PeerJ Computer Science:Bioinformaticshttps://peerj.com/articles/index.atom?journal=cs&subject=540Bioinformatics articles published in PeerJ Computer SciencePerformance discrepancy mitigation in heart disease prediction for multisensory inter-datasetshttps://peerj.com/articles/cs-19172024-03-182024-03-18Mahmudul HasanMd Abdus SahidMd Palash UddinMd Abu MarjanSeifedine KadryJungeun Kim
Heart disease is one of the primary causes of morbidity and death worldwide. Millions of people have had heart attacks every year, and only early-stage predictions can help to reduce the number. Researchers are working on designing and developing early-stage prediction systems using different advanced technologies, and machine learning (ML) is one of them. Almost all existing ML-based works consider the same dataset (intra-dataset) for the training and validation of their method. In particular, they do not consider inter-dataset performance checks, where different datasets are used in the training and testing phases. In inter-dataset setup, existing ML models show a poor performance named the inter-dataset discrepancy problem. This work focuses on mitigating the inter-dataset discrepancy problem by considering five available heart disease datasets and their combined form. All potential training and testing mode combinations are systematically executed to assess discrepancies before and after applying the proposed methods. Imbalance data handling using SMOTE-Tomek, feature selection using random forest (RF), and feature extraction using principle component analysis (PCA) with a long preprocessing pipeline are used to mitigate the inter-dataset discrepancy problem. The preprocessing pipeline builds on missing value handling using RF regression, log transformation, outlier removal, normalization, and data balancing that convert the datasets to more ML-centric. Support vector machine, K-nearest neighbors, decision tree, RF, eXtreme Gradient Boosting, Gaussian naive Bayes, logistic regression, and multilayer perceptron are used as classifiers. Experimental results show that feature selection and classification using RF produce better results than other combination strategies in both single- and inter-dataset setups. In certain configurations of individual datasets, RF demonstrates 100% accuracy and 96% accuracy during the feature selection phase in an inter-dataset setup, exhibiting commendable precision, recall, F1 score, specificity, and AUC score. The results indicate that an effective preprocessing technique has the potential to improve the performance of the ML model without necessitating the development of intricate prediction models. Addressing inter-dataset discrepancies introduces a novel research avenue, enabling the amalgamation of identical features from various datasets to construct a comprehensive global dataset within a specific domain.
Heart disease is one of the primary causes of morbidity and death worldwide. Millions of people have had heart attacks every year, and only early-stage predictions can help to reduce the number. Researchers are working on designing and developing early-stage prediction systems using different advanced technologies, and machine learning (ML) is one of them. Almost all existing ML-based works consider the same dataset (intra-dataset) for the training and validation of their method. In particular, they do not consider inter-dataset performance checks, where different datasets are used in the training and testing phases. In inter-dataset setup, existing ML models show a poor performance named the inter-dataset discrepancy problem. This work focuses on mitigating the inter-dataset discrepancy problem by considering five available heart disease datasets and their combined form. All potential training and testing mode combinations are systematically executed to assess discrepancies before and after applying the proposed methods. Imbalance data handling using SMOTE-Tomek, feature selection using random forest (RF), and feature extraction using principle component analysis (PCA) with a long preprocessing pipeline are used to mitigate the inter-dataset discrepancy problem. The preprocessing pipeline builds on missing value handling using RF regression, log transformation, outlier removal, normalization, and data balancing that convert the datasets to more ML-centric. Support vector machine, K-nearest neighbors, decision tree, RF, eXtreme Gradient Boosting, Gaussian naive Bayes, logistic regression, and multilayer perceptron are used as classifiers. Experimental results show that feature selection and classification using RF produce better results than other combination strategies in both single- and inter-dataset setups. In certain configurations of individual datasets, RF demonstrates 100% accuracy and 96% accuracy during the feature selection phase in an inter-dataset setup, exhibiting commendable precision, recall, F1 score, specificity, and AUC score. The results indicate that an effective preprocessing technique has the potential to improve the performance of the ML model without necessitating the development of intricate prediction models. Addressing inter-dataset discrepancies introduces a novel research avenue, enabling the amalgamation of identical features from various datasets to construct a comprehensive global dataset within a specific domain.Sensor-based systems for the measurement of Functional Reach Test results: a systematic reviewhttps://peerj.com/articles/cs-18232024-03-152024-03-15Luís FranciscoJoão DuarteAntónio Nunes GodinhoEftim ZdravevskiCarlos AlbuquerqueIvan Miguel PiresPaulo Jorge Coelho
The measurement of Functional Reach Test (FRT) is a widely used assessment tool in various fields, including physical therapy, rehabilitation, and geriatrics. This test evaluates a person’s balance, mobility, and functional ability to reach forward while maintaining stability. Recently, there has been a growing interest in utilizing sensor-based systems to objectively and accurately measure FRT results. This systematic review was performed in various scientific databases or publishers, including PubMed Central, IEEE Explore, Elsevier, Springer, the Multidisciplinary Digital Publishing Institute (MDPI), and the Association for Computing Machinery (ACM), and considered studies published between January 2017 and October 2022, related to methods for the automation of the measurement of the Functional Reach Test variables and results with sensors. Camera-based devices and motion-based sensors are used for Functional Reach Tests, with statistical models extracting meaningful information. Sensor-based systems offer several advantages over traditional manual measurement techniques, as they can provide objective and precise measurements of the reach distance, quantify postural sway, and capture additional parameters related to the movement.
The measurement of Functional Reach Test (FRT) is a widely used assessment tool in various fields, including physical therapy, rehabilitation, and geriatrics. This test evaluates a person’s balance, mobility, and functional ability to reach forward while maintaining stability. Recently, there has been a growing interest in utilizing sensor-based systems to objectively and accurately measure FRT results. This systematic review was performed in various scientific databases or publishers, including PubMed Central, IEEE Explore, Elsevier, Springer, the Multidisciplinary Digital Publishing Institute (MDPI), and the Association for Computing Machinery (ACM), and considered studies published between January 2017 and October 2022, related to methods for the automation of the measurement of the Functional Reach Test variables and results with sensors. Camera-based devices and motion-based sensors are used for Functional Reach Tests, with statistical models extracting meaningful information. Sensor-based systems offer several advantages over traditional manual measurement techniques, as they can provide objective and precise measurements of the reach distance, quantify postural sway, and capture additional parameters related to the movement.SUTrans-NET: a hybrid transformer approach to skin lesion segmentationhttps://peerj.com/articles/cs-19352024-03-132024-03-13Yaqin LiTonghe TianJing HuCao Yuan
Melanoma is a malignant skin tumor that threatens human life and health. Early detection is essential for effective treatment. However, the low contrast between melanoma lesions and normal skin and the irregularity in size and shape make skin lesions difficult to detect with the naked eye in the early stages, making the task of skin lesion segmentation challenging. Traditional encoder-decoder built with U-shaped networks using convolutional neural network (CNN) networks have limitations in establishing long-term dependencies and global contextual connections, while the Transformer architecture is limited in its application to small medical datasets. To address these issues, we propose a new skin lesion segmentation network, SUTrans-NET, which combines CNN and Transformer in a parallel fashion to form a dual encoder, where both CNN and Transformer branches perform dynamic interactive fusion of image information in each layer. At the same time, we introduce our designed multi-grouping module SpatialGroupAttention (SGA) to complement the spatial and texture information of the Transformer branch, and utilize the Focus idea of YOLOV5 to construct the Patch Embedding module in the Transformer to prevent the loss of pixel accuracy. In addition, we design a decoder with full-scale information fusion capability to fully fuse shallow and deep features at different stages of the encoder. The effectiveness of our method is demonstrated on the ISIC 2016, ISIC 2017, ISIC 2018 and PH2 datasets and its advantages over existing methods are verified.
Melanoma is a malignant skin tumor that threatens human life and health. Early detection is essential for effective treatment. However, the low contrast between melanoma lesions and normal skin and the irregularity in size and shape make skin lesions difficult to detect with the naked eye in the early stages, making the task of skin lesion segmentation challenging. Traditional encoder-decoder built with U-shaped networks using convolutional neural network (CNN) networks have limitations in establishing long-term dependencies and global contextual connections, while the Transformer architecture is limited in its application to small medical datasets. To address these issues, we propose a new skin lesion segmentation network, SUTrans-NET, which combines CNN and Transformer in a parallel fashion to form a dual encoder, where both CNN and Transformer branches perform dynamic interactive fusion of image information in each layer. At the same time, we introduce our designed multi-grouping module SpatialGroupAttention (SGA) to complement the spatial and texture information of the Transformer branch, and utilize the Focus idea of YOLOV5 to construct the Patch Embedding module in the Transformer to prevent the loss of pixel accuracy. In addition, we design a decoder with full-scale information fusion capability to fully fuse shallow and deep features at different stages of the encoder. The effectiveness of our method is demonstrated on the ISIC 2016, ISIC 2017, ISIC 2018 and PH2 datasets and its advantages over existing methods are verified.Efficient-gastro: optimized EfficientNet model for the detection of gastrointestinal disorders using transfer learning and wireless capsule endoscopy imageshttps://peerj.com/articles/cs-19022024-03-112024-03-11Shaha Al-OtaibiAmjad RehmanMuhammad MujahidSarah AlotaibiTanzila Saba
Gastrointestinal diseases cause around two million deaths globally. Wireless capsule endoscopy is a recent advancement in medical imaging, but manual diagnosis is challenging due to the large number of images generated. This has led to research into computer-assisted methodologies for diagnosing these images. Endoscopy produces thousands of frames for each patient, making manual examination difficult, laborious, and error-prone. An automated approach is essential to speed up the diagnosis process, reduce costs, and potentially save lives. This study proposes transfer learning-based efficient deep learning methods for detecting gastrointestinal disorders from multiple modalities, aiming to detect gastrointestinal diseases with superior accuracy and reduce the efforts and costs of medical experts. The Kvasir eight-class dataset was used for the experiment, where endoscopic images were preprocessed and enriched with augmentation techniques. An EfficientNet model was optimized via transfer learning and fine tuning, and the model was compared to the most widely used pre-trained deep learning models. The model’s efficacy was tested on another independent endoscopic dataset to prove its robustness and reliability.
Gastrointestinal diseases cause around two million deaths globally. Wireless capsule endoscopy is a recent advancement in medical imaging, but manual diagnosis is challenging due to the large number of images generated. This has led to research into computer-assisted methodologies for diagnosing these images. Endoscopy produces thousands of frames for each patient, making manual examination difficult, laborious, and error-prone. An automated approach is essential to speed up the diagnosis process, reduce costs, and potentially save lives. This study proposes transfer learning-based efficient deep learning methods for detecting gastrointestinal disorders from multiple modalities, aiming to detect gastrointestinal diseases with superior accuracy and reduce the efforts and costs of medical experts. The Kvasir eight-class dataset was used for the experiment, where endoscopic images were preprocessed and enriched with augmentation techniques. An EfficientNet model was optimized via transfer learning and fine tuning, and the model was compared to the most widely used pre-trained deep learning models. The model’s efficacy was tested on another independent endoscopic dataset to prove its robustness and reliability.Electroencephalography (EEG) based epilepsy diagnosis via multiple feature space fusion using shared hidden space-driven multi-view learninghttps://peerj.com/articles/cs-18742024-03-072024-03-07Xiujian HuYicheng XieHui ZhaoGuanglei ShengKhin Wee LaiYuanpeng Zhang
Epilepsy is a chronic, non-communicable disease caused by paroxysmal abnormal synchronized electrical activity of brain neurons, and is one of the most common neurological diseases worldwide. Electroencephalography (EEG) is currently a crucial tool for epilepsy diagnosis. With the development of artificial intelligence, multi-view learning-based EEG analysis has become an important method for automatic epilepsy recognition because EEG contains difficult types of features such as time-frequency features, frequency-domain features and time-domain features. However, current multi-view learning still faces some challenges, such as the difference between samples of the same class from different views is greater than the difference between samples of different classes from the same view. In view of this, in this study, we propose a shared hidden space-driven multi-view learning algorithm. The algorithm uses kernel density estimation to construct a shared hidden space and combines the shared hidden space with the original space to obtain an expanded space for multi-view learning. By constructing the expanded space and utilizing the information of both the shared hidden space and the original space for learning, the relevant information of samples within and across views can thereby be fully utilized. Experimental results on a dataset of epilepsy provided by the University of Bonn show that the proposed algorithm has promising performance, with an average classification accuracy value of 0.9787, which achieves at least 4% improvement compared to single-view methods.
Epilepsy is a chronic, non-communicable disease caused by paroxysmal abnormal synchronized electrical activity of brain neurons, and is one of the most common neurological diseases worldwide. Electroencephalography (EEG) is currently a crucial tool for epilepsy diagnosis. With the development of artificial intelligence, multi-view learning-based EEG analysis has become an important method for automatic epilepsy recognition because EEG contains difficult types of features such as time-frequency features, frequency-domain features and time-domain features. However, current multi-view learning still faces some challenges, such as the difference between samples of the same class from different views is greater than the difference between samples of different classes from the same view. In view of this, in this study, we propose a shared hidden space-driven multi-view learning algorithm. The algorithm uses kernel density estimation to construct a shared hidden space and combines the shared hidden space with the original space to obtain an expanded space for multi-view learning. By constructing the expanded space and utilizing the information of both the shared hidden space and the original space for learning, the relevant information of samples within and across views can thereby be fully utilized. Experimental results on a dataset of epilepsy provided by the University of Bonn show that the proposed algorithm has promising performance, with an average classification accuracy value of 0.9787, which achieves at least 4% improvement compared to single-view methods.Proj2Proj: self-supervised low-dose CT reconstructionhttps://peerj.com/articles/cs-18492024-02-292024-02-29Mehmet Ozan UnalMetin ErtasIsa Yildirim
In Computed Tomography (CT) imaging, one of the most serious concerns has always been ionizing radiation. Several approaches have been proposed to reduce the dose level without compromising the image quality. With the emergence of deep learning, thanks to the increasing availability of computational power and huge datasets, data-driven methods have recently received a lot of attention. Deep learning based methods have also been applied in various ways to address the low-dose CT reconstruction problem. However, the success of these methods largely depends on the availability of labeled data. On the other hand, recent studies showed that training can be done successfully without the need for labeled datasets. In this study, a training scheme was defined to use low-dose projections as their own training targets. The self-supervision principle was applied in the projection domain. The parameters of a denoiser neural network were optimized through self-supervised training. It was shown that our method outperformed both traditional and compressed sensing-based iterative methods, and deep learning based unsupervised methods, in the reconstruction of analytic CT phantoms and human CT images in low-dose CT imaging. Our method’s reconstruction quality is also comparable to a well-known supervised method.
In Computed Tomography (CT) imaging, one of the most serious concerns has always been ionizing radiation. Several approaches have been proposed to reduce the dose level without compromising the image quality. With the emergence of deep learning, thanks to the increasing availability of computational power and huge datasets, data-driven methods have recently received a lot of attention. Deep learning based methods have also been applied in various ways to address the low-dose CT reconstruction problem. However, the success of these methods largely depends on the availability of labeled data. On the other hand, recent studies showed that training can be done successfully without the need for labeled datasets. In this study, a training scheme was defined to use low-dose projections as their own training targets. The self-supervision principle was applied in the projection domain. The parameters of a denoiser neural network were optimized through self-supervised training. It was shown that our method outperformed both traditional and compressed sensing-based iterative methods, and deep learning based unsupervised methods, in the reconstruction of analytic CT phantoms and human CT images in low-dose CT imaging. Our method’s reconstruction quality is also comparable to a well-known supervised method.A SE-DenseNet-LSTM model for locomotion mode recognition in lower limb exoskeletonhttps://peerj.com/articles/cs-18812024-02-292024-02-29Jing TangLun ZhaoMinghu WuZequan JiangJiaxun CaoXiang Bao
Locomotion mode recognition in humans is fundamental for flexible control in wearable-powered exoskeleton robots. This article proposes a hybrid model that combines a dense convolutional network (DenseNet) and long short-term memory (LSTM) with a channel attention mechanism (SENet) for locomotion mode recognition. DenseNet can automatically extract deep-level features from data, while LSTM effectively captures long-dependent information in time series. To evaluate the validity of the hybrid model, inertial measurement units (IMUs) and pressure sensors were used to obtain motion data from 15 subjects. Five locomotion modes were tested for the hybrid model, such as level ground walking, stair ascending, stair descending, ramp ascending, and ramp descending. Furthermore, the data features of the ramp were inconspicuous, leading to large recognition errors. To address this challenge, the SENet module was incorporated, which improved recognition rates to some extent. The proposed model automatically extracted the features and achieved an average recognition rate of 97.93%. Compared with known algorithms, the proposed model has substantial recognition results and robustness. This work holds promising potential for applications such as limb support and weight bearing.
Locomotion mode recognition in humans is fundamental for flexible control in wearable-powered exoskeleton robots. This article proposes a hybrid model that combines a dense convolutional network (DenseNet) and long short-term memory (LSTM) with a channel attention mechanism (SENet) for locomotion mode recognition. DenseNet can automatically extract deep-level features from data, while LSTM effectively captures long-dependent information in time series. To evaluate the validity of the hybrid model, inertial measurement units (IMUs) and pressure sensors were used to obtain motion data from 15 subjects. Five locomotion modes were tested for the hybrid model, such as level ground walking, stair ascending, stair descending, ramp ascending, and ramp descending. Furthermore, the data features of the ramp were inconspicuous, leading to large recognition errors. To address this challenge, the SENet module was incorporated, which improved recognition rates to some extent. The proposed model automatically extracted the features and achieved an average recognition rate of 97.93%. Compared with known algorithms, the proposed model has substantial recognition results and robustness. This work holds promising potential for applications such as limb support and weight bearing.Integrating hybrid transfer learning with attention-enhanced deep learning models to improve breast cancer diagnosishttps://peerj.com/articles/cs-18502024-02-282024-02-28Sudha Prathyusha JakkaladikiFilip Maly
Cancer, with its high fatality rate, instills fear in countless individuals worldwide. However, effective diagnosis and treatment can often lead to a successful cure. Computer-assisted diagnostics, especially in the context of deep learning, have become prominent methods for primary screening of various diseases, including cancer. Deep learning, an artificial intelligence technique that enables computers to reason like humans, has recently gained significant attention. This study focuses on training a deep neural network to predict breast cancer. With the advancements in medical imaging technologies such as X-ray, magnetic resonance imaging (MRI), and computed tomography (CT) scans, deep learning has become essential in analyzing and managing extensive image datasets. The objective of this research is to propose a deep-learning model for the identification and categorization of breast tumors. The system’s performance was evaluated using the breast cancer identification (BreakHis) classification datasets from the Kaggle repository and the Wisconsin Breast Cancer Dataset (WBC) from the UCI repository. The study’s findings demonstrated an impressive accuracy rate of 100%, surpassing other state-of-the-art approaches. The suggested model was thoroughly evaluated using F1-score, recall, precision, and accuracy metrics on the WBC dataset. Training, validation, and testing were conducted using pre-processed datasets, leading to remarkable results of 99.8% recall rate, 99.06% F1-score, and 100% accuracy rate on the BreakHis dataset. Similarly, on the WBC dataset, the model achieved a 99% accuracy rate, a 98.7% recall rate, and a 99.03% F1-score. These outcomes highlight the potential of deep learning models in accurately diagnosing breast cancer. Based on our research, it is evident that the proposed system outperforms existing approaches in this field.
Cancer, with its high fatality rate, instills fear in countless individuals worldwide. However, effective diagnosis and treatment can often lead to a successful cure. Computer-assisted diagnostics, especially in the context of deep learning, have become prominent methods for primary screening of various diseases, including cancer. Deep learning, an artificial intelligence technique that enables computers to reason like humans, has recently gained significant attention. This study focuses on training a deep neural network to predict breast cancer. With the advancements in medical imaging technologies such as X-ray, magnetic resonance imaging (MRI), and computed tomography (CT) scans, deep learning has become essential in analyzing and managing extensive image datasets. The objective of this research is to propose a deep-learning model for the identification and categorization of breast tumors. The system’s performance was evaluated using the breast cancer identification (BreakHis) classification datasets from the Kaggle repository and the Wisconsin Breast Cancer Dataset (WBC) from the UCI repository. The study’s findings demonstrated an impressive accuracy rate of 100%, surpassing other state-of-the-art approaches. The suggested model was thoroughly evaluated using F1-score, recall, precision, and accuracy metrics on the WBC dataset. Training, validation, and testing were conducted using pre-processed datasets, leading to remarkable results of 99.8% recall rate, 99.06% F1-score, and 100% accuracy rate on the BreakHis dataset. Similarly, on the WBC dataset, the model achieved a 99% accuracy rate, a 98.7% recall rate, and a 99.03% F1-score. These outcomes highlight the potential of deep learning models in accurately diagnosing breast cancer. Based on our research, it is evident that the proposed system outperforms existing approaches in this field.An efficient combined intelligent system for segmentation and classification of lung cancer computed tomography imageshttps://peerj.com/articles/cs-18022024-02-272024-02-27Maheswari SivakumarSundar ChinnasamyThanabal MS
Background and Objective
One of the illnesses with most significant mortality and morbidity rates worldwide is lung cancer. From CT images, automatic lung tumor segmentation is significantly essential. However, segmentation has several difficulties, such as different sizes, variable shapes, and complex surrounding tissues. Therefore, a novel enhanced combined intelligent system is presented to predict lung cancer in this research.
Methods
Non-small cell lung cancer should be recognized for detecting lung cancer. In the pre-processing stage, the noise in the CT images is eliminated by using an average filter and adaptive median filter, and histogram equalization is used to enhance the filtered images to enhance the lung image quality in the proposed model. The adapted deep belief network (ADBN) is used to segment the affected region with the help of network layers from the noise-removed lung CT image. Two cascaded RBMs are used for the segmentation process in the structure of ADBN, including Bernoulli–Bernoulli (BB) and Gaussian-Bernoulli (GB), and then relevant significant features are extracted. The hybrid spiral optimization intelligent-generalized rough set (SOI-GRS) approach is used to select compelling features of the CT image. Then, an optimized light gradient boosting machine (LightGBM) model using the Ensemble Harris hawk optimization (EHHO) algorithm is used for lung cancer classification.
Results
LUNA 16, the Kaggle Data Science Bowl (KDSB), the Cancer Imaging Archive (CIA), and local datasets are used to train and test the proposed approach. Python and several well-known modules, including TensorFlow and Scikit-Learn, are used for the extensive experiment analysis. The proposed research accurately spot people with lung cancer according to the results. The method produced the least classification error possible while maintaining 99.87% accuracy.
Conclusion
The integrated intelligent system (ADBN-Optimized LightGBM) gives the best results among all input prediction models, taking performance criteria into account and boosting the system’s effectiveness, hence enabling better lung cancer patient diagnosis by physicians and radiologists.
Background and Objective
One of the illnesses with most significant mortality and morbidity rates worldwide is lung cancer. From CT images, automatic lung tumor segmentation is significantly essential. However, segmentation has several difficulties, such as different sizes, variable shapes, and complex surrounding tissues. Therefore, a novel enhanced combined intelligent system is presented to predict lung cancer in this research.
Methods
Non-small cell lung cancer should be recognized for detecting lung cancer. In the pre-processing stage, the noise in the CT images is eliminated by using an average filter and adaptive median filter, and histogram equalization is used to enhance the filtered images to enhance the lung image quality in the proposed model. The adapted deep belief network (ADBN) is used to segment the affected region with the help of network layers from the noise-removed lung CT image. Two cascaded RBMs are used for the segmentation process in the structure of ADBN, including Bernoulli–Bernoulli (BB) and Gaussian-Bernoulli (GB), and then relevant significant features are extracted. The hybrid spiral optimization intelligent-generalized rough set (SOI-GRS) approach is used to select compelling features of the CT image. Then, an optimized light gradient boosting machine (LightGBM) model using the Ensemble Harris hawk optimization (EHHO) algorithm is used for lung cancer classification.
Results
LUNA 16, the Kaggle Data Science Bowl (KDSB), the Cancer Imaging Archive (CIA), and local datasets are used to train and test the proposed approach. Python and several well-known modules, including TensorFlow and Scikit-Learn, are used for the extensive experiment analysis. The proposed research accurately spot people with lung cancer according to the results. The method produced the least classification error possible while maintaining 99.87% accuracy.
Conclusion
The integrated intelligent system (ADBN-Optimized LightGBM) gives the best results among all input prediction models, taking performance criteria into account and boosting the system’s effectiveness, hence enabling better lung cancer patient diagnosis by physicians and radiologists.An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet modelhttps://peerj.com/articles/cs-18842024-02-262024-02-26Anubhav DeNilamadhab MishraHsien-Tsung Chang
This research addresses the challenge of automating skin disease diagnosis using dermatoscopic images. The primary issue lies in accurately classifying pigmented skin lesions, which traditionally rely on manual assessment by dermatologists and are prone to subjectivity and time consumption. By integrating a hybrid CNN-DenseNet model, this study aimed to overcome the complexities of differentiating various skin diseases and automating the diagnostic process effectively. Our methodology involved rigorous data preprocessing, exploratory data analysis, normalization, and label encoding. Techniques such as model hybridization, batch normalization and data fitting were employed to optimize the model architecture and data fitting. Initial iterations of our convolutional neural network (CNN) model achieved an accuracy of 76.22% on the test data and 75.69% on the validation data. Recognizing the need for improvement, the model was hybridized with DenseNet architecture and ResNet architecture was implemented for feature extraction and then further trained on the HAM10000 and PAD-UFES-20 datasets. Overall, our efforts resulted in a hybrid model that demonstrated an impressive accuracy of 95.7% on the HAM10000 dataset and 91.07% on the PAD-UFES-20 dataset. In comparison to recently published works, our model stands out because of its potential to effectively diagnose skin diseases such as melanocytic nevi, melanoma, benign keratosis-like lesions, basal cell carcinoma, actinic keratoses, vascular lesions, and dermatofibroma, all of which rival the diagnostic accuracy of real-world clinical specialists but also offer customization potential for more nuanced clinical uses.
This research addresses the challenge of automating skin disease diagnosis using dermatoscopic images. The primary issue lies in accurately classifying pigmented skin lesions, which traditionally rely on manual assessment by dermatologists and are prone to subjectivity and time consumption. By integrating a hybrid CNN-DenseNet model, this study aimed to overcome the complexities of differentiating various skin diseases and automating the diagnostic process effectively. Our methodology involved rigorous data preprocessing, exploratory data analysis, normalization, and label encoding. Techniques such as model hybridization, batch normalization and data fitting were employed to optimize the model architecture and data fitting. Initial iterations of our convolutional neural network (CNN) model achieved an accuracy of 76.22% on the test data and 75.69% on the validation data. Recognizing the need for improvement, the model was hybridized with DenseNet architecture and ResNet architecture was implemented for feature extraction and then further trained on the HAM10000 and PAD-UFES-20 datasets. Overall, our efforts resulted in a hybrid model that demonstrated an impressive accuracy of 95.7% on the HAM10000 dataset and 91.07% on the PAD-UFES-20 dataset. In comparison to recently published works, our model stands out because of its potential to effectively diagnose skin diseases such as melanocytic nevi, melanoma, benign keratosis-like lesions, basal cell carcinoma, actinic keratoses, vascular lesions, and dermatofibroma, all of which rival the diagnostic accuracy of real-world clinical specialists but also offer customization potential for more nuanced clinical uses.