Optimizing the radiomics-machine-learning model based on non-contrast enhanced CT for the simplified risk categorization of thymic epithelial tumors: A large cohort retrospective study.

PURPOSE: This study aimed to establish and compare the radiomics machine learning (ML) models based on non-contrast enhanced computed tomography (NECT) and clinical features for predicting the simplified risk categorization of thymic epithelial tumors (TETs). EXPERIMENTAL DESIGN: A total of 509 patients with pathologically confirmed TETs from January 2009 to May 2018 were retrospectively enrolled, consisting of 238 low-risk thymoma (LRT), 232 high-risk thymoma (HRT), and 39 thymic carcinoma (TC), and were divided into training (n = 433) and testing cohorts (n = 76) according to the admission time. Volumes of interest (VOIs) covering the whole tumor were manually segmented on preoperative NECT images. A total of 1218 radiomic features were extracted from the VOIs, and 4 clinical variables were collected from the hospital database. Fourteen ML models, along with varied feature selection strategies, were used to establish triple-classification models using the radiomic features (radiomic models), while clinical-radiomic models were built after combining with the clinical variables. The diagnostic accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC) of radiologist assessment, the radiomic and clinical-radiomic models were evaluated on the testing cohort. RESULTS: The Support Vector Machine (SVM) clinical-radiomic model demonstrated the highest AUC of 0.841 (95% CI 0.820 to 0.861) on the cross-validation result and reached an AUC of 0.844 (95% CI 0.793 to 0.894) in the testing cohort. For the one-vs-rest question of LRT vs HRT + TC, the sensitivity, specificity, and accuracy reached 80.00%, 63.41%, and 71.05%, respectively. For HRT vs LRT + TC, they reached 60.53%, 78.95%, and 69.74%. For TC vs LRT + HRT they reached 33.33%, 98.63%, and 96.05%, respectively. Compared with the radiomic models, superior diagnostic efficacy was demonstrated for most clinical-radiomics models, and the AUC of the Bernoulli Naive Bayes model was significantly improved. Radiologist2's assessment achieved a higher AUC of 0.813 (95% CI: 0.756-0.8761) than other radiologists, which was slightly lower than the SVM clinical-radiomic model. Combined with other evaluation indicators, SVM, as the best ML model, demonstrated the potential of predicting the simplified risk categorization of TETs with superior predictive performance to that of radiologists' assessment. CONCLUSION: Most of the ML models are promising in predicting the simplified TETs risk categorization with superior efficacy to that of radiologists' assessment, especially the SVM models, demonstrated the integration of ML with NECT may be valuable in aiding the diagnosis and treatment planning.

Predicting pathological subtypes and stages of thymic epithelial tumors using DWI: value of combining ADC and texture parameters.

OBJECTIVES: To explore the value of combining apparent diffusion coefficients (ADC) and texture parameters from diffusion-weighted imaging (DWI) in predicting the pathological subtypes and stages of thymic epithelial tumors (TETs). METHODS: Fifty-seven patients with TETs confirmed by pathological analysis were retrospectively enrolled. ADC values and optimal texture feature parameters were compared for differences among low-risk thymoma (LRT), high-risk thymoma (HRT), and thymic carcinoma (TC) by one-way ANOVA, and between early and advanced stages of TETs were tested using the independent samples t test. Receiver operating characteristic (ROC) curve analysis was performed to determine the differentiating efficacy. RESULTS: The ADC values in LRT and HRT were significantly higher than the values in TC (p = 0.004 and 0.001, respectively), also in early stage, values were significantly higher than ones in advanced stage of TETs (p < 0.001). Among all texture parameters analyzed in order to differentiate LRT from HRT and TC, the V312 achieved higher diagnostic efficacy with an AUC of 0.875, and combination of ADC and V312 achieved the highest diagnostic efficacy with an AUC of 0.933, for differentiating the LRT from HRT and TC. Furthermore, combination of ADC and V1030 achieved a relatively high differentiating ability with an AUC of 0.772, for differentiating early from advanced stages of TETs. CONCLUSIONS: Combination of ADC and DWI texture parameters improved the differentiating ability of TET grades, which could potentially be useful in clinical practice regarding the TET evaluation before treatment. KEY POINTS: • DWI texture analysis is useful in differentiating TET subtypes and stages. • Combination of ADC and DWI texture parameters may improve the differentiating ability of TET grades. • DWI texture analysis could potentially be useful in clinical practice regarding the TET evaluation before treatment.

Iodine Quantification Using Dual-Energy Computed Tomography for Differentiating Thymic Tumors.

The aim of the study was to explore the efficacy of iodine quantification with dual-energy computed tomography (DECT) in differentiating thymoma, thymic carcinoma, and thymic lymphoma. MATERIALS AND METHODS: Fifty-seven patients with pathologically confirmed low-risk thymoma (n = 16), high-risk thymoma (n = 15), thymic carcinoma (n = 14), and thymic lymphoma (n = 12) underwent chest contrast-enhanced DECT scan were enrolled in this study. Tumor DECT parameters including iodine-related Hounsfield unit (IHU), iodine concentration (IC), mixed HU (MHU), and iodine ratio in dual phase, slope of energy spectral HU curve (λ), and virtual noncontrast (VNC) were compared for differences among 4 groups by one-way analysis of variance. Receiver operating characteristic curve was used to determine the efficacy for differentiating the low-risk thymoma from other thymic tumor by defined parameters. RESULTS: According to quantitative analysis, dual-phase IHU, IC, and MHU values in patients with low-risk thymoma were significantly increased compared with patients with high-risk thymoma, thymic carcinoma, and thymic lymphoma (P < 0.05/4).The venous phase IHU value yielded the highest performance with area under the curve of 0.893, 75.0% sensitivity, and 89.7% specificity for differentiating the low-risk thymomas from high-risk thymomas or thymic carcinoma at the cutoff value of 34.3 HU. When differentiating low-risk thymomas from thymic lymphoma, the venous phase IC value obtained the highest diagnostic efficacy with the area under the curve of 0.969, and sensitivity, specificity, and cutoff value were 87.5%, 100.0%, and 1.25 mg/mL, respectively. CONCLUSIONS: Iodine quantification with DECT may be useful for differentiating the low-risk thymomas from other thymic tumors.

Incidence and clinical variable inter-relationships of thymic epithelial tumors in northwest China.

BACKGROUND: Thymic epithelial tumors (TETs) are the most common primary thymus tumors, but neither the possible ethnical/regional differences in the incidence of TETs nor the inter-relationships among the clinical variables has been revealed in northwest China. METHODS: A retrospective chart review was performed among pathologically confirmed TET patients from January 2004 to December 2015 in a tertiary general hospital of northwest China and the incidence, clinical features and the inter-relationships among clinical variables were analyzed. RESULTS: A total of 603 pathologically confirmed TETs patients (age range, 5-78 years; 308 males) were enrolled and the most common lesion location was anterior mediastinum (98.5%), among them, 192 (31.8%) had myasthenia gravis (MG). Twenty-six (5.7%), 112 (24.6%), 83 (18.2%), 137 (30.1%), 74 (16.3%), and 23 (5.1%) patients fell into the World Health Organization (WHO) type A, AB, B1, B2, B3 and thymic carcinoma (TC), respectively. The incidence of TETs was slightly higher in the female population and the age group of 40-60 years old. In addition, MG predominantly coexisted with WHO types A-B3 TETs and the TETs with MG were smaller than those without MG. The correct diagnosis rates were 42.3% (77 out of 182), 61.1% (127 out of 208), 89.3% (250 out of 280) and 75.0% (3 out of 4) for chest X-ray, non-contrast computed tomography (CT), contrast CT scan and magnetic resonance imaging (MRI), respectively. CONCLUSIONS: Distinct gender and age differences exist in the incidence of TETs and the A-B3 TETs are closely related with MG. Contrast CT scan plays more important role in diagnosing TETs.

Early total care pattern for intertrochanteric fracture of femur in the elderly / 中国骨伤

<p><b>OBJECTIVE</b>To evaluate clinical results of early total care (ETC) treatment for elderly patients with intertrochanteric femur fractures.</p><p><b>METHODS</b>Clinical data of 106 elderly patients with intertrochanteric fracture treated from January 2012 and February 2015 were retrospectively studied. According to whether receiving the early total care mode, the patients were divided into 2 groups, 34 cases were diagnosed and treated with early total care pattern (ETC group), including 14 males and 20 females with an average age of (74.88 ± 4.38) years old ranging from 70 to 86. According to Evans types, 4 cases were type I, 5 cases were type II, 13 cases were type III, 11 cases were type IV, 1 case was type V. Seventy-two patients were treated with conventional trauma method (conventional group), including 35 males and 37 females with an average age of (74.46 ± 3.63) years old ranging from 70 to 85. According to Evans type, 8 cases were type I ,13 cases were type II, 25 cases were type III, 25 cases were type IV, and 1 case was type V. All fractures were treated with proximal femoral nails anti-rotation (PFNA). Operative time, hospital stays, leaving bed time, complications, cases of death at 1 year after operation, postoperative Harris score at 12 months were observed and compared.</p><p><b>RESULTS</b>All patients were followed up, the time of ETC group ranged from 9 to 18 months with an average of 13.29 ± 1.51, and the time in conventional group ranged from 12 to 16 months with an average 12.93 ± 1.15, while there was no significant difference between two groups in time of following-up (t = 1.368, P = 0.174). There was no significant meaning in cases of death between ETC group (2 cases) and conventional group (8 cases). Three cases occurred complications in ETC group, and 20 cases in conventional group,there was obvious meaning between two groups (χ² = 0.739, P = 0.318). Operative time,hospital stays,leaving bed time in ETC group respectively was (2.03 ± 0.67) d, (15.41 ± 2.87) d and (3.62 ± 0.74) d; while in conventional group respectively was (4.17 ± 1.59) d, (20.11 ± 4.24) d and (5.35 ± 1.22) d; there were significant differences between two groups in operative time, hospital stays, leaving bed time. Postoperative Harris scores at 12 months in ETC group was (82.32 ± 4.56), and (79.24 ± 5.52) in conventional group, there was obvious meaning between two groups (t = 2.833, P = 0.006).</p><p><b>CONCLUSION</b>ETC pattern is a novel method for diagnosis and treatment of intertrochanteric femur fractures in elderly, it could shorten operative time, hospital stays, leaving bed time, decrease complications and promote recovery of function.</p>

Asymmetrical osteotomy for elderly degenerative lumbar kyphoscoliosis / 中国骨伤

<p><b>OBJECTIVE</b>To investigate the safety and efficacy of asymmetrical osteotomy in treating elderly degenerative lumbar kyphoscoliosis.</p><p><b>METHODS</b>From January 2010 to June 2012,17 elder patients with degenerative lumbar kyphoscoliosis were treated with asymmetrical osteotomy,their data were retrospectively analyzed. There were 6 males and 11 females with an average age of 61 years old (57 to 72). Total length spinal X-ray was performed for all patients before operation,and sagittal and coronal balance were analyzed. The follow-up time was 1 year at least. VAS score, thoracolumbar Cobb angle and pelvic parameters were analyzed.</p><p><b>RESULTS</b>All patients were operated successfully. The average operation time was 210 min (180 to 260) and intraoperative blood loss was 1,100 ml (750 to 2 200). At 1 year after operation, VAS score decreased from preoperative 7.0 +/- 1.5 to 1.1 +/- 0.6; lumbar lordosis (LL) corrected from (1.9 +/- 9.6) degrees to (35.2 +/- 6.7) degrees; thoracic kyphosis (TK) increased from (26.3 +/- 9.7) degrees to (32.5 +/- 11.2) degrees; lumbar scoliosis decreased from (25.1 +/- 11.0) degrees to (7.9 +/- 3.6) degrees; pelvic tilt (PT) restored from (33.0 +/- 10.1) degrees to (25.3 +/- 8.9) degrees; sacral slope (SS) increased from (13.9 +/- 9.7) degrees to (27.2 +/- 11.0) degrees; sagittal balance improved from (10.3 +/- 8.1) cm to (3.1 +/- 4.2) cm,and coronal balance improved from (3.5 +/- 2.1) cm to (1.3 +/- 1.1) cm. There was statistically significant difference above data between preoperation and postoperation.</p><p><b>CONCLUSION</b>Asymmetrical osteotomy can not only correct scoliosis deformity, but also restore lumbar lordosis, and may safely and effectively solve the problem of elderly degenerative lumbar kyphoscoliosis.</p>