Abstract 75P
Background
A parallel deep learning network framework for whole-body bone scan image analysis Whole-body bone scan image analysis in nuclear medicine is a common method assisting physicians in bone metastases detection of cancer. As the increasing need for diagnostic examinations in the huge and elderly population in China, physicians are facing a significant growth of workload but must still manage to read the diagnostic images carefully and avoid errors in interpretation. It is crucial to develop a clinical decision support tool in assisting physicians in their clinical routine.
Methods
In this study, we proposed a parallel deep learning network framework for bone-scan interpretations of the presence or absence of bone metastases. The whole-body bone scans (anterior and posterior views) of 707 patients who are suspected bone metastatic disease were studied. The physicians were asked to classify each case for the presence or absence of bone metastasis manually. Each bone scan image was automatically segmented into 26 different anatomical regions of homogeneous bones based on the skeletal frame. The corresponding 26 deep learning networks made a diagnosis by inspecting each region and searching for abnormal lesion activity simultaneously. To estimate the performance of each anatomical sub-region identification models, a ten-fold cross testing scheme was applied where the data set was divided into ten parts of equal size randomly.
Results
The sensitivity, specificity and the mean number of false lesions detected were adopted as performance indices to evaluate the proposed model. The best sensitivity and specificity of an individual network corresponding to each sub-region are 99.9 % and 97.3% respectively. The overall mean sensitivity and specificity of the parallel model are 99.2% and 71.8% respectively, as well as 2.0 false detections per patient scan image within millisecond.
Conclusions
With an extremely high sensitivity, specificity and a low false lesions detection rate, this proposed parallel deep learning network model is demonstrated as useful for detecting metastases in bone scans. Our proposed framework appears to have significant potential as a clinical decision support tool in assisting physicians in their clinical routine.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
X. Pu: Full / Part-time employment: University of Electronic Science and Technology of China; Full / Part-time employment: University of Electronic Science and Technology of China; Full / Part-time employment: University of Electronic Science and Technology of China. G. Tang: Full / Part-time employment: West China University Hospital, Sichuan University. K. Cai: Research grant / Funding (institution): School of Computer Science and Engineering, University of Electronic Science and Technology of China. Y. Huang: Research grant / Funding (institution): College of Computer Science, Sichuan University. M. Ping: Research grant / Funding (institution): School of Computer Science and Engineering, University of Electronic Science and Technology of China. Z. Peng: Research grant / Funding (institution): Big Data Research Center, University of Electronic Science and Technology of China. H. Qiu: Full / Part-time employment: School of Computer Science and Engineering, University of Electronic Science and Technology of China.
Resources from the same session
196P - The tolerability and efficacy of FOLFIRINOX in gastro-oesophageal carcinoma
Presenter: Nicholas Travers
Session: Poster display session
Resources:
Abstract
197TiP - GLOW: Zolbetuximab + CAPOX compared with placebo + CAPOX as first-line treatment for patients with Claudin18.2+/HER2– Locally advanced unresectable or metastatic gastric or gastroesophageal junction (GEJ) adenocarcinoma: A randomized phase III study
Presenter: Rui-Hua Xu
Session: Poster display session
Resources:
Abstract
198TiP - SPOTLIGHT: Comparison of zolbetuximab or placebo + mFOLFOX6 as first-line treatment in patients with claudin18.2+/HER2– locally advanced unresectable or metastatic gastric or gastroesophageal junction adenocarcinoma (GEJ): A randomized phase III study
Presenter: Kensei Yamaguchi
Session: Poster display session
Resources:
Abstract
199TiP - Phase III (COSMIC-312) study of cabozantinib (C) in combination with atezolizumab (A) vs sorafenib (S) in patients (pts) with advanced hepatocellular carcinoma (aHCC) who have not received previous systemic anticancer therapy
Presenter: Thomas Yau
Session: Poster display session
Resources:
Abstract
200P - Apalutamide (APA) plus androgen deprivation therapy (ADT) for metastatic castration-sensitive prostate cancer (mCSPC): Analysis of pain and fatigue in the TITAN study
Presenter: Byung Ha Chung
Session: Poster display session
Resources:
Abstract
201P - Efficacy and safety of darolutamide in non-metastatic castration-resistant prostate cancer (nmCRPC) in the ARAMIS trial
Presenter: Jacob See-tong Pang
Session: Poster display session
Resources:
Abstract
202P - What is the best first-line therapy for metastatic castration-sensitive prostate cancer in 2019? A network meta-analysis
Presenter: Tsz Him So
Session: Poster display session
Resources:
Abstract
203P - Long term outcomes of 2-weekly docetaxel in metastatic high-volume hormone sensitive prostate cancer
Presenter: Suhas Singla
Session: Poster display session
Resources:
Abstract
204P - The effect of radium-223 therapy in agent orange related veterans with metastatic castrate resistance prostate carcinoma (CRPC)
Presenter: Andrew Liman
Session: Poster display session
Resources:
Abstract
205P - Treatment pattern and outcomes of radium-223 (Ra223) in metastatic castration resistant prostate cancer (mCRPC): Retrospective cohort analysis from Hong Kong
Presenter: Darren Poon
Session: Poster display session
Resources:
Abstract