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
490P - Outcomes of sequential epidermal growth factor receptor tyrosine (EGFR) tyrosine kinase inhibitor (TKI) therapy in patients with advanced non-small cell lung carcinoma (NSCLC)- a real-world institutional experience
Presenter: Yvonne Ang
Session: Poster display session
Resources:
Abstract
498P - An observational retrospective study to evaluate the incidence of acquired EGFR T790M resistance in NSCLC patients with EGFR mutation following progression after at least one prior EGFR TKI treatment in Taiwan: ARISE study
Presenter: Shang-gin Wu
Session: Poster display session
Resources:
Abstract
501P - Clinical characteristics and efficacy in non-small cell lung cancer patients with EGFR exon 20 insertion and EGFR amplification
Presenter: Xin Gao
Session: Poster display session
Resources:
Abstract
502P - Epidermal growth factor receptor tyrosine kinase inhibitor treatment response in advanced non-small cell lung cancer with uncommon mutations: A multicenter observational study
Presenter: Masaki Kanazu
Session: Poster display session
Resources:
Abstract
482P - Interim analysis from a phase IIIb, open-label study of afatinib in EGFR TKI-naïve patients (pts) with EGFR mutation-positive (EGFRm+) NSCLC
Presenter: Filippo De Marinis
Session: Poster display session
Resources:
Abstract
483P - A phase IIIb, open-label study of afatinib in EGFR TKI-naïve patients with EGFR mutation-positive NSCLC: A biomarker analysis
Presenter: Rafael Rosell
Session: Poster display session
Resources:
Abstract
484P - Activity of afatinib in patients (pts) with EGFR mutation-positive (EGFRm+) NSCLC and baseline brain metastases: Pooled analysis of three large phase IIIb trials
Presenter: Maya Gottfried
Session: Poster display session
Resources:
Abstract
491P - Clinical outcomes of leptomeningeal metastases in EGFR-mutant lung adenocarcinoma
Presenter: Chia-I Shen
Session: Poster display session
Resources:
Abstract
510P - Paclitaxel as continuation maintenance therapy in patients with advanced non-small cell lung cancer
Presenter: Suzy Gohar
Session: Poster display session
Resources:
Abstract
496P - Higher osimertinib introduction rate achieved by multiple repeated re-biopsy after acquired resistance to first/second generation EGFR-TKIs
Presenter: Taira Ninomaru
Session: Poster display session
Resources:
Abstract