Radiogenomic analysis of prediction HER2 status in breast cancer by linking ultrasound radiomic feature module with biological functions

Journal of Translational Medicine, Journal Year: 2023, Volume and Issue: 21(1)

Published: Jan. 24, 2023

Abstract Background Human epidermal growth factor receptor 2 (HER2) overexpressed associated with poor prognosis in breast cancer and HER2 has been defined as a therapeutic target for treatment. We aimed to explore the molecular biological information ultrasound radiomic features (URFs) of HER2-positive using radiogenomic analysis. Moreover, radiomics model was developed predict status cancer. Methods This retrospective study included 489 patients who were diagnosed URFs extracted from analysis set PyRadiomics. The correlations between differential HER2-related genes calculated Pearson correlation Functional enrichment identified URFs-correlated positive-specific performed. Lastly, based on URF-module mined auxiliary assess Results Eight ( p < 0.05) among 86 by Pyradiomics. 25 that found be most closely URFs. Then, relevant functions each URF obtained through functional Among them, Zone Entropy is related immune cell activity, which regulate generation calcification Logistic classifier showed good discriminative ability (AUC = 0.80, 95% CI). Conclusion searched cancer, explored underlying these Furthermore, relatively accurately predicted

Language: Английский

---

Intra- and peritumoral radiomics features based on multicenter automatic breast volume scanner for noninvasive and preoperative prediction of HER2 status in breast cancer: a model ensemble research

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Feb. 29, 2024

Abstract The aim to investigate the predictive efficacy of automatic breast volume scanner (ABVS), clinical and serological features alone or in combination at model level for predicting HER2 status. weighted method was developed identify status compared with single data source feature method. 271 patients invasive cancer were included retrospective study, which 174 our center randomized into training validation sets, 97 external as test set. Radiomics extracted from ABVS-based tumor, peritumoral 3 mm region, 5 region used construct four types optimal models, Tumor, R3mm, R5mm, Clinical model, respectively. Then, methods performed optimize models. proposed models achieved better performance both set For set, highest area under curve (AUC) 0.803 (95% confidence interval [CI] 0.660–947), 0.739 (CI 0.556,0.921), 0.826 CI 0.689,0.962), respectively; sensitivity specificity 100%, 62.5%; 81.8%, 66.7%; 90.9%,75.0%; attained best AUC 0.695 0.583, 0.807), 0.668 0.555,0.782), 0.700 0.590,0.811), 86.1%, 41.9%; 61.1%, 71.0%; a model. optimized composed intratumoral radiomics may be potential biomarkers noninvasive preoperative prediction cancer.

Language: Английский

---

Ultrasound radiomics in personalized breast management: Current status and future prospects

Frontiers in Oncology, Journal Year: 2022, Volume and Issue: 12

Published: Aug. 17, 2022

Breast cancer is the most common in women worldwide. Providing accurate and efficient diagnosis, risk stratification timely adjustment of treatment strategies are essential steps achieving precision medicine before, during after treatment. Radiomics provides image information that cannot be recognized by naked eye through deep mining medical images. Several studies have shown radiomics, as a second reader images, can assist physicians not only detection diagnosis breast lesions but also assessment prediction response. Recently, more focused on application ultrasound radiomics management. We summarized recent research advances for benign malignant lesions, molecular subtype, lymph node status, neoadjuvant chemotherapy response, survival. In addition, we discuss current challenges future prospects radiomics.

Language: Английский

---

Reproducibility of radiomics features from ultrasound images: influence of image acquisition and processing

European Radiology, Journal Year: 2022, Volume and Issue: 32(9), P. 5843 - 5851

Published: March 22, 2022

Language: Английский

---

Prognostic Value of ¹⁸F-FDG PET/CT Radiomics in Extranodal Nasal-Type NK/T Cell Lymphoma

Korean Journal of Radiology, Journal Year: 2024, Volume and Issue: 25(2), P. 189 - 189

Published: Jan. 1, 2024

To investigate the prognostic utility of radiomics features extracted from

Language: Английский

---

Prediction of heart failure and all-cause mortality using cardiac ultrasomics in patients with breast cancer

The International Journal of Cardiovascular Imaging, Journal Year: 2024, Volume and Issue: 40(6), P. 1305 - 1317

Published: April 16, 2024

Language: Английский

---

Ultrasound deep learning radiomics and clinical machine learning models to predict low nuclear grade, ER, PR, and HER2 receptor status in pure ductal carcinoma in situ

Gland Surgery, Journal Year: 2024, Volume and Issue: 13(4), P. 516 - 531

Published: April 1, 2024

Meng Zhu, Yalan Kuang, Zekun Jiang, Jingyan Liu, Heqing Zhang, Haina Zhao, Honghao Luo, Yujuan Chen, Yulan Peng

---

Artificial intelligence in breast imaging: potentials and challenges

Physics in Medicine and Biology, Journal Year: 2023, Volume and Issue: 68(23), P. 23TR01 - 23TR01

Published: Sept. 18, 2023

Breast cancer, which is the most common type of malignant tumor among humans, a leading cause death in females. Standard treatment strategies, including neoadjuvant chemotherapy, surgery, postoperative targeted therapy, endocrine and radiotherapy, are tailored for individual patients. Such personalized therapies have tremendously reduced threat breast cancer Furthermore, early imaging screening plays an important role reducing cycle improving prognosis. The recent innovative revolution artificial intelligence (AI) has aided radiologists accurate diagnosis cancer. In this review, we introduce necessity incorporating AI into applications mammography, ultrasonography, magnetic resonance imaging, positron emission tomography/computed tomography based on published articles since 1994. Moreover, challenges discussed.

Language: Английский

---

Diagnostic performance of ultrasound-based artificial intelligence for predicting key molecular markers in breast cancer: A systematic review and meta-analysis

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(5), P. e0303669 - e0303669

Published: May 31, 2024

Background Breast cancer (BC) diagnosis and treatment rely heavily on molecular markers such as HER2, Ki67, PR, ER. Currently, these are identified by invasive methods. Objective This meta-analysis investigates the diagnostic accuracy of ultrasound-based radiomics a novel approach to predicting markers. Methods A comprehensive search PubMed, EMBASE, Web Science databases was conducted identify studies evaluating in BC. Inclusion criteria encompassed research ER key Quality assessment using Assessment Diagnostic Accuracy Studies (QUADAS-2) Radiomics Score (RQS) performed. The data extraction step performed systematically. Results Our quantifies with sensitivity specificity 0.76 0.78 for 0.80, Ki67 biomarkers. did not provide sufficient quantitative PR prediction analysis. overall quality based RQS tool moderate. QUADAS-2 evaluation showed that had an unclear risk bias regarding flow timing domain. Conclusion analysis indicated AI models have promising biomarkers’ status BC patients. We HER2 biomarkers which yielded moderate high accuracy. However, adequate developed models. acceptable. In future research, need report results thoroughly. Also, we suggest more prospective from different centers.

Language: Английский

---

Integration of ultrasound radiomics features and clinical factors: A nomogram model for identifying the Ki-67 status in patients with breast carcinoma

Frontiers in Oncology, Journal Year: 2022, Volume and Issue: 12

Published: Oct. 5, 2022

Objective The aim of this study was to develop and validate an ultrasound-based radiomics nomogram model by integrating the clinical risk factors score (Rad-Score) predict Ki-67 status in patients with breast carcinoma. Methods Ultrasound images 284 (196 high expression 88 low expression) were retrospectively analyzed, which 198 belonged training set 86 test set. region interest tumor delineated, features extracted. Radiomics underwent dimensionality reduction analysis using independent sample t least absolute shrinkage selection operator (LASSO) algorithm. support vector machine (SVM), logistic regression (LR), decision tree (DT), random forest (RF), naive Bayes (NB) XGBoost (XGB) learning classifiers trained establish prediction based on selected features. classifier highest AUC value convert output results into Rad-Score regarded as model. In addition, method used integrate generate leave group out cross-validation (LGOCV) performed 200 times verify reliability stability Results Six models established 15 non-zero coefficient Among them, LR achieved best performance set, area under receiver operating characteristic curve (AUC) 0.786, obtained model, while XGB worst (AUC, 0.615). multivariate analysis, factor for age (odds ratio [OR] = 0.97, p 0.04). had a slightly higher than that 0.808 vs. 0.798) but no statistical difference (p 0.144, DeLong test). LGOCV yielded median 0.793 Conclusions This proposed convenient, clinically useful ultrasound can be preoperative individualized BC.

Language: Английский

---