Viable tumor cell density after neoadjuvant chemotherapy assessed using deep learning model reflects the prognosis of osteosarcoma

Abstract

Prognosis after neoadjuvant chemotherapy (NAC) for osteosarcoma is generally predicted using manual necrosis-rate assessments; however, necrosis rates obtained in these assessments are not reproducible and do not adequately reflect individual cell responses. We aimed to investigate whether viable tumor cell density assessed using a deep-learning model (DLM) reflects the prognosis of osteosarcoma. Seventy-one patients were included in this study. Initially, the DLM was trained to detect viable tumor cells, following which it calculated their density. Patients were stratified into high and low-viable tumor cell density groups based on DLM measurements, and survival analysis was performed to evaluate disease-specific survival and metastasis-free survival (DSS and MFS). The high viable tumor cell density group exhibited worse DSS (p = 0.023) and MFS (p = 0.033). DLM-evaluated viable density showed correct stratification of prognosis groups. Therefore, this evaluation method may enable precise stratification of the prognosis in osteosarcoma patients treated with NAC.

A novel prognostic signature related to programmed cell death in osteosarcoma

“…The use of multiple integrated machine learning algorithms resulted in improved accuracy of prognostic predictions for osteosarcoma, as evidenced by higher concordance index scores compared to traditional methods. The experimental results are consistent with findings from other studies, which have used similar methodologies and analytical frameworks ( 47 – 50 ). OS samples from all datasets are classified by the OS-PCDS into high-risk and low-risk groups, with survival analysis indicating that a lower prognosis is associated with the low-risk group and a higher prognosis is associated with the high-risk group.…”