Using T2-weighted magnetic resonance imaging-derived radiomics to classify cervical lymphadenopathy in children.

BACKGROUND: Cervical lymphadenopathy is common in children and has diverse causes varying from benign to malignant, their similar manifestations making differential diagnosis difficult. OBJECTIVE: This study aimed to investigate whether radiomic models using conventional magnetic resonance imaging (MRI) could classify pediatric cervical lymphadenopathy. METHODS: A total of 419 cervical lymph nodes from 146 patients, and encompassing four common etiologies (Kikuchi disease, reactive hyperplasia, suppurative lymphadenitis and malignancy), were randomly divided into training and testing sets in a ratio of 7:3. For each lymph node, 1,218 features were extracted from T2-weighted images. Then, the least absolute shrinkage and selection operator (LASSO) models were used to select the most relevant ones. Two models were built using a support vector machine classifier, one was to classify benign and malignant lymph nodes and the other further distinguished four different diseases. The performance was assessed by receiver operating characteristic curves and decision curve analysis. RESULTS: By LASSO, 20 features were selected to construct a model to distinguish benign and malignant lymph nodes, which achieved an area under the curve (AUC) of 0.89 and 0.80 in the training and testing sets, respectively. Sixteen features were selected to construct a model to distinguish four different cervical lymphadenopathies. For each etiology, Kikuchi disease, reactive hyperplasia, suppurative lymphadenitis, and malignancy, an AUC of 0.97, 0.91, 0.88, and 0.87 was achieved in the training set, and an AUC of 0.96, 0.80, 0.82, and 0.82 was achieved in the testing set, respectively. CONCLUSION: MRI-derived radiomic analysis provides a promising non-invasive approach for distinguishing causes of cervical lymphadenopathy in children.

Primary Endodermal Sinus Tumor of the Intraspinal Cavity: A Case Report and Review of the Literature.

Endodermal sinus tumor (EST) occurs most frequently in the gonads and is relatively rare in other sites, particularly in the spinal cavity. We report a 19-year-old woman who presented with back pain and weakness of both lower extremities who was found to have an EST in the spinal canal cavity. She had severely elevated serum alpha-fetoprotein (AFP) level at presentation. Magnetic resonance imaging (MRI) revealed the mass in the spinal canal. The tumor was excised. Serum AFP returned to normal after three cycles of chemotherapy. We describe the imaging findings and the macroscopic and microscopic features of this rare tumor. EST is a relatively rare malignant germ cell tumor that usually originates in the gonads and has poor prognosis. This is a rare case of the primary EST in the spinal canal. Radiologists need to be aware of the MRI appearance of extragonadal EST.

Multidimensional analysis using low-dose computed tomography to evaluate the severity of Mycoplasma pneumoniae pneumonia in children.

Background: It is unclear whether local pathological pulmonary changes truly reflect the severity of childhood Mycoplasma pneumoniae infection, which is characterized by rapid progress and potential mortality. This study multi-dimensionally analyzed low-dose computed tomography findings to assess the severity of Mycoplasma pneumoniae infection and predict its progress in such patients. Methods: In all, 752 children with Mycoplasma pneumoniae pneumonia (MPP) who underwent low-dose computed tomography examinations from February 2016 to July 2020 were retrospectively enrolled to conduct a cohort study. Clinical and radiological variables were analyzed using univariate analysis, and radiological variables were further analyzed using multivariable logistic regression in severe cases. Then, the correlation between the key computed tomography features and clinical symptoms, laboratory indicators, and medical costs were assessed using the chi-squared and Kruskal-Wallis H tests. Kaplan-Meier curves and Cox regression models were created to evaluate the correlations between the key computed tomography features, fever duration, and the length of hospital stay. Results: Of the 752 included patients, 16.2% (122/752) developed severe MPP. Atelectasis, pleural effusion, and lung consolidation occurred in 9.7% (73/752), 15.8% (119/752), and 90.3% (679/752) of patients, respectively. In addition to pleural effusion, the number of lobes of lung consolidation was the highest risk feature of severe MPP. Patients with consolidation in 2, 3, and 4 lobes had a 1.0-, 3.1-, and 7.5-fold increased risk of severe MPP, compared with patients with consolidation in fewer than 1 lobe. The duration of fever prior to admission had no effect on the proportions of the lobar consolidation (P=0.14) but did have significant effect on the incidence of pleural effusion (P=0.004). Levels of inflammatory markers and medical costs rose consistently with the increase in the number of lobar consolidations (P<0.001). After adjustments for pleural effusion, 1, 2, 3, and 4 lobes of consolidation remained positively associated with fever duration [1 lobe: hazard ratio (HR) =1.55, 95% CI: 1.10-2.18; 2 lobes: HR =1.65, 95% CI: 1.13-2.42l; 3 lobes: HR =1.82, 95% CI: 1.11-2.98; 4 lobes: HR =2.87, 95% CI: 1.25-6.61] compared to 0 lobes of consolidation. Compared to 0 lobes of consolidation, 1, 2, 3, and 4 lobes of consolidation were also positively correlated with the length of hospital stay (1 lobe: HR =2.24, 95% CI: 1.73-2.89; 2 lobes: HR =2.56, 95% CI: 1.91-3.43; 3 lobes: HR =2.87, 95% CI: 1.90-4.32; 4 lobes: HR =4.12, 95% CI: 2.01-8.46). Conclusions: Lobar consolidation is a stable and reliable computed tomography feature that can be used to assess the severity of MPP in children. Quantitative analysis of lobar consolidation can comprehensively and accurately predict the progression of Mycoplasma pneumoniae. Low-dose computed tomography is recommended for children with severe MPP with complicated courses.

The role of flexible bronchoscopy in children with Mycoplasma pneumoniae pneumonia.

PURPOSE: To explore the effectiveness of flexible bronchoscopy in pediatric Mycoplasma pneumoniae pneumonia (MPP). METHODS: This retrospective cohort study included children with MPP admitted between 2016 and 2019 in Shanghai. Tracheobronchial manifestations, etiologic findings, therapeutic effect, and health-economic indicators were assessed in bronchoscopy (plus bronchoalveolar lavage (BAL)) and non-bronchoscopy group. We used propensity-score matching and multivariable logistic regression to investigate the effect of bronchoscopy and BAL on disease recovery. RESULTS: In 900 children with MPP, 24/278 (8.6%) of those who underwent bronchoscopy had sputum plugs. Coinfection rate was four-fold enhanced by BAL (19.6% vs. 4.5%, p < 0.01) in patients with severe MPP (SMPP) and nearly doubled (10.8% vs. 5.9%, p = 0.03) in those without SMPP, compared with no BAL. Total of 224 (24.9%) patients had multilobar consolidation; after BAL, a significantly shorter lesion-resolution duration was observed on imaging (OR: 0.2, 95% CI: 0.0-0.7). However, longer fever duration (OR: 2.8, 95% CI: 1.7-4.8), hospital stay (OR: 3.1, 95% CI: 1.9-5.1), and higher costs were found in the bronchoscopy group than in the non-bronchoscopy group. CONCLUSIONS: Through BAL, coinfection may explain one-fifth of causes for SMPP. Bronchoscopy with BAL may increase the detection rate of pathogen and resolve pulmonary lesions in patients with multilobar consolidation. IMPACT: Flexible bronchoscopy with bronchoalveolar lavage is of great assistance in the timely detection of coinfection, sputum plug and inflammatory polyps in children with Mycoplasma pneumoniae pneumonia (MPP), and improves the recovery of lung damage in MPP patients with multilobar consolidation. This study provides new insights into the indications of flexible bronchoscopy for the diagnosis and treatment of pediatric patients with MPP.

A combined radiomics and clinical variables model for prediction of malignancy in T2 hyperintense uterine mesenchymal tumors on MRI.

OBJECTIVE: This study aims to develop a machine learning model for prediction of malignancy in T2 hyperintense mesenchymal uterine tumors based on T2-weighted image (T2WI) features and clinical information. METHODS: This retrospective study included 134 patients with T2 hyperintense uterine mesenchymal tumors (104 patients in training cohort and 30 in testing cohort). A total of 960 radiomics features were initially computed and extracted from each 3D segmented tumor depicting on T2WI. The support vector machine (SVM) classifier was applied to build computer-aided diagnosis (CAD) models by using selected clinical and radiomics features, respectively. Finally, an observer study was conducted by comparing with two radiologists to evaluate the diagnostic performance. The area under the receiver operating characteristic (ROC) curve (AUC) was computed to assess the performance of each model. RESULTS: Comparing with the T2WI-based radiomics model (AUC: 0.76 ± 0.09) and the clinical model (AUC: 0.79 ± 0.09), the combined model significantly improved the AUC value to 0.91 ± 0.05 (p < 0.05). The clinical-radiomics combined model yielded equivalent or higher performance than two radiologists (AUC: 0.78 vs. 0.91, p = 0.03; 0.90 vs.0.91, p = 0.13). There was a significant difference between the AUC values of two radiologists (p < 0.05). CONCLUSIONS: It is feasible to predict malignancy risk of T2 hyperintense uterine mesenchymal tumors by combining clinical variables and T2WI-based radiomics features. Machine learning-based classification model may be useful to assist radiologists in decision-making. KEY POINTS: • Radiomics approach has the potential to distinguish between benign and malignant mesenchymal uterine tumors. • T2WI-based radiomics analysis combined with clinical variables performed well in predicting malignancy risk of T2 hyperintense uterine mesenchymal tumors. • Machine learning-based classification model may be useful to assist radiologists in characterization of a T2 hyperintense uterine mesenchymal tumor.

Pure dysgerminoma of the ovary: CT and MRI features with pathological correlation in 13 tumors.

BACKGROUND: To investigate the spectrum of CT and MRI findings of dysgerminoma of the ovary. METHODS: CT and MRI imaging of 12 patients with 13 histologically proven dysgerminomas of the ovary were retrospectively reviewed. Patients, ages ranged from 6 ~ 27 years (mean, 17.2 years). Two observers evaluated the following CT and MRI features of the tumor by consensus: (i) location, shape, and size; (ii) attenuation, T2 signal intensity, and ADC value; (iii) patterns of contrast enhancement; (iv) presence of fibrovascular septa; (v) presence of necrosis, hemorrhage, and calcification; (vi) presence of "ovarian vascular pedicle" sign. We also noted the extent or stage of the tumors. RESULTS: 75% lesions arised in the right ovary. Bilateral ovaries were involved in one case. Tumors displayed as a purely or predominantly solid mass (mean size, 17.0 ± 7.8 cm). Ten tumors were shaped multilobulated. The mean ADC value of lesions was 0.830 ± 0.154 × 10- 3 mm2/s. Characteristic fibrovascular septa were observed in all lesions. Among them, classic septa were present in 69% lesions. They were thin, hypointense on T2WI with a linear intense enhancement indicating the blood vessels in septa. Due to the stromal edema, fibrovascular septa may become thick even amorphous in shape, hyperintense on T2WI and even low attenuation on CT with a slight enhancement except for a bright blood vessel on the edge. Massive necrosis was observed only in one lesion. Calcification was present in 3 of the 5 tumors on CT. "Ovarian vascular pedicle" sign was present in 12 lesions. Lymphadenopathy, retroperitoneal spread, and distant metastases combined with an implantation in Douglas' cul-de-sac were present in one patient respectively. CONCLUSION: On CT and MR images, ovarian dysgerminoma often appears as a large solid mass. The edematous condition of characteristic fibrovascular septa can be well displayed by imaging which then can guide the radiologists to make an accurate diagnosis. Calcifications often occur in the tumor. Nonspecific low ADC value and "ovarian vascular pedicle" sign may narrow the differential diagnosis.

Characterization of tubo-ovarian abscess mimicking adnexal masses: Comparison between contrast-enhanced CT, 18F-FDG PET/CT and MRI.

0BJECTIVE: We compared the diagnostic accuracy of contrast-enhanced computed tomography (CT), fluorine 18-labeled-fludeoxyglucose (18F-FDG) positron emission tomography (PET)/CT and conventional magnetic resonance imaging (MRI) without and with diffusion-weighted imaging (DWI) for characterization of tubo-ovarian abscesses (TOAs) that mimic adnexal tumors. MATERIALS AND METHODS: We evaluated (retrospectively) 43 patients who underwent contrast-enhanced CT, PET/CT, conventional MRI without and with DWI, and who were found to have TOAs and complex adnexal tumors. All images were evaluated independently by four radiologists using a two-point grading system. Results of contrast-enhanced CT, PET/CT, MRI without DWI, and MRI with DWI were compared for each patient using receiver operating characteristic curves. Sensitivity, specificity, and positive predictive value (PPV) were calculated and compared using the chi-square test. RESULTS: Sensitivity of MRI with DWI (95%) was significantly higher than that of contrast-enhanced CT (78.6%), PET/CT (86.7%) and MRI without DWI (87.5%). Specificities of these modalities were not significantly different. The PPV of MRI with DWI (100%) was significantly higher than that of the other three modalities (CT, 72.4%; PET/CT 78.5%; MRI without DWI, 81.5%). Overall accuracy of MRI with DWI was significantly higher than that of the other three modalities (CT, 74.4%; PET/CT, 81.4%; MRI without DWI, 83.7%). CONCLUSION: MRI with DWI shows high accuracy for characterization of complex ovarian lesions, and is the most useful method for differentiation of TOAs from ovarian tumors.

Tubo-Ovarian Abscess (with/without Pseudotumor Area) Mimicking Ovarian Malignancy: Role of Diffusion-Weighted MR Imaging with Apparent Diffusion Coefficient Values.

OBJECTIVE: To assess the added value of diffusion-weighted magnetic resonance imaging (DWI) with apparent diffusion coefficient (ADC) values compared to MRI, for characterizing the tubo-ovarian abscesses (TOA) mimicking ovarian malignancy. MATERIALS AND METHODS: Patients with TOA (or ovarian abscess alone; n = 34) or ovarian malignancy (n = 35) who underwent DWI and MRI were retrospectively reviewed. The signal intensity of cystic and solid component of TOAs and ovarian malignant tumors on DWI and the corresponding ADC values were evaluated, as well as clinical characteristics, morphological features, MRI findings were comparatively analyzed. Receiver operating characteristic (ROC) curve analysis based on logistic regression was applied to identify different imaging characteristics between the two patient groups and assess the predictive value of combination diagnosis with area under the curve (AUC) analysis. RESULTS: The mean ADC value of the cystic component in TOA was significantly lower than in malignant tumors (1.04 ± 0 .41 × 10(-3) mm(2)/s vs. 2.42 ± 0.38 × 10(-3) mm(2)/s; p < 0.001). The mean ADC value of the enhanced solid component in 26 TOAs was 1.43 ± 0.16×10(-3) mm(2)/s, and 46.2% (12 TOAs; pseudotumor areas) showed significantly higher signal intensity on DW-MRI than in ovarian malignancy (mean ADC value 1.44 ± 0.20×10(-3) mm(2)/s vs.1.18 ± 0.36 × 10(-3) mm(2)/s; p = 0.043). The combination diagnosis of ADC value and dilated tubal structure achieved the best AUC of 0.996. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of MRI vs. DWI with ADC values for predicting TOA were 47.1%, 91.4%, 84.2%, 64%, and 69.6% vs. 100%, 97.1%, 97.1%, 100%, and 98.6%, respectively. CONCLUSIONS: DW-MRI is superior to MRI in the assessment of TOA mimicking ovarian malignancy, and the ADC values aid in discriminating the pseudotumor area of TOA from the solid portion of ovarian malignancy.

Value of diffusion-weighted imaging combined with conventional magnetic resonance imaging in the diagnosis of thecomas/fibrothecomas and their differential diagnosis with malignant pelvic solid tumors.

BACKGROUND: Our study aims to determine the value of diffusion-weighted imaging (DWI) combined with conventional magnetic resonance imaging (MRI) in the diagnosis of thecomas/fibrothecomas and their differential diagnosis with malignant pelvic solid tumors. METHODS: In total, 36 thecomas/fibrothecomas and 40 malignant pelvic solid tumors were included in our study. All patients underwent 1.5 T conventional MRI and DWI examinations except one patient with a fibrothecoma in whom DWI examination was not performed. The clinical features and characteristics of conventional MRI and DWI of these two groups were analyzed. Apparent diffusion coefficient (ADC) values were measured and compared between groups. Univariate analysis, multivariate logistic regression analysis, and the receiver operating characteristic curve were used for statistical analysis. RESULTS: All the thecomas/fibrothecomas showed isointensity on T1 weighted imaging (T1WI) and 77.8% (28/36) lesions showed hypo- to isointensity on T2 weighted imaging (T2WI). After administration of contrast medium, 94.4% (34/36) tumors appeared as minor to mild enhancement. On DWI, they showed a diversity of low to very high signal intensity. All malignant pelvic masses manifested as hyperintensity on T2WI and 87.5% (35/40) tumors showed very high signal (grade 3) on DWI. Higher area under the curve (AUC) and specificity could be achieved by using the lowest ADC value than the mean ADC value. Multivariate logistic regression analysis showed that shape, signal intensity on T2WI, capsule, and the lowest ADC value were the important indicators in discriminating thecomas/fibrothecomas from malignant pelvic solid tumors. CONCLUSIONS: The combination of DWI and conventional MRI is of great value in the diagnosis of thecomas/fibrothecomas and their differential diagnosis with malignant pelvic solid tumors.

Role of apparent diffusion coefficients with diffusion-weighted magnetic resonance imaging in differentiating between benign and malignant bone tumors.

BACKGROUND: Benign and malignant bone tumors can present similar imaging features. This study aims to evaluate the significance of apparent diffusion coefficients (ADC) in differentiating between benign and malignant bone tumors. METHODS: A total of 187 patients with 198 bone masses underwent diffusion-weighted (DW) magnetic resonance (MR) imaging. The ADC values in the solid components of the bone masses were assessed. Statistical differences between the mean ADC values in the different tumor types were determined by Student's t-test. RESULTS: Histological analysis showed that 84/198 (42.4%) of the bone masses were benign and 114/198 (57.6%) were malignant. There was a significant difference between the mean ADC values in the benign and malignant bone lesions (P<0.05). However, no significant difference was found in the mean ADC value between non-ossifying fibromas, osteofibrous dysplasia, and malignant bone tumors. When an ADC cutoff value≥1.10×10(-3) mm2/s was applied, malignant bone lesions were excluded with a sensitivity of 89.7%, a specificity of 84.5%, a positive predictive value of 82.6%, and a negative predictive value of 95.3%. CONCLUSIONS: The combination of DW imaging with ADC quantification and T2-weighted signal characteristics of the solid components in lesions can facilitate differentiation between benign and malignant bone tumors.

Nasal chondromesenchymal hamartoma in young children: CT and MRI findings and review of the literature.

BACKGROUND: Nasal chondromesenchymal hamartoma (NCMH) is an extremely rare benign tumor, primarily diagnosed in young infants and children and it often simulates malignant tumors on imaging. CASE PRESENTATION: We present computerized tomography and magnetic resonance imaging findings of two nasal chondromesenchymal hamartomas in a 5-year-old boy and a 6-week-old girl. CONCLUSIONS: NCMH is a rare, benign tumor-like lesion with good biologic behavior. No recurrence after complete resection or malignant transformation of NCMH has been reported. A correct diagnosis is imperative to avoid unnecessary adjuvant therapy.

Diagnostic accuracy of diffusion-weighted imaging with conventional MR imaging for differentiating complex solid and cystic ovarian tumors at 1.5T.

BACKGROUND: Preoperative characterization of complex solid and cystic adnexal masses is crucial for informing patients about possible surgical strategies. Our study aims to determine the usefulness of apparent diffusion coefficients (ADC) for characterizing complex solid and cystic adnexal masses. METHODS: One-hundred and 91 patients underwent diffusion-weighted (DW) magnetic resonance (MR) imaging of 202 ovarian masses. The mean ADC value of the solid components was measured and assessed for each ovarian mass. Differences in ADC between ovarian masses were tested using the Student's t-test. The receiver operating characteristic (ROC) was used to assess the ability of ADC to differentiate between benign and malignant complex adnexal masses. RESULTS: Eighty-five patients were premenopausal, and 106 were postmenopausal. Seventy-four of the 202 ovarian masses were benign and 128 were malignant. There was a significant difference between the mean ADC values of benign and malignant ovarian masses (p < 0.05). However, there were no significant differences in ADC values between fibrothecomas, Brenner tumors and malignant ovarian masses. The ROC analysis indicated that a cutoff ADC value of 1.20 x10-3 mm2/s may be the optimal one for differentiating between benign and malignant tumors. CONCLUSIONS: A high signal intensity within the solid component on T2WI was less frequently in benign than in malignant adnexal masses. The combination of DW imaging with ADC value measurements and T2-weighted signal characteristics of solid components is useful for differentiating between benign and malignant ovarian masses.

Diffusion-weighted MRI: a useful technique to discriminate benign versus malignant ovarian surface epithelial tumors with solid and cystic components.

PURPOSE: To evaluate differences in apparent diffusion coefficient (ADC) values for the solid component of benign and malignant ovarian surface epithelial tumors with the goal of differentiating benign versus malignant ovarian tumors preoperatively. MATERIALS AND METHODS: A total of 127 patients with 131 pelvic masses identified by ultrasound between January 2006 and January 2011 were enrolled in this study. 46 patients were diagnosed with benign tumors, and 85 patients were diagnosed with malignant pathologies. For all of the patients, routine spin-echo MRI and diffusion-weighted imaging were performed. ADC values were determined for all of the masses, and the mean ADC values for the benign and malignant tumors were analyzed using Student's t test. A P value <0.05 was considered statistically significant. RESULTS: Mean ADC values associated with malignant ovarian surface epithelial tumors were significantly lower than the mean ADC values of the benign tumors. In addition, the range of ADC values associated with a 95% confidence interval did not overlap between the two groups. ROC analysis indicated that a cutoff ADC value of 1.25 × 10(-3) mm(2)/s was associated with 90.1% sensitivity and 89.9% specificity. CONCLUSION: ADC values determined from 1.5 T MR DWI of benign and malignant ovarian masses were found to be significantly different.