The sheer volume and sensitive nature of patient records compel these organizations to exercise a healthy amount of caution in implementing EHR. Cyberattacks have also increased the risks associated with non-optimal EHR implementations. An influx of high-profile data breaches has plagued the sector during the COVID-19 pandemic, which put the spotlight on EHR cybersecurity. One objective of this research project is to aid the acceleration of EHR adoption. Another objective is to ensure the robustness of the system to resist malicious attacks. For the former, a systematic review was used to unearth all the possible causes why the adoption of EHR has been anemic. In this paper, sixty-five existing proposed EHR solutions were analyzed and it was found that there are fourteen major challenges that need to be addressed to reduce friction and risk for health organizations. These were privacy, security, confidentiality, interoperability, access control, scalability, authentication, accessibility, availability, data storage, data ownership, data validity, data integrity, and ease of use. We propose EHRChain, a new framework that tackles all the listed challenges simultaneously to address the first objective while also being designed to achieve the second objective. It is enabled by dual-blockchains based on Hyperledger Sawtooth to allow patient data decentralization via a consortium blockchain and IPFS for distributed data storage.
Asunto(s)
Cadena de Bloques , COVID-19 , COVID-19/epidemiología , Seguridad Computacional , Registros Electrónicos de Salud , Humanos , PandemiasRESUMEN
Objective: Early diagnosis of breast cancer can lead to effective treatment, possibly increase long-term survival rates, and improve quality of life. The objective of this study is to present an automated analysis and classification system for breast cancer using clinical markers such as tumor shape, orientation, margin, and surrounding tissue. The novelty and uniqueness of the study lie in the approach of considering medical features based on the diagnosis of radiologists. Methods: Using clinical markers, a graph is generated where each feature is represented by a node, and the connection between them is represented by an edge which is derived through Pearson's correlation method. A graph convolutional network (GCN) model is proposed to classify breast tumors into benign and malignant, using the graph data. Several statistical tests are performed to assess the importance of the proposed features. The performance of the proposed GCN model is improved by experimenting with different layer configurations and hyper-parameter settings. Results: Results show that the proposed model has a 98.73% test accuracy. The performance of the model is compared with a graph attention network, a one-dimensional convolutional neural network, and five transfer learning models, ten machine learning models, and three ensemble learning models. The performance of the model was further assessed with three supplementary breast cancer ultrasound image datasets, where the accuracies are 91.03%, 94.37%, and 89.62% for Dataset A, Dataset B, and Dataset C (combining Dataset A and Dataset B) respectively. Overfitting issues are assessed through k-fold cross-validation. Conclusion: Several variants are utilized to present a more rigorous and fair evaluation of our work, especially the importance of extracting clinically relevant features. Moreover, a GCN model using graph data can be a promising solution for an automated feature-based breast image classification system.
RESUMEN
This study proposes a novel approach for breast tumor classification from ultrasound images into benign and malignant by converting the region of interest (ROI) of a 2D ultrasound image into a 3D representation using the point-e system, allowing for in-depth analysis of underlying characteristics. Instead of relying solely on 2D imaging features, this method extracts 3D mesh features that describe tumor patterns more precisely. Ten informative and medically relevant mesh features are extracted and assessed with two feature selection techniques. Additionally, a feature pattern analysis has been conducted to determine the feature's significance. A feature table with dimensions of 445 × 12 is generated and a graph is constructed, considering the rows as nodes and the relationships among the nodes as edges. The Spearman correlation coefficient method is employed to identify edges between the strongly connected nodes (with a correlation score greater than or equal to 0.7), resulting in a graph containing 56,054 edges and 445 nodes. A graph attention network (GAT) is proposed for the classification task and the model is optimized with an ablation study, resulting in the highest accuracy of 99.34%. The performance of the proposed model is compared with ten machine learning (ML) models and one-dimensional convolutional neural network where the test accuracy of these models ranges from 73 to 91%. Our novel 3D mesh-based approach, coupled with the GAT, yields promising performance for breast tumor classification, outperforming traditional models, and has the potential to reduce time and effort of radiologists providing a reliable diagnostic system.
Asunto(s)
Neoplasias de la Mama , Imagenología Tridimensional , Humanos , Neoplasias de la Mama/diagnóstico por imagen , Neoplasias de la Mama/patología , Neoplasias de la Mama/cirugía , Femenino , Imagenología Tridimensional/métodos , Interpretación de Imagen Asistida por Computador/métodos , Algoritmos , Ultrasonografía Mamaria/métodos , Redes Neurales de la ComputaciónRESUMEN
An automated computer-aided approach might aid radiologists in diagnosing breast cancer at a primary stage. This study proposes a novel decision support system to classify breast tumors into benign and malignant based on clinically important features, using ultrasound images. Nine handcrafted features, which align with the clinical markers used by radiologists, are extracted from the region of interest (ROI) of ultrasound images. To validate that these elected clinical markers have a significant impact on predicting the benign and malignant classes, ten machine learning (ML) models are experimented with resulting in test accuracies in the range of 96 to 99%. In addition, four feature selection techniques are explored where two features are eliminated according to the feature ranking score of each feature selection method. The Random Forest classifier is trained with the resultant four feature sets. Results indicate that even when eliminating only two features, the performance of the model is reduced for each feature selection technique. These experiments validate the efficiency and effectiveness of the clinically important features. To develop the decision support system, a probability density function (PDF) graph is generated for each feature in order to find a threshold range to distinguish benign and malignant tumors. Based on the threshold range of particular features, a decision support system is developed in such a way that if at least eight out of nine features are within the threshold range, the image will be denoted as true predicted. With this algorithm, a test accuracy of 99.38% and an F1 Score of 99.05% is achieved, which means that our decision support system outperforms all the previously trained ML models. Moreover, after calculating individual class-based test accuracies, for the benign class, a test accuracy of 99.31% has been attained where only three benign instances are misclassified out of 437 instances, and for the malignant class, a test accuracy of 99.52% has been attained where only one malignant instance is misclassified out of 210 instances. This system is robust, time-effective, and reliable as the radiologists' criteria are followed and may aid specialists in making a diagnosis.
RESUMEN
Hearing loss is a prevalent health issue that affects individuals worldwide. Binaural hearing refers to the ability to integrate information received simultaneously from both ears, allowing individuals to identify, locate, and separate sound sources. Auditory evoked potentials (AEPs) refer to the electrical responses that are generated within any part of the auditory system in response to auditory stimuli presented externally. Electroencephalography (EEG) is a non-invasive technology used for the monitoring of AEPs. This research aims to investigate the use of audiometric EEGs as an objective method to detect specific features of binaural hearing with frequency and time domain analysis techniques. Thirty-five subjects with normal hearing and a mean age of 27.35 participated in the research. The stimuli used in the current study were designed to investigate the impact of binaural phase shifts of the auditory stimuli in the presence of noise. The frequency domain and time domain analyses provided statistically significant and promising novel findings. The study utilized Blackman windowed 18 ms and 48 ms pure tones as stimuli, embedded in noise maskers, of frequencies 125 Hz, 250 Hz, 500 Hz, 750 Hz, 1000 Hz in homophasic (the same phase in both ears) and antiphasic (180-degree phase difference between the two ears) conditions. The study focuses on the effect of phase reversal of auditory stimuli in noise of the middle latency response (MLR) and late latency response (LLR) regions of the AEPs. The frequency domain analysis revealed a significant difference in the frequency bands of 20 to 25 Hz and 25 to 30 Hz when elicited by antiphasic and homophasic stimuli of 500 Hz for MLRs and 500 Hz and 250 Hz for LLRs. The time domain analysis identified the Na peak of the MLR for 500 Hz, the N1 peak of the LLR for 500 Hz stimuli and the P300 peak of the LLR for 250 Hz as significant potential markers in detecting binaural processing in the brain.
RESUMEN
The binaural masking level difference (BMLD) is a psychoacoustic method to determine binaural interaction and central auditory processes. The BMLD is the difference in hearing thresholds in homophasic and antiphasic conditions. The duration, phase and frequency of the stimuli can affect the BMLD. The main aim of the study is to evaluate the BMLD for stimuli of different durations and frequencies which could also be used in future electrophysiological studies. To this end we developed a GUI to present different frequency signals of variable duration and determine the BMLD. Three different durations and five different frequencies are explored. The results of the study confirm that the hearing threshold for the antiphasic condition is lower than the hearing threshold for the homophasic condition and that differences are significant for signals of 18ms and 48ms duration. Future objective binaural processing studies will be based on 18ms and 48ms stimuli with the same frequencies as used in the current study.
RESUMEN
In this study, multiple lung diseases are diagnosed with the help of the Neural Network algorithm. Specifically, Emphysema, Infiltration, Mass, Pleural Thickening, Pneumonia, Pneumothorax, Atelectasis, Edema, Effusion, Hernia, Cardiomegaly, Pulmonary Fibrosis, Nodule, and Consolidation, are studied from the ChestX-ray14 dataset. A proposed fine-tuned MobileLungNetV2 model is employed for analysis. Initially, pre-processing is done on the X-ray images from the dataset using CLAHE to increase image contrast. Additionally, a Gaussian Filter, to denoise images, and data augmentation methods are used. The pre-processed images are fed into several transfer learning models; such as InceptionV3, AlexNet, DenseNet121, VGG19, and MobileNetV2. Among these models, MobileNetV2 performed with the highest accuracy of 91.6% in overall classifying lesions on Chest X-ray Images. This model is then fine-tuned to optimise the MobileLungNetV2 model. On the pre-processed data, the fine-tuned model, MobileLungNetV2, achieves an extraordinary classification accuracy of 96.97%. Using a confusion matrix for all the classes, it is determined that the model has an overall high precision, recall, and specificity scores of 96.71%, 96.83% and 99.78% respectively. The study employs the Grad-cam output to determine the heatmap of disease detection. The proposed model shows promising results in classifying multiple lesions on Chest X-ray images.
Asunto(s)
Enfisema Pulmonar , Humanos , Rayos X , Tórax , Algoritmos , AprendizajeRESUMEN
Current research indicates that for the identification of lung disorders, comprising pneumonia and COVID-19, structural distortions of bronchi and arteries (BA) should be taken into account. CT scans are an effective modality to detect lung anomalies. However, anomalies in bronchi and arteries can be difficult to detect. Therefore, in this study, alterations of bronchi and arteries are considered in the classification of lung diseases. Four approaches to highlight these are introduced: (a) a Hessian-based approach, (b) a region-growing algorithm, (c) a clustering-based approach, and (d) a color-coding-based approach. Prior to this, the lungs are segmented, employing several image preprocessing algorithms. The utilized COVID-19 Lung CT scan dataset contains three classes named Non-COVID, COVID, and community-acquired pneumonia, having 6983, 7593, and 2618 samples, respectively. To classify the CT scans into three classes, two deep learning architectures, (a) a convolutional neural network (CNN) and (b) a CNN with long short-term memory (LSTM) and an attention mechanism, are considered. Both these models are trained with the four datasets achieved from the four approaches. Results show that the CNN model achieved test accuracies of 88.52%, 87.14%, 92.36%, and 95.84% for the Hessian, the region-growing, the color-coding, and the clustering-based approaches, respectively. The CNN with LSTM and an attention mechanism model results in an increase in overall accuracy for all approaches with an 89.61%, 88.28%, 94.61%, and 97.12% test accuracy for the Hessian, region-growing, color-coding, and clustering-based approaches, respectively. To assess overfitting, the accuracy and loss curves and k-fold cross-validation technique are employed. The Hessian-based and region-growing algorithm-based approaches produced nearly equivalent outcomes. Our proposed method outperforms state-of-the-art studies, indicating that it may be worthwhile to pay more attention to BA features in lung disease classification based on CT images.
RESUMEN
BACKGROUND: In today's society, cancer has become a big concern. The most common cancers in women are breast cancer (BC), endometrial cancer (EC), ovarian cancer (OC), and cervical cancer (CC). CC is a type of cervix cancer that is the fourth most common cancer in women and the fourth major cause of death. RESULTS: This research uses a network approach to discover genetic connections, functional enrichment, pathways analysis, microRNAs transcription factors (miRNA-TF) co-regulatory network, gene-disease associations, and therapeutic targets for CC. Three datasets from the NCBI's GEO collection were considered for this investigation. Then, using a comparison approach between the datasets, 315 common DEGs were discovered. The PPI network was built using a variety of combinatorial statistical approaches and bioinformatics tools, and the PPI network was then utilized to identify hub genes and critical modules. CONCLUSION: Furthermore, we discovered that CC has specific similar links with the progression of different tumors using Gene Ontology terminology and pathway analysis. Transcription factors-gene linkages, gene-disease correlations, and the miRNA-TF co-regulatory network were revealed to have functional enrichments. We believe the candidate drugs identified in this study could be effective for advanced CC treatment.
RESUMEN
Diabetic retinopathy (DR) is the foremost cause of blindness in people with diabetes worldwide, and early diagnosis is essential for effective treatment. Unfortunately, the present DR screening method requires the skill of ophthalmologists and is time-consuming. In this study, we present an automated system for DR severity classification employing the fine-tuned Compact Convolutional Transformer (CCT) model to overcome these issues. We assembled five datasets to generate a more extensive dataset containing 53,185 raw images. Various image pre-processing techniques and 12 types of augmentation procedures were applied to improve image quality and create a massive dataset. A new DR-CCTNet model is proposed. It is a modification of the original CCT model to address training time concerns and work with a large amount of data. Our proposed model delivers excellent accuracy even with low-pixel images and still has strong performance with fewer images, indicating that the model is robust. We compare our model's performance with transfer learning models such as VGG19, VGG16, MobileNetV2, and ResNet50. The test accuracy of the VGG19, ResNet50, VGG16, and MobileNetV2 were, respectively, 72.88%, 76.67%, 73.22%, and 71.98%. Our proposed DR-CCTNet model to classify DR outperformed all of these with a 90.17% test accuracy. This approach provides a novel and efficient method for the detection of DR, which may lower the burden on ophthalmologists and expedite treatment for patients.
RESUMEN
Named Entity Recognition (NER) plays a significant role in enhancing the performance of all types of domain specific applications in Natural Language Processing (NLP). According to the type of application, the goal of NER is to identify target entities based on the context of other existing entities in a sentence. Numerous architectures have demonstrated good performance for high-resource languages such as English and Chinese NER. However, currently existing NER models for Bengali could not achieve reliable accuracy due to morphological richness of Bengali and limited availability of resources. This work integrates both Data and Model Centric AI concepts to achieve a state-of-the-art performance. A unique dataset was created for this study demonstrating the impact of a good quality dataset on accuracy. We proposed a method for developing a high quality NER dataset for any language. We have used our dataset to evaluate the performance of various Deep Learning models. A hybrid model performed with the exact match F1 score of 87.50%, partial match F1 score of 92.31%, and micro F1 score of 98.32%. Our proposed model reduces the need for feature engineering and utilizes minimal resources.
Asunto(s)
Inteligencia Artificial , Lenguaje , Procesamiento de Lenguaje NaturalRESUMEN
Introduction: Breast cancer stands as the second most deadly form of cancer among women worldwide. Early diagnosis and treatment can significantly mitigate mortality rates. Purpose: The study aims to classify breast ultrasound images into benign and malignant tumors. This approach involves segmenting the breast's region of interest (ROI) employing an optimized UNet architecture and classifying the ROIs through an optimized shallow CNN model utilizing an ablation study. Method: Several image processing techniques are utilized to improve image quality by removing text, artifacts, and speckle noise, and statistical analysis is done to check the enhanced image quality is satisfactory. With the processed dataset, the segmentation of breast tumor ROI is carried out, optimizing the UNet model through an ablation study where the architectural configuration and hyperparameters are altered. After obtaining the tumor ROIs from the fine-tuned UNet model (RKO-UNet), an optimized CNN model is employed to classify the tumor into benign and malignant classes. To enhance the CNN model's performance, an ablation study is conducted, coupled with the integration of an attention unit. The model's performance is further assessed by classifying breast cancer with mammogram images. Result: The proposed classification model (RKONet-13) results in an accuracy of 98.41 %. The performance of the proposed model is further compared with five transfer learning models for both pre-segmented and post-segmented datasets. K-fold cross-validation is done to assess the proposed RKONet-13 model's performance stability. Furthermore, the performance of the proposed model is compared with previous literature, where the proposed model outperforms existing methods, demonstrating its effectiveness in breast cancer diagnosis. Lastly, the model demonstrates its robustness for breast cancer classification, delivering an exceptional performance of 96.21 % on a mammogram dataset. Conclusion: The efficacy of this study relies on image pre-processing, segmentation with hybrid attention UNet, and classification with fine-tuned robust CNN model. This comprehensive approach aims to determine an effective technique for detecting breast cancer within ultrasound images.
RESUMEN
PURPOSE: An automated computerized approach can aid radiologists in the early diagnosis of breast cancer. In this study, a novel method is proposed for classifying breast tumors into benign and malignant, based on the ultrasound images through a Graph Neural Network (GNN) model utilizing clinically significant features. METHOD: Ten informative features are extracted from the region of interest (ROI), based on the radiologists' diagnosis markers. The significance of the features is evaluated using density plot and T test statistical analysis method. A feature table is generated where each row represents individual image, considered as node, and the edges between the nodes are denoted by calculating the Spearman correlation coefficient. A graph dataset is generated and fed into the GNN model. The model is configured through ablation study and Bayesian optimization. The optimized model is then evaluated with different correlation thresholds for getting the highest performance with a shallow graph. The performance consistency is validated with k-fold cross validation. The impact of utilizing ROIs and handcrafted features for breast tumor classification is evaluated by comparing the model's performance with Histogram of Oriented Gradients (HOG) descriptor features from the entire ultrasound image. Lastly, a clustering-based analysis is performed to generate a new filtered graph, considering weak and strong relationships of the nodes, based on the similarities. RESULTS: The results indicate that with a threshold value of 0.95, the GNN model achieves the highest test accuracy of 99.48%, precision and recall of 100%, and F1 score of 99.28%, reducing the number of edges by 85.5%. The GNN model's performance is 86.91%, considering no threshold value for the graph generated from HOG descriptor features. Different threshold values for the Spearman's correlation score are experimented with and the performance is compared. No significant differences are observed between the previous graph and the filtered graph. CONCLUSION: The proposed approach might aid the radiologists in effective diagnosing and learning tumor pattern of breast cancer.
Asunto(s)
Neoplasias de la Mama , Humanos , Femenino , Neoplasias de la Mama/diagnóstico por imagen , Teorema de Bayes , Ultrasonografía , Mama , Redes Neurales de la ComputaciónRESUMEN
Bronchiectasis in children can progress to a severe lung condition if not diagnosed and treated early. The radiological diagnostic criteria for the diagnosis of bronchiectasis is an increased broncho-arterial (BA) ratio. From high-resolution computed tomography (HRCT) scans, the BA pairs must be detected first to derive the BA ratio. This study aims to identify potential BA pairs from HRCT scans of children undertaken to evaluate suppurative lung disease through an automated approach. After segmenting the lung regions, the HRCT scans are cleaned using a histogram analysis-based approach followed by a potential arteries identification process comprising four conditions based on imaging features. Potential arteries and their connected components are extracted, and potential bronchi are identified. Finally, the coordinates of potential arteries and potential bronchi are matched as the last step of BA pairs extraction. A total of 8-50 BA pairs are detected for each patient. Additionally, the area and several diameters of the bronchi and arteries are measured, and BA ratios based on these are calculated. Through this approach, the BA pairs of a CT scan datasets are detected and utilizing a deep learning model, a high classification test accuracy of 98.53% is achieved, validating the robustness of the proposed BA detection approach. The results show that visible BA pairs can be identified and segmented automatically, and the BA ratio calculated may help diagnose bronchiectasis with less effort and time.
RESUMEN
Knee Osteoarthritis (KOA) is a leading cause of disability and physical inactivity. It is a degenerative joint disease that affects the cartilage, cushions the bones, and protects them from rubbing against each other during motion. If not treated early, it may lead to knee replacement. In this regard, early diagnosis of KOA is necessary for better treatment. Nevertheless, manual KOA detection is time-consuming and error-prone for large data hubs. In contrast, an automated detection system aids the specialist in diagnosing KOA grades accurately and quickly. So, the main objective of this study is to create an automated decision system that can analyze KOA and classify the severity grades, utilizing the extracted features from segmented X-ray images. In this study, two different datasets were collected from the Mendeley and Kaggle database and combined to generate a large data hub containing five classes: Grade 0 (Healthy), Grade 1 (Doubtful), Grade 2 (Minimal), Grade 3 (Moderate), and Grade 4 (Severe). Several image processing techniques were employed to segment the region of interest (ROI). These included Gradient-weighted Class Activation Mapping (Grad-Cam) to detect the ROI, cropping the ROI portion, applying histogram equalization (HE) to improve contrast, brightness, and image quality, and noise reduction (using Otsu thresholding, inverting the image, and morphological closing). Besides, the focus filtering method was utilized to eliminate unwanted images. Then, six feature sets (morphological, GLCM, statistical, texture, LBP, and proposed features) were generated from segmented ROIs. After evaluating the statistical significance of the features and selection methods, the optimal feature set (prominent six distance features) was selected, and five machine learning (ML) models were employed. Additionally, a decision-making strategy based on the six optimal features is proposed. The XGB model outperformed other models with a 99.46 % accuracy, using six distance features, and the proposed decision-making strategy was validated by testing 30 images.
RESUMEN
COVID-19, pneumonia, and tuberculosis have had a significant effect on recent global health. Since 2019, COVID-19 has been a major factor underlying the increase in respiratory-related terminal illness. Early-stage interpretation and identification of these diseases from X-ray images is essential to aid medical specialists in diagnosis. In this study, (COV-X-net19) a convolutional neural network model is developed and customized with a soft attention mechanism to classify lung diseases into four classes: normal, COVID-19, pneumonia, and tuberculosis using chest X-ray images. Image preprocessing is carried out by adjusting optimal parameters to preprocess the images before undertaking training of the classification models. Moreover, the proposed model is optimized by experimenting with different architectural structures and hyperparameters to further boost performance. The performance of the proposed model is compared with eight state-of-the-art transfer learning models for a comparative evaluation. Results suggest that the COV-X-net19 outperforms other models with a testing accuracy of 95.19%, precision of 96.49% and F1-score of 95.13%. Another novel approach of this study is to find out the probable reason behind image misclassification by analyzing the handcrafted imaging features with statistical evaluation. A statistical analysis known as analysis of variance test is performed, to identify at which point the model can identify a class accurately, and at which point the model cannot identify the class. The potential features responsible for the misclassification are also found. Moreover, Random Forest Feature importance technique and Minimum Redundancy Maximum Relevance technique are also explored. The methods and findings of this study can benefit in the clinical perspective in early detection and enable a better understanding of the cause of misclassification.
RESUMEN
Heart disease can be life-threatening if not detected and treated at an early stage. The electrocardiogram (ECG) plays a vital role in classifying cardiovascular diseases, and often physicians and medical researchers examine paper-based ECG images for cardiac diagnosis. An automated heart disease prediction system might help to classify heart diseases accurately at an early stage. This study aims to classify cardiac diseases into five classes with paper-based ECG images using a deep learning approach with the highest possible accuracy and the lowest possible time complexity. This research consists of two approaches. In the first approach, five deep learning models, InceptionV3, ResNet50, MobileNetV2, VGG19, and DenseNet201, are employed. In the second approach, an integrated deep learning model (InRes-106) is introduced, combining InceptionV3 and ResNet50. This model is developed as a deep convolutional neural network capable of extracting hidden and high-level features from images. An ablation study is conducted on the proposed model altering several components and hyperparameters, improving the performance even further. Before training the model, several image pre-processing techniques are employed to remove artifacts and enhance the image quality. Our proposed hybrid InRes-106 model performed best with a testing accuracy of 98.34%. The InceptionV3 model acquired a testing accuracy of 90.56%, the ResNet50 89.63%, the DenseNet201 88.94%, the VGG19 87.87%, and the MobileNetV2 achieved 80.56% testing accuracy. The model is trained with a k-fold cross-validation technique with different k values to evaluate the robustness further. Although the dataset contains a limited number of complex ECG images, our proposed approach, based on various image pre-processing techniques, model fine-tuning, and ablation studies, can effectively diagnose cardiac diseases.
RESUMEN
The complex feature characteristics and low contrast of cancer lesions, a high degree of inter-class resemblance between malignant and benign lesions, and the presence of various artifacts including hairs make automated melanoma recognition in dermoscopy images quite challenging. To date, various computer-aided solutions have been proposed to identify and classify skin cancer. In this paper, a deep learning model with a shallow architecture is proposed to classify the lesions into benign and malignant. To achieve effective training while limiting overfitting problems due to limited training data, image preprocessing and data augmentation processes are introduced. After this, the 'box blur' down-scaling method is employed, which adds efficiency to our study by reducing the overall training time and space complexity significantly. Our proposed shallow convolutional neural network (SCNN_12) model is trained and evaluated on the Kaggle skin cancer data ISIC archive which was augmented to 16485 images by implementing different augmentation techniques. The model was able to achieve an accuracy of 98.87% with optimizer Adam and a learning rate of 0.001. In this regard, parameter and hyper-parameters of the model are determined by performing ablation studies. To assert no occurrence of overfitting, experiments are carried out exploring k-fold cross-validation and different dataset split ratios. Furthermore, to affirm the robustness the model is evaluated on noisy data to examine the performance when the image quality gets corrupted.This research corroborates that effective training for medical image analysis, addressing training time and space complexity, is possible even with a lightweighted network using a limited amount of training data.