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
221P - Comparative analysis of first-line immune checkpoint inhibitor versus carboplatin-based chemotherapy for cisplatin-ineligible metastatic urothelial carcinoma: A multicenter, retrospective real-world evidence
Presenter: Hsiang‐Lan Lai
Session: Poster display session
Resources:
Abstract
222P - Does tumor grade really improve the prognostic ability of the staging system for men with penile cancer: A SEER database analysis
Presenter: Ravi Kanodia
Session: Poster display session
Resources:
Abstract
223TiP - EV-301: A phase III trial in progress evaluating enfortumab vedotin versus chemotherapy in patients with locally advanced or metastatic urothelial carcinoma
Presenter: Daniel Petrylak
Session: Poster display session
Resources:
Abstract
230P - Olaparib maintenance therapy in patients (pts) with a BRCA1 and/or BRCA2 mutation (BRCAm) and newly diagnosed advanced ovarian cancer (OC): SOLO1 China cohort
Presenter: Lingying Wu
Session: Poster display session
Resources:
Abstract
231P - Cost-effectiveness of olaparib vs routine surveillance in the maintenance setting for patients with BRCA-mutated advanced ovarian cancer after response to first-line platinum-based chemotherapy in Singapore
Presenter: David SP Tan
Session: Poster display session
Resources:
Abstract
233P - Incorporation of correlative studies in ovarian cancers in the era of precision medicine: Assessment of accountability and utility
Presenter: Nadia Hitchen
Session: Poster display session
Resources:
Abstract
234P - Implementation of mainstream BRCA testing in epithelial ovarian cancer in a tertiary centre
Presenter: Edbert Wong
Session: Poster display session
Resources:
Abstract
235P - The efficacy of radiation therapy in ovarian carcinoma: A propensity score analysis of a population-based study
Presenter: Jian-Guo Zhou
Session: Poster display session
Resources:
Abstract
236P - Front-line maintenance therapy for platinum-sensitive ovarian cancer: What’s next PARP inhibitors?
Presenter: Han Gong
Session: Poster display session
Resources:
Abstract
237P - PARP inhibitor in platinum resistant ovarian cancer: Single center real world experience
Presenter: Saphalta Baghmar
Session: Poster display session
Resources:
Abstract