A software program for automated compressive vertebral fracture detection on elderly women's lateral chest radiograph: Ofeye 1.0.

Background: Because osteoporotic vertebral fracture (OVF) on chest radiographs is commonly missed in radiological reports, we aimed to develop a software program which offers automated detection of compressive vertebral fracture (CVF) on lateral chest radiographs, and which emphasizes CVF detection specificity with a low false positivity rate. Methods: For model training, we retrieved 3,991 spine radiograph cases and 1,979 chest radiograph cases from 16 sources, with among them in total 1,404 cases had OVF. For model testing, we retrieved 542 chest radiograph cases and 162 spine radiograph cases from four independent clinics, with among them 215 cases had OVF. All cases were female subjects, and except for 31 training data cases which were spine trauma cases, all the remaining cases were post-menopausal women. Image data included DICOM (Digital Imaging and Communications in Medicine) format, hard film scanned PNG (Portable Network Graphics) format, DICOM exported PNG format, and PACS (Picture Archiving and Communication System) downloaded resolution reduced DICOM format. OVF classification included: minimal and mild grades with <20% or ≥20-25% vertebral height loss respectively, moderate grade with ≥25-40% vertebral height loss, severe grade with ≥40%-2/3 vertebral height loss, and collapsed grade with ≥2/3 vertebral height loss. The CVF detection base model was mainly composed of convolution layers that include convolution kernels of different sizes, pooling layers, up-sampling layers, feature merging layers, and residual modules. When the model loss function could not be further decreased with additional training, the model was considered to be optimal and termed 'base-model 1.0'. A user-friendly interface was also developed, with the synthesized software termed 'Ofeye 1.0'. Results: Counting cases and with minimal and mild OVFs included, base-model 1.0 demonstrated a specificity of 97.1%, a sensitivity of 86%, and an accuracy of 93.9% for the 704 testing cases. In total, 33 OVFs in 30 cases had a false negative reading, which constituted a false negative rate of 14.0% (30/215) by counting all OVF cases. Eighteen OVFs in 15 cases had OVFs of ≥ moderate grades missed, which constituted a false negative rate of 7.0% (15/215, i.e., sensitivity 93%) if only counting cases with ≥ moderate grade OVFs missed. False positive reading was recorded in 13 vertebrae in 13 cases (one vertebra in each case), which constituted a false positivity rate of 2.7% (13/489). These vertebrae with false positivity labeling could be readily differentiated from a true OVF by a human reader. The software Ofeye 1.0 allows 'batch processing', for example, 100 radiographs can be processed in a single operation. This software can be integrated into hospital PACS, or installed in a standalone personal computer. Conclusions: A user-friendly software program was developed for CVF detection on elderly women's lateral chest radiographs. It has an overall low false positivity rate, and for moderate and severe CVFs an acceptably low false negativity rate. The integration of this software into radiological practice is expected to improve osteoporosis management for elderly women.

Application of Neurite Orientation Dispersion and Density Imaging in Assessing Glioma Grades and Cellular Proliferation.

OBJECTIVE: To explore the performance of neurite orientation dispersion and density imaging (NODDI) in grading gliomas and to evaluate the cellular proliferation. METHODS: NODDI and diffusion-weighted imaging were performed on 79 patients with histopathologically proven gliomas. Parameter maps of intracellular volume fraction (ICVF), orientation dispersion index (ODI), and apparent diffusion coefficient (ADC) were calculated. Regions of interest were placed in the most solid part of the tumor. These metrics were normalized to the contralateral normal-appearing white matter and correlated with Ki-67 expression. RESULTS: ICVF and ODI increased as tumor grades increased, whereas ADC decreased with the increase of tumor grades. Significant differences in normalized ICVF and ODI were observed between low-grade gliomas and high-grade gliomas (ICVF: 0.208 ± 0.104 vs. 0.718 ± 0.234; ODI: 0.952 ± 0.428 vs. 1.767 ± 0.636, P < 0.001, respectively) and between grades II and III (ICVF: 0.208 ± 0.104 vs. 0.603 ± 0.253; ODI: 0.952 ± 0.428 vs. 1.762 ± 0.542, P < 0.001, respectively). Normalized ICVF was also significantly different between grades III and IV (0.603 ± 0.253 vs. 0.803 ± 0.182, P = 0.004). Ki-67 labeling index was positively correlated with normalized ICVF and ODI (r = 0.755 and 0.572, P < 0.001, respectively), and negatively correlated with normalized ADC (r = -0.709, P < 0.001). CONCLUSIONS: NODDI is a promising method in grading gliomas and predicting cellular proliferation. These results may be of great significance for the clinical diagnosis and treatment of gliomas.

[Myocardial single photon emission tomography imaging of reporter gene expression in rabbits].

OBJECTIVE: To explore the feasibility of single photon emission computed tomography (SPECT) detection of heart reporter gene expression and observed the optimal transfecting titer and imaging time by using herpes simplex virus 1-thymidine kinase (HSV1-tk) as reporter gene and 131I-2'-fluoro-2'-deoxy-1-beta-D-arabinofuranosyl-5-iodouracil (131I-FIAU) as reporter probe in rabbit myocardium. METHODS: The recombinant Ad-tk carrying HSV1-tk gene and adenovirus (Ad) as vector was constructed and intramyocardially injected to rabbits at various concentrations (1 x 10(9) pfu, 5 x 10(8) pfu, 1 x 10(8) pfu, 5 x 10(7) pfu, 1 x 10(7) pfu). Two days later, rabbits were injected with 600 microCi 131I-FIAU in ear-margin vein and then underwent SPECT myocardium imaging for detection of HSV1-tk expression at 6 h, 24 h, 48 h and 72 h after injection, rabbits with 1 x 10(9) pfu Ad-tk injection were imaged at 96 h and 120 h. Rabbits were sacrificed after imaging and the total myocardial 131I-FIAU accumulation was quantified in percent of injected dose per gram myocardium (% ID/g). The myocardial Ad-tk expression was determined with RT-PCR. RESULTS: Reporter gene was detected by SPECT imaging in the injection site while not detected in the control myocardium and site remote from injection. RT-PCR results also evidenced HSV1-tk express in the injection site. The SPECT target/nontarget ratio was correlated with ex vivo gamma-counting (r2 = 0.933, P<0.01) and expression of HSV1-tk (r2 = 0.877, P<0.01). Myocardial accumulation could be identified at viral titers as low as 1 x 10(7) pfu by SPECT imaging. CONCLUSION: The cardiac SPECT reporter gene imaging with HSV1-tk as reporter gene and 131I-FIAU as reporter probe is feasible.