Detection of tumors in brain on time saves the patient life. The brain tumor detection is usually done in Magnetic Resonance Imaging (MRI) of the human brain. An automated model is framed to identify tumor pixels in method for detecting and image. This proposed method contains the following modules as enhancement, transformation, feature extraction, classifications and segmentation. The Oriented Local Histogram Equalization (OLHE) method is applied on the brain MRI images in order to enhance the pixel intensity in boundary regions. This enhanced brain image is transformed to multi orientation image using Gabor transform with respect to various scale and orientation of pixels. Then, set of features (Higher Order Spectra (HOS), Gradient, Grey Level Co-occurrence Matrix (GLCM), Local Binary Pattern (LBP) and Curvelet) are extracted from this Gabor transformed image and these features are further trained and classified into benign or malignant using Adaptive Neuro Fuzzy Inference (ANFIS) classification approach. Finally, morphological algorithm is used for segmenting the tumor regions in the classified responses. MATLAB R2018 version is used in this paper to simulate the proposed algorithm for brain tumor detection. This proposed system achieves 98.6% of sensitivity, 99.5% of specificity and 99.4% of segmentation accuracy.
{"title":"An Efficient Approach to Detect Meningioma Brain Tumor Using Adaptive Neuro Fuzzy Inference System Method","authors":"B. Prakash, A. Kannan","doi":"10.1166/jmihi.2022.3931","DOIUrl":"https://doi.org/10.1166/jmihi.2022.3931","url":null,"abstract":"Detection of tumors in brain on time saves the patient life. The brain tumor detection is usually done in Magnetic Resonance Imaging (MRI) of the human brain. An automated model is framed to identify tumor pixels in method for detecting and image. This proposed method contains the following\u0000 modules as enhancement, transformation, feature extraction, classifications and segmentation. The Oriented Local Histogram Equalization (OLHE) method is applied on the brain MRI images in order to enhance the pixel intensity in boundary regions. This enhanced brain image is transformed to\u0000 multi orientation image using Gabor transform with respect to various scale and orientation of pixels. Then, set of features (Higher Order Spectra (HOS), Gradient, Grey Level Co-occurrence Matrix (GLCM), Local Binary Pattern (LBP) and Curvelet) are extracted from this Gabor transformed image\u0000 and these features are further trained and classified into benign or malignant using Adaptive Neuro Fuzzy Inference (ANFIS) classification approach. Finally, morphological algorithm is used for segmenting the tumor regions in the classified responses. MATLAB R2018 version is used in this paper\u0000 to simulate the proposed algorithm for brain tumor detection. This proposed system achieves 98.6% of sensitivity, 99.5% of specificity and 99.4% of segmentation accuracy.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"299302 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123445694","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}
Breast cancer is the utmost generally occurring cancer in women and the second most communal cancer. The ground truth standard used in real-time clinical application for the diagnosis is a mammogram. A novel approach is projected in this paper for the automated diagnosis of breast cancer from mammogram images composed from the MIAS data set using curvelet/wavelet transform-based features and a convolutional neural network. The following sequences of operations are involved, namely pre-processing, application of curvelet/wavelet transform, statistical and gray level co-occurrence matrix-based features extracted from curvelet/wavelet coefficients followed by a selection of highly discriminative features by statistical p-test. Initially, pre-trained models VGG16 and VGG19 are used for classification, and Deep convolutional neural network architecture is constructed for which feature matrix is given as input. Pretrained models are used for classification using the concept of transfer learning. The constructed architecture hyperparameters are adjusted, and the highest classification precision of 93% is achieved. The obtained results outperform the state of art methods available in the state of art.
{"title":"Automated Diagnosis of Breast Cancer from Mammogram Using Wavelet, Curvelet Features, and Convolutional Neural Network","authors":"R. S. Karthic, K. A. Britto","doi":"10.1166/jmihi.2022.3853","DOIUrl":"https://doi.org/10.1166/jmihi.2022.3853","url":null,"abstract":"Breast cancer is the utmost generally occurring cancer in women and the second most communal cancer. The ground truth standard used in real-time clinical application for the diagnosis is a mammogram. A novel approach is projected in this paper for the automated diagnosis of breast cancer\u0000 from mammogram images composed from the MIAS data set using curvelet/wavelet transform-based features and a convolutional neural network. The following sequences of operations are involved, namely pre-processing, application of curvelet/wavelet transform, statistical and gray level co-occurrence\u0000 matrix-based features extracted from curvelet/wavelet coefficients followed by a selection of highly discriminative features by statistical p-test. Initially, pre-trained models VGG16 and VGG19 are used for classification, and Deep convolutional neural network architecture is constructed for\u0000 which feature matrix is given as input. Pretrained models are used for classification using the concept of transfer learning. The constructed architecture hyperparameters are adjusted, and the highest classification precision of 93% is achieved. The obtained results outperform the state of\u0000 art methods available in the state of art.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115465847","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}
Cognitive Behavior Therapy (CBT) effectively treats impulse/anger attacks and aggressive-impulsive behaviors, frequently conducted concerning domestic violence, among patients with alcohol dependence. CBT combined with virtual reality (VR) is a new and beneficial psychotherapeutic intervention for patients and violent offenders with impulse-anger control problems and alcohol dependence. This clinical study evaluated the effects of the “anger management virtual reality cognitive behavior therapy (AM-VR-CBT)” and motivational interviewing (MI) intervention program on quantitative electroencephalography (QEEG) mapping patterns among violent offenders with alcohol dependence (N = 29) in the National Probation Service. A clinical sample of twenty-nine violent offenders with alcohol dependence, who were evaluated and diagnosed with destructive and impulse-control disorders (DICD), underwent AM-VR-CBT combined with MI. The sessions lasted 150 minutes (AM-VR-CBT: 90 min; MI: 60 min) and were conducted twice a week for three weeks (six sessions). The intervention outcomes were measured using advanced QEEG brain mapping and standardized neurocognitive, emotional, and behavioral inventories, including the Alcohol Dependence Scale (ADS), the Obsessive Compulsive Drinking Scale (OCDS), the Readiness to Change Questionnaire (RTCQ), the Barratt Impulsiveness Scale-II (BIS-II), the Beck Anxiety Inventory (BAI), the Beck Depression Inventory-Second Edition (BDI-2), and the State-Trait Anger Expression Inventory-2 (STAXI-2), to identify neuro-psycho-physiological changes in violent offenders with alcohol dependence. The Wilcoxon signed-rank test was used at p < 0.05. The intervention showed significant improvements and healthy behavioral changes related to obsessive drinking thoughts, compulsive drinking behaviors, attentional control, intrinsic motivation, worry, anxiety, depression, impulse-anger control issues, aggressive behaviors, over-control, interpersonal relationships, self-efficacy, self-reflection, self-inhibition, creativity, mental navigation/imagery, and episodic memory retrieval among violent offenders with alcohol dependence. Therefore, the results demonstrate the efficacy of the novel and promising clinical evidence-based implementation of the AM-VR-CBT + MI program intervention for non-invasive neuromodulation and related neuro-psycho-physiological, neurocognitive, emotional, and behavioral changes among violent offenders demonstrating alcohol dependence, impulse-anger control, and aggressive behaviors.
认知行为疗法(CBT)有效地治疗酒精依赖患者的冲动/愤怒攻击和攻击冲动行为，这些行为通常与家庭暴力有关。CBT与虚拟现实(VR)相结合是一种新的有益的心理治疗干预方法，适用于有冲动愤怒控制问题和酒精依赖的暴力罪犯和患者。本临床研究评估了“愤怒管理虚拟现实认知行为疗法(AM-VR-CBT)”和动机性访谈(MI)干预方案对国家缓刑服务处酒精依赖暴力罪犯定量脑电图(QEEG)映射模式的影响。临床样本为29名酒精依赖的暴力罪犯，他们被评估并诊断为破坏性和冲动控制障碍(DICD)，接受AM-VR-CBT联合MI治疗。疗程持续150分钟(AM-VR-CBT: 90分钟;MI: 60分钟)，每周进行两次，持续三周(六次)。干预结果采用先进的QEEG脑图和标准化的神经认知、情绪和行为量表进行测量，包括酒精依赖量表(ADS)、强迫性饮酒量表(OCDS)、改变准备问卷(RTCQ)、Barratt冲动量表- ii (BIS-II)、Beck焦虑量表(BAI)、Beck抑郁量表第二版(BDI-2)和状态-特质愤怒表达量表-2 (STAXI-2)。鉴定酒精依赖的暴力罪犯的神经心理生理变化。采用Wilcoxon符号秩检验，p < 0.05。干预对酒精依赖暴力罪犯的强迫饮酒想法、强迫饮酒行为、注意力控制、内在动机、担忧、焦虑、抑郁、冲动愤怒控制问题、攻击行为、过度控制、人际关系、自我效能、自我反思、自我抑制、创造力、心理导航/意象和情景记忆检索等方面均有显著改善和健康的行为改变。因此，该研究结果证明了AM-VR-CBT + MI方案在无创神经调节和相关神经心理生理、神经认知、情绪和行为改变方面的有效性，这是一种新颖且有前景的临床循证实施方法。
{"title":"Using Anger Management Virtual Reality Cognitive Behavior Therapy to Treat Violent Offenders with Alcohol Dependence in South Korea: A Preliminary Investigation","authors":"Chang Hyun Ryu","doi":"10.1166/jmihi.2022.3925","DOIUrl":"https://doi.org/10.1166/jmihi.2022.3925","url":null,"abstract":"Cognitive Behavior Therapy (CBT) effectively treats impulse/anger attacks and aggressive-impulsive behaviors, frequently conducted concerning domestic violence, among patients with alcohol dependence. CBT combined with virtual reality (VR) is a new and beneficial psychotherapeutic intervention\u0000 for patients and violent offenders with impulse-anger control problems and alcohol dependence. This clinical study evaluated the effects of the “anger management virtual reality cognitive behavior therapy (AM-VR-CBT)” and motivational interviewing (MI) intervention program on quantitative\u0000 electroencephalography (QEEG) mapping patterns among violent offenders with alcohol dependence (N = 29) in the National Probation Service. A clinical sample of twenty-nine violent offenders with alcohol dependence, who were evaluated and diagnosed with destructive and impulse-control\u0000 disorders (DICD), underwent AM-VR-CBT combined with MI. The sessions lasted 150 minutes (AM-VR-CBT: 90 min; MI: 60 min) and were conducted twice a week for three weeks (six sessions). The intervention outcomes were measured using advanced QEEG brain mapping and standardized neurocognitive,\u0000 emotional, and behavioral inventories, including the Alcohol Dependence Scale (ADS), the Obsessive Compulsive Drinking Scale (OCDS), the Readiness to Change Questionnaire (RTCQ), the Barratt Impulsiveness Scale-II (BIS-II), the Beck Anxiety Inventory (BAI), the Beck Depression Inventory-Second\u0000 Edition (BDI-2), and the State-Trait Anger Expression Inventory-2 (STAXI-2), to identify neuro-psycho-physiological changes in violent offenders with alcohol dependence. The Wilcoxon signed-rank test was used at p < 0.05. The intervention showed significant improvements and healthy\u0000 behavioral changes related to obsessive drinking thoughts, compulsive drinking behaviors, attentional control, intrinsic motivation, worry, anxiety, depression, impulse-anger control issues, aggressive behaviors, over-control, interpersonal relationships, self-efficacy, self-reflection, self-inhibition,\u0000 creativity, mental navigation/imagery, and episodic memory retrieval among violent offenders with alcohol dependence. Therefore, the results demonstrate the efficacy of the novel and promising clinical evidence-based implementation of the AM-VR-CBT + MI program intervention for non-invasive\u0000 neuromodulation and related neuro-psycho-physiological, neurocognitive, emotional, and behavioral changes among violent offenders demonstrating alcohol dependence, impulse-anger control, and aggressive behaviors.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121736461","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}
{"title":"Functional Magnetic Resonance Imaging Study of Thymus Activation Induced by Different Intensity Electrical Stimulation (Journal of Medical Imaging and Health Informatics, Vol. 11(2), pp. 378-385 (2021))","authors":"Tao Li, Kai Chen, X. Quan","doi":"10.1166/jmihi.2022.3930","DOIUrl":"https://doi.org/10.1166/jmihi.2022.3930","url":null,"abstract":"","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129317387","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}
Han Zhou, Jing Li, A. Li, X. Qiu, Zetian Shen, Y. Ge
Purpose: Analyze the clinical application of MIM maestro in cancer radiotherapy and evaluate the advantage of the software compare to the clinical applied tools. Materials and Methods: Potentially relevant studies published were identified through a pubmed and web of science search using words “MIM Maestro,” “Atlas,” “image registration,” “dose accumulation,” “irradiation.” Combinations of words were also searched as were bibliographies of downloaded papers in order to avoid missing relevant publications. Results: In many patients with cancer radiotherapy, multiple types of images are demanded, MIM Maestro is a multi-modality image information processing system for radiotherapy. Contour atlas and image registration among dose accumulation and individual fractions is beneficial for radiotherapy. Overall 34 papers were enrolled for analysis. The MIM appears to provide excellent clinical applications such as the function of contour altas, image fusion and registration, dose accumulation in radiotherapy compared to the other software. Conclusions: The regular optimization of radiotherapy technology and the development of image technology, improve the clinical efficiency. The current paper give a systematic review of MIM Maestro multi-modality image processing software.
{"title":"Diagnostic Application and Systematic Evaluation of Image Registration Software in External Radiotherapy","authors":"Han Zhou, Jing Li, A. Li, X. Qiu, Zetian Shen, Y. Ge","doi":"10.1166/jmihi.2022.3928","DOIUrl":"https://doi.org/10.1166/jmihi.2022.3928","url":null,"abstract":"Purpose: Analyze the clinical application of MIM maestro in cancer radiotherapy and evaluate the advantage of the software compare to the clinical applied tools. Materials and Methods: Potentially relevant studies published were identified through a pubmed and web of science\u0000 search using words “MIM Maestro,” “Atlas,” “image registration,” “dose accumulation,” “irradiation.” Combinations of words were also searched as were bibliographies of downloaded papers in order to avoid missing relevant publications.\u0000 Results: In many patients with cancer radiotherapy, multiple types of images are demanded, MIM Maestro is a multi-modality image information processing system for radiotherapy. Contour atlas and image registration among dose accumulation and individual fractions is beneficial for radiotherapy.\u0000 Overall 34 papers were enrolled for analysis. The MIM appears to provide excellent clinical applications such as the function of contour altas, image fusion and registration, dose accumulation in radiotherapy compared to the other software. Conclusions: The regular optimization of radiotherapy\u0000 technology and the development of image technology, improve the clinical efficiency. The current paper give a systematic review of MIM Maestro multi-modality image processing software.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133089752","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}
Telemedicine is one of the IoMT applications transmitting medical images from hospital to remote medical centers for diagnosis and treatment. To share this multimedia content across internet, storage and transmission become a challenge because of its huge volume. New compression techniques are being continuously introduced to circumvent this issue. Compressive sensing (CS) is a new paradigm in signal compression. Block based compressive sensing (BCS) is a standard and commonly used technique in color image compression. However, BCS suffers from block artifacts and during transmission, mistakes can be introduced to affect the BCS coefficients, degrading the reconstructed image’s quality. The performance of BCS at low compression ratios is also poor. To overcome these limitations, without dividing the image into blocks, the image matrix is considered as a whole and compressively sensed by segment based compressive sensing (SBCS). This is a novel strategy that is offered in this article, for efficient compression of digital color images at low compression ratios. Metrics of performance The peak signal to noise ratio (PSNR), the mean structural similarity index (MSSIM), and the colour perception metric delta E are computed and compared to those obtained using block-based compressive sensing (BBCS). The results show that SBCS performs better than BBCS.
{"title":"Segment Based Compressive Sensing (SBCS) of Color Images for Internet of Multimedia Things Applications","authors":"B. Lalithambigai, S. Chitra","doi":"10.1166/jmihi.2022.3848","DOIUrl":"https://doi.org/10.1166/jmihi.2022.3848","url":null,"abstract":"Telemedicine is one of the IoMT applications transmitting medical images from hospital to remote medical centers for diagnosis and treatment. To share this multimedia content across internet, storage and transmission become a challenge because of its huge volume. New compression techniques\u0000 are being continuously introduced to circumvent this issue. Compressive sensing (CS) is a new paradigm in signal compression. Block based compressive sensing (BCS) is a standard and commonly used technique in color image compression. However, BCS suffers from block artifacts and during transmission,\u0000 mistakes can be introduced to affect the BCS coefficients, degrading the reconstructed image’s quality. The performance of BCS at low compression ratios is also poor. To overcome these limitations, without dividing the image into blocks, the image matrix is considered as a whole and\u0000 compressively sensed by segment based compressive sensing (SBCS). This is a novel strategy that is offered in this article, for efficient compression of digital color images at low compression ratios. Metrics of performance The peak signal to noise ratio (PSNR), the mean structural similarity\u0000 index (MSSIM), and the colour perception metric delta E are computed and compared to those obtained using block-based compressive sensing (BBCS). The results show that SBCS performs better than BBCS.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133196569","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}
The collection of fluid at the back of the fetal neck, known as nuchal translucency (NT), is linked to chromosomal abnormalities and early heart failure in the first trimester of pregnancy. Using the Co-Active Adaptive Neuro Fuzzy Inference System (CANFIS) classification algorithm, this research presents an effective way for recognising and localising the NT region in fetus images in which noise removed. Then, pattern features are extracted Initially, the noises in fetus images are detected and eliminated using directional filtering technique and then Gabor transform from the magnitude of Gabor transformed fetus image and then they are optimized using Genetic Algorithm (GA) approach. The extracted GLCM, ELBP and LTP features are integrated into feature vector for further classifications. The size of constructed feature vector is high and leads to high computation time for the classification process. These optimized feature set is classified using CANFIS. Finally, the graph cut segmentation method is used for segmenting the NT region. This proposed method is practically used in many health care centers in rural areas.
{"title":"Execution Analysis of Clarity Locale Segmentation for Condition Recognition Utilizing Genetic Algorithm Method","authors":"S. Saranya, S. Sudha","doi":"10.1166/jmihi.2022.3887","DOIUrl":"https://doi.org/10.1166/jmihi.2022.3887","url":null,"abstract":"The collection of fluid at the back of the fetal neck, known as nuchal translucency (NT), is linked to chromosomal abnormalities and early heart failure in the first trimester of pregnancy. Using the Co-Active Adaptive Neuro Fuzzy Inference System (CANFIS) classification algorithm,\u0000 this research presents an effective way for recognising and localising the NT region in fetus images in which noise removed. Then, pattern features are extracted Initially, the noises in fetus images are detected and eliminated using directional filtering technique and then Gabor transform\u0000 from the magnitude of Gabor transformed fetus image and then they are optimized using Genetic Algorithm (GA) approach. The extracted GLCM, ELBP and LTP features are integrated into feature vector for further classifications. The size of constructed feature vector is high and leads to high\u0000 computation time for the classification process. These optimized feature set is classified using CANFIS. Finally, the graph cut segmentation method is used for segmenting the NT region. This proposed method is practically used in many health care centers in rural areas.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129703258","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}
Melanoma is the most serious form of skin cancer that affects millions of people globally. Through image analytics, early identification of skin cancer is enabled, resulting in more effective treatment and a lower mortality rate. The ph2 and human against machine datasets were used to collect images. After preprocessing the image with a weighted median filter, segmentation is investigated using a number of common techniques, with the best result generated by combining watershed transform and maximum similarity region merging. U-net architecture is explored for segmentation. Segmentation efficiency is calculated by dice loss and Jaccard coefficient. Segmentation architecture outperform the conventional method. Additionally, a novel wavelet transform-based approach is used to extract features, followed by local ternary pattern analysis. The intersection of the histograms, the Bhattacharya distance, the Chi-square distance, and the Pearson correlation coefficients are all computed. This inquiry makes use of only the Histogram intersection and Chi-square distance characteristics. Additional categorization is examined through the use of a range of machine learning algorithms, including the k-nearest neighbour approach, Bayesian classification, decision trees, and Support Vector Machines (SVM). When a Radial Basis Function (RBF) kernel based SVM is applied, the classification accuracy is maximised. This work is entirely devoted to binary categorization. As evidenced by the data, they outperform other state-of-the-art approaches reported in the literature. SVM classifies data with an accuracy of 98.6 percent. Weighted median filter, Watershed transform, Merging regions with the highest degree of similarity, Wavelet transform, Local Ternary Pattern, Histogram intersection Pearson correlation coefficient, chi-square distance Distance between Bhattacharya and support vector machine.
{"title":"Melanoma Skin Cancer Detection Using Wavelet Transform and Local Ternary Pattern","authors":"R. Ragumadhavan, K. R. Britto, R. Vimala","doi":"10.1166/jmihi.2022.3856","DOIUrl":"https://doi.org/10.1166/jmihi.2022.3856","url":null,"abstract":"Melanoma is the most serious form of skin cancer that affects millions of people globally. Through image analytics, early identification of skin cancer is enabled, resulting in more effective treatment and a lower mortality rate. The ph2 and human against machine datasets were used\u0000 to collect images. After preprocessing the image with a weighted median filter, segmentation is investigated using a number of common techniques, with the best result generated by combining watershed transform and maximum similarity region merging. U-net architecture is explored for segmentation.\u0000 Segmentation efficiency is calculated by dice loss and Jaccard coefficient. Segmentation architecture outperform the conventional method. Additionally, a novel wavelet transform-based approach is used to extract features, followed by local ternary pattern analysis. The intersection of the\u0000 histograms, the Bhattacharya distance, the Chi-square distance, and the Pearson correlation coefficients are all computed. This inquiry makes use of only the Histogram intersection and Chi-square distance characteristics. Additional categorization is examined through the use of a range of\u0000 machine learning algorithms, including the k-nearest neighbour approach, Bayesian classification, decision trees, and Support Vector Machines (SVM). When a Radial Basis Function (RBF) kernel based SVM is applied, the classification accuracy is maximised. This work is entirely devoted to binary\u0000 categorization. As evidenced by the data, they outperform other state-of-the-art approaches reported in the literature. SVM classifies data with an accuracy of 98.6 percent. Weighted median filter, Watershed transform, Merging regions with the highest degree of similarity, Wavelet transform,\u0000 Local Ternary Pattern, Histogram intersection Pearson correlation coefficient, chi-square distance Distance between Bhattacharya and support vector machine.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134534150","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}
Purpose: Meta-heuristic (MH) methods are used to develop an adaptive sliding mode controller for a POEL converter. MH algorithms have been used to address a variety of engineering optimization problems. Which will use for Bio medical hybrid systems applications. Design/Methodology: Particle Swarm Optimization (PSO) approach is well known and it could expedite the convergence characteristic in numerous applications. By means of amending PSO parameters like, inertia mass, social and perceptive agents at every generation, Modern Parameter Improved Particle Swarm Optimization (MPIPSO) algorithm which is a more enhanced version of PSO is developed. Findings: Since the converter output voltage’s integral squared error (ISE) has been chosen as a neutral function, the optimal PI controller design may be expressed in terms of optimization problems. Originality/Value: The superiority of the proposed MPIPSO based sliding mode controller has been shown by comparing the results with other existing MH optimization methodologies.
{"title":"A Novel Modified Adaptive Controller Design for Non Negative DC-DC Converter Using Meta-Heuristic Algorithms for Bio Medical Hybrid Application","authors":"M. Moses, S. Rajarajacholan","doi":"10.1166/jmihi.2022.3929","DOIUrl":"https://doi.org/10.1166/jmihi.2022.3929","url":null,"abstract":"Purpose: Meta-heuristic (MH) methods are used to develop an adaptive sliding mode controller for a POEL converter. MH algorithms have been used to address a variety of engineering optimization problems. Which will use for Bio medical hybrid systems applications. Design/Methodology:\u0000 Particle Swarm Optimization (PSO) approach is well known and it could expedite the convergence characteristic in numerous applications. By means of amending PSO parameters like, inertia mass, social and perceptive agents at every generation, Modern Parameter Improved Particle Swarm Optimization\u0000 (MPIPSO) algorithm which is a more enhanced version of PSO is developed. Findings: Since the converter output voltage’s integral squared error (ISE) has been chosen as a neutral function, the optimal PI controller design may be expressed in terms of optimization problems. Originality/Value:\u0000 The superiority of the proposed MPIPSO based sliding mode controller has been shown by comparing the results with other existing MH optimization methodologies.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"197 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115256402","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}
Diabetic Retinopathy (DR) is a critical abnormality in the retina mainly caused by diabetes. The early diagnosis of DR is essential to avoid painless blindness. The conventional DR diagnosis is manual and requires skilled Ophthalmologists. The Ophthalmologist’s analyses are subjective to inconsistency and record maintenance issues. Hence, there is a need for other DR diagnosis methods. In this paper, we proposed an AdaBoost algorithm-based ensemble classification approach to classify DR grades. The major objective of the proposed approach is an enhancement of DR classification performance by using optimized features and ensemble machine learning techniques. The proposed method classifies different grades of DR using the Meyer wavelet and retinal vessel-based features extracted from multiple regions of interest of the retina. To improve the predictive accuracy, we used a Bayesian algorithm to optimize the hyper-parameters of the proposed ensemble classifier. The proposed DR grading model was constructed and evaluated by using the MESSIDOR fundus image dataset. In evaluation experiment, the classification outcome of the proposed approach was evaluated by the confusion matrix and receiver operating characteristic (ROC) based metrics. The evaluation experiments show that the proposed approach attained 99.2% precision, 98.2% recall, 99% accuracy, and 0.99 AUC. The experimental findings also indicate that the proposed approach’s classification outcome is significantly better than that of state of art DR classification methods.
{"title":"Optimized Ensemble Machine Learning-Based Diabetic Retinopathy Grading Using Multiple Region of Interest Analysis and Bayesian Approach","authors":"W. Nancy, A. C. Kavida","doi":"10.1166/jmihi.2022.3923","DOIUrl":"https://doi.org/10.1166/jmihi.2022.3923","url":null,"abstract":"Diabetic Retinopathy (DR) is a critical abnormality in the retina mainly caused by diabetes. The early diagnosis of DR is essential to avoid painless blindness. The conventional DR diagnosis is manual and requires skilled Ophthalmologists. The Ophthalmologist’s analyses are subjective\u0000 to inconsistency and record maintenance issues. Hence, there is a need for other DR diagnosis methods. In this paper, we proposed an AdaBoost algorithm-based ensemble classification approach to classify DR grades. The major objective of the proposed approach is an enhancement of DR classification\u0000 performance by using optimized features and ensemble machine learning techniques. The proposed method classifies different grades of DR using the Meyer wavelet and retinal vessel-based features extracted from multiple regions of interest of the retina. To improve the predictive accuracy, we\u0000 used a Bayesian algorithm to optimize the hyper-parameters of the proposed ensemble classifier. The proposed DR grading model was constructed and evaluated by using the MESSIDOR fundus image dataset. In evaluation experiment, the classification outcome of the proposed approach was evaluated\u0000 by the confusion matrix and receiver operating characteristic (ROC) based metrics. The evaluation experiments show that the proposed approach attained 99.2% precision, 98.2% recall, 99% accuracy, and 0.99 AUC. The experimental findings also indicate that the proposed approach’s classification\u0000 outcome is significantly better than that of state of art DR classification methods.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123571448","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：