A novel artificial intelligence biomarker: Validation of the automated bone scan index (aBSI) in veterans with metastatic prostate cancer.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e17507-e17507
Author(s):  
Vipal P. Durkal ◽  
Nicholas George Nickols ◽  
Matthew Rettig
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Overall Survival ◽  
Bone Scan ◽  
Metastatic Prostate Cancer ◽  
Unmet Need ◽  
Bone Scan Index ◽  
Cancer Specific Survival ◽  
Cancer Specific Mortality ◽  
Bone Scans

e17507 Background: Prostate cancer commonly metastasizes to the bone and is associated with reduced survival, pathologic fractures and bone pain. The assessment of bone lesions is made with the technetium Tc99m(99mTc) bone scan, which relies on the subjective interpretation of radiologists and has a wide interobserver variability. There is an unmet need for a more objective and quantifiable measurement tool. Progenics Pharmaceuticals has introduced an automated bone scan index (aBSI), which employs artificial intelligence to quantify skeletal tumor burden. The automated bone scan index has been prospectively validated and is reproducible in large Phase III studies. The aBSI was validated by our study in the Veteran population at the West LA VA Medical Center. Methods: The first positive technetium 99 Tc99m bone scans of veterans diagnosed with metastatic, castration-sensitive prostate cancer were evaluated. Since 2011, a total of 107 evaluable patient bone scans were studied (n = 107). Patients with visceral metastases were excluded to evaluate only those with skeletal metastases. An automated bone scan index (aBSI) was generated for each scan using the Progenics Pharmaceuticals’ artificial intelligence platform. Multivariate analysis of aBSI with overall survival, prostate cancer specific survival, time from diagnosis to first positive bone scan, age at diagnosis, ethnicity, and Gleason score was assessed. Results: The study demonstrated a wide range of aBSI values (Range 0-16.84). Values calculated above the Median aBSI value (1.0) were prognostic for Overall Survival (p = 0.0009) and Prostate Cancer-Specific Survival (p = 0.0011). Patients in the highest quartile of aBSI values (range 5.2-16.84) showed a statistically significant Prostate Cancer-Specific Mortality (p = 0.0300) when compared to the lowest two quartiles (Range 0-1.07). The time from diagnosis to the first positive Tc99m bone scan statistically correlated with aBSI values (p = 0.0016). Multivariate analysis using Cox regression was utilized in the final statistical analysis of prostate cancer-specific mortality and overall survival. Conclusions: The automated Bone Scan Index provides a quantifiable and validated artificial intelligence biomarker to address an unmet need among metastatic prostate cancer patients. This tool was validated among Veterans, a pertinent population that is commonly affected by metastatic prostate cancer.

Predictive value of bone scan index using computer-aided diagnosis system for bone scans in patients receiving first-line hormone therapy for metastatic hormone-sensitive prostate cancer.

2016 ◽  
Vol 34 (2_suppl) ◽  
pp. 225-225
Author(s):  
Yasuhide Miyoshi ◽  
Masato Yasui ◽  
Shuko Yoneyama ◽  
Koichi Uemura ◽  
Takashi Kawahara ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Hormone Therapy ◽  
Survival Benefit ◽  
Bone Scan ◽  
First Line ◽  
Bone Scan Index ◽  
Computer Aided ◽  
Hormone Sensitive ◽  
Bone Scans ◽  
Aided Diagnosis

225 Background: Recently, the CHAARTED and STAMPEDE studies showed a survival benefit for docetaxel when started with androgen deprivation therapy (ADT) in men with newly diagnosed metastatic hormone-sensitive prostate cancer (mHSPC). While GETUG-AFU 15 failed to demonstrate a survival benefit of early chemotherapy. New biomarker for select the candidate for early chemotherapy in mHSPC is warranted. The objective of this study is to evaluate the bone scan index (BSI) using computer-aided diagnosis system for bone scans for predictive factor in patients receiving ADT as first-line hormone therapy for mHSPC. Methods: We identified consecutive 85 mHSPC patients treated with maximum androgen blockade (MAB) as first-line hormone therapy. We analyzed the correlations between progression-free survival (PFS) of MAB and clinicopathological characteristics, including patients’ age, initial PSA levels, Gleason scores, clinical TNM stage, hemoglobin (Hb), lactase dehydrogenase (LDH), c-reactive protein (CRP), and bone scan index (BSI). Statistical analyses were assessed using cox proportional hazards regression models. Results: The median patients’ age was 73 and the median follow-up duration was 11.3months. The median initial PSA value was 270 ng/ml. Median BSI was 2.7 % (range: 0.0-14.6). Clinical or PSA progression occurred in 55 (64.7%) patients. The median time to progression was 12.9 months. In multivariate analysis, three significant risk factors for PFS were identified; patients’ age ( > 73 years old vs ≤ 73; HR 0.53, p = 0.038), initial PSA levels ( > 270 ng/mL vs ≤ 270; HR 0.53, p = 0.038), and BSI ( > 2.7 vs ≤ 2.7; HR 3.0, p < 0.000). We stratified the patients into two cohorts with low risk (0-1 risk factor present) and high risk (2-3 risk factors present). We found a significant difference in PFS among risk groups (median PFS 15.3 months vs 8.5, p < 0.000). Conclusions: Patients’ age, initial PSA levels, and bone scan index were the significant predictive factors for MAB as first-line hormone therapy in patients with mHSPC. These findings might support the decision-making of induction of early chemotherapy for mHSPC.

Association of PET index quantifying skeletal uptake in NaF PET/CT images with overall survival in prostate cancer patients.

2017 ◽  
Vol 35 (6_suppl) ◽  
pp. 178-178
Author(s):  
Sarah Lindgren Belal ◽  
May Sadik ◽  
Reza Kaboteh ◽  
Nezar Hasani ◽  
Olof Enqvist ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Overall Survival ◽  
Survival Time ◽  
Median Survival Time ◽  
Bone Scan ◽  
Ct Images ◽  
Imaging Biomarker ◽  
Pet Ct ◽  
Bone Scans ◽  
Pet Index

178 Background: Bone Scan Index (BSI) derived from 2D whole-body bone scans is considered an imaging biomarker of bone metastases burden carrying prognostic information. Sodium fluoride (NaF) PET/CT is more sensitive than bone scan in detecting bone changes due to metastases. We aimed to develop a semi-quantitative PET index similar to the BSI for NaF PET/CT imaging and to study its relationship to BSI and overall survival in patients with prostate cancer. Methods: NaF PET/CT and bone scans were analyzed in 48 patients (aged 53-92 years) with prostate cancer. Thoracic and lumbar spines, sacrum, pelvis, ribs, scapulae, clavicles, and sternum were automatically segmented from the CT images, representing approximately 1/3 of the total skeletal volume. Hotspots in the PET images, within the segmented parts in the CT images, were visually classified and hotspots interpreted as metastases were included in the analysis. The PET index was defined as the quotient obtained as the hotspot volume from the PET images divided by the segmented bone tissue volume from the CT images. BSI was automatically calculated using EXINIboneBSI. Results: The correlation between the PET index and BSI was r2= 0.54. The median BSI was 0.39 (IQR 0.08-2.05). The patients with a BSI ≥ 0.39 had a significantly shorter median survival time than patients with a BSI < 0.39 (2.3 years vs. not reached after 5 years). BSI was significantly associated with overall survival (HR 1.13, 95% CI 1.13 to 1.41; p < 0.001), and the C-index was 0.68. The median PET index was 0.53 (IQR 0.02-2.62). The patients with a PET index ≥ 0.53 had a significantly shorter median survival time than patients with a PET index < 0.53 (2.5 years vs. not reached after 5 years). The PET index was significantly associated with overall survival (HR 1.18, 95% CI 1.01 to 1.30; p < 0.001) and C-index was 0.68. Conclusions: PET index based on NaF PET/CT images was correlated to BSI and significantly associated with overall survival in patients with prostate cancer. Further studies are needed to evaluate the clinical value of this novel 3D PET index as a possible future imaging biomarker.

scholarly journals Quantitative bone scan lesion area as an early surrogate outcome measure indicative of overall survival in metastatic prostate cancer

2018 ◽  
Vol 5 (01) ◽  
pp. 1 ◽  
Author(s):  
Matthew S. Brown ◽  
Grace Hyun J. Kim ◽  
Gregory H. Chu ◽  
Bharath Ramakrishna ◽  
Martin Allen-Auerbach ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Overall Survival ◽  
Bone Scan ◽  
Metastatic Prostate Cancer ◽  
Outcome Measure ◽  
Lesion Area ◽  
Surrogate Outcome ◽  
Surrogate Outcome Measure

scholarly journals Bone Scan Index: A Quantitative Treatment Response Biomarker for Castration-Resistant Metastatic Prostate Cancer

2012 ◽  
Vol 30 (5) ◽  
pp. 519-524 ◽  
Author(s):  
Elizabeth R. Dennis ◽  
Xiaoyu Jia ◽  
Irina S. Mezheritskiy ◽  
Ryan D. Stephenson ◽  
Heiko Schoder ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Bone Scintigraphy ◽  
Bone Scan ◽  
Metastatic Prostate Cancer ◽  
Univariate Analysis ◽  
Imaging Biomarker ◽  
Bone Scan Index ◽  
Risk Of Death ◽  
Percent Change ◽  
Castration Resistant

Purpose There is currently no imaging biomarker for metastatic prostate cancer. The bone scan index (BSI) is a promising candidate, being a reproducible, quantitative expression of tumor burden seen on bone scintigraphy. Prior studies have shown the prognostic value of a baseline BSI. This study tested whether treatment-related changes in BSI are prognostic for survival and compared BSI to prostate-specific antigen (PSA) as an outcome measure. Patients and Methods We retrospectively examined serial bone scans from patients with castration-resistant metastatic prostate cancer (CRMPC) enrolled in four clinical trials. We calculated BSI at baseline and at 3 and 6 months on treatment and performed univariate and bivariate analyses of PSA, BSI, and survival. Results Eighty-eight patients were scanned, 81 of whom have died. In the univariate analysis, the log percent change in BSI from baseline to 3 and 6 months on treatment prognosticated for survival (hazard ratio [HR], 2.44; P = .0089 and HR, 2.54; P < .001, respectively). A doubling in BSI resulted in a 1.9-fold increase in risk of death. Log percent change in PSA at 6 months on treatment was also associated with survival (HR, 1.298; P = .013). In the bivariate analysis, change in BSI while adjusting for PSA was prognostic at 3 and 6 months on treatment (HR, 2.368; P = .012 and HR, 2.226; P = .002, respectively), but while adjusting for BSI, PSA was not prognostic. Conclusion These data furnish early evidence that on-treatment changes in BSI are a response indicator and support further exploration of bone scintigraphy as an imaging biomarker in CRMPC.

scholarly journals Prognostic value of bone scan index as an imaging biomarker in metastatic prostate cancer: a meta-analysis

Oncotarget ◽  
2017 ◽  
Vol 8 (48) ◽  
pp. 84449-84458 ◽  
Author(s):  
Dongyang Li ◽  
Hang Lv ◽  
Xuanyu Hao ◽  
Yudi Dong ◽  
Huixu Dai ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Prognostic Value ◽  
Bone Scan ◽  
Metastatic Prostate Cancer ◽  
Meta Analysis ◽  
Imaging Biomarker ◽  
Bone Scan Index

Computer automated bone scan index (BSI) as an analytically validated imaging biomarker to quantitate change in bone scan of patients with metastatic prostate cancer.

2015 ◽  
Vol 33 (15_suppl) ◽  
pp. 5044-5044
Author(s):  
Aseem Anand ◽  
David Minarik ◽  
Reza Kaboteh ◽  
Sarah Lindgren Belal ◽  
Mariana Reza ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Bone Scan ◽  
Metastatic Prostate Cancer ◽  
Imaging Biomarker ◽  
Bone Scan Index
Sign in / Sign up

Export Citation Format

Share Document