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

Radiomics in breast MRI: current progress toward clinical application in the era of artificial intelligence DOI
Hiroko Satake, Satoko Ishigaki, Rintaro Ito

et al.

La radiologia medica, Journal Year: 2021, Volume and Issue: 127(1), P. 39 - 56

Published: Oct. 26, 2021

Language: Английский

Citations

69
Potential Antihuman Epidermal Growth Factor Receptor 2 Target Therapy Beneficiaries: The Role of MRI‐Based Radiomics in Distinguishing Human Epidermal Growth Factor Receptor 2‐Low Status of Breast Cancer DOI

Xiaoqian Bian,

Siyao Du,

Zhibin Yue

et al.

Journal of Magnetic Resonance Imaging, Journal Year: 2023, Volume and Issue: 58(5), P. 1603 - 1614

Published: Feb. 10, 2023

Multiparametric MRI radiomics could distinguish human epidermal growth factor receptor 2 (HER2)-positive from HER2-negative breast cancers. However, its value for further distinguishing HER2-low cancers has not been investigated.To investigate whether multiparametric MRI-based can HER2-positive (task 1) and 2).Retrospective.Task 1: 310 operable cancer patients center 1 (97 213 HER2-negative); task 2: (108 105 HER2-zero); 59 (16 HER2-positive, 27 16 HER2-zero) external validation.A 3.0 T/T1-weighted contrast-enhanced imaging (T1CE), diffusion-weighted (DWI)-derived apparent diffusion coefficient (ADC).Patients in were assigned to a training internal validation cohort at 2:1 ratio. Intratumoral peritumoral features extracted T1CE ADC. After dimensionality reduction, the signatures (RS) of two tasks developed using (RS-T1CE), ADC (RS-ADC) alone + combination (RS-Com).Mann-Whitney U tests, least absolute shrinkage selection operator, receiver operating characteristic (ROC) curve, calibration decision curve analysis (DCA).For 1, RS-ADC yielded higher area under ROC (AUC) training, internal, 0.767/0.725/0.746 than RS-T1CE (AUC = 0.733/0.674/0.641). For 2, AUC 0.765/0.755/0.678 0.706/0.608/0.630). both RS-Com achieved best performance with 0.793/0.778/0.760 0.820/0.776/0.711, respectively, obtained clinical benefit DCA compared RS-ADC. The curves all RS demonstrated good fitness.Multiparametric noninvasively robustly cancers.3.Stage 2.

Language: Английский

Citations

30
Discrimination between HER2-overexpressing, -low-expressing, and -zero-expressing statuses in breast cancer using multiparametric MRI-based radiomics DOI

Shaoyan Zheng,

Zehong Yang,

Guangzhou Du

et al.

European Radiology, Journal Year: 2024, Volume and Issue: 34(9), P. 6132 - 6144

Published: Feb. 16, 2024

Language: Английский

Citations

17
Development and Validation of MRI Radiomics Models to Differentiate HER2-Zero, -Low, and -Positive Breast Cancer DOI

Yuqin Peng,

Xiang Zhang,

Ya Qiu

et al.

American Journal of Roentgenology, Journal Year: 2024, Volume and Issue: 222(4)

Published: Jan. 24, 2024

Breast cancer HER2 expression has been redefined using a three-tiered system, with HER2-zero cancers considered ineligible for HER2-targeted therapy, HER2-low candidates novel drugs, and HER2-positive treated traditional medications.

Language: Английский

Citations

11
Artificial intelligence in multiparametric magnetic resonance imaging: A review DOI
Cheng Li,

Wen Li,

Chenyang Liu

et al.

Medical Physics, Journal Year: 2022, Volume and Issue: 49(10)

Published: Aug. 18, 2022

Abstract Multiparametric magnetic resonance imaging (mpMRI) is an indispensable tool in the clinical workflow for diagnosis and treatment planning of various diseases. Machine learning–based artificial intelligence (AI) methods, especially those adopting deep learning technique, have been extensively employed to perform mpMRI image classification, segmentation, registration, detection, reconstruction, super‐resolution. The current availabilities increasing computational power fast‐improving AI algorithms empowered numerous computer‐based systems applying disease diagnosis, imaging‐guided radiotherapy, patient risk overall survival time prediction, development advanced quantitative technology fingerprinting. However, wide application these developed clinic still limited by a number factors, including robustness, reliability, interpretability. This survey aims provide overview new researchers field as well radiologists with hope that they can understand general concepts, main scenarios, remaining challenges mpMRI.

Language: Английский

Citations

34
Strategies for Enhancing the Multi-Stage Classification Performances of HER2 Breast Cancer from Hematoxylin and Eosin Images DOI Creative Commons
Md Sakib Hossain Shovon, Md. Jahidul Islam,

Mohammed Nawshar Ali Khan Nabil

et al.

Diagnostics, Journal Year: 2022, Volume and Issue: 12(11), P. 2825 - 2825

Published: Nov. 16, 2022

Breast cancer is a significant health concern among women. Prompt diagnosis can diminish the mortality rate and direct patients to take steps for treatment. Recently, deep learning has been employed diagnose breast in context of digital pathology. To help this area, transfer learning-based model called 'HE-HER2Net' proposed multiple stages HER2 (HER2-0, HER2-1+, HER2-2+, HER2-3+) on H&E (hematoxylin & eosin) images from BCI dataset. HE-HER2Net modified version Xception model, which additionally comprised global average pooling, several batch normalization layers, dropout dense layers with swish activation function. This exceeds all existing models terms accuracy (0.87), precision (0.88), recall (0.86), AUC score (0.98) immensely. In addition, our explained through class-discriminative localization technique using Grad-CAM build trust make more transparent. Finally, nuclei segmentation performed StarDist method.

Language: Английский

Citations

32
Radiomics and artificial intelligence in breast imaging: a survey DOI
Tianyu Zhang, Tao Tan, Riccardo Samperna

et al.

Artificial Intelligence Review, Journal Year: 2023, Volume and Issue: 56(S1), P. 857 - 892

Published: July 8, 2023

Language: Английский

Citations

23
Noninvasive identification of HER2-low-positive status by MRI-based deep learning radiomics predicts the disease-free survival of patients with breast cancer DOI
Yuan Guo,

Xiaotong Xie,

Wenjie Tang

et al.

European Radiology, Journal Year: 2023, Volume and Issue: 34(2), P. 899 - 913

Published: Aug. 19, 2023

Language: Английский

Citations

21
Radiomics analysis of intratumoral and different peritumoral regions from multiparametric MRI for evaluating HER2 status of breast cancer: A comparative study DOI Creative Commons
Jing Zhou, Xuan Yu, Qingxia Wu

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(7), P. e28722 - e28722

Published: April 1, 2024

To investigate the potential of radiomics signatures (RSs) from intratumoral and peritumoral regions on multiparametric magnetic resonance imaging (MRI) to noninvasively evaluate HER2 status in breast cancer.

Language: Английский

Citations

8
Preoperative ultrasound radiomics analysis for expression of multiple molecular biomarkers in mass type of breast ductal carcinoma in situ DOI Creative Commons

Linyong Wu,

Yujia Zhao, Peng Lin

et al.

BMC Medical Imaging, Journal Year: 2021, Volume and Issue: 21(1)

Published: May 17, 2021

Abstract Background The molecular biomarkers of breast ductal carcinoma in situ (DCIS) have important guiding significance for individualized precision treatment. This study was intended to explore the radiomics based on ultrasound images predict expression mass type DCIS. Methods 116 patients with DCIS were included this retrospective study. features extracted images. According ratio 7:3, data sets split into training set and test set. models developed estrogen receptor (ER), progesterone (PR), human epidermal growth factor 2 (HER2), Ki67, p16, p53 by using combination multiple feature selection classifiers. predictive performance evaluated area under curve (AUC) receiver operating curve. Results investigators 5234 from 12, 23, 41, 51, 31 23 constructing models. scores significantly (P < 0.05) each marker showed AUC greater than 0.7 set: ER (0.94 0.84), PR (0.90 0.78), HER2 0.74), Ki67 (0.95 0.86), p16 (0.96 respectively. Conclusion Ultrasonic-based analysis provided a noninvasive preoperative method predicting markers good accuracy.

Language: Английский

Citations

33