Sürdürülebilir Kalkınma Amaçları
Yayınlar
- MakaleYalnız künye2026Efficient ensemble learning with multi-scale fusion based deep neural network for skin lesion classification
Reis, Hatice Catal; Turk, Veysel
Melanoma, a type of skin cancer, is a severe skin cancer that is critical for early diagnosis but difficult to detect. Deep learning is promising in melanoma diagnosis because it can automatically analyze visual features and perform end-to-end learning. However, achieving the optimum balance between performance and computational efficiency for the effective use of these models in clinical applications is an important research topic. In this study, three innovative methods are proposed for skin cancer detection: PADSCNet, P-DEFF, and M–DEFF. The PADSCNet is an effective neural network developed with CNN and multi-head attention techniques, designed with fusion methods, and stands out with its minimum number of parameters despite being quite deep. The P-DEFF and M–DEFF are based on ensemble learning techniques; P-DEFF was developed with a single deep learning model, and M–DEFF was developed with multiple pre-trained deep learning models. The proposed approaches were tested on the Skin Cancer: Malignant vs. Benign dataset, which was pre-processed using image enhancement techniques. According to the experimental results, PADSCNet achieved accuracy rates of 88.12 %, P-DEFF 93.75 %, and M–DEFF 95.00 %. In additional experiments conducted with the PADSCNet model, 93.12 % accuracy rates were achieved in the CNN for Melanoma Detection Dataset, and 95.00 % accuracy rates were achieved in the PH2 dataset. These findings show that the proposed methods are effective in skin cancer detection and can achieve successful results in clinical applications.
- MakaleYalnız künye2026Multi-scale deep fusion architecture for brain tumor detection via local-contextual feature integration
Reis, Hatice Catal; Turk, Veysel
Early detection of brain tumors is crucial for enhancing treatment strategies and improving clinical prognosis. However, current conventional methods limit diagnostic accuracy and slow down diagnostic processes due to subjective interpretations and dependence on experts. Deep learning-based approaches have the potential to enhance diagnostic accuracy and facilitate early diagnosis by mitigating current limitations in automatic learning techniques for feature extraction and modeling processes. In this study, an advanced deep learning model, Multi-Scale Local-Context Fusion Network (MSLCFNet), is proposed for automatic diagnosis of brain tumors within the scope of oncological diseases. The proposed model evaluates local spatial features, global patterns, and long-range contextual relationships holistically through multi-layered representations, enabling effective identification of complex structures of tumor morphology. This architecture has the potential to increase diagnostic consistency and minimize the risk of misdiagnosis by reducing inter-observer variability, especially in cases where limited contrast and unclear boundaries lead to diagnostic uncertainty. The proposed model achieved accuracy rates of 96.51% and 98.17% on two different MRI brain tumor datasets, respectively. Additionally, a hybrid model based on MSLCFNet+ResNet50 was proposed in the study to obtain high-level feature representations for brain tumor diagnosis. The model offers a significant improvement in the diagnosis process by reducing misdiagnosis rates to 98.86% and 99.50% accuracy. The proposed methods make a significant contribution to enhancing diagnostic accuracy in clinical decision support systems, as they enable the efficient processing of complex morphological structures.
- MakaleYalnız künye2026A multi-scale context-aware deep learning framework for medical disease diagnosis
Reis, Hatice Catal; Turk, Veysel
Early and accurate diagnosis of brain tumors, skin lesions, and diabetic retinopathy is essential for effective treatment planning and improving patient prognosis. Nevertheless, the diagnostic process for these conditions remains challenging due to the reliance on conventional methods, which are often subjective, time-intensive, and dependent on expert interpretation. In this context, deep learning-based approaches offer promising opportunities to enhance diagnostic precision and support clinical decision-making. This study introduces BSCRADNet, a novel deep learning model designed for the automated diagnosis of oncological and retinopathic diseases. The proposed architecture employs a multi-layered analytical framework that integrates local and spatial features with long-range contextual dependencies, enabling the effective recognition of complex morphological patterns in medical images. By enhancing diagnostic consistency, BSCRADNet reduces the risk of misclassification—particularly in cases characterized by high inter-observer variability or subtle lesion presentation. The model demonstrated strong performance across multiple datasets, achieving classification accuracies of 94.67% for brain tumors, 89.58% for skin cancer, and 90.40% for diabetic retinopathy. Furthermore, to improve the discriminative power of feature representations across diverse disease categories, a composite hybrid architecture combining BSCRADNet with ResMLP was developed. This hybrid model yielded competitive results, with accuracies of 93.33%, 88.19%, and 87.40% for the respective diagnostic tasks. Experimental findings indicate that the proposed approach is capable of distinguishing intricate patterns in medical imaging data and holds significant potential for integration into clinical diagnostic workflows, contributing to more reliable and efficient disease classification.
- MakaleYalnız künye2025A deep neural network combined with a two-stage ensemble model for detecting cracks in concrete structures
Reis, Hatice Catal; Turk, Veysel; Kaya Yildiz, Cagla Melisa; Bozkurt, Muhammet Furkan; Karagoz, Seray Nur; Ustuner, Mustafa
Detection of cracks in concrete structures is critical for their safety and the sustainability of maintenance processes. Traditional inspection techniques are costly, time-consuming, and inefficient regarding human resources. Deep learning architectures have become more widespread in recent years by accelerating these processes and increasing their efficiency. Deep learning models (DLMs) stand out as an effective solution in crack detection due to their features such as end-to-end learning capability, model adaptation, and automatic learning processes. However, providing an optimal balance between model performance and computational efficiency of DLMs is a vital research topic. In this article, three different methods are proposed for detecting cracks in concrete structures. In the first method, a Separable Convolutional with Attention and Multi-layer Enhanced Fusion Network (SCAMEFNet) deep neural network, which has a deep architecture and can provide a balance between the depth of DLMs and model parameters, has been developed. This model was designed using a convolutional neural network, multi-head attention, and various fusion techniques. The second method proposes a modified vision transformer (ViT) model. A two-stage ensemble learning model, deep feature-based two-stage ensemble model (DFTSEM), is proposed in the third method. In this method, deep features and machine learning methods are used. The proposed approaches are evaluated using the Concrete Cracks Image Data set, which the authors collected and contains concrete cracks on building surfaces. The results show that the SCAMEFNet model achieved an accuracy rate of 98.83%, the ViT model 97.33%, and the DFTSEM model 99.00%. These findings show that the proposed techniques successfully detect surface cracks and deformations and can provide practical solutions to real-world problems. In addition, the developed methods can contribute as a tool for BIM platforms in smart cities for building health.
- MakaleAçık Erişim2025Advanced brain tumor analysis: a novel strategy for segmentation and classification using modern computational methods
Reis, Hatice Catal; Turk, Veysel
Despite their low incidence, brain tumors are one of the most invasive cancer types, constituting a significant burden of death and disease in all age groups. Early and accurate diagnosis of brain tumors plays a vital role in reducing mortality rates. The heterogeneous nature of brain tumors and the diversity of tumor lesions may make it difficult for radiologists to make the right decision in the manual diagnosis process. This study proposes the use of machine learning methods for the classification of brain tumors (pituitary, meningioma, and glioma) and the use of metaheuristic algorithms graph theory, and random walker algorithms in the segmentation of brain tumors. The classification performed with the proposed method obtained an overall accuracy rate of 98.33%. In addition, the classification accuracy of 99.50%, 99.50%, 98.67%, and 99.00% was achieved for no tumor, pituitary, meningioma, and glioma, respectively. Experiments in the segmentation process show that metaheuristic algorithms and max-flow graph cut approach produce successful results.
- MakaleAçık Erişim2025Post-seismic structural assessment: advanced crack detection through complex feature extraction using pre-trained deep learning and machine learning integration
Reis, Hatice Catal; Turk, Veysel; Ustuner, Mustafa; Kaya Yildiz, Cagla Melisa; Tatli, Ramazan
Earthquakes can often cause significant damage to buildings. After an earthquake, experts/managers need to make quick and accurate damage assessments. Traditionally, manual analysis processes have been widely used in damage assessment studies. The fact that these methods are time-consuming and based on human observation leads to certain limitations in damage assessment studies. In recent years, artificial intelligence techniques such as deep learning and machine learning have frequently been preferred in damage detection studies, and significant success has been achieved. This study aimed to automatically detect cracks/damages in the buildings in Diyarbakir city after the February 6, 2023 Kahramanmaras, Turkey earthquake. Our experimental dataset was collected by the researchers and named Kahramanmaras-Diyarbakir Earthquake Building Crack Dataset (KDBECD-2023). The data set consists of four categories in terms of damage level: undamaged, slightly damaged, moderately damaged, and heavily damaged buildings. DenseNet201 deep learning architecture and popular machine learning algorithms, Support Vector Machine, Random Forest, Decision Tree, and K-Nearest Neighbors (KNN) were used to classify cracks at different damage levels. In the experimental phase, feature extraction was performed with the DenseNet201 architecture. In addition, dimensional reduction was applied with the Principal Component Analysis method to reduce the computational complexity of the proposed hybrid study. According to the experimental results, the DenseNet201-KNN hybrid model gave the most successful result with an accuracy value of 94.62%. The results of this study can make important contributions to decision makers and experts in detecting cracks and damages in buildings after an earthquake.
- MakaleAçık Erişim2025DSCIMABNet: A novel multi-head attention depthwise separable CNN model for skin cancer detection
Reis, Hatice Catal; Turk, Veysel
Skin cancer is a common type of cancer worldwide. Early diagnosis of skin cancer can reduce the risk of death by increasing treatment success. However, it is challenging for dermatologists or specialists because the symptoms are vague in the early stages and cannot be noticed by the naked eye. This study examines digital diagnostic techniques supported by artificial intelligence, focusing on early skin cancer detection and two methods have been proposed. In the first method, DSCIMABNet deep learning architecture was developed by combining multi-head attention and depthwise separable convolution techniques. This model provides flexibility in learning the dataset's local features, abstract concepts, and long-term relationships. The DSCIMABNet model and modern deep learning models trained on ImageNet are proposed to be combined with the ensemble learning method in the second method. This approach provides a comprehensive feature extraction process that will increase the performance of the classification process with ensemble learning. The proposed approaches are trained and evaluated on the ISIC 2018 dataset with image enhancement applied in preprocessing. In the experimental results, DSCIMABNet achieved 84.28% accuracy, while the proposed hybrid method achieved 99.40% accuracy. Moreover, on the Mendeley dataset (CNN for Melanoma Detection Data), DSCIMABNet achieved 92.58% accuracy, while the hybrid method achieved 99.37% accuracy. This study may significantly contribute to developing new and effective methods for the early diagnosis and treatment of skin cancer.
- MakaleAçık Erişim2025A multi-stage fusion deep learning framework merging local patterns with attention-driven contextual dependencies for cancer detection
Catal Reis, Hatice; Turk, Veysel
Cancer is a severe threat to public health. Early diagnosis of disease is critical, but the lack of experts in this field, the personal assessment process, the clinical workload, and the high level of similarity in disease classes make it difficult. In recent years, deep learning-based artificial intelligence models have shown promise, with the potential to increase diagnosis speed and accuracy. These models attract attention with their automatic learning and adaptation capabilities. In this study, the deep learning-based PADBSRNet model and the PADBSRNet-Vision Transformer (ViT) hybrid method are proposed for the detection of brain tumors and skin and lung cancers. PADBSRNet is a comprehensive deep neural network architecture that integrates separable and traditional convolution layers, multiple attention mechanisms, bidirectional recurrent neural networks, and cross-connections/multi-stage feature fusion strategies. This architecture offers significant advantages in terms of effectively extracting local-global, contextual features and accurately modeling long-term dependencies in image classification tasks. The second proposed approach developed a hybrid method that combines the advantages of the PADBSRNet model and the ViT model. Experimental analysis on medical datasets such as the Figshare Brain Tumor Dataset, IQ-OTH/NCCD Dataset, and Skin Cancer: Malignant vs. Benign Dataset has evaluated the proposed models' performances. According to the experimental results, the PADBSRNet model has shown successful performance with 95.24 %, 99.55 %, and 88.61 % accuracy rates, respectively. The experimental findings show that the proposed deep learning model can effectively learn the complex relationships and hidden patterns of cancer disease, thus producing applicable and effective results in cancer diagnosis.
- MakaleAçık Erişim2024Integrated deep learning and ensemble learning model for deep feature-based wheat disease detection
Catal Reis, Hatice; Turk, Veysel
Early detection of plant diseases is critical to prevent disease spread and assist farmers. Thanks to their high discrimination ability, Convolutional Neural Network (CNN)-based architectures can offer practical solutions in identifying different plant diseases. This study proposes a combined method to classify wheat plant diseases using the Integrated Deep Learning Framework (IDLF) and ensemble learning (EL) model. The proposed method uses pre-trained deep neural networks (ImageNet -based model (w/pre-training)). In addition, in the classification process, the performance of hybrid methods consisting of 13 deep learning architectures (DLA) trained from scratch, pre-trained DLA, deep, and-machine learning models were analyzed. Moreover, the use of hypercolumn, contrast stretching, and “Contrast Limited Adaptive Histogram Equalization (CLAHE)” techniques are used to improve the image quality of the dataset. It is aimed to obtain a strong classification performance by combining these methods. In the experimental process, in the study using the original dataset, the RegNetY080 model trained from scratch had an accuracy value of 97.64%; in the study with the optimized dataset with CLAHE, an accuracy value of 98.33%; in the study performed with the CLAHE-improved dataset and transfer learning method, an accuracy value of 99.58% was obtained. An accuracy of 99.58% was achieved in the proposed hybrid study with the pre-trained RegNetY080 model and Random Forest (RF). The proposed method using IDLF and EL model provided 99.72% accuracy. When the proposed method was applied to the Wheat Leaf Dataset and Wheat Leaf Disease dataset, 97.56% accuracy was obtained for the Wheat Leaf Dataset and 99.43% for Wheat Leaf Disease. The results of this study can be helpful to experts and farmers in the detection of plant diseases.
- MakaleAçık Erişim2024Fusion of transformer attention and CNN features for skin cancer detection
Reis, Hatice Catal; Turk, Veysel
Melanoma is a skin cancer that spreads quickly and has serious risks. Early diagnosis is essential, but since the symptoms of skin lesions in the early stages are vague and similar, they can be difficult for specialists to detect. Therefore, machine learning-based alternative diagnostic methods can be developed in addition to existing ones. This study proposes a new deep learning model, a modified lightweight vision transformer (ViT) architecture, and a hybrid framework developed with an integrated deep learning model and an Ensemble Learning (EL) model for the early-stage diagnosis of skin lesions. The proposed deep learning model was developed based on convolution layers and transformers. The model is called multi-head attention block depthwise separable convolution network (MABSCNET). The proposed hybrid framework was developed by combining modern deep learning and EL models pre-trained with the ImageNet dataset along with the MABSCNET model. In the experimental process, the effectiveness of the proposed methods was evaluated on the ISIC 2020 dataset. Additionally, additional experiments were conducted on ISIC 2018 and a Kaggle dataset to analyze the proposed hybrid framework's classification performance. Image enhancement techniques were used in the datasets. In the ISIC 2020 dataset, the MABSCNET model reached 78.63 % accuracy, the ViT model obtained 76.50 %, and the hybrid framework reached 92.74 % accuracy. Moreover, the proposed hybrid framework achieved 100 % on the ISIC 2018 dataset and 94.24 % on the Kaggle dataset.
- MakaleAçık Erişim2024Integration of a CNN-based model and ensemble learning for detecting post-earthquake road cracks with deep features
Reis, Hatice Catal; Turk, Veysel; Karacur, Soner; Kurt, Ahmet Melih
A safe and healthy infrastructure is essential for humanity. Maintenance and repair of roads, which are of great importance, especially in transportation, is essential. Roads can sometimes be damaged due to natural disasters or human factors. In this study, roads damaged as a result of the natural disaster and the 6 February 2023 Gaziantep-Kahramanmaras earthquakes, which had devastating/fatal consequences, were studied. In recent years, the use of machine learning methods in the automatic detection process of road cracks has become widespread. Here, deep learning architectures generally based on multilayer convolutional neural networks have become a popular solution, mainly thanks to their high discrimination power in visual data. In this study, it was aimed to automatically detect cracks on the roads in Gaziantep (Nurdagi) and Adiyaman provinces after the earthquake. The data set used in the experimental process consists of two categories: uncracked and cracked, and was collected by the researchers. ResNet152 deep learning architecture, traditional machine learning algorithms, and an ensemble learning (EL) model were used to classify cracks. Among the machine learning algorithms used in the experiments are support vector machine (SVM), K-nearest neighbors, Adaptive Boosting, and Naive Bayes. In the experimental process, ResNet152 architecture was used for feature extraction, and classification was carried out with machine learning algorithms. In addition, the EL method has been used to improve the success of machine learning algorithms. According to experimental results, the SVM algorithm and EL method gave the most successful results with 98.68% accuracy values. The proposed method can benefit experts in the automatic classification of road cracks. The study can contribute to activating rapid coordination and transportation networks in natural disasters that cause fatal and destructive causes, such as earthquakes.
- MakaleYayıncıda açık erişim2024Potato leaf disease detection with a novel deep learning model based on depthwise separable convolution and transformer networks
Catal Reis, Hatice; Turk, Veysel
Early diagnosis of plant diseases is essential in reducing economic losses for farmers and increasing production efficiency. Therefore, Computer-Aided Diagnosis (CAD) systems supported by artificial intelligence technologies can be developed to help diagnose diseases quickly and accurately by examining the symptoms and signs in plant leaves. In this study, Multi-head Attention Mechanism Depthwise Separable Convolution Inception Reduction Network (MDSCIRNet) architecture, an image-based deep convolutional neural network, is proposed for classifying potato leaf diseases. The main components of the MDSCIRNet architecture are depthwise separable convolution (DSC) and a multi-head attention mechanism. The proposed architecture has been compared with modern algorithms developed with DSC technology, such as Xception, MobileNet, and deep learning algorithms, such as ResNet101, InceptionV3, and EfficientNetB2, to evaluate its performance in the classification process. In addition, hybrid methods developed with the classical machine learning algorithms Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), Adaptive Boosting (AdaBoost), and MDSCIRNet model, integrated deep learning model, hard voting ensemble learning model. Suggested methods such as these were also used in the experimental process. Moreover, techniques such as Contrast Limited Adaptive Histogram Equalization (CLAHE), Enhanced Super-Resolution Generative Adversarial Networks (ESRGAN), and Hypercolumn were used to improve the image quality of the data set. In the experimental process, the MDSCIRNet deep learning architecture achieved 99.24% accuracy in the study using the original dataset. While a 99.11% accuracy rate was achieved with the integrated deep learning model and hard voting ensemble learning model, the highest success rate of 99.33% was performed in the study conducted with the MDSCIRNet + SVM method. This study contributes to developing new and effective strategies in the agricultural industry for the early diagnosis and control of potato plant diseases. Machine learning-based approaches offer the potential to minimize economic losses and increase productivity in production by allowing farmers to intervene early.
- MakaleAçık Erişim2023Transfer Learning Approach and Nucleus Segmentation with MedCLNet Colon Cancer Database
Reis, Hatice Catal; Turk, Veysel
Machine learning has been recently used especially in the medical field. In the diagnosis of serious diseases such as cancer, deep learning techniques can be used to reduce the workload of experts and to produce quick solutions. The nuclei found in the histopathology dataset are an essential parameter in disease detection. The nucleus segmentation was performed using the colorectal histology MNIST dataset for nucleus detection in this study. The graph theory, PSO, watershed, and random walker algorithms were used for the segmentation process. In addition, we present the 10-class MedCLNet visual dataset consisting of the NCT-CRC-HE-100 K dataset, LC25000 dataset, and GlaS dataset that can be used in transfer learning studies from deep learning techniques. The study proposes a transfer learning technique using the MedCLNet database. Deep neural networks pre-trained with the proposed transfer learning method were used in the classification with the colorectal histology MNIST dataset in the experimental process. DenseNet201, DenseNet169, InceptionResNetV2, InceptionV3, ResNet152V2, ResNet101V2, and Xception deep learning algorithms were used in transfer learning and the classification studies. The proposed approach was analyzed before and after transfer learning with different methods (DenseNet169 + SVM, DenseNet169 + GRU). In the performance measurement, using the colorectal histology MNIST dataset, 94.29% accuracy was obtained in the DenseNet169 model, which was initiated with random weights in the multi-classification study, and 95.00% accuracy after transfer learning was applied. In comparison with the results obtained from empirical studies, it was demonstrated that the proposed method produced satisfactory outcomes. The application is expected to provide a secondary evaluation for physicians in colon cancer detection and the segmentation. Graphical Abstract: [Figure not available: see fulltext.].
- MakaleYalnız künye2023Detection of forest fire using deep convolutional neural networks with transfer learning approach[Formula presented]
Reis, Hatice Catal; Turk, Veysel
Forest fires caused by natural causes such as climate change, temperature increase, lightning strikes, volcanic activity or human effects are among the world's most dangerous, deadly, and destructive disasters. Detection, prevention, and extinguishing forest fires is challenging. In addition, forest fires can cause habitat destruction that cannot be controlled in time and cause great material and moral losses. Therefore, fast and accurate Detection of forest fires is vital in emergency response. Here, in solving the problem, the transfer learning method from deep learning sub-topics can be used, which allows the application of pre-trained networks to a new problem. The Fire Luminosity Airborne-based Machine learning Evaluation dataset (consisting of forest fire images) obtained by Unmanned Aerial Vehicle was used in this study. In the Detection of forest fire images in the dataset, InceptionV3, DenseNet121, ResNet50V2, NASNetMobile, VGG-19 deep learning algorithms, transfer learning techniques that can produce more successful results than networks trained from scratch, and hybrid proposed with Support Vector Machine, Random Forest, Bidirectional Long Short-Term Memory, Gated Recurrent Unit algorithms methods have been applied. In the classification study with the Fire Luminosity Airborne-based Machine learning Evaluation dataset in performance measurement, 97.95% accuracy was obtained from the DenseNet121 model, which was started with random weights. In the transfer learning study using ImageNet weights, satisfactory results were obtained with 99.32% accuracy in the DenseNet121 model. We anticipate that working in forest fire detection and response can be entirely satisfactory.
- MakaleYayıncıda açık erişim2023MediNet: transfer learning approach with MediNet medical visual database
Reis, Hatice Catal; Turk, Veysel; Khoshelham, Kourosh; Kaya, Serhat
The rapid development of machine learning has increased interest in the use of deep learning methods in medical research. Deep learning in the medical field is used in disease detection and classification problems in the clinical decision-making process. Large amounts of labeled datasets are often required to train deep neural networks; however, in the medical field, the lack of a sufficient number of images in datasets and the difficulties encountered during data collection are among the main problems. In this study, we propose MediNet, a new 10-class visual dataset consisting of Rontgen (X-ray), Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Ultrasound, and Histopathological images such as calcaneal normal, calcaneal tumor, colon benign colon adenocarcinoma, brain normal, brain tumor, breast benign, breast malignant, chest normal, chest pneumonia. AlexNet, VGG19-BN, Inception V3, DenseNet 121, ResNet 101, EfficientNet B0, Nested-LSTM + CNN, and proposed RdiNet deep learning algorithms are used in the transfer learning for pre-training and classification application. Transfer learning aims to apply previously learned knowledge in a new task. Seven algorithms were trained with the MediNet dataset, and the models obtained from these algorithms, namely feature vectors, were recorded. Pre-training models were used for classification studies on chest X-ray images, diabetic retinopathy, and Covid-19 datasets with the transfer learning technique. In performance measurement, an accuracy of 94.84% was obtained in the traditional classification study for the InceptionV3 model in the classification study performed on the Chest X-Ray Images dataset, and the accuracy was increased 98.71% after the transfer learning technique was applied. In the Covid-19 dataset, the classification success of the DenseNet121 model before pre-trained was 88%, while the performance after the transfer application with MediNet was 92%. In the Diabetic retinopathy dataset, the classification success of the Nested-LSTM + CNN model before pre-trained was 79.35%, while the classification success was 81.52% after the transfer application with MediNet. The comparison of results obtained from experimental studies observed that the proposed method produced more successful results. Graphical abstract: [Figure not available: see fulltext.]
- MakaleYalnız künye2022InSiNet: a deep convolutional approach to skin cancer detection and segmentation
Reis, Hatice Catal; Turk, Veysel; Khoshelham, Kourosh; Kaya, Serhat
Cancer is among the common causes of death around the world. Skin cancer is one of the most lethal types of cancer. Early diagnosis and treatment are vital in skin cancer. In addition to traditional methods, method such as deep learning is frequently used to diagnose and classify the disease. Expert experience plays a major role in diagnosing skin cancer. Therefore, for more reliable results in the diagnosis of skin lesions, deep learning algorithms can help in the correct diagnosis. In this study, we propose InSiNet, a deep learning-based convolutional neural network to detect benign and malignant lesions. The performance of the method is tested on International Skin Imaging Collaboration HAM10000 images (ISIC 2018), ISIC 2019, and ISIC 2020, under the same conditions. The computation time and accuracy comparison analysis was performed between the proposed algorithm and other machine learning techniques (GoogleNet, DenseNet-201, ResNet152V2, EfficientNetB0, RBF-support vector machine, logistic regression, and random forest). The results show that the developed InSiNet architecture outperforms the other methods achieving an accuracy of 94.59%, 91.89%, and 90.54% in ISIC 2018, 2019, and 2020 datasets, respectively. Since the deep learning algorithms eliminate the human factor during diagnosis, they can give reliable results in addition to traditional methods. Graphical abstract: [Figure not available: see fulltext.]
- MakaleAçık Erişim2022COVID-DSNet: A novel deep convolutional neural network for detection of coronavirus (SARS-CoV-2) cases from CT and Chest X-Ray images
Reis, Hatice Catal; Turk, Veysel
COVID-19 (SARS-CoV-2), which causes acute respiratory syndrome, is a contagious and deadly disease that has devastating effects on society and human life. COVID-19 can cause serious complications, especially in patients with pre-existing chronic health problems such as diabetes, hypertension, lung cancer, weakened immune systems, and the elderly. The most critical step in the fight against COVID-19 is the rapid diagnosis of infected patients. Computed Tomography (CT), chest X-ray (CXR), and RT-PCR diagnostic kits are frequently used to diagnose the disease. However, due to difficulties such as the inadequacy of RT-PCR test kits and false negative (FN) results in the early stages of the disease, the time-consuming examination of medical images obtained from CT and CXR imaging techniques by specialists/doctors, and the increasing workload on specialists, it is challenging to detect COVID-19. Therefore, researchers have suggested searching for new methods in COVID- 19 detection. In analysis studies with CT and CXR radiography images, it was determined that COVID-19-infected patients experienced abnormalities related to COVID-19. The anomalies observed here are the primary motivation for artificial intelligence researchers to develop COVID-19 detection applications with deep convolutional neural networks. Here, convolutional neural network-based deep learning algorithms from artificial intelligence technologies with high discrimination capabilities can be considered as an alternative approach in the disease detection process. This study proposes a deep convolutional neural network, COVID-DSNet, to diagnose typical pneumonia (bacterial, viral) and COVID-19 diseases from CT, CXR, hybrid CT + CXR images. In the multi-classification study with the CT dataset, 97.60 % accuracy and 97.60 % sensitivity values were obtained from the COVID-DSNet model, and 100 %, 96.30 %, and 96.58 % sensitivity values were obtained in the detection of typical, common pneumonia and COVID-19, respectively. The proposed model is an economical, practical deep learning network that data scientists can benefit from and develop. Although it is not a definitive solution in disease diagnosis, it may help experts as it produces successful results in detecting pneumonia and COVID-19.
- MakaleAçık Erişim2022Automatic prediction of covid-19 from chest-computed tomography (CT) images using deep learning architectures; [Derin öğrenme mimarilerini kullanarak göğüs BT görüntülerinden otomatik Covid-19 tahmini]
Turk, Veysel; Catal Reis, Hatice; Kaya, Serhat
Machine learning has been actively used in disease detection and segmentation in recent years. For the last few years, the world has been coping with the Coronavirus disease 2019 (COVID-19) pandemic. Chest-computerized tomography (CT) is often a meaningful way to detect and detect patients with possible COVID-19. This study aims to classify COVID-19 and non-COVID-19 chest-CT images using deep learning (DL) algorithms and investigate whether we can achieve successful results in different parameters using four architectures. The study was performed on proved positive COVID-19 CT images, and the datasets were obtained from the GitHub public platform. The study evaluated four different deep learning architectures of VGG16, VGG19, LeNet-5, and MobileNet. The performance evaluations were used with ROC curve, recall, accuracy, F1-score, precision, and Root Mean Square Error (RMSE). MobileNet model showed the best result ; F1 score of 95%, the accuracy of 95%, the precision of 100%, recall of 90%, AUC of 95%, and RMSE of 0.23. On the other hand, VGG 19 model gave the lowest performance; F1 score of 90%, the accuracy of 89%, the precision of 90%, recall of 90%, AUC of 89%, and RMSE of 0.32. When the algorithms' performances were compared, the highest accuracy was obtained from MobileNet, LeNet-5, VGG16, and VGG19, respectively. This study has proven the usefulness of deep learning models to detect COVID-19 in chest-CT images based on the proposed model framework. Therefore, it can contribute to the literature in Medical and Engineering in COVID-19 detection research.