Comparison of conventional magnetic resonance imaging and diffusion-weighted imaging in the differentiation of bone plasmacytoma from bone metastasis in the extremities

Radiomics model based on MRI to differentiate spinal multiple myeloma from metastases: A two-center study

Purpose

Spinal multiple myeloma (MM) and metastases are two common cancer types with similar imaging characteristics, for which differential diagnosis is needed to ensure precision therapy. The aim of this study is to establish radiomics models for effective differentiation between them.

Methods

Enrolled in this study were 263 patients from two medical institutions, including 127 with spinal MM and 136 with spinal metastases. Of them, 210 patients from institution I were used as the internal training cohort and 53 patients from Institution II were used as the external validation cohort. Contrast-enhanced T1-weighted imaging (CET1) and T2-weighted imaging (T2WI) sequences were collected and reviewed. Based on the 1037 radiomics features extracted from both CET1 and T2WI images, Logistic Regression (LR), AdaBoost (AB), Support Vector Machines (SVM), Random Forest (RF), and multiple kernel learning based SVM (MKL-SVM) were constructed. Hyper-parameters were tuned by five-fold cross-validation. The diagnostic efficiency among different radiomics models was compared by accuracy (ACC), sensitivity (SEN), specificity (SPE), area under the ROC curve (AUC), YI, positive predictive value (PPV), negative predictive value (NPY), and F1-score.

Results

Based on single-sequence, the RF model outperformed all other models. All models based on T2WI images performed better than those based on CET1. The efficiency of all models was boosted by incorporating CET1 and T2WI sequences, and the MKL-SVM model achieved the best performance with ACC, AUC, and F1-score of 0.862, 0.870, and 0.874, respectively.

Conclusions

The radiomics models constructed based on MRI achieved satisfactory diagnostic performance for differentiation of spinal MM and metastases, demonstrating broad application prospects for individualized diagnosis and treatment.

Synovial Sarcoma in the Extremity: Diversity of Imaging Features for Diagnosis and Prognosis

Synovial sarcomas are rare and highly aggressive soft-tissue sarcomas, primarily affecting adolescents and young adults aged 15-40 years. These tumors typically arise in the deep soft tissues, often near the large joints of the extremities. While the radiological features of these tumors are not definitely indicative, the presence of calcification in a soft-tissue mass (occurring in 30% of cases), adjacent to a joint, strongly suggests the diagnosis. Cross-sectional imaging characteristics play a crucial role in diagnosing synovial sarcomas. They often reveal significant characteristics such as multilobulation and pronounced heterogeneity (forming the "triple sign"), in addition to features like hemorrhage and fluid-fluid levels with septa (resulting in the "bowl of grapes" appearance). Nevertheless, the existence of non-aggressive features, such as gradual growth (with an average time to diagnosis of 2-4 years) and small size (initially measuring < 5 cm) with well-defined margins, can lead to an initial misclassification as a benign lesion. Larger size, older age, and higher tumor grade have been established as adverse predictive indicators for both local disease recurrence and the occurrence of metastasis. Recently, the prognostic importance of CT and MRI characteristics for synovial sarcomas was elucidated. These include factors like the absence of calcification, the presence of cystic components, hemorrhage, the bowl of grape sign, the triple sign, and intercompartmental extension. Wide surgical excision remains the established approach for definitive treatment. Gaining insight into and identifying the diverse range of presentations of synovial sarcomas, which correlate with the prognosis, might be helpful in achieving the optimal patient management.

Pitfalls of Diffusion-Weighted Imaging: Clinical Utility of T2 Shine-through and T2 Black-out for Musculoskeletal Diseases

Diffusion-weighted imaging (DWI) with an apparent diffusion coefficient (ADC) value is a relatively new magnetic resonance imaging (MRI) sequence that provides functional information on the lesion by measuring the microscopic movement of water molecules. While numerous studies have evaluated the promising role of DWI in musculoskeletal radiology, most have focused on tumorous diseases related to cellularity. This review article aims to summarize DWI-acquisition techniques, considering pitfalls such as T2 shine-through and T2 black-out, and their usefulness in interpreting musculoskeletal diseases with imaging. DWI is based on the Brownian motion of water molecules within the tissue, achieved by applying diffusion-sensitizing gradients. Regardless of the cellularity of the lesion, several pitfalls must be considered when interpreting DWI with ADC values in musculoskeletal radiology. This review discusses the application of DWI in musculoskeletal diseases, including tumor and tumor mimickers, as well as non-tumorous diseases, with a focus on lesions demonstrating T2 shine-through and T2 black-out effects. Understanding these pitfalls of DWI can provide clinically useful information, increase diagnostic accuracy, and improve patient management when added to conventional MRI in musculoskeletal diseases.

Contribution of an artificial intelligence deep-learning reconstruction algorithm for dose optimization in lumbar spine CT examination: A phantom study

PURPOSE

The purpose of this study was to assess the impact of the new artificial intelligence deep-learning reconstruction (AI-DLR) algorithm on image quality and radiation dose compared with iterative reconstruction algorithm in lumbar spine computed tomography (CT) examination.

MATERIALS AND METHODS

Acquisitions on phantoms were performed using a tube current modulation system for four DoseRight Indexes (DRI) (i.e., 26/23/20/15). Raw data were reconstructed using the Level 4 of iDose⁴ (i4) and three levels of AI-DLR (Smoother/Smooth/Standard) with a bone reconstruction kernel. The Noise power spectrum (NPS), task-based transfer function (TTF) and detectability index (d') were computed (d' modeled detection of a lytic and a sclerotic bone lesions). Image quality was subjectively assessed on an anthropomorphic phantom by two radiologists.

RESULTS

The Noise magnitude was lower with AI-DLR than i4 and decreased from Standard to Smooth (-31 ± 0.1 [SD]%) and Smooth to Smoother (-48 ± 0.1 [SD]%). The average NPS spatial frequency was similar with i4 (0.43 ± 0.01 [SD] mm^-1) and Standard (0.42 ± 0.01 [SD] mm^-1) but decreased from Standard to Smoother (0.36 ± 0.01 [SD] mm^-1). TTF values at 50% decreased as the dose decreased but were similar with i4 and all AI-DLR levels. For both simulated lesions, d' values increased from Standard to Smoother levels. Higher detectabilities were found with a DRI at 15 and Smooth and Smoother levels than with a DRI at 26 and i4. The images obtained with these dose and AI-DLR levels were rated satisfactory for clinical use by the radiologists.

CONCLUSION

Using Smooth and Smoother levels with CT allows a significant dose reduction (up to 72%) with a high detectability of lytic and sclerotic bone lesions and a clinical overall image quality.

Differentiation between spinal multiple myeloma and metastases originated from lung using multi-view attention-guided network

Purpose

Multiple myeloma (MM) and metastasis originated are the two common malignancy diseases in the spine. They usually show similar imaging patterns and are highly demanded to differentiate for precision diagnosis and treatment planning. The objective of this study is therefore to construct a novel deep-learning-based method for effective differentiation of two diseases, with the comparative study of traditional radiomics analysis.

Methods

We retrospectively enrolled a total of 217 patients with 269 lesions, who were diagnosed with spinal MM (79 cases, 81 lesions) or spinal metastases originated from lung cancer (138 cases, 188 lesions) confirmed by postoperative pathology. Magnetic resonance imaging (MRI) sequences of all patients were collected and reviewed. A novel deep learning model of the Multi-view Attention-Guided Network (MAGN) was constructed based on contrast-enhanced T1WI (CET1) sequences. The constructed model extracts features from three views (sagittal, coronal and axial) and fused them for a more comprehensive differentiation analysis, and the attention guidance strategy is adopted for improving the classification performance, and increasing the interpretability of the method. The diagnostic efficiency among MAGN, radiomics model and the radiologist assessment were compared by the area under the receiver operating characteristic curve (AUC).

Results

Ablation studies were conducted to demonstrate the validity of multi-view fusion and attention guidance strategies: It has shown that the diagnostic model using multi-view fusion achieved higher diagnostic performance [ACC (0.79), AUC (0.77) and F1-score (0.67)] than those using single-view (sagittal, axial and coronal) images. Besides, MAGN incorporating attention guidance strategy further boosted performance as the ACC, AUC and F1-scores reached 0.81, 0.78 and 0.71, respectively. In addition, the MAGN outperforms the radiomics methods and radiologist assessment. The highest ACC, AUC and F1-score for the latter two methods were 0.71, 0.76 & 0.54, and 0.69, 0.71, & 0.65, respectively.

Conclusions

The proposed MAGN can achieve satisfactory performance in differentiating spinal MM between metastases originating from lung cancer, which also outperforms the radiomics method and radiologist assessment.

Reproducibility of apparent diffusion coefficient measurement in normal prostate peripheral zone at 1.5T MRI

PURPOSE

The purpose of this study was to quantify the influence of factors of variability on apparent diffusion coefficient (ADC) estimation in the normal prostate peripheral zone (PZ).

MATERIALS AND METHODS

Fifty healthy volunteers underwent in 2017 (n = 17) or 2020 (n = 33) two-point (0, 800 s/mm²) prostate diffusion-weighted imaging in the morning on 1.5 T scanners A and B from different manufacturers. Additional five-point (50, 150, 300, 500, 800 s/mm²) acquisitions were performed on scanner B in the morning and evening. ADC was measured in PZ at midgland using ADC maps reconstructed with various b-value combinations. ADC distributions from 2017 and 2020 were compared using Wilcoxon rank sum test. ADC obtained in the same volunteers were compared using Bland Altman methodology. The 95% confidence interval upper limit of the repeatability/reproducibility coefficient defined the lowest detectable ADC difference.

RESULTS

Forty-nine participants with a mean age of 24.6 ± 3.8 [SD] years (range: 21-37 years) were finally included. ADC distributions from 2017 and 2020 were not significantly different and were combined. Despite high individual variability, there was no significant bias (10 × 10^-6 mm²/s, P = 0.58) between ADC measurements made on both scanners. On scanner B, differences in lowest b-values chosen within the 0-500 s/mm² range for two-point ADC computation induced significant biases (56-109 × 10^-6 mm²/s, P < 0.0001). ADC was significantly lower in the morning (bias: 33 × 10^-6 mm²/s, P = 0.006). The number of b-values had little influence on ADC values. The lowest detectable ADC difference varied from 85 × 10^-6 to 311 × 10^-6 mm²/s across scanners, b-value combinations and periods of the day.

CONCLUSIONS

The MRI scanner, the lowest b-value used and the period of the day induce substantial variability in ADC computation.

Diagnostic Value and Clinical Application of Diffusion-Weighted Magnetic Resonance Imaging for Female Pelvic Lesions

Pelvic inflammatory disease refers to a group of infectious diseases of the female upper genital tract, often caused by ascending infection of vaginitis and cervicitis, causing endometritis, salpingitis, tubo-ovarian abscess, pelvic connective tissue inflammation, and/or pelvic peritonitis. PID is the most common and important infectious disease in nonpregnant women of childbearing age, and inflammation in multiple parts often coexists and affects each other. The functional MRI techniques currently used in pelvic floor muscle injury are magnetic resonance diffusion tensor imaging, T2 mapping, and magnetic resonance elastography. Diffusion tensor imaging is a new imaging and postprocessing technology developed on the basis of magnetic resonance diffusion-weighted imaging. Due to the lack of specificity of clinical symptoms, many subclinical patients are often not detected and diagnosed in time, so it is very difficult to accurately estimate the incidence of PID. This article retrospectively analyzed 72 patients with pelvic inflammatory disease confirmed by surgical pathology from February 2020 to 2022, who had undergone pelvic MRI examination before surgery, including 25 patients with chronic pelvic inflammation (hydrosalpinx), 25 patients with acute pelvic inflammation, and 47 cases (including 21 cases of hydrosalpinx, 19 cases of tubo-ovarian abscess, and 7 cases of pelvic abscess). The age range was 13 to 59 years old. The clinical data and MRI findings were analyzed, the ADC value of the cystic part of the lesion was measured, and the differences in age, maximum diameter of the lesion, thickness of the vessel wall/separation, and the ADC value of the cystic part of chronic and acute pelvic inflammation were compared. In this part of the cases, there were 25 cases of chronic pelvic inflammation and 47 cases of acute pelvic inflammation. The average ADC value of the cystic component of chronic inflammation was significantly higher than that of acute inflammation, which were (2.86 ± 0.20) × 10−3 mm2/s and (1.07 ± 0.38) ×10−3 mm2/s, respectively, $P$ value <0.001.