Review
Oncology
Yun Qin, Li-Hua Zhu, Wei Zhao, Jun-Jie Wang, Hao Wang
Summary: This article summarizes the application of radiomics and dosiomics in medical imaging, particularly in tumor diagnosis and prognosis modeling. It also discusses the latest research progress of dosiomics in radiation oncology, providing new ideas for the treatment of future related diseases.
FRONTIERS IN ONCOLOGY
(2022)
Article
Biology
Amine Amyar, Romain Modzelewski, Pierre Vera, Vincent Morard, Su Ruan
Summary: In this study, a multi-task, multi-scale learning framework is proposed to predict patient survival and treatment response. The results show that this framework can extract meaningful and powerful features, improving the performance of radiomics. The subsidiary tasks provide an inductive bias, enabling the model to better generalize.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Medicine, Research & Experimental
Xiaoli Zheng, Wei Guo, Yunhan Wang, Jiang Zhang, Yuanpeng Zhang, Chen Cheng, Xinzhi Teng, Saikit Lam, Ta Zhou, Zongrui Ma, Ruining Liu, Hui Wu, Hong Ge, Jing Cai, Bing Li
Summary: This study aimed to predict the occurrence of acute radiation esophagitis (ARE) in patients with locally advanced lung cancer (LALC) treated with intensity-modulated radiation therapy (IMRT) using multi-omics features, including radiomics and dosiomics. Four classification models were constructed based on the extracted features. The results showed that these multi-omics features can accurately predict the occurrence of ARE.
EUROPEAN JOURNAL OF MEDICAL RESEARCH
(2023)
Review
Gastroenterology & Hepatology
Pak Kin Wong, In Neng Chan, Hao-Ming Yan, Shan Gao, Chi Hong Wong, Tao Yan, Liang Yao, Ying Hu, Zhong-Ren Wang, Hon Ho Yu
Summary: This study focuses on the application of deep learning technology in radiomics for gastrointestinal cancers, providing comprehensive analysis of challenges and recommendations to advance DLR.
WORLD JOURNAL OF GASTROENTEROLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Xin Jin, Yuze Li, Fei Yan, Ye Liu, Xinghua Zhang, Tao Li, Li Yang, Huijun Chen
Summary: An automatic system combining neural network and radiomics was proposed for coronary plaque detection, classification, and stenosis grading, achieving high accuracy and efficiency in the detection and analysis of coronary plaques.
EUROPEAN RADIOLOGY
(2022)
Article
Medicine, General & Internal
Yangyang Zhu, Zheling Meng, Xiao Fan, Yin Duan, Yingying Jia, Tiantian Dong, Yanfang Wang, Juan Song, Jie Tian, Kun Wang, Fang Nie
Summary: The study developed a DL radiomics model based on ultrasound images to assist radiologists in diagnosing unexplained CLA, achieving accurate classification of specific etiologies. The DL model significantly improved the accuracy, sensitivity, and specificity of radiologists with different levels of experience, reducing false-negative and false-positive rates.
Article
Computer Science, Artificial Intelligence
Weichen Zhang, Dong Xu, Jing Zhang, Wanli Ouyang
Summary: The proposed Progressive Modality Cooperation (PMC) framework effectively transfers knowledge between source and target domains by utilizing multiple modality clues under MMDA and MMDA-PI settings. Through effective collaboration among multiple modalities, reliable pseudo-labeled target samples are selected, capturing modality-specific and modality-integrated information.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Mingzhen Chen, Chunli Kong, Enqi Qiao, Yaning Chen, Weiyue Chen, Xiaole Jiang, Shiji Fang, Dengke Zhang, Minjiang Chen, Weiqian Chen, Jiansong Ji
Summary: This study compared the accuracy of predicting TACE outcomes for HCC patients using four different classifiers. The DNN model performed better than others and integrated with clinically significant factors to create the CD model, which may be valuable in pre-treatment counseling for HCC patients who may benefit from TACE intervention.
INSIGHTS INTO IMAGING
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Lulu Peng, Zehong Yang, Jue Liu, Yi Liu, Jianwei Huang, Junwei Chen, Yun Su, Xiang Zhang, Ting Song
Summary: This study aimed to explore whether deep learning radiomics (DLR) from MRI can be used to identify pregnancies with placenta accreta spectrum (PAS). The analysis of the training and validation datasets showed that the MRI-based DLR model had better performance in diagnosing PAS compared to the clinical model and MRI morphologic model.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2023)
Article
Oncology
Bingxin Gu, Mingyuan Meng, Lei Bi, Jinman Kim, David Dagan Feng, Shaoli Song
Summary: This study aimed to explore the capability of deep learning-based radiomics (DLR) for predicting 5-year progression-free survival (PFS) in advanced nasopharyngeal carcinoma (NPC). By developing a deep learning model and integrating clinical and traditional radiomics features, the DLR model showed good performance in predicting PFS.
FRONTIERS IN ONCOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Zhiyong Zhou, Xusheng Qian, Jisu Hu, Guangqiang Chen, Caiyuan Zhang, Jianbing Zhu, Yakang Dai
Summary: Researchers developed a user-friendly artificial intelligence-assisted diagnosis modeling software platform called AIMS, which provides standardized machine learning-based workflows for computer-assisted diagnosis and prognosis systems using medical images. AIMS contains both radiomics and CNN-based deep learning workflows, making it an all-in-one software platform for machine learning-based medical image analysis. The modular design of AIMS allows users to easily build machine learning models, comprehensively test models, and compare their performance in specific applications. The GUI of AIMS enables users to process large numbers of medical images without programming or script addition. Furthermore, AIMS provides a flexible image processing toolkit for various types of analysis.
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
(2023)
Article
Environmental Sciences
Tao Lei, Linze Li, Zhiyong Lv, Mingzhe Zhu, Xiaogang Du, Asoke K. Nandi
Summary: A multi-modality and multi-scale attention fusion network was proposed for land cover classification from very high-resolution remote sensing images, achieving better classification results through feature fusion and spatial context enhancement.
Article
Computer Science, Artificial Intelligence
Zheng Cao, Chuanbin Sun, Wenzhe Wang, Xiangshang Zheng, Jian Wu, Honghao Gao
Summary: Optic neuropathy is a common eye disease that causes irreversible vision loss if not diagnosed early. The deep learning architecture GroupFusionNet (GFN) proposed in this paper effectively diagnoses five types of optic neuropathy with an accuracy of 87.82% on the test dataset, by combining multi-modalities and utilizing ResNet pathways.
PATTERN RECOGNITION LETTERS
(2021)
Article
Biology
Yassine Bouchareb, Pegah Moradi Khaniabadi, Faiza Al Kindi, Humoud Al Dhuhli, Isaac Shiri, Habib Zaidi, Arman Rahmim
Summary: The study highlights the significant potential of AI methods in the diagnosis and prognosis of COVID-19 infections. Interest among the scientific community in using imaging biomarkers for detection and management of COVID-19 is evident. The review outlines AI-based COVID-19 analysis workflows and discusses existing limitations, showcasing potential improvements that can be made.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Review
Biochemical Research Methods
Yixuan Qiao, Lianhe Zhao, Chunlong Luo, Yufan Luo, Yang Wu, Shengtong Li, Dechao Bu, Yi Zhao
Summary: Digital pathology research utilizes computational technologies to improve the efficiency of diagnosis and treatment, with artificial intelligence algorithms having significant advantages in data analysis. This article investigates the use of hematoxylin-eosin stained tissue slide images to address the imbalance of healthcare resources and discusses the opportunities and challenges of artificial intelligence.
BRIEFINGS IN BIOINFORMATICS
(2022)
Review
Oncology
Xingping Zhang, Yanchun Zhang, Guijuan Zhang, Xingting Qiu, Wenjun Tan, Xiaoxia Yin, Liefa Liao
Summary: This review summarizes the characteristics and advancements of radiomics and deep learning in oncology, and discusses their clinical utility and methodological robustness. It also identifies the barriers and proposes solutions for integrating these methods into clinical practice.
CRITICAL REVIEWS IN ONCOLOGY HEMATOLOGY
(2022)