Radiomics analysis of patellofemoral joint improves knee replacement risk prediction: Data from the Multicenter Osteoarthritis Study (MOST)

Objective

Knee replacement (KR) is the last-resort treatment for knee osteoarthritis. Although radiographic evidence of tibiofemoral joint has been widely adopted for prognostication, patellofemoral joint has gained little attention and may hold additional value for further improvements. We aimed to quantitatively analyse patellofemoral joint through radiomics analysis of lateral view radiographs for improved KR risk prediction.

Design

From the Multicenter Osteoarthritis Study dataset, we retrospectively retrieved the initial-visit lateral left knee radiographs of 2943 patients aged 50 to 79. They were split into training and test cohorts at a 2:1 ratio. A comprehensive set of radiomic features were extracted within the best-performing subregion of patellofemoral joint and combined into a radiomics score (RadScore). A KR risk score, derived from Kellgren-Lawrence grade (KLG) of tibiofemoral joint and RadScore of patellofemoral joint, was developed by multivariate Cox regression and assessed using time-dependent area under receiver operating characteristic curve (AUC).

Results

While patellofemoral osteoarthritis (PFOA) was insignificant during multivariate analysis, RadScore was identified as an independent risk factor (multivariate Cox p-value < 0.001) for KR. The subgroup analysis revealed that RadScore was particularly effective in predicting rapid progressor (KR occurrence before 30 months) among early- (KLG < 2) and mid-stage (KLG ​= ​2) patients. Combining two joints radiographic information, the AUC reached 0.89/0.87 for predicting 60-month KR occurrence.

Conclusions

The RadScore of the patellofemoral joint on lateral radiographs emerges as an independent prognostic factor for improving KR prognosis prediction. The KR risk score could be instrumental in managing progressive knee osteoarthritis interventions.

Deep learning-based bronchial tree-guided semi-automatic segmentation of pulmonary segments in computed tomography images

Background

Pulmonary segments are valuable because they can provide more precise localization and intricate details of lung cancer than lung lobes. With advances in precision therapy, there is an increasing demand for the identification and visualization of pulmonary segments in computed tomography (CT) images to aid in the precise treatment of lung cancer. This study aimed to integrate multiple deep-learning models to accurately segment pulmonary segments in CT images using a bronchial tree (BT)-based approach.

Methods

The proposed segmentation method for pulmonary segments using the BT-based approach comprised the following five essential steps: (I) segmentation of the lung using a U-Net (R231) (public access) model; (II) segmentation of the lobes using a V-Net (self-developed) model; (III) segmentation of the airway using a combination of a differential geometric approach method and a BronchiNet (public access) model; (IV) labeling of the BT branches based on anatomical position; and (V) segmentation of the pulmonary segments based on the distance of each voxel to the labeled BT branches. This five-step process was applied to 14 high-resolution breath-hold CT images and compared against manual segmentations for evaluation.

Results

For the lung segmentation, the lung mask had a mean dice similarity coefficient (DSC) of 0.98±0.03. For the lobe segmentation, the V-Net model had a mean DSC of 0.94±0.06. For the airway segmentation, the average total length of the segmented airway trees per image scan was 1,902.8±502.1 mm, and the average number of the maximum airway tree generations was 8.5±1.3. For the segmentation of the pulmonary segments, the proposed method had a DSC of 0.73±0.11 and a mean surface distance of 6.1±2.9 mm.

Conclusions

This study demonstrated the feasibility of combining multiple deep-learning models for the auxiliary segmentation of pulmonary segments on CT images using a BT-based approach. The results highlighted the potential of the BT-based method for the semi-automatic segmentation of the pulmonary segment.

Multi-omics and Multi-VOIs to predict esophageal fistula in esophageal cancer patients treated with radiotherapy

OBJECTIVE

This study aimed to develop a prediction model for esophageal fistula (EF) in esophageal cancer (EC) patients treated with intensity-modulated radiation therapy (IMRT), by integrating multi-omics features from multiple volumes of interest (VOIs).

METHODS

We retrospectively analyzed pretreatment planning computed tomographic (CT) images, three-dimensional dose distributions, and clinical factors of 287 EC patients. Nine groups of features from different combination of omics [Radiomics (R), Dosiomics (D), and RD (the combination of R and D)], and VOIs [esophagus (ESO), gross tumor volume (GTV), and EG (the combination of ESO and GTV)] were extracted and separately selected by unsupervised (analysis of variance (ANOVA) and Pearson correlation test) and supervised (Student T test) approaches. The final model performance was evaluated using five metrics: average area under the receiver-operator-characteristics curve (AUC), accuracy, precision, recall, and F1 score.

RESULTS

For multi-omics using RD features, the model performance in EG model shows: AUC, 0.817 ± 0.031; 95% CI 0.805, 0.825; p < 0.001, which is better than single VOI (ESO or GTV).

CONCLUSION

Integrating multi-omics features from multi-VOIs enables better prediction of EF in EC patients treated with IMRT. The incorporation of dosiomics features can enhance the model performance of the prediction.

Breast Multiparametric MRI for Prediction of Neoadjuvant Chemotherapy Response in Breast Cancer: The BMMR2 Challenge

Purpose To describe the design, conduct, and results of the Breast Multiparametric MRI for prediction of neoadjuvant chemotherapy Response (BMMR2) challenge. Materials and Methods The BMMR2 computational challenge opened on May 28, 2021, and closed on December 21, 2021. The goal of the challenge was to identify image-based markers derived from multiparametric breast MRI, including diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) MRI, along with clinical data for predicting pathologic complete response (pCR) following neoadjuvant treatment. Data included 573 breast MRI studies from 191 women (mean age [±SD], 48.9 years ± 10.56) in the I-SPY 2/American College of Radiology Imaging Network (ACRIN) 6698 trial (ClinicalTrials.gov: NCT01042379). The challenge cohort was split into training (60%) and test (40%) sets, with teams blinded to test set pCR outcomes. Prediction performance was evaluated by area under the receiver operating characteristic curve (AUC) and compared with the benchmark established from the ACRIN 6698 primary analysis. Results Eight teams submitted final predictions. Entries from three teams had point estimators of AUC that were higher than the benchmark performance (AUC, 0.782 [95% CI: 0.670, 0.893], with AUCs of 0.803 [95% CI: 0.702, 0.904], 0.838 [95% CI: 0.748, 0.928], and 0.840 [95% CI: 0.748, 0.932]). A variety of approaches were used, ranging from extraction of individual features to deep learning and artificial intelligence methods, incorporating DCE and DWI alone or in combination. Conclusion The BMMR2 challenge identified several models with high predictive performance, which may further expand the value of multiparametric breast MRI as an early marker of treatment response. Clinical trial registration no. NCT01042379 Keywords: MRI, Breast, Tumor Response Supplemental material is available for this article. © RSNA, 2024.

Comparing effectiveness of image perturbation and test retest imaging in improving radiomic model reliability

Image perturbation is a promising technique to assess radiomic feature repeatability, but whether it can achieve the same effect as test-retest imaging on model reliability is unknown. This study aimed to compare radiomic model reliability based on repeatable features determined by the two methods using four different classifiers. A 191-patient public breast cancer dataset with 71 test-retest scans was used with pre-determined 117 training and 74 testing samples. We collected apparent diffusion coefficient images and manual tumor segmentations for radiomic feature extraction. Random translations, rotations, and contour randomizations were performed on the training images, and intra-class correlation coefficient (ICC) was used to filter high repeatable features. We evaluated model reliability in both internal generalizability and robustness, which were quantified by training and testing AUC and prediction ICC. Higher testing performance was found at higher feature ICC thresholds, but it dropped significantly at ICC = 0.95 for the test-retest model. Similar optimal reliability can be achieved with testing AUC = 0.7-0.8 and prediction ICC > 0.9 at the ICC threshold of 0.9. It is recommended to include feature repeatability analysis using image perturbation in any radiomic study when test-retest is not feasible, but care should be taken when deciding the optimal feature repeatability criteria.

Respiratory Invariant Textures From Static Computed Tomography Scans for Explainable Lung Function Characterization

PURPOSE

The inherent characteristics of lung tissue independent of breathing maneuvers may provide fundamental information for function assessment. This paper attempted to correlate textural signatures from computed tomography (CT) with pulmonary function measurements.

MATERIALS AND METHODS

Twenty-one lung cancer patients with thoracic 4-dimensional CT, DTPA-single-photon emission CT ventilation ( VNM ) scans, and available spirometry measurements (forced expiratory volume in 1 s, FEV 1 ; forced vital capacity, FVC; and FEV 1 /FVC) were collected. In subregional feature discovery, function-correlated candidates were identified from 79 radiomic features based on the statistical strength to differentiate defected/nondefected lung regions. Feature maps (FMs) of selected candidates were generated on 4-dimensional CT phases for a voxel-wise feature distribution study. Quantitative metrics were applied for validations, including the Spearman correlation coefficient (SCC) and the Dice similarity coefficient for FM- VNM spatial agreement assessments, intraclass correlation coefficient for FM interphase robustness evaluations, and FM-spirometry comparisons.

RESULTS

At the subregion level, 8 function-correlated features were identified (effect size>0.330). The FMs of candidates yielded moderate-to-strong voxel-wise correlations with the reference VNM . The FMs of gray level dependence matrix dependence nonuniformity showed the highest robust (intraclass correlation coefficient=0.96 and P <0.0001) spatial correlation, with median SCCs ranging from 0.54 to 0.59 throughout the 10 breathing phases. Its phase-averaged FM achieved a median SCC of 0.60, a median Dice similarity coefficient of 0.60 (0.65) for high (low) functional lung volumes, and a correlation of 0.565 (0.646) between the spatially averaged feature values and FEV 1 (FEV 1 /FVC).

CONCLUSIONS

The results provide further insight into the underlying association of specific pulmonary textures with both local ( VNM ) and global (FEV 1 /FVC, FEV 1 ) functions. Further validations of the FM generalizability and the standardization of implementation protocols are warranted before clinically relevant investigations.

Noninvasive imaging signatures of HER2 and HR using ADC in invasive breast cancer: repeatability, reproducibility, and association with pathological complete response to neoadjuvant chemotherapy

BACKGROUND

The immunohistochemical test (IHC) of HER2 and HR can provide prognostic information and treatment guidance for invasive breast cancer patients. We aimed to develop noninvasive image signatures IS_HER2 and IS_HR of HER2 and HR, respectively. We independently evaluate their repeatability, reproducibility, and association with pathological complete response (pCR) to neoadjuvant chemotherapy.

METHODS

Pre-treatment DWI, IHC receptor status HER2/HR, and pCR to neoadjuvant chemotherapy of 222 patients from the multi-institutional ACRIN 6698 trial were retrospectively collected. They were pre-separated for development, independent validation, and test-retest. 1316 image features were extracted from DWI-derived ADC maps within manual tumor segmentations. IS_HER2 and IS_HR were developed by RIDGE logistic regression using non-redundant and test-retest reproducible features relevant to IHC receptor status. We evaluated their association with pCR using area under receiver operating curve (AUC) and odds ratio (OR) after binarization. Their reproducibility was further evaluated using the test-retest set with intra-class coefficient of correlation (ICC).

RESULTS

A 5-feature IS_HER2 targeting HER2 was developed (AUC = 0.70, 95% CI 0.59 to 0.82) and validated (AUC = 0.72, 95% CI 0.58 to 0.86) with high perturbation repeatability (ICC = 0.92) and test-retest reproducibility (ICC = 0.83). IS_HR was developed using 5 features with higher association with HR during development (AUC = 0.75, 95% CI 0.66 to 0.84) and validation (AUC = 0.74, 95% CI 0.61 to 0.86) and similar repeatability (ICC = 0.91) and reproducibility (ICC = 0.82). Both image signatures showed significant associations with pCR with AUC of 0.65 (95% CI 0.50 to 0.80) for IS_HER2 and 0.64 (95% CI 0.50 to 0.78) for IS_HER2 in the validation cohort. Patients with high IS_HER2 were more likely to achieve pCR to neoadjuvant chemotherapy with validation OR of 4.73 (95% CI 1.64 to 13.65, P value = 0.006). Low IS_HR patients had higher pCR with OR = 0.29 (95% CI 0.10 to 0.81, P value = 0.021). Molecular subtypes derived from the image signatures showed comparable pCR prediction values to IHC-based molecular subtypes (P value > 0.05).

CONCLUSION

Robust ADC-based image signatures were developed and validated for noninvasive evaluation of IHC receptors HER2 and HR. We also confirmed their value in predicting treatment response to neoadjuvant chemotherapy. Further evaluations in treatment guidance are warranted to fully validate their potential as IHC surrogates.

Explainable machine learning via intra-tumoral radiomics feature mapping for patient stratification in adjuvant chemotherapy for locoregionally advanced nasopharyngeal carcinoma

PURPOSE

This study aimed to discover intra-tumor heterogeneity signature and validate its predictive value for adjuvant chemotherapy (ACT) following concurrent chemoradiotherapy (CCRT) in locoregionally advanced nasopharyngeal carcinoma (LA-NPC).

MATERIALS AND METHODS

397 LA-NPC patients were retrospectively enrolled. Pre-treatment contrast-enhanced T1-weighted (CET1-w) MR images, clinical variables, and follow-up were retrospectively collected. We identified single predictive radiomic feature from primary gross tumor volume (GTVnp) and defined predicted subvolume by calculating voxel-wised feature mapping and within GTVnp. We independently validate predictive value of identified feature and associated predicted subvolume.

RESULTS

Only one radiomic feature, gldm_DependenceVariance in 3 mm-sigma LoG-filtered image, was discovered as a signature. In the high-risk group determined by the signature, patients received CCRT + ACT achieved 3-year disease free survival (DFS) rate of 90% versus 57% (HR, 0.20; 95%CI, 0.05-0.94; P = 0.007) for CCRT alone. The multivariate analysis showed patients receiving CCRT + ACT had a HR of 0.21 (95%CI: 0.06-0.68, P = 0.009) for DFS compared to those receiving CCRT alone. The predictive value can also be generalized to the subvolume with multivariate HR of 0.27 (P = 0.017) for DFS.

CONCLUSION

The signature with its heterogeneity mapping could be a reliable and explainable ACT decision-making tool in clinical practice.

Multimodal Data Integration to Predict Severe Acute Oral Mucositis of Nasopharyngeal Carcinoma Patients Following Radiation Therapy

(1) Background: Acute oral mucositis is the most common side effect for nasopharyngeal carcinoma patients receiving radiotherapy. Improper or delayed intervention to severe AOM could degrade the quality of life or survival for NPC patients. An effective prediction method for severe AOM is needed for the individualized management of NPC patients in the era of personalized medicine. (2) Methods: A total of 242 biopsy-proven NPC patients were retrospectively recruited in this study. Radiomics features were extracted from contrast-enhanced CT (CECT), contrast-enhanced T1-weighted (cT1WI), and T2-weighted (T2WI) images in the primary tumor and tumor-related area. Dosiomics features were extracted from 2D or 3D dose-volume histograms (DVH). Multiple models were established with single and integrated data. The dataset was randomized into training and test sets at a ratio of 7:3 with 10-fold cross-validation. (3) Results: The best-performing model using Gaussian Naive Bayes (GNB) (mean validation AUC = 0.81 ± 0.10) was established with integrated radiomics and dosiomics data. The GNB radiomics and dosiomics models yielded mean validation AUC of 0.6 ± 0.20 and 0.69 ± 0.14, respectively. (4) Conclusions: Integrating radiomics and dosiomics data from the primary tumor area could generate the best-performing model for severe AOM prediction.

Multi-omics to predict acute radiation esophagitis in patients with lung cancer treated with intensity-modulated radiation therapy

PURPOSE

The study aimed to predict acute radiation esophagitis (ARE) with grade  ≥ 2 for patients with locally advanced lung cancer (LALC) treated with intensity-modulated radiation therapy (IMRT) using multi-omics features, including radiomics and dosiomics.

METHODS

161 patients with stage IIIA-IIIB LALC who received chemoradiotherapy (CRT) or radiotherapy by IMRT with a prescribed dose from 45 to 70 Gy from 2015 to 2019 were enrolled retrospectively. All the toxicity gradings were given following the Common Terminology Criteria for Adverse Events V4.0. Multi-omics features, including radiomics, dosiomics (including dose-volume histogram dosimetric parameters), were extracted based on the planning CT image and three-dimensional dose distribution. All data were randomly divided into training cohorts (N = 107) and testing cohorts (N = 54). In the training cohorts, features with reliably high outcome relevance and low redundancy were selected under random patient subsampling. Four classification models (using clinical factors (CF) only, using radiomics features (RFs) only, dosiomics features (DFs) only, and the hybrid features (HFs) containing clinical factors, radiomics and dosiomics) were constructed employing the Ridge classifier using two-thirds of randomly selected patients as the training cohort. The remaining patient was treated as the testing cohort. A series of models were built with 30 times training-testing splits. Their performances were assessed using the area under the ROC curve (AUC) and accuracy.

RESULTS

Among all patients, 51 developed ARE grade  ≥ 2, with an incidence of 31.7%. Next, 8990 radiomics and 213 dosiomics features were extracted, and 3, 6, 12, and 13 features remained after feature selection in the CF, DF, RF and DF models, respectively. The RF and HF models achieved similar classification performance, with the training and testing AUCs of 0.796 ± 0.023 (95% confidence interval (CI [0.79, 0.80])/0.744 ± 0.044 (95% CI [0.73, 0.76]) and 0.801 ± 0.022 (95% CI [0.79, 0.81]) (p = 0.74), respectively. The model performances using CF and DF features were poorer, with training and testing AUCs of 0.573 ± 0.026 (95% CI [0.56, 0.58])/ 0.509 ± 0.072 (95% CI [0.48, 0.53]) and 0.679 ± 0.027 (95% CI [0.67, 0.69])/0.604 ± 0.041 (95% CI [0.53, 0.63]) compared with the above two models (p < 0.001), respectively.

CONCLUSIONS

In LALC patients treated with CRT IMRT, the ARE grade  ≥ 2 can be predicted using the pretreatment radiotherapy image features. To predict ARE, the multi-omics features had similar predictability with radiomics features; however, the dosiomics features and clinical factors had a limited classification performance.

Radiomic feature repeatability and its impact on prognostic model generalizability: A multi-institutional study on nasopharyngeal carcinoma patients

BACKGROUND AND PURPOSE

To investigate the radiomic feature (RF) repeatability via perturbation and its impact on cross-institutional prognostic model generalizability in Nasopharyngeal Carcinoma (NPC) patients.

MATERIALS AND METHODS

286 and 183 NPC patients from two institutions were included for model training and validation. Perturbations with random translations and rotations were applied to contrast-enhanced T1-weighted (CET1-w) MR images. RFs were extracted from primary tumor volume under a wide range of image filtering and discretization settings. RF repeatability was assessed by intraclass correlation coefficient (ICC), which was used to equally separate the RFs into low- and high-repeatable groups by the median value. After feature selection, multivariate Cox regression and Kaplan-Meier analysis were independently employed to develop and analyze prognostic models. Concordance index (C-index) and P-value from log-rank test were used to assess model performance.

RESULTS

Most textural RFs from high-pass wavelet-filtered images were susceptible to image perturbations. It was more prominent when a smaller discretization bin number was used (e.g., 8, mean ICC = 0.69). Using high-repeatable RFs for model development yielded a significantly higher C-index (0.63) in the validation cohort than when only low-repeatable RFs were used (0.57, P = 0.024), suggesting higher model generalizability. Besides, significant risk stratification in the validation cohort was observed only when high-repeatable RFs were used (P < 0.001).

CONCLUSION

Repeatability of RFs from high-pass wavelet-filtered CET1-w MR images of primary NPC tumor was poor, particularly when a smaller bin number was used. Exclusive use of high-repeatable RFs is suggested to safeguard model generalizability for wide-spreading clinical utilization.

Effect of Multicomponent Intervention on Functional Decline in Chinese Older Adults: A Multicenter Randomized Clinical Trial

OBJECTIVES

To confirm whether multicomponent exercise following vivifrail recommendations was an effective method for improving physical ability, cognitive function, gait, balance, and muscle strength in Chinese older adults.

METHODS

This was a multicenter and randomized clinical trial conducted in Jiangsu, China, from April 2021 to April 2022. Intervention lasted for 12 weeks and 104 older adults with functional declines were enrolled. All participants were randomly assigned to a control (usual care plus health education) or exercise group (usual care plus health education plus exercise). Primary outcomes were the change score of Short Physical Performance Battery (SPPB) and activities of daily living (ADL). The secondary outcomes included instrumental activities of daily living, Tinetti scores, Frailty score, short-form Mini Nutritional Assessment, Mini-Mental State Examination, Geriatric Depression Scale-15, the 12-item Short Form Survey, 4-meter gait speed test, 6-min walking distance, grip strength, and body composition analysis.

RESULTS

Among the participants, the average age was 85 (82, 88) years. After 12 weeks of follow-up, the exercise group showed a significant improvement in SPPB, with a change of 2 points (95% confidence interval [0, 3.5], P<0.001) compared to control. In contrast, SPPB remained stable in the control group. Compared to the control group, ADL improved in the exercise group, as did instrumental activities of daily living, Tinetti, Frailty, Short Form Survey, 4-meter gait speed test, and 6-min walking distance. Although there was no significant difference between groups in body composition analysis after post-intervention, the exercise group still improved in soft lean mass (P=0.002), fat-free mass (P=0.002), skeletal muscle mass index (P<0.001), fat-free mass index (P=0.004), appendicular skeletal muscle mass (P<0.001), and leg muscle mass (P<0.001), while the control group had no significant increase. No difference was observed in adverse events during trial period.

CONCLUSIONS

The multicomponent exercise intervention following vivifrail recommendations is an effective method for older adults with functional decline and can reverse the functional decline and improve gait, balance, and muscle strength. Additionally, the 12-week multicomponent exercise method provides guidance for Chinese medical professionals working in the field of geriatrics and is a promising method to improve physical function in the general population.

Artificial intelligence-assisted multistrategy image enhancement of chest X-rays for COVID-19 classification

Background

The coronavirus disease 2019 (COVID-19) led to a dramatic increase in the number of cases of patients with pneumonia worldwide. In this study, we aimed to develop an AI-assisted multistrategy image enhancement technique for chest X-ray (CXR) images to improve the accuracy of COVID-19 classification.

Methods

Our new classification strategy consisted of 3 parts. First, the improved U-Net model with a variational encoder segmented the lung region in the CXR images processed by histogram equalization. Second, the residual net (ResNet) model with multidilated-rate convolution layers was used to suppress the bone signals in the 217 lung-only CXR images. A total of 80% of the available data were allocated for training and validation. The other 20% of the remaining data were used for testing. The enhanced CXR images containing only soft tissue information were obtained. Third, the neural network model with a residual cascade was used for the super-resolution reconstruction of low-resolution bone-suppressed CXR images. The training and testing data consisted of 1,200 and 100 CXR images, respectively. To evaluate the new strategy, improved visual geometry group (VGG)-16 and ResNet-18 models were used for the COVID-19 classification task of 2,767 CXR images. The accuracy of the multistrategy enhanced CXR images was verified through comparative experiments with various enhancement images. In terms of quantitative verification, 8-fold cross-validation was performed on the bone suppression model. In terms of evaluating the COVID-19 classification, the CXR images obtained by the improved method were used to train 2 classification models.

Results

Compared with other methods, the CXR images obtained based on the proposed model had better performance in the metrics of peak signal-to-noise ratio and root mean square error. The super-resolution CXR images of bone suppression obtained based on the neural network model were also anatomically close to the real CXR images. Compared with the initial CXR images, the classification accuracy rates of the internal and external testing data on the VGG-16 model increased by 5.09% and 12.81%, respectively, while the values increased by 3.51% and 18.20%, respectively, for the ResNet-18 model. The numerical results were better than those of the single-enhancement, double-enhancement, and no-enhancement CXR images.

Conclusions

The multistrategy enhanced CXR images can help to classify COVID-19 more accurately than the other existing methods.

Improving radiomic model reliability using robust features from perturbations for head-and-neck carcinoma

Background

Using high robust radiomic features in modeling is recommended, yet its impact on radiomic model is unclear. This study evaluated the radiomic model’s robustness and generalizability after screening out low-robust features before radiomic modeling. The results were validated with four datasets and two clinically relevant tasks.

Materials and methods

A total of 1,419 head-and-neck cancer patients’ computed tomography images, gross tumor volume segmentation, and clinically relevant outcomes (distant metastasis and local-regional recurrence) were collected from four publicly available datasets. The perturbation method was implemented to simulate images, and the radiomic feature robustness was quantified using intra-class correlation of coefficient (ICC). Three radiomic models were built using all features (ICC &gt; 0), good-robust features (ICC &gt; 0.75), and excellent-robust features (ICC &gt; 0.95), respectively. A filter-based feature selection and Ridge classification method were used to construct the radiomic models. Model performance was assessed with both robustness and generalizability. The robustness of the model was evaluated by the ICC, and the generalizability of the model was quantified by the train-test difference of Area Under the Receiver Operating Characteristic Curve (AUC).

Results

The average model robustness ICC improved significantly from 0.65 to 0.78 (P&lt; 0.0001) using good-robust features and to 0.91 (P&lt; 0.0001) using excellent-robust features. Model generalizability also showed a substantial increase, as a closer gap between training and testing AUC was observed where the mean train-test AUC difference was reduced from 0.21 to 0.18 (P&lt; 0.001) in good-robust features and to 0.12 (P&lt; 0.0001) in excellent-robust features. Furthermore, good-robust features yielded the best average AUC in the unseen datasets of 0.58 (P&lt; 0.001) over four datasets and clinical outcomes.

Conclusions

Including robust only features in radiomic modeling significantly improves model robustness and generalizability in unseen datasets. Yet, the robustness of radiomic model has to be verified despite building with robust radiomic features, and tightly restricted feature robustness may prevent the optimal model performance in the unseen dataset as it may lower the discrimination power of the model.

Lung Subregion Partitioning by Incremental Dose Intervals Improves Omics-Based Prediction for Acute Radiation Pneumonitis in Non-Small-Cell Lung Cancer Patients

Purpose: To evaluate the effectiveness of features obtained from our proposed incremental-dose-interval-based lung subregion segmentation (IDLSS) for predicting grade ≥ 2 acute radiation pneumonitis (ARP) in lung cancer patients upon intensity-modulated radiotherapy (IMRT). (1) Materials and Methods: A total of 126 non-small-cell lung cancer patients treated with IMRT were retrospectively analyzed. Five lung subregions (SRs) were generated by the intersection of the whole lung (WL) and five sub-regions receiving incremental dose intervals. A total of 4610 radiomics features (RF) from pre-treatment planning computed tomographic (CT) and 213 dosiomics features (DF) were extracted. Six feature groups, including WL-RF, WL-DF, SR-RF, SR-DF, and the combined feature sets of WL-RDF and SR-RDF, were generated. Features were selected by using a variance threshold, followed by a Student t-test. Pearson’s correlation test was applied to remove redundant features. Subsequently, Ridge regression was adopted to develop six models for ARP using the six feature groups. Thirty iterations of resampling were implemented to assess overall model performance by using the area under the Receiver-Operating-Characteristic curve (AUC), accuracy, precision, recall, and F1-score. (2) Results: The SR-RDF model achieved the best classification performance and provided significantly better predictability than the WL-RDF model in training cohort (Average AUC: 0.98 ± 0.01 vs. 0.90 ± 0.02, p < 0.001) and testing cohort (Average AUC: 0.88 ± 0.05 vs. 0.80 ± 0.04, p < 0.001). Similarly, predictability of the SR-DF model was significantly stronger than that of the WL-DF model in training cohort (Average AUC: 0.88 ± 0.03 vs. 0.70 ± 0.030, p < 0.001) and in testing cohort (Average AUC: 0.74 ± 0.08 vs. 0.65 ± 0.06, p < 0.001). By contrast, the SR-RF model significantly outperformed the WL-RF model only in the training set (Average AUC: 0.93 ± 0.02 vs. 0.85 ± 0.03, p < 0.001), but not in the testing set (Average AUC: 0.79 ± 0.05 vs. 0.77 ± 0.07, p = 0.13). (3) Conclusions: Our results demonstrated that the IDLSS method improved model performance for classifying ARP with grade ≥ 2 when using dosiomics or combined radiomics-dosiomics features.

Function-Wise Dual-Omics analysis for radiation pneumonitis prediction in lung cancer patients

Purpose: This study investigates the impact of lung function on radiation pneumonitis prediction using a dual-omics analysis method.

Methods: We retrospectively collected data of 126 stage III lung cancer patients treated with chemo-radiotherapy using intensity-modulated radiotherapy, including pre-treatment planning CT images, radiotherapy dose distribution, and contours of organs and structures. Lung perfusion functional images were generated using a previously developed deep learning method. The whole lung (WL) volume was divided into function-wise lung (FWL) regions based on the lung perfusion functional images. A total of 5,474 radiomics features and 213 dose features (including dosiomics features and dose-volume histogram factors) were extracted from the FWL and WL regions, respectively. The radiomics features (R), dose features (D), and combined dual-omics features (RD) were used for the analysis in each lung region of WL and FWL, labeled as WL-R, WL-D, WL-RD, FWL-R, FWL-D, and FWL-RD. The feature selection was carried out using ANOVA, followed by a statistical F-test and Pearson correlation test. Thirty times train-test splits were used to evaluate the predictability of each group. The overall average area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, and f1-score were calculated to assess the performance of each group.

Results: The FWL-RD achieved a significantly higher average AUC than the WL-RD group in the training (FWL-RD: 0.927 ± 0.031, WL-RD: 0.849 ± 0.064) and testing cohorts (FWL-RD: 0.885 ± 0.028, WL-RD: 0.762 ± 0.053, p < 0.001). When using radiomics features only, the FWL-R group yielded a better classification result than the model trained with WL-R features in the training (FWL-R: 0.919 ± 0.036, WL-R: 0.820 ± 0.052) and testing cohorts (FWL-R: 0.862 ± 0.028, WL-R: 0.750 ± 0.057, p < 0.001). The FWL-D group obtained an average AUC of 0.782 ± 0.032, obtaining a better classification performance than the WL-D feature-based model of 0.740 ± 0.028 in the training cohort, while no significant difference was observed in the testing cohort (FWL-D: 0.725 ± 0.064, WL-D: 0.710 ± 0.068, p = 0.54).

Conclusion: The dual-omics features from different lung functional regions can improve the prediction of radiation pneumonitis for lung cancer patients under IMRT treatment. This function-wise dual-omics analysis method holds great promise to improve the prediction of radiation pneumonitis for lung cancer patients.

Pharmacological inhibition of eIF2alpha phosphorylation by integrated stress response inhibitor (ISRIB) ameliorates vascular calcification in rats

Vascular calcification (VC) is an independent risk factor for cardiovascular events and all-cause mortality with the absence of current treatment. This study aimed to investigate whether eIF2alpha phosphorylation inhibition could ameliorate VC. VC in rats was induced by administration of vitamin D3 (3×10(5) IU/kg, intramuscularly) plus nicotine (25 mg/kg, intragastrically). ISRIB (0.25 mg/kg·week), an inhibitor of eIF2alpha phosphorylation, ameliorated the elevation of calcium deposition and ALP activity in calcified rat aortas, accompanied by amelioration of increased SBP, PP, and PWV. The decreased protein levels of calponin and SM22alpha, and the increased levels of RUNX2 and BMP2 in calcified aorta were all rescued by ISRIB, while the increased levels of the GRP78, GRP94, and C/EBP homologous proteins in rats with VC were also attenuated. Moreover, ISRIB could prevent the elevation of eIF2alpha phosphorylation and ATF4, and partially inhibit PERK phosphorylation in the calcified aorta. These results suggested that an eIF2alpha phosphorylation inhibitor could ameliorate VC pathogenesis by blocking eIF2alpha/ATF4 signaling, which may provide a new target for VC prevention and treatment.

THE INCREASED PLASMA LEVELS OF INTERMEDIN IN PATIENTS WITH TYPE 2 DIABETES MELLITUS

Context

Intermedin (IMD) is the member of calcitonin gene-related peptide family, and tightly associated with type 2 diabetes mellitus (T2DM). The change of plasma IMD levels in T2DM is still unknown.

Objective

We aimed to investigate the plasma levels of IMD in patients with T2DM.

Design

Fortyone patients with T2DM who were hospitalized in the endocrinology department of Civil Aviation General Hospital from January 2012 to June 2015 were enrolled, and 44 volunteers were selected as the control group.

Subjects and Methods

Plasma level of IMD was detected by ELISA. Diagnostic value of IMD was analyzed by area under the receiver operating characteristic (ROC) curve (AUC).

Results

The plasma level of IMD in T2DM group was higher than that in the healthy control group, whereas smoking or cardiovascular complications did no influence the IMD levels. IMD levels were correlated with BMI, DBP, triglyceride, uric acid, urea nitrogen, fasting and 2 hours postprandial blood glucose, and HbA1C. The greatest value of AUC for IMD was only 58.73%.

Conclusions

Although plasma levels of IMD were increased in patients with T2DM, the very low diagnostic value of IMD for T2DM might not be used for the disease diagnosis.

Building reliable radiomic models using image perturbation

Radiomic model reliability is a central premise for its clinical translation. Presently, it is assessed using test–retest or external data, which, unfortunately, is often scarce in reality. Therefore, we aimed to develop a novel image perturbation-based method (IPBM) for the first of its kind toward building a reliable radiomic model. We first developed a radiomic prognostic model for head-and-neck cancer patients on a training (70%) and evaluated on a testing (30%) cohort using C-index. Subsequently, we applied the IPBM to CT images of both cohorts (Perturbed-Train and Perturbed-Test cohort) to generate 60 additional samples for both cohorts. Model reliability was assessed using intra-class correlation coefficient (ICC) to quantify consistency of the C-index among the 60 samples in the Perturbed-Train and Perturbed-Test cohorts. Besides, we re-trained the radiomic model using reliable RFs exclusively (ICC > 0.75) to validate the IPBM. Results showed moderate model reliability in Perturbed-Train (ICC: 0.565, 95%CI 0.518–0.615) and Perturbed-Test (ICC: 0.596, 95%CI 0.527–0.670) cohorts. An enhanced reliability of the re-trained model was observed in Perturbed-Train (ICC: 0.782, 95%CI 0.759–0.815) and Perturbed-Test (ICC: 0.825, 95%CI 0.782–0.867) cohorts, indicating validity of the IPBM. To conclude, we demonstrated capability of the IPBM toward building reliable radiomic models, providing community with a novel model reliability assessment strategy prior to prospective evaluation.

Multi-Organ Omics-Based Prediction for Adaptive Radiation Therapy Eligibility in Nasopharyngeal Carcinoma Patients Undergoing Concurrent Chemoradiotherapy

Purpose

To investigate the role of different multi-organ omics-based prediction models for pre-treatment prediction of Adaptive Radiotherapy (ART) eligibility in patients with nasopharyngeal carcinoma (NPC).

Methods and Materials

Pre-treatment contrast-enhanced computed tomographic and magnetic resonance images, radiotherapy dose and contour data of 135 NPC patients treated at Hong Kong Queen Elizabeth Hospital were retrospectively analyzed for extraction of multi-omics features, namely Radiomics (R), Morphology (M), Dosiomics (D), and Contouromics (C), from a total of eight organ structures. During model development, patient cohort was divided into a training set and a hold-out test set in a ratio of 7 to 3 via 20 iterations. Four single-omics models (R, M, D, C) and four multi-omics models (RD, RC, RM, RMDC) were developed on the training data using Ridge and Multi-Kernel Learning (MKL) algorithm, respectively, under 10-fold cross validation, and evaluated on hold-out test data using average area under the receiver-operator-characteristics curve (AUC). The best-performing single-omics model was first determined by comparing the AUC distribution across the 20 iterations among the four single-omics models using two-sided student t-test, which was then retrained using MKL algorithm for a fair comparison with the four multi-omics models.

Results

The R model significantly outperformed all other three single-omics models (all p-value<0.0001), achieving an average AUC of 0.942 (95%CI: 0.938-0.946) and 0.918 (95%CI: 0.903-0.933) in training and hold-out test set, respectively. When trained with MKL, the R model (R_MKL) yielded an increased AUC of 0.984 (95%CI: 0.981-0.988) and 0.927 (95%CI: 0.905-0.948) in training and hold-out test set respectively, while demonstrating no significant difference as compared to all studied multi-omics models in the hold-out test sets. Intriguingly, Radiomic features accounted for the majority of the final selected features, ranging from 64% to 94%, in all the studied multi-omics models.

Conclusions

Among all the studied models, the Radiomic model was found to play a dominant role for ART eligibility in NPC patients, and Radiomic features accounted for the largest proportion of features in all the multi-omics models.

A Dual-supervised Deformation Estimation Model (DDEM) for constructing ultra-quality 4D-MRI based on a commercial low-quality 4D-MRI for liver cancer radiation therapy

BACKGROUND

Most available 4D-MRI techniques are limited by insufficient image quality and long acquisition times or require specially designed sequences or hardware that are not available in the clinic. These limitations have greatly hindered the clinical implementation of 4D-MRI.

PURPOSE

This study aims to develop a fast ultra-quality (UQ) 4D-MRI reconstruction method using a commercially available 4D-MRI sequence and dual-supervised deformation estimation model (DDEM).

METHODS

Thirty-nine patients receiving radiotherapy for liver tumors were included. Each patient was scanned using a TWIST-VIBE MRI sequence to acquire 4D-MR images. They also received 3D T1-/T2-weighted MRI scans as prior images and UQ 4D-MRI at any instant was considered a deformation of them. A DDEM was developed to obtain a 4D deformable vector field (DVF) from 4D-MRI data, and the prior images were deformed using this 4D-DVF to generate UQ 4D-MR images. The registration accuracies of the DDEM, VoxelMorph (normalized cross-correlation (NCC) supervised), VoxelMorph (end-to-end point error (EPE) supervised), and the parametric total variation (pTV) algorithm were compared. Tumor motion on UQ 4D-MRI was evaluated quantitatively using region-of-interest (ROI) tracking errors, while image quality was evaluated using the contrast-to-noise ratio (CNR), lung-liver edge sharpness, and perceptual blur metric (PBM).

RESULTS

The registration accuracy of the DDEM was significantly better than those of VoxelMorph (NCC supervised), VoxelMorph (EPE supervised) and the pTV algorithm (all, p < 0.001), with an inference time of 69.3 ± 5.9 ms. UQ 4D-MRI yielded ROI tracking errors of 0.79 ± 0.65, 0.50 ± 0.55, and 0.51 ± 0.58 mm in the superior-inferior, anterior-posterior, and mid-lateral directions, respectively. From the original 4D-MRI to UQ 4D-MRI, the CNR increased from 7.25 ± 4.89 to 18.86 ± 15.81; the lung-liver edge full-width-at-half-maximum decreased from 8.22 ± 3.17 to 3.65 ± 1.66 mm in the in-plane direction and from 8.79 ± 2.78 to 5.04 ± 1.67 mm in the cross-plane direction, and the PBM decreased from 0.68 ± 0.07 to 0.38 ± 0.01.

CONCLUSION

This novel DDEM method successfully generated UQ 4D-MR images based on a commercial 4D-MRI sequence. It shows great promise for improving liver tumor motion management during radiation therapy. This article is protected by copyright. All rights reserved.

Deep learning-based bone suppression in chest radiographs using CT-derived features: a feasibility study

Background

Bone suppression of chest X-ray holds the potential to improve the accuracy of target localization in image-guided radiation therapy (IGRT). However, the training dataset for bone suppression is limited because of the scarcity of bone-free radiographs. This study aims to develop a deep learning-based bone suppression method using CT-derived features to reduce the reliance on the bone-free dataset.

Methods

In this study, 59 high-resolution lung CT scans were processed to generate the lung digital radiographs (DRs), bone DRs, and bone-free DRs, for the training and internal validation of the proposed cascade convolutional neural network (CCNN). A three-stage image processing framework (CT segmentation, DR simulation, and feature expansion) was developed to expand simulated lung DRs with different weightings of bone intensity. The CCNN consists of a bone detection network and a bone suppression network. In external validation, the trained CCNN was evaluated using 30 chest radiographs. The synthesized bone-suppressed radiographs were compared with the bone-suppressed reference in terms of peak signal-to-noise ratio (PSNR), mean absolute error (MAE), structural similarity index measure (SSIM), and Spearman's correlation coefficient. Furthermore, the effectiveness of the proposed feature expansion method and CCNN model were assessed via the ablation experiment and replacement experiment, respectively.

Results

Evaluation on real chest radiographs showed that the bone-suppressed chest radiographs closely matched with the bone-suppressed reference, achieving an accuracy of MAE =0.0087±0.0030, SSIM =0.8458±0.0317, correlation of 0.9554±0.0170, and PNSR of 20.86±1.60. After removing the feature expansion from the CCNN model, the performance decreased in terms of MAE (0.0294±0.0093, -237.9%), SSIM (0.7747±0.0.0416, -8.4%), correlation (0.8772±0.0271, -8.2%), and PSNR (15.53±1.42, -25.5%) metrics.

Conclusions

We successfully demonstrated a novel deep learning-based bone suppression method using CT-derived features to reduce the reliance on the bone-free dataset. Implementation of the feature expansion procedures resulted in a remarkable reinforcement of the model performance. For the application of target localization in IGRT, the clinical testing of the proposed method in the context of radiation therapy is a necessary procedure to move from theory into practice.

A review of deep learning-based three-dimensional medical image registration methods

Medical image registration is a vital component of many medical procedures, such as image-guided radiotherapy (IGRT), as it allows for more accurate dose-delivery and better management of side effects. Recently, the successful implementation of deep learning (DL) in various fields has prompted many research groups to apply DL to three-dimensional (3D) medical image registration. Several of these efforts have led to promising results. This review summarized the progress made in DL-based 3D image registration over the past 5 years and identify existing challenges and potential avenues for further research. The collected studies were statistically analyzed based on the region of interest (ROI), image modality, supervision method, and registration evaluation metrics. The studies were classified into three categories: deep iterative registration, supervised registration, and unsupervised registration. The studies are thoroughly reviewed and their unique contributions are highlighted. A summary is presented following a review of each category of study, discussing its advantages, challenges, and trends. Finally, the common challenges for all categories are discussed, and potential future research topics are identified.

Virtual Contrast-enhanced Magnetic Resonance Images Synthesis for Patients With Nasopharyngeal Carcinoma Using Multimodality-guided Synergistic Neural Network

PURPOSE

To investigate a novel deep-learning network that synthesizes virtual contrast-enhanced T1-weighted (vceT1w) magnetic resonance images (MRI) from multimodality contrast-free MRI for patients with nasopharyngeal carcinoma (NPC).

METHODS AND MATERIALS

This article presents a retrospective analysis of multiparametric MRI, with and without contrast enhancement by gadolinium-based contrast agents (GBCAs), obtained from 64 biopsy-proven cases of NPC treated at Hong Kong Queen Elizabeth Hospital. A multimodality-guided synergistic neural network (MMgSN-Net) was developed to leverage complementary information between contrast-free T1-weighted and T2-weighted MRI for vceT1w MRI synthesis. Thirty-five patients were randomly selected for model training, whereas 29 patients were selected for model testing. The synthetic images generated from MMgSN-Net were quantitatively evaluated against real GBCA-enhanced T1-weighted MRI using a series of statistical evaluating metrics, which include mean absolute error (MAE), mean squared error (MSE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). Qualitative visual assessment between the real and synthetic MRI was also performed. Effectiveness of our MMgSN-Net was compared with 3 state-of-the-art deep-learning networks, including U-Net, CycleGAN, and Hi-Net, both quantitatively and qualitatively. Furthermore, a Turing test was performed by 7 board-certified radiation oncologists from 4 hospitals for assessing authenticity of the synthesized vceT1w MRI against the real GBCA-enhanced T1-weighted MRI.

RESULTS

Results from the quantitative evaluations demonstrated that our MMgSN-Net outperformed U-Net, CycleGAN and Hi-Net, yielding the top-ranked scores in averaged MAE (44.50 ± 13.01), MSE (9193.22 ± 5405.00), SSIM (0.887 ± 0.042), and PSNR (33.17 ± 2.14). Furthermore, the mean accuracy of the 7 readers in the Turing tests was determined to be 49.43%, equivalent to random guessing (ie, 50%) in distinguishing between real GBCA-enhanced T1-weighted and synthetic vceT1w MRI. Qualitative evaluation indicated that MMgSN-Net gave the best approximation to the ground-truth images, particularly in visualization of tumor-to-muscle interface and the intratumor texture information.

CONCLUSIONS

Our MMgSN-Net was capable of synthesizing highly realistic vceT1w MRI that outperformed the 3 comparable state-of-the-art networks.

Multi-contrast four-dimensional magnetic resonance imaging (MC-4D-MRI): Development and initial evaluation in liver tumor patients

PURPOSE

To develop a novel multi-contrast four-dimensional magnetic resonance imaging (MC-4D-MRI) technique that expands single image contrast 4D-MRI to a spectrum of native and synthetic image contrasts and to evaluate its feasibility in liver tumor patients.

METHODS AND MATERIALS

The MC-4D-MRI technique integrates multi-parametric MRI fusion, 4D-MRI, and deformable image registration (DIR) techniques. The fusion technique consists of native MRI as input, image pre-processing, fusion algorithm, adaptation, and fused multi-contrast MRI as output. Four-dimensional deformation vector fields (4D-DVF) were generated from an original T2/T1-w 4D-MRI by deforming end-of-inhalation (EOI) to nine other phase volumes via DIR. The 4D-DVF were applied to multi-contrast MRI to generate a spectrum of 4D-MRI in different image contrasts. The MC-4D-MRI technique was evaluated in five liver tumor patients on tumor contrast-to-noise ratio (CNR), internal target volume (ITV) contouring consistency, diaphragm motion range, and tumor motion trajectory; and in digital anthropomorphic phantoms on 4D-DIR introduced errors in tumor motion range, centroid location, extent, and volume.

RESULTS

MC-4D-MRI consisting of 4D-MRIs in native image contrasts (T1-w, T2-w, and T2/T1-w) and synthetic image contrasts, such as tumor-enhanced contrast (TEC) were generated in five liver tumor patients. Patient tumor CNR increased from 2.6 ± 1.8 in the T2/T1-w MRI, to -4.4 ± 2.4, 6.6 ± 3.0, and 9.6 ± 3.9 in the T1-w, T2-w, and TEC MRI, respectively. Patient ITV inter-observer mean Dice similarity coefficient (mDSC) increased from 0.65 ± 0.10 in the original T2/T1-w 4D-MRI, to 0.76 ± 0.14, 0.77 ± 0.12, and 0.86 ± 0.05 in the T1-w, T2-w, and TEC 4D-MRI, respectively. Patient diaphragm motion range absolute differences between the three new 4D-MRIs and original T2/T1-w 4D-MRI were 1.2 ± 1.3, 0.3 ± 0.7, and 0.5 ± 0.5 mm, respectively. Patient tumor displacement phase-averaged absolute differences between the three 4D-MRIs and the original 4D-MRI were 0.72 ± 0.33, 0.62 ± 0.54, and 0.74 ± 0.43 mm in the superior-inferior (SI) direction, and 0.59 ± 0.36, 0.51 ± 0.30, and 0.50 ± 0.24 mm in the anterior-posterior (AP) direction, respectively. In the digital phantoms, phase-averaged absolute tumor centroid shift caused by the 4D-DIR were at or below 0.5 mm in SI, AP, and left-right (LR) directions.

CONCLUSION

We developed an MC-4D-MRI technique capable of expanding single image contrast 4D-MRI along a new dimension of image contrast. Initial evaluations in liver tumor patients showed enhancements in image contrast variety, tumor contrast, and ITV contouring consistencies using MC-4D-MRI. The technique might offer new perspectives on the image contrast of MRI and 4D-MRI in MR-guided radiotherapy.

Respiratory deformation registration in 4D-CT/cone beam CT using deep learning

BACKGROUND

To investigate the feasibility of using a supervised convolutional neural network (CNN) to register phase-to-phase deformable vector field of lung 4D-CT/4D-cone beam CT for 4D dose accumulation, contour propagation, motion modeling, or target verification.

METHODS

We built a CNN-based deep learning method to register the deformation field directly between phases of patients' 4D-CT or 4D-cone beam CT. The input consists of patch pairs of two phases, while the output is the corresponding deformation field that registers the patch pairs. The centers of the patch pairs were uniformly sampled across the lung, and the size of the patches was chosen to cover the range of the respiratory motion. The network was trained to generate deformation field that matches with the reference deformation field generated by VelocityAI (Varian). The network is structured with four convolutional layers, two average pooling layers, and two fully connected layers. Half mean squared error is applied to guide the study as loss function. Nine patients with eleven sets of 4D-CT/cone beam CT image volumes were used for training and testing. The performance of the network was validated with intra-patient and inter-patient setups.

RESULTS

Registered images were generated with Velocity deformation field and the CNN deformation field, respectively. Main anatomic features such as the main vessels and the diaphragm matched well between two deformed images. In the diaphragm region, the coefficients of cross-correlation, root mean squared error, and structural similarity index measure (SSIM) between deformed images registered by CNN and VelocityAI was calculated. The cross-correlation was above 0.9 for all the intra-patient cases.

CONCLUSIONS

Patch-based deep learning methods achieved comparable deformable registration accuracy as VelocityAI. Compared to VelocityAI, the deep learning method is fully automatic and faster without user dependency, which makes it more preferable in clinical applications.

Expression of PD-L1 for predicting response to immune checkpoint inhibitors in metastatic urothelial carcinoma: a systematic review and meta-analysis

Background

We conducted this meta-analysis and systematic literature review to study the ability of PD-L1 to predict objective response in patients with urothelial cancer treated with PD-1/PD-L1 inhibitors.

Methods

Relevant studies of PD-1 or PD-L1 inhibitors in urothelial cancer that reported objective response rate (orr) based on PD-L1 expression status in PubMed, embase, and the Cochrane Library were retrieved. Efficacy of PD-L1 expression status in predicting orr and the efficacy, safety of PD-1 and PD-L1 drugs were analyzed.

Results

Studies were divided into ≥1%, ≥5%, and ≥25% based on PD-L1 positivity threshold, and the patients were grouped into PD-L1 positive and negative. In all 3 expression thresholds, patients with positive PD-L1 expression were more likely to experience an objective response [≥1% threshold odds ratio (or): 1.74; 95% confidence interval (ci): 1.20 to 2.53; ≥5% threshold or: 2.74; 95% ci: 2.01 to 3.724; ≥25% threshold or: 7.13; 95% ci: 2.38 to 21.40] in comparison with patients with negative PD-L1 expression. Of the 3 thresholds, the ≥25% threshold was better in predicting orr (1.74 vs. 2.93 vs. 7.13; p < 0.0001). The ≥1% PD-L1 threshold had a relatively high sensitivity in predicting orr; the ≥5% PD-L1 threshold was better for specificity. Sensitivity was higher at the ≥25% threshold than at the other two thresholds, but specificity was lower. Further, we found that there is no statistically significant difference in efficacy between PD-1 and PD-L1 drugs.

Conclusions

Urothelial cancer patients with PD-L1 positive expression responded better than PD-L1 negative patients did, and a threshold of ≥5% or greater for PD-L1 expression might predict positive clinical response.

MiR-7a ameliorates spinal cord injury by inhibiting neuronal apoptosis and oxidative stress

OBJECTIVE

The aim of this study was to investigate the therapeutic effect of microRNA-7a (miR-7a) on spinal cord injured rats and to explore its underlying mechanism in vivo.

MATERIALS AND METHODS

The spinal cord injury (SCI) model was first established in adult rats. The epicenter of the lesion was treated with miR-7a mimics via intrathecal injection. The Basso-Beattie-Bresnahan (BBB) locomotor rating scale was used to evaluate the functional recovery of hindlimbs in rats within 4 weeks following SCI. Western blotting and qPCR were utilized to detect the apoptosis and oxidative stress in rats treated with or without miR-7a. In addition, the neuron survival and neuro-filament amount were determined using immunofluorescence.

RESULTS

After SCI and miR-7a treatment, the locomotor recovery of treated rats was significantly improved when compared with rats without treatment. The mitochondrial disorder and cell death were significantly reduced in miR-7a treated rats. Meanwhile, the nuclear transcription factor-κB (NF-κB) pathway was significantly reduced as well. Contrarily, the expression of anti-apoptotic protein Bcl-2 and NF-κB inhibitor I-κB was remarkably elevated in miR-7a treated rats. In addition, up-regulation of miR-7a rescued neurons and maintained the neural structure.

CONCLUSIONS

The up-regulation of miR-7a alleviated the injury-induced oxidative stress and inhibited apoptosis by down-regulating NF-κB pathway in SCI rats.

Improved quantitative assessment of HBV-associated liver fibrosis using second-harmonic generation microscopy with feature selection

BACKGROUND AND AIM

Quantitative assessments of liver fibrosis using second-harmonic generation/two-photon excited fluorescence microscopy provide greater sensitivity and accuracy than collagen proportionate area while eliminating operator-dependent variation in the staining process. In conjunction with sophisticated image analysis algorithms and feature selection, we might reduce the computation cost in future and narrow down the candidates for further clinical studies.

METHODS

We sampled a total of 244 liver specimens from patients with hepatitis B viral infections who underwent liver biopsy or liver resection at the National Taiwan University Hospital. The samples were then imaged using a Genesis (HistoIndex Pte. Ltd, Singapore) system, wherein second-harmonic generation microscopy was used to visualize collagen, and two-photon excited fluorescence microscopy was used to visualize other cell structures. We used 100 morphological features extracted from the images to assess correlations with METAVIR fibrosis scores.

RESULTS

Out of 100 quantitative measurements, 76 showed significant correlation with METAVIR scoring, thereby enabling the statistical discrimination of patients in various stages of the disease. These 76 features were also narrowed down by the nonlinear test to 10 candidate measurements, which can be further investigated in detail.

CONCLUSIONS

Our experimental results showed that the model with 10 selected features can beat the one with second-harmonic generation only, and performed equivalently well compared the model with 76 features, especially for early-stage discrimination. Features presenting significant correlation were used to fit a single combined index in order to predict pathological staging, thereby making it possible to reveal incremental progress during treatment.

Immune cell metabolism in autoimmunity

Immune metabolism is a rapidly moving field. While most of the research has been conducted to define the metabolism of healthy immune cells in the mouse, it is recognized that the overactive immune system that drives autoimmune diseases presents metabolic abnormalities that provide therapeutic opportunities, as well as a means to understand the fundamental mechanisms of autoimmune activation more clearly. Here, we review recent publications that have reported how the major metabolic pathways are affected in autoimmune diseases, with a focus on rheumatic diseases.

Abstract P4-02-12: Comparison of RT-qPCR with consensus immunohistochemistry by three pathologists for ER, PR, HER2 and Ki-67 in Chinese breast cancer patients

Background

During the diagnostic work-up of breast carcinomas, immunohistochemistry (IHC) is the currently used method for assessing the expression of estrogen- (ER) and progesterone-receptors (PR), human epidermal growth factor receptor 2 (HER2) as well as of Ki-67 as a marker of tumor cell proliferation. In this study, we analyzed the concordance of these four breast cancer biomarkers between the RT-qPCR- and IHC-based (evaluated by three independent pathologists) determinations.

Methods

The expression of ER/ESR1, PR/PGR, HER2/ERBB2 and Ki-67/MKI67 was determined in 269 FFPE breast cancer samples with tumor content &gt;20% from Chinese patients. For IHC, the samples were freshly cut, stained and assessed by three independent pathologists using the same scoring methods in a blinded fashion (positivity defined as: ER/PR ≥1%, HER2 &gt;2+ and Ki-67 ≥20%). Measurement of the markers on the mRNA level was done on total RNA extracts prepared from whole tissue sections from the same FFPE blocks using the CE-marked RT-qPCR based IVD MammaTyper® on a Cobas® z480 qPCR cycler. IHC assessments of the three pathologists were compared to each other with regard to concordance of positive/negative results. Subsequently, agreement of RT-qPCR and IHC results for each marker and in samples in which the three pathologists had a consensus positive/negative IHC result was determined. Furthermore, we compared the MammaTyper® assessments from a subset of whole FFPE sections to data obtained from paired samples enriched for invasive carcinoma via macrodissection.

Results

From the 269 samples, 256 were available for final analysis. When excluding cases with discordant IHC callings between the three pathologists (6.0% for ER; 7.4% PR; 4.1% Her2; 17.1% Ki-67)) the concordance to the RT-qPCR determination and consensus IHC-based analysis displayed an excellent agreement for ER (OPA: 95.4%, PPA: 97.5%, NPA: 91.5%, Kappa: 0.897), PR (OPA: 91.1%, PPA: 89.6%, NPA: 93.1%, Kappa: 0.820) and HER2 (OPA: 97.1%, PPA: 91.9%, NPA: 100.0%, Kappa: 0.936). For cancer MKI67 mRNA and Ki-67 protein expression, a lower but still good concordance was found (OPA: 90.1%, PPA: 91.8%, NPA: 83.3%, Kappa: 0.707). In addition, we could demonstrate an excellent agreement of quantitative RT-qPCR measurements between whole surface and paired tumor-enriched samples in 99 Chinese breast cancer patients with R2 of 0.927 for ER, 0.926 for PR, 0.923 for HER2 and 0.908 for KI67. Even under highly standardized IHC scoring conditions, the discordance rates in the RT-qPCR marker callings with 0.0% for ESR1, 5.0% for PGR, 3.0% for ERBB2, 13.1% for MKI67 were lower than disagreements by three pathologists on the identical slide.

Conclusion

Standardized determination of the breast cancer biomarkers ER, PR, HER2 and Ki-67 on the mRNA level shows high concordance to a consensus IHC determined by three experienced pathologists indicating that RT-qPCR may be a valid alternative for determining the four breast cancer biomarkers. In line with previous research we could show on a large set of samples that macrodissection is not required for reliable assessment of the four breast cancer markers in clinical FFPE samples.

Citation Format: Teng X, Li X, Xu S, Zhang J, Hartmann K, Laible M, Hipfel R, Bai Y, Ba X, Wu Z, Wirtz RM, Liu S, Ugur S. Comparison of RT-qPCR with consensus immunohistochemistry by three pathologists for ER, PR, HER2 and Ki-67 in Chinese breast cancer patients [abstract]. In: Proceedings of the 2018 San Antonio Breast Cancer Symposium; 2018 Dec 4-8; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2019;79(4 Suppl):Abstract nr P4-02-12.

[The multicenter study on the registration and follow-up of low anticoagulation therapy for the heart valve operation in China]

OBJECTIVE

To investigate the optimal anticoagulation methods and monitoring strategy for Chinese patients undergoing heart valve replacement, which is potentially quite different from western populations.

METHODS

In this multicenter prospective cohort study, the anticoagulation and monitoring strategy data was acquired from 25 773 in-hospital patients in 35 medical centers and 20 519 patients in outpatient clinic in 11 medical centers from January 1st, 2011 to December 31th, 2015.

RESULTS

As for in-hospital patients, mean age of study population was (48.6±11.2) years old; main etiology of valve pathology was rheumatic (87.5%) origin among study cohort; 94.8% of study population received mechanical valve implantation; international normalized ratio (INR) monitoring (in all the study centers) and low-intensity anticoagulation strategy (31 hospitals chose target INR range of 1.5-2.5, and actual values of INR among 89.2% of 100 069 in-hospital monitoring samples were 1.5-2.5), with mean actual INR values of 1.84±0.53, and warfarin dosage of (2.82±0.93) mg/d were widely adopted among the study centers; strategies of in-hospital warfarin administration were similar in all the study centers; complication rates of low-intensity anticoagulation strategy were low in severe hemorrhage (0.02%), thrombosis (0.05%), and thromboembolism (0.05%) events, without anticoagulation-related death.As for 18 974 outpatient clinic patients, the follow-up rate was 92.47%, with a total of 30 012 patient-years (Pty). Anticoagulation-related morbidity and mortality rates were 0.67% and 0.15% Pty; major hemorrhage morbidity and mortality rates were 0.25% and 0.13% Pty; thromboembolism morbidity and mortality rates were 0.45% and 0.03% Pty.The mean dosage of warfarin daily dosage was (2.85±1.23) mg/d and INR value was 1.82±0.57.No significant regional difference in the intensity of anticoagulation therapy was noted during the study.

CONCLUSIONS

INR can be used as a normalized indicator for intensity of anticoagulation therapy in China.The optimal anticoagulation intensity with INR range from 1.5 to 2.5 is safe and effective for Chinese patients with heart valve replacement, and there is no significant regional difference in the intensity of anticoagulation therapy.

[Management of valgus or varus knee deformity with fixator assist nailing technique and distal femur osteotomy]

OBJECTIVE

To discuss the result of treating valgus or varus knee deformity with fixator assist nailing (FAN) technique and distal femur osteotomy(DFO).

METHODS

In this retrospective study, 14 patients with 17 limbs, 12 valgus and 5 varus knee deformity were treated with DFO and FAN. The average age of the patients was 23 (17-44) years . The unilateral external fixator was mounted on the lateral side of femur, the minimal invasive distal femoral osteotomy was performed. After the deformity was corrected, the intramedully nail was inserted to fix the femur. None of the patients need bone autograft. The preoperation and postoperation lateral distal femur angle (LDFA), mechanical axis deviation (MAD) and range of motion (ROM) were measured and analyzed.

RESULTS

All the 14 patients were followed-up for 12-72 months (average 34 months). The osteotomy site united in 3-5 months (average 3.5 months) postoperatively. According to Paley's functional scores, 12 patients were excellent, 2 patients were good. We achieved desired postoperative MAD ( from medial 15 mm to lateral 10 mm) in 15 limbs of 12 patients. The LDFA in 11 limbs was corrected to normal (84°-90°). The ROM was not significantly changed before and after operation in the both groups. No infection or neuro-vascular injury occurred.

CONCLUSION

The FAN technique is an effective method to treat valgus knee or varus knee deformity in young patients with DFO.

Inhalation of recombinant adenovirus expressing granulysin protects mice infected with Mycobacterium tuberculosis

Granulysin is a cytolytic molecule with perforin and granzymes that is expressed by activated human CTLs, NK and γδ T cells, and it has broad antimicrobial activity, including to drug-sensitive and drug-resistant Mycobacterium tuberculosis. We hypothesized that approaches facilitating the expression of granulysin in M. tuberculosis-infected host cells in the lung may provide a novel treatment strategy for pulmonary TB. In this study, a recombinant replication-deficient adenovirus serotype 5-based rAdhGLi was constructed that expressed human granulysin in the cytosol of the U937 and RAW264.7 macrophage-like cell lines as confirmed by western blotting and co-localization technology using indirect immunofluorescence staining. Ninety-six hours after both cell lines were infected with M. tuberculosis, acid-fast staining and enumeration demonstrated that rAdhGLi-treated cells had a lower colony-forming units (CFU) of intracellular bacteria than culture medium or AdNull controls. Granulysin was only expressed in the lung and not in other organs following inhalation of rAdhGLi. In particular, immunocompetent BALB/c mice or SCID mice intranasally infected with ~200 CFU of virulent M. tuberculosis H37Rv intranasally were treated with rAdhGLi, and they showed decreased bacterial loads in the lung when compared with phosphate-buffered saline or AdNull controls. Importantly, a clear dose-dependent rAdhGLi treatment efficacy was found in infected BALB/c mice, with the most significant reduction in lung bacteria obtained in BALB/c mice treated with 10(9) plaque-forming units of rAdhGLi without any pathological changes. Our study indicates that rAdhGLi may be used as a novel and efficient treatment strategy with the capability to directly kill intracellular M. tuberculosis.

Secretory clusterin is upregulated in rats with pulmonary arterial hypertension induced by systemic-to-pulmonary shunts and exerts important roles in pulmonary artery smooth muscle cells

AIM

Phenotype modification of pulmonary artery smooth muscle cells (PASMCs) (excessive proliferation, migration and impaired apoptosis) plays central roles in pulmonary vascular remodelling of pulmonary arterial hypertension (PAH); however, the potential mechanism and contributing factors involved in the phenotype alteration in PASMCs are still not completely elucidated. This study attempted to investigate the expression pattern of secretory clusterin (sCLU), a prosurvival protein, in systemic-to-pulmonary shunt-induced PAH rats and the potential roles of sCLU in pulmonary vascular remodelling.

METHODS

An original rat model of systemic-to-pulmonary shunt-induced PAH was established by combined surgery as we previously reported. Lung tissues were harvested at specific time points for real-time polymerase chain reaction, Western blot and immunohistochemisty analysis; meanwhile, plasma was collected for enzyme-linked immunosorbent assay. Cell culture experiments were performed using cultured human PASMCs (HPASMCs).

RESULTS

Expression of sCLU was significantly increased in lungs exposed to systemic-to-pulmonary shunt. Moreover, plasma sCLU levels were markedly elevated with the progression of PAH in rats and also presented a positive correlation with pulmonary hemodynamic indices. In vitro cell culture assay indicated that sCLU expression and secretion increased with the phenotype modification of HPASMCs; furthermore, sCLU promoted HPASMCs proliferation, migration and apoptosis resistance, at least in part, via Erk1/2 and Akt signalling pathways.

CONCLUSION

These results demonstrate that sCLU is functionally an important phenotype modulator of PASMCs, and its upregulation in lung tissues may exert a deteriorative role in pulmonary vascular remodelling.

Correlation analysis of the progesterone-induced sperm acrosome reaction rate and the fertilisation rate in vitro

In this study, we aimed to investigate whether progesterone-induced acrosome reaction (AR) rate could be an indicator for fertilisation rate in vitro. Twenty-six couples with unexplained infertility and undergoing in vitro fertilisation (IVF) treatment were involved. On the oocytes retrieval day after routine IVF, residual sperm samples were collected to receive progesterone induction (progesterone group) or not (control group). AR rate was calculated and fertilisation rate was recorded. The correlation between progesterone-induced AR and fertilisation rate and between sperm normal morphology and 3PN (tripronuclear) were analysed using the Spearman correlation analysis. The AR rate of progesterone group was statistically higher than that of the control group (15.6 ± 5.88% versus 9.66 ± 5.771%, P < 0.05), but not significantly correlated with fertilisation rate (r = -0.053, P > 0.01) or rate of high-quality embryo development (r = -0.055, P > 0.01). Normal sperm morphology also showed no significant correlation with the amount of 3PN zygotes (r = 0.029, P > 0.01), rate of 3PN zygotes production (r = 0.20, P > 0.01), rate of 3PN embryo development (r = -0.406, P > 0.01), fertilisation rate (r = -0.148, P > 0.01) or progesterone-induced AR rate (r = 0.214, P > 0.01). Progesterone can induce AR in vitro significantly; however, the progesterone-induced AR may not be used to indicate fertilisation rate.