Ultrasound-based radiomics nomogram: A potential biomarker to predict axillary lymph node metastasis in early-stage invasive breast cancer

European Journal of Radiology, Journal Year: 2019, Volume and Issue: 119, P. 108658 - 108658

Published: Sept. 7, 2019

Language: Английский

---

Joint Prediction of Breast Cancer Histological Grade and Ki-67 Expression Level Based on DCE-MRI and DWI Radiomics

IEEE Journal of Biomedical and Health Informatics, Journal Year: 2019, Volume and Issue: 24(6), P. 1632 - 1642

Published: Nov. 27, 2019

Objective: Histologic grade and Ki-67 proliferation status are important clinical indictors for breast cancer prognosis treatment. The purpose of this study is to improve prediction accuracy these indicators based on tumor radiomic analysis. Methods: We jointly predicted with a multitask learning framework by separately utilizing radiomics from MRI series. Additionally, we showed how models (MTLs) could be extended combined the series better assumption that features different sources images share common patterns while providing complementary information. Tumor analysis was performed morphological, statistical textural extracted DWI dynamic contrast-enhanced (DCE-MRI) precontrast subtraction images, respectively. Results: Joint MR using MTL achieved performance improvements over single-task-based predictive models. Similarly, tasks grade, apparent diffusion coefficient (ADC) AUCs 0.811 0.816, which were significantly than single-task- model p values 0.005 0.017, Conclusion: Mapping two related improves both expression level grade. Significance: combines correlations optimal therapy treatment because decisions made integrating multiple indicators.

Language: Английский

---

T₂‐based MRI Delta‐radiomics improve response prediction in soft‐tissue sarcomas treated by neoadjuvant chemotherapy.

Journal of Magnetic Resonance Imaging, Journal Year: 2018, Volume and Issue: 50(2), P. 497 - 510

Published: Dec. 19, 2018

Background Standard of care for patients with high‐grade soft‐tissue sarcoma (STS) are being redefined since neoadjuvant chemotherapy (NAC) has demonstrated a positive effect on patients' outcome. Yet response evaluation in clinical trials still relies RECIST criteria. Purpose To investigate the added value Delta‐radiomics approach early prediction STS undergoing NAC. Study Type Retrospective. Population Sixty‐five adult newly‐diagnosed, locally‐advanced, histologically proven trunk and extremities. All were treated by anthracycline‐based NAC followed surgery had available MRI at baseline after two cycles. Field Strength/Sequence Pre‐ postcontrast enhanced T 1 ‐weighted imaging (T ‐WI), turbo spin echo 2 ‐WI 1.5 T. Assessment A threshold <10% viable cells surgical specimens defined good (Good‐HR). Two senior radiologists performed semantic analysis MRI. After 3D manual segmentation tumors evaluation, standardization voxel‐sizes intensities, absolute changes 33 texture shape features calculated. Statistical Tests Classification models based logistic regression, support vector machine, k‐nearest neighbors, random forests elaborated using crossvalidation (training validation) 50 ("training cohort") was validated 15 other ("test cohort"). Results Sixteen good‐HR. Neither status ( P = 0.112) nor radiological variables associated (range ‐values: 0.134–0.490) except an edema decrease 0.003), although 14 0.002–0.037). On training cohort, highest diagnostic performances obtained built three features: Δ_Histogram_Entropy, Δ_Elongation, Δ_Surrounding_Edema, which provided: area under curve receiver operating characteristic 0.86, accuracy 88.1%, sensitivity 94.1%, specificity 66.3%. test this model provided 74.6% but 3/5 good‐HR systematically ill‐classified. Data Conclusion ‐based might improve assessment limited number features. Level Evidence : 3 Technical Efficacy Stage J. Magn. Reson. Imaging 2019;50:497–510.

Language: Английский

---

Radiomics in Breast Imaging from Techniques to Clinical Applications: A Review

Korean Journal of Radiology, Journal Year: 2020, Volume and Issue: 21(7), P. 779 - 779

Published: Jan. 1, 2020

Recent advances in computer technology have generated a new area of research known as radiomics.Radiomics is defined the high throughput extraction and analysis quantitative features from imaging data.Radiomic provide information on gray-scale patterns, inter-pixel relationships, well shape spectral properties radiological images.Moreover, these can be used to develop computational models that may serve tool for personalized diagnosis treatment guidance.Although radiomics becoming popular widely oncology, many problems such overfitting reproducibility issues remain unresolved.In this review, we will outline steps specifically addressing applications breast cancer patients focusing technical issues.

Language: Английский

---

A machine learning-based radiomics model for the prediction of axillary lymph-node metastasis in breast cancer

Breast Cancer, Journal Year: 2021, Volume and Issue: 28(3), P. 664 - 671

Published: Jan. 17, 2021

Language: Английский

---