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
329P - High-level expression of HDAC10 is associated with PD-L1 expression and poor prognosis in patients with non-small cell lung cancer receiving pulmonectomy
Presenter: Xiaomei Liu
Session: Poster display session
Resources:
Abstract
331P - A retrospective analysis of immune checkpoint therapy in patients with non-small cell lung cancer: Focus on thyroid disorder
Presenter: Sawana Ono
Session: Poster display session
Resources:
Abstract
332P - Analyse the association between adverse events (AEs) and survival in patients treated with immune checkpoint inhibitors (ICIs)
Presenter: Chi-yuan Cheng
Session: Poster display session
Resources:
Abstract
333P - Study of searching on efficacy of immune checkpoint inhibitor for the non-small cell lung cancer using FDG-PET/CT and thallium SPECT
Presenter: KAYOKO Kibata
Session: Poster display session
Resources:
Abstract
334P - Incidence and characteristic of adrenal insufficiency due to immune checkpoint inhibitors therapy
Presenter: Daisuke Etoh
Session: Poster display session
Resources:
Abstract
335P - PD-L1 profile of nasopharyngeal cancer patients in Indonesia
Presenter: Handoko Handoko
Session: Poster display session
Resources:
Abstract
336P - Pembrolizumab plus chemotherapy versus pembrolizumab monotherapy for PD-L1-positive advanced non-small cell lung cancer in the real world
Presenter: Jun Sugisaka
Session: Poster display session
Resources:
Abstract
337P - Neutrophil-to-Lymphocyte ratio as a predictive factor for hyperprogressive disease in NSCLC patients treated with immune checkpoint inhibitor
Presenter: Ryo Takahashi
Session: Poster display session
Resources:
Abstract
338P - A new insight into tumour immune-evasion: Crosstalk between cancer stem cells and T regulatory cells
Presenter: Abhishek Dutta
Session: Poster display session
Resources:
Abstract
339TiP - PACIFIC-5: Phase III study of durvalumab after either concurrent or sequential chemoradiotherapy (CRT) in patients with stage III NSCLC
Presenter: Yi-Long Wu
Session: Poster display session
Resources:
Abstract