Image Texture Features Research Articles

Optimized Swarm Enabled Deep Learning Technique for Bone Tumor Detection using Histopathological Image

Cancer subjugates a community that lacks proper care. It remains apparent that research studies enhance novel benchmarks in developing a computer-assisted tool for prognosis in radiology yet an indication of illness detection should be recognized by the pathologist. In bone cancer (BC), Identification of malignancy out of the BC’s histopathological image (HI) remains difficult because of the intricate structure of the bone tissue (BTe) specimen. This study proffers a new approach to diagnosing BC by feature extraction alongside classification employing deep learning frameworks. In this, the input is processed and segmented by Tsallis Entropy for noise elimination, image rescaling, and smoothening. The features are excerpted employing Efficient Net-based Convolutional Neural Network (CNN) Feature Extraction. ROI extraction will be employed to enhance the precise detection of atypical portions surrounding the affected area. Next, for classifying the accurate spotting and for grading the BTe as typical and a typical employing augmented XGBoost alongside Whale optimization (WOA). HIs gathering out of prevailing scales patients is acquired alongside texture characteristics of such images remaining employed for training and testing the Neural Network (NN). These classification outcomes exhibit that NN possesses a hit ratio of 99.48 percent while this occurs in BT classification.

Detection of the storage time of light bruises in yellow peaches based on spectrum and texture features of hyperspectral image

AbstractYellow peaches are soft, and they bruise easily; the bruised areas of them are prone to breed bacteria and molds, so the consumption and the safety of related products of yellow peaches are affected by the difference in the storage time of light bruises in them. In order to accurately distinguish of the storage time of light bruises in yellow peaches, the spectra of the sample bruised region were combined with texture features extracted based on gray‐level co‐occurrence matrix (GLCM), and the deep learning algorithm was used for modeling. A total of 80 samples were prepared in the experiment, and the hyperspectral images of them were acquired at four time periods (2, 8, 24, and 48 h), and the reflection spectral data as well as the texture features of the bruised samples were extracted from the hyperspectral images. First, the random forest (RF) and extreme gradient boosting (XGBoost) models were built based on spectral, texture, and spectral features combined with texture features (Feature Fusion 1), respectively, and the best model discrimination was the RF model under Feature Fusion 1, with an overall accuracy of 98.33%. In order to remove the redundant information of spectrum, the UVE and CARS algorithms were used to screen the normalized spectral feature data, and then, the texture features were combined again (Feature Fusion 2), and the RF and XGBoost models were built. The results show that the optimal model for distinguishing the storage time of yellow peaches after bruising is the RF model under Feature Fusion 2 (CARS), with an overall accuracy of 98.33%. In summary, this study shows that spectral features combined with texture features can be used to effectively improve the model's discrimination of storage time after bruising of yellow peaches, and it also provides a certain theoretical basis for hyperspectral imaging technology to discriminate storage time after bruising of fruits.

Sugarcane nitrogen nutrition estimation with digital images and machine learning methods

The color and texture characteristics of crops can reflect their nitrogen (N) nutrient status and help optimize N fertilizer management. This study conducted a one-year field experiment to collect sugarcane leaf images at tillering and elongation stages using a commercial digital camera and extract leaf image color feature (CF) and texture feature (TF) parameters using digital image processing techniques. By analyzing the correlation between leaf N content and feature parameters, feature dimensionality reduction was performed using principal component analysis (PCA), and three regression methods (multiple linear regression; MLR, random forest regression; RF, stacking fusion model; SFM) were used to construct N content estimation models based on different image feature parameters. All models were built using five-fold cross-validation and grid search to verify the model performance and stability. The results showed that the models based on color-texture integrated principal component features (C-T-PCA) outperformed the single-feature models based on CF or TF. Among them, SFM had the highest accuracy for the validation dataset with the model coefficient of determination (R2) of 0.9264 for the tillering stage and 0.9111 for the elongation stage, with the maximum improvement of 9.85% and 8.91%, respectively, compared with the other tested models. In conclusion, the SFM framework based on C-T-PCA combines the advantages of multiple models to enhance the model performance while enhancing the anti-interference and generalization capabilities. Combining digital image processing techniques and machine learning facilitates fast and nondestructive estimation of crop N-substance nutrition.

MM-GLCM-CNN: A multi-scale and multi-level based GLCM-CNN for polyp classification.

Distinguishing malignant from benign lesions has significant clinical impacts on both early detection and optimal management of those early detections. Convolutional neural network (CNN) has shown great potential in medical imaging applications due to its powerful feature learning capability. However, it is very challenging to obtain pathological ground truth, addition to collected in vivo medical images, to construct objective training labels for feature learning, leading to the difficulty of performing lesion diagnosis. This is contrary to the requirement that CNN algorithms need a large number of datasets for the training. To explore the ability to learn features from small pathologically-proven datasets for differentiation of malignant from benign polyps, we propose a Multi-scale and Multi-level based Gray-level Co-occurrence Matrix CNN (MM-GLCM-CNN). Specifically, instead of inputting the lesions' medical images, the GLCM, which characterizes the lesion heterogeneity in terms of image texture characteristics, is fed into the MM-GLCN-CNN model for the training. This aims to improve feature extraction by introducing multi-scale and multi-level analysis into the construction of lesion texture characteristic descriptors (LTCDs). To learn and fuse multiple sets of LTCDs from small datasets for lesion diagnosis, we further propose an adaptive multi-input CNN learning framework. Furthermore, an Adaptive Weight Network is used to highlight important information and suppress redundant information after the fusion of the LTCDs. We evaluated the performance of MM-GLCM-CNN by the area under the receiver operating characteristic curve (AUC) merit on small private lesion datasets of colon polyps. The AUC score reaches 93.99% with a gain of 1.49% over current state-of-the-art lesion classification methods on the same dataset. This gain indicates the importance of incorporating lesion characteristic heterogeneity for the prediction of lesion malignancy using small pathologically-proven datasets.

A Second-Order Method for Removing Mixed Noise from Remote Sensing Images.

Remote sensing image denoising is of great significance for the subsequent use and research of images. Gaussian noise and salt-and-pepper noise are prevalent noises in images. Contemporary denoising algorithms often exhibit limitations when addressing such mixed noise scenarios, manifesting in suboptimal denoising outcomes and the potential blurring of image edges subsequent to the denoising process. To address the above problems, a second-order removal method for mixed noise in remote sensing images was proposed. In the first stage of the method, dilated convolution was introduced into the DnCNN (denoising convolutional neural network) network framework to increase the receptive field of the network, so that more feature information could be extracted from remote sensing images. Meanwhile, a DropoutLayer was introduced after the deep convolution layer to build the noise reduction model to prevent the network from overfitting and to simplify the training difficulty, and then the model was used to perform the preliminary noise reduction on the images. To further improve the image quality of the preliminary denoising results, effectively remove the salt-and-pepper noise in the mixed noise, and preserve more image edge details and texture features, the proposed method employed a second stage on the basis of adaptive median filtering. In this second stage, the median value in the original filter window median was replaced by the nearest neighbor pixel weighted median, so that the preliminary noise reduction result was subjected to secondary processing, and the final denoising result of the mixed noise of the remote sensing image was obtained. In order to verify the feasibility and effectiveness of the algorithm, the remote sensing image denoising experiments and denoised image edge detection experiments were carried out in this paper. When the experimental results are analyzed through subjective visual assessment, images denoised using the proposed method exhibit clearer and more natural details, and they effectively retain edge and texture features. In terms of objective evaluation, the performance of different denoising algorithms is compared using metrics such as mean square error (MSE), peak signal-to-noise ratio (PSNR), and mean structural similarity index (MSSIM). The experimental outcomes indicate that the proposed method for denoising mixed noise in remote sensing images outperforms traditional denoising techniques, achieving a clearer image restoration effect.

Artificial Intelligence in Tongue Image Recognition

Tongue image recognition is a traditional Chinese medicine diagnosis method, which uses the shape, color, and texture of the tongue to judge the health of the human body. With the rapid development of artificial intelligence technology, the application of artificial intelligence in the field of tongue recognition has been widely considered. Based on the intelligent analysis of tongue diagnosis in traditional Chinese medicine, this paper reviews the application progress of artificial intelligence in tongue image recognition in recent years and analyzes its potential and challenges in this field. Firstly, this paper introduces three steps of tongue image recognition, including tongue image acquisition, tongue image preprocessing, and tongue image feature analysis. The application of traditional methods and artificial intelligence methods in the whole process of tongue image recognition is reviewed, especially the tongue body segmentation, and the advantages and disadvantages of convolutional neural networks are analyzed and compared. Artificial intelligence can use technologies such as deep learning and computer vision to automatically analyze and extract features from tongue images. By constructing a tongue image recognition model, tongue shape, color, texture, and other features can be accurately recognized and quantitatively analyzed. Finally, this paper summarizes the problems existing in artificial intelligence in tongue image recognition and looks forward to the future developmental direction of this field. It can promote the modernization of TCM diagnostic methods, achieve early disease screening and prevention, personalized medicine and treatment optimization, and support medical research and knowledge accumulation. However, there is still a need for further validation and practice, with a focus on patient privacy and data security.

Analysis of image texture features and database of drama art pattern design based on speech recognition

Analysis of image texture features and database of drama art pattern design based on speech recognition

Graph ‘texture’ features as novel metrics that can summarize complex biological graphs

Objective. Image texture features, such as those derived by Haralick et al, are a powerful metric for image classification and are used across fields including cancer research. Our aim is to demonstrate how analogous texture features can be derived for graphs and networks. We also aim to illustrate how these new metrics summarize graphs, may aid comparative graph studies, may help classify biological graphs, and might assist in detecting dysregulation in cancer. Approach. We generate the first analogies of image texture for graphs and networks. Co-occurrence matrices for graphs are generated by summing over all pairs of neighboring nodes in the graph. We generate metrics for fitness landscapes, gene co-expression and regulatory networks, and protein interaction networks. To assess metric sensitivity we varied discretization parameters and noise. To examine these metrics in the cancer context we compare metrics for both simulated and publicly available experimental gene expression and build random forest classifiers for cancer cell lineage. Main results. Our novel graph ‘texture’ features are shown to be informative of graph structure and node label distributions. The metrics are sensitive to discretization parameters and noise in node labels. We demonstrate that graph texture features vary across different biological graph topologies and node labelings. We show how our texture metrics can be used to classify cell line expression by lineage, demonstrating classifiers with 82% and 89% accuracy. Significance. New metrics provide opportunities for better comparative analyzes and new models for classification. Our texture features are novel second-order graph features for networks or graphs with ordered node labels. In the complex cancer informatics setting, evolutionary analyses and drug response prediction are two examples where new network science approaches like this may prove fruitful.

Classification of Microscopic Malaria Parasitized Images Using Deep Learning Feature Fusion

An infectious disease that causes a chronic and potentially life-threatening infection caused by microorganisms of the Plasmodium class, is malaria, or malarial disease. It is critical to detect the presence of Malaria parasites as early as possible to ensure that antimalarial treatment is adequate to cure the particular type of Plasmodium. This is to reduce death rates and to focus on various infections in the event of an adverse outcome. The purpose of this study was to develop an artificial intelligence approach capable of separating parasitized erythrocytes from normal basophilic erythrocytes as well as platelets overlying the red blood cells to overcome the high cost of Ma-laria diagnostic equipment. The tone and texture characteristics of erythrocyte images were extracted using histo-gram thresholds and watershed methods, and then fused with Squeeze Net and ShuffleNet algorithms. The measures included planning, preparing, approving, and testing Deep Convolution Neural Network Segmentation without preparation using a graphic processor unit. A total of 96 percent accuracy and specificity was obtained for the position of malaria in red blood cells based on the results of all of the tests. It has been demonstrated that deep learning can be effective in the field of clinical pathology. This provides new directions for development as well as increasing awareness of researchers in this field.

Damage detection method of automobile hub based on image texture feature

With the rapid growth in the number of motor vehicles worldwide, the general public is beginning to attach importance to the quality inspection of wheels before they leave the factory. The current wheel defect detection systems are often cumbersome to operate and have low practical performance. Therefore, this research will use dynamic image segmentation, image texture feature extraction and Back Propagation neural network classification based on wheel image defect feature analysis algorithm to achieve automatic intelligent detection of automotive wheel defects. In this study, an intelligent detection system for automotive wheel defects is also designed, and finally the performance of the detection system is tested experimentally to illustrate its practicality. The experimental results show that the proposed intelligent detection system for automotive wheel defects based on image texture features identifies defects in wheel castings with a correct rate of 96% and a false positive rate of only 2%. This illustrates that the detection system proposed in this study has a high recognition rate and can provide a useful reference for the automotive industry inspection.

Efficient LBP-GLCM texture analysis for asphalt pavement raveling detection using eXtreme Gradient Boost

The raveling of asphalt pavement is the primary cause of decreasing road safety, comfort, and service life. Because of the asphalt's complex texture, automatic raveling detection from image samples is a challenging operation. In this study, a computer vision technique, based on image texture features, for automatic detection of asphalt pavement raveling is proposed and verified. Two scenarios are taken into account for feature extraction. First, texture features from images are extracted using the traditional GLCM (Gray-Level Co-occurrence Matrix) algorithm. Second, the images are subjected to LBP (Local Binary Pattern) and then GLCM is employed to extract texture features. Utilizing the eXtreme Gradient Boost (XGBoost) technique, two models are built using the mentioned feature extraction scenarios and then compared. The results indicate that compared to the first scenarios prediction performance (Accuracy, Precision, Recall, and F1-Score are all approximately equal to %81), the second feature extraction scenario can offer higher prediction performance (Accuracy, Precision, Recall, and F1-Score are all approximately equal to %97). In order to demonstrate the model’s generalizability, a separate dataset is tested. Due to the acceptable performance values for this dataset (with more than %97 in terms of Accuracy, Precision, Recall, and F1-Score), the suggested model can be beneficial for transportation agencies to enhance the efficiency of road inspection activities.

Impact of fat types on the visual, textural, and sensory properties of Nanberenji (a traditional gluten-free cookie)

Abstract The objective of this research was to evaluate the effects of various fat types (Bakery fat, Ghee, and Olive oil) on visual characteristics, baking behavior, textural, and sensory properties of a traditional gluten-free rice-based cookie (Nanberenji). The ability of image analysis for measuring some quality properties of prepared samples were also assessed. The obtained data demonstrated that the dough prepared with bakery and olive oil had maximum and minimum hardness values, respectively. However, after baking, the samples prepared with olive oil showed the highest hardness, meaningfully. The given outputs from image processing depicted that cookie prepared with bakery fat (NBF) and samples prepared with olive oil (NOO) had the highest and lowest surface color uniformity, respectively. Over baking time, the intensity and changes in the behavior of image textural features of NG and NBF samples were the same, while NOO samples showed a different behavior. Based on sensory analysis results, olive oil, as a healthy unsaturated fat, is advised to be used in the formulation of Nanberenji to produce a gluten-free cookie with a desirable texture, color, and flavor.

Vibration and Image Texture Data Fusion-Based Terrain Classification Using WKNN for Tracked Robots

For terrain recognition needs during vehicle driving, this paper carries out terrain classification research based on vibration and image information. Twenty time-domain features and eight frequency-domain features of vibration signals that are highly correlated with terrain are selected, and principal component analysis (PCA) is used to reduce the dimensionality of the time-domain and frequency-domain features and retain the main information. Meanwhile, the texture features of the terrain images are extracted using the gray-level co-occurrence matrix (GLCM) technique, and the feature information of the vibration and images are fused in the feature layer. Then, the improved weighted K-nearest neighbor (WKNN) algorithm is used to achieve the terrain classification during the travel process of tracked robots. Finally, the experimental results verify that the proposed method improves the terrain classification accuracy of the tracked robot and provides a basis for improving the stable autonomous driving of tracked vehicles.

Compression and reconstruction of flotation foam images based on generative adversarial networks

The froth flotation is a beneficiation method that utilizes the differences in the physical and chemical properties of the surface of mineral particles to achieve the effective separation of different minerals. Recently, with the development of image processing and computer technology, machine vision has been widely used in mineral froth flotation. However, due to the high pixels of the flotation froth image and the limited storage space of the industrial computer, it is difficult to save a large amount of image data at the industrial site. To this end, a flotation foam image compression and reconstruction method is presented in this work. First, a lossless froth image is collected from the flotation cell in a gold hydrometallurgical plant. Then, the JPEG image compression algorithm compresses the original images to one in dozens. Under this situation, low-quality and small-volume images can be stored in an industrial computer easily. To reconstruct the compressed image, the generative adversarial networks (GAN) is used in this work, and RRDB and VGG19 are employed as the generative and discriminative models of the network, respectively. The loss function of the model is the sum of three losses, which are L1 loss, perceptual loss, and adversarial loss. Three methods for testing the texture features of the froth image are selected to verify the efficiency of the proposed method. The results show that the reconstructed image can effectively restore the details of the bubbles, reflect the image features, and has less noise and high visual similarity with the original image. The reconstructed images generated by low-resolution images with different compression qualities mostly maintain a restoration degree of more than 90% compared with the original images in three texture features.

An intelligent diagnosis method for oil-well pump leakage fault in oilfield production Internet of Things system based on convolutional attention residual learning

In the Internet of Things (IoT) system for oil field production, oil-well pump leakage is one of the most challenging faults to detect. Once the pump leakage fault occurs, it will severely impact crude oil production. Therefore, accurate diagnosis of oil-well pump leakage faults is highly necessary. However, achieving accurate diagnosis through existing artificial intelligence methods remains a challenge due to the prolonged and progressive nature of oil-well pump leakage faults. This paper proposes a novel methodology for diagnosing oil-well pump leakage. Specifically, we propose a time-series data transformation method that ingeniously transforms difficult-to-identify pump leakage long time-series data variation features into image pixel-level texture features, and based on the characteristics of differences in image texture features under different states, we propose the structure of convolutional residual blocks with attributes and spatial attention for oil-well pump leakage fault diagnosis, which enables more accurate fault diagnosis by assigning more attention weights to extract valuable fault information. Through extensive experimentation, we found that the diagnosis process proposed in this paper outperforms sequence models such as LSTM and GRU, achieving a diagnostic accuracy of 98.36% for oil-well pump leakage faults. Moreover, it leads to a significant improvement of 19.40% and 10.36% in accuracy compared to conventional CNN and ResNet models, respectively. Therefore, in the actual production of oilfields, this method can effectively meet the detection requirements for oil-well pump leakage.

ASTER VNIR‐SWIR Based Lithological Mapping of Granitoids in the Western Junggar Orogen (NW Xinjiang): Improved Inputs to Random Forest Method

AbstractAlthough advanced spaceborne thermal emission and reflection radiometer multispectral analysis for lithological mapping has been widely applied, traditional methods such as band ratios (BR) and principal component analysis (PCA) are still hampered by cumbersome data processing and poor classification performance. In this study, we utilize improved data inputs for random forest (RF) to extract lithological information of granitoids, which are the predominant rock type for intrusion‐related polymetallic ore deposits in the western Junggar Orogen (NW Xinjiang). Based on spectral absorption features of minerals (e.g., orthoclase, K‐feldspar, hornblende, biotite, plagioclase, and oligoclase), image statistical information and textural features, we tested different combinations of bands, BR, PCA, and texture using RF method, and found that the combination of B13678 + T1 (Mean texture) achieved the highest weighted‐F1 score for granitoids, with an accuracy of 87.32%. Compared to the support vector machine, RF effectively distinguishes lithological differences between different types of granitoid and wallrocks, especially the granite, granodiorite, and alkali granite in the Akebasito intrusion, as well as the alkali granite, plagiogranite and biotite granite in the Karamay intrusions. Moreover, the large number of rare metal deposits (including Cu, Au, Mo, etc.) distributed near the granitoid intrusions in the western Junggar, our result facilitates the analysis of regional tectonic evolution and mineralization controlling.

Breast Cancer Diagnosis Using Texture and Shape Features in MRI.

Contrast-enhanced magnetic resonance (MR) breast imaging represents a tool with great potential for the detection, evaluation and diagnosis of breast cancer (BC). Due to its high sensitivity and in combination with medical imaging biomarkers, it can overcome setbacks and limitations manifested in other diagnostic modalities such as mammography or ultrasound. In order to aid and assist clinicians in the diagnosis of BC, a methodology based on the extraction of 2D texture and 3D shape features in MR images is proposed. To categorize breast tumor malignancy, we considered its location in the coronal plane, divided into 4 quadrants (UOQ, UIQ, LOQ and LOQ), and the tumor type according to its genetic information (positive HER2 and Luminal B with negative HER2). In this regard, six different studies were conducted: one per feature type (texture and shape), as well as the combination of both features (texture + shape) for each of the two covariables (tumor type and location in the coronal plane). A dataset of 43 BC patients were considered. A radiomics approach was implemented extracting 43 texture and 17 shape features and using to train 5 different predictive models (Linear SVM, Gaussian SVM, Bagged Tree, KNN and Naïve Bayes). The highest precision result for the tumor type study (74.04% in terms of AUC) was obtained with 43 texture features. Whereas for the quadrant localization study, the highest precision result (67.99% AUC) was obtained as a combination of 3 textures and shape features. Both results were achieved with the SVM with Linear Kernel classification model.Clinical Relevance- This work emphasizes the use of quantitative biomarkers as texture and shape features in combination with machine learning techniques to aid in breast tumor malignancy diagnosis on MR imaging. Moreover, considering the location of the tumor in the coronal plane and its type according to its genetic information may improve the selection of appropriate treatments, survival rate, and quality of life for breast cancer patients.

Preliminary Analysis on the Effect of Different Denoising Techniques towards Texture Features of MRI Images of Alzheimer’s Disease

Early detection of Alzheimer’s disease (AD) has become one of the major research topics nowadays. The utilization of the computerized system may help medical experts to better understand and analyse the magnetic resonance imaging (MRI) images of AD patients for early detection. One of the commonly steps taken for the analysis of the image is image denoising using certain filters. However, finding shows that previous researchers use different approaches. This study aims to analyse the effect of different denoising techniques towards detection of Alzheimer’s disease. Data of two different groups (AD patients and Normal Control) were collected from Alzheimer's Disease Neuroimaging Initiative (ADNI). Then brain extraction and skull stripping were performed. Several image denoising techniques were implemented for both groups namely median filter, Wiener filter, histogram equalization filter and Gaussian low pass filter. After that, all images underwent texture feature extraction process and analysis were made to see the effect of those denoising techniques towards the features of Gray-Level Co-occurrence Matrix (GLCM) extracted which are the contract, correlation, energy and homogeneity features. The result shows that the use of mentioned denoising filters do not give effect to the extracted features. All values of contrast, correlation, energy and homogeneity cannot clearly distinguish between AD and NC groups. Without any filters on the other hand, contrast feature gives the best output in distinguishing between AD and NC groups with the normalized value of 0.1. The result from this study may help in thorough investigation of other features or hybrid features that could be used for the purpose of detection and classification of AD.

Application of MR Imaging Characteristics in the Differentiation of Renal Changes Between Patients with Stage III Type 2 Diabetic Kidney Disease and Healthy People.

To explore the value of 1.5T magnetic resonance (MR) fat saturation-T2-weighted imaging (FS-T2WI) and apparent diffusion coefficient (ADC) imaging texture features in distinguishing the renal changes of patients with stage III type 2 diabetic kidney disease (DKD) from healthy people. This study collected 55 patients with stage III DKD (39 males and 16 females) and 33 healthy controls (13 males and 20 females) from December 2021 to June 2022 in the China-Japan Union Hospital of Jilin University. All subjects were randomly divided in a ratio of 6:4 to extract and screen the FS-T2WI and ADC texture features of the right kidney of the subjects. The area under the curve (AUC) was used to assess the diagnostic accuracy of each model. There were significant differences between urea, creatinine and sex (p<0.05) of the two groups in the training and test set, and no significant difference in age and body mass index (BMI). We extracted 1409 imaging features from the original ADC sequence and selected them by wavelet and Laplace-Gaussian filter and LASSO algorithm, and using the same methods of FS-T2WI. Finally, FS-T2WI and ADC models were selected to construct the united model, including 3 first-order features and 8 texture features. The AUC values of the training set of FS-T2WI, ADC, FS-T2WI+ADC combined logistic regression model were 0.96, 0.91, 0.98; the AUC values of the test set were 0.91, 0.89 and 0.93, and the specificity and accuracy values of the united model were 0.90 and 0.89, respectively. FS-T2WI and ADC imaging features based on 1.5 T MR had diagnostic value in the early diagnosis of DKD stage III, and the combined model of FS-T2WI and ADC had high diagnostic efficiency.

MR Imaging Findings and Texture Analysis of Pure and Mixed Mucinous Breast Carcinoma

Purpose: To evaluate the ability of magnetic resonance imaging (MRI) findings and texture features to differentiate between pure and mixed subtypes of mucinous breast carcinoma.Methods: This retrospective study included 136 patients who were surgically diagnosed with mucinous breast carcinoma and underwent pre-treatment breast MRI between January 2008 and December 2020. All clinicopathological and MRI features were reviewed. For texture analysis, regions of interest of the tumors were drawn manually on T2-weighted images and first-subtraction T1-weighted images. Texture feature extraction and analysis were conducted using open-source 3D slicer software. Univariate and multivariate analyses were used to identify significant MRI findings and texture features to differentiate between the two subtypes. To evaluate the diagnostic performance of the texture features, a receiver operating characteristic curve analysis was conducted.Results: Among the MRI findings, very high signal intensity on T2-weighted images was significantly associated with pure mucinous breast carcinoma (odds ratio=5.23, &lt;i&gt;p&lt;/i&gt;=0.001). The homogeneity and skewness texture features from T2-weighted imaging showed statistically significant differences between pure and mixed subtypes, and the areas under the receiver operating curve were 0.749 and 0.815, respectively.Conclusion: Signal intensity and texture features on T2- weighted images derived from breast MRI can assist in the differential diagnosis of pure and mixed types of mucinous breast carcinoma.