Article
Radiology, Nuclear Medicine & Medical Imaging
Noam Nissan, Vera Sorin, Ethan Bauer, Debbie Anaby, David Samoocha, Yael Yagil, Renata Faermann, Osnat Halshtok-Neiman, Anat Shalmon, Michael Gotlieb, Miri Sklair-Levy
Summary: This study investigates the application of computer-added diagnosis (CAD) in dynamic contrast-enhanced (DCE) MRI of healthy lactating breasts. The results show that false-positive CAD coloring is common among lactating patients, with background parenchymal enhancement (BPE) being the main cause. Lactation BPE is characterized by non-mass enhancement (NME) shape, bilateral and symmetric coloring. Compared to healthy non-lactating controls, lactating patients have a significantly increased probability of CAD false positives, while CAD features are mostly inconclusive when compared to breast cancer patients, although increased size parameters are significantly associated with lactation BPE.
ACADEMIC RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Dong Wei, Nariman Jahani, Eric Cohen, Susan Weinstein, Meng-Kang Hsieh, Lauren Pantalone, Despina Kontos
Summary: The study proposed and evaluated a fully automated technique for quantifying fibroglandular tissue (FGT) and background parenchymal enhancement (BPE) in breast MRI. Results showed high spatial correspondence and correlation between automatic and manual segmentations of FGT and BPE, with small differences between the quantifications. However, there was a lower correlation for BPE when correlated with qualitative clinical ratings.
Article
Oncology
Sachiko Yuen, Shuichi Monzawa, Ayako Gose, Seiji Yanai, Yoshihiro Yata, Hajime Matsumoto, You Ichinose, Takashi Tashiro, Kazuhiko Yamagami
Summary: This study compared the diagnostic performances of contrast-enhanced digital mammography (CEDM) and breast MRI in evaluations of breast cancer, and found that CEDM had superior diagnostic performance to MRI in patients with minimal-mild background parenchymal enhancement (BPE).
Article
Radiology, Nuclear Medicine & Medical Imaging
Zhou Liu, Fuliang Lin, Junhui Huang, Xia Wu, Jie Wen, Meng Wang, Ya Ren, Xiaoer Wei, Xinyu Song, Jing Qin, Elaine Yuen-Phin Lee, Dan Shao, Yixiang Wang, Xiaoguang Cheng, Zhanli Hu, Dehong Luo, Na Zhang
Summary: This study investigated the effectiveness of a machine learning classification method based on Dempster-Shafer (D-S) evidence theory for the histologic grading of breast cancer. It found that multiple classifiers can be effectively combined based on D-S evidence theory to improve the prediction of histologic grade in breast cancer.
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Hui Wang, Ling Gao, Xu Chen, Shou-Ju Wang
Summary: The Kaiser score is a more accurate diagnostic tool for evaluating benign and malignant lesions in high-grade BPE as compared to the BI-RADS, with higher specificity, positive predictive value, and diagnostic accuracy.
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Zhou Liu, Fuliang Lin, Junhui Huang, Xia Wu, Jie Wen, Meng Wang, Ya Ren, Xiaoer Wei, Xinyu Song, Jing Qin, Elaine Yuen-Phin Lee, Dan Shao, Yixiang Wang, Xiaoguang Cheng, Zhanli Hu, Dehong Luo, Na Zhang
Summary: This study explored the effectiveness of a machine learning classification method based on Dempster-Shafer (D-S) evidence theory for the histologic grading of breast cancer. The results showed that combining multiple classifiers using D-S evidence theory significantly improved the accuracy and area under the curve compared to using individual classifiers.
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
(2023)
Article
Oncology
Wenlong Ming, Yanhui Zhu, Yunfei Bai, Wanjun Gu, Fuyu Li, Zixi Hu, Tiansong Xia, Zuolei Dai, Xiafei Yu, Huamei Li, Yu Gu, Shaoxun Yuan, Rongxin Zhang, Haitao Li, Wenyong Zhu, Jianing Ding, Xiao Sun, Yun Liu, Hongde Liu, Xiaoan Liu
Summary: This study investigated the associations between dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) features and gene expression characteristics in breast cancer (BC). The researchers identified specific imaging features that were significantly associated with BC subtypes and prognosis, and developed classifiers to predict clinical receptors, PAM50 subtypes, and prognostic gene sets. These imaging features have the potential to non-invasively predict clinical characteristics and prognosis of breast cancer.
FRONTIERS IN ONCOLOGY
(2022)
Article
Oncology
Xiaoxin Hu, Luan Jiang, Chao You, Yajia Gu
Summary: The study results indicate that increased BPEV is highly correlated with a high risk of breast cancer, while FGT is not significantly associated.
FRONTIERS IN ONCOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Wakana Murakami, Shabnam Mortazavi, Tiffany Yu, Nikhita Kathuria-Prakash, Ran Yan, Cheryce Fischer, Kelly E. McCann, Stephanie Lee-Felker, Sung
Summary: This study evaluated the relationship between background parenchymal enhancement (BPE) levels and breast cancer risk, and found that premenopausal women with BRCA mutations had significantly lower BPE levels compared to non-high-risk premenopausal women.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Bethany L. Niell, Mahmoud Abdalah, Olya Stringfield, Natarajan Raghunand, Dana Ataya, Robert Gillies, Yoganand Balagurunathan
Summary: The use of quantitative BPE measures may outperform radiologist-assigned category in predicting breast cancer risk, especially at specific enhancement ratio thresholds like BPE%. Further research on risk prediction models incorporating quantitative measures is warranted.
AMERICAN JOURNAL OF ROENTGENOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Ali M. Hasan, Noor K. N. Al-Waely, Hadeel K. Aljobouri, Hamid A. Jalab, Rabha W. Ibrahim, Farid Meziane
Summary: Breast cancer is a highly concerning disease worldwide, and the use of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in breast cancer evaluation is increasing. This study focuses on using breast DCE-MRI to identify molecular subtypes, providing breast cancer patients with a better chance for an early and effective treatment plan.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Radiology, Nuclear Medicine & Medical Imaging
Sarah Eskreis-Winkler, Elizabeth J. Sutton, Donna D'Alessio, Katherine Gallagher, Nicole Saphier, Joseph Stember, Danny F. Martinez, Elizabeth A. Morris, Katja Pinker
Summary: This study aimed to develop a deep learning model for automated classification of background parenchymal enhancement (BPE) in breast MRI and compare its performance with current standard-of-care radiology report BPE designations. The results showed that the deep learning model significantly outperformed the radiology report in terms of performance and could provide more accurate BPE assessments.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2022)
Article
Oncology
Mitsuhiro Tozaki, Hidetake Yabuuchi, Mariko Goto, Michiro Sasaki, Kazunori Kubota, Hiroshi Nakahara
Summary: The study evaluated the effect of gadobutrol on background parenchymal enhancement (BPE) and differential diagnosis between benign and malignant lesions in dynamic MRI of the breast, finding no significant difference in breast cancer signal intensity (SI) in premenopausal patients but a significant difference in cancer/BPE ratio in premenopausal patients. Differentiation of benign and malignant masses was found to be most influenced by the mass margin.
Article
Radiology, Nuclear Medicine & Medical Imaging
Yoonho Nam, Ga Eun Park, Junghwa Kang, Sung Hun Kim
Summary: A deep-learning algorithm was developed and evaluated for breast FGT segmentation and BPE classification, showing high accuracy in BPE classification task.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
H. Sallam, L. Lenga, C. Solbach, S. Becker, T. J. Vogl
Summary: This study evaluated the prognostic value of background parenchymal enhancement (BPE) in breast magnetic resonance imaging (MRI) for high-risk breast cancer patients. The results showed weak or no significant correlations between BPE and patient age, fibroglandular tissue (FGT), Breast Imaging Reporting and Data System (BIRADS) categories, presence of breast cancer, and expression of human epidermal growth factor receptor 2 (HER2), progesterone receptor (PR), estrogen receptor (ER), and Ki67. Therefore, BPE in MRI may not be a reliable biomarker for breast cancer development.
CLINICAL RADIOLOGY
(2023)
Article
Computer Science, Interdisciplinary Applications
Seyedehnafiseh Mirniaharikandehei, Morteza Heidari, Gopichandh Danala, Sivaramakrishnan Lakshmivarahan, Bin Zheng
Summary: This study successfully utilized a random projection algorithm to develop and optimize a radiomics-based machine learning model for predicting peritoneal metastasis in gastric cancer patients, demonstrating the potential of CT images in predicting the risk of peritoneal metastasis.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Oncology
Megan E. Buechel, Danielle Enserro, Robert A. Burger, Mark F. Brady, Katrina Wade, Angeles Alvarez Secord, Andrew B. Nixon, Seyedehnafiseh Mirniaharikandehei, Hong Liu, Bin Zheng, David M. O'Malley, Heidi Gray, Krishnansu S. Tewari, Robert S. Mannel, Michael J. Birrer, Kathleen N. Moore
Summary: The increased subcutaneous fat density and visceral fat density are associated with higher risk of death in patients, and may affect the predictive efficacy of bevacizumab in ovarian cancer treatment.
GYNECOLOGIC ONCOLOGY
(2021)
Article
Engineering, Biomedical
Gopichandh Danala, Masoom Desai, Bappaditya Ray, Morteza Heidari, Sai Kiran R. Maryada, Calin Prodan, Bin Zheng
Summary: This study aims to develop and test a new fully-automated computer-aided detection (CAD) scheme to predict prognosis of aneurysmal subarachnoid hemorrhage (aSAH) patients. By segmenting CT images and computing image features, support vector machine (SVM) models were built to predict clinically relevant parameters and short-term and long-term clinical outcomes of patients.
ANNALS OF BIOMEDICAL ENGINEERING
(2022)
Article
Engineering, Biomedical
Tianyu Shi, Huiyan Jiang, Bin Zheng
Summary: This study proposes a network with a cross-modal and cross-attention mechanism for segmenting acute ischemic stroke lesions. The network achieves higher recall and F2 scores compared to other state-of-the-art models.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2022)
Article
Biochemical Research Methods
Ke Zhang, Xianglan Lu, Xuxin Chen, Roy Zhang, Kar-Ming Fung, Hong Liu, Bin Zheng, Shibo Li, Yuchen Qiu
Summary: This study initially verified the feasibility of utilizing FPM to develop a high-resolution and wide-field chromosome sample scanner.
JOURNAL OF BIOMEDICAL OPTICS
(2022)
Article
Instruments & Instrumentation
Tiancheng Gai, Theresa Thai, Meredith Jones, Javier Jo, Bin Zheng
Summary: The study developed a radiomics-based computer-aided diagnosis scheme for detecting and classifying suspicious pancreatic tumors in CT images. By applying image processing algorithms and machine learning methods, the scheme achieved accurate classification results with a high area under the receiver operating characteristic curve (AUC).
JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY
(2022)
Article
Instruments & Instrumentation
Muhammad U. Ghani, Farid H. Omoumi, Xizeng Wu, Laurie L. Fajardo, Bin Zheng, Hong Liu
Summary: This study compared the imaging performance of a CdTe-based PCD and a CMOS-based EID for phase sensitive imaging of breast cancer. The results showed that the PCD had a substantial improvement in the detection of simulated tumors, calcification clusters, and fibrous structures compared to the EID. At lower dose levels, the PCD images maintained good image quality.
JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY
(2022)
Article
Engineering, Biomedical
Meredith A. Jones, Rowzat Faiz, Yuchen Qiu, Bin Zheng
Summary: This study tested the hypothesis that handcrafted and automated features contain complementary classification information and found that the fusion of these two types of features can improve the performance of computer-aided diagnosis of medical images.
PHYSICS IN MEDICINE AND BIOLOGY
(2022)
Article
Clinical Neurology
Claire Delpirou Nouh, Bappaditya Ray, Chao Xu, Bin Zheng, Gopichand Danala, Ahmed Koriesh, Kimberly Hollabaugh, David Gordon, Evgeny Sidorov
Summary: Researchers found that GG can independently predict mortality in ICH patients and is positively correlated with intraparenchymal hemorrhage volume. However, causality between the two is not established and would require specifically designed studies.
TRANSLATIONAL STROKE RESEARCH
(2022)
Article
Oncology
Lili Wang, Peng Lv, Zhen Xue, Lihong Chen, Bin Zheng, Guifang Lin, Weiwen Lin, Jingming Chen, Jiangao Xie, Qing Duan, Jun Lu
Summary: This study developed novel predictive models based on CT to identify occult peritoneal metastasis (OPM) in advanced gastric cancer (AGC) patients. The clinical models and radiomics models showed comparable classification accuracy in identifying OPM, with high sensitivity when the specificity is higher than 90%.
Article
Computer Science, Artificial Intelligence
Xuxin Chen, Ximin Wang, Ke Zhang, Kar-Ming Fung, Theresa C. Thai, Kathleen Moore, Robert S. Mannel, Hong Liu, Bin Zheng, Yuchen Qiu
Summary: This paper reviews the recent studies on applying deep learning methods in medical image analysis, emphasizing the latest progress and contributions of state-of-the-art unsupervised and semi-supervised deep learning in this field. It also discusses major technical challenges and suggests possible solutions for future research efforts.
MEDICAL IMAGE ANALYSIS
(2022)
Article
Medicine, General & Internal
Xuxin Chen, Ke Zhang, Neman Abdoli, Patrik W. Gilley, Ximin Wang, Hong Liu, Bin Zheng, Yuchen Qiu
Summary: This study proposes a method for breast cancer diagnosis using multi-view vision transformers to capture long-range dependencies between multiple mammograms. The results show that the proposed method outperforms traditional CNNs and one-view two-side models in case classification performance.
Article
Radiology, Nuclear Medicine & Medical Imaging
Laurie L. Fajardo, Stephen L. Hillis, Bin Zheng, Molly Donovan Wong, Muhammad U. Ghani, Farid H. Omoumi, Yuhua Li, Peter Jenkins, Michael E. Peterson, Xizeng Wu, Hong Liu
Summary: This pilot study compared the performance of a phase-sensitive breast tomosynthesis (PBT) system with a conventional digital breast tomosynthesis (DBT) system. The results showed that the PBT system had a 24% lower radiation dose compared with the DBT system, but with lower image quality. The diagnostic performance of the PBT system remains to be determined in larger studies.
Article
Radiology, Nuclear Medicine & Medical Imaging
Warid Islam, Meredith Jones, Rowzat Faiz, Negar Sadeghipour, Yuchen Qiu, Bin Zheng
Summary: This study optimized a new deep transfer learning model by implementing a novel attention mechanism, improving the accuracy of breast lesion classification. Experimental results showed that the new CBAM-based ResNet50 model achieved a significantly higher AUC value compared to the standard ResNet50 model, further demonstrating the importance of attention mechanisms in optimizing deep transfer learning models.
Article
Biotechnology & Applied Microbiology
Gopichandh Danala, Sai Kiran Maryada, Warid Islam, Rowzat Faiz, Meredith Jones, Yuchen Qiu, Bin Zheng
Summary: This study investigates and compares the advantages and potential limitations of radiomics and deep transfer learning technologies in developing CAD schemes. The results demonstrate that using deep transfer learning is more efficient and enables higher lesion classification performance than using radiomics-based technology.
BIOENGINEERING-BASEL
(2022)