Researchers Develop AI to Accurately Detect Tumor Cells for Bone Cancer Diagnosis

Researchers at Kyushu University have developed and validated a machine-learning model that can accurately evaluate the density of surviving tumor cells after treatment in pathological images of osteosarcoma.

Osteosarcoma is a predominant type of bone cancer that affects adolescents and is the most prevalent malignant bone tumor. The developed model can assess how individual tumor cells respond to treatment and can predict overall patient prognosis more reliably than conventional methods.
 
Although surgery and chemotherapy have improved patient outcomes of localized osteosarcoma, those with advanced metastatic disease have a low survival rate. Currently, prognosis relies on necrosis rate assessment, involving pathologists evaluations of the proportion of dead tissue within a tumor. Unfortunately, these methods are limited by variability between pathologists’ assessments and may not accurately predict treatment response.
 
Dr. Kengo Kawaguchi and Dr. Kazuki Miyama, from the Department of Orthopedic Surgery at Graduate School of Medical Sciences at Kyushu University, Japan, and Dr. Makoto Endo, a lecturer of Orthopedic Surgery at Kyushu University Hospital, and collaborators have turned to artificial intelligence (AI) for a more nuanced evaluation. 
 
The multidisciplinary team was led by Dr. Endo and Kyushu University’s Professor Ryoma Bise, Professor Yoshinao Oda, and Professor Yasuharu Nakashima. The team’s research has been published in njp Precision Oncology in January 2024. 
 
Endo commented, “In the traditional method, the necrosis rate is calculated as a necrotic area rather than individual cell counts, which is not sufficiently reproducible between assessors and does not adequately reflect the effects of anticancer drugs. We therefore considered using AI to improve the estimation.”
 
The team trained a type of deep-learning model AI to detect surviving tumor cells in Phase 1 of the study. The AI validated its detection performance using patient data and showed proficiency in detecting viable tumor cells in pathological images, aligning with expert pathologists’ capabilities.
 
In Phase 2, researchers analyzed two key measures: disease-specific survival, which tracks the duration after diagnosis or treatment without death directly caused by the disease, and metastasis free survival, which monitors the time post-treatment without cancer cells spreading to distant body parts.
 
The AI model showed comparable detection performance and precision to that of a pathologist with good reproducibility. 
 
Patients were sorted into groups based on the density of the viable tumor cell. The survival analysis revealed that the high-density group showed a worse prognosis. The low-density group showed a better prognosis for disease-specific survival and metastasis-free survival. Necrosis rate was not associated with disease-specific survival or metastasis-free survival. Individual patient analysis revealed that AI-estimated viable tumor cell density was a more reliable predictor of prognosis than necrosis rate.
 
These findings suggest the AI-based measurement of viable tumor cells reflects inherent malignancy and individual tumor cells response of osteosarcomas. The AI analysis of pathology images have improved detection accuracy, reduced inter-assessor variability, and enabled timely assessments.
 
“This new approach has the potential to enhance the accuracy of prognoses for osteosarcoma patients treated with chemotherapy. In the future, we intend to actively apply AI to rare diseases such as osteosarcoma, which have seen limited advancements in epidemiology, pathogenesis, and etiology. Despite the passage of decades, particularly in treatment strategies, substantial progress remains elusive. By putting AI to the problem, this might finally change,” Endo concluded.