Back
For best output, select "Paper Size" as "A4" and "Margin" as "0" or "None".
To save or print to PDF, please select Print Destination > Save as PDF, enable Background Graphics under "More Settings", then click "Save".
During the congress, E-Posters will be accessible to all participants on the congress website 24/7, as well as in the E-poster stations in the congress center.
Preparing your E-Poster
Please review the E-Poster format requirements carefully when preparing your E-Poster. Should your E-Poster not meet the mentioned requirements, it may not be displayed as described above.
E-Poster Submission Deadline
Please prepare and upload your E-Poster no later than March 14, 2026 11.59PM CET. After this date, you will no longer be able to prepare and upload your E-poster and it will not be displayed and accessible on the congress website.
Please follow the instructions below to input your abstract title.
Abstract titles should be brief and reflect the content of the abstract.
IgA nephropathy (IgAN) is the most common primary glomerulonephritis worldwide. However, there are still many limitations in using renal pathology to assess the risk of progression of IgAN. As emerging technologies, pathomics can assist renal pathologists in discovering subvisual features, and becoming an important tool for assessing the risk of IgAN progression. This study utilize pathomics to identify valuable subvisual features in renal pathology for the prognosis of IgAN, and further validate the clinical value of these features.
In this study, we selected 285 patients who underwent renal biopsy at Zhejiang Provincial Hospital of Chinese Medicine, Zhejiang Provincial Zhongshan Hospital, Zhejiang Provincial Dongfang Hospital, and Jiangshan Hospital of Chinese Medicine from January 1, 2017 to January 1, 2020 and were diagnosed with primary IgAN. We randomly selected 200 patients to train the deep learning model, and the remaining 85 patients were used for validation. We obtained whole-slide images (WSI) for HE, PAS, Masson and PASM of this patients and divided the WSI into 512×512 pixel patches at magnification of 100x, 200x, and 400x. After removing the blank patches, we applied the Vahadane method to standardize the color of all patches. The Residual Network 18 is utilized for deep learning to predict the risk of each patch experiencing the study outcome, and then the prediction probabilities of each patch are aggregated onto the corresponding WSI using the multi-instance learning. We used principal component analysis to reduce the dimension of the data and selected the optimal magnification rate based on the C-index of the Cox model. We also used visualization techniques to project the prediction of the patch on the optimal condition onto the WSI. Finally, we invited renal pathologists to summarize all the patches and identify the pathological features with prognostic value. Additionally, we invited another renal pathologist to conduct independent validation on the validation set patients to confirm the value of the features discovered by the pathomics.
We found the prognostic model constructed using deep learning (0.837±0.051) significantly outperforms the Lee grading(0.676±0.059) and Oxford classification(0.766±0.055) in predicting the occurrence of the adverse study outcome in IgAN. And we found that the pathological features of deep learning mainly focused on ‘renal tubular atrophy with inflammatory cell infiltration’, and through independent validation by renal pathologists on patients in the validation set, this feature proved to be of great value in predicting the prognosis of patients with IgAN.
This study utilized pathomics to identify renal tubular atrophy with inflammatory cell infiltration is associated with the progression risk of IgAN. It is expected to complement the Oxford Classification (MEST-CL), thereby enabling a more accurate assessment of the prognosis of patients with IgAN.
