A novel algorithm for classification of SPECT images of a human heart

2002 ◽  
Author(s):  
K.J. Cios ◽  
L.S. Goodenday ◽  
K.K. Shah ◽  
G. Serpen
Keyword(s):  
Human Heart ◽  
Novel Algorithm ◽  
Spect Images

A Study on the Auxiliary Diagnosis of Thyroid Disease Images Based on Multiple Dimensional Deep Learning Algorithms

2020 ◽  
Vol 16 (3) ◽  
pp. 199-205
Author(s):  
Yuejun Liu ◽  
Yifei Xu ◽  
Xiangzheng Meng ◽  
Xuguang Wang ◽  
Tianxu Bai
Keyword(s):  
Deep Learning ◽  
Learning Algorithms ◽  
Region Of Interest ◽  
Classification Performance ◽  
Thyroid Diseases ◽  
Great Success ◽  
Learning Models ◽  
Good Classification Performance ◽  
Spect Images

Background: Medical imaging plays an important role in the diagnosis of thyroid diseases. In the field of machine learning, multiple dimensional deep learning algorithms are widely used in image classification and recognition, and have achieved great success. Objective: The method based on multiple dimensional deep learning is employed for the auxiliary diagnosis of thyroid diseases based on SPECT images. The performances of different deep learning models are evaluated and compared. Methods: Thyroid SPECT images are collected with three types, they are hyperthyroidism, normal and hypothyroidism. In the pre-processing, the region of interest of thyroid is segmented and the amount of data sample is expanded. Four CNN models, including CNN, Inception, VGG16 and RNN, are used to evaluate deep learning methods. Results: Deep learning based methods have good classification performance, the accuracy is 92.9%-96.2%, AUC is 97.8%-99.6%. VGG16 model has the best performance, the accuracy is 96.2% and AUC is 99.6%. Especially, the VGG16 model with a changing learning rate works best. Conclusion: The standard CNN, Inception, VGG16, and RNN four deep learning models are efficient for the classification of thyroid diseases with SPECT images. The accuracy of the assisted diagnostic method based on deep learning is higher than that of other methods reported in the literature.

scholarly journals The Application of Deep Learning for the Classification of Internal Human Cardiac Anatomy

2018 ◽  
Author(s):  
Erik Gaasedelen ◽  
Alex Deakyne ◽  
Paul Iaizzo
Keyword(s):  
Deep Learning ◽  
Surgical Procedures ◽  
Electrical Conduction ◽  
Human Heart ◽  
Cardiac Anatomy ◽  
Non Invasive ◽  
Spatial Environment ◽  
The Creation

The applications of sensing and localization are becoming more sophisticated in many invasive and non-invasive surgical procedures and there is great interest to apply them to the human heart. Ideally, such tools could be indispensable for allowing physicians to spatially understand relative tissue morphologies and their associated electrical conduction. Yet today there remains a steep divide between the creation of spatial environment models and the contextual understandings of adjacent features. To begin to address this, we explore the problem of anatomical perception by applying deep learning to the identification of internal cardiac anatomy images.

Classification of SPECT Images Using Clustering Techniques Revisited

2009 ◽  
pp. 168-178 ◽  
Author(s):  
J. M. Górriz ◽  
J. Ramírez ◽  
A. Lassl ◽  
I. Álvarez ◽  
F. Segovia ◽  
...  
Keyword(s):  
Clustering Techniques ◽  
Spect Images

Automatic classification of 123I-FP-CIT (DaTSCAN) SPECT images

2011 ◽  
Vol 32 (8) ◽  
pp. 699-707 ◽  
Author(s):  
David J. Towey ◽  
Peter G. Bain ◽  
Kuldip S. Nijran
Keyword(s):  
Automatic Classification ◽  
Spect Images

scholarly journals Segmentation and Classification of Heart Angiographic Images Using Machine Learning Techniques

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Abdullah ◽  
Muhammad Hameed Siddiqi ◽  
Yousef Salamah Alhwaiti ◽  
Ibrahim Alrashdi ◽  
Amjad Ali ◽  
...  
Keyword(s):  
Blood Vessels ◽  
Human Heart ◽  
Automatic Segmentation ◽  
Ensemble Classification ◽  
Machine Learning Techniques ◽  
Computer Assisted ◽  
Time Saving ◽  
Significant Information ◽  
Heart Blood

Heart angiography is a test in which the concerned medical specialist identifies the abnormality in heart vessels. This type of diagnosis takes a lot of time by the concerned physician. In our proposed method, we segmented the interested regions of heart vessels and then classified. Segmentation and classification of heart angiography provides significant information for the physician as well as patient. Contradictorily, in the mention domain of heart angiography, the charge is prone to error, phase overwhelming, and thought-provoking task for the physician (heart specialist). An automatic segmentation and classification of heart blood vessels descriptions can improve the truthfulness and speed up the finding of heart illnesses. In this work, we recommend a computer-assisted conclusion arrangement for the localization of human heart blood vessels within heart angiographic imageries by using multiclass ensemble classification mechanism. In the proposed work, the heart blood vessels will be first segmented, and the various features according to accuracy have been extracted. Low-level features such as texture, statistical, and geometrical features were extracted in human heart blood vessels. At last, in the proposed framework, heart blood vessels have been categorized in their four respective classes including normal, block, narrow, and blood flow-reduced vessels. The proposed approach has achieved best result which provides very useful, easy, accurate, and time-saving environment to cardiologists for the diagnosis of heart-related diseases.

scholarly journals Texture classification of fabric defects using machine learning

2020 ◽  
Vol 10 (4) ◽  
pp. 4390
Author(s):  
Yassine Ben Salem ◽  
Mohamed Naceur Abdelkrim
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Comparative Study ◽  
Texture Classification ◽  
Support Vector ◽  
Defect Classification ◽  
Analysis Method ◽  
Fabric Defect ◽  
Novel Algorithm

In this paper, a novel algorithm for automatic fabric defect classification was proposed, based on the combination of a texture analysis method and a support vector machine SVM. Three texture methods were used and compared, GLCM, LBP, and LPQ. They were combined with SVM’s classifier. The system has been tested using TILDA database. A comparative study of the performance and the running time of the three methods was carried out. The obtained results are interesting and show that LBP is the best method for recognition and classification and it proves that the SVM is a suitable classifier for such problems. We demonstrate that some defects are easier to classify than others.

A novel algorithm for defect extraction and classification of mobile phone screen based on machine vision

2020 ◽  
Vol 146 ◽  
pp. 106530 ◽  
Author(s):  
Changsheng Li ◽  
Xianmin Zhang ◽  
Yanjiang Huang ◽  
Chuangang Tang ◽  
Sergej Fatikow
Keyword(s):  
Machine Vision ◽  
Mobile Phone ◽  
Defect Extraction ◽  
Novel Algorithm
Sign in / Sign up

Export Citation Format

Share Document