- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[SPIE Image Processing - Houston, United States (2018.2.10-2018.2.15)] Medical Imaging 2018: Image Processing - Deep learning for biomarker regression: application to osteoporosis and emphysema on chest CT scans
摘要： Introduction: Biomarker computation using deep-learning often relies on a two-step process, where the deep learning algorithm segments the region of interest and then the biomarker is measured. We propose an alternative paradigm, where the biomarker is estimated directly using a regression network. We showcase this image-to-biomarker paradigm using two biomarkers: the estimation of bone mineral density (BMD) and the estimation of lung percentage of emphysema from CT scans. Materials and methods: We use a large database of 9,925 CT scans to train, validate and test the network for which reference standard BMD and percentage emphysema have been already computed. First, the 3D dataset is reduced to a set of canonical 2D slices where the organ of interest is visible (either spine for BMD or lungs for emphysema). This data reduction is performed using an automatic object detector. Second, The regression neural network is composed of three convolutional layers, followed by a fully connected and an output layer. The network is optimized using a momentum optimizer with an exponential decay rate, using the root mean squared error as cost function. Results: The Pearson correlation coefficients obtained against the reference standards are r = 0.940 (p < 0.00001) and r = 0.976 (p < 0.00001) for BMD and percentage emphysema respectively. Conclusions: The deep-learning regression architecture can learn biomarkers from images directly, without indicating the structures of interest. This approach simplifies the development of biomarker extraction algorithms. The proposed data reduction based on object detectors conveys enough information to compute the biomarkers of interest.
关键词： regression,deep learning,bone mineral density,computed tomography,emphysema
更新于2025-09-23 15:23:52
-
Effects of ultraviolet irradiation with a LED device on bone metabolism associated with vitamin D deficiency in senescence-accelerated mouse P6
摘要： Aims: This study investigated effects of narrow-range ultraviolet irradiation (UVR) by a new UV–LED device on vitamin D supply and changes of bone in senescence-accelerated mouse P6 (SAMP6) with vitamin D deficiency. Main methods: We used female SAMP6 mice as a senile osteoporotic model. We set a total of 3 groups (n ? 4 per group); D-UVRt group (vitamin D deficient–dietary and UVR), D- (vitamin D deficient–dietary), and Dt groups (vitamin D contained–dietary). Mice in the D-UVR t group were UV–irradiated (305nm) with 1 kJ/m2 twice a week for 12 weeks from 20 to 32 weeks of age. Serum 25(OH)D, 1,25(OH)2D, and micro–computed tomography (CT) were assessed over time. Mechanical test, and histological assay were performed for femurs removed at 32 weeks of age. Key findings: UVR increased both serum 25(OH)D and 1,25(OH)2D levels at 4 and 8 weeks–UVR in the D-UVRt group compared with that in the D- group (P < 0.05, respectively). Relative levels of trabecular bone mineral density in micro–CT were higher in the D-UVRt group than in the D- group at 8 weeks–UVR (P ? 0.048). The ultimate load was significantly higher in the D-UVRt group than in the D- group (P ? 0.036). In histological assay, fewer osteoclasts and less immature bone (/mature bone) could be observed in the D-UVRt group than in the D- group, significantly. Significance: UVR may have possibility to improve bone metabolism associated with vitamin D deficiency in SAMP6 mice.
关键词： Vitamin D,Musculoskeletal system,Osteoporosis,Pathology,Endocrinology,Metabolism,Bone mineral density,LED,Physiology
更新于2025-09-19 17:13:59