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
119P - The impacts of dose-time-fractionation schedules on pathological complete response rate (pCR) and local recurrence (LR)
Presenter: Fu Jin
Session: Poster display session
Resources:
Abstract
120P - Platelet to lymphocyte ratio is associated with tumour localization and outcomes in patients with metastatic colorectal cancer
Presenter: Ahmet Bilici
Session: Poster display session
Resources:
Abstract
121P - Meta-analysis of three-dimensional versus two-dimensional laparoscopic surgery for rectal cancer
Presenter: Laiyuan Li
Session: Poster display session
Resources:
Abstract
127P - Outcomes based on albumin‐bilirubin (ALBI) grade in the phase III CELESTIAL trial of cabozantinib versus placebo in patients with advanced hepatocellular carcinoma (HCC)
Presenter: Stephen Chan
Session: Poster display session
Resources:
Abstract
128P - Tislelizumab in combination with chemotherapy for Chinese patients (Pts) with gastric/gastroesophageal junction cancer (GC/GEJC) or esophageal squamous cell carcinoma (ESCC)
Presenter: Yuxian Bai
Session: Poster display session
Resources:
Abstract
129P - Monitoring patient-specific mutation in ctDNA and CTC for tumour response evaluation after neoadjuvant chemotherapy in advanced gastric adenocarcinoma (NCT03425058)
Presenter: Tao Fu
Session: Poster display session
Resources:
Abstract
130P - Development of a liver cancer risk prediction model for the general population in china: A potential tool for screening
Presenter: Xiaoshuang Feng
Session: Poster display session
Resources:
Abstract
131P - Cabozantinib in Asian patients with hepatocellular carcinoma and other solid tumours: Population pharmacokinetics analysis
Presenter: Chih-Hung Hsu
Session: Poster display session
Resources:
Abstract
132P - Liposomal irinotecan (nal-IRI) plus 5-fluorouracil/levoleucovorin (5 FU/LV) vs 5-FU/LV in Japanese patients (pts) with gemcitabine-refractory metastatic pancreatic cancer (mPAC)
Presenter: Tatsuya Ioka
Session: Poster display session
Resources:
Abstract
133P - Prognostic and predictive factors from the phase III CELESTIAL trial of cabozantinib (C) versus placebo (P) in previously treated advanced hepatocellular carcinoma (aHCC)
Presenter: Thomas Yau
Session: Poster display session
Resources:
Abstract