Clinical Research Directory

AI-Based Quality Control for Radiology Reporting

The goal of this clinical trial is to learn whether an artificial intelligence (AI)-based radiology report quality-control system can improve the accuracy and workflow efficiency of routine radiology reporting among active radiologists at Tongji Hospital. The main questions it aims to answer are: * Does access to the AI quality-control system reduce quality problems remaining in final radiology reports? * Does access to the AI quality-control system improve reporting and reviewing efficiency? * In the two-stage reporting workflow, do the effects of AI differ depending on whether AI is available to the reporting radiologist, the reviewing radiologist, or both? Researchers will compare radiologists assigned to receive access to Radiology Report GPT with radiologists who continue the usual reporting workflow without access to the study AI system. Radiologists are randomized at the individual level. Because CT and MR reports commonly involve both a reporting radiologist and a reviewing radiologist, report-level analyses will classify reports according to AI availability at the two workflow stages, resulting in four combinations of reporter and reviewer AI exposure. The primary randomized evaluation will cover the first month after intervention initiation, with prespecified secondary and exploratory analyses extending through 3 months. Participants will: * Be assigned to either the AI quality-control group or the usual-workflow control group. * Continue their routine radiology reporting and reviewing work during the study period. * If assigned to the AI group, receive access to Radiology Report GPT, which automatically pre-reviews submitted radiology reports and provides quality-control alerts and suggested revisions. Radiologists will retain final decision authority over all reports. Final-report accuracy will be assessed independently of the intervention AI system and will include human review. Additional prespecified outcomes will examine report revisions, AI interaction measures, stage-specific and cross-stage workflow effects, recommended imaging follow-up and other downstream health-care utilization, patient satisfaction, and referring-clinician satisfaction.

Searching for Masses and Calcifications at the Same Time in Breast Cancer Screening

Brief Summary A task like breast cancer screening (mammography) can be described as a "hybrid search" task. In basic visual search tasks, observers search for a target among distractors that are not the target. In hybrid search, observers search for two or more target types. In mammography, observers are searching for masses, calcifications ("calcs"), and some other signs of cancer like architectural distortion. In this experiment, the investigators have created a simulated version of mammography where non-expert (non-radiologist) observers can look for simulated masses and calcs. There are two types of stimuli, a 2D version (like an x-ray) and a 3D version (like the output of Digital Breast Tomosynthesis - DBT). The question that is being asked is whether it is better to ask about masses and calcs separately (first one, then the other) or to just let observers look for both at the same time.

Measuring AI Reliance Among Intern Doctors in Palestine

This study aims to enroll intern doctors and have them sit one of three identical radiology exams. The only difference between them is an AI-assistant. The differences between these groups will be used to measure the extent of AI reliance among intern doctors in Palestine.

AI-Driven Multimodal Imaging Integration for Diagnosis and Prognostication of Digestive System Diseases

The goal of this observational, retrospective and prospective study is to develop a noninvasive disease assessment system by leveraging artificial intelligence (AI) to comprehensively analyze multi-modal imaging features, including magnetic resonance enterography (MRE) and computed tomography enterography (CTE), for the diagnosis and prognostication of digestive diseases. To this end, the investigators retrospectively enrolled imaging, endoscopic, and clinical data from 21 centers across China to construct and iteratively optimize the AI model. The model's performance will be prospectively validated in two centers, and its accuracy in lesion localization will be verified through real-world deployment in endoscopy suites.

National Registry of Surgical Treatment and Percutaneous Cryoablation of Parietal Endometriosis

National multicentric registry of a cohort of patient with suffering parietal endometriosis, carried out by a multidisciplinary radiosurgery team

The Safety and Efficacy of Irreversible Electroporation for the Treatment of Perivascular Liver Cancers

Malignant liver tumors are among the most common cancers worldwide, with over 10,000 new cases reported annually in Taiwan. Despite the availability of various treatment options, the prognosis for primary hepatocellular carcinoma and other metastatic liver cancers remains poor, with more than 8,000 deaths each year. The majority of patients (approximately 70%-85%) are diagnosed at an advanced stage or are deemed unresectable. In contrast, patients with small tumors often have a chance of cure. According to numerous studies, patients undergoing hepatic resection achieve a five-year disease-free survival rate exceeding 50%. For patients with unresectable malignant liver tumors who do not have vascular invasion or extrahepatic metastasis, radiofrequency ablation (RFA) serves as an alternative curative treatment. However, a major limitation of RFA lies in its reduced efficacy when tumors are located near blood vessels, making complete ablation difficult. Irreversible electroporation (IRE) offers a safer ablation modality that is unaffected by vascular proximity. Both preclinical and clinical studies have demonstrated that IRE is a safe and effective treatment for liver tumors. According to reports in the international journal Radiology, complete ablation rates of 77.3%-92% have been achieved in patients with liver cancer treated with IRE, with complication rates of around 19%, most of which were mild. The irreversible electroporation ablation system (Irreversible Electroporation Ablation Generator) used in this study delivers an ablation field with a voltage of 3,000 volts. It received U.S. Food and Drug Administration (FDA) approval in 2023 but has not yet been introduced in Taiwan. This study will target patients with malignant liver tumors who are unsuitable for surgical resection but are eligible for local ablation therapy, specifically those with tumors located adjacent to the inferior vena cava, hepatic veins, or within 1 cm of the main trunks of both portal veins. A total of 20 patients will undergo ablation treatment under intubation and general anesthesia. Postoperative monitoring will focus on potential complications, and patients will be followed for four months to assess complete tumor ablation and intrahepatic recurrence, in order to verify the clinical feasibility and advantages of this system.

An Explainable Neuroradiologist Artificial Intelligence Assistance System for Brain CT and MRI

This clinic trial aims to validate the working performance of radiologists with or without artificial intelligence (AI) diagnostic tool at neurological diseases diagnosis on brain CT/MRI. Routine diagnosis workflow in real clinical scenario including imaging reading, feature interpretation, differential diagnosis, writing initial report and optimizing revised version. And the gold standards of diagnosis are the histopathology references for brain tumors and the discharge diagnosis integrating all the examination results for the other neurological diseases. The performance of AI-assisted tools on diagnosing should be examined in a clinical process with multiple aspects identical to human radiologists' work before being transformed and putted to use. This study hypothesizes that AI models, trained with over 100,000 patient scans, are non-inferior to radiologists in neurological disease diagnosis on brain CT and MRI. For the secondary end-points, we investigate the performance of AI-radiologist collaboration of reasoning-enhanced AI-assisted systems. We hypothesize that, by visualizing the process of imaging interpretation and diagnosis, reasoning-enhanced AI can not only improve working performance of radiologists but also boost their trust in AI tools.

Three-in-One Stop Computed Topography Angiography(CTA) and CT Perfusion(CTP) in Cerebrovascular Disease

This research takes patients with cerebrovascular diseases as the research subjects and employs the experimental design of a prospective cohort study, aiming to innovatively develop and validate a "one-stop" multimodal CT examination scheme. The 301-CTAP multimodal CT technique implies that three modalities are acquired through a single collection, including head and neck CTA (head and neck CTA), multiphase CTA imaging of the brain (multiphase CTA), and CT perfusion imaging of the brain (CT perfusion).

Neoadjuvant Radiotherapy Before Surgery for Rectal Cancer, Surgical and Oncological Outcome Analysis, Retrospective Case Control Study in a Single Institute.

Pre-operative radiotherapy for clinical stage 3 rectal cancer outcome analysis, retrospective case-control study.

Long-term Outcomes of Early-stage Nasopharyngeal Carcinoma Patients Treated with Radiotherapy Alone

Nasopharyngeal carcinoma (NPC) is a malignant tumor primarily originating in the nasopharynx, commonly found in populations in southern China, certain regions of Asia, and North Africa. The main treatment for NPC is primarily radiotherapy, with some patients receiving combined chemotherapy. Early-stage NPC patients can achieve adequate tumor control with radiation therapy alone. Various studies report that the 5-year survival rate for very early-stage NPC exceeds 90%. However, some stage I patients experience local recurrence or distant metastasis after treatment, indicating treatment failure. This study aims to retrospectively analyze the factors contributing to treatment failure and prognostic factors in this group of early-stage NPC patients.

Artificial Intelligent Image Processing and Diagnosis of Pulmonary Vessels in CT

In this study, patients with chest pain, lung cancer, pulmonary embolism, and routine inpatient physical examination were selected as the research objects, and the experimental design of retrospective cohort study was adopted to carry out artificial intelligence analysis related to pulmonary vascular diseases in patients with multi-dimensional big data. The multi-modal CT acquisition process included plain scan CT(NCCT) and CT pulmonary angiography (CTPA). Ctpa-like image effects can be simulated or reconstructed by non-enhanced plain scan CT images, so that CTPA-like image quality can be obtained without injecting contrast agent. The synthetic CTPA images were further analyzed by artificial intelligence to assist doctors in the intelligent diagnosis of pulmonary vascular diseases.

Deep Enhanced Imaging in Stroke and Vascular Neurology

To investigate the performance of enhanced computed tomography (CT) or magnetic resonance (MR) imaging by deep learning relative to conventional CT or MR imaging in brain stroke and vascular neurology. We expect that the deep enhanced imaging method can shorten the time stay in the imaging session of stroke patients, optimize the overall imaging quality and improve the patients' care in imaging session.

Correlation of Radiological Lesions With Vestibular Function in Patients With Bilateral Vestibulopathy

In 2014 radiologic lesions were detected at one or more semicircular canals using CT and MR imaging of temporal bone in subjects carrying the p.P51S mutation in COCH. These lesions are believed to present at more advanced stages of the hearing and vestibular deterioration. Since then, other authors have described similar lesions in advanced non-genetic hearing and vestibular impairment as well. The purpose of this study is therefore to assess the radiologic investigation using CT and MR imaging of temporal bone to all subjects presenting with bilateral vestibulopathy, using the Barany criteria, compared to the p.P51S population.