The aim of this study was to develop a deep learning-based method for segmentation of bones in CT scans and test its accuracy compared to manual delineation, as a first step in the creation of an automated PET/ CT-based method for quantifying skeletal tumour burden. Methods: Convolutional neural networks (CNNs) were trained to segment 49 bones using manual segmentations from 100 CT scans. After training, the CNN-based segmentation method was tested on 46 patients with prostate cancer, who had undergone 18 F-choline-PET/CT and 18 F-NaF PET/CT less than three weeks apart. Bone volumes were calculated from the segmentations. The network's performance was compared with manual segmentations of five bones made by an experienced physician. Accuracy of the spatial overlap between automated CNN-based and manual segmentations of these five bones was assessed using the Sørensen-Dice index (SDI). Reproducibility was evaluated applying the Bland-Altman method. Results: The median (SD) volumes of the five selected bones were by CNN and manual segmentation: Th7 41 (3.8) and 36 (5.1), L3 76 (13) and 75 (9.2), sacrum 284 (40) and 283 (26), 7th rib 33 (3.9) and 31 (4.8), sternum 80 (11) and 72 (9.2), respectively. Median SDIs were 0.86 (Th7), 0.85 (L3), 0.88 (sacrum), 0.84 (7th rib) and 0.83 (sternum). The intraobserver volume difference was less with CNN-based than manual approach: Th7 2% and 14%, L3 7% and 8%, sacrum 1% and 3%, 7th rib 1% and 6%, sternum 3% and 5%, respectively. The average volume difference measured as ratio volume difference/mean volume between the two CNN-based segmentations was 5-6% for the vertebral column and ribs and ≤3% for other bones. Conclusion:The new deep learning-based method for automated segmentation of bones in CT scans provided highly accurate bone volumes in a fast and automated way and, thus, appears to be a valuable first step in the development of a clinical useful processing procedure providing reliable skeletal segmentation as a key part of quantification of skeletal metastases.

BackgroundSodium fluoride (NaF) positron emission tomography combined with computer tomography (PET/CT) has shown to be more sensitive than the whole-body bone scan in the detection of skeletal uptake due to metastases in prostate cancer. We aimed to calculate a 3D index for NaF PET/CT and investigate its correlation to the bone scan index (BSI) and overall survival (OS) in a group of patients with prostate cancer.MethodsNaF PET/CT and bone scans were studied in 48 patients with prostate cancer. Automated segmentation of the thoracic and lumbar spines, sacrum, pelvis, ribs, scapulae, clavicles, and sternum were made in the CT images. Hotspots in the PET images were selected using both a manual and an automated method. The volume of each hotspot localized in the skeleton in the corresponding CT image was calculated. Two PET/CT indices, based on manual (manual PET index) and automatic segmenting using a threshold of SUV 15 (automated PET15 index), were calculated by dividing the sum of all hotspot volumes with the volume of all segmented bones. BSI values were obtained using a software for automated calculations.ResultsBSI, manual PET index, and automated PET15 index were all significantly associated with OS and concordance indices were 0.68, 0.69, and 0.70, respectively. The median BSI was 0.39 and 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 of follow-up [p = 0.01]). The median manual PET index was 0.53 and patients with a manual PET index >0.53 had a significantly shorter median survival time than patients with a manual PET index <0.53 (2.5 years vs not reached after 5 years of follow-up [p < 0.001]). The median automated PET15 index was 0.11 and patients with an automated PET15 index >0.11 had a significantly shorter median survival time than patients with an automated PET15 index <0.11 (2.3 years vs not reached after 5 years of follow-up [p < 0.001]).ConclusionsPET/CT indices based on NaF PET/CT are correlated to BSI and significantly associated with overall survival in patients with prostate cancer.

Purpose The aim of this study was to develop and validate an artificial intelligence (AI)-based method using convolutional neural networks (CNNs) for the detection of pelvic lymph node metastases in scans obtained using [18F]PSMA-1007 positron emission tomography-computed tomography (PET-CT) from patients with high-risk prostate cancer. The second goal was to make the AI-based method available to other researchers. Methods [18F]PSMA PET-CT scans were collected from 211 patients. Suspected pelvic lymph node metastases were marked by three independent readers. A CNN was developed and trained on a training and validation group of 161 of the patients. The performance of the AI method and the inter-observer agreement between the three readers were assessed in a separate test group of 50 patients. Results The sensitivity of the AI method for detecting pelvic lymph node metastases was 82%, and the corresponding sensitivity for the human readers was 77% on average. The average number of false positives was 1.8 per patient. A total of 5–17 false negative lesions in the whole cohort were found, depending on which reader was used as a reference. The method is available for researchers at www.recomia.org. Conclusion This study shows that AI can obtain a sensitivity on par with that of physicians with a reasonable number of false positives. The difficulty in achieving high inter-observer sensitivity emphasizes the need for automated methods. On the road to qualifying AI tools for clinical use, independent validation is critical and allows performance to be assessed in studies from different hospitals. Therefore, we have made our AI tool freely available to other researchers.

Unfortunately, the original version of this article contains an error. In Fig. 6, the plotted curves are incorrect. Please note that the original data is correct and statistical tests are valid for the survival analysis. The correct version of Fig. 6 can be found below.

Purpose Consistent assessment of bone metastases is crucial for patient management and clinical trials in prostate cancer (PCa). We aimed to develop a fully automated convolutional neural network (CNN)-based model for calculating PET/CT skeletal tumor burden in patients with PCa. Methods A total of 168 patients from three centers were divided into training, validation, and test groups. Manual annotations of skeletal lesions in [18F]fluoride PET/CT scans were used to train a CNN. The AI model was evaluated in 26 patients and compared to segmentations by physicians and to a SUV 15 threshold. PET index representing the percentage of skeletal volume taken up by lesions was estimated. Results There was no case in which all readers agreed on prevalence of lesions that the AI model failed to detect. PET index by the AI model correlated moderately strong to physician PET index (mean r = 0.69). Threshold PET index correlated fairly with physician PET index (mean r = 0.49). The sensitivity for lesion detection was 65–76% for AI, 68–91% for physicians, and 44–51% for threshold depending on which physician was considered reference. Conclusion It was possible to develop an AI-based model for automated assessment of PET/CT skeletal tumor burden. The model’s performance was superior to using a threshold and provides fully automated calculation of whole-body skeletal tumor burden. It could be further developed to apply to different radiotracers. Objective scan evaluation is a first step toward developing a PET/CT imaging biomarker for PCa skeletal metastases.

No abstract

288 Background: Enzalutamide (ENZ), an androgen receptor antagonist therapy, was approved for patients (pts) with mCRPC. However, in standard of care for mCRPC pts, change in prostate specific antigen (PSA) is not accepted as an efficacy response measurement and the radiological change is inadequately measured in an interpreter-dependent subjective analysis of bone scan. Therefore, an objective efficacy response biomarker is warranted. In this registry study, we evaluated BSI as a quantitative analysis of bone scintigraphy, to access response in mCRPC pts being treated with ENZ. Methods: Pts with mCRPC, at Skåne University Hospital (SUH), Sweden, who initiated treatment with ENZ after failing chemotherapy were eligible for the study. Primary objective was to associate the change in BSI and PSA, after 12 weeks (wks) of treatment with EZN, with overall survival (OS). Automated BSI generated by EXINI boneBSI platform is quantitative representation of tumor burden as a percent of total skeletal mass. Bivariate cox regression analysis was used to evaluate the association of BSI and PSA with OS. Results: Thirty-five pts, who initiated ENZ treatment at (SUH), were eligible for the BSI analysis. Follow-up scans for the BSI analysis were available from 24 pts. Median baseline BSI value was 2.92 (range: 0.0 - 11.72) and at follow-up the median BSI value was 2.83 (range: 0.0 - 12.65). OS was associated with BSI at both baseline and at follow-up as opposed to that of PSA (table 1). The change in BSI between baseline and follow-up was also significantly associated with OS, whereas the change in PSA was not. Conclusions: Automated BSI and its relative change were observed to be associated with OS in mCRPC pts receiving ENZ as standard of care treatment. The result deserves further validation, in controlled investigational studies, of BSI as a quantitative imaging biomarker indicative of efficacy response to second-line treatment in mCRPC pts. [Table: see text]

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.