Predicting microvascular invasion in hepatocellular carcinoma with a CT- and MRI-based multimodal deep learning model

PURPOSE

To investigate the value of a multimodal deep learning (MDL) model based on computed tomography (CT) and magnetic resonance imaging (MRI) for predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC).

METHODS

A total of 287 patients with HCC from our institution and 58 patients from another individual institution were included. Among these, 119 patients with only CT data and 116 patients with only MRI data were selected for single-modality deep learning model development, after which select parameters were migrated for MDL model development with transfer learning (TL). In addition, 110 patients with simultaneous CT and MRI data were divided into a training cohort (n = 66) and a validation cohort (n = 44). We input the features extracted from DenseNet121 into an extreme learning machine (ELM) classifier to construct a classification model.

RESULTS

The area under the curve (AUC) of the MDL model was 0.844, which was superior to that of the single-phase CT (AUC = 0.706-0.776, P < 0.05), single-sequence MRI (AUC = 0.706-0.717, P < 0.05), single-modality DL model (AUCall-phase CT = 0.722, AUCall-sequence MRI = 0.731; P < 0.05), clinical (AUC = 0.648, P < 0.05), but not to that of the delay phase (DP) and in-phase (IP) MRI and portal venous phase (PVP) CT models. The MDL model achieved better performance than models described above (P < 0.05). When combined with clinical features, the AUC of the MDL model increased from 0.844 to 0.871. A nomogram, combining deep learning signatures (DLS) and clinical indicators for MDL models, demonstrated a greater overall net gain than the MDL models (P < 0.05).

CONCLUSION

The MDL model is a valuable noninvasive technique for preoperatively predicting MVI in HCC.

Deep learning vs. robust federal learning for distinguishing adrenal metastases from benign lesions with multi-phase CT images

Background

Differentiating adrenal adenomas from metastases poses a significant challenge, particularly in patients with a history of extra-adrenal malignancy. This study investigates the performance of three-phase computed tomography (CT) based robust federal learning algorithm and traditional deep learning for distinguishing metastases from benign adrenal lesions.

Material and methods

This retrospective analysis includes 1187 instances who underwent three-phase CT scans between January 2008 and March 2021, comprising 720 benign lesions and 467 metastases. Utilizing the three-phase CT images, both a Robust Federal Learning Signature (RFLS) and a traditional Deep Learning Signature (DLS) were constructed using the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression. Their diagnostic capabilities were subsequently validated and compared using metrics such as the Areas Under the Receiver Operating Curve (AUCs), Net Reclassification Improvement (NRI), and Decision Curve Analysis (DCA).

Results

Compared with DLS, the RFLS showed better capability in distinguishing metastases from benign adrenal lesions (average AUC: 0.816 vs.0.798, NRI = 0.126, P < 0.072; 0.889 vs.0.838, NRI = 0.209, P < 0.001; 0.903 vs.0.825, NRI = 0.643, p < 0.001) in the four-testing cohort, respectively. DCA showed that the RFLS added more net benefit than DLS for clinical utility. Moreover, Comparison with state-of-the-art federal learning methods, the results once again confirmed that the RFLS significantly improved the diagnostic performance based on three-phase CT (AUC: AP, 0.727 vs. 0.757 vs. 0.739 vs. 0.796; PCP, 0.781 vs. 0.851 vs. 0.790 vs. 0.882; VP, 0.789 vs. 0.814 vs. 0.779 vs. 0.886).

Conclusion

RFLS was superior to DLS for preoperative distinguishing metastases from benign adrenal lesions with multi-phase CT Images.

Robustly federated learning model for identifying high-risk patients with postoperative gastric cancer recurrence

The prediction of patient disease risk via computed tomography (CT) images and artificial intelligence techniques shows great potential. However, training a robust artificial intelligence model typically requires large-scale data support. In practice, the collection of medical data faces obstacles related to privacy protection. Therefore, the present study aims to establish a robust federated learning model to overcome the data island problem and identify high-risk patients with postoperative gastric cancer recurrence in a multicentre, cross-institution setting, thereby enabling robust treatment with significant value. In the present study, we collect data from four independent medical institutions for experimentation. The robust federated learning model algorithm yields area under the receiver operating characteristic curve (AUC) values of 0.710, 0.798, 0.809, and 0.869 across four data centres. Additionally, the effectiveness of the algorithm is evaluated, and both adaptive and common features are identified through analysis.

Dietary supplementation of proteases on growth performance, nutrient digestibility, blood characteristics and gut microbiota of growing pigs fed sorghum-based diets

Low-tannin sorghum is an excellent energy source in pig diets. However, sorghum contains several anti-nutritional factors that may have negative effects on nutrient digestibility. The impacts of proteases on growth performance, nutrient digestibility, blood parameters, and gut microbiota of growing pigs fed sorghum-based diets were studied in this study. Ninety-six pigs (20.66 ± 0.65 kg BW) were allocated into three groups (eight pens/group, four pigs/pen): (1) CON (control diet, sorghum-based diet included 66.98% sorghum), (2) PRO1 (CON + 200 mg/kg proteases), (3) PRO2 (CON + 400 mg/kg proteases) for 28 d. No differences were observed in growth performance and apparent total tract digestibility (ATTD) of nutrients between CON and PRO1 groups. Pigs fed PRO2 diet had increased (P < 0.05) BW on d 21 and 28, and increased (P < 0.05) average daily gain during d 14-21 and the overall period compared with pigs fed CON diet. In addition, pigs fed PRO2 diet had improved (P < 0.05) ATTD of gross energy, CP, and DM compared with pigs fed CON and PRO1 diets. Pigs fed PRO2 diet had lower (P < 0.05) plasma globulin (GLB) level and higher (P < 0.05) plasma glucose, albumin (ALB) and immunoglobulin G levels, and ALB/GLB ratio than pigs fed CON and PRO1 diets. Furthermore, pigs fed PRO2 diet had decreased (P < 0.05) the relative abundance of Acidobacteriota at the phylum level and increased (P < 0.05) the relative abundance of Prevotella_9 at the genus level. The linear discriminant analysis effect size analysis also showed that pigs fed PRO2 diet had significantly enriched short-chain fatty acid-producing bacteria, such as Subdoligranulum and Parabacteroides. In conclusion, protease supplementation at 400 mg/kg improved the growth performance of growing pigs fed sorghum-based diets, which may be attributed to the improvement of nutrient digestibility, host metabolism, immune status and associated with the altered gut microbiota profiles.

Differentiating adrenal metastases from benign lesions with multiphase CT imaging: Deep learning could play an active role in assisting radiologists

OBJECTIVES

To develop and externally validate multiphase CT-based deep learning (DL) models for differentiating adrenal metastases from benign lesions.

MATERIALS AND METHODS

This retrospective two-center study included 1146 adrenal lesions from 1059 patients who underwent multiphase CT scanning between January 2008 and March 2021. The study encompassed 564 surgically confirmed adenomas, along with 135 benign lesions and 447 metastases confirmed by observation. DL models based on multiphase CT images were developed, validated and tested. The diagnostic performance of the classification models, imaging phases and radiologists with or without DL were compared using accuracy (ACC) and receiver operating characteristic (ROC) curves. Integrated discrimination improvement (IDI) analysis and the DeLong test were used to compare the area under the curve (AUC) among models. Decision curve analysis (DCA) was used to assess the clinical usefulness of the predictive models.

RESULTS

The DL signature based on LASSO (DLSL) had a higher AUC than that of the other classification models (IDI > 0, P < 0.05). Furthermore, the precontrast phase (PCP)-based DLSL performed best in the independent external validation (AUC = 0.881, ACC = 82.9 %) and clinical test cohorts (AUC = 0.790, ACC = 70.4 %), outperforming DLSL based on the other single-phase or three-phase images (IDI > 0, P < 0.05). DCA demonstrated that PCP-based DLSL provided a higher net benefit (0.01-0.95). The diagnostic performance led to statistically significant improvements when radiologists incorporated the DL model, with the AUC improving by 0.056-0.159 and the ACC improving by 0.069-0.178 (P < 0.05).

CONCLUSION

The DL model based on PCP CT images performed acceptably in differentiating adrenal metastases from benign lesions, and it may assist radiologists in accurate tumor staging for patients with a history of extra-adrenal malignancy.

A transfer learning nomogram for predicting prostate cancer and benign conditions on MRI

BACKGROUND

Deep learning has been used to detect or characterize prostate cancer (PCa) on medical images. The present study was designed to develop an integrated transfer learning nomogram (TLN) for the prediction of PCa and benign conditions (BCs) on magnetic resonance imaging (MRI).

METHODS

In this retrospective study, a total of 709 patients with pathologically confirmed PCa and BCs from two institutions were included and divided into training (n = 309), internal validation (n = 200), and external validation (n = 200) cohorts. A transfer learning signature (TLS) that was pretrained with the whole slide images of PCa and fine-tuned on prebiopsy MRI images was constructed. A TLN that integrated the TLS, the Prostate Imaging-Reporting and Data System (PI-RADS) score, and the clinical factor was developed by multivariate logistic regression. The performance of the TLS, clinical model (CM), and TLN were evaluated in the validation cohorts using the receiver operating characteristic (ROC) curve, the Delong test, the integrated discrimination improvement (IDI), and decision curve analysis.

RESULTS

TLS, PI-RADS score, and age were selected for TLN construction. The TLN yielded areas under the curve of 0.9757 (95% CI, 0.9613-0.9902), 0.9255 (95% CI, 0.8873-0.9638), and 0.8766 (95% CI, 0.8267-0.9264) in the training, internal validation, and external validation cohorts, respectively, for the discrimination of PCa and BCs. The TLN outperformed the TLS and the CM in both the internal and external validation cohorts. The decision curve showed that the TLN added more net benefit than the CM.

CONCLUSIONS

The proposed TLN has the potential to be used as a noninvasive tool for PCa and BCs differentiation.

Cauchy non-convex sparse feature selection method for the high-dimensional small-sample problem in motor imagery EEG decoding

Introduction

The time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these temporal-frequency-spatial features are high-dimensional small-sample data, which poses significant challenges for motor imagery decoding. Sparse regularization is an effective method for addressing this issue. However, the most commonly employed sparse regularization models in motor imagery decoding, such as the least absolute shrinkage and selection operator (LASSO), is a biased estimation method and leads to the loss of target feature information.

Methods

In this paper, we propose a non-convex sparse regularization model that employs the Cauchy function. By designing a proximal gradient algorithm, our proposed model achieves closer-to-unbiased estimation than existing sparse models. Therefore, it can learn more accurate, discriminative, and effective feature information. Additionally, the proposed method can perform feature selection and classification simultaneously, without requiring additional classifiers.

Results

We conducted experiments on two publicly available motor imagery EEG datasets. The proposed method achieved an average classification accuracy of 82.98% and 64.45% in subject-dependent and subject-independent decoding assessment methods, respectively.

Conclusion

The experimental results show that the proposed method can significantly improve the performance of motor imagery decoding, with better classification performance than existing feature selection and deep learning methods. Furthermore, the proposed model shows better generalization capability, with parameter consistency over different datasets and robust classification across different training sample sizes. Compared with existing sparse regularization methods, the proposed method converges faster, and with shorter model training time.

Effects of dietary methionine supplementation from different sources on growth performance and meat quality of barrows and gilts

Methionine is indispensable for growth and meat formation in pigs. However, it is still unclear that increasing dietary sulphur-containing amino acid (SAA) levels using different methionine sources affects the growth performance and meat quality of barrows and gilts. To investigate this, 144 pigs (half barrows and half gilts) were fed the control (100% SAA, CON), DL-Methionine (125% SAA, DL-Met)-supplemented, or OH-Methionine (125% SAA, OH-Met)-supplemented diets during the 11-110 kg period. The results showed that plasma methionine levels varied among treatments during the experimental phase, with increased plasma methionine levels observed following increased SAA consumption during the 25-45 kg period. In contrast, pigs fed the DL-Met diet had lower plasma methionine levels than those fed the CON diet (95-110 kg). Additionally, gilts fed the DL-Met or OH-Met diets showed decreased drip loss in longissimus lumborum muscle (LM) compared to CON-fed gilts. OH-Met-fed gilts had higher pH45min values than those fed the CON or DL-Met diets, whereas OH-Met-fed barrows had higher L45min values than those fed the CON or DL-Met diets. Moreover, increased consumption of SAA, regardless of the methionine source, tended to decrease the shear force of the LM in pigs. In conclusion, this study indicates that increasing dietary levels of SAA (+25%) appeared to improve the meat quality of gilts by decreasing drip loss and increasing meat tenderness.

Development and validation of a deep learning radiomics nomogram for preoperatively differentiating thymic epithelial tumor histologic subtypes

OBJECTIVES

Using contrast-enhanced computed tomography (CECT) and deep learning technology to develop a deep learning radiomics nomogram (DLRN) to preoperative predict risk status of patients with thymic epithelial tumors (TETs).

METHODS

Between October 2008 and May 2020, 257 consecutive patients with surgically and pathologically confirmed TETs were enrolled from three medical centers. We extracted deep learning features from all lesions using a transformer-based convolutional neural network and created a deep learning signature (DLS) using selector operator regression and least absolute shrinkage. The predictive capability of a DLRN incorporating clinical characteristics, subjective CT findings and DLS was evaluated by the area under the curve (AUC) of a receiver operating characteristic curve.

RESULTS

To construct a DLS, 25 deep learning features with non-zero coefficients were selected from 116 low-risk TETs (subtypes A, AB, and B1) and 141 high-risk TETs (subtypes B2, B3, and C). The combination of subjective CT features such as infiltration and DLS demonstrated the best performance in differentiating TETs risk status. The AUCs in the training, internal validation, external validation 1 and 2 cohorts were 0.959 (95% confidence interval [CI]: 0.924-0.993), 0.868 (95% CI: 0.765-0.970), 0.846 (95% CI: 0.750-0.942), and 0.846 (95% CI: 0.735-0.957), respectively. The DeLong test and decision in curve analysis revealed that the DLRN was the most predictive and clinically useful model.

CONCLUSIONS

The DLRN comprised of CECT-derived DLS and subjective CT findings showed a high performance in predicting risk status of patients with TETs.

CLINICAL RELEVANCE STATEMENT

Accurate risk status assessment of thymic epithelial tumors (TETs) may aid in determining whether preoperative neoadjuvant treatment is necessary. A deep learning radiomics nomogram incorporating enhancement CT-based deep learning features, clinical characteristics, and subjective CT findings has the potential to predict the histologic subtypes of TETs, which can facilitate decision-making and personalized therapy in clinical practice.

KEY POINTS

• A non-invasive diagnostic method that can predict the pathological risk status may be useful for pretreatment stratification and prognostic evaluation in TET patients. • DLRN demonstrated superior performance in differentiating the risk status of TETs when compared to the deep learning signature, radiomics signature, or clinical model. • The DeLong test and decision in curve analysis revealed that the DLRN was the most predictive and clinically useful in differentiating the risk status of TETs.

Complexity Metrics and Planning Dose-Based Pretreatment Patient-Specific Quality Assurance Prediction: Classification, Gamma Passing Rates, and DVH Deviation

PURPOSE/OBJECTIVE(S)

Patient-specific quality assurance (QA) prediction before treatment is beneficial to the clinical resource allocation and the dosimetric monitoring of the patient plans. The aim of this study is to investigate the potential of complexity metrics of radiotherapy plan and patient planning dose to predict QA result, gamma passing rates and dose-volume indices deviation.

MATERIALS/METHODS

Planning dose from treatment planning system (TPS), reconstructed dose from a vendor provided QA phantom and complexity metrics of the 499 radiotherapy plans of patients in our institution from March 2022 to September 2022 were used for methodology verification. Gamma passing rate (3%/2mm,10% threshold) 90% was regarded as criterion of QA pass or fail. A deep learning model ResNet-50 was modified to 3D dose processing and a multilayer perceptron (MLP) with three layers were adopted to extract features from 3D dose and 1D metrics in two parallel ways, then, the features were concatenate together to predict QA results. The dataset was split into 349 for train, 50 for validation and 100 for testing. Evaluation of predictions was based on absolute value deviation and area under the curves (AUC) of receiver operator characteristic (ROC) curve.

RESULTS

In this dataset, 71% (355/499) plans pass the pretreatment QA test. For QA passing prediction in 100 testing cases, the AUC of ROC could achieve 0.92. For gamma passing rates prediction, a mean absolute error (MAE) of 1.8% could be observed for cases with gamma passing rates bigger than 90%, and a MAE of 4.5% deviation could be observed for cases with gamma passing rates from 80% to 90%. For PTV ΔD95 (%) and PTV ΔHI (%), the MAE of prediction and ground truth is 1%. The model with only complexity metrics and only 3D dose could achieve the AUC of ROC 0.91 and 0.84, respectively.

CONCLUSION

The complexity metrics and 3D planning dose-based model could predict pretreatment patient specific QA results with high accuracy and the complexity metrics play a leading role in the model. Dose-volume metrics deviations of PTV could be predicted and more clinically useful information could be provided.

A deep-learning model using enhanced chest CT images to predict PD-L1 expression in non-small-cell lung cancer patients

AIM

To develop a deep-learning model using contrast-enhanced chest computed tomography (CT) images to predict programmed death-ligand 1 (PD-L1) expression in patients with non-small-cell lung cancer (NSCLC).

MATERIALS AND METHODS

Preoperative enhanced chest CT images and immunohistochemistry results for PD-L1 expression (<1% and ≥1% were defined as negative and positive, respectively) were collected retrospectively from 125 NSCLC patients to train and validate a deep-learning radiomics model (DLRM) for the prediction of PD-L1 expression in tumours. The DLRM was developed by combining the deep-learning signature (DLS) obtained from a convolutional neural network and clinicopathological factors. The indexes of the area under the curve (AUC), integrated discrimination improvement (IDI), and decision curve analysis (DCA) were used to evaluate the efficiency of the DLRM.

RESULTS

DLS and tumour stage were identified as independent predictors of PD-L1 expression by the DLRM. The AUCs of the DLRM were 0.804 (95% confidence interval: 0.697-0.911) and 0.804 (95% confidence interval: 0.679-0.929) in the training and validation cohorts, respectively. IDI analysis showed the DLRM had better diagnostic accuracy than DLS (0.0028 [p<0.05]) in the validation cohort. Additionally, DCA revealed that the DLRM had more net benefit than the DLS for clinical utility.

CONCLUSION

The proposed DLRM using enhanced chest CT images could function as a non-invasive diagnostic tool to differentiate PD-L1 expression in NSCLC patients.

Feasibility of Using Pseudo-CT for Dosimetry, Radiomics, and Efficacy Assessment in IMRT/VMAT of Brain Tumors: A Multi-Omics Analysis

PURPOSE/OBJECTIVE(S)

Pseudo-CT generated by convolutional neural networks (CNN) and planning MRI has facilitated the promotion of MRI-Only. The technology not only reduces the time and money spent on CT scans, but also eliminates the cumbersome CT-MR registration. The feasibility in Stereotactic Brain Radiotherapy has been analyzed in previous studies by our team. However, when the prescribed requirements are not met, IMRT/VMAT are still selected. The study aims to evaluate the feasibility of pseudo-CT in IMRT/VMAT for brain cancer via the following 5 aspects: (1) image difference, (2) dose accuracy, (3) radiomics feature, (4) efficacy assessment, and (5) correlation analysis.

MATERIALS/METHODS

Brain tumor patients who had received radiotherapy at our institution and had planning MRI and CT were included in the study. Redesign of IMRT and VMAT radiotherapy plans according to 3 × 15Gy for each patient. Hounsfield unit (HU) values for PTV and OARs were used to assess image differences. And dose accuracy analysis contained a 2D dose volume histogram (DVH) metrics (Dmax, Dmean, D2%, D50%, D98%, HI, CI) and 3D gamma metrics (criteria: 1-3%/2mm, 1%/1mm, 10% threshold). Then 107 original image features of PTV and OARs were extracted for radiometry analysis. And tumor control probability (TCP) of PTV (Poisson model) and normal tissue complication probability (NTCP) of OARs (Lyman-Kutcher-Burman model) were used for the variance analysis of efficacy assessment. Wilcox-test was used for significance of differences test (0.05), and spearman correlation analysis was used to explore the key features of the dose bias.

RESULTS

A total of 42 patients were included, with 42 planning CTs and pseudo-CTs (mDixon-T1), and 38 pseudo-CTs (mDixon-T1-CE). The median volume of PTV was 4.1 cc (range 0.5-27.3), with no significant differences in HU, DVH, 3D gamma, and NTCP/TCP metrics. The median local gamma passing rates (1%/1mm) between planning CTs and pseudo-CTs (mDixon-T1) were 93.1% (range 65.5%-99.7%, IMRT) and 93.3% (range 63.9%-99.6%, VMAT). And more than 85% original radiomics features have significant difference. Further, the feature HU-Min was found to be more correlated with dose metrics in the correlation analysis. We speculate that it may be caused by the smoothing of the low frequency signal before outputting image. And since Shape_MeshVolume, Shape_VoxelVolume and PTV volume difference are highly correlated with dose deviation, it indicates that dose deviation affected by CT-MR registration.

CONCLUSION

This study has the potential to provide guidance for the clinical application of pseudo-CT in the MRI-Only workflow with IMRT/VMAT for brain tumors. These quantitative results strongly indicate pseudo-CT can be used as a substitute for the initial CT in IMRT/VMAT for small brain lesions (size <5 cm, numbers <5), but not for radiomics analysis. Additionally, the impact of inter-image differences on dose accuracy is less significant compared to the deviation caused by image registration.

A 2-Stage Root Analog Implant with Compact Structure, Uniform Roughness, and High Accuracy

Immediate implant placement has the advantages of shortening the operation time, reducing the treatment cycle and cost. At present, this technology has been used widely, but the indications of immediate implantation are still limited. Here, a novel type of root analog implant (RAI) was manufactured by selective laser melting technology to address the limitation. Under optimized condition, RAIs were printed with the internal density of 99.73% and the uniform surface roughness of 11 μm (Sa). Besides, the deviation between RAI specimen and design models is controlled within 0.15 mm after optimizing scanning parameters. The substrate printed could promote human bone marrow stromal cell proliferation, spreading, and osteogenic differentiation. The bone-implant contact (BIC, 75% ± 7%) and bone volume/total volume (BV/TV, 74% ± 7%) of RAIs were significantly higher than that of conventional implants (BIC, 66% ± 5%; BV/TV, 62% ± 5%) in in vivo experiments. Further, customized abutments were designed for the RAIs, improving the masticatory ability of the beagle dogs after crown restoration. This study aims to design a personalized 2-stage RAI with compact structure and uniform roughness, in order to achieve better fracture resistance, initial osseointegration efficiency, and dispersed stress in immediate implantation. It provides a certain guiding value for standardizing the manufacture and clinical application of RAI in immediate implantation.

Identifying Solitary Granulomatous Nodules from Solid Lung Adenocarcinoma: Exploring Robust Image Features with Cross-Domain Transfer Learning

PURPOSE

This study aimed to find suitable source domain data in cross-domain transfer learning to extract robust image features. Then, a model was built to preoperatively distinguish lung granulomatous nodules (LGNs) from lung adenocarcinoma (LAC) in solitary pulmonary solid nodules (SPSNs).

METHODS

Data from 841 patients with SPSNs from five centres were collected retrospectively. First, adaptive cross-domain transfer learning was used to construct transfer learning signatures (TLS) under different source domain data and conduct a comparative analysis. The Wasserstein distance was used to assess the similarity between the source domain and target domain data in cross-domain transfer learning. Second, a cross-domain transfer learning radiomics model (TLRM) combining the best performing TLS, clinical factors and subjective CT findings was constructed. Finally, the performance of the model was validated through multicentre validation cohorts.

RESULTS

Relative to other source domain data, TLS based on lung whole slide images as source domain data (TLS-LW) had the best performance in all validation cohorts (AUC range: 0.8228-0.8984). Meanwhile, the Wasserstein distance of TLS-LW was 1.7108, which was minimal. Finally, TLS-LW, age, spiculated sign and lobulated shape were used to build the TLRM. In all validation cohorts, The AUC ranges were 0.9074-0.9442. Compared with other models, decision curve analysis and integrated discrimination improvement showed that TLRM had better performance.

CONCLUSIONS

The TLRM could assist physicians in preoperatively differentiating LGN from LAC in SPSNs. Furthermore, compared with other images, cross-domain transfer learning can extract robust image features when using lung whole slide images as source domain data and has a better effect.

Distinguishing common renal cell carcinomas from benign renal tumors based on machine learning: comparing various CT imaging phases, slices, tumor sizes, and ROI segmentation strategies

OBJECTIVES

To determine whether a CT-based machine learning (ML) can differentiate benign renal tumors from renal cell carcinomas (RCCs) and improve radiologists' diagnostic performance, and evaluate the impact of variable CT imaging phases, slices, tumor sizes, and region of interest (ROI) segmentation strategies.

METHODS

Patients with pathologically proven RCCs and benign renal tumors from our institution between 2008 and 2020 were included as the training dataset for ML model development and internal validation (including 418 RCCs and 78 benign tumors), and patients from two independent institutions and a public database (TCIA) were included as the external dataset for individual testing (including 262 RCCs and 47 benign tumors). Features were extracted from three-phase CT images. CatBoost was used for feature selection and ML model establishment. The area under the receiver operating characteristic curve (AUC) was used to assess the performance of the ML model.

RESULTS

The ML model based on 3D images performed better than that based on 2D images, with the highest AUC of 0.81 and accuracy (ACC) of 0.86. All three radiologists achieved better performance by referring to the classifier's decision, with accuracies increasing from 0.82 to 0.87, 0.82 to 0.88, and 0.76 to 0.87. The ML model achieved higher negative predictive values (NPV, 0.82-0.99), and the radiologists achieved higher positive predictive values (PPV, 0.91-0.95).

CONCLUSIONS

A ML classifier based on whole-tumor three-phase CT images can be a useful and promising tool for differentiating RCCs from benign renal tumors. The ML model also perfectly complements radiologist interpretations.

KEY POINTS

• A machine learning classifier based on CT images could be a reliable way to differentiate RCCs from benign renal tumors. • The machine learning model perfectly complemented the radiologists' interpretations. • Subtle variances in ROI delineation had little effect on the performance of the ML classifier.

Predicting lymphovascular invasion in clinically node-negative breast cancer detected by abbreviated magnetic resonance imaging: Transfer learning vs. radiomics

Objective

To compare the performance of abbreviated breast magnetic resonance imaging (AB-MRI)-based transfer learning (TL) algorithm and radionics analysis for lymphovascular invasion (LVI) prediction in patients with clinically node-negative invasive breast cancer (IBC).

Methods

Between November 2017 and October 2020, 233 clinically node-negative IBCs detected by AB-MRI were retrospectively enrolled. One hundred thirty IBCs from center 1 (37 LVI-positive and 93 LVI-negative) were assigned as the training cohort and 103 from center 2 (25 LVI-positive and 78 LVI-negative) as the validation cohort. Based on AB-MRI, a TL signature (TLS) and a radiomics signature (RS) were built with the least absolute shrinkage and selection operator (LASSO) logistic regression. Their diagnostic performances were validated and compared using areas under the receiver operating curve (AUCs), net reclassification improvement (NRI), integrated discrimination improvement (IDI), decision curve analysis (DCA), and stratification analysis. A convolutional filter visualization technique was used to map the response areas of LVI on the AB-MRI.

Results

In the validation cohort, compared with RS, the TLS showed better capability in discriminating LVI-positive from LVI-negative lesions (AUC: 0.852 vs. 0.726, p < 0.001; IDI = 0.092, p < 0.001; NRI = 0.554, p < 0.001). The diagnostic performance of TLS was not affected by the menstrual state, molecular subtype, or contrast agent type (all p > 0.05). Moreover, DCA showed that the TLS added more net benefit than RS for clinical utility.

Conclusions

An AB-MRI-based TLS was superior to RS for preoperative LVI prediction in patients with clinically node-negative IBC.

[Medial border of D3 lymphadenectomy for right colon cancer]

The extent of D3 lymphadenectomy for right colon cancer, especially the medial border of central lymph node dissection remains controversial. D3 lymphadenectomy and complete mesocolon excision (CME) are two standard procedures for locally advanced right colon carcinoma. D3 lymphadenectomy determines the medial border according to the distribution of the lymph nodes. The mainstream medial border should be the left side of superior mesenteric vein (SMV) according to the definition of D3, but there are also some reports that regards the left side of superior mesenteric artery (SMA) as the medial border. In contrast, the CME procedure emphasizes the beginning of the colonic mesentery and the left side of SMA should be considered as the medial border. Combined with the anatomical basis, oncological efficacy and technical feasibility of D3 lymph node dissection, we think that it is safe and feasible to take the left side of SMA as the medial boundary of D3 lymph node dissection. This procedure not only takes into account the integrity of mesangial and regional lymph node dissection, but also dissects more distant lymph nodes at risk of metastasis. It has its anatomical basis and potential oncological advantages. However, at present, this technical concept is still in the exploratory stage in practice, and the related clinical evidence is not sufficient.

A Transfer Learning Radiomics Nomogram for Preoperative Prediction of Borrmann Type IV Gastric Cancer From Primary Gastric Lymphoma

Objective

This study aims to differentiate preoperative Borrmann type IV gastric cancer (GC) from primary gastric lymphoma (PGL) by transfer learning radiomics nomogram (TLRN) with whole slide images of GC as source domain data.

Materials and Methods

This study retrospectively enrolled 438 patients with histopathologic diagnoses of Borrmann type IV GC and PGL. They received CT examinations from three hospitals. Quantitative transfer learning features were extracted by the proposed transfer learning radiopathomic network and used to construct transfer learning radiomics signatures (TLRS). A TLRN, which integrates TLRS, clinical factors, and CT subjective findings, was developed by multivariate logistic regression. The diagnostic TLRN performance was assessed by clinical usefulness in the independent validation set.

Results

The TLRN was built by TLRS and a high enhanced serosa sign, which showed good agreement by the calibration curve. The TLRN performance was superior to the clinical model and TLRS. Its areas under the curve (AUC) were 0.958 (95% confidence interval [CI], 0.883–0.991), 0.867 (95% CI, 0.794–0.922), and 0.921 (95% CI, 0.860–0.960) in the internal and two external validation cohorts, respectively. Decision curve analysis (DCA) showed that the TLRN was better than any other model. TLRN has potential generalization ability, as shown in the stratification analysis.

Conclusions

The proposed TLRN based on gastric WSIs may help preoperatively differentiate PGL from Borrmann type IV GC.

Borrmann type IV gastric cancer, primary gastric lymphoma, transfer learning, whole slide image, deep learning.

Toward Elucidating the Physiological Impacts of Residual Stresses in the Colorectum

Irritable bowel syndrome afflicts 10-20% of the global population, causing visceral pain with increased sensitivity to colorectal distension and normal bowel movements. Understanding and predicting these biomechanics will further advance our understanding of visceral pain and complement the existing literature on visceral neurophysiology. We recently performed a series of experiments at three longitudinal segments (colonic, intermediate, and rectal) of the distal 30 mm of colorectums of mice. We also established and fitted constitutive models addressing mechanical heterogeneity in both the through-thickness and longitudinal directions of the colorectum. Afferent nerve endings, strategically located within the submucosa, are likely nociceptors that detect concentrations of mechanical stresses to evoke the perception of pain from the viscera. In this study, we aim to: (1) establish and validate a method for incorporating residual stresses into models of colorectums, (2) predict the effects of residual stresses on the intratissue mechanics within the colorectum, and (3) establish intratissue distributions of stretches and stresses within the colorectum in vivo. To these ends we developed two-layered, composite finite element models of the colorectum based on our experimental evidence and validated our approaches against independent experimental data. We included layer- and segment-specific residual stretches/stresses in our simulations via the prestrain algorithm built into the finite element software febio. Our models and modeling approaches allow researchers to predict both organ and intratissue biomechanics of the colorectum and may facilitate better understanding of the underlying mechanical mechanisms of visceral pain.

Deep learning nomogram for predicting lymph node metastasis using computed tomography image in cervical cancer

BACKGROUND

Deep learning (DL) has been used on medical images to grade, differentiate, and predict prognosis in many tumors.

PURPOSE

To explore the effect of computed tomography (CT)-based deep learning nomogram (DLN) for predicting cervical cancer lymph node metastasis (LNM) before surgery.

MATERIAL AND METHODS

In total, 418 patients with stage IB-IIB cervical cancer were retrospectively enrolled for model exploration (n = 296) and internal validation (n = 122); 62 patients from another independent institution were enrolled for external validation. A convolutional neural network (CNN) was used for DL features extracting from all lesions. The least absolute shrinkage and selection operator (Lasso) logistic regression was used to develop a deep learning signature (DLS). A DLN incorporating the DLS and clinical risk factors was proposed to predict LNM individually. The performance of the DLN was evaluated on internal and external validation cohorts.

RESULTS

Stage, CT-reported pelvic lymph node status, and DLS were found to be independent predictors and could be used to construct the DLN. The combination showed a better performance than the clinical model and DLS. The proposed DLN had an area under the curve (AUC) of 0.925 in the training cohort, 0.771 in the internal validation cohort, and 0.790 in the external validation cohort. Decision curve analysis and stratification analysis suggested that the DLN has potential ability to generate a personalized probability of LNM in cervical cancer.

CONCLUSION

The proposed CT-based DLN could be used as a personalized non-invasive tool for preoperative prediction of LNM in cervical cancer, which could facilitate the choice of clinical treatment methods.

A CT-based deep learning model for subsolid pulmonary nodules to distinguish minimally invasive adenocarcinoma and invasive adenocarcinoma

OBJECTIVE

To develop and validate a deep learning nomogram (DLN) model constructed from non-contrast computed tomography (CT) images for discriminating minimally invasive adenocarcinoma (MIA) from invasive adenocarcinoma (IAC) in patients with subsolid pulmonary nodules (SSPNs).

MATERIALS AND METHODS

In total, 365 consecutive patients who presented with SSPNs and were pathologically diagnosed with MIA or IAC after surgery, were recruited from two medical institutions from 2016 to 2019. Deep learning features were selected from preoperative CT images using convolutional neural network. Deep learning signature (DLS) was developed via the least absolute shrinkage and selection operator (LASSO). New DLN integrating clinical variables, subjective CT findings, and DLS was constructed. The diagnostic efficiency and discriminative capability were analyzed using the receiver operating characteristic method and decision curve analysis (DCA).

RESULTS

In total, 18 deep learning features with non-zero coefficients were enrolled to develop the DLS, which was statistically different between the MIA and IAC groups. Independent predictors of DLS and lobulated sharp were used to build the DLN. The areas under the curves of the DLN were 0.889 (95% confidence interval (CI): 0.824-0.936), 0.915 (95% CI: 0.846-0.959), and 0.914 (95% CI: 0.848-0.958) in the training, internal validation, and external validation cohorts, respectively. After stratification analysis and DCA, the DLN showed potential generalization ability.

CONCLUSION

The DLN incorporating the DLS and subjective CT findings have strong potential to distinguish MIA from IAC in patients with SSPNs, and will facilitate the suitable treatment method selection for the management of SSPNs.

Computed Tomography-Based Radiomics Nomogram: Potential to Predict Local Recurrence of Gastric Cancer After Radical Resection

Objective

Accurate prediction of postoperative recurrence risk of gastric cancer (GC) is critical for individualized precision therapy. We aimed to investigate whether a computed tomography (CT)-based radiomics nomogram can be used as a tool for predicting the local recurrence (LR) of GC after radical resection.

Materials and Methods

342 patients (194 in the training cohort, 78 in the internal validation cohort, and 70 in the external validation cohort) with pathologically proven GC from two centers were included. Radiomics features were extracted from the preoperative CT imaging. The clinical model, radiomics signature, and radiomics nomogram, which incorporated the radiomics signature and independent clinical risk factors, were developed and verified. Furthermore, the performance of these three models was assessed by using the area under the curve (AUC) of receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA).

Results

The radiomics signature, which was comprised of two selected radiomics features, namely, contrast_GLCM and dissimilarity_GLCM, showed better performance than the clinical model in predicting the LR of GC, with AUC values of 0.83 in the training cohort, 0.84 in the internal validation cohort, and 0.73 in the external cohort, respectively. By integrating the independent clinical risk factors (N stage, bile acid duodenogastric reflux and nodular or irregular outer layer of the gastric wall) into the radiomics signature, the radiomics nomogram achieved the highest accuracy in predicting LR, with AUC values of 0.89, 0.89 and 0.80 in the three cohorts, respectively. DCA in the validation cohort showed that radiomics nomogram added more net benefit than the clinical model within the range of 0.01-0.98.

Conclusion

The CT-based radiomics nomogram has the potential to predict the LR of GC after radical resection.

A mechanical, electrical dual autonomous self-healing multifunctional composite hydrogel

The versatile properties make hydrogels a potential multipurpose material that finds wide applications. However, the preparation of multipurpose hydrogels is very challenging. Here, we report a method based on free radical reaction and composite mechanisms to prepare mechanical and electrical self-healing multifunctional hydrogels. In this study, the introduction of imidazolium salt ionic liquids and glycerol in the hydrogel system endows the gels with good antibacterial, conductive, and adhesive properties and excellent antifreeze properties. The testing results show that the as-prepared hydrogel has stable mechanical and electrical properties even under the extremely cold condition of -50°C after self-healing. Moreover, the active esters formed in the dynamic radical reaction have better reducibility, thus further investing the as-prepared hydrogel with high antioxidant activity. The application results show that these comprehensive properties make such hydrogel system very useful in wound repair and wearable strain sensors.

Current practices of Western Australian general dentists regarding management of patients on anticoagulant/antiplatelet therapy

PURPOSE

Currently, there are little to no published studies outlining general dentists' knowledge in the management of patients on anticoagulant/antiplatelet therapies in Australia. The aim of this study was to investigate the current practices of Western Australian (WA) general dentists with regards to dental management of patients taking anticoagulants/antiplatelets.

MATERIALS AND METHODS

WA dentists were invited to undertake a survey to investigate their knowledge on the management of patients taking anticoagulant/antiplatelet. The questionnaire provided to WA general dentists consisted of pre-extraction advice on patients (direct oral anticoagulants [DOACs], antiplatelets, warfarin, dual antiplatelets and antiplatelet/anticoagulant). Results were analysed using descriptive statistics as well as chi-square tests.

RESULTS

Of the 89 participants, 40.5% had <5 years of general dental experience. Most WA general dentists (64%-71%) responded with 'no change' when performing extractions on patients on DOACs, antiplatelet therapy, warfarin, dual antiplatelets and antiplatelets/anticoagulants (P = 0.00). Furthermore, dentists with 6-10 years of experience were more likely to cease antiplatelet for 24 h before extractions (P < 0.05). Dentists who extracted 10-30 teeth per month were likely to stop antiplatelets and DOACs for more than 48 h compared to other groups (P < 0.05).

CONCLUSION

Most WA dentists would not cease anticoagulant/antiplatelet therapy when undergoing dental extractions.

Identification of Thioflavin T Binding Modes to DNA: A Structure-Specific Molecular Probe for Lasing Applications

The binding mechanism of thioflavin T (ThT) to DNA was studied using polarized light spectroscopy and fluorescence-based techniques in solutions and in solid films. Linear dichroism measurements showed that ThT binds to DNA duplex by intercalation. Time-resolved fluorescence studies revealed a second binding mode which is the external binding to the DNA phosphate groups. Both binding modes represent the nonspecific type of interactions. The studies were complemented with the analysis of short oligonucleotides having DNA cavities. The results indicate that the interplay between three binding modes-intercalation, external binding, and binding inside DNA cavities-determines the effective fluorescence quantum yield of the dye in the DNA structures. External binding was found to be responsible for fluorescence quenching because of energy transfer between intercalated and externally bound molecules. Finally, amplified spontaneous emission (ASE) was successfully generated in the ThT-stained films and used for detecting different DNA structures. ASE measurements show that ThT-stained DNA structures can be used for designing bioderived microlasers.

POS0262 IDENTIFYING EROSIVE DISEASE FROM RADIOLOGY REPORTS OF VETERANS WITH INFLAMMATORY ARTHRITIS USING NATURAL LANGUAGE PROCESSING

Background:

The presence of erosive disease influences diagnosis, management, and prognosis in inflammatory arthritis (IA).Research of IA in large datasets is limited by a lack of methods for identifying erosions.

Objectives:

To develop methods for identifying articular erosions in radiology reports from veterans with IA.

Methods:

Included veterans had ≥2 ICD codes for ankylosing spondylitis (AS), psoriatic arthritis (PsA), or rheumatoid arthritis (RA) between 2005- 2019, in Veterans Affairs Corporate Data Warehouse. Chart review & annotation of radiology notes produced the reference standard, & identified erosion terms that informed classification rule development. A rule-based natural language processing (NLP) model was created & revised in training snippets. The NLP method was validated in an independent reference sample of IA patients at the snippet & patient levels

StepDescriptionNumber & example1 Radiology notesa.Select note titles potentially relevant to IAa. 35,141 notes titlesb.Extract notes with titles potentially related to IAb. 2,926,113 radiology notes2 Possible meaningful termsa.Compile list of root terms that may indicate erosiona. 11 root terms (i.e. ero*, pencil*cup, irreg*)b.Query radiology notes for root term variationsb. 1178 variations (i.e. erosion, erotic, erode)c.Select possible meaningful termsc. 179 possible terms (i.e. erosion, erode)3 Annotationa.Extract snippets^ containing possible meaningful termsa.5000 snippets from radiology notesb.Classify snippets according to: 1) Meaningful term, 2) Relevance to joint, 3) Attribution to IA, 4) Affirmationb.4068 classifications with 1017 snippets (in rounds of 50-417 snippets for NLP training & testing)4 Rule developmenta.Identify meaningful terms representing erosiona. 6 terms (pencil * cup, erosion, erosive, etc.)b.Exclude erosive processes irrelevant to joint(s)b. 28 irrelevant processes (i.e. gastric erosion)c. Exclude articular erosive processes not attributed to IAc. 5 non-IA processes IA (i.e. infection)d. Classify as affirmed/negated (erosion present/absent)d. 83 affirmation/negation rules5 NLP trainingDesign & revise NLP model until accuracy ≥90%6 rounds, 817 snippets (AS 417, RA 200, PsA 200)6 NLP testingTest NLP model200 snippets (AS 100, RA 50, PsA 50)7 Pt classificationa. Develop rules for classifying pts with discordant snippetsa. 5 rules developed in 368 ptsb. Build reference sample (pts classified as erosive or non-erosive via chart review)b. 30 IA pts (10 AS, 10 RA, 10 PsA)8 NLP validationValidate NLP model in reference sample at snippet level149 snippets (29 AS, 76 RA, 44 PsA)9 Method validationValidate methods (NLP+pt classification) at pt level30 IA pts (reference sample)

pt= patient. ^Snippets include text containing 30 words before & after meaningful terms

Results:

In 168,667 veterans with IA, the mean age was 63.1 & 90.3% were male. Method development involved radiology note & erosion term selection, rule development, NLP model building, & method validation. The NLP model accuracy was 94.6% at the snippet level & 90.0% at the patient level, for all IA patients.

Accuracy of methods.

Conclusion:

The methods accurately identify erosions from radiology reports of veterans with IA. They may facilitate a broad range of research involving cohort identification & disease severity stratification

References:

[1]Walsh JA, et al. J Rheumatol. 2020;47(1):42-49

Disclosure of Interests:

Gopi Penmetsa: None declared, Shaobo Pei: None declared, Brian Sauer Grant/research support from: I have been an investigator on research contracts supported by Abbvie., Jessica A. Walsh Consultant of: AbbVie, Amgen, Janssen, Lilly, Novartis, Pfizer, UCB, Grant/research support from: AbbVie, Merck, Pfizer, Bingjian Feng Grant/research support from: Bing-Jian Feng reports funding and sponsorship to his institution on his behalf from Pfizer Inc., Regeneron Genetics Center LLC, and Astra Zeneca (UK). The PERCH software, for which Bing-Jian Feng is the inventor, has been non-exclusively licensed to Ambry Genetics for clinical genetic testing services and research., Jodi Walker Shareholder of: Abbvie and mutual funds containing various pharmaceutical companies, Employee of: Abbvie, Kevin Douglas Shareholder of: employed by Abbvie, Employee of: employed by Abbvie, Jerry Clewell Shareholder of: Own Abbvie Shares and mutual funds that hold pharmaceutical and other health care stocks, Employee of: I am current Abbvie Inc employee and past employee of Eli Lilly co

[Value of gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid enhanced magnetic resonance imaging and diffusion-weighted MR imaging in predicting microvascular invasion in hepatocellular carcinoma and the prognostic significance]

Objective: To investigate the combined value of gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA) enhanced magnetic resonance imaging (MRI) and diffusion-weighted imaging (DWI) in predicting pathological microvascular invasion (pMVI) preoperatively, and to determine the relationship between prediction results and prognosis in hepatocellular carcinoma (HCC) patients. Methods: A total of 181 newly diagnosed HCC patients were enrolled in this study. Imaging characteristics and the apparent diffusion coefficient (ADC) value of DWI were analyzed. The differences of imaging characteristics and ADC values between different pMVI groups were analyzed.Multivariate logistic regression and receiver operating characteristic (ROC) curve were used to analyze the value for pMVI prediction by using significant parameters. The patients were grouped based on MRI predicted MVI (mrMVI), and the relationship between mrMVI and recurrence free survival time (RFS) was analyzed. Results: Fifty-one patients were pMVI positive and 130 patients were pMVI negative. The ADC value in pMVI positive group were (1.10±0.17)×10(-3) mm(2)/s, significantly lower than (1.27±0.22)×10(-3) mm(2)/s of pEMVI negative group (P<0.001). The incidence rates of incomplete enhancing "capsule" , non-smooth tumor margin, arterial peritumoral enhancement, mosaic architecture and peritumoral hypointensity on hepatobiliary phase (HBP) in pMVI positive group were significantly higher than those of negative group (all P<0.05). Multivariate logistic regression analysis showed that tumor margin, arterial peritumoral enhancement, peritumoral hypointensity on HBP and ADC value were independently associated with pMVI. ROC analysis showed that the area under curve, sensitivity and specificity of pMVI predicted by combined parameters were 0.830, 76.5% and 81.5%, respectively. The median RFS of mrMVI positive group was 23.6 months, significantly lower than 38.2 months of mrEMVI negative group (P=0.004). Conclusion: Tumor margin, arterial peritumoral enhancement, peritumoral hypointensity on HBP and ADC value are independent predictors of pMVI in HCC, and mrMVI is related with RFS.

[An investigation of musculoskeletal disorders at multiple sites and related influencing factors among workers in an automobile assembly shop]

Objective: To investigate the current status of work-related musculoskeletal disorders (WMSDs) in automobile assembly workers, as well as the distribution of WMSDs at multiple sites and related influencing factors. Methods: From March to July 2019, cluster sampling was performed to select 663 male automobile assembly workers as respondents, and the musculoskeletal injury questionnaire was used to investigate their general status and working condition. A multinomial logistic regression analysis was used to analyze the influencing factors for WMSDs at multiple sites. Results: The detection rate of WMSDs within the past 7 days was 37.9% (251/663) among the automobile assembly workers, and the detection rate of WMSDs within the past 1 year was 51.9% (344/663) . Of all workers, 13.6% (90/663) had WMSDs involving only 1 site, while 38.3% (254/663) had WMSDs involving 2 or more sites. The multinomial logistic regression analysis showed that frequent turns during work was a risk factor for WMSDs involving 1-3, 4-6, and 7-9 sites (odds ratio [OR]=1.65, 2.47, and 3.65, respectively) . Repeated action of lower extremities and ankles was a risk factor for WMSDs involving 4-6 and 7-9 sites (OR=2.15 and 2.98, respectively) . Working in an uncomfortable position was a risk factor for WMSDs involving 1-3, 4-6, and 7-9 sites (OR=1.95, 2.67, and 3.04, respectively) . Prolonged standing during work was a risk factor for WMSDs involving 1-3 and 4-6 sites (OR= 1.87 and 1.79, respectively) . Working overtime was a risk factor for WMSDs involving 7-9 sites (OR=5.48) . Adequate time for rest was a protective factor against WMSDs involving 1-3 and 4-6 sites (OR=0.50 and 0.31, respectively) . Conclusion: There is a high detection rate of WMSDs in automobile assembly workers, and WMSDs at multiple sites are more common than WMSDs at a single site. Poor position and organizational management factors are risk factors for occupational WMSDs at multiple sites.

Computational Modeling of Mouse Colorectum Capturing Longitudinal and Through-thickness Biomechanical Heterogeneity

Mechanotransduction, the encoding of local mechanical stresses and strains at sensory endings into neural action potentials at the viscera, plays a critical role in evoking visceral pain, e.g., in the distal colon and rectum (colorectum). The wall of the colorectum is structurally heterogeneous, including two major composites: the inner consists of muscular and submucosal layers, and the outer consists of circular muscular, intermuscular, longitudinal muscular, and serosal layers. In fact the colorectum presents biomechanical heterogenity across both the longitudinal and through-thickness directions thus highlighting the differential roles of sensory nerve endings within different regions of the colorectum in visceral mechanotransduction. We determined constitutive models and model parameters for individual layers of the colorectum from three longitudinal locations (colonic, intermediate, and distal) using nonlinear optimization to fit our experimental results from biaxial extension tests on layer-separated colorectal tissues (mouse model, 7×7 mm2, Siri et al., Am. J. Physiol. Gastrointest. Liver Physiol. 316, G473-G481 and 317, G349-G358), and quantified the thicknesses of the layers. In this study we also quantified the residual stretches stemming from separating colorectal specimens into inner and outer composites and we completed new pressure-diameter mechanical testing to provide an additional validation case. We implemented the constitutive equations and created two-layered, 3-D finite element models using FEBio (University of Utah), and incorporated the residual stretches. We validated the modeling framework by comparing FE-predicted results for both biaxial extension testing of bulk specimens of colorectum and pressure-diameter testing of bulk segments against corresponding experimental results independent of those used in our model fitting. We present the first theoretical framework to simulate the biomechanics of distal colorectum, including both longitudinal and through-thickness heterogeneity, based on constitutive modeling of biaxial extension tests of colon tissues from mice. Our constitutive models and modeling framework facilitate analyses of both fundamental questions (e.g., the impact of organ/tissue biomechanics on mechanotransduction of the sensory nerve endings, structure-function relationships, and growth and remodeling in health and disease) and specific applications (e.g., device design, minimally invasive surgery, and biomedical research).

MULTIPHYSICS MODELING OF PRECURSORS IN MOLTEN SALT FAST REACTORS USING PROTEUS AND Nek5000

The goal of this work was to calculate the impact of the delayed neutron precursor drift in fast spectrum Molten Salt Reactors (MSRs) using coupled solutions from the neutronics code PROTEUS and the computational fluid dynamics code Nek5000. Specifically, using a multiphysics approach to solve the effective delayed neutron fraction (βeff) or delayed neutron precursor distribution for reactors with flowing fuel salts would provide valuable information for transient simulations and safety assessments. Given the multiple options for the flux solution and geometric resolution/fidelity in PROTEUS, two approaches were developed and applied to various test cases: PROTEUS-NODAL/Nek5000 and PROTEUS-SN/Nek5000. For the former, the precursors are tracked in the built-in precursor drift model in PROTEUS-NODAL, whereas in the latter, Nek5000 directly tracks the precursors. Both approaches were used to solve a single test channel problem and showed excellent agreement in the calculated βeff. Separately, a 3D hourglass-shaped core was modeled using the PROTEUS-SN/Nek5000 approach. This problem was designed to demonstrate the capability of the discrete ordinates (SN) solver and Nek5000 to model complex core designs with axially varying geometries and the ability for Nek5000 to track the precursors and calculate the resulting βeff. In addition, the Nek5000 calculations revealed the presence of recirculation zones in the hourglass design, which could lead to significant temperatures in the fuel salt and surrounding materials. These first coupled solutions show why these approaches may be necessary for not only predicting the precursor drift effect in fast MSRs but also for reactor design and performance assessments.

Application of sensitivity analysis in DYMOND/Dakota to fuel cycle transition scenarios

The ability to perform sensitivity analysis has been enabled for the nuclear fuel cycle simulator DYMOND through its coupling with the design and analysis toolkit Dakota. To test and demonstrate these new capabilities, a transition scenario and multi-parameter study were devised. The transition scenario represents a partial transition from the US nuclear fleet to a closed fuel cycle with small modular LWRs and fast reactors fueled by reprocessed used nuclear fuel. Four uncertain parameters in this transition were studied – start date of reprocessing, total reprocessing capacity, the nuclear energy demand growth, and the rate at which the fast reactors are deployed – with respect to their impact on four response metrics. The responses – total natural uranium consumed, maximum annual enrichment capacity required, total disposed mass, and total cost of the nuclear fuel cycle – were chosen based on measures known to be of interest in transition scenarios [2] and to be significantly impacted by the varying parameters. Analysis of this study was performed both from the direct sampling and through surrogate models developed in Dakota to calculate the global sensitivity measures Sobol’ indices. This example application of this new capability showed that the most consequential parameter to most metrics was the share of new build capacity that is fast reactors. However, for the cost metric, the scaling factor of the energy demand growth was significant and had synergistic behavior with the fast reactor new build share.

MSRE TRANSIENT BENCHMARKS USING SAM

In recent years, there has been renewed interest in Molten Salter Reactors (MSRs) for their potential advantages compared to reactors that rely on solid fuel. In response to such interest, the System Analysis Module (SAM) was enhanced to include MSR-specific modeling features including a delayed neutron precursor drift model and a modified point kinetics model. This paper discusses the validation of these features using the experiments conducted in the Molten Salt Reactor Experiment (MSRE). These experiments include the pump start-up and coast-down tests at zero power and a thermal convection test. For the zero power tests, the change in pump speeds induces flow rate changes in the core that impact the precursor concentrations. This introduces a neutron imbalance and requires the adjustment of the control rods to counter-balance this effect. SAM was used to evaluate the precursor concentration in the core as a function of time, and the resulting changes in reactivity were evaluated through the modified point kinetics equation. The results show good agreement with the experimental data. It should be noted that the pump performance curve used in this analysis was re-constructed based on the initial water test data of the fuel pump. The steady-state pump curve is assumed to be applicable to transient flow operations. The thermal convection test was conducted by shutting off the pumps, reducing the inlet core temperature for 360 minutes, and allowing the power to be adjusted by the inherent feedbacks of the system. The power level during this transient was evaluated by SAM as a function of time.

[Application value of urinary IGFBP7 and TIMP-2 in acute kidney injury with decompensated hepatitis B virus-related liver cirrhosis]

Objective: To investigate the application value of new urinary biomarkers insulin-like growth factor binding protein 7 (IGFBP7) and tissue matrix metalloproteinase inhibitor-2 (TIMP-2) in acute kidney injury with decompensated hepatitis B virus-related liver cirrhosis. Methods: 45 newly hospitalized cases with decompensated hepatitis B virus-related liver cirrhosis were selected. Among them, 19 cases were combined with AKI on admission (cirrhosis-AKI group), 26 cases without AKI (cirrhosis-non-AKI group), and 12 healthy cases (normal control group). First-morning urine samples were collected and IGFBP7 and TIMP-2 were detected by enzyme-linked immunosorbent assay (ELISA). Urinary IGFBP7 and serum creatinine (SCr) were dynamically monitored after hospitalization in cirrhosis-non-AKI group. Normally distributed measurement data were compared by t-test, and non-normally distributed measurement data were compared by rank sum test. The receiver operating characteristic (ROC) curve and area under the curve (AUC) were used to evaluate the diagnostic accuracy of the indicators. Results: Urinary IGFBP7, IGFBP7 with TIMP-2 (IGFBP7×TIMP-2) in cirrhosis-AKI group (n = 19) were equally higher than that of the cirrhosis-non-AKI group (P < 0.05). Urinary IGFBP7, TIMP-2 and IGFBP7×TIMP-2 in cirrhosis-AKI group or cirrhosis-non-AKI group were significantly higher than those of the normal control group (P < 0.01). The AUC of urinary IGFBP7 and urinary IGFBP7×TIMP-2 for diagnosis of AKI were 0.703 (95% CI 0.547-0.860) and 0.700 (95% CI 0.541-0.859), respectively. In the liver cirrhosis-non-AKI group (n = 26), 5 cases of AKI were newly diagnosed according to the changes in SCr during hospitalization (progressive group). Urinary IGFBP7 was significantly increased 2 days before the diagnosis of AKI. The concentration of urinary IGFBP7 at admission in the progressive group (n = 5) was higher than that of the non-progressive group (n = 21) (P < 0.05). Conclusion: Urinary IGFBP7 and TIMP-2 concentrations were significantly increased in patients with decompensated hepatitis B virus-related liver cirrhosis. When AKI occurred, urinary IGFBP7 and IGFBP7×TIMP-2 was further increased. Urinary IGFBP7 is valuable for early AKI diagnosis, and may play a role in predicting AKI occurrence.

The acquisition of Mycobacterium tuberculosis infection in village doctors in China: a prospective study

BACKGROUND: Occupational exposure-related risk of Mycobacterium tuberculosis infection has been reported for village doctors in China. This prospective study aims to estimate the infection acquisition in this key population.METHODS: At baseline, all village doctors registered in Zhongmu County were tested by QuantiFERON^®-TB Gold In-Tube (QFT) and QuantiFERON^®-TB Gold Plus (QFT-Plus) in parallel. Those negatives for either of the tests were retested to identify conversions at the 2-year follow-up investigation.RESULTS: A total of 367 eligible participants completed the 2-year follow-up survey with frequency of conversion of 5.0% (18/361) for QFT and 6.1% (21/343) for QFT-Plus. The agreement of follow-up results between the tests was 93.2% with a κ coefficient of 0.43 (95%CI 0.20-0.65). Among QFT-Plus convertors, the difference between TB1 and TB2 tubes (TB2-TB1) was significantly increased as compared with baseline results (P = 0.039). Participants from the villages with occurrence of microbiologically confirmed pulmonary TB showed higher frequency of QFT conversions (11.0% vs. 3.2%, P = 0.011) and QFT-Plus conversions (12.3% vs. 4.4%, P = 0.027) than those from the villages without occurrence.CONCLUSION: Our results consistently suggest that capability on occupational protection and M. tuberculosis infection control should be improved in village doctors in China.

MIP image derived from abbreviated breast MRI: potential to reduce unnecessary sub-nipple biopsies during nipple-sparing mastectomy for breast cancer

OBJECTIVE

To determine the value of a maximum-intensity projection (MIP) image derived from abbreviated breast MRI for excluding occult nipple-areolar complex (NAC) involvement in patients with breast cancer.

METHODS

This prospective study included breast cancer patients with clinically normal NACs between April 2016 and May 2019. Abbreviated breast MRI was performed, and an MIP image was generated for each patient. MIP images were examined for the following features: asymmetric nipple enhancement, tumor-nipple distance (TND), tumor diameter, lesion type, location, and multifocality. Independent predictive MIP features for occult NAC involvement were identified by univariable and multivariable logistic regression analyses. Models based on independent predictive MIP features were developed, and their diagnostic performances were evaluated using ROC analysis. The utility of an MIP image for excluding occult NAC involvement was assessed by considering NPVs across patient subgroups.

RESULTS

Eight hundred forty-three patients (67 NAC-positive and 776 NAC-negative) were enrolled. On MIP images, asymmetric nipple enhancement (odds ratio, 6.098; p < 0.001) and TND (odds ratio, 0.564; p = 0.003) were independent predictors of occult NAC involvement. A parallel test model of "asymmetric nipple enhancement or TND ≤ 15 mm" yielded the highest AUC value (0.838) among prediction models. The NPV of MIP images for excluding occult NAC involvement was 99.5%, which was applicable across various patient subgroups.

CONCLUSIONS

A single MIP image derived from abbreviated breast MRI has utility for excluding occult NAC involvement in breast cancer patients and reducing the number of unnecessary sub-nipple biopsies in nipple-sparing mastectomy.

KEY POINTS

• On MIP images derived from abbreviated breast MRI, asymmetric nipple enhancement and tumor-nipple distance were independent predictors for occult nipple involvement in patients with breast cancer. • Negative findings on MIP image can help select patients at minimal risk of occult nipple involvement, for whom unnecessary intraoperative sub-nipple biopsies in nipple-sparing mastectomy can be omitted.

[Investigation on occupational hazards in a refrigeration equipment manufacturing enterprise]

Objective: To investigate the distribution and intensity of noise and ultraviolet radiation of welding posts in a refrigeration equipment manufacturing enterprise, in conjunction with the health status of welding workers, providing scientific evidence for the prevention and control of occupational diseases in this type of post. Methods: In May 2019, a cross-sectional survey method was used to select 576 welding workers in the pressure vessel workshop and the unit assembly workshop of a refrigeration complete equipment manufacturer from 2016 to 2018 as the research objects. The occupational hygiene survey and occupational hazard factor measurement were carried out in the workplace, and the measurement data and occupational health examination results were statistically analyzed. Results: The over standard rate of individual Lex in pressure vessel workshop was 82.2% (37/45) . Compared with the unit assembly workshop, the individual Lex of welding workers in pressure vessel workshop was higher than that in unit assembly workshop (t=13.43, P= 0.00) ; the effective irradiance exceeding rate of welding workers in pressure vessel workshop and unit assembly workshop was 33.3% (4/12) and 25.0% (3/12) , The meacurement of ovradiation in the moskment the occupational exposure limit. The deaf rate and hearing loss rate in pressure vessel workshop were 1.5% (5/336) 20.5% (69/336) , respectively, significantly higher than that in umit assembly workshop (P<0.05) . The detection rate of hearing loss of pressure vessel workshop workers increased year by year, and the difference was statistically significant (χ(2trend)=22.42, P<0.01) ; compared with the unit assembly workshop from 2016 to 2018, the detection rates of lens opacity, corneal cloudiness and hearing loss of pressure vessel workshop workers were statistically significant (χ(2)=9.45, 14.80, 55.99, P<0.01) . Conclusion: Welding workers exposed to noise and ultraviolet radiation are easy to be ignored. The enterprise management department should attach great importance to it and take comprehensive measures to protect the health of welding workers.

Protective effects of gliclazide on high glucose and AGEs-induced damage of glomerular mesangial cells and renal tubular epithelial cells via inhibiting RAGE-p22phox-NF-kB pathway

OBJECTIVE

Gliclazide is one of the most widely used therapeutic drugs for diabetes. As a second-generation sulfonylurea oral hypoglycemic drug, it can lower blood glucose level and delay the occurrence and development of diabetic nephropathy (DN). However, the underlying mechanism remains unclear. Therefore, the aim of this study was to explore whether gliclazide had protective effects on high glucose and advanced glycation end products (AGEs)-induced injury of human mesangial cells (HMCs) and renal tubular epithelial cells.

MATERIALS AND METHODS

HMC and renal tubular epithelial cell lines [human kidney 2 (HK-2)] were cultured in vitro. All cells were then divided into the follow groups: 1) blank control group (5.6 mmol/L glucose), 2) AGEs group [400 μg/mL AGE-bovine serum albumin (AGE-BSA)], 3) high glucose group (25 mmol/L glucose), 4) gliclazide + AGEs group (400 μg/mL AGE-BSA + 20 μmol/L gliclazide) and 5) gliclazide + high glucose group (25 mmol/L glucose + 20 μmol/L gliclazide). Cell counting kit-8 (CCK-8) assay was adopted to determine cell viability. Flow cytometry was used to detect cell apoptosis. The levels of malondialdehyde (MDA), superoxide dismutase (SOD) and glutathione peroxidase (GSH-Px) were measured as well. Furthermore, the mRNA expressions of receptor for AGE (RAGE), p22phox and nuclear factor kappa-light-chain-enhancer of activated B cells (NF-κB) were measured via fluorescence quantitative Real-time polymerase chain reaction (qRT-PCR).

RESULTS

Compared with control group, significantly accelerated apoptosis of HMCs and HK-2, increased MDA level, decreased SOD and GSH-Px levels, and up-regulated mRNA expressions of RAGE, p22phox and NF-κB were observed in HMCs and HK-2 of high glucose group and AGEs group. Meanwhile, there were obviously alleviated apoptosis of HMCs and HK-2, decreased MDA level, increased SOD and GSH-Px levels, as well as down-regulated mRNA expressions of RAGE, p22phox and NF-κB in HMCs and HK-2 of gliclazide group compared with high glucose and AGEs group. Furthermore, significant correlations were found between the mRNA expression of RAGE and the apoptosis rate of HMCs and HK-2 (HMCs: r=0.701, p=0.004 and HK-2: r=0.633, p=0.011).

CONCLUSIONS

Gliclazide has protective effects on high glucose and AGEs-induced damage of glomerular mesangial cells and renal tubular epithelial cells via inhibiting RAGE-NADPH oxidase-NF-kB pathway.

The CSP-Based New Features Plus Non-Convex Log Sparse Feature Selection for Motor Imagery EEG Classification

The common spatial pattern (CSP) is a very effective feature extraction method in motor imagery based brain computer interface (BCI), but its performance depends on the selection of the optimal frequency band. Although a lot of research works have been proposed to improve CSP, most of these works have the problems of large computation costs and long feature extraction time. To this end, three new feature extraction methods based on CSP and a new feature selection method based on non-convex log regularization are proposed in this paper. Firstly, EEG signals are spatially filtered by CSP, and then three new feature extraction methods are proposed. We called them CSP-wavelet, CSP-WPD and CSP-FB, respectively. For CSP-Wavelet and CSP-WPD, the discrete wavelet transform (DWT) or wavelet packet decomposition (WPD) is used to decompose the spatially filtered signals, and then the energy and standard deviation of the wavelet coefficients are extracted as features. For CSP-FB, the spatially filtered signals are filtered into multiple bands by a filter bank (FB), and then the logarithm of variances of each band are extracted as features. Secondly, a sparse optimization method regularized with a non-convex log function is proposed for the feature selection, which we called LOG, and an optimization algorithm for LOG is given. Finally, ensemble learning is used for secondary feature selection and classification model construction. Combing feature extraction and feature selection methods, a total of three new EEG decoding methods are obtained, namely CSP-Wavelet+LOG, CSP-WPD+LOG, and CSP-FB+LOG. Four public motor imagery datasets are used to verify the performance of the proposed methods. Compared to existing methods, the proposed methods achieved the highest average classification accuracy of 88.86, 83.40, 81.53, and 80.83 in datasets 1–4, respectively. The feature extraction time of CSP-FB is the shortest. The experimental results show that the proposed methods can effectively improve the classification accuracy and reduce the feature extraction time. With comprehensive consideration of classification accuracy and feature extraction time, CSP-FB+LOG has the best performance and can be used for the real-time BCI system.

A CT-based radiomics nomogram for prediction of lung adenocarcinomas and granulomatous lesions in patient with solitary sub-centimeter solid nodules

PURPOSE

To develop a radiomics nomogram based on computed tomography (CT) images that can help differentiate lung adenocarcinomas and granulomatous lesions appearing as sub-centimeter solid nodules (SCSNs).

MATERIALS AND METHODS

The records of 214 consecutive patients with SCSNs that were surgically resected and histologically confirmed as lung adenocarcinomas (n = 112) and granulomatous lesions (n = 102) from 2 medical institutions between October 2011 and June 2019 were retrospectively analyzed. Patients from center 1 ware enrolled as training cohort (n = 150) and patients from center 2 were included as external validation cohort (n = 64), respectively. Radiomics features were extracted from non-contrast chest CT images preoperatively. The least absolute shrinkage and selection operator (LASSO) regression model was used for radiomics feature extraction and radiomics signature construction. Clinical characteristics, subjective CT findings, and radiomics signature were used to develop a predictive radiomics nomogram. The performance was examined by assessment of the area under the receiver operating characteristic curve (AUC).

RESULTS

Lung adenocarcinoma was significantly associated with an irregular margin and lobulated shape in the training set (p = 0.001, < 0.001) and external validation set (p = 0.016, = 0.018), respectively. The radiomics signature consisting of 22 features was significantly associated with lung adenocarcinomas of SCSNs (p < 0.001). The radiomics nomogram incorporated the radiomics signature, gender and lobulated shape. The AUCs of combined model in the training and external validation dataset were 0.885 (95% confidence interval [CI]: 0.823-0.931), 0.808 (95% CI: 0.690-0.896), respectively. Decision curve analysis (DCA) demonstrated that the radiomics nomogram was clinically useful.

CONCLUSION

A radiomics signature based on non-enhanced CT has the potential to differentiate between lung adenocarcinomas and granulomatous lesions. The radiomics nomogram incorporating the radiomics signature and subjective findings may facilitate the individualized, preoperative treatment in patients with SCSNs.

Solitary solid pulmonary nodules: a CT-based deep learning nomogram helps differentiate tuberculosis granulomas from lung adenocarcinomas

OBJECTIVES

To evaluate the differential diagnostic performance of a computed tomography (CT)-based deep learning nomogram (DLN) in identifying tuberculous granuloma (TBG) and lung adenocarcinoma (LAC) presenting as solitary solid pulmonary nodules (SSPNs).

METHODS

Routine CT images of 550 patients with SSPNs were retrospectively obtained from two centers. A convolutional neural network was used to extract deep learning features from all lesions. The training set consisted of data for 218 patients. The least absolute shrinkage and selection operator logistic regression was used to create a deep learning signature (DLS). Clinical factors and CT-based subjective findings were combined in a clinical model. An individualized DLN incorporating DLS, clinical factors, and CT-based subjective findings was constructed to validate the diagnostic ability. The performance of the DLN was assessed by discrimination and calibration using internal (n = 140) and external validation cohorts (n = 192).

RESULTS

DLS, gender, age, and lobulated shape were found to be independent predictors and were used to build the DLN. The combination showed better diagnostic accuracy than any single model evaluated using the net reclassification improvement method (p < 0.05). The areas under the curve in the training, internal validation, and external validation cohorts were 0.889 (95% confidence interval [CI], 0.839-0.927), 0.879 (95% CI, 0.813-0.928), and 0.809 (95% CI, 0.746-0.862), respectively. Decision curve analysis and stratification analysis showed that the DLN has potential generalization ability.

CONCLUSIONS

The CT-based DLN can preoperatively distinguish between LAC and TBG in patients presenting with SSPNs.

KEY POINTS

• The deep learning nomogram was developed to preoperatively differentiate TBG from LAC in patients with SSPNs. • The performance of the deep learning feature was superior to that of the radiomics feature. • The deep learning nomogram achieved superior performance compared to the deep learning signature, the radiomics signature, or the clinical model alone.

Segmentation of small ground glass opacity pulmonary nodules based on Markov random field energy and Bayesian probability difference

BACKGROUND

Image segmentation is an important part of computer-aided diagnosis (CAD), the segmentation of small ground glass opacity (GGO) pulmonary nodules is beneficial for the early detection of lung cancer. For the segmentation of small GGO pulmonary nodules, an integrated active contour model based on Markov random field energy and Bayesian probability difference (IACM_MRFEBPD) is proposed in this paper.

METHODS

First, the Markov random field (MRF) is constructed on the computed tomography (CT) images, then the MRF energy is calculated. The MRF energy is used to construct the region term. It can not only enhance the contrast between pulmonary nodule and the background region, but also solve the problem of intensity inhomogeneity using local spatial correlation information between neighboring pixels in the image. Second, the Gaussian mixture model is used to establish the probability model of the image, and the model parameters are estimated by the expectation maximization (EM) algorithm. So the Bayesian posterior probability difference of each pixel can be calculated. The probability difference is used to construct the boundary detection term, which is 0 at the boundary. Therefore, the blurred boundary problem can be solved. Finally, under the framework of the level set, the integrated active contour model is constructed.

RESULTS

To verify the effectiveness of the proposed method, the public data of the lung image database consortium and image database resource initiative (LIDC-IDRI) and the clinical data of the Affiliated Jiangmen Hospital of Sun Yat-sen University are used to perform experiments, and the intersection over union (IOU) score is used to evaluate the segmentation methods. Compared with other methods, the proposed method achieves the best results with the highest average IOU of 0.7444, 0.7503, and 0.7450 for LIDC-IDRI test set, clinical test set, and all test sets, respectively.

CONCLUSIONS

The experiment results show that the proposed method can segment various small GGO pulmonary nodules more accurately and robustly, which is helpful for the accurate evaluation of medical imaging.

Radiomics nomogram for preoperative differentiation of lung tuberculoma from adenocarcinoma in solitary pulmonary solid nodule

PURPOSE

To investigate the preoperative differential diagnostic performance of a radiomics nomogram in tuberculous granuloma (TBG) and lung adenocarcinoma (LAC) appearing as solitary pulmonary solid nodules (SPSNs).

METHOD

We retrospectively recruited 426 patients with SPSNs from two centers and assigned them to training (n = 123), internal validation (n = 121), and external validation cohorts (n = 182). A model of deep learning (DL) was built for tumor segmentation from routine computed tomography (CT) images and extraction of 3D radiomics features. We used the least absolute shrinkage and selection operator (LASSO) logistic regression to build a radiomics signature. A clinical model was developed with clinical factors, including age, gender, and CT-based subjective findings (eg, lesion size, lesion location, lesion margin, lobulated sharp, and spiculation sign). We constructed individualized radiomics nomograms incorporating the radiomics signature and clinical factors to validate the diagnostic ability.

RESULTS

Three factors - radiomics signature, age, and spiculation sign - were found to be independent predictors and were used to build the radiomics nomogram, which showed better diagnostic accuracy than any single model (all net reclassification improvement p < 0.05). The area under curve yielded was 0.9660 (95% confidence interval [CI], 0.9390-0.9931), 0.9342 (95% CI, 0.8944-0.9739), and 0.9064 (95% CI, 0.8639-0.9490) for the training, internal validation, and external validation cohorts, respectively. Decision curve analysis (DCA) and stratification analysis showed the nomogram has potential for generalizability.

CONCLUSION

The radiomics nomogram we developed can preoperatively distinguish between LAC and TBG in patient with a SPSN.

Clinical effectiveness of 3 days preoperative treatment with recombinant human erythropoietin in total knee arthroplasty surgery: a clinical trial

AIMS

The purpose of study is to evaluate the effect and complication of preoperative short-term daily recombinant human erythropoietin (rhEPO) treatment for blood-saving in patients undergoing unilateral primary total knee arthroplasty (TKA).

METHODS

This three-arm randomized clinical trial compared three different rhEPO-based treatment protocols for unilateral primary TKA. Group A: application of daily doses of rhEPO combined with iron supplement starting 3 days before surgery; Group B: application of daily doses of rhEPO combined with iron supplement starting the day of surgery; Group C: iron supplement alone. Perioperative hemoglobin (Hb) level gaps, total perioperative blood loss, reticulocyte levels and treatment-related complications were studied.

RESULTS

A total of 102 patients were included (35, 35 and 32 patients in Groups A, B and C, respectively). Total blood loss (TBL) in Groups A, B and C was 490.84, 806.76 and 924.21 ml, respectively. Patients in Group A had a significant lower TBL than Groups B and C (A vs. B: P = 0.010; A vs. C: P < 0.001). There was no difference as for TBL between Groups B and C (P = 0.377). Group A patients had significant smaller Hb decline than Group C on the third and fifth postoperative day (P = 0.049, P = 0.037), as well as than Group B on the fifth postoperative day (P = 0.048). There was no difference as for Hb decline between Groups B and C. No difference was shown in levels of inflammatory biomarkers or blood-saving protocol-related complications among three groups.

CONCLUSIONS

Daily dose of rhEPO combined with iron supplement administered 3 days before TKA procedures could significantly decrease perioperative blood loss and improve postoperative Hb levels, without significantly elevating risks of complication, when compared with admission of rhEPO on the day of surgery and iron supplement alone. Preoperative daily rhEPO treatment could be a more effective blood-saving protocol in TKA procedures.

Reduced Complexity in Stroke with Motor Deficits: A Resting-State fMRI Study

Recently, alterations of complexity due to brain disorders have been demonstrated using brain entropy (BEN), while the changes of brain complexity in stroke, a common cerebrovascular disease, remain unclear. In this research, resting-state functional magnetic resonance imaging (fMRI) was performed to explore the alterations of brain complexity using BEN in twenty stroke patients with motor deficits and nineteen matched healthy controls. The sample entropy (SampEn) was applied to build the BEN mapping for each participant. Compared with healthy controls, stroke patients exhibited lower BEN values in the contralesional precentral gyrus (preCG), bilateral dorsolateral frontal gyrus (SFGdor) and bilateral supplementary motor area (SMA). Moreover, significantly positive correlations between BEN values and Fugl-Meyer Assessment scores were detected in the ipsilesional SFGdor and ipsilesional SMA. Mutual information independence was observed between BEN and regional homogeneity (ReHo), amplitude of low-frequency fluctuations (ALFF), respectively, in the stroke patients. Our findings implied that brain complexity had been impacted after stroke, and also suggested that BEN could be a complementary tool for evaluating the motor impairment after stroke.