Article
Engineering, Biomedical
A. A. Kolchev, D. V. Pasynkov, I. A. Egoshin, I. V. Kliouchkin, O. O. Pasynkova
Summary: The research aimed to develop a noninvasive automated US grayscale image analysis based on mathematical image post-processing for differentiation of cystic and solid breast lesions. By feature selection and correlation analysis, the accuracy and specificity of lesion classification were improved.
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
(2022)
Article
Engineering, Electrical & Electronic
Gulhan Kilicarslan, Canan Koc, Fatih Ozyurt, Yeliz Gul
Summary: Medical Imaging with Deep Learning has become a prominent topic, with significant results in the classification of medical images using deep learning. Breast cancer was chosen as the focus due to its impact on women's mortality rate. In this study, ultrasound images were collected and three ResNet CNN architectures were used for feature extraction. The results showed that the proposed method outperformed classical deep learning approaches.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2023)
Article
Engineering, Biomedical
Ruihan Yao, Yufeng Zhang, Keyan Wu, Zhiyao Li, Meng He, Baoping Fengyue
Summary: This study proposes a small-window entropy based on adaptively decomposed ultrasound RF images for the diagnosis of breast lesions. By calculating the entropy values of different IMF images and their combinations, it is able to distinguish between benign and malignant lesions. The experimental results demonstrate that this method outperforms traditional methods in terms of diagnostic capability.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Tianwen Xie, Qiufeng Zhao, Caixia Fu, Robert Grimm, Yajia Gu, Weijun Peng
Summary: Compared with qualitative BI-RADS assessment, quantitative whole-lesion histogram analysis on dynamic contrast-enhanced (DCE) parametric maps was better at discriminating between small benign and malignant breast lesions (<= 1 cm) initially defined as suspicious on DCE-MRI.
EUROPEAN RADIOLOGY
(2022)
Article
Engineering, Biomedical
Mingue Song, Yanggon Kim
Summary: This paper introduces a simple yet powerful framework for breast ultrasound lesion characterization that effectively addresses the limitations of existing methods and achieves satisfactory discrimination performance. The method utilizes independent networks and diverse automated representations to train, and achieves good feature balance by adjusting the ratio.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2024)
Article
Oncology
Bin Xu, Weidong Luo, Xin Chen, Yiping Jia, Mengyuan Wang, Lulu Tian, Yi Liu, Bowen Lei, Jiayuan Li
Summary: This study compared the accuracy of Artificial Intelligent Breast Ultrasound (AIBUS) with hand-held breast ultrasound (HHUS) in asymptomatic women and provided recommendations for screening in regions with limited resources. The results showed that AIBUS had good image quality and moderate agreement with HHUS in the BI-RADS final recall assessment and breast density category. Additionally, AIBUS was more efficient for primary screening compared to HHUS.
FRONTIERS IN ONCOLOGY
(2023)
Article
Acoustics
Cheng Liu, Yaoheng Yang, Weibao Qiu, Yan Chen, Jiyan Dai, Lei Sun
Summary: High-frequency endoscopic QUS technique shows potential as a complementary method to distinguish colorectal malignancies by leveraging its morphological and micro-structural ultrasound information. The study found significant differences in mean Midband Fit (M) and intercept (I) between malignant and normal tissue regions, as well as in all mean FLD values of spectral parameter combinations.
Article
Engineering, Biomedical
Xiaoyan Shen, He Ma, Ruibo Liu, Hong Li, Jiachuan He, Xinran Wu
Summary: Breast cancer is a serious disease affecting women's health. Early screening based on ultrasound can help detect and treat tumors in the early stage. Computer-aided diagnosis technology can effectively segment breast ultrasound images for more accurate diagnosis and treatment.
BIOMEDICAL ENGINEERING ONLINE
(2021)
Article
Computer Science, Artificial Intelligence
Ruobing Huang, Mingrong Lin, Haoran Dou, Zehui Lin, Qilong Ying, Xiaohong Jia, Wenwen Xu, Zihan Mei, Xin Yang, Yijie Dong, Jianqiao Zhou, Dong Ni
Summary: Breast ultrasound (BUS) is effective for early detection of breast cancer, but automating nodule segmentation is challenging due to blurry edges and irregular shapes. To address this, we propose a boundary-rendering framework that highlights the importance of boundary for accurate segmentation and classification.
MEDICAL IMAGE ANALYSIS
(2022)
Article
Computer Science, Information Systems
Karima Amara Korba, Djamel Abed, Mohamed Fezari
Summary: In this work, two new cascaded chaotic maps were generated to enhance the complexity of chaos and improve the security of image transmission, achieving high peak signal-to-noise ratios and close-to-ideal entropies. These new maps outperformed competitive recently proposed maps in multimedia cryptosystems, showing strong resistance against attacks and high ciphering speed.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Engineering, Biomedical
Rahul Mehta, Yangyang Bu, Zheng Zhong, Guangyu Dan, Ping-Shou Zhong, Changyu Zhou, Weihong Hu, Xiaohong Joe Zhou, Maosheng Xu, Shiwei Wang, M. Muge Karaman
Summary: This study investigates quantitative imaging markers based on parameters from continuous-time random-walk (CTRW) and intravoxel incoherent motion (IVIM) models to characterize malignant and benign breast lesions using a machine learning algorithm. The histogram features of the CTRW and IVIM model parameters play important roles in distinguishing malignant and benign lesions. The performance of various machine learning classifiers, including Support Vector Machine, Random Forest, Naive Bayes, Gradient Boosted Classifier (GB), Decision Trees, AdaBoost, and Gaussian Process, was evaluated.
PHYSICS IN MEDICINE AND BIOLOGY
(2023)
Article
Computer Science, Information Systems
Adriano Pinto, Joana Amorim, Arsany Hakim, Victor Alves, Mauricio Reyes, Carlos A. Silva
Summary: Stroke is the second most common cause of death in developed countries, and rapid clinical assessment and intervention play a crucial role in improving patients' quality of life. Clinical interventions aim to restore perfusion deficits, and a deep learning method can automatically predict ischemic stroke tissue outcome.
Article
Computer Science, Interdisciplinary Applications
Xiaohui Di, Shengzhou Zhong, Yu Zhang
Summary: In this paper, a saliency map-guided hierarchical dense feature aggregation framework is proposed for breast lesion classification using breast ultrasound images. By generating saliency maps and constructing a triple-branch network, this method can extract and fuse features from foreground and background, thus improving the performance of breast lesion diagnosis.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Medicine, General & Internal
Ismini Papageorgiou, Nektarios A. Valous, Stathis Hadjidemetriou, Ulf Teichgraeber, Ansgar Malich
Summary: This study proposes a histogram-based shear-wave elastography (SWE) analysis to improve breast malignancy detection. Compared to conventional SWE metrics, the histogram method shows differences between malignant and benign tumors and reveals the reduction of soft-tissue components as a significant SWE biomarker. However, the diagnostic accuracy of the suggested method is still low and needs improvement in future studies.
Article
Mathematics, Applied
Katarzyna Mazowiecka, Jean Van Schaftingen
Summary: This paper provides a quantitative characterization of traces on the boundary of Sobolev maps and establishes some properties and conditions.
COMMUNICATIONS IN CONTEMPORARY MATHEMATICS
(2023)
Letter
Oncology
Nicholas Meti, Ali Sadeghi-Naini, William T. Tran
JCO CLINICAL CANCER INFORMATICS
(2021)
Article
Oncology
Hadi Moghadas-Dastjerdi, Shan-E-Tallat Hira Rahman, Lakshmanan Sannachi, Frances C. Wright, Sonal Gandhi, Maureen E. Trudeau, Ali Sadeghi-Naini, Gregory J. Czarnota
Summary: This study successfully predicted the response of breast cancer patients to neoadjuvant chemotherapy by analyzing features of CT images and utilizing machine learning techniques. Implementing a personalized treatment approach, this method improved treatment outcomes.
TRANSLATIONAL ONCOLOGY
(2021)
Article
Multidisciplinary Sciences
Majid Jaberipour, Hany Soliman, Arjun Sahgal, Ali Sadeghi-Naini
Summary: This study utilized machine learning techniques and quantitative MRI features to investigate the effectiveness of predicting local failure in patients with brain metastasis. The findings suggest that quantitative MRI biomarkers can improve the accuracy of predicting therapy outcomes.
SCIENTIFIC REPORTS
(2021)
Article
Multidisciplinary Sciences
Hamidreza Taleghamar, Seyed Ali Jalalifar, Gregory J. Czarnota, Ali Sadeghi-Naini
Summary: This study investigates the use of deep learning and quantitative ultrasound multi-parametric imaging to predict breast cancer response to neo-adjuvant chemotherapy. The developed deep convolutional neural network model successfully predicts the response and shows significant differences in survival rates between responders and non-responders when predicted before treatment.
SCIENTIFIC REPORTS
(2022)
Article
Engineering, Biomedical
Khadijeh Saednia, William T. Tran, Ali Sadeghi-Naini
Summary: This study proposes a multi-scale attention-guided deep learning model for accurate classification of breast tissue in digital histology images. By analyzing images at low and high magnifications using parallel convolutional neural networks and incorporating an attention mechanism, the model improves the accuracy of deep learning models in classifying digital histology images.
COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Seyed Ali Jalalifar, Hany Soliman, Arjun Sahgal, Ali Sadeghi-Naini
Summary: This study introduces a novel deep learning architecture that utilizes treatment-planning MRI and standard clinical attributes to predict the outcome of local control/failure in brain metastasis treated with stereotactic radiation therapy. The results demonstrate the promising potential of MRI deep learning features for outcome prediction and highlight the importance of tumor/lesion margins in local outcome prediction for brain metastasis.
Article
Multidisciplinary Sciences
Khadijeh Saednia, Andrew Lagree, Marie A. Alera, Lauren Fleshner, Audrey Shiner, Ethan Law, Brianna Law, David W. Dodington, Fang- Lu, William T. Tran, Ali Sadeghi-Naini
Summary: This study utilizes machine learning and quantitative digital histopathology to predict the response of breast cancer to neoadjuvant chemotherapy. The results show that this method can accurately predict the treatment response of breast cancer, providing guidance for the treatment of breast cancer patients.
SCIENTIFIC REPORTS
(2022)
Article
Oncology
Seyed Ali Jalalifar, Hany Soliman, Arjun Sahgal, Ali Sadeghi-Naini
Summary: This study investigated the impact of using less accurate but automatically generated tumor outlines on the efficacy of imaging biomarkers for predicting the response of brain metastasis to radiotherapy. The findings suggest that the imaging biomarkers and prediction models are resilient to imperfections in the automatically generated tumor masks.
Review
Oncology
Christopher J. Pinard, Andrew Lagree, Fang- Lu, Jonathan Klein, Michelle L. Oblak, Roberto Salgado, Juan Carlos Pinto Cardenas, Barbara Brunetti, Luisa Vera Muscatello, Giuseppe Sarli, Maria Pia Foschini, Alexandros Hardas, Simon P. Castillo, Khalid AbdulJabbar, Yinyin Yuan, David A. Moore, William T. Tran
Summary: Laboratory experiments studying solid tumors are limited. Veterinary oncology provides a naturally occurring cancer model that could complement biomarker discovery, clinical trials, and drug development. Comparative research studies involving veterinary oncology may bridge the translational pathway to human studies and advance the discovery of new treatment strategies, such as immunotherapies.
Article
Oncology
Tara Behroozian, Lauren Milton, Irene Karam, Liying Zhang, Keyue Ding, Julia Lou, Francois Gallant, Eileen Rakovitch, William Tran, Hany Soliman, Eric Leung, Danny Vesprini, Ewa Szumacher, Hanbo Chen, Elysia Donovan, Jacqueline Lam, Silvana Spadafora, Matt Wronski, Chris Lavoie, Natalie Walde, Emily Lam, Gina Wong, Erin McKenzie, Krista Ariello, Samantha Kennedy, Saba Shariati, Katherine Carothers, Glen Gonzales, Yulya Kagan, Edward Chow
Summary: A confirmatory randomized controlled trial was conducted to evaluate the effectiveness of Mepitel film (MF) in reducing radiation dermatitis (RD) in patients undergoing breast radiotherapy. The results showed that MF significantly reduced the incidence of grade 2 or 3 RD and had positive effects on patient-reported outcomes and clinician-reported outcomes.
JOURNAL OF CLINICAL ONCOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Niusha Kheirkhah, Sergio Dempsey, Ali Sadeghi-Naini, Abbas Samani
Summary: This study proposes a technique to improve the accuracy of displacement data in ultrasound elastography, especially in the lateral direction. The technique uses mathematical constraints to regularize displacement and strain fields, resulting in substantial improvement in image quality.
Article
Computer Science, Information Systems
Seyed Ali Jalalifar, Hany Soliman, Arjun Sahgal, Ali Sadeghi-Naini
Summary: This study introduces a novel system for automatic assessment of Stereotactic Radiation Therapy (SRT) outcome in brain metastasis using standard serial MRI. The system utilizes a deep learning-based segmentation framework to delineate tumors longitudinally on serial MRI with high precision and analyze the longitudinal changes in tumor size to evaluate therapy outcome and detect adverse radiation effects (ARE). The comparison between automatic evaluation and manual assessments by experts shows a high agreement. This study is of great significance for the workflow in radio-oncology.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Engineering, Biomedical
Seyed Ali Jalalifar, Hany Soliman, Arjun Sahgal, Ali Sadeghi-Naini
Summary: This study proposes and investigates new explainable deep-learning models for predicting the outcome of radiotherapy for brain metastases. The proposed self-attention-guided 3D residual network outperforms other models in accuracy, F1-score, and AUC. The visualization results demonstrate the importance of lesion characteristics in treatment-planning MRI for predicting local outcome.
IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE
(2023)
Meeting Abstract
Medicine, Research & Experimental
David Dodington, Andrew Lagree, Sami Tabbarah, Majidreza Mohebpour, Ali Sadeghi-Naini, William Tran, Fang-I Lu
LABORATORY INVESTIGATION
(2021)
Meeting Abstract
Pathology
David Dodington, Andrew Lagree, Sami Tabbarah, Majidreza Mohebpour, Ali Sadeghi-Naini, William Tran, Fang-I Lu