Search

ObjectivesTo propose a deep learning-based classification framework, which can carry out patient-level benign and malignant tumors classification according to the patient’s multi-plane images and clinical information.MethodsA total of 430 cases of spinal tumor, including axial and sagittal plane images by MRI, of which 297 cases for training (14072 images), and 133 cases for testing (6161 images) were included. Based on the bipartite graph and attention learning, this study proposed a multi-plane attention learning framework, BgNet, for benign and malignant tumor diagnosis. In a bipartite graph structure, the tumor area in each plane is used as the vertex of the graph, and the matching between different planes is used as the edge of the graph. The tumor areas from different plane images are spliced at the input layer. And based on the convolutional neural network ResNet and visual attention learning model Swin-Transformer, this study proposed a feature fusion model named ResNetST for combining both global and local information to extract the correlation features of multiple planes. The proposed BgNet consists of five modules including a multi-plane fusion module based on the bipartite graph, input layer fusion module, feature layer fusion module, decision layer fusion module, and output module. These modules are respectively used for multi-level fusion of patient multi-plane image data to realize the comprehensive diagnosis of benign and malignant tumors at the patient level.ResultsThe accuracy (ACC: 79.7%) of the proposed BgNet with multi-plane was higher than that with a single plane, and higher than or equal to the four doctors’ ACC (D1: 70.7%, p=0.219; D2: 54.1%, p

Abstract Introduction Predicting the postoperative neurological function of cervical spondylotic myelopathy (CSM) patients is generally based on conventional magnetic resonance imaging (MRI) patterns, but this approach is not completely satisfactory. This study utilized radiomics, which produced advanced objective and quantitative indicators, and machine learning to develop, validate, test, and compare models for predicting the postoperative prognosis of CSM. Materials and methods In total, 151 CSM patients undergoing surgical treatment and preoperative MRI was retrospectively collected and divided into good/poor outcome groups based on postoperative modified Japanese Orthopedic Association (mJOA) scores. The datasets obtained from several scanners (an independent scanner) for the training (testing) cohort were used for cross‐validation (CV). Radiological models based on the intramedullary hyperintensity and compression ratio were constructed with 14 binary classifiers. Radiomic models based on 237 robust radiomic features were constructed with the same 14 binary classifiers in combination with 7 feature reduction methods, resulting in 98 models. The main outcome measures were the area under the receiver operating characteristic curve (AUROC) and accuracy. Results Forty‐one (11) radiomic models were superior to random guessing during CV (testing), with significant increased AUROC and/or accuracy (PAUROC

Background: Numerous studies have investigated the influence of osseous factors on patellofemoral joint instability, but research on the influence of dynamic muscle factors in vivo is still in the exploratory stage. This study aimed to use magnetic resonance imaging (MRI) and diffusion tensor imaging (DTI) to evaluate vastus medialis oblique (VMO) fiber bundles in patients with recurrent patellar dislocation to explore the changes in muscle morphology and function. Methods: This prospective study involved 30 patients (7 males and 23 females; average age, 21.4 ± 3.8 years) clinically diagnosed with recurrent patellar dislocation in Peking University Third Hospital and 30 healthy volunteers matched for age, sex, and body mass index in our medical school between January 2014 and October 2014. None of the patients had a recent history of traumatic patellar dislocation or transient patellar dislocation. All patients underwent conventional MRI and DTI of the knee. The cross-sectional area of the VMO on MRI and the fractional anisotropy (FA), apparent diffusion coefficient (ADC), and primary (λ1), secondary (λ2), and three-level characteristic (λ3) values on DTI were measured. The independent-samples t-test was used to compare these parameters between the two groups. Results: Compared with the control group, the patient group showed significantly higher FA values (0.39 ± 0.05 vs. 0.33 ± 0.03) and significantly lower ADC (1.51 ± 0.13 vs. 1.58 ± 0.07), λ2 (4.96 ± 0.13 vs. 5.04 ± 0.07), and λ3 values (4.44 ± 0.14 vs. 4.58 ± 0.07; t = 5.99, t = –2.58, t = –3.02, and t = –4.88, respectively; all P < 0.05). Cross-sectional VMO area and λ1 values did not differ between the two groups (t = –1.82 and t = 0.22, respectively; both P > 0.05). Conclusions: The functional status of the VMO is closely associated with recurrent patellar dislocation. MRI, especially DTI (FA, ADC, λ2, and λ3), can detect early changes in VMO function and might facilitate the noninvasive monitoring of the functional status of the VMO in patients with recurrent patellar dislocation.

Background: Diffusion-weighted imaging (DWI) can quantify the microstructural changes in the spinal cord. It might be a substitute for T2 increased signal intensity (ISI) for cervical spondylotic myelopathy (CSM) evaluation and prognosis. Purpose: The purpose of the study is to investigate the relationship between DWI metrics and neurologic function of patients with CSM. Study Type: Retrospective. Population: Forty-eight patients with CSM (18.8% females) and 36 healthy controls (HCs, 25.0% females). Field Strength/Sequence: 3 T; spin-echo echo-planar imaging-DWI; turbo spin-echo T1/T2; multi-echo gradient echo T2*. Assessment: For patients, conventional MRI indicators (presence and grades of T2 ISI), DWI indicators (neurite orientation dispersion and density imaging [NODDI]-derived isotropic volume fraction [ISOVF], intracellular volume fraction, and orientation dispersion index [ODI], diffusion tensor imaging [DTI]-derived fractional anisotropy [FA] and mean diffusivity [MD], and diffusion kurtosis imaging [DKI]-derived FA, MD, and mean kurtosis), clinical conditions, and modified Japanese Orthopaedic Association (mJOA) were recorded before the surgery. Neurologic function improvement was measured by the 3-month follow-up recovery rate (RR). For HCs, DWI, and mJOA were measured as baseline comparison. Statistical Tests: Continuous (categorical) variables were compared between patients and HCs using Student's t-tests or Mann-Whitney U tests (chi-square or Fisher exact tests). The relationships between DWI metrics/conventional MRI findings, and the pre-operative mJOA/RR were assessed using correlation and multivariate analysis. P < 0.05 was considered statistically significant. Results: Among patients, grades of T2 ISI were not correlated with pre-surgical mJOA/RR (P = 0.717 and 0.175, respectively). NODDI ODI correlated with pre-operative mJOA (r = -0.31). DTI FA, DKI FA, and NODDI ISOVF were correlated with the recovery rate (r = 0.31, 0.41, and -0.34, respectively). In multivariate analysis, NODDI ODI (DTI FA, DKI FA, NODDI ISOVF) significantly contributed to the pre-operative mJOA (RR) after adjusting for age. Data Conclusion: DTI FA, DKI FA, and NODDI ISOVF are predictors for prognosis in patients with CSM. NODDI ODI can be used to evaluate CSM severity. [ABSTRACT FROM AUTHOR]

Objective To determine the association of carotid plaque features with collateral circulation status in elderly patients with moderate to severe carotid stenosis. Methods Elderly patients (> 60 years) with moderate to severe carotid stenosis were recruited and categorized into good and poor collateral circulation groups, and underwent magnetic resonance imaging and computed tomography imaging. The carotid plaque features including lipid-rich necrotic core, intraplaque hemorrhage, calcification, and fibrous cap rupture (FCR) were evaluated, and maximum wall thickness, normalized wall index (NWI), and luminal stenosis were measured. The association between these variables and collateral circulation status was analyzed. Results Of the 97 patients (78 males, mean age: 69.0 ± 6.1 years), 19 (19.6%) had poor collaterals. The poor collateral group had a significantly higher NWI (93.7% ± 5.0% vs. 89.0% ± 7.9%, P = 0.011), a greater extent of stenosis (80.0% ± 11.4% vs. 75.3% ± 9.4%, P = 0.036) and FCR (84.2% vs. 55.1%, P = 0.020) compared with good collateral group. Carotid NWI (OR = 3.83, 95% CI: 1.36-10.82, P = 0.011) and more FCR (OR = 6.77, 95% CI: 1.35-33.85, P = 0.020) were associated with poor collateral circulation after adjustment for the confounding factors. The combination of NWI, FCR, systolic blood pressure, and triglycerides had the highest area-under-the-curve (AUC = 0.85) for detection of poor collaterals. Conclusions Carotid plaque features, specifically NWI and FCR, are independently associated with poor collateral circulation, and the combination of carotid plaque features and traditional risk factors has a stronger predictive value for poor collateral circulation than plaque features alone. [ABSTRACT FROM AUTHOR]

The objective this study was to measure the changes of sphenoid sinusin the Chinese in AsiausingCT sagittal thin-slice reconstruction images, and to clarify the three-dimensional anatomical features of sphenoid sinus with its surrounding structures, relevant to the performing of the endoscopic sphenoidotomy. The sagittal reconstruction images were obtained from 178 CT images of 89 cases of normal adult participants (54 males and 35 females) with sphenoid sinus. We took the high-resolution axial CT images, from all the subjects, of the thickness by 0.625 mm, and reconstructed 1-mm-thick gapless sagittal CT images to measure the distance of all the sellar and pre-sellar types on the three-dimensional reconstructable sagittal plane under the bone window (4,000 at its width, and 400 at its level) in the CT images. The length of mean vertical line from the center of sphenoid ostium to the roof of sphenoid sinus of Non Onodi cell type is 10.6 ± 1.5 mm, and of Onodi cell type is 3.3 ± 1.5 mm. The length of vertical line from the center of sphenoid ostium to the lowest level of the bottom of sphenoid sinus is 12 mm ± 3.7 mm. The length of mean horizontal line from the sphenoid ostium to the posterior wall of sphenoid sinus is 18 ± 1.5 mm or 28 ± 2.5 mm. The mean horizontal line from the lowest point of the sella to the anterior wall of sphenoid sinus is 17.5 ± 1.3 mm in length. The mean horizontal distance from anterior wall to posterior wall of sphenoid sinus of Non Onodi cell type lining skull base is 10.1 ± 1.0 mm, and of Onodi cell type, is 5.2 ± 4.3 mm. The longest horizontal distance from the anterior wall to the posterior wall of sphenoid sinus is 22.0 ± 7.7 mm. The present study provides atomical information about sphenoid sinus of the Chinese in Asia with some surgical distance measured between the sphenoid ostium and the surrounding structures, which is essential to avoid the complications during surgery. [ABSTRACT FROM AUTHOR]

To assess the feasibility, efficacy, and morbidity of 125I seeds interstitial permanent implant as salvage therapy for re-recurrent rectal cancer. From September 2003 to October 2007, 125I seeds implant procedures were performed under CT or ultrasound guidance for thirteen patients with locally re-recurrent rectal carcinoma. The minimal peripheral doses (MPD) of 125I seeds implanted ranged from 120 to 160 Gy, with a median MPD of 140 Gy to total decay. Three patients also received two to four cycles of chemotherapy after seed implantation. After a median follow-up of 10 months (range 3–45), the pain-free interval was 0–14 months with a median of 7 months (95% CI: 3–11 months). The response rate of pain relief was 46.2% (6/13). Local control was 3–14 months with a median of 7 months (95% CI: 3.5–10.5 months). The 1- and 2-year local control rates were 14.4% and 0%, respectively. Three (23.1%) patients died of local recurrence; seven (53.8%) patients died of local recurrence and metastases; one (7.7%) patient died of metastases. Two (15.4%) patients survived to follow-up. At the time of analysis, the median survival was 10 months (95% CI: 3.9–16.1 months). The 1- and 2-year actuarial overall survival rates were 46.2% and 11.5%, respectively. Two (15.4%) patients experienced a grade 4 toxic event. Seed migration to the pelvic wall was observed in one (7.7%) patient. There was no associated neuropathy. 125I seed implantation is feasible, effective, and safe as a salvage or palliative treatment for patients with re-recurrent rectal cancer. [ABSTRACT FROM AUTHOR]