Assessing Therapeutic Response to Radium-223 with an Automated Bone Scan Index among Metastatic Castration-Resistant Prostate Cancer Patients: Data from Patients in the J-RAP-BSI Trial

Abstract

To evaluate the usefulness of change in the automated bone scan index (aBSI) value derived from bone scintigraphy findings as an imaging biomarker for the assessment of treatment response and survival prediction in metastatic castration-resistant prostate cancer (mCRPC) patients treated with Ra-223. This study was a retrospective investigation of a Japanese cohort of 205 mCRPC patients who received Ra-223 in 14 hospitals between July 2016 and August 2020 and for whom bone scintigraphy before and after radium-223 treatment was available. Correlations of aBSI change, with changes in the serum markers alkaline phosphatase (ALP) and prostate-specific antigen (PSA) were evaluated. Additionally, the association of those changes with overall survival (OS) was assessed using the Cox proportional-hazards model and Kaplan–Meier curve results. Of the 205 patients enrolled, 165 (80.5%) completed six cycles of Ra-223. Following treatment, ALP decline (%ALP < 0%) was noted in 72.2% (148/205), aBSI decline (%aBSI < 0%) in 52.7% (108/205), and PSA decline (%PSA < 0%) in 27.8% (57/205). Furthermore, a reduction in both aBSI and ALP was seen in 87 (42.4%), a reduction in only ALP was seen in 61 (29.8%), a reduction in only aBSI was seen in 21 (10.2%), and in both aBSI and ALP increasing/stable (≥0%) was seen in 36 (17.6%) patients. Multiparametric analysis showed changes in PSA [hazard ratio (HR) 4.30, 95% confidence interval (CI) 2.32–8.77, p < 0.0001], aBSI (HR 2.22, 95%CI 1.43–3.59, p = 0.0003), and ALP (HR 2.06, 95%CI 1.35–3.14, p = 0.0008) as significant prognostic factors for OS. For mCRPC patients treated with Ra-223, aBSI change is useful as an imaging biomarker for treatment response assessment and survival prediction.

Theranostics and artificial intelligence: new frontiers in personalized medicine

“…In their study, the radiomic model predicted histopathologic grade with an 88% sensitivity and an 89% specificity for panNET. These studies demonstrate that AI can predict tumor grade and metastatic potential for certain cancers, such as prostate cancer and NETs 25 - 28 . Therefore, implementation of AI into clinical decision-making processes may yield a result in better risk stratification and patient selection for theranostic applications (Figure 2 ) .…”

“…Radiomics, fundamentally, is a quantitative method that transforms imaging data into actionable clinical information. Kitajima et al demonstrated that the imaging biomarker, developed using AI software trained on pre- and post-therapy bone scan images, effectively distinguished the responders and the non-responders of 223 RaCl 2 therapy 25 . Papp et al explored the potential of their ML models, trained with PET/MRI radiomic data, to differentiate between low and high-risk prostate lesions and predict biochemical recurrence in patients with prostate cancer 26 .…”