View clinical trials related to Artificial Intelligence.
Filter by:All subjects shall sign informed consent before screening, and subjects shall be included according to inclusion and exclusion criteria. A total of four endoscopists were included in the study, two in each group of senior endoscopists and two in each group of junior endoscopists. Patients were randomly enrolled into the senior endoscopy group and the junior endoscopy group, and received artificial intelligence assisted colonoscopy and conventional colonoscopy successively. The two colonoscopy methods were performed back to back by different endoscopy physicians with the same seniority. All patients were examined and treated according to routine medical procedures. The routine colonoscopy group and the artificial-intelligence-assisted colonoscopy group made detailed records of the patients' withdrawal time, entry time, number of polyps detected, polyp Paris classification, polyp size, polyp shape, polyp location and intestinal preparation during the colonoscopy process
Digestive endoscopy center of the second affiliated hospital of medical college of zhejiang university and engineers of naki medical co., ltd. in Hong Kong independently developed an ai-assisted diagnostic model of digestive endoscopy in the early stage, namely the deep learning model.The deep learning model through the early stage of the study, is able to identify lesions of digest tract.The sensitivity for the diagnosis of some diseases, such as colon polyps, is 99%. On the one hand, this auxiliary diagnostic model can guide endoscopic examination for beginners; on the other hand, it can improve the detection rate of lesions and reduce the rate of missed diagnosis; on the other hand, the overall operating efficiency of the endoscopic center is improved, which is conducive to the quality control of endoscopic examination. Now the AI-assisted diagnostic model has been further improved, and it is planned to carry out further clinical verification in the digestive endoscopy center of our hospital. It is connected to the endoscopic system of our hospital and used simultaneously with the existing image-text system of endoscopy to compare the practicability, sensitivity and specificity of AI-assisted diagnosis model in the diagnosis of digestive tract diseases, and focus on the quality control of endoscopic examination.
The standard treatment for non-operative cervical cancer is concurrent external radiation therapy and chemotherapy followed by brachytherapy. During the period of radiotherapy, organ movement and tumor shrinkage may lead to insufficient or excessive radiation dose for the tumor and organs at risk. Adaptive radiotherapy can use images information acquired during treatment as feedback to reduce errors. Total 122 cases of cervical cancer with stage IB2-IVA will be randomly enrolled. Concurrent external volumetric rotational intensity modulated radiotherapy and chemotherapy followed by image-guided adaptive brachytherapy is the treatment strategies of control group patients. Concurrent adaptive external volumetric rotational intensity modulated radiotherapy and chemotherapy followed by image-guided adaptive brachytherapy is the treatment strategies of experimental group patients. CT repositioning will be performed after 15fractions of external radiotherapy, then new target volume will be contoured and new radiotherapy plan will be formulated with the assistance of artificial intelligence program. New radiotherapy plan will be performed from the 17th fraction external radiotherapy. Information on side effects, survival, dosimetry, imaging, clinical features, and cost-effectiveness will be collected. The statistical analysis is as follows, First is the difference in grade 3 side effects between the two groups. Second is 2-year PFS and OS differences between the two groups. Third is relationship between dosimetric differences and prognosis. Fourth one is to analyze the prognostic and predictive factors of adaptive radiotherapy from the patient's clinical characteristics, Positron emission tomography-computed tomography(PET/CT), Magnetic Resonance Imaging(MRI) and other multimodal information. Fifth is cost-benefit analysis of Artificial Intelligence(AI).
The aim of this study is to show the physiological changes during manic episode in bipolar mania how much they differentiate from remission and healthy control. Relation of audio-visual features as physiological changes and cognitive functions and clinical variables will be searched. The aim is to find biologic markers for predictors of treatment response via machine learning techniques to be able to reduce treatment resistance and give an idea for personalized treatment of bipolar patients.
Rationale: Diminutive colorectal polyps (1-5mm in size) have a high prevalence and very low risk of harbouring cancer. Current practice is to send all these polyps for histopathological assessment by the pathologist. If an endoscopist would be able to correctly predict the histology of these diminutive polyps during colonoscopy, histopathological examination could be omitted and practise could become more time- and cost-effective. Studies have shown that prediction of histology by the endoscopist remains dependent on training and experience and varies greatly between endoscopists, even after systematic training. Computer aided diagnosis (CAD) based on convolutional neural networks (CNN) may facilitate endoscopists in diminutive polyp differentiation. Up to date, studies comparing the diagnostic performance of CAD-CNN to a group of endoscopists performing optical diagnosis during real-time colonoscopy are lacking. Objective: To develop a CAD-CNN system that is able to differentiate diminutive polyps during colonoscopy with high accuracy and to compare the performance of this system to a group of endoscopist performing optical diagnosis, with the histopathology as the gold standard. Study design: Multicentre, prospective, observational trial. Study population: Consecutive patients who undergo screening colonoscopy (phase 2) Main study parameters/endpoints: The accuracy of optical diagnosis of diminutive colorectal polyps (1-5mm) by CAD-CNN system compared with the accuracy of the endoscopists. Histopathology is used as the gold standard.
Probe-based confocal laser endomicroscopy (pCLE) is an endoscopic technique that enables real-time histological evaluation of gastrointestinal mucosa during ongoing endoscopy examination. It can predict the classification of Colorectal Polyps accurately. However this requires much experience, which limits the application of pCLE. The investigators designed a computer program using deep neural networks to differentiate hyperplastic from neoplastic polyps automatically in pCLE examination.
Probe-based confocal laser endomicroscopy (pCLE) is an endoscopic technique that enables real-time histological evaluation of gastric mucosal disease during ongoing endoscopy examination. However this requires much experience, which limits the application of pCLE. The investigators designed a computer-aided diagnosis program using deep neural network to make diagnosis automatically in pCLE examination and contrast its performance with endoscopists.
Our group, prior to the present study, developed a handcrafted predictive model based on the extraction of surface patterns (textons) with a diagnostic accuracy of over 90%24. This method was validated in a small dataset containing only high-quality images. Artificial intelligence is expected to improve the accuracy of colorectal polyp optical diagnosis. We propose a hybrid approach combining a Deep learning (DL) system with polyp features indicated by clinicians (HybridAI). A pilot in vivo experiment will carried out.
Traditional school scoliosis screening approaches remains debatable due to unnecessary referal and excessive cost. Deep learning algorithms have proven to be powerful tools for the detection of multiple diseases; however, the application of such methods in scoliosis screening requires further assessment and validation. Here, the investigators develop an artificial system for the automated screening of scoliosis using disrobed back images, and conduct clinical trial to validate if the diagnostic system can offsetting the shortcomings of human doctors.
Visual development during early childhood is a vital process. Examining the visual acuity of children is essential for the early detection of visual abnormality, but performing such an assessment in children is challenging. Here, the investigators developed a human-in-the-loop artificial intelligence (AI) paradigm that combines traditional vision examination and AI with integrated software and hardware, thus making the vision examination easy to perform. The investigator also establish a entity intelligent visual acuity diagnostic system based on the paradigm, and conduct clinical trial to validate if the diagnostic system can offsetting the shortcomings of human doctors.