View clinical trials related to Deep Learning.
Filter by:This study (IEDAL study) intends to prospectively enroll more than 6800 patients who will undergo head CT angiography (CTA) scanning in the outpatient clinic. It will be carried out in 25 hospitals in more than 10 provinces in China. The patient's head CTA images will be randomly assigned to the True-AI and Sham-AI group with a ratio of 1:1, and the patients and radiologists are unaware of the allocation. The primary outcomes are sensitivity and specificity of detecting intracranial aneurysms. The secondary outcomes focus on the prognosis and outcomes of the patients.
The early noninvasive screening of patients suitable for neoadjuvant chemotherapy (NCT) is essential for personalized treatment in locally advanced gastric cancer (LAGC). The aim of this study was to develop and visualized a radio-clinical biomarker from pretreatment oversampled CT images to predict the response and prognosis to NCT in LAGC patients.
CT-enhanced scans are routine imaging modality for the diagnosis and follow-up of liver disease. However, this means that patients will receive more radiation dose. Therefore, it is necessary to reduce the radiation dose received by patients as much as possible. Deep learning-based reconstruction algorithms have been introduced to improve image quality recently. For many years, researchers attempt to maintain image quality using an advanced method while reducing radiation dose. Recently, a new deep-learning based iterative reconstruction algorithm, namely artificial intelligence iterative reconstruction (AIIR, United Imaging Healthcare, Shanghai, China) has been introduced. In this study, we evaluate the image and diagnostic qualities of AIIR for low-dose portal vein and delayed phase liver CT with those of a KARL method normally used in standard-dose CT.
This registry has the following objectives. First, according to the guidance of 2021 WHO of CNS classification, we constructed and externally tested a multi-task DL model for simultaneous diagnosis of tumor segmentation, glioma classification and more extensive molecular subtype, including IDH mutation, ATRX deletion status, 1p19q co-deletion, TERT gene mutation status, etc. Second, based on the same ultimate purpose of liquid biopsy and radiomics, we innovatively put forward the concept and idea of combining radiomics and liquid biopsy technology to improve the diagnosis of glioma. And through our study, it will provide some clinical validation for this concept, hoping to supply some new ideas for subsequent research and supporting clinical decision-making.
In this study, the investigators used the optical flow method to measure the colonoscopy withdrawal speed, and doctors were selected from multiple hospitals to collect prospective colonoscopy screening videos, and the percentage of colonoscopy withdrawal overspeed was calculated to explore the relationship between it based on optical flow method and the adenoma detection rate.
To improve the accuracy of risk prediction, screening and treatment outcome of cancer, we aim to establish a medical database that includes standardized and structured clinical diagnosis and treatment information, image features, pathological features, and multi-omics information and to develop a multi-modal data fusion-based technology system using artificial intelligence technology based on database.
This project will use deep learning to classify colonoscopy images of different severity of ulcerative colitis, so as to assist clinicians in the accurate diagnosis of ulcerative colitis.
In this study, the AI-assisted system EndoAngel has the functions of reminding the ileocecal junction, withdrawal time, withdrawal speed, sliding lens, polyps in the field of vision, etc. These functions can assist novice endoscopists in performing colonoscopy and improve the quality.
Clinician and the multidisciplinary team meeting in oncologic urology (MMO) play a key-role in the decision making. An unexplained surgeon attributable variance, probably linked to the subjective "eyeball test" effect, was identified as a strongest factor underlying non-compliance with guide line recommendations in the management of bladder cancer. So high-quality studies that identify barriers and modulators (such as comorbidities) of provider-level adoption of guidelines and how comorbidities are associated in making therapeutic choice and their impact in bladder cancer specific survival and overall survival, are crucial. To identify patients at high risk of early death, and to improve specific guideline for treatment might be decisive. In order to assess survival, where mortality events compete, it will be more appropriate to compute a Cumulative Incidence Function (namely CIF). The investigators will compare outcomes across patient populations to obtain information to improve clinical decision-making. Such learning will be done through the use of neural networks or by applying population-based approaches, such as Genetic Algorithms (GA), Ant Colony Systems (ACS) and Particle Swarm Optimization (PSO), using as a four-stage based approach. First, the investigators propose a "pretopology space" in order to study a dynamic phenomenon. Second, the investigators recall that the K-means approach remains one of the most used approaches for classifying a set of elements (patients / persons / others) into K (disjunctive) clusters. Third, the investigators propose a learning pretopology space for enhancing the clustering. Such an approach can be assimilated in spirit to one applied with high success on deep learning. Fourth and last, the investigators propose a reactive method that is able to include some new elements or remove some contained elements
This study aims to compare image qualities between conventionally reconstructed MRI sequences and deep-learning reconstructed MRI sequences from the same data in patients who undergo Gd-EOB-DTPA enhanced liver MRI. The AIRTM deep learning sequence is applicable for various MRI sequences including T2-weighted image (T2WI), T1-weighted image and diffusion-weighted image (DWI). We plan to perform intra-individual comparisons of the image qualities between two reconstructed image datasets.