The value of whole-tumor histogram and texture analysis based on apparent diffusion coefficient (ADC) maps for the discrimination of breast fibroepithelial lesions: corresponds to clinical management decisions

Li, Xue; Chai, Weimin; Kim, Sun; Fu, Caixia; Yan, Fuhua

doi:10.1007/s11604-022-01304-y

Cited by 9 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, many studies have recently reported radiomic approaches for applying quantitative DWI in decision-making for breast diseases. 29,[33][34][35] On the other hand, the standardization of imaging acquisition and identification of robust and reproducible features are the biggest challenges in the clinical application of radiomics. Zhu et al demonstrated that a deep learning-based radiomics model on CE-MRI showed moderate predictive power for DCIS upgrade with an AUC of 0.70.…”

Section: Discussionmentioning

confidence: 99%

Predictive Performance of Radiomic Features Extracted from Breast MR Imaging in Postoperative Upgrading of Ductal Carcinoma <i>in Situ</i> to Invasive Carcinoma

Satake,

Kinoshita,

Ishigaki

et al. 2024

magn reson med sci

View full text Add to dashboard Cite

To investigate the predictive performance of radiomic features extracted from breast MRI for upgrade of ductal carcinoma in situ (DCIS) to invasive carcinoma.Methods: This retrospective study included 71 women with DCIS lesions diagnosed preoperatively by biopsy. All women underwent breast dynamic contrast-enhanced (DCE) MRI of the breast, which included pre-contrast and five post-contrast phases continuously with a time resolution of 60s. Lesion segmentation was performed manually, and 144 radiomic features of the lesions were extracted from T2-weighted images (T2WI), pre-contrast T1-weighted images (T1WI), and post-contrast 1st, 2nd, and 5th phase subtraction images on DCE-MRI. Qualitative features of mammography, ultrasound, and MRI were also assessed. Clinicopathological features were evaluated using medical records. The least absolute shrinkage and selection operator (LASSO) algorithm was applied for features selection and model building. The predictive performance of postoperative upgrade to invasive carcinoma was assessed using the area under the receiver operating characteristic curve.Results: Surgical specimens revealed 13 lesions (18.3%) that were upgraded to invasive carcinoma. Among clinicopathological and qualitative features, age was the only significant predictive variable. No significant radiomic features were observed on T2WI and post-contrast 2nd phase subtraction images on DCE-MRI. The area under the curves (AUCs) of the LASSO radiomics model integrated with age were 0.915 for precontrast T1WI, 0.862 for post-contrast 1st phase subtraction images, and 0.833 for post-contrast 5th phase subtraction images. The AUCs of the 200-times bootstrap internal validations were 0.885, 0.832, and 0.775. Conclusion:A radiomics approach using breast MRI may be a promising method for predicting the postoperative upgrade of DCIS. The present study showed that the radiomic features extracted from pre-contrast T1WI and post-contrast subtraction images in the very early phase of DCE-MRI were more predictable.

show abstract

Section: Discussionmentioning

confidence: 99%

Predictive Performance of Radiomic Features Extracted from Breast MR Imaging in Postoperative Upgrading of Ductal Carcinoma <i>in Situ</i> to Invasive Carcinoma

Satake,

Kinoshita,

Ishigaki

et al. 2024

magn reson med sci

View full text Add to dashboard Cite

show abstract

“…Wang et al [28] compared texture analyses between the whole-tumor ROIs and the partial ROIs in glioma and revealed that those of the whole-tumor ROIs had higher accuracy for distinguishing each grade of gliomas than those of the partial ROIs, perhaps because the whole-tumor ROIs could contain the required information about tumor heterogeneity owing to the cellularity, angiogenesis, extravascular extracellular matrix, and areas of necrosis. Li et al [29] selected the whole-tumor ROIs for texture analyses of breast tumors to avoid the inconsistency between ROI delineators and reported that it can provide rich and valuable information for differentiating breast fibroepithelial tumors. In line with previous studies, we selected texture analyses of whole-tumor ROIs to evaluate USMTs which have various internal characteristics such as necrosis and hemorrhage, and to lower interobserver variability this time.…”

Section: Discussionmentioning

confidence: 99%

Quantitative MR texture analysis for the differentiation of uterine smooth muscle tumors with high signal intensity on T2-weighted imaging

et al. 2023

View full text Add to dashboard Cite

The purpose of this study was to distinguish leiomyosarcomas/smooth muscle tumors of uncertain malignant potential (STUMP) from leiomyomas with high signal intensity (SI) on T2-weighted imaging (T2WI) using quantitative MR texture analysis combined with patient characteristics and visual assessment. Thirty-one leiomyomas, 2 STUMPs, and 6 leiomyosarcomas showing high SI on T2WI were included. First, we searched for differences in patient characteristics and visual assessment between leiomyomas and leiomyosarcomas/STUMPs. We also compared the MR texture on T2WI and the apparent diffusion coefficient (ADC) to identify differences between leiomyomas and leiomyosarcomas/STUMPs. In the univariate analysis, significant differences between leiomyomas and leiomyosarcomas/STUMPs were observed in age, menopausal status, margin, hemorrhage, long diameter, T2-variance, T2-volume, ADC-variance, ADC-entropy, ADC-uniformity, ADC-90th and 95th percentile values, and ADC-volume (P < .05, respectively). There were significantly more postmenopausal patients with leiomyosarcomas/STUMPs than with leiomyomas, and leiomyosarcomas/STUMPs had more irregular margins, more frequent presence of hemorrhage and exhibited larger tumor diameters, T2-volume, T2-variance, ADC-volume, ADC-variance, ADC-entropy, and higher ADC-90th and 95th percentile values but lower ADC-uniformity. Multivariate analyses revealed that the independent differentiators were menopausal status, hemorrhage and ADC-entropy (P < .05, respectively). The area under the curve obtained by combining the 3 items was 0.980. The best cutoff value for ADC-entropy was 9.625 (sensitivity: 100%, specificity: 58%). The combination of menopausal status, hemorrhage, and ADC-entropy can help accurately distinguish leiomyosarcomas/STUMPs from leiomyomas with high SI on T2WI; however, external validation in a larger population is required because of the small sample size of our study.

show abstract

“…In recent years, breast imaging diagnostics have advanced significantly, with improvements in imaging technology and diagnostic accuracy [27][28][29][30][31][32]. This progress is not only due to enhancements in the quality of mammography and ultrasound images and the establishment of more refined reading techniques but also to the emergence of new modalities such as contrast-enhanced Magnetic Resonance Imaging (MRI), Positron Emission Tomography/Computed Tomography (PET/CT), and PET mammography.…”

Section: Discussionmentioning

confidence: 99%

Clinical Utility of Breast Ultrasound Images Synthesized by a Generative Adversarial Network

Zama,

Fujioka,

Yamaga

et al. 2023

Medicina

View full text Add to dashboard Cite

Background and Objectives: This study compares the clinical properties of original breast ultrasound images and those synthesized by a generative adversarial network (GAN) to assess the clinical usefulness of GAN-synthesized images. Materials and Methods: We retrospectively collected approximately 200 breast ultrasound images for each of five representative histological tissue types (cyst, fibroadenoma, scirrhous, solid, and tubule-forming invasive ductal carcinomas) as training images. A deep convolutional GAN (DCGAN) image-generation model synthesized images of the five histological types. Two diagnostic radiologists (reader 1 with 13 years of experience and reader 2 with 7 years of experience) were given a reading test consisting of 50 synthesized and 50 original images (≥1-month interval between sets) to assign the perceived histological tissue type. The percentages of correct diagnoses were calculated, and the reader agreement was assessed using the kappa coefficient. Results: The synthetic and original images were indistinguishable. The correct diagnostic rates from the synthetic images for readers 1 and 2 were 86.0% and 78.0% and from the original images were 88.0% and 78.0%, respectively. The kappa values were 0.625 and 0.650 for the synthetic and original images, respectively. The diagnoses made from the DCGAN synthetic images and original images were similar. Conclusion: The DCGAN-synthesized images closely resemble the original ultrasound images in clinical characteristics, suggesting their potential utility in clinical education and training, particularly for enhancing diagnostic skills in breast ultrasound imaging.

show abstract

The value of whole-tumor histogram and texture analysis based on apparent diffusion coefficient (ADC) maps for the discrimination of breast fibroepithelial lesions: corresponds to clinical management decisions

Cited by 9 publications

References 17 publications

Predictive Performance of Radiomic Features Extracted from Breast MR Imaging in Postoperative Upgrading of Ductal Carcinoma <i>in Situ</i> to Invasive Carcinoma

Predictive Performance of Radiomic Features Extracted from Breast MR Imaging in Postoperative Upgrading of Ductal Carcinoma <i>in Situ</i> to Invasive Carcinoma

Quantitative MR texture analysis for the differentiation of uterine smooth muscle tumors with high signal intensity on T2-weighted imaging

Clinical Utility of Breast Ultrasound Images Synthesized by a Generative Adversarial Network

Contact Info

Product

Resources

About