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
458P - Mutation tracking in circulating tumour DNA predicts relapse in completely resected EGFR-mutated NSCLC
Presenter: Martin Filipits
Session: Poster display session
Resources:
Abstract
460P - Mendelian randomization study showed no causality between metformin use and lung cancer risk
Presenter: Jiayi Shen
Session: Poster display session
Resources:
Abstract
461P - Blood trace minerals and lung cancer: A Mendelian randomization study
Presenter: Wei Xian
Session: Poster display session
Resources:
Abstract
463P - Prediction of invasiveness in lung adenocarcinoma using machine learning algorithm based on 3D-CT imaging
Presenter: Yusuke Saeki
Session: Poster display session
Resources:
Abstract
459P - Fish intake, dietary polyunsaturated fatty acids, and lung cancer: systematic review and dose-response meta-analysis of 1.7 million men and women
Presenter: Chao Cao
Session: Poster display session
Resources:
Abstract
462P - Usefulness for prevention of postoperative cerebrovascular complications in patients with lung cancer using carotid ultrasonography
Presenter: Sadanori Takeo
Session: Poster display session
Resources:
Abstract
468P - Histological type analysis of 10-year follow-up of WJTOG0105: A phase III study comparing second- and third-generation regimens with concurrent thoracic radiotherapy in unresectable stage III non-small cell lung cancer
Presenter: Masahiro Tsuboi
Session: Poster display session
Resources:
Abstract
469P - Comparison of combined chemoradiotherapy regimens; Paclitaxel plus carboplatin and cisplatin plus etoposide for locally advanced non-small cell lung cancer: A randomised phase III trial
Presenter: Alper Ata
Session: Poster display session
Resources:
Abstract
472P - Integration of expression rate and absolute cell counts of PD-1+ stromal tumour-infiltrating lymphocytes: Prognostic significance in esophageal squamous cell carcinoma
Presenter: Qingkun Song
Session: Poster display session
Resources:
Abstract
467P - The free-circulating mtDNA copies number in plasma of patients with NSCLC
Presenter: Olga Bulgakova
Session: Poster display session
Resources:
Abstract