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
15P - Comparing the outcomes of the mastectomy using the tumescent technique by between the special and non-special surgeons
Presenter: Naoya Takeda
Session: Poster display session
Resources:
Abstract
16P - Risk factors and prognostic value of non-alcoholic fatty liver disease (NAFLD) in hormone positive, non-metastatic breast cancer receiving adjuvant hormonal therapy
Presenter: Kartika Taroeno Hariadi
Session: Poster display session
Resources:
Abstract
17P - Distance related outcome in indigenous and non-indigenous breast cancer women of Western Australia
Presenter: Azim Khan
Session: Poster display session
Resources:
Abstract
18P - Usefulness of neutrophil to lymphocyte ratio in early stage breast cancer as predictor of disease-free survival in a Babylon Oncology Center
Presenter: Yaala Raof Al-Bairmany
Session: Poster display session
Resources:
Abstract
19P - Silymarin functionalized quantum cores as selective inhibitor of polo-like kinase 1, and preclinical antitumor activity in human breast cancer xenografts
Presenter: Manickam Paulpandi
Session: Poster display session
Resources:
Abstract
20P - Diagnostic value of serum HER-2 level in compression with tissue HER-2 in breast cancer: A systematic review and meta-analysis
Presenter: Amir Shamshirian
Session: Poster display session
Resources:
Abstract
21P - Clinical outcome of treatment without trastuzumab in HER2 positive breast cancer patients
Presenter: Than Than Aye
Session: Poster display session
Resources:
Abstract
22P - Clinical outcomes after skin-sparing or nipple areolar complex-sparing mastectomy with sentinel lymph node biopsy in early breast cancer patients
Presenter: Hye Yoon Lee
Session: Poster display session
Resources:
Abstract
23P - The correlations between knowledge and attitudes of productive age women toward “SADARI” (breast self-assessment) as early detection of breast cancer in Pejeng Kaja Village, Ubud, Bali
Presenter: Yorky Brahmantya
Session: Poster display session
Resources:
Abstract
24TiP - KEYNOTE-756: A randomized, double-blind, phase III study of pembrolizumab or placebo with neoadjuvant chemotherapy and adjuvant endocrine therapy for high-risk, early-stage, ER+/HER2−breast cancer
Presenter: Fatima Cardoso
Session: Poster display session
Resources:
Abstract