Next Article in Journal
FUCCI Real-Time Cell-Cycle Imaging as a Guide for Designing Improved Cancer Therapy: A Review of Innovative Strategies to Target Quiescent Chemo-Resistant Cancer Cells
Next Article in Special Issue
Computer Extracted Features from Initial H&E Tissue Biopsies Predict Disease Progression for Prostate Cancer Patients on Active Surveillance
Previous Article in Journal
Classifying Lung Neuroendocrine Neoplasms through MicroRNA Sequence Data Mining
Previous Article in Special Issue
Radiomics at a Glance: A Few Lessons Learned from Learning Approaches
Open AccessArticle

Analysis of Bone Scans in Various Tumor Entities Using a Deep-Learning-Based Artificial Neural Network Algorithm—Evaluation of Diagnostic Performance

1
Department of Radiology and Nuclear Medicine, University Hospital Magdeburg, Leipziger Street 44, 39120 Magdeburg, Germany
2
Research Campus STIMULATE, Otto-von-Guericke University, 39106 Magdeburg, Germany
*
Author to whom correspondence should be addressed.
Cancers 2020, 12(9), 2654; https://doi.org/10.3390/cancers12092654
Received: 23 July 2020 / Revised: 11 September 2020 / Accepted: 13 September 2020 / Published: 17 September 2020
(This article belongs to the Special Issue Radiomics and Cancers)
Standardized reading schemes, the use of indicators derived from medical images and the use of deep learning-based algorithms become very popular in medical imaging. In this retrospective study, we evaluated the performance of an automatic deep-learning-based algorithm for computer-assisted diagnosis in the field of oncological whole-body bone imaging in nuclear medicine. In addition to prostate cancer, representing a tumor entity evaluated thoroughly using the examined methodology (Bone Scan Imaging (BSI) methodology), a modification of the BSI based standard rating scheme facilitate the use of the methodology for other tumor entities (e.g., breast cancer, lung cancer, hepatocellular carcinoma). Diagnostics in clinical routine can benefit from the examined methodology, mainly due to its sensitivity and the high negative predictive value. Non-pathological bone scans may be easily identified. This may lead to a reduced working load in nuclear medicine departments and may result in an improved and more standardized workflow.
The bone scan index (BSI), initially introduced for metastatic prostate cancer, quantifies the osseous tumor load from planar bone scans. Following the basic idea of radiomics, this method incorporates specific deep-learning techniques (artificial neural network) in its development to provide automatic calculation, feature extraction, and diagnostic support. As its performance in tumor entities, not including prostate cancer, remains unclear, our aim was to obtain more data about this aspect. The results of BSI evaluation of bone scans from 951 consecutive patients with different tumors were retrospectively compared to clinical reports (bone metastases, yes/no). Statistical analysis included entity-specific receiver operating characteristics to determine optimized BSI cut-off values. In addition to prostate cancer (cut-off = 0.27%, sensitivity (SN) = 87%, specificity (SP) = 99%), the algorithm used provided comparable results for breast cancer (cut-off 0.18%, SN = 83%, SP = 87%) and colorectal cancer (cut-off = 0.10%, SN = 100%, SP = 90%). Worse performance was observed for lung cancer (cut-off = 0.06%, SN = 63%, SP = 70%) and renal cell carcinoma (cut-off = 0.30%, SN = 75%, SP = 84%). The algorithm did not perform satisfactorily in melanoma (SN = 60%). For most entities, a high negative predictive value (NPV ≥ 87.5%, melanoma 80%) was determined, whereas positive predictive value (PPV) was clinically not applicable. Automatically determined BSI showed good sensitivity and specificity in prostate cancer and various other entities. Particularly, the high NPV encourages applying BSI as a tool for computer-aided diagnostic in various tumor entities. View Full-Text
Keywords: bone scan; bone scan index; bone metastases; deep learning; radiomics bone scan; bone scan index; bone metastases; deep learning; radiomics
Show Figures

Figure 1

MDPI and ACS Style

Wuestemann, J.; Hupfeld, S.; Kupitz, D.; Genseke, P.; Schenke, S.; Pech, M.; Kreissl, M.C.; Grosser, O.S. Analysis of Bone Scans in Various Tumor Entities Using a Deep-Learning-Based Artificial Neural Network Algorithm—Evaluation of Diagnostic Performance. Cancers 2020, 12, 2654.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop