scholarly journals Content Based Medical Image Retrieval for Accurate Disease Diagnosis

2021 ◽  
Vol 15 (1) ◽  
pp. 235-248
Author(s):  
Mayank R. Kapadia ◽  
Chirag N. Paunwala
Keyword(s):  
Image Retrieval ◽  
Performance Metrics ◽  
The Other ◽  
X Ray ◽  
Proposed Model ◽  
Chest Disease ◽  
Minimum Number ◽  
Medical Dataset ◽  
Precision Rate ◽  
Better Than

Introduction: Content Based Image Retrieval (CBIR) system is an innovative technology to retrieve images from various media types. One of the CBIR applications is Content Based Medical Image Retrieval (CBMIR). The image retrieval system retrieves the most similar images from the historical cases, and such systems can only support the physician's decision to diagnose a disease. To extract the useful features from the query image for linking similar types of images is the major challenge in the CBIR domain. The Convolution Neural Network (CNN) can overcome the drawbacks of traditional algorithms, dependent on the low-level feature extraction technique. Objective: The objective of the study is to develop a CNN model with a minimum number of convolution layers and to get the maximum possible accuracy for the CBMIR system. The minimum number of convolution layers reduces the number of mathematical operations and the time for the model's training. It also reduces the number of training parameters, like weights and bias. Thus, it reduces the memory requirement for the model storage. This work mainly focused on developing an optimized CNN model for the CBMIR system. Such systems can only support the physicians' decision to diagnose a disease from the images and retrieve the relevant cases to help the doctor decide the precise treatment. Methods: The deep learning-based model is proposed in this paper. The experiment is done with several convolution layers and various optimizers to get the maximum accuracy with a minimum number of convolution layers. Thus, the ten-layer CNN model is developed from scratch and used to derive the training and testing images' features and classify the test image. Once the image class is identified, the most relevant images are determined based on the Euclidean distance between the query features and database features of the identified class. Based on this distance, the most relevant images are displayed from the respective class of images. The general dataset CIFAR10, which has 60,000 images of 10 different classes, and the medical dataset IRMA, which has 2508 images of 9 various classes, have been used to analyze the proposed method. The proposed model is also applied for the medical x-ray image dataset of chest disease and compared with the other pre-trained models. Results: The accuracy and the average precision rate are the measurement parameters utilized to compare the proposed model with different machine learning techniques. The accuracy of the proposed model for the CIFAR10 dataset is 93.9%, which is better than the state-of-the-art methods. After the success for the general dataset, the model is also tested for the medical dataset. For the x-ray images of the IRMA dataset, it is 86.53%, which is better than the different pre-trained model results. The model is also tested for the other x-ray dataset, which is utilized to identify chest-related disease. The average precision rate for such a dataset is 97.25%. Also, the proposed model fulfills the major challenge of the semantic gap. The semantic gap of the proposed model for the chest disease dataset is 2.75%, and for the IRMA dataset, it is 13.47%. Also, only ten convolution layers are utilized in the proposed model, which is very small in number compared to the other pre-trained models. Conclusion: The proposed technique shows remarkable improvement in performance metrics over CNN-based state-of-the-art methods. It also offers a significant improvement in performance metrics over different pre-trained models for the two different medical x-ray image datasets.

scholarly journals Content Based Medical Image Retrieval for Accurate Disease Diagnosis

2021 ◽  
Vol 15 (1) ◽  
pp. 236-249
Author(s):  
Mayank R. Kapadia ◽  
Chirag N. Paunwala
Keyword(s):  
Image Retrieval ◽  
Performance Metrics ◽  
The Other ◽  
X Ray ◽  
Proposed Model ◽  
Chest Disease ◽  
Minimum Number ◽  
Medical Dataset ◽  
Precision Rate ◽  
Better Than

Introduction: Content Based Image Retrieval (CBIR) system is an innovative technology to retrieve images from various media types. One of the CBIR applications is Content Based Medical Image Retrieval (CBMIR). The image retrieval system retrieves the most similar images from the historical cases, and such systems can only support the physician's decision to diagnose a disease. To extract the useful features from the query image for linking similar types of images is the major challenge in the CBIR domain. The Convolution Neural Network (CNN) can overcome the drawbacks of traditional algorithms, dependent on the low-level feature extraction technique. Objective: The objective of the study is to develop a CNN model with a minimum number of convolution layers and to get the maximum possible accuracy for the CBMIR system. The minimum number of convolution layers reduces the number of mathematical operations and the time for the model's training. It also reduces the number of training parameters, like weights and bias. Thus, it reduces the memory requirement for the model storage. This work mainly focused on developing an optimized CNN model for the CBMIR system. Such systems can only support the physicians' decision to diagnose a disease from the images and retrieve the relevant cases to help the doctor decide the precise treatment. Methods: The deep learning-based model is proposed in this paper. The experiment is done with several convolution layers and various optimizers to get the maximum accuracy with a minimum number of convolution layers. Thus, the ten-layer CNN model is developed from scratch and used to derive the training and testing images' features and classify the test image. Once the image class is identified, the most relevant images are determined based on the Euclidean distance between the query features and database features of the identified class. Based on this distance, the most relevant images are displayed from the respective class of images. The general dataset CIFAR10, which has 60,000 images of 10 different classes, and the medical dataset IRMA, which has 2508 images of 9 various classes, have been used to analyze the proposed method. The proposed model is also applied for the medical x-ray image dataset of chest disease and compared with the other pre-trained models. Results: The accuracy and the average precision rate are the measurement parameters utilized to compare the proposed model with different machine learning techniques. The accuracy of the proposed model for the CIFAR10 dataset is 93.9%, which is better than the state-of-the-art methods. After the success for the general dataset, the model is also tested for the medical dataset. For the x-ray images of the IRMA dataset, it is 86.53%, which is better than the different pre-trained model results. The model is also tested for the other x-ray dataset, which is utilized to identify chest-related disease. The average precision rate for such a dataset is 97.25%. Also, the proposed model fulfills the major challenge of the semantic gap. The semantic gap of the proposed model for the chest disease dataset is 2.75%, and for the IRMA dataset, it is 13.47%. Also, only ten convolution layers are utilized in the proposed model, which is very small in number compared to the other pre-trained models. Conclusion: The proposed technique shows remarkable improvement in performance metrics over CNN-based state-of-the-art methods. It also offers a significant improvement in performance metrics over different pre-trained models for the two different medical x-ray image datasets.

scholarly journals Both Freud and Hoffman are Right: Anxious-Aggressive and Empathic Dimensions of Guilt

2008 ◽  
Vol 11 (1) ◽  
pp. 159-171 ◽  
Author(s):  
Itziar Etxebarria ◽  
Pedro Apodaca
Keyword(s):  
Young Adults ◽  
Subjective Experience ◽  
Negative Emotions ◽  
The Other ◽  
Point Scale ◽  
Nested Models ◽  
Proposed Model ◽  
Better Than

The purpose of the study was to confirm a model which proposed two basic dimensions in the subjective experience of guilt, one anxious-aggressive and the other empathic, as well as another dimension associated but not intrinsic to it, namely, the associated negative emotions dimension. Participants were 360 adolescents, young adults and adults of both sexes. They were asked to relate one of the situations that most frequently caused them to experience feelings of guilt and to specify its intensity and that of 9 other emotions that they may have experienced, to a greater or lesser extent, at the same time on a 7-point scale. The proposed model was shown to adequately fit the data and to be better than other alternative nested models. This result supports the views of both Freud and Hoffman regarding the nature of guilt, contradictory only at a first glance.

A Dynamically Optimized Fluctuation Smoothing Rule for Scheduling Jobs in a Wafer Fabrication Factory

2011 ◽  
Vol 7 (4) ◽  
pp. 47-64 ◽  
Author(s):  
Toly Chen
Keyword(s):  
Standard Deviation ◽  
Test Data ◽  
Cycle Time ◽  
Performance Metrics ◽  
The Other ◽  
Wafer Fabrication ◽  
Fluctuation Smoothing ◽  
Time Standard ◽  
Nonlinear Fluctuation ◽  
Better Than

This paper presents a dynamically optimized fluctuation smoothing rule to improve the performance of scheduling jobs in a wafer fabrication factory. The rule has been modified from the four-factor bi-criteria nonlinear fluctuation smoothing (4f-biNFS) rule, by dynamically adjusting factors. Some properties of the dynamically optimized fluctuation smoothing rule were also discussed theoretically. In addition, production simulation was also applied to generate some test data for evaluating the effectiveness of the proposed methodology. According to the experimental results, the proposed methodology was better than some existing approaches to reduce the average cycle time and cycle time standard deviation. The results also showed that it was possible to improve the performance of one without sacrificing the other performance metrics.

scholarly journals Novel Privacy Preserving Non-Invasive Sensing-Based Diagnoses of Pneumonia Disease Leveraging Deep Network Model

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 461
Author(s):  
Mujeeb Ur Rehman ◽  
Arslan Shafique ◽  
Kashif Hesham Khan ◽  
Sohail Khalid ◽  
Abdullah Alhumaidi Alotaibi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Medical Records ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
X Ray ◽  
Non Invasive ◽  
Proposed Model ◽  
Pneumonia Diagnosis ◽  
Better Than

This article presents non-invasive sensing-based diagnoses of pneumonia disease, exploiting a deep learning model to make the technique non-invasive coupled with security preservation. Sensing and securing healthcare and medical images such as X-rays that can be used to diagnose viral diseases such as pneumonia is a challenging task for researchers. In the past few years, patients’ medical records have been shared using various wireless technologies. The wireless transmitted data are prone to attacks, resulting in the misuse of patients’ medical records. Therefore, it is important to secure medical data, which are in the form of images. The proposed work is divided into two sections: in the first section, primary data in the form of images are encrypted using the proposed technique based on chaos and convolution neural network. Furthermore, multiple chaotic maps are incorporated to create a random number generator, and the generated random sequence is used for pixel permutation and substitution. In the second part of the proposed work, a new technique for pneumonia diagnosis using deep learning, in which X-ray images are used as a dataset, is proposed. Several physiological features such as cough, fever, chest pain, flu, low energy, sweating, shaking, chills, shortness of breath, fatigue, loss of appetite, and headache and statistical features such as entropy, correlation, contrast dissimilarity, etc., are extracted from the X-ray images for the pneumonia diagnosis. Moreover, machine learning algorithms such as support vector machines, decision trees, random forests, and naive Bayes are also implemented for the proposed model and compared with the proposed CNN-based model. Furthermore, to improve the CNN-based proposed model, transfer learning and fine tuning are also incorporated. It is found that CNN performs better than other machine learning algorithms as the accuracy of the proposed work when using naive Bayes and CNN is 89% and 97%, respectively, which is also greater than the average accuracy of the existing schemes, which is 90%. Further, K-fold analysis and voting techniques are also incorporated to improve the accuracy of the proposed model. Different metrics such as entropy, correlation, contrast, and energy are used to gauge the performance of the proposed encryption technology, while precision, recall, F1 score, and support are used to evaluate the effectiveness of the proposed machine learning-based model for pneumonia diagnosis. The entropy and correlation of the proposed work are 7.999 and 0.0001, respectively, which reflects that the proposed encryption algorithm offers a higher security of the digital data. Moreover, a detailed comparison with the existing work is also made and reveals that both the proposed models work better than the existing work.

scholarly journals Assessment of Level-3 Gridded Global Precipitation Mission (GPM) Products Over Oceans

2019 ◽  
Vol 11 (3) ◽  
pp. 255 ◽  
Author(s):  
Sana Khan ◽  
Viviana Maggioni
Keyword(s):  
Performance Metrics ◽  
Probability Of Detection ◽  
The Other ◽  
Coefficient Of Determination ◽  
Dual Frequency ◽  
Level 3 ◽  
The Times ◽  
Global Precipitation Mission ◽  
Global Precipitation ◽  
Better Than

The performance of Level-3 gridded Global Precipitation Mission (GPM)-based precipitation products (IMERG, Integrated Multi-satellite Retrievals for GPM) is assessed against two references over oceans: the OceanRAIN dataset, derived from oceanic shipboard disdrometers, and a satellite-based radar product (the Level-3 Dual-frequency Precipitation Radar, 3DPRD). Daily IMERG products (early, late, final) and microwave-only (MW) and Infrared-only (IR) precipitation components are evaluated at four different spatial resolutions (0.5°, 1°, 2°, and 3°) during a 3-year study period (March 2014–February 2017). Their performance is assessed based on both categorical and continuous performance metrics, including correlation coefficient, probability of detection, success ratio, bias, and root mean square error (RMSE). A triple collocation analysis (TCA) is also presented to further investigate the performance of these satellite-based products. Overall, the IMERG products show an underestimation with respect to OceanRAIN. Rain events in OceanRAIN are correctly detected by all IMERG products ~80% of the times. IR estimates show relatively large errors and low correlations with OceanRAIN compared to the other products. On the other hand, the MW component performs better than other products in terms of both categorical and continuous statistics. TCA reveals that 3DPRD performs consistently better than OceanRAIN in terms of RMSE and coefficient of determination at all spatial resolutions. This work is part of a larger effort to validate GPM products over nontraditional regions such as oceans.

COVID-19 Chest X-Ray Images Diagnosis: A Neutrosophic and Deep Transfer Learning Approach

2020 ◽  
Author(s):  
Nour Eldeen M. Khalifa ◽  
Florentin Smarandache ◽  
Mohamed Loey
Keyword(s):  
Deep Learning ◽  
Performance Metrics ◽  
World Health ◽  
Transfer Model ◽  
X Ray ◽  
Proposed Model ◽  
The World ◽  
Chest X Ray ◽  
Testing Accuracy ◽  
Transfer Models

Coronavirus, also known as COVID-19, has spread to several countries around the world. It was announced as a pandemic disease by The World Health Organization (WHO) in 2020 for its devastating impact on humans. With the advancements in computer science algorithms, the detection of this type of virus in the early stages is urgently needed for the fast recovery of patients. In this paper, a neutrosophic with a deep learning model for the detection of COVID-19 from chest X-ray medical digital images is presented. The proposed model relies on neutrosophic theory by converting the medical images from the grayscale spatial domain to the neutrosophic domain. The neutrosophic domain consists of three types of images and they are, the True (T) images, the Indeterminacy (I) images, and the Falsity (F) images. Using neutrosophic images has positively affected the accuracy of the proposed model. The dataset used in this research has been collected from different sources as there is no benchmark dataset for COVID-19 chest X-ray until the writing of this research. The dataset consists of four classes and they are COVID-19, Normal, Pneumonia bacterial, and Pneumonia virus. After the conversion to the neutrosophic domain, the images are fed into three different deep transfer models and they are Alexnet, Googlenet, and Restnet18. Those models are selected as they have a small number of layers on their architectures and they have been used with related work. To test the performance of the conversion to the neutrosophic domain, four scenarios have been tested. The first scenario is training the deep transfer models with True (T) neutrosophic images only. The second one is training on Indeterminacy (I) neutrosophic images, while the third scenario is training the deep models over the Falsity (F) neutrosophic images. The fourth scenario is training over the combined (T, I, F) neutrosophic images. According to the experimental results, the combined (T, I, F) neutrosophic images achieved the highest accuracy possible for the validation, testing and all performance metrics such Precision, Recall and F1 Score using Resnet18 as a deep transfer model. The proposed model achieved a testing accuracy with 78.70%. Furthermore, the proposed model using neutrosophic and Resnet18 had achieved superior testing accuracy with a related work which achieved 52.80% with the same experimental environmental setup and the same deep learning hyperparameters.

scholarly journals A Fast, Accurate and Easy to Implement Method for Pose Recognition of an Intramedullary Nail using a Tracked C-arm

2014 ◽  
Vol XL-5 ◽  
pp. 217-223 ◽  
Author(s):  
H. Esfandiari ◽  
S. Amiri ◽  
D.D. Lichti ◽  
C. Anglin
Keyword(s):  
Intramedullary Nail ◽  
Accuracy Assessment ◽  
Computation Time ◽  
X Ray ◽  
Main Challenge ◽  
Lower Radiation Dose ◽  
Minimum Number ◽  
Automated Technique ◽  
Orthopaedic Community ◽  
Better Than

A C-arm is a mobile X-ray device that is frequently used during orthopaedic surgeries. It consists of a semi-circular, arc-shaped arm that holds an X-ray transmitter at one end and an X-ray detector at the other. Intramedullary nail (IM nail) fixation is a popular orthopaedic surgery in which a metallic rod is placed into the patient's fractured bone (femur or tibia) and fixed using metal screws. The main challenge of IM-nail fixation surgery is to achieve the X-ray shot in which the distal holes of the IM nail appear as circles (desired view) so that the surgeon can easily insert the screws. Although C-arm X-ray devices are routinely used in IM-nail fixation surgeries, the surgeons or radiation technologists (rad-techs) usually use it in a trial-and-error manner. This method raises both radiation exposure and surgery time. In this study, we have designed and developed an IM-nail distal locking navigation technique that leads to more accurate and faster screw placement with a lower radiation dose and a minimum number of added steps to the operation to make it more accepted within the orthopaedic community. The specific purpose of this study was to develop and validate an automated technique for identifying the current pose of the IM nail relative to the C-arm. An accuracy assessment was performed to test the reliability of the navigation results. Translational accuracy was demonstrated to be better than 1 mm, roll and pitch rotations better than 2° and yaw rotational accuracy better than 2–5° depending on the separate angle. Computation time was less than 3.5 seconds.

scholarly journals COMPARISON BETWEEN DIFFERENT METHODS FOR IDENTIFYING LESION IN PULMONARY X-RAY IMAGES

2021 ◽  
Vol 03 (03) ◽  
pp. 77-86
Author(s):  
Rana M. HASAN ◽  
Ielaf O. Abdul MAJJED
Keyword(s):  
Image Retrieval ◽  
Retrieval System ◽  
Good Accuracy ◽  
Support Vector ◽  
X Ray ◽  
Learning Techniques ◽  
Image Retrieval System ◽  
Class Labels ◽  
Fully Connected ◽  
Better Than

The image retrieval system is one of the most prevalent and challenging systems of deep learning. To perform image retrieval for lung disease radiography systems, three methods were used: Firstly, we built a convolution neural network from scratch to extract and classify features by using six convolution layers and two fully connected layers. Secondly, it trained the feature patterns and classified categories by transfer learning techniques (Resnet_50). Thirdly, by training feature patterns by (inception V3) and classifying them by Support Vector Machine (SVM). After the system retrieval set of images depending on the class labels, these methods were compared to find the most accurate and fastest method among them. The concluded from the results of our proposed system that the accuracy of CNN from scratch was better than the learning methods (96.2%), but Resnet-50 was faster than the other methods and had good accuracy (94.81%).

scholarly journals Applications of Potassium Silicate Decrease Black Spot Infection in Rosa hybrida `Meipelta' (Fuschia Meidiland™)

HortScience ◽  
2003 ◽  
Vol 38 (6) ◽  
pp. 1144-1147 ◽  
Author(s):  
Jeffrey H. Gillman ◽  
David C. Zlesak ◽  
Jason A. Smith
Keyword(s):  
Irrigation Water ◽  
Black Spot ◽  
Daily Basis ◽  
Potassium Silicate ◽  
The Other ◽  
X Ray ◽  
Diplocarpon Rosae ◽  
Daily Schedule ◽  
Scanning Electron ◽  
Better Than

Roses in nursery and landscape settings are frequently damaged by black spot, whose causal agent is the fungus Diplocarpon rosae F.A. Wolf. Potassium silicate was assessed as a media-applied treatment for decreasing the severity and incidence of black spot infection. Roses were treated with 0, 50, 100, or 150 mg·L-1 silicon as potassium silicate incorporated into irrigation water on either a weekly or daily schedule. Five weeks after treatments were initiated, plants were inoculated with D. rosae. Roses began to show visual symptoms of infection §4 days later. Roses that had 150 mg·L-1 silicon applied on a daily schedule had significantly more silicon present in their leaves than other treatments as measured by scanning electron microscopy and energy-dispersive x-ray analysis. In addition, roses that had 100 and 150 mg·L-1 silicon applied on a daily schedule had fewer black spot lesions per leaf and fewer infected leaves than any of the other treatments by the end of the experiment 7 weeks later. Although roses treated with higher levels of silicon on a daily basis fared better than roses in the other treatments, all of the roses were heavily infected with D. rosae by the end of the study. The results reported here indicate that using potassium silicate in irrigation water may be a useful component of a disease management system.

Säure-Base-Eigenschaften des zyklischen Triamins N,N′,N″-Trimethyl-1,4,7-triazacyclononan: Die Kristallstruktur seiner monoprotonierten Form [C9H22N3]ClO4) / Acid-Base Properties of the Cyclic Triamine N,N′,N″-Trimethyl-1,4,7-triazacyclononane and Crystal Structure of its Monoprotonated Form [C9H22N3](ClO4)

1987 ◽  
Vol 42 (3) ◽  
pp. 279-281 ◽  
Author(s):  
K. Wieghardt ◽  
S. Brodka ◽  
K. Peters ◽  
E. M. Peters ◽  
A. Simon
Keyword(s):  
Crystal Structure ◽  
Hydrogen Bonds ◽  
Single Crystal ◽  
The Other ◽  
X Ray Diffraction ◽  
Acid Base ◽  
Amine Nitrogen ◽  
X Ray ◽  
Acidic Proton ◽  
Proposed Model

The crystal structure of the monohydroperchlorate of N,N',N"-trimethyl-1,4,7-triazacyclo-nonane, [C9H22N3](ClO4), has been determined by single crystal X-ray diffraction. The acidic proton of the cation is bonded to one amine nitrogen and it forms hydrogen bonds to the other two N-atoms in agreement with a proposed model, which has been invoked to interpret successive protonation constants of cyclic triamines. The salt [Me6[9]aneN3](BF4)3 has also been prepared

Sign in / Sign up

Export Citation Format

Share Document