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
27P - The prognostic value of neutrophil to lymphocyte ratio (NLR) and 18F-FDG PET SUV in breast cancer patients underwent neoadjuvant chemotherapy
Presenter: Soong June Bae
Session: Poster display session
Resources:
Abstract
28P - Accuracy of core biopsy in predicting pathologic complete response in the breast in patients with complete/near complete clinical and radiological response (Complete Responders in the Breast – CRBr): A feasibility study
Presenter: Nisha Hariharan
Session: Poster display session
Resources:
Abstract
29P - Tumour response to neoadjuvant chemotherapy in breast cancer: Routine pathologic markers improve the predictive power of a cell-loss metric based on release of thymidine kinase 1 into blood
Presenter: Bernhard Tribukait
Session: Poster display session
Resources:
Abstract
30P - Comparison of metabolic changes between neoadjuvant chemotherapy and neoadjuvant endocrine therapy in premenopausal women with ER positive, HER2 negative breast cancer
Presenter: Ho-hyun Ryu
Session: Poster display session
Resources:
Abstract
31P - Circulating miR-155 as a potential therapeutic monitoring marker in breast cancer
Presenter: Sumadi Lukman Anwar
Session: Poster display session
Resources:
Abstract
32P - Profile of breast cancer epidemiology in Sanglah General Hospital, Denpasar, Bali from 2012 to 2019
Presenter: Citra Aryanti
Session: Poster display session
Resources:
Abstract
33P - Contrast enhanced chest CT in patients with breast cancer: Comprehensive imaging analysis and correlation with biological markers
Presenter: Bo Hwa Choi
Session: Poster display session
Resources:
Abstract
34P - Verification of metabolic regulatory mechanisms in androgen receptor-positive triple negative breast cancer
Presenter: Yuka Asano
Session: Poster display session
Resources:
Abstract
35TiP - Ribociclib plus goserelin with hormonal therapy versus physician choice chemotherapy in pre-/perimenopausal patients with HR+, HER2– inoperable locally advanced breast cancer (ABC): RIGHT choice study
Presenter: Yen-Shen Lu
Session: Poster display session
Resources:
Abstract
36TiP - A prospective study to assess response to neoadjuvant hormonal therapy in postmenopausal women with hormone-receptor positive breast cancer at a regional cancer centre in South India
Presenter: Shina Goyal
Session: Poster display session
Resources:
Abstract