A5003610429- Radiomics and Machine Learning in Medical Imaging
- Prostate Cancer Treatment and Research
- Prostate Cancer Diagnosis and Treatment
- Renal cell carcinoma treatment
- MRI in cancer diagnosis
- AI in cancer detection
- Machine Learning in Healthcare
- Renal and Vascular Pathologies
- Robotics and Sensor-Based Localization
- 3D Surveying and Cultural Heritage
- Renal and related cancers
- Advanced Image and Video Retrieval Techniques
- Advanced X-ray and CT Imaging
Ministry of Industry and Information Technology
2022-2025
Beihang University
2022-2025
Beijing Jiaotong University
2020
Localization accuracy is a fundamental requirement for Simultaneous and Mapping (SLAM) systems. Traditional visual SLAM (vSLAM) schemes are usually based upon the assumption of static environments, so they do not perform well in dynamic environments. While number vSLAM frameworks have been reported localization unsatisfactory. In this article, we present novel motion detection segmentation method using Red Green Blue-Depth (RGB-D) data to improve feature-based RGB-D To overcome problem due...
This study aimed to develop deep learning (DL) models based on multicentre biparametric magnetic resonance imaging (bpMRI) for the diagnosis of clinically significant prostate cancer (csPCa) and compare performance these with that Prostate Imaging Reporting Data System (PI-RADS) assessment by expert radiologists multiparametric MRI (mpMRI).We included 1861 consecutive male patients who underwent radical prostatectomy or biopsy at seven hospitals mpMRI. These were divided into training (1216...
Early prediction of treatment response to neoadjuvant therapy (NAT) in breast cancer patients can facilitate timely adjustment regimens. We aimed develop and validate a MRI-based enhanced self-attention network (MESN) for predicting pathological complete (pCR) based on longitudinal images at the early stage NAT. Two imaging datasets were utilized: subset from ACRIN 6698 trial (dataset A, n = 227) prospective collection Chinese hospital B, 245). These divided into three cohorts: an training...
Abstract Objective The objective of this study was to explore the application radiomics combined with machine learning establish different models assist in diagnosis venous wall invasion patients renal cell carcinoma and tumor thrombus evaluate diagnostic efficacy. Materials Methods We retrospectively reviewed data 169 Peking University Third Hospital from March 2015 January 21, who diagnosed as mass invasion. According intraoperative findings, 111 were classified group 58 cases non-invasion...
The management of complex renal cysts is guided by the Bosniak classification system, which may be inadequate for risk stratification patients to determine appropriate intervention. Radiomics models based on CT imaging provide additional useful information. A total 322 with II-IV were included in study from January 2010 December 2019. Contrast-enhanced scans performed all patients. ITK-snap was used segmentation, and PyRadiomics 3.0.1 package feature extraction. radiomics features screened...
Abstract Purpose: To construct deep learning (DL) models based on multicentre biparametric MRI (bpMRI) for the diagnosis of clinically significant prostate cancer (csPCa), and compare performance these with that Prostate Imaging Reporting Data System (PI-RADS) assessment expert-level radiologists multiparametric (mpMRI). Methods: This study included 1861 consecutive men mpMRI from seven hospitals, who underwent radical prostatectomy or biopsy. These patients were divided into training cohort...