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
144P - Severe hypovitaminosis D in metastatic gastric cancer patients from the Northern and Southern hemispheres: Data from the EXPAND phase III trial
Presenter: Radka Obermannova
Session: Poster display session
Resources:
Abstract
145P - Role of Glasgow prognostic score in chemo-naïve patients with advanced biliary tract cancer and good performance status
Presenter: Toshikazu Moriwaki
Session: Poster display session
Resources:
Abstract
146P - Anatomic versus non-anatomic resection for hepatocellular carcinoma: A meta-analysis of high-quality studies
Presenter: Bin Zhang
Session: Poster display session
Resources:
Abstract
147P - Clinical outcomes of proximal gastrectomy versus total gastrectomy for locally advanced proximal gastric cancer: a propensity score matching analysis
Presenter: Yingtai Chen
Session: Poster display session
Resources:
Abstract
148P - Efficacy of capecitabine and oxaliplatin versus S-1 as adjuvant chemotherapy in gastric cancer after D2 lymph node dissection according to lymph node ratio and N stage
Presenter: Seunghwan Lee
Session: Poster display session
Resources:
Abstract
150P - A Phase Ib Study of IMU-131 HER2/neu peptide vaccine plus chemotherapy in patients with HER2/neu overexpressing metastatic or advanced adenocarcinoma of the stomach or gastroesophageal junction
Presenter: Yee Chao
Session: Poster display session
Resources:
Abstract
151P - Gene expression profiling for a better understanding of gastric cancer: From the perspective of metabolic rearrangement
Presenter: Midie Xu
Session: Poster display session
Resources:
Abstract
152P - Long-term outcomes of three-dimensional conformal radiotherapy-based and intensity-modulated radiotherapy-based concurrent chemoradiotherapy in patients with thoracic esophageal squamous cell carcinoma
Presenter: Chia-Lun Chang
Session: Poster display session
Resources:
Abstract
153P - Exosomal LINC00174 facilitates epithelial-mesenchymal transition in residual hepatocellular carcinoma after insufficient radiofrequency ablation by regulating c-JUN/MYCBP/c-Myc axis
Presenter: Dening Ma
Session: Poster display session
Resources:
Abstract
154P - Genetic characteristics of participants in the Australian Pancreatic Screening Study
Presenter: Krithika Murali
Session: Poster display session
Resources:
Abstract