Status
Conditions
Treatments
About
Investigators propose hyperspectral imaging analysis as a method to distinguish the efficacy of hormone-combined cyclophosphamide therapy for PMN, and classify sensitive and insensitive patients treated with hormone-combined cyclophosphamide regimen. A variety of machine learning models were used to prove that hyperspectral imaging technology could assist patients in selecting the optimal treatment plan, and further explore the predictive indicators of PMN treatment effect.
Full description
Renal puncture pathological sections from patients with nephropathy. ENVI Classic software was used to process the hyperspectral images and delineate the region of interest, and the one-dimensional spectral data of each pixel in each region were derived. Machine learning and deep learning methods were used to analyze the characteristics of hyperspectral data and classify them.
The data of the previous study came from the Department of Pathology and Nephrology of Qianfoshan Hospital in Shandong Province. Under the light microscope, electron microscope and immunofluorescence microscope, the pathological types of glomerular diseases in patients with proteinuria were identified. By scanning the corresponding patient's H&E stained pathological sections, the hyperspectral microscopic images were classified by machine learning and deep learning methods, and the classification accuracy was greater than 85%. It was concluded that hyperspectral imaging technology can be used as a non-invasive diagnostic method to predict treatment response.
Enrollment
Sex
Ages
Volunteers
Inclusion criteria
Exclusion criteria
40 participants in 2 patient groups
Loading...
Central trial contact
Wang Zunsong, doctor
Data sourced from clinicaltrials.gov
Clinical trials
Research sites
Resources
Legal