Multi-institutional validation of a radiomics signature for identification of postoperative progression of soft tissue sarcoma.

BACKGROUND: To develop a magnetic resonance imaging (MRI)-based radiomics signature for evaluating the risk of soft tissue sarcoma (STS) disease progression. METHODS: We retrospectively enrolled 335 patients with STS (training, validation, and The Cancer Imaging Archive sets, n = 168, n = 123, and n = 44, respectively) who underwent surgical resection. Regions of interest were manually delineated using two MRI sequences. Among 12 machine learning-predicted signatures, the best signature was selected, and its prediction score was inputted into Cox regression analysis to build the radiomics signature. A nomogram was created by combining the radiomics signature with a clinical model constructed using MRI and clinical features. Progression-free survival was analyzed in all patients. We assessed performance and clinical utility of the models with reference to the time-dependent receiver operating characteristic curve, area under the curve, concordance index, integrated Brier score, decision curve analysis. RESULTS: For the combined features subset, the minimum redundancy maximum relevance-least absolute shrinkage and selection operator regression algorithm + decision tree classifier had the best prediction performance. The radiomics signature based on the optimal machine learning-predicted signature, and built using Cox regression analysis, had greater prognostic capability and lower error than the nomogram and clinical model (concordance index, 0.758 and 0.812; area under the curve, 0.724 and 0.757; integrated Brier score, 0.080 and 0.143, in the validation and The Cancer Imaging Archive sets, respectively). The optimal cutoff was - 0.03 and cumulative risk rates were calculated. DATA CONCLUSION: To assess the risk of STS progression, the radiomics signature may have better prognostic power than a nomogram/clinical model.

Normal bone marrow signal characteristics in whole-body diffusion-weighted images of amateur marathon runners.

Background: Marathon training can reverse bone marrow conversion; however, little is known about the normal bone marrow whole-body diffusion-weighted imaging (WB-DWI) signal characteristics of amateur marathon runners. If marathon training can cause diffuse hyperintensity of bone marrow on WB-DWI is essential for correctly interpreting the diffusion-weighted (DW) images. This study sought to evaluate the WB-DWI signal characteristics of normal bone marrow in amateur marathon runners. Methods: In this prospective cross-sectional study, 30 amateur marathon runners who had trained for over 3 years for regular or half-marathon races and had a running frequency of more than 20 days a month at a distance of more than 100 km per month from the Chengde Marathon Outdoor Sports Association in Hebei, China, and 30 age- and gender-matched, healthy volunteers (the control group) who had no long-term heavy-load sports history were recruited between April 2021 to September 2021. All the subjects underwent WB-DWI (b-value: 0, 800 s/mm2) and lumbar vertebral transverse relaxation time (T2) mapping. The bone marrow WB-DWI signal characteristics were analyzed visually and statistically by chi-square (χ2) tests. The apparent diffusion coefficient (ADC), DWI signal intensity, and T2 values of the bone marrow were quantitatively and statistically analyzed by the independent sample t-test and Mann-Whitney U test. Results: No subjects were excluded from the study. The bone marrow of 30 of the 60 subjects (aged 30-50 years) showed diffuse hyperintensity in the DW images. However, in all 60 subjects, the humeral heads, femoral heads, and great trochanters had low signals. The frequency of diffuse bone marrow DWI hyperintensity was significantly higher in the male amateur marathon runners (50%) than the male controls (5%, P=0.003), but no such significant difference was found between the female amateur marathon runners (100%) and female controls (90%, P>0.99). The DW signal intensity ratios of bone marrow to muscle (SIRBM-muscle) were significantly higher in the male amateur marathon runners than the male controls in the thoracic vertebrae (4.68 vs. 3.57, P=0.021), lumbar vertebrae (4.49 vs. 3.01, P<0.001), sacrum (3.67 vs. 2.62, P=0.002), and hip (3.45 vs. 2.50, P=0.002), but were only significantly higher in the female amateur marathon runners than the female controls in the thoracic vertebrae (7.69 vs. 5.87, P=0.029) and hip (4.76 vs. 3.92, P=0.004). The mean T2 values of the lumbar vertebrae were significantly higher in the male amateur marathon runners than the male controls (116.76 vs. 97.63 ms, P=0.001), but no such significant difference was observed between the female amateur marathon runners and the corresponding controls (118.58 vs. 124.10 ms, P=0.386). Conclusions: Marathon training resulted in diffuse hyperintensity in the bone marrow based on WB-DWI in 50% of the male amateur marathon runners aged 30-50 years. Thus, when WB-DWI is used for bone marrow disease screening, marathon training history should be considered to avoid false-positive diagnoses.

Monitoring early responses to neoadjuvant chemotherapy and the factors affecting neoadjuvant chemotherapy responses in primary osteosarcoma.

Background: This study sought to predict the early responses to neoadjuvant chemotherapy (NACT) of patients with primary conventional osteosarcoma (COS) using the apparent diffusion coefficient (ADC) and to evaluate the factors affecting the tumor necrosis rate (TNR). Methods: The data of 41 patients who underwent magnetic resonance imaging (MRI) and diffusion-weighted imaging sequence scans before NACT, 5 days after the end of the first phase of NACT, after the end of the whole course of chemotherapy, were prospectively collected. ADC1 refers to the ADC before chemotherapy, ADC2 refers to the ADC after the first phase of chemotherapy, and ADC3 refers to the ADC before surgery. The change in values before and after the first phase of chemotherapy was calculated as follows: ADC2-1 = ADC2 - ADC1. The change in values before and after the last phase of chemotherapy was calculated as follows: ADC3-1 = ADC3 - ADC1. The change in values after the first phase and the last phase of chemotherapy was calculated as follows: ADC3-2 = ADC3 - ADC2. We recorded the patient characteristics, including age, gender, pulmonary metastasis, alkaline phosphatase (ALP), and lactate dehydrogenase (LDH). The patients were divided into the following 2 groups based on their histological TNR after postoperative: (I) the good-response group (≥90% necrosis, n=13) and (II) the poor-response group (<90% necrosis, n=28). Changes in the ADCs were compared between the good-response and poor-response groups. The different ADCs between the 2 groups were compared, and a receiver operating characteristic analysis was performed. A correlation analysis was performed to assess the correlations of the clinical features, laboratory features, and different ADCs with patients' histopathological responses to NACT. Results: The ADC2 (P<0.001), ADC3 (P=0.004), ADC3-1 (P=0.008), ADC3-2 (P=0.047), and ALP before NACT (P=0.019) were significantly higher in the good-response group than in the poor-response group. The ADC2 [area under the curve (AUC) =0.723; P=0.023], ADC3 (AUC =0.747; P=0.012), and ADC3-1 (AUC =0.761; P=0.008) showed good diagnostic performance. Based on the univariate binary logistic regression analysis, the ADC2 (P=0.022), ADC3 (P=0.009), ADC2-1 (P=0.041), and ADC3-1 (P=0.014) were correlated with the TNR. However, based on the multivariate analysis, these parameters were not significantly correlated with the TNR. Conclusions: In patients with COS who are undergoing neoadjuvant chemotherapy, the ADC2 is a promisingindicator for predicting tumor response to chemotherapy in early.

Comparing the blood oxygen level-dependent fluctuation power of benign and malignant musculoskeletal tumors using functional magnetic resonance imaging.

Purpose: The aim of this study is to compare the blood oxygen level-dependent (BOLD) fluctuation power in 96 frequency points ranging from 0 to 0.25 Hz between benign and malignant musculoskeletal (MSK) tumors via power spectrum analyses using functional magnetic resonance imaging (fMRI). Materials and methods: BOLD-fMRI and T1-weighted imaging (T1WI) of 92 patients with benign or malignant MSK tumors were acquired by 1.5-T magnetic resonance scanner. For each patient, the tumor-related BOLD time series were extracted, and then, the power spectrum of BOLD time series was calculated and was then divided into 96 frequency points. A two-sample t-test was used to assess whether there was a significant difference in the powers (the "power" is the square of the BOLD fluctuation amplitude with arbitrary unit) of each frequency point between benign and malignant MSK tumors. The receiver operator characteristic (ROC) analysis was used to assess the diagnostic capability of distinguishing between benign and malignant MSK tumors. Results: The result of the two-sample t-test showed that there was significant difference in the power between benign and malignant MSK tumor at frequency points of 58 (0.1508 Hz, P = 0.036), 59 (0.1534 Hz, P = 0.032), and 95 (0.247 Hz, P = 0.014), respectively. The ROC analysis of mean power of three frequency points showed that the area of under curve is 0.706 (P = 0.009), and the cutoff value is 0.73130. If the power of the tumor greater than or equal to 0.73130 is considered the possibility of benign tumor, then the diagnostic sensitivity and specificity values are 83% and 59%, respectively. The post hoc analysis showed that the merged power of 0.1508 and 0.1534 Hz in benign MSK tumors was significantly higher than that in malignant ones (P = 0.014). The ROC analysis showed that, if the benign MSK tumor was diagnosed with the power greater than or equal to the cutoff value of 1.41241, then the sensitivity and specificity were 67% and 68%, respectively. Conclusion: The mean power of three frequency points at 0.1508, 0.1534, and 0.247 Hz may potentially be a biomarker to differentiate benign from malignant MSK tumors. By combining the power of 0.1508 and 0.1534 Hz, we could better detect the difference between benign and malignant MSK tumors with higher specificity.

Research on imbalance machine learning methods for MR[Formula: see text]WI soft tissue sarcoma data.

BACKGROUND: Soft tissue sarcoma is a rare and highly heterogeneous tumor in clinical practice. Pathological grading of the soft tissue sarcoma is a key factor in patient prognosis and treatment planning while the clinical data of soft tissue sarcoma are imbalanced. In this paper, we propose an effective solution to find the optimal imbalance machine learning model for predicting the classification of soft tissue sarcoma data. METHODS: In this paper, a large number of features are first obtained based on [Formula: see text]WI images using the radiomics methods.Then, we explore the methods of feature selection, sampling and classification, get 17 imbalance machine learning models based on the above features and performed extensive experiments to classify imbalanced soft tissue sarcoma data. Meanwhile, we used another dataset splitting method as well, which could improve the classification performance and verify the validity of the models. RESULTS: The experimental results show that the combination of extremely randomized trees (ERT) classification algorithm using SMOTETomek and the recursive feature elimination technique (RFE) performs best compared to other methods. The accuracy of RFE+STT+ERT is 81.57% , which is close to the accuracy of biopsy, and the accuracy is 95.69% when using another dataset splitting method. CONCLUSION: Preoperative predicting pathological grade of soft tissue sarcoma in an accurate and noninvasive manner is essential. Our proposed machine learning method (RFE+STT+ERT) can make a positive contribution to solving the imbalanced data classification problem, which can favorably support the development of personalized treatment plans for soft tissue sarcoma patients.

Deep Learning Radiomics Nomogram to Predict Lung Metastasis in Soft-Tissue Sarcoma: A Multi-Center Study.

Objectives: To build and evaluate a deep learning radiomics nomogram (DLRN) for preoperative prediction of lung metastasis (LM) status in patients with soft tissue sarcoma (STS). Methods: In total, 242 patients with STS (training set, n=116; external validation set, n=126) who underwent magnetic resonance imaging were retrospectively enrolled in this study. We identified independent predictors for LM-status and evaluated their performance. The minimum redundancy maximum relevance (mRMR) method and least absolute shrinkage and selection operator (LASSO) algorithm were adopted to screen radiomics features. Logistic regression, decision tree, random forest, support vector machine (SVM), and adaptive boosting classifiers were compared for their ability to predict LM. To overcome the imbalanced distribution of the LM data, we retrained each machine-learning classifier using the synthetic minority over-sampling technique (SMOTE). A DLRN combining the independent clinical predictors with the best performing radiomics prediction signature (mRMR+LASSO+SVM+SMOTE) was established. Area under the receiver operating characteristics curve (AUC), calibration curves, and decision curve analysis (DCA) were used to assess the performance and clinical applicability of the models. Result: Comparisons of the AUC values applied to the external validation set revealed that the DLRN model (AUC=0.833) showed better prediction performance than the clinical model (AUC=0.664) and radiomics model (AUC=0.799). The calibration curves indicated good calibration efficiency and the DCA showed the DLRN model to have greater clinical applicability than the other two models. Conclusion: The DLRN was shown to be an accurate and efficient tool for LM-status prediction in STS.

Deep learning radiomic nomogram to predict recurrence in soft tissue sarcoma: a multi-institutional study.

OBJECTIVES: To evaluate the performance of a deep learning radiomic nomogram (DLRN) model at predicting tumor relapse in patients with soft tissue sarcomas (STS) who underwent surgical resection. METHODS: In total, 282 patients who underwent MRI and resection for STS at three independent centers were retrospectively enrolled. In addition, 113 of the 282 patients received additional contrast-enhanced MRI scans. We separated the participants into a development cohort and an external test cohort. The development cohort consisted of patients from one center and the external test cohort consisted of patients from two other centers. Two MRI-based DLRNs for prediction of tumor relapse after resection of STS were established. We universally tested the DLRNs and compared them with other prediction models constructed by using widespread adopted predictors (i.e., staging systems and Ki67) instead of radiomics features. RESULTS: The DLRN1 model incorporated plain MRI-based radiomics signature into the clinical data, and the DLRN2 model integrated radiomics signature extracted from plain and contrast-enhanced MRI with the clinical predictors. Across both study sets, the two MRI-based DLRNs had relatively better prognostic capability (C index ≥ 0.721 and median AUC ≥ 0.746; p < 0.05 compared with most other models and predictors) and less opportunity for prediction error (integrated Brier score ≤ 0.159). The decision curve analysis indicates that the DLRNs have greater benefits than staging systems, Ki67, and other models. We selected appropriate cutoff values for the DLRNs to divide STS recurrence into three risk strata (low, medium, and high) and calculated those groups' cumulative risk rates. CONCLUSION: The DLRNs were shown to be a reliable and externally validated tool for predicting STS recurrence by comparing with other prediction models. KEY POINTS: • The prediction of a high recurrence rate of STS before emergence of local recurrence can help to determine whether more active treatment should be implemented. • Two MRI-based DLRNs for prediction of tumor relapse were shown to be a reliable and externally validated tool for predicting STS recurrence. • We used the DLRNs to divide STS recurrence into three risk strata (low, medium, and high) to facilitate more targeted postoperative management in the clinic.

The signal intensity characteristics of normal bone marrow in diffusion weighted imaging at various menstrual status women.

PURPOSE: Diffuse hyperintensities of the bone marrow in whole-body diffusion-weighted (DW) imaging (DWI) have been encountered more frequently in females aged 21-50 compared to elder females or men. Therefore, we aimed to visually evaluate DWI among pre-, peri- and postmenopausal women and to verify whether it correlates also quantitatively with hormonal status. METHOD: The prospective study was approved by our institutional review board and informed consent was obtained in a total of 70 healthy premenopausal, perimenopausal, and postmenopausal women aged 40-58 years from February 2017 to October 2017. The bone marrow DW imaging signal characteristics were visually evaluated in comparison to the erector spinae muscle. Imaging data were acquired using a 1.5 T MRI yielding signal intensity values from a DWI-pulse sequence (b-value of 800 s/mm2; apparent diffusion coefficient (ADC) maps from b-values of 0-800 s/mm2), and a T2 mapping sequence covering the L2-L4 lumbar vertebrae. Serous estradiol (E2), follicle stimulating hormone (FSH), and luteinizing hormone (LH) were measured through venous blood assay. The relationship of the mean DW signal intensity (SIDWI) with T2 values, female hormone level, and mean ADC were analyzed using Spearman's rho test. RESULTS: The proportion of diffuse DWI hyperintensities of the bone marrow was significantly higher in premenopausal (91% (21/23)) women compared to peri- (75% (18/24)) and postmenopausal (8% (2/23)) women. A positive correlation was observed for the mean SIDWI (median [interquartile range], 47.33 [30.14]) and mean T2 (mean ± SD, 121.01 ± 13.54) (r = 0.438, p < 0.001) as well as for the mean SIDWI and E2 (median [interquartile range], 52.45 [92.78]) (r = 0.407, p < 0.001). A negative correlation was observed for the mean SIDWI and serous FSH (median [interquartile range], 15.55 [42.08]) as well as for the mean SIDWI and serous LH (median [interquartile range], 6.96 [31.06]) (r = -0.557, p < 0.001; r = -0.535, p < 0.001; respectively), but no significant correlation was found for mean SIDWI and mean ADC (mean ± SD, 599.36 ± 82.70) (r = 0.099, p = 0.415). A negative correlation was also encountered for the mean T2 values and serous FSH (r = -0.339, p = 0.004) as well as for the mean T2 values and serous LH (r = -0.281, p = 0.018). CONCLUSIONS: The mean SIDWI correlates positively with mean T2 and serous E2 values, while there's no significant correlation with mean ADC, indicating that T2 shine-through effects might interfere with bone marrow signaling on DW images. Knowledge of the bone marrow signal characteristics changing in DW images in close relationship with menstrual status is essential to correctly interpret DWI in clinical practice.

Magnetic Resonance Imaging-Based Radiomics Nomogram for Prediction of the Histopathological Grade of Soft Tissue Sarcomas: A Two-Center Study.

BACKGROUND: Preoperative prediction of soft tissue sarcoma (STS) grade is important for treatment decisions. Therefore, formulation an STS grade model is strongly needed. PURPOSE: To develop and test an magnetic resonance imaging (MRI)-based radiomics nomogram for predicting the grade of STS (low-grade vs. high grade). STUDY TYPE: Retrospective POPULATION: One hundred and eighty patients with STS confirmed by pathologic results at two independent institutions were enrolled (training set, N = 109; external validation set, N = 71). FIELD STRENGTH/SEQUENCE: Unenhanced T1-weighted (T1WI) and fat-suppressed T2-weighted images (FS-T2WI) were acquired at 1.5 T and 3.0 T. ASSESSMENT: Clinical-MRI characteristics included age, gender, tumor-node-metastasis (TNM) stage, American Joint Committee on Cancer (AJCC) stage, progression-free survival (PFS), and MRI morphological features (ie, margin). Radiomics feature extraction were performed on T1WI and FS-T2WI images by minimum redundancy maximum relevance (MRMR) method and least absolute shrinkage and selection operator (LASSO) algorithm. The selected features constructed three radiomics signatures models (RS-T1， RS-FST2, and RS-Combined). Univariate and multivariate logistic regression analysis were applied for screening significant risk factors. Radiomics nomogram was constructed by incorporating the radiomics signature and risk factors. STATISTICAL TESTS: Clinical-MRI characteristics were performed by a univariate analysis. Model performances (discrimination, calibration, and clinical usefulness) were validated in the external validation set. The RS-T1 model, RS-FST2 model, and RS-Combined model had an area under curves (AUCs) of 0.645, 0.641, and 0.829, respectively, in the external validation set. The radiomics nomogram, incorporating significant risk factors and the RS-Combined model had AUCs of 0.916 (95%CI, 0.866-0.966, training set) and 0.879 (95%CI, 0.791-0.967, external validation set), and demonstrated good calibration and good clinical utility. DATA CONCLUSION: The proposed noninvasive MRI-based radiomics models showed good performance in differentiating low-grade from high-grade STSs. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2.

Coralloluteibacterium thermophilus sp. nov., A Gammaproteobacterium Isolated from an Oil Reservoir.

A Gram-negative, yellow-pigmented, aerobic bacterium, designated strain B51-30T, was isolated from oil-well production liquid in Baolige oilfield, China. The strain was able to grow at pH 6-10 (optimum at pH 7.5), in 0-6% (w/v) NaCl (optimum at 1%, w/v) at 15-55 °C (optimum at 45 °C). Cells of the isolate were non-motile and non-spore-forming rods. The major cellular fatty acids were iso-C15:0, iso-C11:0, iso-C11:0 3OH, iso-C17:1 ω9c, and iso-C17:0. Ubiquinone 8 was the predominant respiratory quinone. The major polar lipids consisted of phosphatidylethanolamine and diphosphatidylglycerol. The genomic DNA G+C content of the isolate was 70.6 mol%. Phylogenetic analysis based on 16S rRNA gene sequences revealed that strain B51-30T was most closely related to Coralloluteibacterium stylophorae KCTC 52167T (98.7% similarity). The two strains showed DNA-DNA relatedness values of 58.5%. Genotypic and phenotypic features indicate that strain B51-30T represents a novel species of the genus Coralloluteibacterium, for which the name Coralloluteibacterium thermophilus sp. nov. is proposed. The type strain is B51-30T (= CGMCC 1.13574T = KCTC 62780T).

Tumor Tissue Detection using Blood-Oxygen-Level-Dependent Functional MRI based on Independent Component Analysis.

Accurate delineation of gliomas from the surrounding normal brain areas helps maximize tumor resection and improves outcome. Blood-oxygen-level-dependent (BOLD) functional MRI (fMRI) has been routinely adopted for presurgical mapping of the surrounding functional areas. For completely utilizing such imaging data, here we show the feasibility of using presurgical fMRI for tumor delineation. In particular, we introduce a novel method dedicated to tumor detection based on independent component analysis (ICA) of resting-state fMRI (rs-fMRI) with automatic tumor component identification. Multi-center rs-fMRI data of 32 glioma patients from three centers, plus the additional proof-of-concept data of 28 patients from the fourth center with non-brain musculoskeletal tumors, are fed into individual ICA with different total number of components (TNCs). The best-fitted tumor-related components derived from the optimized TNCs setting are automatically determined based on a new template-matching algorithm. The success rates are 100%, 100% and 93.75% for glioma tissue detection for the three centers, respectively, and 85.19% for musculoskeletal tumor detection. We propose that the high success rate could come from the previously overlooked ability of BOLD rs-fMRI in characterizing the abnormal vascularization, vasomotion and perfusion caused by tumors. Our findings suggest an additional usage of the rs-fMRI for comprehensive presurgical assessment.

Characterizing the Blood Oxygen Level-Dependent Fluctuations in Musculoskeletal Tumours Using Functional Magnetic Resonance Imaging.

This study characterized the blood oxygen level-dependent (BOLD) fluctuations in benign and malignant musculoskeletal tumours via power spectrum analyses in pre-established low-frequency bands. BOLD MRI and T1-weighted imaging (T1WI) were collected for 52 patients with musculoskeletal tumours. Three ROIs were drawn on the T1WI image in the tumours' central regions, peripheral regions and neighbouring tissue. The power spectrum of the BOLD within each ROI was calculated and divided into the following four frequency bands: 0.01-0.027 Hz, 0.027-0.073 Hz, 0.073-0.198 Hz, and 0.198-0.25 Hz. ANOVA was conducted for each frequency band with the following two factors: the location of the region of interest (LoR, three levels: tumour "centre", "peripheral" and "healthy tissue") and tumour characteristic (TC, two levels: "malignant" and "benign"). There was a significant main effect of LoR in the frequencies of 0.073-0.198 Hz and 0.198-0.25 Hz. These data were further processed with post-hoc pair-wise comparisons. BOLD fluctuations at 0.073-0.198 Hz were stronger in the peripheral than central regions of the malignant tumours; however, no such difference was observed for the benign tumours. Our findings provide evidence that the BOLD signal fluctuates with spatial heterogeneity in malignant musculoskeletal tumours at the frequency band of 0.073-0.198 Hz.