Quantitative Analysis of Lesion Morphology and Texture Features for Diagnostic Prediction in Breast MRI

doi:10.1016/j.acra.2008.06.005

Academic Radiology

Volume 15, Issue 12, December 2008, Pages 1513-1525

This work was presented at the 2007 Joint ISMRM-ESMRMB meeting held in Berlin, Germany.

https://doi.org/10.1016/j.acra.2008.06.005 Get rights and content

Rationale and Objectives

To investigate the feasibility using quantitative morphology/texture features of breast lesions for diagnostic prediction, and to explore the association of computerized features with lesion phenotype appearance on magnetic resonance imaging.

Materials and Methods

Forty-three malignant/28 benign lesions were used in this study. A systematic approach from automated lesion segmentation, quantitative feature extraction, diagnostic feature selection using an artificial neural network (ANN), and lesion classification was carried out. Eight morphologic parameters and 10 gray level co-occurrence matrix texture features were obtained from each lesion. The diagnostic performance of selected features to differentiate between malignant and benign lesions was analyzed using receiver-operating characteristic analysis.

Results

Six features were selected by an ANN using leave-one-out cross validation, including compactness, normalized radial length entropy, volume, gray level entropy, gray level sum average, and homogeneity. The area under the receiver-operating characteristic curve was 0.86. When dividing the database into half training and half validation set, a classifier of five features selected in the half training set achieved an area under the curve of 0.82 in the other half validation set. The selected morphology feature “compactness” was associated with shape and margin in the Breast Imaging Reporting and Data System lexicon, round shape and smooth margin for the benign lesions, and more irregular shape for the malignant lesions. The selected texture features were associated with homogeneous/heterogeneous patterns and the enhancement intensity. The malignant lesions had higher intensity and broader distribution on the enhancement histogram (more heterogeneous) compared to the benign lesions.

Conclusion

Quantitative analysis of morphology/texture features of breast lesions was feasible, and these features could be selected by an ANN to form a classifier for differential diagnosis. Establishing the link between computer-based features and visual descriptors defined in the BI-RADS lexicon will provide the foundation for the acceptance of quantitative diagnostic features in the development of computer-aided diagnosis.

Section snippets

Subjects and MRI Protocol

The study included 28 histologically proven benign and 43 malignant lesions selected from our breast MRI database collected from 1999–2005. The age of the patients was from 29–76 years old (48 ± 9, median 48) in the malignant group, and 21 to 74 (45 ± 7, median 45) in the benign group. Only lesions that showed strong contrast enhancements with a clearly defined boundary were selected for this study. Those cases presenting diffuse infiltrating enhancements or ill-defined tumor margins were

Evaluation of Computerized vs. Manual Lesion Segmentation

First, the consistency between two manual segmentations performed by a radiologist was evaluated, as shown in Figure 2a, which is separately labeled for benign and malignant lesions. The Pearson's correlation coefficient was r = 0.97 for both benign and malignant lesions. Taking the average of the two radiologist's segmentation as the “ground truth,” it was compared to the segmentation obtained by computerized algorithms, as shown in Figure 2b. The correlation coefficient for all lesions was r =

Discussion

Compared to the well-established CAD for mammography, development of automated CAD for breast MRI is in its early stage. Only a few investigations have pursued automated lesion segmentation and/or feature extraction for lesions detected by breast MRI, as summarized in Table 3. In this study, we applied quantitative analysis to characterize the morphology and texture features of breast lesions and used the ANN to select a classifier for differential diagnosis. This comprehensive approach was

References (30)

K. Schelfout et al.
Contrast-enhanced MR imaging of breast lesions and effect on treatment
Eur J Surg Oncol
(2004)
K. Drukker et al.
Computerized detection and classification of cancer on breast ultrasound
Acad Radiol
(2004)
Y.L. Huang et al.
Support vector machines in sonography: application to decision making in the diagnosis of breast cancer
Clin Imaging
(2005)
K.G. Kim et al.
Computerized scheme for assessing ultrasonographic features of breast masses
Acad Radiol
(2005)
W. Chen et al.
A fuzzy c-means (FCM)-based approach for computerized segmentation of breast lesions in dynamic contrast-enhanced MR images
Acad Radiol
(2006)
S. Behrens et al.
Computer assistance for MR based diagnosis of breast cancer: present and future challenges
Comput Med Imaging Graph
(2007)
B.K. Szabo et al.
Neural network approach to the segmentation and classification of dynamic magnetic resonance images of the breast: comparison with empiric and quantitative kinetic parameters
Acad Radiol
(2004)
Y.H. Chou et al.
Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis
Ultrasound Med Biol
(2001)
U. Fischer et al.
Breast carcinoma: effect of preoperative contrast-enhanced MR imaging on the therapeutic approach
Radiology
(1999)
H. Mumtaz et al.
Staging of symptomatic primary breast cancer with MR imaging
Am J Roentgenol
(1997)

L. Esserman et al.

Utility of magnetic resonance imaging in the management of breast cancer: evidence for improved preoperative staging

J Clin Oncol

(1999)

Y. Zhang et al.

The role of contrast-enhanced MR mammography for determining candidates for breast conservation surgery

Breast Cancer

(2002)

A. Rieber et al.

Pre-operative staging of invasive breast cancer with MR mammography and/or PET: boon or bunk?

Br J Radiol

(2002)

H. Li et al.

Computerized radiographic mass detection—part ILesion site selection by morphological enhancement and contextual segmentation

IEEE Trans Med Imaging

(2001)

W.E. Polakowski et al.

Computer-aided breast cancer detection and diagnosis of masses using difference of Gaussians and derivative-based feature saliency

IEEE Trans Med Imaging

(1997)

Cited by (203)

Deep Learning-based Automatic Diagnosis of Breast Cancer on MRI Using Mask R-CNN for Detection Followed by ResNet50 for Classification
2023, Academic Radiology
Diagnosis of breast cancer on MRI requires, first, the identification of suspicious lesions; second, the characterization to give a diagnostic impression. We implemented Mask Reginal-Convolutional Neural Network (R-CNN) to detect abnormal lesions, followed by ResNet50 to estimate the malignancy probability.
Two datasets were used. The first set had 176 cases, 103 cancer, and 73 benign. The second set had 84 cases, 53 cancer, and 31 benign. For detection, the pre-contrast image and the subtraction images of left and right breasts were used as inputs, so the symmetry could be considered. The detected suspicious area was characterized by ResNet50, using three DCE parametric maps as inputs. The results obtained using slice-based analyses were combined to give a lesion-based diagnosis.
In the first dataset, 101 of 103 cancers were detected by Mask R-CNN as suspicious, and 99 of 101 were correctly classified by ResNet50 as cancer, with a sensitivity of 99/103 = 96%. 48 of 73 benign lesions and 131 normal areas were identified as suspicious. Following classification by ResNet50, only 16 benign and 16 normal areas remained as malignant. The second dataset was used for independent testing. The sensitivity was 43/53 = 81%. Of the total of 121 identified non-cancerous lesions, only 6 of 31 benign lesions and 22 normal tissues were classified as malignant.
ResNet50 could eliminate approximately 80% of false positives detected by Mask R-CNN. Combining Mask R-CNN and ResNet50 has the potential to develop a fully-automatic computer-aided diagnostic system for breast cancer on MRI.
Can magnetic resonance imaging texture analysis change the breast imaging reporting and data system category of breast lesions?
2023, Clinical Imaging
This study aimed to reveal magnetic resonance imaging (MRI) texture analysis (TA)'s contribution to categorizing breast lesions according to the Breast Imaging-Reporting and Data System (BI-RADS) lexicon.
Two hundred and seventeen women with BI-RADS category 3, 4, and 5 lesions on breast MRI were included in the study. For TA, the region of interest was drawn manually to encompass the entire lesion on the fat-suppressed T2W and the first post-contrast T1W images. To identify the independent predictors of breast cancer, multivariate logistic regression analyses were performed using texture parameters. Estimated benign and malignant groups were formed according to the TA regression model.
Texture parameters extracted from T2WI, including median, gray-level co-occurrence matrix (GLCM) contrast, GLCM correlation, GLCM joint entropy, GLCM sum entropy, and GLCM sum of squares, and parameters extracted from T1WI, including maximum, GLCM contrast, GLCM joint entropy, GLCM sum entropy, were independent predictors of breast cancer. In the estimated new groups according to the TA regression model, 19 (91%) of the benign 4a lesions were downgraded to BI-RADS category 3.
The addition of quantitative parameters obtained by MRI TA to BI-RADS criteria significantly increased the accuracy rate in differentiating benign and malignant breast lesions. When categorizing BI-RADS 4a lesions, the use of MRI TA in addition to conventional imaging findings may reduce unnecessary biopsy rates.
3D DCE-MRI Radiomic Analysis for Malignant Lesion Prediction in Breast Cancer Patients
2022, Academic Radiology
To develop and validate a radiomic model, with radiomic features extracted from breast Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) from a 1.5T scanner, for predicting the malignancy of masses with enhancement. Images were acquired using an 8-channel breast coil in the axial plane. The rationale behind this study is to show the feasibility of a radiomics-powered model that could be integrated into the clinical practice by exploiting only standard-of-care DCE-MRI with the goal of reducing the required image pre-processing (ie, normalization and quantitative imaging map generation).
107 radiomic features were extracted from a manually annotated dataset of 111 patients, which was split into discovery and test sets. A feature calibration and pre-processing step was performed to find only robust non-redundant features. An in-depth discovery analysis was performed to define a predictive model: for this purpose, a Support Vector Machine (SVM) was trained in a nested 5-fold cross-validation scheme, by exploiting several unsupervised feature selection methods. The predictive model performance was evaluated in terms of Area Under the Receiver Operating Characteristic (AUROC), specificity, sensitivity, PPV and NPV. The test was performed on unseen held-out data.
The model combining Unsupervised Discriminative Feature Selection (UDFS) and SVMs on average achieved the best performance on the blinded test set: AUROC = 0.725±0.091, sensitivity = 0.709±0.176, specificity = 0.741±0.114, PPV = 0.72±0.093, and NPV = 0.75±0.114.
In this study, we built a radiomic predictive model based on breast DCE-MRI, using only the strongest enhancement phase, with promising results in terms of accuracy and specificity in the differentiation of malignant from benign breast lesions.
Development of computer-aided model to differentiate COVID-19 from pulmonary edema in lung CT scan: EDECOVID-net
2022, Computers in Biology and Medicine
The efforts made to prevent the spread of COVID-19 face specific challenges in diagnosing COVID-19 patients and differentiating them from patients with pulmonary edema. Although systemically administered pulmonary vasodilators and acetazolamide are of great benefit for treating pulmonary edema, they should not be used to treat COVID-19 as they carry the risk of several adverse consequences, including worsening the matching of ventilation and perfusion, impaired carbon dioxide transport, systemic hypotension, and increased work of breathing. This study proposes a machine learning-based method (EDECOVID-net) that automatically differentiates the COVID-19 symptoms from pulmonary edema in lung CT scans using radiomic features. To the best of our knowledge, EDECOVID-net is the first method to differentiate COVID-19 from pulmonary edema and a helpful tool for diagnosing COVID-19 at early stages. The EDECOVID-net has been proposed as a new machine learning-based method with some advantages, such as having simple structure and few mathematical calculations. In total, 13 717 imaging patches, including 5759 COVID-19 and 7958 edema images, were extracted using a CT incision by a specialist radiologist. The EDECOVID-net can distinguish the patients with COVID-19 from those with pulmonary edema with an accuracy of 0.98. In addition, the accuracy of the EDECOVID-net algorithm is compared with other machine learning methods, such as VGG-16 (Acc = 0.94), VGG-19 (Acc = 0.96), Xception (Acc = 0.95), ResNet101 (Acc = 0.97), and DenseNet20l (Acc = 0.97).
Texture appearance model, a new model-based segmentation paradigm, application on the segmentation of lung nodule in the CT scan of the chest
2022, Computers in Biology and Medicine
Lung cancer causes more than one million deaths worldwide each year. Averages of 5-year survival rate of patients with Non-small cell lung cancer (NSCLC), which is the most common type of lung cancer, is 15%. Computer-Aided Detection (CAD) is a very important tool for identifying lung lesions in medical imaging. In general, the process line of a CAD system can be divided into four main stages: preprocessing, localization, feature extraction, and classification. As segmentation is required for localization in computer vision and medical image analysis, this step has become a major and challenging problem, and much research has been done on new segmentation techniques. In recent years, interest in model-based segmentation methods has increased, and the reason for this is even if some object information is lost, such gaps can be filled by using the previous information in the model. This paper proposed Texture Appearance Model (TAM), which is a new model-based method and segments all types of nodule areas accurately and efficiently, including juxta-pleural nodules, without separating the lung from the surrounding area in a CT scan of the lung. In this method, Texture Representation of Image (TRI) is obtained using tissue texture feature extraction and feature selection algorithms. The proposed method has been evaluated in 85 nodules of the dataset, received from the Iranian hospital, in which the ground-truth annotation by physicians and CT imaging data were provided. The results show that the proposed algorithm has an encouraging performance for distinguishing different types of nodules, including pleural, cavity and non-solid nodules, achieving an average dice similarity coefficient (DSC) of 84.75%.
Automatic Detection and Segmentation of Breast Cancer on MRI Using Mask R-CNN Trained on Non–Fat-Sat Images and Tested on Fat-Sat Images
2022, Academic Radiology
Citation Excerpt :
DCE-MRI was acquired using a fat-suppressed three-dimensional fast low angle shot (3D-FLASH) sequence with one precontrast and four postcontrast frames, with TR/TE = 4.50/1.82 msec, flip angle = 12°, matrix size = 512 × 512, field of view = 32 cm, and slice thickness = 1.5 mm. The tumor was segmented on the subtraction image generated by subtracting the pre-contrast image from the 2nd DCE postcontrast image, using the fuzzy c-means clustering algorithm (33). This DCE frame was selected based on the high tissue contrast between the boundary of the mass lesion (often showing strong peripheral enhancement) and the adjacent normal tissue.
Computer-aided methods have been widely applied to diagnose lesions on breast magnetic resonance imaging (MRI). The first step was to identify abnormal areas. A deep learning Mask Regional Convolutional Neural Network (R-CNN) was implemented to search the entire set of images and detect suspicious lesions.
Two DCE-MRI datasets were used, 241 patients acquired using non–fat-sat sequence for training, and 98 patients acquired using fat-sat sequence for testing. All patients have confirmed unilateral mass cancers. The tumor was segmented using fuzzy c-means clustering algorithm to serve as the ground truth. Mask R-CNN was implemented with ResNet-101 as the backbone. The neural network output the bounding boxes and the segmented tumor for evaluation using the Dice Similarity Coefficient (DSC). The detection performance, and the trade-off between sensitivity and specificity, was analyzed using free response receiver operating characteristic.
When the precontrast and subtraction image of both breasts were used as input, the false positive from the heart and normal parenchymal enhancements could be minimized. The training set had 1469 positive slices (containing lesion) and 9135 negative slices. In 10-fold cross-validation, the mean accuracy = 0.86 and DSC = 0.82. The testing dataset had 1568 positive and 7264 negative slices, with accuracy = 0.75 and DSC = 0.79. When the obtained per-slice results were combined, 240 of 241 (99.5%) lesions in the training and 98 of 98 (100%) lesions in the testing datasets were identified.
Deep learning using Mask R-CNN provided a feasible method to search breast MRI, localize, and segment lesions. This may be integrated with other artificial intelligence algorithms to develop a fully automatic breast MRI diagnostic system.

View all citing articles on Scopus

¹: This work was conducted at Tu and Yuen Center for Functional Onco-Imaging at University of California, Irvine, CA.

: This work was supported in part by NIH/NCI Grants R01 CA90437, CA121568 and the California Breast Cancer Research Program # 9WB-0020.

View full text

Original investigationQuantitative Analysis of Lesion Morphology and Texture Features for Diagnostic Prediction in Breast MRI1,

Rationale and Objectives

Materials and Methods

Results

Conclusion

Section snippets

Subjects and MRI Protocol

Evaluation of Computerized vs. Manual Lesion Segmentation

Discussion

Eur J Surg Oncol

Acad Radiol

Clin Imaging

Acad Radiol

Acad Radiol

Comput Med Imaging Graph

Acad Radiol

Ultrasound Med Biol

Breast carcinoma: effect of preoperative contrast-enhanced MR imaging on the therapeutic approach

Radiology

Staging of symptomatic primary breast cancer with MR imaging

Am J Roentgenol

Utility of magnetic resonance imaging in the management of breast cancer: evidence for improved preoperative staging

J Clin Oncol

The role of contrast-enhanced MR mammography for determining candidates for breast conservation surgery

Breast Cancer

Pre-operative staging of invasive breast cancer with MR mammography and/or PET: boon or bunk?

Br J Radiol

Computerized radiographic mass detection—part ILesion site selection by morphological enhancement and contextual segmentation

IEEE Trans Med Imaging

Computer-aided breast cancer detection and diagnosis of masses using difference of Gaussians and derivative-based feature saliency

IEEE Trans Med Imaging

Original investigation
Quantitative Analysis of Lesion Morphology and Texture Features for Diagnostic Prediction in Breast MRI1,