Article
Computer Science, Information Systems
Imran Ul Haq, Haider Ali, Hong Yu Wang, Cui Lei, Hazrat Ali
Summary: The world is facing a concerning situation regarding breast cancer patients. A Computer-Aided Diagnosis (CAD) system based on deep convolution neural network (DCNN) and feature fusion has been proposed to improve the detection and classification of abnormalities in mammographic scans. The model achieved high sensitivity, specificity, and accuracy in the evaluation on two publicly available datasets.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Meredith A. A. Jones, Negar Sadeghipour, Xuxin Chen, Warid Islam, Bin Zheng
Summary: This study aims to develop and test a novel CAD framework that optimally fuses information extracted from ipsilateral views of bilateral mammograms using both deep transfer learning (DTL) and radiomics feature extraction methods, in order to classify between malignant and benign breast lesions.
Review
Chemistry, Analytical
Joanna Czajkowska, Martyna Borak
Summary: Computer-aided diagnosis systems have been widely used in clinical practice, providing assistance to clinicians in daily diagnostic tasks. The rapid development of image processing techniques, especially in high-frequency ultrasound analysis, has opened up new possibilities in dermatology, allergology, cosmetology, and aesthetic medicine. This paper presents a comprehensive overview of high-frequency ultrasound image processing techniques and discusses the bridge between diagnostic needs and existing solutions, as well as their limitations and future directions.
Article
Automation & Control Systems
Charles Arputham, Krishnaraj Nagappan, Lenin Babu Russeliah, Adaline Suji Russeliah
Summary: This study focuses on efficient breast cancer diagnosis and classification using deep learning techniques for mammography. By combining preprocessing, segmentation, feature extraction, and classification, the proposed model achieved a maximum classification accuracy level of 99.13% and outperformed other classifiers in the experiments.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2021)
Article
Biology
Haythem Ghazouani, Walid Barhoumi
Summary: Analyzing local texture and generating features are crucial for automatic cancer detection in mammographic images. Deep neural networks have shown promise as an alternative to hand-driven features, but require large and balanced training data. This study proposes a fully-automated method for breast cancer diagnosis using small sets of data and a genetic programming-based descriptor for feature extraction.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Computer Science, Information Systems
Guanjie Liu, Yan Wei, Yunshen Xie, Jianqiang Li, Liyan Qiao, Ji-Jiang Yang
Summary: The study introduces an aided diagnostic system for Ocular Myasthenia Gravis, which calculates three clinical indicators from eye images to assist in diagnosis and reduce time and effort. The system was evaluated and showed promising results, with the potential for widespread application in clinical practice.
TSINGHUA SCIENCE AND TECHNOLOGY
(2021)
Review
Computer Science, Artificial Intelligence
Ramzi Guetari, Helmi Ayari, Houneida Sakly
Summary: The diagnostic phase is crucial in patient guidance and follow-up, as its accuracy and effectiveness can determine the patient's outcome. Machine learning offers new solutions to healthcare professionals, saving time and optimizing diagnosis.
KNOWLEDGE AND INFORMATION SYSTEMS
(2023)
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)
Article
Business
Vasundhara Acharya, Vinayakumar Ravi, Tuan D. Pham, Chinmay Chakraborty
Summary: This article proposes a new computer-aided diagnosis model to accurately segment blood smear images and identify the stage of acute myeloid leukemia (AML). The model utilizes machine learning algorithms to classify different types of cells, achieving a high accuracy rate.
IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT
(2023)
Article
Oncology
Jing-Hang Ma, Shang-Feng You, Ji-Sen Xue, Xiao-Lin Li, Yi-Yao Chen, Yan Hu, Zhen Feng
Summary: Computer-aided diagnosis system plays an important role in cervical lesion diagnosis by using auto-segmented colposcopic images to extract features, augmenting minority data, and generating preliminary diagnosis results. The system improves sensitivity while maintaining acceptable specificity and accuracy.
FRONTIERS IN ONCOLOGY
(2022)
Article
Computer Science, Information Systems
Guliz Toz, Pakize Erdogmus
Summary: This study proposes a hybrid thresholding method for efficient segmentation of mammograms in CAD systems, which can reduce the number of suspicious regions and provide fully-automatic segmentation of these regions.
Article
Engineering, Biomedical
Dezhong Bi, Dongxia Zhu, Fatima Rashid Sheykhahmad, Mingqi Qiao
Summary: This study develops a computer-aided diagnosis system for accurate diagnosis of skin cancer, which outperforms traditional methods and other new algorithms. By optimizing feature selection and using support vector machine classifier, the proposed method achieves higher detection rates and lower false acceptance and rejection rates.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Computer Science, Artificial Intelligence
Yuanzhe Deng, Matthew Mueller, Chris Rogers, Alison Olechowski
Summary: The emerging multi-user CAD systems have the potential for collaborative learning, leading to the proposal of a MUCAD collaborative learning framework. This framework interprets user actions from MUCAD software and observes differences in CAD behavior among different user types.
ADVANCED ENGINEERING INFORMATICS
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Si Eun Lee, Kyunghwa Han, Eun-Kyung Kim
Summary: This study compared the diagnostic agreement and performances of synthetic and conventional mammograms when artificial intelligence-based computer-assisted diagnosis (AI-CAD) is used. The results showed good agreement and comparable diagnostic performance between the two types of mammograms, indicating that AI-CAD can work well on synthetic mammograms.
EUROPEAN RADIOLOGY
(2021)
Article
Endocrinology & Metabolism
Lin-Lin Zheng, Su-Ya Ma, Ling Zhou, Cong Yu, Hai-Shan Xu, Li-Long Xu, Shi-Yan Li
Summary: This study aimed to evaluate the ability of a computer-aided diagnosis system based on artificial intelligence (AI-CADS) to predict thyroid malignancy by analyzing different ultrasound sections of thyroid nodules. The study included patients with preoperative ultrasound data and postoperative pathological results, and assessed the diagnostic performance and consistency of AI-CADS in different sections. The results showed that the performance of AI-CADS was better in the transverse section, and certain ultrasonic features had higher diagnostic agreement.
FRONTIERS IN ENDOCRINOLOGY
(2023)
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
Radiology, Nuclear Medicine & Medical Imaging
Muhammad U. Ghani, Xizeng Wu, Laurie L. Fajardo, Zhengxue Jing, Molly D. Wong, Bin Zheng, Farid Omoumi, Yuhua Li, Aimin Yan, Peter Jenkins, Stephen L. Hillis, Laura Linstroth, Hong Liu
Summary: This article reports the preclinical evaluation and comparison of the first x-ray phase sensitive breast tomosynthesis system for breast cancer diagnosis. Results showed improvements in contrast resolution, spatial resolution, and conspicuity with the PBT system, validated by signal-to-noise ratio values, particularly in depicting microcalcifications.
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)