Integrating clinical data and ultrasonographic imaging for non-invasive prediction of HER2 status in breast cancer DOI Creative Commons

Anli Zhao,

Jiang‐Feng Wu,

YanHong Du

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: March 14, 2024

Abstract Background The most common cancer in the world, breast (BC), poses serious problems to healthcare. Making an accurate diagnosis of these patients' HER2 status is essential for therapy planning.Methods A prospective cohort patients with BC was enrolled between June 2020 and october 2023. patient's clinical data features from their ultrasonography were gathered. Postoperative tumor pathology specimens subjected immunohistochemistry fluorescence situ hybridization examinations ascertain status. Lasso regression used choose characteristic variables. Univariate multivariate logistic analysis find status-independent factors. performance nomogram model then assessed using calibration curves decision curve (DCA).Result 97 (22.25%) 436 research had positive results. Progesterone receptor expression, Ki-67 levels, estrogen expression differed statistically amongst different statuses. identified six ultrasonographic variables closely associated a pool 786 features, leading generation radiomic score each patient. Multivariate revealed that PR (OR = 0.15, 95%CI 0.06–0.36, p < 0.001), 1.02, 1.00-1.03, 0.012), Radiomic 5.89, 2.58–13.45, 0.001) independent predictors demonstrated areas under (AUC) 0.823 (95% CI 0.772–0.874) 0.812 0.717–0.906) training validation cohort, respectively.Conclusions methodology integrates data, cutting-edge imaging, machine learning provide individualized treatment plans presented non-invasive prediction cancer.

Language: Английский

Performance of 3-T Nonenhanced Whole-Heart bSSFP Coronary MR Angiography: A Comparison with 3-T Modified Dixon Water-Fat Separation Sequence DOI
Yong Yuan, Yue Jiang, Guangming Lu

et al.

Radiology Cardiothoracic Imaging, Journal Year: 2025, Volume and Issue: 7(2)

Published: April 1, 2025

Improved nonenhanced whole-heart balanced steady-state free precession coronary MR angiography performs better at 3-T imaging than the modified Dixon water-fat separation sequence.

Language: Английский

Citations

0

Multiparametric Approach to Breast Cancer With Emphasis on Magnetic Resonance Imaging in the Era of Personalized Breast Cancer Treatment DOI Creative Commons
Masako Kataoka, Mami Iima, Kanae Kawai Miyake

et al.

Investigative Radiology, Journal Year: 2023, Volume and Issue: unknown

Published: Nov. 22, 2023

Abstract A multiparametric approach to breast cancer imaging offers the advantage of integrating diverse contributions various parameters. Dynamic contrast-enhanced magnetic resonance (DCE-MRI) is most important MRI sequence for imaging. The vascularity and permeability lesions can be estimated through use semiquantitative quantitative increased ultrafast DCE-MRI has facilitated introduction novel kinetic In addition DCE-MRI, diffusion-weighted provides information associated with tumor cell density, advanced techniques such as intravoxel incoherent motion, diffusion kurtosis imaging, time-dependent opening up new horizons in microscale tissue evaluation. Furthermore, T2-weighted plays a key role measuring degree aggressiveness, which may related microenvironment. Magnetic is, however, not only modality providing parameters from tumors. Breast positron emission tomography demonstrates superior spatial resolution whole-body allows comparable delineation MRI, well metabolic information, often precedes vascular morphological changes occurring response treatment. integration these imaging-derived factors accomplished this article, we explore relationship among parameters, diagnosis, histological characteristics, technical theoretical background review recent studies on application significance

Language: Английский

Citations

9

MRI‐Based Machine Learning Radiomics for Preoperative Assessment of Human Epidermal Growth Factor Receptor 2 Status in Urothelial Bladder Carcinoma DOI

Ruixi Yu,

Lingkai Cai,

Yuxi Gong

et al.

Journal of Magnetic Resonance Imaging, Journal Year: 2024, Volume and Issue: 60(6), P. 2694 - 2704

Published: March 8, 2024

Background The human epidermal growth factor receptor 2 (HER2) has recently emerged as hotspot in targeted therapy for urothelial bladder cancer (UBC). HER2 status is mainly identified by immunohistochemistry (IHC), preoperative and noninvasive methods determining UBC remain searching. Purposes To investigate whether radiomics features extracted from MRI using machine learning algorithms can noninvasively evaluate the UBC. Study Type Retrospective. Population One hundred ninety‐five patients (age: 68.7 ± 10.5 years) with 14.3% females January 2019 to May 2023 were divided into training (N = 156) validation 39) cohorts, 43 67.1 13.1 13.9% June 2024 constituted test cohort 43). Field Strength/Sequence 3 T, T2‐weighted imaging (turbo spin‐echo), diffusion‐weighted (breathing‐free spin echo). Assessment assessed IHC. Radiomics images. Pearson correlation coefficient least absolute shrinkage selection operator (LASSO) applied feature selection, six models established optimal identify Statistical Tests Mann–Whitney U ‐test, chi‐square test, LASSO algorithm, receiver operating characteristic analysis, DeLong test. Results Three thousand forty‐five each lesion, 22 retained analysis. Support Vector Machine model demonstrated best performance, an AUC of 0.929 (95% CI: 0.888–0.970) accuracy 0.859 cohort, 0.886 0.780–0.993) 0.846 0.712 0.535–0.889) 0.744 cohort. Data Conclusion MRI‐based combining algorithm provide a promising approach assess preoperatively. Evidence Level Technical Efficacy Stage

Language: Английский

Citations

3

Personalized optimization of systematic prostate biopsy core number based on mpMRI radiomics features: a large-sample retrospective analysis DOI Creative Commons
Zhenlin Chen, Zhihao Li,

Ruiling Dou

et al.

BMC Cancer, Journal Year: 2025, Volume and Issue: 25(1)

Published: Jan. 22, 2025

Prostate cancer (PCa) is definitively diagnosed by systematic prostate biopsy (SBx) with 13 cores. This method, however, can increase the risk of urinary retention, infection and bleeding due to excessive number We retrospectively analyzed 622 patients who underwent SBx multiparametric MRI (mpMRI) from two centers between January 2014 June 2022. The data were collected manually segment Regions Interest (ROI) tumor layer layer. ROI reconstructions fused form outline volume interest (VOI), which exported applied subsequent extraction radiomics features. t-tests, Mann-Whitney U-tests chi-squared tests performed evaluate significance logistic regression was used for calculating PCa score (PCS). PCS model trained optimize core number, utilizing both mpMRI clinical predicted cores determined model. Optimal numbers subgroups 1–5 calculated as 13, 10, 8, 6, respectively. Accuracies high: 100%, 95.8%, 91.7%, 90.6%, 92.7% 1–5. Optimized reduced rate 41.9%. Leakage rates clinically significant 8.2% 3.4%, optimized also demonstrated high accuracy on validation set. optimization described in this study could therefore effectively reduce obtained PCS, especially far away suspicious lesions. method enhance patient experience without reducing detection rate.

Language: Английский

Citations

0

Multi-sequence MRI-based Nomogram for Prediction of Human Epidermal Growth Factor Receptor 2 Expression in Breast Cancer DOI Creative Commons

Mengyi Shen,

Li Zhang, Dingyi Zhang

et al.

Heliyon, Journal Year: 2025, Volume and Issue: 11(3), P. e42398 - e42398

Published: Feb. 1, 2025

To develop a nomogram based on multi-sequence MRI (msMRI) radiomics features and imaging characteristics for predicting human epidermal growth factor receptor 2 (HER2) expression in breast cancer (BC). 206 women diagnosed with invasive BC were retrospectively enrolled randomly divided into training set (n = 144) validation 62) at the ratio of 7 : 3. Tumor segmentation feature extraction performed dynamic contrast-enhanced (DCE) MRI, T2-weighted (T2WI), apparent diffusion coefficient (ADC) map. Radiomics models constructed using score (Rad-score) was calculated. Rad-score significant included multivariate analysis to establish nomogram. The performance mainly evaluated via area under receiver operating characteristic curve (AUC). Edema types T2WI (OR 4.480, P 0.008), enhancement type 7.550, 0.002), 5.906, < 0.001) independent predictors HER2 expression. model msMRI (including DCE-MRI, T2WI, ADC map) had AUCs 0.936 0.880 sets, respectively, exceeding one sequence or dual sequences. With combination edema types, achieved highest (AUC: 0.940) 0.893). developed MRI-based presents promising tool expression, is expected improve diagnosis treatment BC.

Language: Английский

Citations

0

Identifying the risk factors of ICU-acquired fungal infections: clinical evidence from using machine learning DOI Creative Commons

Yi-si Zhao,

Qingpei Lai,

Hong Tang

et al.

Frontiers in Medicine, Journal Year: 2024, Volume and Issue: 11

Published: May 9, 2024

Background Fungal infections are associated with high morbidity and mortality in the intensive care unit (ICU), but their diagnosis is difficult. In this study, machine learning was applied to design define predictive model of ICU-acquired fungi (ICU-AF) early stage fungal using Random Forest. Objectives This study aimed provide evidence for warning management infections. Methods We analyzed data patients culture-positive during admission seven ICUs First Affiliated Hospital Chongqing Medical University from January 1, 2015, December 31, 2019. Patients whose first culture positive longer than 48 h after ICU were included ICU-AF cohort. A obtained Least Absolute Shrinkage Selection Operator learning, relationship between features within disease severity analyzed. Finally, relationships model, antifungal therapy empirical Results total 1,434 cases finally. used lasso dimensionality reduction all selected six importance ≥0.05 optimal namely, times arterial catheter, enteral nutrition, corticosteroids, broadspectrum antibiotics, urinary invasive mechanical ventilation. The area under curve predicting 0.981 test set, a sensitivity 0.960 specificity 0.990. catheter ( p = 0.011, OR 1.057, 95% CI 1.053–1.104) ventilation 0.007, 1.056, 95%CI 1.015–1.098) independent risk factors ICU-AF. 0.004, 1.098, 0.855–0.970) an factor therapy. Conclusion most important time-related clinical parameters (arterial ventilation), which occurrence infection. Furthermore, can help physicians assess whether empiric should be administered who susceptible

Language: Английский

Citations

2

Development and Validation of a Deep Learning System to Differentiate HER2‐Zero, HER2‐Low, and HER2‐Positive Breast Cancer Based on Dynamic Contrast‐Enhanced MRI DOI Open Access
Yi Dai,

Chun Lian,

Zhuo Zhang

et al.

Journal of Magnetic Resonance Imaging, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 6, 2024

Background Previous studies explored MRI‐based radiomic features for differentiating between human epidermal growth factor receptor 2 (HER2)‐zero, HER2‐low, and HER2‐positive breast cancer, but deep learning's effectiveness is uncertain. Purpose This study aims to develop validate a learning system using dynamic contrast‐enhanced MRI (DCE‐MRI) automated tumor segmentation classification of HER2‐zero, statuses. Study Type Retrospective. Population One thousand two hundred ninety‐four cancer patients from three centers who underwent DCE‐MRI before surgery were included in the (52 ± 11 years, 811/204/279 training/internal testing/external testing). Field Strength/Sequence 3 T scanners, T1‐weighted 3D fast spoiled gradient‐echo sequence, enhanced sequence turbo field echo sequence. Assessment An model segmented tumors utilizing data, followed by models (ResNetGN) trained classify HER2 Three developed distinguish their respective non‐HER2 categories. Statistical Tests Dice similarity coefficient (DSC) was used evaluate performance model. Evaluation performances statuses involved receiver operating characteristic (ROC) curve analysis area under (AUC), accuracy, sensitivity, specificity. The P ‐values <0.05 considered statistically significant. Results automatic network achieved DSC values 0.85 0.90 compared manual across different sets. ResNetGN AUCs 0.782, 0.776, 0.768 HER2‐zero others training, internal test, external test sets, respectively. Similarly, 0.820, 0.813, 0.787 HER2‐low vs. others, 0.792, 0.745, 0.781 Data Conclusion proposed DCE‐MRI‐based may have potential preoperatively distinct expressions cancers with therapeutic implications. Evidence Level 4 Technical Efficacy Stage

Language: Английский

Citations

2

A comparative study on the features of breast sclerosing adenosis and invasive ductal carcinoma via ultrasound and establishment of a predictive nomogram DOI Creative Commons
Yuan Li,

Xiu-liang Wei,

Kun-kun Pang

et al.

Frontiers in Oncology, Journal Year: 2023, Volume and Issue: 13

Published: Oct. 23, 2023

To analyze the clinical and ultrasonic characteristics of breast sclerosing adenosis (SA) invasive ductal carcinoma (IDC), construct a predictive nomogram for SA.A total 865 patients were recruited at Second Hospital Shandong University from January 2016 to November 2022. All underwent routine ultrasound examinations before surgery, diagnosis was confirmed by histopathological examination following operation. Ultrasonic features recorded using Breast Imaging Data Reporting System (BI-RADS). Of patients, 203 (252 nodules) diagnosed as SA 662 (731 IDC. They randomly divided into training set validation ratio 6:4. Lastly, difference in comparatively analyzed.There statistically significant multiple between IDC (P<0.05). As age lesion size increased, probability significantly decreased, with cut-off value 36 years old 10 mm, respectively. In logistic regression analysis set, age, nodule size, menopausal status, symptoms, palpability lesions, margins, internal echo, color Doppler flow imaging (CDFI) grading, resistance index (RI) These indicators included static dynamic model, which showed high performance, calibration both sets.SA should be suspected asymptomatic young women, especially those younger than who present small-size lesions (especially less mm) distinct homogeneous lack blood supply. The model can provide more convenient tool clinicians.

Language: Английский

Citations

4

Personalized Optimization of Systematic Prostate Biopsy Core Number Based on mpMRI Radiomics Features DOI Creative Commons
Zhenlin Chen, Zhihao Li,

Ruiling Dou

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: April 19, 2024

Abstract Background Prostate cancer (PCa) is definitively diagnosed by systematic prostate biopsy (SBx) with 13 cores. This method, however, can increase the risk of urinary retention, infection and bleeding due to excessive number Methods We retrospectively analyzed 622 patients who underwent SBx multiparametric MRI (mpMRI) from two centers between January 2014 June 2022. The data were collected manually segment Regions Interest (ROI) tumor layer by-layer. ROI reconstructions fused form VOIs, which exported applied subsequent extraction radiomics features. t-tests, Mann-Whitney U-tests chi-squared tests performed evaluated significance logistic regression was used for calculating PCa score(PCS). PCS model trained optimize core number, utilizing both mpMRI clinical Results predicted cores determined model. Optimal numbers subgroups 1–5 calculated as 13, 10, 8, 6, respectively. Accuracies high: 100%, 95.8%, 91.7%, 90.6%, 92.7% 1–5. Optimized reduced rate 41.9%. Leakage rates clinically significant 8.2% 3.4%, optimized also demonstrated high accuracies on validation set. Conclusion optimization described in this study could therefore effectively reduce obtained PCS. method enhance patient experiences without reducing detection rate.

Language: Английский

Citations

1

Preoperative Differentiation of HER2‐Zero and HER2‐Low from HER2‐Positive Invasive Ductal Breast Cancers Using BI‐RADS MRI Features and Machine Learning Modeling DOI
Jiejie Zhou, Yang Zhang,

Haiwei Miao

et al.

Journal of Magnetic Resonance Imaging, Journal Year: 2024, Volume and Issue: unknown

Published: May 10, 2024

Background Accurate determination of human epidermal growth factor receptor 2 (HER2) is important for choosing optimal HER2 targeting treatment strategies. HER2‐low currently considered HER2‐negative, but patients may be eligible to receive new anti‐HER2 drug conjugates. Purpose To use breast MRI BI‐RADS features classifying three levels, first distinguish HER2‐zero from HER2‐low/positive (Task‐1), and then HER2‐positive (Task‐2). Study Type Retrospective. Population 621 invasive ductal cancer, 245 HER2‐zero, 191 HER2‐low, 185 HER2‐positive. For Task‐1, 488 cases training 133 testing. Task‐2, 294 82 Field Strength/Sequence 3.0 T; 3D T1‐weighted DCE, short time inversion recovery T2, single‐shot EPI DWI. Assessment Pathological information were compared. Random Forest was used select features, four machine learning (ML) algorithms: decision tree (DT), support vector (SVM), k ‐nearest neighbors ( ‐NN), artificial neural nets (ANN), applied build models. Statistical Tests Chi‐square test, one‐way analysis variance, Kruskal–Wallis test performed. The P values <0.05 statistically significant. ML models, the generated probability construct ROC curves. Results Peritumoral edema, presence multiple lesions non‐mass enhancement (NME) showed significant differences. distinguishing non‐zero (low + positive), lesions, margin, tumor size selected, ‐NN model achieved highest AUC 0.86 in set 0.79 testing set. differentiating HER2‐positive, margin DT 0.69 Data Conclusion read by radiologists preoperative can analyzed using more sophisticated feature selection algorithms models classification status identify HER2‐low. Level Evidence 4. Technical Efficacy Stage 2.

Language: Английский

Citations

1