Clinical trials

Globally, prostate cancer is the second most common malignant tumor and the fifth leading cause of cancer-related death in men. In China, there will be more than 125,000 new cases of prostate cancer in 2022, ranking sixth in the incidence of male cancers, causing about 56,000 deaths, ranking tenth among male malignancies. The gold standard for the diagnosis of prostate cancer is prostate biopsy. In the past, whether to initiate a biopsy procedure depended on the screening results of abnormal prostate cancer, namely, elevated serum PSA levels (\>4.0 ng/mL) and abnormal digital rectal examination (DRE), but the low accuracy led to a large number of negative biopsy results, overdiagnosis and overtreatment of indolent tumors, causing many patients to undergo unnecessary biopsies, resulting in a large social burden. Magnetic resonance imaging (MRI) has been widely used in clinical practice due to its advantages of high soft tissue resolution, multi-plane, multi-sequence, multi-parameter imaging and no ionizing radiation. Studies have shown that multiparametric MRI (mpMRI), including T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and dynamic contrast enhancement (DCE), can help select patients for initial biopsy and improve the detection rate of biopsy. MRI plays a vital role in the clinical diagnosis and treatment of prostate lesions. However, prostate MRI examinations often show "same disease, different images" and "different diseases, same images". Benign prostate lesions can simulate the characteristics of malignant lesions to interfere with the image and the judgment of clinicians, resulting in misdiagnosis and mistreatment. For example, inflammation in the peripheral zone of the prostate, like tumors, appears as low signal on T2WI, and hyperplastic nodules in the transition zone may also appear as restricted diffusion on DWI like tumors. Therefore, the complementary addition of different parameter sequences and the comprehensive judgment of qualitative and quantitative characteristics are very important for accurate diagnosis. With the development of magnetic resonance technology, new imaging sequences continue to emerge, which can not only show the anatomical decomposition of the prostate more clearly, but also reflect the characteristics of the lesions from the pathological and physiological perspectives such as function, metabolism, and blood perfusion, and can better characterize prostate lesions. The purpose of this study is to study the routine and functional MR imaging data of patients with prostate lesions in our institution, use pathology as the gold standard, and use image processing software to conduct qualitative and quantitative analysis of body composition, imaging characteristics, peritumoral tissue characteristics, and lymph node characteristics, so as to achieve benign and malignant differentiation, pathological feature prediction, and prognosis evaluation, in order to better perform accurate diagnosis, clinical decision-making, and prognosis evaluation in patients with prostate lesions.

Currently, renal biopsy is the gold standard for evaluating renal pathology and renal fibrosis, but it is invasive and carries the risk of serious complications; and the sampled tissue is only a small part of the kidney, which is prone to sampling bias. The lack of reliable, comprehensive test results has hindered the research of new anti-fibrotic drugs and delayed the clinical application of effective new drugs. Therefore, the development of a non-invasive dynamic detection method for renal insufficiency and renal fibrosis in vivo is an urgent clinical problem to be solved. With the continuous development and update of technology, imaging provides a new way to non-invasively evaluate renal fibrosis. Due to the high resolution of soft tissue and the ability to perform multi-parameter analysis, magnetic resonance has developed the diagnosis of renal insufficiency and renal fibrosis from macroscopic simple biomorphological changes to microscopically complex pathophysiological changes. Many imaging techniques measure renal dysfunction and renal fibrosis by assessing the impact of fibrosis on the functional status, physical properties, and molecular properties of the kidney. In recent years, in the context of precision medicine, artificial intelligence technologies such as radiomics and machine learning are rapidly becoming very promising auxiliary tools in the imaging assessment of renal fibrosis. It can extract and learn features in images with high throughput, make greater use of information in medical images that cannot be recognized by the human eye, and achieve disease diagnosis, prognosis assessment, and efficacy prediction by building models. However, most of the current research is in the preliminary stage, and there are still few studies on the assessment of renal insufficiency and renal fibrosis. I believe that with the continuous improvement of algorithms and the optimization of models, the progress of radiomics and machine learning will be great. To a certain extent, it promotes the development of personalized medicine and precision medicine for patients with renal insufficiency and renal fibrosis.