V. S. Bakkialakshmi, V. Arulalan, Gowdham Chinnaraju, Hritwik Ghosh, Irfan Sadiq Rahat, Ankit Saha
INTRODUCTION: Parkinson's Disease (PD) is a progressive neurological disorder affecting a significant portion of the global population, leading to profound impacts on daily life and imposing substantial burdens on healthcare systems. Early identification and precise classification are crucial for effectively managing this disease. This research investigates the potential of deep learning techniques in facilitating early recognition and accurate classification of PD. OBJECTIVES: The primary objective of this study is to leverage advanced deep learning techniques for the early detection and precise classification of Parkinson's Disease. By utilizing a rich dataset comprising speech signal features extracted from 3000 PD patients, including Time Frequency Features, Mel Frequency Cepstral Coefficients (MFCCs), Wavelet Transform based Features, Vocal Fold Features, and TWQT features, this research aims to evaluate the performance of various deep learning models in PD classification. METHODS: The dataset containing diverse speech signal features from PD patients' recordings serves as the foundation for training and evaluating five different deep learning models: ResNet50, VGG16, Inception v2, AlexNet, and VGG19. Each model undergoes training and assessment to determine its capability in accurately classifying PD patients. Performance metrics such as accuracy are employed to evaluate the models' effectiveness. RESULTS: The results demonstrate promising potential, with overall accuracies ranging from 89% to 95% across the different deep learning models. Notably, AlexNet emerges as the top-performing model, achieving an accuracy of 95% and demonstrating balanced performance in accurately identifying both true and false PD cases. CONCLUSION: This research highlights the significant potential of deep learning in facilitating the early detection and classification of Parkinson's Disease. Leveraging speech signal features offers a non-invasive and cost-effective approach to PD assessment. The findings contribute to the growing body of evidence supporting the integration of artificial intelligence in healthcare, particularly in the realm of neurodegenerative disorders. Further exploration into the application of deep learning in this domain holds promise for advancing PD diagnosis and management.
{"title":"Exploring the Potential of Deep Learning in the Classification and Early Detection of Parkinson's Disease","authors":"V. S. Bakkialakshmi, V. Arulalan, Gowdham Chinnaraju, Hritwik Ghosh, Irfan Sadiq Rahat, Ankit Saha","doi":"10.4108/eetpht.10.5568","DOIUrl":"https://doi.org/10.4108/eetpht.10.5568","url":null,"abstract":"INTRODUCTION: Parkinson's Disease (PD) is a progressive neurological disorder affecting a significant portion of the global population, leading to profound impacts on daily life and imposing substantial burdens on healthcare systems. Early identification and precise classification are crucial for effectively managing this disease. This research investigates the potential of deep learning techniques in facilitating early recognition and accurate classification of PD. \u0000OBJECTIVES: The primary objective of this study is to leverage advanced deep learning techniques for the early detection and precise classification of Parkinson's Disease. By utilizing a rich dataset comprising speech signal features extracted from 3000 PD patients, including Time Frequency Features, Mel Frequency Cepstral Coefficients (MFCCs), Wavelet Transform based Features, Vocal Fold Features, and TWQT features, this research aims to evaluate the performance of various deep learning models in PD classification. \u0000METHODS: The dataset containing diverse speech signal features from PD patients' recordings serves as the foundation for training and evaluating five different deep learning models: ResNet50, VGG16, Inception v2, AlexNet, and VGG19. Each model undergoes training and assessment to determine its capability in accurately classifying PD patients. Performance metrics such as accuracy are employed to evaluate the models' effectiveness. \u0000RESULTS: The results demonstrate promising potential, with overall accuracies ranging from 89% to 95% across the different deep learning models. Notably, AlexNet emerges as the top-performing model, achieving an accuracy of 95% and demonstrating balanced performance in accurately identifying both true and false PD cases. \u0000CONCLUSION: This research highlights the significant potential of deep learning in facilitating the early detection and classification of Parkinson's Disease. Leveraging speech signal features offers a non-invasive and cost-effective approach to PD assessment. The findings contribute to the growing body of evidence supporting the integration of artificial intelligence in healthcare, particularly in the realm of neurodegenerative disorders. Further exploration into the application of deep learning in this domain holds promise for advancing PD diagnosis and management.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"18 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140374977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Khushi Gupta, Shrey Aggarwal, Avinash Jha, Aamir Habib, Jayant Jagtap, Shrikrishna Kolhar, S. Patil, K. Kotecha, Tanupriya Choudhury
INTRODUCTION: Segregating hepatic tumors from the liver in computed tomography (CT) scans is vital in hepatic surgery planning. Extracting liver tumors in CT images is complex due to the low contrast between the malignant and healthy tissues and the hazy boundaries in CT images. Moreover, manually detecting hepatic tumors from CT images is complicated, time-consuming, and needs clinical expertise. OBJECTIVES: An automated liver and hepatic malignancies segmentation is essential to improve surgery planning, therapy, and follow-up evaluation. Therefore, this study demonstrates the creation of an intuitive approach for segmenting tumors from the liver in CT scans. METHODS: The proposed framework uses residual UNet (ResUNet) architecture and local region-based segmentation. The algorithm begins by segmenting the liver, followed by malignancies within the liver envelope. First, ResUNet trained on labeled CT images predicts the coarse liver pixels. Further, the region-level segmentation helps determine the tumor and improves the overall segmentation map. The model is tested on a public 3D-IRCADb dataset. RESULTS: Two metrics, namely dice coefficient and volumetric overlap error (VOE), were used to evaluate the performance of the proposed method. ResUNet model achieved dice of 0.97 and 0.96 in segmenting liver and tumor, respectively. The value of VOE is also reduced to 1.90 and 0.615 for liver and tumor segmentation. CONCLUSION: The proposed ResUNet model performs better than existing methods in the literature. Since the proposed model is built using U-Net, the model ensures quality and precise dimensions of the output.
{"title":"Deep Learning Framework for Liver Tumor Segmentation","authors":"Khushi Gupta, Shrey Aggarwal, Avinash Jha, Aamir Habib, Jayant Jagtap, Shrikrishna Kolhar, S. Patil, K. Kotecha, Tanupriya Choudhury","doi":"10.4108/eetpht.10.5561","DOIUrl":"https://doi.org/10.4108/eetpht.10.5561","url":null,"abstract":"INTRODUCTION: Segregating hepatic tumors from the liver in computed tomography (CT) scans is vital in hepatic surgery planning. Extracting liver tumors in CT images is complex due to the low contrast between the malignant and healthy tissues and the hazy boundaries in CT images. Moreover, manually detecting hepatic tumors from CT images is complicated, time-consuming, and needs clinical expertise. \u0000OBJECTIVES: An automated liver and hepatic malignancies segmentation is essential to improve surgery planning, therapy, and follow-up evaluation. Therefore, this study demonstrates the creation of an intuitive approach for segmenting tumors from the liver in CT scans. \u0000METHODS: The proposed framework uses residual UNet (ResUNet) architecture and local region-based segmentation. The algorithm begins by segmenting the liver, followed by malignancies within the liver envelope. First, ResUNet trained on labeled CT images predicts the coarse liver pixels. Further, the region-level segmentation helps determine the tumor and improves the overall segmentation map. The model is tested on a public 3D-IRCADb dataset. \u0000RESULTS: Two metrics, namely dice coefficient and volumetric overlap error (VOE), were used to evaluate the performance of the proposed method. ResUNet model achieved dice of 0.97 and 0.96 in segmenting liver and tumor, respectively. The value of VOE is also reduced to 1.90 and 0.615 for liver and tumor segmentation. \u0000CONCLUSION: The proposed ResUNet model performs better than existing methods in the literature. Since the proposed model is built using U-Net, the model ensures quality and precise dimensions of the output.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"59 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140376509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
L. Chandra, Sekhar Reddy, Muniyandy Elangovan, M. Vamsikrishna, Ch Ravindra
INTRODUCTION: The primary goal of artificial intelligence (AI) is to develop computers that exhibit human-like behavior and functionality. Computer-based activities employing artificial intelligence encompass a variety of extra features beyond only pattern detection, planning, and problem resolution. METHODOLOGY: Machines use a set of techniques collectively called "deep learning." Magnetic resonance imaging (MRI) is employed with the use of deep learning methods to develop models that can effectively identify and classify brain cancers. This technique facilitates the rapid and straightforward detection of brain cancers. Brain problems mainly arise from the abnormal multiplication of brain cells, leading to detrimental alterations in brain structure and finally culminating in the development of cancer in the brain, malignant. Early detection of brain tumors along with following effective intervention can reduce mortality rates. This paper proposes convolutional neural network (CNN) architecture to effectively detect brain cancers using magnetic resonance (MR) images. RESULTS: This research further examines several models, including ResNet-50, VGG16, and Inception V3, and compares the proposed architecture and these models. For the efficacy of the models, many measures were evaluated, including accuracy, recall, loss, and area under the curve (AUC). After analyzing several models and comparing them with the suggested model using the specified metrics, it was determined that the proposed model exhibited superior performance compared to the alternative models. Based on an analysis conducted on data from 3265 MR images. CONCLUSION: It was seen that the CNN model exhibited a classification precision of 93.3%. Additionally, the area under the receiver operating characteristic curve (AUC) was determined to be 98.43%, while the recall rate was 91.19%. Furthermore, the model's loss function yielded a value of 0.25. Based on a comparative analysis with other models, it can be inferred that the suggested model is highly reliable in detecting various types of brain cancers at an early stage.
{"title":"Brain Tumor Detection and Classification Using Deep Learning Models on MRI Scans","authors":"L. Chandra, Sekhar Reddy, Muniyandy Elangovan, M. Vamsikrishna, Ch Ravindra","doi":"10.4108/eetpht.10.5553","DOIUrl":"https://doi.org/10.4108/eetpht.10.5553","url":null,"abstract":"INTRODUCTION: The primary goal of artificial intelligence (AI) is to develop computers that exhibit human-like behavior and functionality. Computer-based activities employing artificial intelligence encompass a variety of extra features beyond only pattern detection, planning, and problem resolution.\u0000METHODOLOGY: Machines use a set of techniques collectively called \"deep learning.\" Magnetic resonance imaging (MRI) is employed with the use of deep learning methods to develop models that can effectively identify and classify brain cancers. This technique facilitates the rapid and straightforward detection of brain cancers. Brain problems mainly arise from the abnormal multiplication of brain cells, leading to detrimental alterations in brain structure and finally culminating in the development of cancer in the brain, malignant. Early detection of brain tumors along with following effective intervention can reduce mortality rates. This paper proposes convolutional neural network (CNN) architecture to effectively detect brain cancers using magnetic resonance (MR) images.\u0000RESULTS: This research further examines several models, including ResNet-50, VGG16, and Inception V3, and compares the proposed architecture and these models. For the efficacy of the models, many measures were evaluated, including accuracy, recall, loss, and area under the curve (AUC). After analyzing several models and comparing them with the suggested model using the specified metrics, it was determined that the proposed model exhibited superior performance compared to the alternative models. Based on an analysis conducted on data from 3265 MR images.\u0000CONCLUSION: It was seen that the CNN model exhibited a classification precision of 93.3%. Additionally, the area under the receiver operating characteristic curve (AUC) was determined to be 98.43%, while the recall rate was 91.19%. Furthermore, the model's loss function yielded a value of 0.25. Based on a comparative analysis with other models, it can be inferred that the suggested model is highly reliable in detecting various types of brain cancers at an early stage.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"90 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140377672","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
INTRODUCTION: Polycystic Ovary Syndrome is a condition in which the ovaries manufacture androgen, seen in small traces, resulting in the production of cysts. Menstrual cycle abnormalities, clinical and/or biochemical hyperandrogenism, and the presence of polycystic ovaries on ultrasound should all be used to diagnose PCOS. PCOS appears to be a multifaceted illness influenced by both genetic and environmental factors and the symptoms include excessive hair on the face and body, weight gain, voice changes, skin type changes, and irregular periods. OBJECTIVES: This is the objective of this paper is to identify PCOS in its initial stage. METHODS: To address this issue the study proposes a comparison of various machine learning algorithms and optimization techniques Among which GSCV gave the best result of 94% accuracy, followed by TPOT with 91% accuracy. Additionally, we also applied Feature selection methods to eliminate zero-importance features to increase the accuracy of algorithms. RESULTS: The main results obtained in this paper This study explored various Feature selection techniques, ML and DL models. It is shown that Grid Search CV and TPOT classifier were best classifiers with 94% and 91% respectively. CONCLUSION: These are the conclusions of this paper and this study will explore various DL methodologies and try to find out best optimal results for the PCOS Detection. And also, to develop an PCOS detection application to keep track of menstrual cycles and track activities and symptoms for PCOS.
{"title":"Comparative Analysis of Polycystic Ovary Syndrome Detection Using Machine Learning Algorithms","authors":"Neha Yadav, Ranjith Kumar A, S. Pande","doi":"10.4108/eetpht.10.5552","DOIUrl":"https://doi.org/10.4108/eetpht.10.5552","url":null,"abstract":"INTRODUCTION: Polycystic Ovary Syndrome is a condition in which the ovaries manufacture androgen, seen in small traces, resulting in the production of cysts. Menstrual cycle abnormalities, clinical and/or biochemical hyperandrogenism, and the presence of polycystic ovaries on ultrasound should all be used to diagnose PCOS. PCOS appears to be a multifaceted illness influenced by both genetic and environmental factors and the symptoms include excessive hair on the face and body, weight gain, voice changes, skin type changes, and irregular periods. \u0000OBJECTIVES: This is the objective of this paper is to identify PCOS in its initial stage. \u0000METHODS: To address this issue the study proposes a comparison of various machine learning algorithms and optimization techniques Among which GSCV gave the best result of 94% accuracy, followed by TPOT with 91% accuracy. Additionally, we also applied Feature selection methods to eliminate zero-importance features to increase the accuracy of algorithms. \u0000RESULTS: The main results obtained in this paper This study explored various Feature selection techniques, ML and DL models. It is shown that Grid Search CV and TPOT classifier were best classifiers with 94% and 91% respectively. \u0000CONCLUSION: These are the conclusions of this paper and this study will explore various DL methodologies and try to find out best optimal results for the PCOS Detection. And also, to develop an PCOS detection application to keep track of menstrual cycles and track activities and symptoms for PCOS. ","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"103 14","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140380947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hritwik Ghosh, Irfan Sadiq Rahat, J. Ravindra, Balajee J, Mohammad Aman Ullah Khan, J. Somasekar
INTRODUCTION: Malaria, a persistent global health threat caused by Plasmodium parasites, necessitates rapid and accurate identification for effective treatment and containment. This study investigates the utilization of convolutional neural networks (CNNs) to enhance the precision and speed of malaria detection through the classification of cell images infected with malaria. OBJECTIVES: The primary objective of this research is to explore the effectiveness of CNNs in accurately classifying malaria-infected cell images. By employing various deep learning models, including ResNet50, AlexNet, Inception V3, VGG19, VGG16, and MobileNetV2, the study aims to assess the performance of each model and identify their strengths and weaknesses in malaria diagnosis. METHODS: A balanced dataset comprising approximately 8,000 enhanced images of blood cells, evenly distributed between infected and uninfected classes, was utilized for model training and evaluation. Performance evaluation metrics such as precision, recall, F1-score, and accuracy were employed to assess the efficacy of each CNN model in malaria classification. RESULTS: The results demonstrate high accuracy across all models, with AlexNet and VGG19 exhibiting the highest levels of accuracy. However, the selection of a model should consider specific application requirements and constraints, as each model presents unique trade-offs between computational efficiency and performance. CONCLUSION: This study contributes to the burgeoning field of deep learning in healthcare, particularly in utilizing medical imaging for disease diagnosis. The findings underscore the considerable potential of CNNs in enhancing malaria diagnosis. Future research directions may involve further model optimization, exploration of larger and more diverse datasets, and the integration of CNNs into practical diagnostic tools for real-world deployment.
{"title":"Convolutional Neural Networks in Malaria Diagnosis: A Study on Cell Image Classification","authors":"Hritwik Ghosh, Irfan Sadiq Rahat, J. Ravindra, Balajee J, Mohammad Aman Ullah Khan, J. Somasekar","doi":"10.4108/eetpht.10.5551","DOIUrl":"https://doi.org/10.4108/eetpht.10.5551","url":null,"abstract":"INTRODUCTION: Malaria, a persistent global health threat caused by Plasmodium parasites, necessitates rapid and accurate identification for effective treatment and containment. This study investigates the utilization of convolutional neural networks (CNNs) to enhance the precision and speed of malaria detection through the classification of cell images infected with malaria. \u0000OBJECTIVES: The primary objective of this research is to explore the effectiveness of CNNs in accurately classifying malaria-infected cell images. By employing various deep learning models, including ResNet50, AlexNet, Inception V3, VGG19, VGG16, and MobileNetV2, the study aims to assess the performance of each model and identify their strengths and weaknesses in malaria diagnosis. \u0000METHODS: A balanced dataset comprising approximately 8,000 enhanced images of blood cells, evenly distributed between infected and uninfected classes, was utilized for model training and evaluation. Performance evaluation metrics such as precision, recall, F1-score, and accuracy were employed to assess the efficacy of each CNN model in malaria classification. \u0000RESULTS: The results demonstrate high accuracy across all models, with AlexNet and VGG19 exhibiting the highest levels of accuracy. However, the selection of a model should consider specific application requirements and constraints, as each model presents unique trade-offs between computational efficiency and performance. \u0000CONCLUSION: This study contributes to the burgeoning field of deep learning in healthcare, particularly in utilizing medical imaging for disease diagnosis. The findings underscore the considerable potential of CNNs in enhancing malaria diagnosis. Future research directions may involve further model optimization, exploration of larger and more diverse datasets, and the integration of CNNs into practical diagnostic tools for real-world deployment.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"115 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140380207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sandeep Kumar Panda, Janjhyam Venkata Naga Ramesh, Hritwik Ghosh, Irfan Sadiq Rahat, Abdus Sobur, Mehadi Hasan Bijoy, Mannava Yesubabu
INTRODUCTION: In the field of medical imaging, accurate categorization of lung tissue is essential for timely diagnosis and management of lung-related conditions, including cancer. Deep Learning (DL) methodologies have revolutionized this domain, promising improved precision and effectiveness in diagnosing ailments based on image analysis. This research delves into the application of DL models for classifying lung tissue, particularly focusing on histopathological imagery. OBJECTIVES: The primary objective of this study is to explore the deployment of DL models for the classification of lung tissue, emphasizing histopathological images. The research aims to assess the performance of various DL models in accurately distinguishing between different classes of lung tissue, including benign tissue, lung adenocarcinoma, and lung squamous cell carcinoma. METHODS: A dataset comprising 9,000 histopathological images of lung tissue was utilized, sourced from HIPAA compliant and validated sources. The dataset underwent augmentation to ensure diversity and robustness. The images were categorized into three distinct classes and balanced before being split into training, validation, and testing sets. Six DL models - DenseNet201, EfficientNetB7, EfficientNetB5, Vgg19, Vgg16, and Alexnet - were trained and evaluated on this dataset. Performance assessment was conducted based on precision, recall, F1-score for each class, and overall accuracy. RESULTS: The results revealed varying performance levels among the DL models, with EfficientNetB5 achieving perfect scores across all metrics. This highlights the capability of DL in improving the accuracy of lung tissue classification, which holds promise for enhancing diagnosis and treatment outcomes in lung-related conditions. CONCLUSION: This research significantly contributes to understanding the effective utilization of DL models in medical imaging, particularly for lung tissue classification. It emphasizes the critical role of a diverse and balanced dataset in developing robust and accurate models. The insights gained from this study lay the groundwork for further exploration into refining DL methodologies for medical imaging applications, with a focus on improving diagnostic accuracy and ultimately, patient outcomes.
{"title":"Deep Learning in Medical Imaging: A Case Study on Lung Tissue Classification","authors":"Sandeep Kumar Panda, Janjhyam Venkata Naga Ramesh, Hritwik Ghosh, Irfan Sadiq Rahat, Abdus Sobur, Mehadi Hasan Bijoy, Mannava Yesubabu","doi":"10.4108/eetpht.10.5549","DOIUrl":"https://doi.org/10.4108/eetpht.10.5549","url":null,"abstract":"INTRODUCTION: In the field of medical imaging, accurate categorization of lung tissue is essential for timely diagnosis and management of lung-related conditions, including cancer. Deep Learning (DL) methodologies have revolutionized this domain, promising improved precision and effectiveness in diagnosing ailments based on image analysis. This research delves into the application of DL models for classifying lung tissue, particularly focusing on histopathological imagery. \u0000OBJECTIVES: The primary objective of this study is to explore the deployment of DL models for the classification of lung tissue, emphasizing histopathological images. The research aims to assess the performance of various DL models in accurately distinguishing between different classes of lung tissue, including benign tissue, lung adenocarcinoma, and lung squamous cell carcinoma. \u0000METHODS: A dataset comprising 9,000 histopathological images of lung tissue was utilized, sourced from HIPAA compliant and validated sources. The dataset underwent augmentation to ensure diversity and robustness. The images were categorized into three distinct classes and balanced before being split into training, validation, and testing sets. Six DL models - DenseNet201, EfficientNetB7, EfficientNetB5, Vgg19, Vgg16, and Alexnet - were trained and evaluated on this dataset. Performance assessment was conducted based on precision, recall, F1-score for each class, and overall accuracy. \u0000RESULTS: The results revealed varying performance levels among the DL models, with EfficientNetB5 achieving perfect scores across all metrics. This highlights the capability of DL in improving the accuracy of lung tissue classification, which holds promise for enhancing diagnosis and treatment outcomes in lung-related conditions. \u0000CONCLUSION: This research significantly contributes to understanding the effective utilization of DL models in medical imaging, particularly for lung tissue classification. It emphasizes the critical role of a diverse and balanced dataset in developing robust and accurate models. The insights gained from this study lay the groundwork for further exploration into refining DL methodologies for medical imaging applications, with a focus on improving diagnostic accuracy and ultimately, patient outcomes.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"104 44","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140380744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Colourisation is the process of synthesising colours in black and white images without altering the image’s structural content and semantics. The authors explore the concept of colourisation, aiming to colourise the multi-modal medical data through X-rays. Colourized X-ray images have a better potential to portray anatomical information than their conventional monochromatic counterparts. These images contain precious anatomical information that, when colourised, will become very valuable and potentially display more information for clinical diagnosis. This will help improve understanding of these X-rays and significantly contribute to the arena of medical image analysis. The authors have implemented three models, a basic auto-encoder architecture, and two combined learnings of the autoencoder module with transfer learning of pre-trained neural networks. The unique feature of this proposed framework is that it can colourise any medical modality in the medical imaging domain. The framework’s performance is evaluated on a chest x-ray image dataset, and it has produced benchmark results enabling high-quality colourisation. The biggest challenge is the need for a correct solution for the mapping between intensity and colour. This makes human interaction and external information from medical professionals crucial for interpreting the results.
色彩化是在不改变图像结构内容和语义的情况下，在黑白图像中合成色彩的过程。作者探索了彩色化的概念，旨在通过 X 射线将多模态医疗数据彩色化。与传统的单色图像相比，彩色 X 光图像更有可能描绘出解剖信息。这些图像包含珍贵的解剖信息，经过彩色化处理后将变得非常有价值，并有可能为临床诊断显示更多信息。这将有助于提高对这些 X 射线的理解，并为医学图像分析领域做出重大贡献。作者实施了三种模型，一种是基本的自动编码器架构，另两种是自动编码器模块与预训练神经网络迁移学习的结合。该框架的独特之处在于，它可以对医学成像领域的任何医学模式进行着色。我们在胸部 X 光图像数据集上对该框架的性能进行了评估，结果显示，该框架能实现高质量的着色。最大的挑战是需要为强度和颜色之间的映射提供正确的解决方案。因此，人机交互和来自医疗专业人员的外部信息对于解释结果至关重要。
{"title":"Colorizing Multi-Modal Medical Data: An Autoencoder-based Approach for Enhanced Anatomical Information in X-ray Images","authors":"Bunny Saini, Divya Venkatesh, Avinaash Ganesh, Amar Parameswaran, Shruti Patil, P. Kamat, Tanupriya Choudhury","doi":"10.4108/eetpht.10.5540","DOIUrl":"https://doi.org/10.4108/eetpht.10.5540","url":null,"abstract":"Colourisation is the process of synthesising colours in black and white images without altering the image’s structural content and semantics. The authors explore the concept of colourisation, aiming to colourise the multi-modal medical data through X-rays. Colourized X-ray images have a better potential to portray anatomical information than their conventional monochromatic counterparts. These images contain precious anatomical information that, when colourised, will become very valuable and potentially display more information for clinical diagnosis. This will help improve understanding of these X-rays and significantly contribute to the arena of medical image analysis. The authors have implemented three models, a basic auto-encoder architecture, and two combined learnings of the autoencoder module with transfer learning of pre-trained neural networks. The unique feature of this proposed framework is that it can colourise any medical modality in the medical imaging domain. The framework’s performance is evaluated on a chest x-ray image dataset, and it has produced benchmark results enabling high-quality colourisation. The biggest challenge is the need for a correct solution for the mapping between intensity and colour. This makes human interaction and external information from medical professionals crucial for interpreting the results.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"117 28","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140380943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Irfan Sadiq Rahat, Tuhin Hossain, Hritwik Ghosh, Kamjula Lakshmi, Kanth Reddy, Srinivas Kumar Palvadi, J. Ravindra
INTRODUCTION: Alzheimer's disease (AD), a complex neurodegenerative condition, presents significant challenges in early and accurate diagnosis. Early prediction of AD severity holds the potential for improved patient care and timely interventions. This research investigates the use of deep learning methodologies to forecast AD severity utilizing data extracted from Magnetic Resonance Imaging (MRI) scans. OBJECTIVES: This study aims to explore the efficacy of deep learning models in predicting the severity of Alzheimer's disease using MRI data. Traditional diagnostic methods for AD, primarily reliant on cognitive assessments, often lead to late-stage detection. MRI scans offer a non-invasive means to examine brain structure and detect pathological changes associated with AD. However, manual interpretation of these scans is labor-intensive and subject to variability. METHODS: Various deep learning models, including Convolutional Neural Networks (CNNs) and advanced architectures like DenseNet, VGG16, ResNet50, MobileNet, AlexNet, and Xception, are explored for MRI scan analysis. The performance of these models in predicting AD severity is assessed and compared. Deep learning models autonomously learn hierarchical features from the data, potentially recognizing intricate patterns associated with different AD stages that may be overlooked in manual analysis. RESULTS: The study evaluates the performance of different deep learning models in predicting AD severity using MRI scans. The results highlight the efficacy of these models in capturing subtle patterns indicative of AD progression. Moreover, the comparison underscores the strengths and limitations of each model, aiding in the selection of appropriate methodologies for AD prognosis. CONCLUSION: This research contributes to the growing field of AI-driven healthcare by showcasing the potential of deep learning in revolutionizing AD diagnosis and prognosis. The findings emphasize the importance of leveraging advanced technologies, such as deep learning, to enhance the accuracy and timeliness of AD diagnosis. However, challenges remain, including the need for large annotated datasets, model interpretability, and integration into clinical workflows. Continued efforts in this area hold promise for improving the management of AD and ultimately enhancing patient outcomes.
简介：阿尔茨海默病（AD）是一种复杂的神经退行性疾病，给早期准确诊断带来了巨大挑战。早期预测阿尔茨海默病的严重程度有望改善患者护理和及时干预。本研究利用从磁共振成像（MRI）扫描中提取的数据，研究如何使用深度学习方法预测老年痴呆症的严重程度。目标：本研究旨在探索深度学习模型在利用核磁共振成像数据预测阿尔茨海默病严重程度方面的功效。阿尔茨海默病的传统诊断方法主要依赖于认知评估，往往导致晚期检测。核磁共振成像扫描提供了一种非侵入性的方法来检查大脑结构并检测与阿兹海默症相关的病理变化。然而，人工解读这些扫描需要耗费大量人力物力，而且容易出现偏差。方法：我们探索了各种深度学习模型，包括卷积神经网络（CNN）和高级架构，如 DenseNet、VGG16、ResNet50、MobileNet、AlexNet 和 Xception，用于 MRI 扫描分析。对这些模型在预测注意力缺失症严重程度方面的性能进行了评估和比较。深度学习模型可从数据中自主学习分层特征，从而有可能识别出与注意力缺失症不同阶段相关的复杂模式，而这些模式在人工分析中可能会被忽略。结果：该研究评估了不同深度学习模型在使用核磁共振扫描预测AD严重程度方面的性能。结果凸显了这些模型在捕捉表明注意力缺失症进展的微妙模式方面的功效。此外，比较还强调了每个模型的优势和局限性，有助于选择适当的方法来预测 AD 的病情。结论：这项研究展示了深度学习在革新注意力缺失症诊断和预后方面的潜力，为不断发展的人工智能驱动的医疗保健领域做出了贡献。研究结果强调了利用深度学习等先进技术提高注意力缺失症诊断的准确性和及时性的重要性。然而，挑战依然存在，包括需要大型注释数据集、模型的可解释性以及与临床工作流程的整合。在这一领域的持续努力有望改善注意力缺失症的管理，并最终提高患者的治疗效果。
{"title":"Exploring Deep Learning Models for Accurate Alzheimer's Disease Classification based on MRI Imaging","authors":"Irfan Sadiq Rahat, Tuhin Hossain, Hritwik Ghosh, Kamjula Lakshmi, Kanth Reddy, Srinivas Kumar Palvadi, J. Ravindra","doi":"10.4108/eetpht.10.5543","DOIUrl":"https://doi.org/10.4108/eetpht.10.5543","url":null,"abstract":"INTRODUCTION: Alzheimer's disease (AD), a complex neurodegenerative condition, presents significant challenges in early and accurate diagnosis. Early prediction of AD severity holds the potential for improved patient care and timely interventions. This research investigates the use of deep learning methodologies to forecast AD severity utilizing data extracted from Magnetic Resonance Imaging (MRI) scans. \u0000OBJECTIVES: This study aims to explore the efficacy of deep learning models in predicting the severity of Alzheimer's disease using MRI data. Traditional diagnostic methods for AD, primarily reliant on cognitive assessments, often lead to late-stage detection. MRI scans offer a non-invasive means to examine brain structure and detect pathological changes associated with AD. However, manual interpretation of these scans is labor-intensive and subject to variability. \u0000METHODS: Various deep learning models, including Convolutional Neural Networks (CNNs) and advanced architectures like DenseNet, VGG16, ResNet50, MobileNet, AlexNet, and Xception, are explored for MRI scan analysis. The performance of these models in predicting AD severity is assessed and compared. Deep learning models autonomously learn hierarchical features from the data, potentially recognizing intricate patterns associated with different AD stages that may be overlooked in manual analysis. \u0000RESULTS: The study evaluates the performance of different deep learning models in predicting AD severity using MRI scans. The results highlight the efficacy of these models in capturing subtle patterns indicative of AD progression. Moreover, the comparison underscores the strengths and limitations of each model, aiding in the selection of appropriate methodologies for AD prognosis. \u0000CONCLUSION: This research contributes to the growing field of AI-driven healthcare by showcasing the potential of deep learning in revolutionizing AD diagnosis and prognosis. The findings emphasize the importance of leveraging advanced technologies, such as deep learning, to enhance the accuracy and timeliness of AD diagnosis. However, challenges remain, including the need for large annotated datasets, model interpretability, and integration into clinical workflows. Continued efforts in this area hold promise for improving the management of AD and ultimately enhancing patient outcomes.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":" 38","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140383732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mallellu Sai Prashanth, Uma Maheswari, Rajinikanth Aluvalu, M. Kantipudi
INTRODUCTION: Blockchain technology is being investigated as a viable solution due to the industry's growing requirement for accountability and traceability. This study describes a fresh method for tracking down medical products that makes use of a decentralised smart contract network set up on the Ethereum blockchain. In order to enable secure and auditable tracking of health products throughout their lifecycle, the suggested system, named "HealthProductTraceability," makes use of the transparency and immutability of blockchain. OBJECTIVES: The system uses a "Product" struct to hold pertinent data such the product name, batch number, temperature, producer, and distributors. To quickly get product information depending on the batch number, a mapping is used. The use of tools to manufacture items, send them to distributors, and market them is one significant contribution of this research.By demanding validation tests, such as verifying that batch numbers are unique and exist before carrying out certain activities, these functions protect the integrity of the traceability system. METHODS: In order to enable interested parties to track the product's travel and temperature changes, the system additionally emits events for product manufacture, distribution, and temperature adjustments. The suggested system is innovative because it can track the temperature of health items from beginning to end on a decentralised, open platform. RESULTS: By utilising blockchain technology, the system lessens reliance on centralised authorities, fosters stakeholder trust, and minimises the likelihood of fraud, forgery, and tampering in the supply chain for health products. The contract's architecture recognises some of the issues with blockchain technology, including scalability and privacy. By investigating solutions like sidechains, off-chain transactions, and enhancements to consensus methods, scalability issues are solved. CONCLUSION: In summary, the suggested HealthProductTraceability system offers a creative and practical solution to the traceability issues facing the health product sector. The solution provides improved transparency, security, and accountability by utilising blockchain technology, paving the path for a more dependable and trustworthy health product supply chain. To increase the system's usefulness and adoption in real-world circumstances, further research can investigate scalability and privacy issues.
{"title":"Enhancing Health Product Traceability on the Blockchain: A Novel Approach for Supply Chain Management inspection to AI","authors":"Mallellu Sai Prashanth, Uma Maheswari, Rajinikanth Aluvalu, M. Kantipudi","doi":"10.4108/eetpht.10.5544","DOIUrl":"https://doi.org/10.4108/eetpht.10.5544","url":null,"abstract":"INTRODUCTION: Blockchain technology is being investigated as a viable solution due to the industry's growing requirement for accountability and traceability. This study describes a fresh method for tracking down medical products that makes use of a decentralised smart contract network set up on the Ethereum blockchain. In order to enable secure and auditable tracking of health products throughout their lifecycle, the suggested system, named \"HealthProductTraceability,\" makes use of the transparency and immutability of blockchain. \u0000OBJECTIVES: The system uses a \"Product\" struct to hold pertinent data such the product name, batch number, temperature, producer, and distributors. To quickly get product information depending on the batch number, a mapping is used. The use of tools to manufacture items, send them to distributors, and market them is one significant contribution of this research.By demanding validation tests, such as verifying that batch numbers are unique and exist before carrying out certain activities, these functions protect the integrity of the traceability system. \u0000METHODS: In order to enable interested parties to track the product's travel and temperature changes, the system additionally emits events for product manufacture, distribution, and temperature adjustments. The suggested system is innovative because it can track the temperature of health items from beginning to end on a decentralised, open platform. \u0000RESULTS: By utilising blockchain technology, the system lessens reliance on centralised authorities, fosters stakeholder trust, and minimises the likelihood of fraud, forgery, and tampering in the supply chain for health products. The contract's architecture recognises some of the issues with blockchain technology, including scalability and privacy. By investigating solutions like sidechains, off-chain transactions, and enhancements to consensus methods, scalability issues are solved. \u0000CONCLUSION: In summary, the suggested HealthProductTraceability system offers a creative and practical solution to the traceability issues facing the health product sector. The solution provides improved transparency, security, and accountability by utilising blockchain technology, paving the path for a more dependable and trustworthy health product supply chain. To increase the system's usefulness and adoption in real-world circumstances, further research can investigate scalability and privacy issues.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":" 41","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140384363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
F. Mercaldo, Luca Brunese, A. Santone, Fabio Martinelli, M. Cesarelli
In the current realm of biomedical image classification, the predominant choice remains deep learning networks, particularly convolutional neural network (CNN) models. However, deep learning suffers from a notable drawback in terms of its high training cost, mainly due to intricate data models. A recent alternative, known as the Extreme Learning Machine (ELM), has emerged as a promising solution. Empirical investigations have indicated that ELM can offer satisfactory predictive performance for a wide array of classification tasks, while significantly reducing training costs when compared to deep learning networks trained using back propagation.This research paper introduces a methodology designed to evaluate the suitability of employing the Extreme Learning Machine for biomedical classification tasks. Our study encompasses binary and multiclass classification across four distinct scenarios, involving the analysis of biomedical images obtained from both dermatoscopes and blood cell microscopes. The findings underscore the effectiveness of the Extreme Learning Machine, showcasing its successful utilization in the classification of biomedical images.
{"title":"Extreme Learning Machine for Biomedical Image Classification: A Multi-Case Study","authors":"F. Mercaldo, Luca Brunese, A. Santone, Fabio Martinelli, M. Cesarelli","doi":"10.4108/eetpht.10.5542","DOIUrl":"https://doi.org/10.4108/eetpht.10.5542","url":null,"abstract":"In the current realm of biomedical image classification, the predominant choice remains deep learning networks, particularly convolutional neural network (CNN) models. However, deep learning suffers from a notable drawback in terms of its high training cost, mainly due to intricate data models. A recent alternative, known as the Extreme Learning Machine (ELM), has emerged as a promising solution. Empirical investigations have indicated that ELM can offer satisfactory predictive performance for a wide array of classification tasks, while significantly reducing training costs when compared to deep learning networks trained using back propagation.This research paper introduces a methodology designed to evaluate the suitability of employing the Extreme Learning Machine for biomedical classification tasks. Our study encompasses binary and multiclass classification across four distinct scenarios, involving the analysis of biomedical images obtained from both dermatoscopes and blood cell microscopes. The findings underscore the effectiveness of the Extreme Learning Machine, showcasing its successful utilization in the classification of biomedical images.","PeriodicalId":36936,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":" 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140384003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：