Development of Convolutional Neural Networks to identify bone metastasis for prostate cancer patients in bone scintigrap
- PDF / 1,107,147 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 65 Downloads / 204 Views
ORIGINAL ARTICLE
Development of Convolutional Neural Networks to identify bone metastasis for prostate cancer patients in bone scintigraphy Nikolaos Papandrianos1 · Elpiniki I. Papageorgiou1,3 · Athanasios Anagnostis2,3 Received: 27 April 2020 / Accepted: 4 August 2020 © The Japanese Society of Nuclear Medicine 2020
Abstract Objective The main aim of this work is to build a robust Convolutional Neural Network (CNN) algorithm that efficiently and quickly classifies bone scintigraphy images, by determining the presence or absence of prostate cancer metastasis. Methods CNN, widely applied in medical image classification, was used for bone scintigraphy image classification. The retrospective study included 778 sequential male patients who underwent whole-body bone scans. A nuclear medicine physician classified all the cases into 3 categories: (1) normal, (2) malignant, and (3) degenerative, which were used as the gold standard. Results An efficient CNN architecture was built, based on CNN exploration performance, achieving high prediction accuracy. The results showed that the method is sufficiently precise when it comes to differentiating a bone metastasis from other either degenerative changes or normal tissue (overall classification accuracy = 91.42% ± 1.64%). To strengthen the outcomes of this study the authors further compared the best performing CNN method to other popular CNN architectures for medical imaging, like ResNet50, VGG16 and GoogleNet, as reported in the literature. Conclusions The prediction results reveal the efficacy of the proposed CNN-based approach and its ability for an easier and more precise interpretation of whole-body images in bone metastasis diagnosis for prostate cancer patients in nuclear medicine. This leads to marked effects on the diagnostic accuracy and decision-making regarding the treatment to be applied. Keywords Bone metastasis · Prostate cancer · Nuclear imaging · Bone scintigraphy · Deep learning · Image classification · Convolutional Neural Networks
Introduction Bone metastasis is one of the most frequent cancer complications and emerges mainly in patients with certain types of primary tumors, especially of the breast, prostate and lung * Nikolaos Papandrianos [email protected]
Elpiniki I. Papageorgiou [email protected]; [email protected]
Athanasios Anagnostis [email protected]; [email protected]
1
Department of Energy Systems, Faculty of Technology, University of Thessaly, Geopolis Campus, Larissa ‑ Trikala Ring Road, 41500 Larissa, Greece
2
Computer Science & Telecommunications Department, University of Thessaly, 35131 Lamia, Greece
3
Institute for Bio-economy and Agri-technology, Center for Research and Technology Hellas, Thessaloníki, Greece
[1]. These types of cancer have great avidity for bone, causing painful and untreatable symptoms; thus, an early diagnosis is a crucial factor for making treatment decisions as well as possibly having a significant impact on the progress of the disease and patient quality of lif
Data Loading...
