Semi-supervised Method for Image Texture Classification of Pituitary Tumors via CycleGAN and Optimized Feature Extraction

Abstract Background: Accurately determining the softness level of pituitary tumors preoperatively by using their image textures can provide a basis for surgical options and prognosis. Existing methods for this problem require manual intervention, which could hinder the efficiency and accuracy considerably. Methods: we present an automatic method for diagnosing the texture of pituitary tumors using unbalanced sequence image data. Firstly, for the small sample problem in our pituitary tumor MRI image dataset where T1 and T2 sequence data are unbalanced (due to data missing) and under-sampled, our method uses a CycleGAN model for domain conversion to obtain fully sampled MRI spatial sequence. Then, it uses a DenseNet-ResNet based Autoencoder framework to optimize the feature extraction process for pituitary tumor image data. Finally, to take advantage of sequence data, it uses a CRNN model to classify pituitary tumors based on their predicted softness levels. Results: Experiments show that our method is the best in terms of efficiency and accuracy(91.78%) compared to other methods. Conclusions: We propose a semi-supervised method for grading pituitary tumor texture. This method can accurately determine the softness level of pituitary tumors, which provides convenience for surgical selection and prognosis, and improves the diagnostic efficiency of pituitary tumors.

Download Full-text

Semi-supervised method for image texture classification of pituitary tumors via CycleGAN and optimized feature extraction

BMC Medical Informatics and Decision Making ◽

10.1186/s12911-020-01230-x ◽

2020 ◽

Vol 20 (1) ◽

Author(s):

Hong Zhu ◽

Qianhao Fang ◽

Yihe Huang ◽

Kai Xu

Keyword(s):

Feature Extraction ◽

Pituitary Tumor ◽

Sequence Data ◽

Texture Classification ◽

Pituitary Tumors ◽

Image Data ◽

Extraction Process ◽

Small Sample ◽

Image Texture ◽

Diagnostic Efficiency

Abstract Background Accurately determining the softness level of pituitary tumors preoperatively by using their image textures can provide a basis for surgical options and prognosis. Existing methods for this problem require manual intervention, which could hinder the efficiency and accuracy considerably. Methods We present an automatic method for diagnosing the texture of pituitary tumors using unbalanced sequence image data. Firstly, for the small sample problem in our pituitary tumor MRI image dataset where T1 and T2 sequence data are unbalanced (due to data missing) and under-sampled, our method uses a CycleGAN (Cycle-Consistent Adversarial Networks) model for domain conversion to obtain fully sampled MRI spatial sequence. Then, it uses a DenseNet (Densely Connected Convolutional Networks)-ResNet(Deep Residual Networks) based Autoencoder framework to optimize the feature extraction process for pituitary tumor image data. Finally, to take advantage of sequence data, it uses a CRNN (Convolutional Recurrent Neural Network) model to classify pituitary tumors based on their predicted softness levels. Results Experiments show that our method is the best in terms of efficiency and accuracy (91.78%) compared to other methods. Conclusions We propose a semi-supervised method for grading pituitary tumor texture. This method can accurately determine the softness level of pituitary tumors, which provides convenience for surgical selection and prognosis, and improves the diagnostic efficiency of pituitary tumors.

Download Full-text

Semi-supervised Method for Image Texture Classification of Pituitary Tumors via CycleGAN and Optimized Feature Extraction

10.21203/rs.2.18161/v1 ◽

2019 ◽

Author(s):

Hong ZHU ◽

Qianhao FANG ◽

Yihe HUANG ◽

Kai XU

Keyword(s):

Feature Extraction ◽

Pituitary Tumor ◽

Sequence Data ◽

Texture Classification ◽

Pituitary Tumors ◽

Image Data ◽

Extraction Process ◽

Small Sample ◽

Image Texture ◽

Diagnostic Efficiency

Abstract Background: Accurately determining the softness level of pituitary tumors preoperatively by using their image textures can provide a basis for surgical options and prognosis. Existing methods for this problem require manual intervention, which could hinder the efficiency and accuracy considerably.Methods: we present an automatic method for diagnosing the texture of pituitary tumors using unbalanced sequence image data. Firstly, for the small sample problem in our pituitary tumor MRI image dataset where T1 and T2 sequence data are unbalanced (due to data missing) and under-sampled, our method uses a CycleGAN model for domain conversion to obtain fully sampled MRI spatial sequence. Then, it uses a DenseNet-ResNet based Autoencoder framework to optimize the feature extraction process for pituitary tumor image data. Finally, to take advantage of sequence data, it uses a CRNN model to classify pituitary tumors based on their predicted softness levels.Results: Experiments show that our method is the best in terms of efficiency and accuracy(91.78%) compared to other methods.Conclusions: We propose a semi-supervised method for grading pituitary tumor texture. This method can accurately determine the softness level of pituitary tumors, which provides convenience for surgical selection and prognosis, and improves the diagnostic efficiency of pituitary tumors.

Download Full-text

Semi-supervised Method for Image Texture Classification of Pituitary Tumors via CycleGAN and Optimized Feature Extraction

10.21203/rs.2.18161/v5 ◽

2020 ◽

Author(s):

Hong ZHU ◽

Qianhao FANG ◽

Yihe HUANG ◽

Kai XU

Keyword(s):

Feature Extraction ◽

Pituitary Tumor ◽

Sequence Data ◽

Texture Classification ◽

Pituitary Tumors ◽

Image Data ◽

Extraction Process ◽

Small Sample ◽

Image Texture ◽

Diagnostic Efficiency

Download Full-text

Semi-supervised Method for Image Texture Classification of Pituitary Tumors via CycleGAN and Optimized Feature Extraction

10.21203/rs.2.18161/v3 ◽

2020 ◽

Author(s):

Hong ZHU ◽

Qianhao FANG ◽

Yihe HUANG ◽

Kai XU

Keyword(s):

Feature Extraction ◽

Pituitary Tumor ◽

Sequence Data ◽

Texture Classification ◽

Pituitary Tumors ◽

Image Data ◽

Extraction Process ◽

Small Sample ◽

Image Texture ◽

Diagnostic Efficiency

Abstract Background: Accurately determining the softness level of pituitary tumors preoperatively by using their image textures can provide a basis for surgical options and prognosis. Existing methods for this problem require manual intervention, which could hinder the efficiency and accuracy considerably. Methods: we present an automatic method for diagnosing the texture of pituitary tumors using unbalanced sequence image data. Firstly, for the small sample problem in our pituitary tumor MRI image dataset where T1 and T2 sequence data are unbalanced (due to data missing) and under-sampled, our method uses a CycleGAN(Cycle-Consistent Adversarial Networks) model for domain conversion to obtain fully sampled MRI spatial sequence. Then, it uses a DenseNet(Densely Connected Convolutional Networks)-ResNet(Deep Residual Networks) based Autoencoder framework to optimize the feature extraction process for pituitary tumor image data. Finally, to take advantage of sequence data, it uses a CRNN(Convolutional Recurrent Neural Network) model to classify pituitary tumors based on their predicted softness levels. Results: Experiments show that our method is the best in terms of efficiency and accuracy(91.78%) compared to other methods. Conclusions: We propose a semi-supervised method for grading pituitary tumor texture. This method can accurately determine the softness level of pituitary tumors, which provides convenience for surgical selection and prognosis, and improves the diagnostic efficiency of pituitary tumors.

Download Full-text

Semi-supervised Method for Image Texture Classification of Pituitary Tumors via CycleGAN and Optimized Feature Extraction

10.21203/rs.2.18161/v4 ◽

2020 ◽

Author(s):

Hong ZHU ◽

Qianhao FANG ◽

Yihe HUANG ◽

Kai XU

Keyword(s):

Feature Extraction ◽

Pituitary Tumor ◽

Sequence Data ◽

Texture Classification ◽

Pituitary Tumors ◽

Image Data ◽

Extraction Process ◽

Small Sample ◽

Image Texture ◽

Diagnostic Efficiency

Abstract Background: Accurately determining the softness level of pituitary tumors preoperatively by using their image textures can provide a basis for surgical options and prognosis. Existing methods for this problem require manual intervention, which could hinder the efficiency and accuracy considerably. Methods: we present an automatic method for diagnosing the texture of pituitary tumors using unbalanced sequence image data. Firstly, for the small sample problem in our pituitary tumor MRI image dataset where T1 and T2 sequence data are unbalanced (due to data missing) and under-sampled, our method uses a CycleGAN(Cycle-Consistent Adversarial Networks) model for domain conversion to obtain fully sampled MRI spatial sequence. Then, it uses a DenseNet(Densely Connected Convolutional Networks)-ResNet(Deep Residual Networks) based Autoencoder framework to optimize the feature extraction process for pituitary tumor image data. Finally, to take advantage of sequence data, it uses a CRNN(Convolutional Recurrent Neural Network) model to classify pituitary tumors based on their predicted softness levels. Results: Experiments show that our method is the best in terms of efficiency and accuracy(91.78%) compared to other methods. Conclusions: We propose a semi-supervised method for grading pituitary tumor texture. This method can accurately determine the softness level of pituitary tumors, which provides convenience for surgical selection and prognosis, and improves the diagnostic efficiency of pituitary tumors.

Download Full-text

A Novel Wavelet Packet Transform Based Feature Extraction Algorithm For Image Texture Classification

TENCON 2005 - 2005 IEEE Region 10 Conference ◽

10.1109/tencon.2005.301130 ◽

2005 ◽

Author(s):

S. Selvan ◽

S. Ramakrishnan

Keyword(s):

Feature Extraction ◽

Texture Classification ◽

Wavelet Packet ◽

Wavelet Packet Transform ◽

Image Texture ◽

Feature Extraction Algorithm ◽

Extraction Algorithm

Download Full-text

Feature Extraction for Image Texture Classification

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.b1078.1292s419 ◽

2019 ◽

Vol 9 (2S4) ◽

pp. 70-73

Keyword(s):

Feature Extraction ◽

Texture Classification ◽

Great Part ◽

Model System ◽

Image Texture ◽

System Use ◽

Critical Activity ◽

Taking Care

Surface request accept a critical activity in PC vision and picture taking care of utilizations. We propose an approach to manage concentrate picture features for surface portrayal. This procedure for removing picture features for request of surfaces is solid to picture insurgency, less sensitive to histogram leveling and bustle. It includes two courses of action of picture features: overpowering close-by twofold models (DLBP) in a surface picture and the beneficial features expelled by using circularly symmetric Gabor channel responses. The predominant close-by twofold model system use the most a great part of the time happened guide to find hypnotizing textural information, while the Gabor-based features go for giving additional overall textural information to the DLBP features

Download Full-text

Expression of HIF-1a and VEGF in human pituitary tumors and rodent pituitary tumor cell lines under hypoxia-mimicking condition

Experimental and Clinical Endocrinology & Diabetes ◽

10.1055/s-0028-1096352 ◽

2008 ◽

Vol 116 (09) ◽

Author(s):

B Shan ◽

C Onofri ◽

M Theodoropoulou ◽

E Arzt ◽

GK Stalla ◽

...

Keyword(s):

Tumor Cell ◽

Cell Lines ◽

Pituitary Tumor ◽

Pituitary Tumors ◽

Tumor Cell Lines ◽

Human Pituitary ◽

Pituitary Tumor Cell

Download Full-text

CNN performance dependence on linear image processing

Electronic Imaging ◽

10.2352/issn.2470-1173.2020.10.ipas-182 ◽

2020 ◽

Vol 2020 (10) ◽

pp. 310-1-310-7

Author(s):

Khalid Omer ◽

Luca Caucci ◽

Meredith Kupinski

Keyword(s):

Image Processing ◽

Texture Classification ◽

Full Rank ◽

Detection Performance ◽

Ideal Observer ◽

Training Data ◽

Image Texture ◽

Training Images ◽

Analytic Expressions ◽

Linear Compression

This work reports on convolutional neural network (CNN) performance on an image texture classification task as a function of linear image processing and number of training images. Detection performance of single and multi-layer CNNs (sCNN/mCNN) are compared to optimal observers. Performance is quantified by the area under the receiver operating characteristic (ROC) curve, also known as the AUC. For perfect detection AUC = 1.0 and AUC = 0.5 for guessing. The Ideal Observer (IO) maximizes AUC but is prohibitive in practice because it depends on high-dimensional image likelihoods. The IO performance is invariant to any fullrank, invertible linear image processing. This work demonstrates the existence of full-rank, invertible linear transforms that can degrade both sCNN and mCNN even in the limit of large quantities of training data. A subsequent invertible linear transform changes the images’ correlation structure again and can improve this AUC. Stationary textures sampled from zero mean and unequal covariance Gaussian distributions allow closed-form analytic expressions for the IO and optimal linear compression. Linear compression is a mitigation technique for high-dimension low sample size (HDLSS) applications. By definition, compression strictly decreases or maintains IO detection performance. For small quantities of training data, linear image compression prior to the sCNN architecture can increase AUC from 0.56 to 0.93. Results indicate an optimal compression ratio for CNN based on task difficulty, compression method, and number of training images.

Download Full-text

Handwritten Balinesse Character Recognition using K-Nearest Neighbor

10.31227/osf.io/z6m8u ◽

2018 ◽

Author(s):

I Wayan Agus Surya Darma

Keyword(s):

Feature Extraction ◽

Success Rate ◽

Character Recognition ◽

Nearest Neighbor ◽

Recognition System ◽

Extraction Process ◽

K Nearest Neighbor ◽

Nearest Neighbor Algorithm ◽

K Nearest Neighbor Algorithm ◽

Character Feature

Balinese character recognition is a technique to recognize feature or pattern of Balinese character. Feature of Balinese character is generated through feature extraction process. This research using handwritten Balinese character. Feature extraction is a process to obtain the feature of character. In this research, feature extraction process generated semantic and direction feature of handwritten Balinese character. Recognition is using K-Nearest Neighbor algorithm to recognize 81 handwritten Balinese character. The feature of Balinese character images tester are compared with reference features. Result of the recognition system with K=3 and reference=10 is achieved a success rate of 97,53%.

Download Full-text