A Multi-Center Study on Intraoperative Glioma Grading Via Deep Learning on Cryosectioned Pathology

Intraoperative glioma grading remains a significant challenge, primarily due to the diminished diagnostic attributable to the suboptimal quality of cryosectioned slides. Precise intraoperative diagnosis is instrumental in guiding surgical strategy to balance the resection extent and the neurological function preservation, thereby optimizing patient prognoses. This study developed a model for intraoperative glioma grading via deep learning on cryosectioned images, termed IGGC. The model was trained and validated on TCGA datasets and one cohort (n_train= 1603, n_validate= 628), and tested on five cohorts (n_test= 213). The IGGC model achieved an AUC value of 0.99 in differentiating between HGG and LGG, and an AUC value of 0.96 in identifying grade 4 glioma. Integrated into the clinical workflow, the IGGC model assisted pathologists of varying experience levels in reducing inter-observer variability and enhancing diagnostic consistency. This integrated diagnostic model possesses the potential for clinical implementation, offering a time-efficient and highly accurate method for classifying adult-type diffuse gliomas.

Note:
Funding Information: This work was supported by the Shanghai Municipal Science and Technology Commission (22S31905400 and 23Y11900700), the Shanghai Municipal Health Commission (20234Y0308 and 2022ZZ01006).

Declaration of Interests: The authors declare no competing interests.

Ethics Approval Statement: The study received ethical approval from each participating institution, with approval document numbers as follows: KY2023-977 (Center 1&2), KYLL-2021-242 (Center 3), FMU-2021-120 (Center 4), and SWYX:NO.2024-516 (Center 5). Patients have signed informed consent forms for enrolling in brain tumor tissue bank in advance of operations, authorizing to use their samples for this study. The related systems of slide scanners have been approved by the Chinese National Medical Products Administration (NMPA, with certificate numbers of 20222223642, and 20212220117, respectively).

Keywords: glioma, deep learning, neuropathology, crysectioned image, multi-center

Suggested Citation: Suggested Citation

Liu, Xi and Jin, Lei and Sun, Tianyang and Chen, Hong and Wu, Shuai and Cheng, Haixia and Liu, Xiaojia and Wang, Kun and Chen, Lin and Lu, Junfeng and Zhang, Jun and Zou, Yaping and Chen, Yi and Liu, Yingchao and Shi, Feng and Shen, Dinggang and Wu, Jinsong and Administrator, Sneak Peek, A Multi-Center Study on Intraoperative Glioma Grading Via Deep Learning on Cryosectioned Pathology. Available at SSRN: https://ssrn.com/abstract=5012220 or http://dx.doi.org/10.2139/ssrn.5012220

This version of the paper has not been formally peer reviewed.