Current development and prospects of deep learning in spine image analysis: a literature review.

Background and Objective: As the spine is pivotal in the support and protection of human bodies, much attention is given to the understanding of spinal diseases. Quick, accurate, and automatic analysis of a spine image greatly enhances the efficiency with which spine conditions can be diagnosed. Deep learning (DL) is a representative artificial intelligence technology that has made encouraging progress in the last 6 years. However, it is still difficult for clinicians and technicians to fully understand this rapidly evolving field due to the diversity of applications, network structures, and evaluation criteria. This study aimed to provide clinicians and technicians with a comprehensive understanding of the development and prospects of DL spine image analysis by reviewing published literature. Methods: A systematic literature search was conducted in the PubMed and Web of Science databases using the keywords "deep learning" and "spine". Date ranges used to conduct the search were from 1 January, 2015 to 20 March, 2021. A total of 79 English articles were reviewed. Key Content and Findings: The DL technology has been applied extensively to the segmentation, detection, diagnosis, and quantitative evaluation of spine images. It uses static or dynamic image information, as well as local or non-local information. The high accuracy of analysis is comparable to that achieved manually by doctors. However, further exploration is needed in terms of data sharing, functional information, and network interpretability. Conclusions: The DL technique is a powerful method for spine image analysis. We believe that, with the joint efforts of researchers and clinicians, intelligent, interpretable, and reliable DL spine analysis methods will be widely applied in clinical practice in the future.

Spatiotemporal Flexible Sparse Reconstruction for Rapid Dynamic Contrast-Enhanced MRI.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a tissue perfusion imaging technique. Some versatile free-breathing DCE-MRI techniques combining compressed sensing (CS) and parallel imaging with golden-angle radial sampling have been developed to improve motion robustness with high spatial and temporal resolution. These methods have demonstrated good diagnostic performance in clinical setting, but the reconstruction quality will degrade at high acceleration rates and overall reconstruction time remains long. In this paper, we proposed a new parallel CS reconstruction model for DCE-MRI that enforces flexible weighted sparse constraint along both spatial and temporal dimensions. Weights were introduced to flexibly adjust the importance of time and space sparsity, and we derived a fast-thresholding algorithm which was proven to be simple and efficient for solving the proposed reconstruction model. Results on both the brain tumor DCE and liver DCE show that, at relatively high acceleration factor of fast sampling, lowest reconstruction error and highest image structural similarity are obtained by the proposed method. Besides, the proposed method achieves faster reconstruction for liver datasets and better physiological measures are also obtained on tumor images.

pFISTA-SENSE-ResNet for parallel MRI reconstruction.

Magnetic resonance imaging has been widely applied in clinical diagnosis. However, it is limited by its long data acquisition time. Although the imaging can be accelerated by sparse sampling and parallel imaging, achieving promising reconstructed images with a fast computation speed remains a challenge. Recently, deep learning methods have attracted a lot of attention for encouraging reconstruction results, but they are lack of proper interpretability for neural networks. In this work, in order to enable high-quality image reconstruction for the parallel magnetic resonance imaging, we design the network structure from the perspective of sparse iterative reconstruction and enhance it with the residual structure. Experimental results on a public knee dataset indicate that, as compared with the state-of-the-art deep learning-based and optimization-based methods, the proposed network achieves lower error in reconstruction and is more robust under different samplings.

Facile preparation of near-infrared fluorescence and magnetic resonance dual-modality imaging probes based on mesoporous organosilica nanoparticles.

In this work, near-infrared fluorescence (NIRF) and magnetic resonance (MR) dual-modality imaging probes are prepared by conjugating maleimide derivative cyanine dye (Mal-Cy5.5), gadolinium-diethylenetriamine pentaacetic acid (Gd-DTPA), and RGD peptide (Mal-PEG2-RGD) on thioether-bridged mesoporous organosilica nanoparticles (MONs) via click reaction. Fourier transform infrared (FT-IR) spectra, zeta potentials, UV-vis spectra, and energy dispersive X-ray (EDX) spectrum confirm the successful modifications of the functional molecules on the MONs. The prepared MON-Gd-Cy5.5-RGD probes shows excellent NIRF and MR imaging properties, and the relaxivity rate (r1) is measured up to 2.85 mM-1 s -1. In addition, the MON-Gd-Cy5.5-RGD probes show excellent in vitro and in vivo biocompatibility. Confocal laser scanning microscopy and flow cytometry demonstrate that the MON-Gd-Cy5.5-RGD can efficiently target to MDA-MB-231 tumor cells. Additionally, ex vivo NIFR and in vivo MR imaging demonstrate that the MON-Gd-Cy5.5-RGD probes can accumulate in tumor and improve the signals of tumor.

Small size mesoporous organosilica nanorods with different aspect ratios: Synthesis and cellular uptake.

In the work, small size thioether-bridged mesoporous organosilica nanorod (MONRs) are successfully synthesized using cetyltrimethylammonium bromide (CTAB) as structure-directing agent and bis[3-(triethoxysilyl)propyl]tetrasulfide (TETS) and tetraethoxysilane (TEOS) as co-precursors. The MONRs have tunable aspect ratios of 2, 3, and 4 (denoted as MONRs-2, MONRs-3, and MONRs-4), small and controllable lengths (75-310nm), high surface area (570-870cm2g-1), uniform mesopores (2.4-2.6nm), large pore volume (0.34cm3g-1), and excellent biocompatibility. The uptake of the MONRs by multidrug resistant human breast cancer MDR-MCF-7 cells is related to their aspect ratios. The MONRs-3 shows a faster and higher cellular internalization compared to the MONRs-4 and MONRs-2, respectively. Thanks to the high cellular uptake, doxorubicin (DOX) loaded MONRs-3 show obviously improved chemotherapeutic effect on MDR-MCF-7 cancer cells. It is expected that the MONRs provide a useful platform for drug delivery and therapeutics.

Underlying Anatomy and Typing Diagnosis of May-Thurner Syndrome and Clinical Significance: An Observation Based on CT.

STUDY DESIGN: Cross-sectional study. OBJECTIVE: To explore the underlying anatomy of May-Thurner syndrome (MTS) using computed tomography (CT) and discuss its clinical significance for typing diagnosis. SUMMARY OF BACKGROUND DATA: Because the anatomical position of the corpse cannot fully illustrate the actual clinical situation in vivo, the diversity of MTS has not been fully elucidated yet. METHODS: We retrospectively analyzed the data of 69 patients with MTS. By CT showing, patients were categorized to simple MTS (sMTS, 22 patients), lumbar degeneration-related MTS (dMTS, 33 patients) and other causes MTS (oMTS, 14 patients); meanwhile, a healthy control group were set. Evaluated indexes were onset age, course of disease, diameter of the iliac vein tunnel (IVTD), lumbar degeneration-related iliac vein compression (IVC), therapeutic effect, and diagnostic cutoff of risk IVTD prone to MTS. RESULTS: The onset age of sMTS, dMTS, and oMTS were respectively 42.3 ±â€Š6.5 years, 61.5 ±â€Š10.6 years, and 53.1 ±â€Š16.8 years (P < 0.001); courses were respectively 12.1 ±â€Š9.2 days, 22.5 ±â€Š7.6 days, and 6.8 ±â€Š6.7 days (P = 0.002). IVTDs of sMTS, dMTS, oMTS, and the control were respectively 2.52 ±â€Š0.50 mm, 2.29 ±â€Š0.30 mm, 5.93 ±â€Š2.21 mm, and 4.34 ±â€Š1.61 mm (P < 0.001). Lumbar degeneration-related IVC in dMTS occurred at 41 places, including forward bulging or protruding intervertebral discs (51%,17/33), osteophytes (50%,16/33), and spondylolisthesis (19%, 8/33), but none happened in sMTS, oMTS, and the control. Eighty-six percent of sMTSs, 55% dMTSs, and none oMTSs needed intravenous stent-implanted operation to obtain effective treatment. MTS type (Waldχ = 6.092, P = 0.009), course (Waldχ = 4.618, P = 0.032), and treatment plan (Waldχ = 14.748, P < 0.001) markedly influence the therapeutic result. The cutoff of risk IVTD for sMTS and dMTS was 2.98 mm, which diagnostic sensitivity was 90% and specificity 100%. CONCLUSION: Owing to the distinct pathoanatomy and causes, diagnosis in classification of MTS by CT is helpful in accurate treatment program. LEVEL OF EVIDENCE: 3.

Features of Computed Tomography Perfusion of Mediastinal Lymphadenopathies: a Pathology-based Retrospective Study.

OBJECTIVE: To explore the features of various mediastinal lymphadenopathies using computed tomography perfusion (CTP). METHODS: CTP parameters (CTPs) of the selected mediastinal nodes from 59 patients with pathology-proven malignant lymph nodes and of those from 29 patients with clinically diagnosed or pathology-proven inflammatory lymphadenopathies were collected. Patients were divided into subgroups by etiology and phase of primary disease, including different pathological malignant nodes and diverse inflammatory nodes. CTPs were defined as blood flow (BF), blood volume (BV), mean transit time (MTT), permeability (PMB), and time to peak (TTP). Differences of CTPs were compared between malignant and benign nodes, and among subgroups, respectively. RESULTS: In the mediastinum, no significant differences of CTPs were found between malignant and benign groups (all P>0.05), the same for subgroups of malignant nodes (all P>0.05). Acute lymphadenitis had higher BF and BV than chronic inflammatory, lymphoid tuberculosis, sarcoidosis and malignant nodes. The BF of malignant nodes was markedly slower than that of acute lymphadenitis (P=0.01), but faster than chronic inflammatory nodes (P=0.04) and sarcoidosis (P=0.03), with no significant difference compared with lymphoid tuberculosis. Pneumonia-complicated lymphoid tuberculosis showed the longest MTT while sarcoidosis displayed the shortest MTT, and inflammatory nodes, lymphoid tuberculosis without complicated pneumonia and malignant nodes had moderate MTT. CONCLUSION: CTPs show promising potential in distinguishing various lymphadenopathies in the mediastinum, but more studies are needed to improve their specificity.

Dysfunctional microcirculation of the lumbar vertebral marrow prior to the bone loss and intervertebral discal degeneration.

STUDY DESIGN: Descriptive study, stratified sampling. OBJECTIVE: Using dynamic computed tomographic perfusion (CTP) to explore the age-related distribution patterns of the microcirculation perfusion in the vertebral marrow, the vertebral bone mineral density (BMD), and the intervertebral discal degeneration (IDD) further to discuss the possible causation between them. SUMMARY OF BACKGROUND DATA: A latest viewpoint deemed that reduced blood supply of the vertebral marrow was correlated with an increased incidence of IDD and loss of BMD. However, the causative relationship between them needs more investigation. METHODS: One hundred eighty-six general people were randomly enrolled by stratified sampling and grouped by age: 15 years or less, 16 to 25 years, 26 to 35 years, 36 to 45 years, 46 to 55 years, 56 to 65 years, 66 to 75 years, and 76 years or more. Both CTP and BMD of the third and fourth lumbar vertebral marrow were measured, and the IDD incidence of the third-fourth vertebrae was assessed. The temporal-spatial distribution patterns of the age-related changes of CTP, BMD, and IDD were described, and the correlations between them were calculated. RESULTS: Microcirculatory perfusion of the vertebral marrow developed to maturate by 25 years, maintained stable at 35 years, and then declined by age after 35 years. BMD grew to a peak phase in 26 to 45 years and then dropped by years. However, IDD presented a sudden increase after 45 years of age. CTP (blood flow [r=0.806], blood volume [r=0.685], and permeability [r=0.619]) showed strong positive correlations and CTP (time to peak [r=-0.211], mean transit time [r=-0.598]) showed negative correlations with BMD. Meanwhile, CTP (blood flow [r=-0.815], blood volume [r=-0.753], and permeability [r=-0.690]) had strong negative correlations and CTP (time to peak [r=0.323] and mean transit time [r=0.628]) had positive correlations with the incidence of IDD. CONCLUSION: Aging-related decrease of the microcirculatory perfusion of the lumbar vertebral marrow preceded the loss of BMD and the onset of IDD, indicating their possible causal relationship. LEVEL OF EVIDENCE: 3.

Decrease with aging of the microcirculatory function of the lumbar vertebral marrow preceding the loss of bone material density and the onset of intervertebral discal degeneration: A study about the potential cause.

OBJECTIVE: Using a dynamic computed tomographic perfusion (CTP) imaging method to explore the age-related distribution of the microcirculation perfusion function in the vertebral marrow, the bone material density (BMD), and the intervertebral discal degeneration (IDD). Further, to discuss a possible causation relationship between them. METHODS: One hundred and eighty-six people were randomly enrolled by stratified sampling and grouped by age: ≤15, 16-25, 26-35, 36-45, 46-55, 56-65, 66-75, and ≥76 years old. The average CTP and BMD of the third and fourth lumbar vertebrae marrow were measured and the IDD incidence of the third-fourth vertebrae was assessed. The temporal-spatial distribution patterns of the age-related changes of the CTP, BMD, and IDD were described, and the correlations between them were calculated. RESULTS: The microcirculatory perfusion function of the vertebral marrow develops to maturity by 25 years and is maintained until age 35, then declines with aging. The BMD grew to a peak from 26 to 45 years old, then decreased yearly. The IDD showed a sudden increase after 45 years of age. The CTP [BF (r = 0.806, P = 0.000), BV (r = 0.685, P = 0.005) and PMB (r = 0.619, P = 0.001)] showed strong positive correlations and CTP [TTP (r = -0.211, P = 0.322) and MTT (r = -0.598, P = 0.002)] showed negative correlations with BMD. The CTP [BF (r = -0.815, P = 0.000), BV (r = -0.753, P = 0.000) and PMB (r = -0.690, P = 0.000)] had strong negative correlations, and CTP [TTP (r = 0.323, P = 0.126) and MTT (r = 0.628, P = 0.001)] had positive correlations with the incidence of IDD. CONCLUSION: The decrease with aging of the microcirculatory perfusion in the lumbar vertebral marrow preceded, and is a potential causative factor for the loss of BMD and the onset of IDD.

[Establishment and application of multiplex PCR for non-O157 H7 STEC virulence genes detection].

OBJECTIVE: Traditional detection approaches for non-O157 STEC are both time and labour consuming in diseases surveillance. Virulence genes detection based on multiplex PCR could not only improve the detection efficiency but also increase the accuracy. METHODS: Six virulence genes of non-O157:H7 (stx1, stx2, eae, hly, etpD, katP6) were detected by two groups of trebling PCRs. The multiplex PCRs were optimized by melting curve analysis in SYBR Green I real-time PCR. Testing result of multiplex PCR was consistent with serological testing. RESULTS: The sensitivity limits of the multiplex PCR for stx1, stx2, eaeP, etpD, katP, and hly were 10 ng/ml, 120 ng/ml, 110 ng/ml,165 ng/ml, 85 ng/ml, and 15 ng/ml, respectively, which is similar with that of single PCR. When the multiplex PCR was applied in 120 adults and 90 children diarrhea samples detection, 13 cases were detected for non-O157 positive. CONCLUSION: The method we established can be used for non-O157 STEC virulence genes detection and screening with high efficiency and accuracy.

[1-(4-Chloro-phen-yl)-5-hy-droxy-3-phenyl-1H-pyrazol-4-yl](thio-phen-2-yl)methanone.

In the title compound, C(20)H(13)ClN(2)O(2)S, the chloro-phenyl, phenyl and thienoyl rings are oriented at dihedral angles 17.84 (7), 53.13 (8) and 34.03 (8)°, respectively, to the central pyrazole ring. An intra-molecular O-H⋯O hydrogen bond occurs. In the crystal, pairs of bifurcated O-H⋯O hydrogen bonds link mol-ecules into inversion dimers with R(2) (2)(12) graph-set motifs.

[HIV prevalence and its associated factors among men who have sex with men in Chongqing].

OBJECTIVE: To examine HIV prevalence and its associated factors among men who have sex with men (MSM) and provide the evidence for the intervention program among MSM. METHODS: A face-to-face questionnaire interview was conducted among MSM recruited by snowball sampling method in Yuzhong, Jiulongpo and Shapingba district of Chongqing from July to September, 2007. Totally, 1044 MSM were recruited. Associated factors with HIV prevalence were analyzed using forward stepwise logistic regression that HIV status was the dependent variable and demographics, AIDS awareness, sexual behaviors and the status of the intervention were independent variables. RESULTS: A total of 1044 MSM were surveyed. The rate of AIDS awareness was 89.5% among MSM. The rate of unprotected anal sex during the past 6 months was 63.8%. The prevalence of HIV and syphilis was 8.5% (89/1044) and 12.5% (131/1044) respectively. The multivariate analysis identified that the older MSM (OR = 1.69, 95% CI: 1.13 - 2.52), junior school education (OR = 1.89, 95% CI: 1.17 - 3.05), younger than 18 years old of the first sex (OR = 3.11, 95% CI: 1.20 - 8.02), more than 10 sexual partners (OR = 2.24, 95% CI: 1.24 - 4.02), the history of having sex with women (OR = 2.40, 95% CI: 1.64 - 3.51) and syphilis infection (OR = 4.52, 95% CI: 2.77 - 7.38) were independent risk factors associated with HIV infection. CONCLUSION: The rate of unprotected anal sex was high, so were the prevalence of HIV and syphilis among MSM. It should be urgent to conduct the intervention to stop AIDS rapid transmission among MSM.