Improved MobileNet V3-Based Identification Method for Road Adhesion Coefficient.

To enable the timely adjustment of the control strategy of automobile active safety systems, enhance their capacity to adapt to complex working conditions, and improve driving safety, this paper introduces a new method for predicting road surface state information and recognizing road adhesion coefficients using an enhanced version of the MobileNet V3 model. On one hand, the Squeeze-and-Excitation (SE) is replaced by the Convolutional Block Attention Module (CBAM). It can enhance the extraction of features effectively by considering both spatial and channel dimensions. On the other hand, the cross-entropy loss function is replaced by the Bias Loss function. It can reduce the random prediction problem occurring in the optimization process to improve identification accuracy. Finally, the proposed method is evaluated in an experiment with a four-wheel-drive ROS robot platform. Results indicate that a classification precision of 95.53% is achieved, which is higher than existing road adhesion coefficient identification methods.

Research progress of microRNAs involved in hematopoiesis.

Hematopoiesis plays an important role(s) in maintenance and physiology of life. Hematopoiesis in vertebrates mainly includes self-renewal of the hematopoietic stem cells, proliferation and differentiation of the hematopoietic progenitor cells, and maturation of the blood cells. The regulation of hematogenesis involves a variety of transcription factors, membrane receptors, hematopoietic growth factors, and microRNAs, which interact with each other and form a variety of signaling pathways and signal networks. MicroRNAs are a class of non-coding RNAs widely distributed in eukaryotic cells and play important roles in the hematopoietic process. The expression of microRNAs is regulated by transcription factors involved in hematopoietic signaling pathways. In turn, their expression can inhibit or down-regulate those of transcription factors involved in hematopoietic related signaling pathways and other related regulatory factors, thereby affecting the signaling pathways related to hematopoiesis and ultimately the hematopoietic process. In this review, we introduce the hematopoiesis processes and related signal pathways in vertebrates, focusing on the relationships between microRNAs and hematopoietic transcription factors and signal pathways, and summarizing the recent research progress of microRNAs in hematopoiesis.

Selection of small plasma peptides for the auxiliary diagnosis and prognosis of epithelial ovarian cancer by using UPLC/MS-based nontargeted and targeted analyses.

Epithelial ovarian cancer (EOC) is the leading cause of gynecologic cancer-related death due to its nonspecific characteristics compared to benign cases and poor prognosis after conventional therapies. Small peptides (SPs) demonstrated to have potential for diagnosis and prognosis were focused on in our study for the discovery of biomarkers that address these issues. Metabolic profiles of 15 SPs, including nine dipeptides and six tripeptides were acquired from plasma samples of 140 EOC and 158 benign ovarian tumor (BOT) patients. Partial least square discriminant analysis showed separations between EOC and BOT subjects of different age brackets. Hyp-Leu, Glu-Trp and Phe-Phe were selected as promising predictive SP-biomarkers for better EOC diagnosis compared to conventional biomarkers. Combined Hyp-Leu, Glu-Trp and CA125 presented an area under the curve (AUC) of 0.904, with a sensitivity and specificity of 0.804 and 0.944, respectively. This finding suggested that the combination of these biomarkers performed much better than CA125 alone. Hyp-Leu and Gly-Phe-Trp showed significantly improved performances in the log-rank tests and Kaplan-Meier curves demonstrating their prognostic potential. All SP-biomarkers proved to have excellent stabilities at room temperature. Correlation network analysis implied latent conversions among amino acids, dipeptides and tripeptides during EOC. In conclusion, the selected SPs in combination with CA125 show profound promise for discriminating EOCs from BOTs and for predicting the progression after surgery, which provides invaluable information for clinicians in the precision diagnosis and treatment of EOC.

Voxel- and tensor-based morphometry with machine learning techniques identifying characteristic brain impairment in patients with cervical spondylotic myelopathy.

Aim: The diagnosis of cervical spondylotic myelopathy (CSM) relies on several methods, including x-rays, computed tomography, and magnetic resonance imaging (MRI). Although MRI is the most useful diagnostic tool, strategies to improve the precise and independent diagnosis of CSM using novel MRI imaging techniques are urgently needed. This study aimed to explore potential brain biomarkers to improve the precise diagnosis of CSM through the combination of voxel-based morphometry (VBM) and tensor-based morphometry (TBM) with machine learning techniques. Methods: In this retrospective study, 57 patients with CSM and 57 healthy controls (HCs) were enrolled. The structural changes in the gray matter volume and white matter volume were determined by VBM. Gray and white matter deformations were measured by TBM. The support vector machine (SVM) was used for the classification of CSM patients from HCs based on the structural features of VBM and TBM. Results: CSM patients exhibited characteristic structural abnormalities in the sensorimotor, visual, cognitive, and subcortical regions, as well as in the anterior corona radiata and the corpus callosum [P < 0.05, false discovery rate (FDR) corrected]. A multivariate pattern classification analysis revealed that VBM and TBM could successfully identify CSM patients and HCs [classification accuracy: 81.58%, area under the curve (AUC): 0.85; P < 0.005, Bonferroni corrected] through characteristic gray matter and white matter impairments. Conclusion: CSM may cause widespread and remote impairments in brain structures. This study provided a valuable reference for developing novel diagnostic strategies to identify CSM.

Single-cell transcriptomics enable the characterization of local extension in retinoblastoma.

Retinoblastoma (RB) is the most prevalent ocular tumor of childhood, and its extraocular invasion significantly increases the risk of metastasis. Nevertheless, a single-cell characterization of RB local extension has been lacking. Here, we perform single-cell RNA sequencing on four RB samples (two from intraocular and two from extraocular RB patients), and integrate public datasets of five normal retina samples, four intraocular samples, and three extraocular RB samples to characterize RB local extension at the single-cell level. A total of 128,454 qualified cells are obtained in nine major cell types. Copy number variation inference reveals chromosome 6p amplification in cells derived from extraocular RB samples. In cellular heterogeneity analysis, we identified 10, 8, and 7 cell subpopulations in cone precursor like cells, retinoma like cells, and MKI67+ photoreceptorness decreased (MKI67+ PhrD) cells, respectively. A high expression level of SOX4 was detected in cells from extraocular samples, especially in MKI67+ PhrD cells, which was verified in additional clinical RB samples. These results suggest that SOX4 might drive RB local extension. Our study presents a single-cell transcriptomic landscape of intraocular and extraocular RB samples, improving our understanding of RB local extension at the single-cell resolution and providing potential therapeutic targets for RB patients.

Nanoarchitectonics of Metallene Materials for Electrocatalysis.

Controlling the synthesis of metal nanostructures is one approach for catalyst engineering and performance optimization in electrocatalysis. As an emerging class of unconventional electrocatalysts, two-dimensional (2D) metallene electrocatalysts with ultrathin sheet-like morphology have gained ever-growing attention and exhibited superior performance in electrocatalysis owing to their distinctive properties originating from structural anisotropy, rich surface chemistry, and efficient mass diffusion capability. Many significant advances in synthetic methods and electrocatalytic applications for 2D metallenes have been obtained in recent years. Therefore, an in-depth review summarizing the progress in developing 2D metallenes for electrochemical applications is highly needed. Unlike most reported reviews on the 2D metallenes, this review starts by introducing the preparation of 2D metallenes based on the classification of the metals (e.g., noble metals, and non-noble metals) instead of synthetic methods. Some typical strategies for preparing each kind of metal are enumerated in detail. Then, the utilization of 2D metallenes in electrocatalytic applications, especially in the electrocatalytic conversion reactions, including the hydrogen evolution reaction, oxygen evolution reaction, oxygen reduction reaction, fuel oxidation reaction, CO2 reduction reaction, and N2 reduction reaction, are comprehensively discussed. Finally, current challenges and opportunities for future research on metallenes in electrochemical energy conversion are proposed.

Cost-effectiveness of switching patients with type 2 diabetes from insulin glargine to insulin detemir in Chinese setting: a health economic model based on the PREDICTIVE study.

OBJECTIVES: To evaluate the long-term cost-effectiveness of switching from insulin glargine (IGla) to insulin detemir (IDet) in patients with type 2 diabetes in the setting of Chinese secondary and tertiary hospitals. METHODS: A published and validated computer simulation model of diabetes (the Center for Outcomes Research model) was used to make the long-term (30 years) projection of health economic outcomes. Patient demographic information and clinical end points were derived from a subgroup analysis of the Predictable Results and Experience in Diabetes through Intensification and Control to Target: an International Variability Evaluation (PREDICTIVE) study. Baseline risk factors and racial characteristic data were obtained from Chinese cohort studies. The diabetes management and complications costs were obtained from Chinese published data and adjusted to 2010 values by using the Chinese consumer price index. An annual discounting rate of 3% was used for both health and cost outcomes, and one-way sensitivities analysis was performed, which illustrated that the results were robust. RESULTS: Conversion to IDet from IGla was projected to improve patient life expectancy by 0.06 year and 0.48 quality-adjusted life-years. Drug costs and management costs of diabetes mellitus were increased by US$368 (US$17,466 vs. US$17,097) and US$31 (US$5464 vs. US$5433), respectively. However, the costs of complications, including cerebrovascular disease, renal complications, ulcer/amputation/neuropathy, eye complications, and hypoglycemia events, were reduced by US$819 (US$21,294 vs. US$22,114), resulting in a total direct medical cost saving of US$420 when converting to IDet. CONCLUSIONS: Conversion to IDet from an IGla regimen improved life expectancy and was a cost-saving treatment approach in a Chinese setting.

Biofeedback electrostimulation for bionic and long-lasting neural modulation.

Invasive electrical stimulation (iES) is prone to cause neural stimulus-inertia owing to its excessive accumulation of exogenous charges, thereby resulting in many side effects and even failure of nerve regeneration and functional recovery. Here, a wearable neural iES system is well designed and built for bionic and long-lasting neural modulation. It can automatically yield biomimetic pulsed electrical signals under the driven of respiratory motion. These electrical signals are full of unique physiological synchronization can give biofeedback to respiratory behaviors, self-adjusting with different physiological states of the living body, and thus realizing a dynamic and biological self-matched modulation of voltage-gated calcium channels on the cell membrane. Abundant cellular and animal experimental evidence confirm an effective elimination of neural stimulus-inertia by these bioelectrical signals. An unprecedented nerve regeneration and motor functional reconstruction are achieved in long-segmental peripheral nerve defects, which is equal to the gold standard of nerve repair -- autograft. The wearable neural iES system provides an advanced platform to overcome the common neural stimulus-inertia and gives a broad avenue for personalized iES therapy of nerve injury and neurodegenerative diseases.

Dopamine/zinc oxide doped poly(N-hydroxyethyl acrylamide)/agar dual network hydrogel with super self-healing, antibacterial and tissue adhesion functions designed for transdermal patch.

Dual network (DN) hydrogels with excellent mechanical strength and controllable component adjustment characteristics have a broad application range in the field of biomedicine. However, the tissue adhesion, skin affinity, self-healing, and antibacterial properties of DN hydrogels are inadequate for their application as skin patches. In this work, we prepared dopamine/zinc oxide (DOPA/ZnO) doped poly(N-hydroxyethyl acrylamide) (p(HEAA))/agar DN hydrogels and combined them to obtain a bilayer hydrogel (two-layer gel) with moisturizing properties. Upon incorporating 0.86 wt% of dopamine (DOPA), the resultant DOPA/p(HEAA))/agar DN hydrogel (DOPA@DNG) exhibited high tensile strain (up to 1600%), excellent self-repair ability, and tissue adhesion. ZnO/p(HEAA))/agar DN hydrogel (ZnO NG) obtained by incorporating 2 w/v ZnO nanoparticles (ZnO NPs) achieved high tensile strength (1.2 MPa), good antibacterial ability, and low charge transfer resistance. Moreover, ZnO NG, which has a tight structure, was employed as a protective layer for the two-layer gel, which can effectively slow down the excessive evaporation of water to protect the DOPA@DNG stability as a skin patch. Evidence showed that the two-layer hydrogel has water retention. Water retention still remains at over 50% after keeping the hydrogel in air for 3 days. These properties mean the two-layer gel based on the DOPA/ZnO doped DN hydrogels could be used as a transdermal patch for numerous applications in drug delivery, wearable devices, and electronic skin.

Physiologically Self-Regulated, Fully Implantable, Battery-Free System for Peripheral Nerve Restoration.

The long-segment peripheral nerve injury (PNI) represents a global medical challenge, leading to incomplete nerve tissue recovery and unsatisfactory functional reconstruction. However, the current electrical stimulation (ES) apparatuses fail perfect nerve repair due to their inability of the variable synchronous self-regulated function with physiological states. It is urgent to develop an implantable ES platform with physiologically adaptive function to provide instantaneous and nerve-preferred ES. Here, a physiologically self-regulated electrical signal is generated by integrating a novel tribo/piezoelectric hybrid nanogenerator with a nanoporous nerve guide conduit to construct a fully implantable neural electrical stimulation (FI-NES) system. The optimal neural ES parameters completely originate from the body itself and are highly self-responsive to different physiological states. The morphological evaluation, representative protein expression level, and functional reconstruction of the regenerated nerves are conducted to assess the PNI recovery process. Evidence shows that the recovery effect of 15 mm length nerve defects under the guidance of the FI-NES system is significantly close to the autograft. The designed FI-NES system provides an effective method for long-term accelerating the recovery of PNI in vivo and is also appropriate for other tissue injury or neurodegenerative diseases.

Rapid reduction in plaque inflammation by sonodynamic therapy inpatients with symptomatic femoropopliteal peripheral artery disease:A randomized controlled trial.

BACKGROUND: Inflammation is actively involved in the clinical manifestation of peripheral artery disease (PAD). Sonodynamic therapy (SDT), a novel non-invasive, plaque-based, macrophage-targeted anti-inflammatory regimen for atherosclerosis has the potential to improve walking performance by reducing plaque inflammation. METHODS: This phase-2, randomized, sham-controlled, double-blind clinical trial enrolled 32 participants with symptomatic femoropopliteal PAD. The primary outcome was the 30-day change in the target-to-background ratio (TBR) within the most diseased segment (MDS) of the femoropopliteal artery assessed through positron emission tomography/computed tomography (PET/CT). The secondary outcomes were changes in walking performance, limb perfusion, lesional morphology and quality of life measurements. RESULTS: The mean age was 64.7 years and 63% were male. Thirty-one completed follow-up. SDT significantly decreased the MDS TBR by 0.53 (95% CI, -0.70 to -0.36, P < 0.001) compared with control. Furthermore, SDT increased peak walking time by 118.6 s (95% CI, 74.3 to 163.0, P < 0.001), increased ankle-brachial index by 0.11 (95% CI, 0.07 to 0.14, P < 0.001), decreased lesional diameter and area stenosis by 7.2% (95% CI, -8.6 to -4.5, P < 0.001) and 9.6% (95% CI, -24.5 to -5.3, P = 0.005), respectively, and increased the walking speed score of the Walking Impairment Questionnaire by 16.1 (95% CI, 2.6 to 29.5, P = 0.021) and the physical functioning score of the 36-item Short-Form Health Survey by 10.0 (95% CI, 5.0 to 20.0, P = 0.003) compared with control. These improvements were maintained in the SDT group up to 6-month. CONCLUSIONS: SDT rapidly reduced plaque inflammation and improved walking performance among patients with symptomatic PAD. TRIAL REGISTRATION: Clinical Trials NCT03457662.

Central rather than brachial pressures are stronger predictors of cardiovascular outcomes: A longitudinal prospective study in a Chinese population.

The purpose of this study was to assess the association of blood pressure (BP) measurements with the risk of cardiovascular disease (CVD) and examine whether central systolic BP (CSBP) predicts CVD better than brachial BP measurements (SBP and pulse pressure [PP]). Based on a cross-sectional study conducted in 2009-2010 with follow-up in 2016-2017 among 35- to 64-year-old subjects in China, we evaluated the performance of non-invasively predicted CSBP over brachial BP measurements on the first CVD events. Each BP measurement, individually and jointly with another BP measurement, was entered into the multivariate Cox proportional-hazards models, to examine the predictability of central and brachial BP measurements. Mean age of participants (n = 8710) was 50.1 years at baseline. After a median follow-up of 6.36 years, 187 CVD events occurred. CSBP was a stronger predictor for CVD than brachial BP measurements (CSBP, 1-standard deviation increment HR = 1.49, 95%CI: 1.31-1.70). With CSBP and SBP entering into models jointly, the HR for CSBP and SBP was 1.28 (1.04-1.58) and 1.22 (0.98-1.50), respectively. With CSBP and PP entering into models jointly, the HR for CSBP and PP was 1.51 (1.28-1.78) and 0.98 (0.83-1.15), respectively. For subgroup analysis, the association of CSBP with CVD was stronger than brachial BP measurements in women, those with hypertension and obesity. In the middle-aged Chinese population, noninvasively estimated CSBP may offer advantages over brachial BP measurements to predict CVD events, especially for participants with higher risk. These findings suggest prospective assessment of CSBP as a prevention and treatment target in further trials.

A Prognostic Nomogram for Cervical Cancer after Surgery from SEER Database.

Background: To develop and validate a nomogram based on the conventional measurements and log of odds between the number of positive lymph node and the number of negative lymph node (LODDS) in predicting prognosis for cervical cancer patients after surgery. Methods: A total of 8202 cervical cancer patients with pathologically confirmed between 2004 and 2014 were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. All the patients were divided into training (n=3603) and validation (n=4599) cohorts based on consecutive age of diagnosis. Demographic and clinical pathological factors were evaluated the association with overall survival (OS). Parameters significantly correlating with OS were used to create a nomogram. An independent external validation cohort was subsequently used to assess the predictive performance of the model. Results: In the training set, age at diagnosis, race, marital status, tumor grade, FIGO stage, histology, size and LODDS were correlated significantly with outcome and used to develop a nomogram. The calibration curve for probability of survival showed excellent agreement between prediction by nomogram and actual observation in the training cohort, with a bootstrap-corrected concordance index of 0.749(95% CI, 0.731-0.767). Importantly, our nomogram performed favorably compared to the currently utilized FIGO model, with concordance indices of 0.786 (95% CI, 0.764 to 0.808) vs 0.685 (95%CI, 0.660 to 0.710) for OS in the validation cohort, respectively. Conclusions: By incorporating LODDS, our nomogram may be superior to the currently utilized FIGO staging system in predicting OS in cervical cancer patients after surgery.

Interankle Systolic Blood Pressure Difference Is a Marker of Prevalent Stroke in Chinese Adults: A Cross-Sectional Study.

This cross-sectional study carried out from November 2014 to December 2014 aimed to determine whether the interankle systolic blood pressure (SBP) difference is an independent marker of prevalent stroke. Simultaneous four-limb blood pressure measurements (oscillometric devices) and calculated SBP difference between the lower limbs were collected from 1485 participants aged 35 years and older. Questionnaires about traditional stroke risk factors were completed. Interankle SBP difference ≥7 mm Hg was independently associated with a history of stroke after adjusting for traditional stroke risk factors (odds ratio, 1.64; 95% confidence interval, 1.53-3.59; P=.0123). Net reclassification improvement analysis showed that adding the interankle SBP difference to traditional risk factors improved the predictive ability for stroke risk by 18.5% (P<.001). In conclusion, an interankle SBP difference ≥7 mm Hg could be an independent marker of stroke history in Chinese adults. It could offer an extra benefit in identifying individuals with risk of stroke beyond conventional clinical features.

Plasma lipid profiling and diagnostic biomarkers for oral squamous cell carcinoma.

Biological requirements for tumor cell proliferation include the sustained increase of structural, energetic, signal transduction and biosynthetic precursors. Because lipids participate in membrane construction, energy storage, and cell signaling. We hypothesized that the differences in lipids between malignant carcinoma and normal controls could be reflected in the bio-fluids. A total of 100 pre-operative plasma samples were collected from 50 oral squamous cell carcinoma (OSCC), 50 normal patients and characterize by lipid profiling using ultra performance liquid chromatography/electro spray ionization mass spectrometry (UPLC-MS). The lipid profiles of the OSCC and control samples as well as the different stages were compared. Differentially expressed lipids were categorized as glycerophospholipids and sphingolipids. All glycerophospholipids were decreased, especially phosphatidylcholine and phosphoethanolamine plasmalogens, whereas sphingolipids were increased in the OSCC patients compared to the controls. We further identified 12 staging related lipids, which could be utilized to discriminate early stage patients from advanced stage patients. In the future, the differential lipids may provide biologists with additional information regarding lipid metabolism and guide clinicians in making individualized therapeutic decisions if these results are confirmed in a larger study.

Proteomics analysis to reveal biological pathways and predictive proteins in the survival of high-grade serous ovarian cancer.

High-grade serous ovarian cancer (HGSC) is an aggressive cancer with a worse clinical outcome. Therefore, studies about the prognosis of HGSC may provide therapeutic avenues to improve patient outcomes. Since genome alteration are manifested at the protein level, we integrated protein and mRNA data of ovarian cancer from The Cancer Genome Atlas (TCGA) and Clinical Proteomic Tumor Analysis Consortium (CPTAC) and utilized the sparse overlapping group lasso (SOGL) method, a new mechanism-driven variable selection method, to select dysregulated pathways and crucial proteins related to the survival of HGSC. We found that biosynthesis of amino acids was the main biological pathway with the best predictive performance (AUC = 0.900). A panel of three proteins, namely EIF2B1, PRPS1L1 and MAPK13 were selected as potential predictive proteins and the risk score consisting of these three proteins has predictive performance for overall survival (OS) and progression free survival (PFS), with AUC of 0.976 and 0.932, respectively. Our study provides additional information for further mechanism and therapeutic avenues to improve patient outcomes in clinical practice.

The Association of Four-Limb Blood Pressure with History of Stroke in Chinese Adults: A Cross-Sectional Study.

OBJECTIVE: We investigated the association of ankle-brachial blood pressure index (ABI), interarm blood pressure (BP) difference and interankle BP difference, obtained by simultaneous four-limb BP measurement, with history of stroke in a Chinese adult population. METHODS: This cross-sectional study included 1485 participants aged ≥35 years in the framework of the China Hypertension Survey. We performed simultaneous four-limb BP measurement using oscillometric devices with the participants in the supine position and calculated ABI and interarm/interankle BP differences between the 4 limbs. Logistic regression analysis was used to estimate the association of these BP parameters and other factors with a history of stroke. RESULTS: In univariate analyses, participants with ABI <0.9, interarm BP difference ≥15 mmHg, and interankle BP difference ≥10 mmHg had a higher prevalence of stroke than those without (p < 0.0001, p = 0.0152, p = 0.002, respectively). Multiple logistic regression analyses suggested, ABI <0.9 was independently associated with a history of stroke after adjustment for interarm BP difference ≥15 mmHg, interankle BP difference ≥10 mmHg, and traditional risk factors for stroke (p = 0.001). An interankle BP difference ≥10 mmHg was associated with prior stroke after the two variables of hypertension and ABI were removed from the logistic regression model (p = 0.0142). Net reclassification improvement analysis showed that inclusion of interankle BP difference ≥10 mmHg to the independent risk factors (age, family history of stroke, hypertension, and ABI) improved net reclassification by 11.92%. CONCLUSION: ABI <0.9 is an independent risk factor for stroke prevalence in Chinese adults and it just detected a small propotion of paticipants. The addition of interankle BP difference ≥10 mmHg to the independent risk factors for stroke may improve the prediction of stroke.

A metabolomics approach for predicting the response to neoadjuvant chemotherapy in cervical cancer patients.

Cervical cancer is a clinical and pathological heterogeneity disease, which requires different types of treatments and leads to a variety of outcomes. In clinical practice, only some patients benefit from chemotherapy treatment. Identifying patients who will be responsive to chemotherapy could increase their survival time, which has important implications in personalized treatment and outcomes, while identifying non-responders may reduce the likelihood for these patients to receive ineffective treatment and thereby enable them to receive other potentially effective treatments. Plasma metabolite profiling was performed in this study to identify the potential biomarkers that could predict the response to neoadjuvant chemotherapy (NACT) for cervical cancer patients. The metabolic profiles of plasma from 38 cervical cancer patients with a complete, partial and non-response to NACT were studied using a combination of liquid chromatography coupled with mass spectrometry (LC/MS) and multivariate analysis methods. L-Valine and L-tryptophan were finally identified and verified as the potential biomarkers. A prediction model constructed with L-valine and L-tryptophan correctly identified approximately 80% of patients who were non-response to chemotherapy and 87% of patients who were had a pathologically complete response to chemotherapy. The model has an excellent discriminant performance with an AUC of 0.9407. These results show promise for larger studies that could produce more personalized treatment protocols for cervical cancer patients.

Evaluation of chemotherapy response with serum squamous cell carcinoma antigen level in cervical cancer patients: a prospective cohort study.

MRI does not always reflect tumor response after chemotherapy. Therefore, it is necessary to explore additional parameters to more accurately evaluate tumor response for the subsequent clinical determination about radiotherapy or radical surgery. A training cohort and an external validation cohort were used to examine the predictive performance of SCC-ag to evaluate tumor response from teaching hospital of Harbin Medical University. The study included 397 women with SCC (age: 28-73 years). Patients consecutively enrolled between August 2008 and January 2010 (n = 205) were used as training cohort. Patients consecutively enrolled between February 2010 and May 2011 (n = 192) were used as validation cohort. A multivariate regression analysis of the data from the training cohort indicated that serum SCC-ag level is an independent factor for neo-adjuvant chemotherapy (NACT) response. Analysis of the data from the validation cohort suggested that chemotherapy response could be more accurately predicted by SCC-ag than by magnetic resonance imaging (MRI) (sensitivity (Se): 0.944 vs. 0.794; specificity (Sp): 0.727 vs. 0.636; positive predictive value (PPV): 0.869 vs. 0.806; negative predictive value (NPV): 0.873 vs. 0.618; the area under ROC curve (AUC): 0.898 vs. 0.734). Combining SCC-ag with MRI was more powerful than MRI alone (Se: 0.952 vs. 0.794; Sp: 0.833 vs. 0.636; PPV: 0.916 vs. 0.806; NPV: 0.902 vs. 0.618; AUC: 0.950 vs. 0.734). Our study indicates that serum SCC-ag level is a sensitive and reliable measure to evaluate cervical cancer response to chemotherapy. Using SCC-ag in combination with MRI findings further improves the predictive power.