Rapid intraoperative multi-molecular diagnosis of glioma with ultrasound radio frequency signals and deep learningResearch in context
Xuan Xie,
Chao Shen,
Xiandi Zhang,
Guoqing Wu,
Bojie Yang,
Zengxin Qi,
Qisheng Tang,
Yuanyuan Wang,
Hong Ding,
Zhifeng Shi,
Jinhua Yu
Affiliations
Xuan Xie
School of Information Science and Technology, Fudan University, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China
Chao Shen
Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China; National Center for Neurological Disorders, Shanghai, China; Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China
Xiandi Zhang
Department of Ultrasound, Huashan Hospital, Fudan University, Shanghai, China
Guoqing Wu
School of Information Science and Technology, Fudan University, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China
Bojie Yang
Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China; National Center for Neurological Disorders, Shanghai, China; Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China
Zengxin Qi
Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China; National Center for Neurological Disorders, Shanghai, China; Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China
Qisheng Tang
Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China; National Center for Neurological Disorders, Shanghai, China; Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China
Yuanyuan Wang
School of Information Science and Technology, Fudan University, Shanghai, China
Hong Ding
Department of Ultrasound, Huashan Hospital, Fudan University, Shanghai, China; Corresponding author. Department of Ultrasound, Huashan Hospital, Fudan University, No.12 Middle Urumqi Road, Shanghai, 200040, China.
Zhifeng Shi
Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai, China; National Center for Neurological Disorders, Shanghai, China; Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China; Corresponding author. Department of Neurosurgery, Huashan Hospital, Fudan University, No.12 Middle Urumqi Road, Shanghai, 200040, China.
Jinhua Yu
School of Information Science and Technology, Fudan University, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China; Corresponding author. School of Information Science and Technology, Fudan University, 220 Handan Road, Yangpu District, Shanghai, 200433, China.
Summary: Background: Molecular diagnosis is crucial for biomarker-assisted glioma resection and management. However, some limitations of current molecular diagnostic techniques prevent their widespread use intraoperatively. With the unique advantages of ultrasound, this study developed a rapid intraoperative molecular diagnostic method based on ultrasound radio-frequency signals. Methods: We built a brain tumor ultrasound bank with 169 cases enrolled since July 2020, of which 43483 RF signal patches from 67 cases with a pathological diagnosis of glioma were a retrospective cohort for model training and validation. IDH1 and TERT promoter (TERTp) mutations and 1p/19q co-deletion were detected by next-generation sequencing. We designed a spatial–temporal integration model (STIM) to diagnose the three molecular biomarkers, thus establishing a rapid intraoperative molecular diagnostic system for glioma, and further analysed its consistency with the fifth edition of the WHO Classification of Tumors of the Central Nervous System (WHO CNS5). We tested STIM in 16-case prospective cohorts, which contained a total of 10384 RF signal patches. Two other RF-based classical models were used for comparison. Further, we included 20 cases additional prospective data for robustness test (ClinicalTrials.gov NCT05656053). Findings: In the retrospective cohort, STIM achieved a mean accuracy and AUC of 0.9190 and 0.9650 (95% CI, 0.94–0.99) respectively for the three molecular biomarkers, with a total time of 3 s and a 96% match to WHO CNS5. In the prospective cohort, the diagnostic accuracy of STIM is 0.85 ± 0.04 (mean ± SD) for IDH1, 0.84 ± 0.05 for TERTp, and 0.88 ± 0.04 for 1p/19q. The AUC is 0.89 ± 0.02 (95% CI, 0.84–0.94) for IDH1, 0.80 ± 0.04 (95% CI, 0.71–0.89) for TERTp, and 0.85 ± 0.06 (95% CI, 0.73–0.98) for 1p/19q. Compared to the second best available method based on RF signal, the diagnostic accuracy of STIM is improved by 16.70% and the AUC is improved by 19.23% on average. Interpretation: STIM is a rapid, cost-effective, and easy-to-manipulate AI method to perform real-time intraoperative molecular diagnosis. In the future, it may help neurosurgeons designate personalized surgical plans and predict survival outcomes. Funding: A full list of funding bodies that contributed to this study can be found in the Acknowledgements section.
