Detecting Small Anatomical Structures in 3D Knee MRI Segmentation by Fully Convolutional Networks

Accurately identifying the pixels of small organs or lesions from magnetic resonance imaging (MRI) has a critical impact on clinical diagnosis. U-net is the most well-known and commonly used neural network for image segmentation. However, the small anatomical structures in medical images cannot be well recognised by U-net. This paper explores the performance of the U-net architectures in knee MRI segmentation to find a relative structure that can obtain high accuracies for both small and large anatomical structures. To maximise the utilities of U-net architecture, we apply three types of components, residual blocks, squeeze-and-excitation (SE) blocks, and dense blocks, to construct four variants of U-net, namely U-net variants. Among these variants, our experiments show that SE blocks can improve the segmentation accuracies of small labels. We adopt DeepLabv3plus architecture for 3D medical image segmentation by equipping SE blocks based on this discovery. The experimental results show that U-net with SE block achieves higher accuracy in parts of small anatomical structures. In contrast, DeepLabv3plus with SE block performs better on the average dice coefficient of small and large labels.

Prevalence and characteristics of the aberrant anterior tibial artery: a single-center magnetic resonance imaging study and scoping review

Background Planning surgical procedures of the lower leg benefits from considering the possibility of an aberrant anterior tibial artery (AATA), but previously published data on the frequency of this anatomic variant shows heterogeneity. We assessed the prevalence of AATA in a Latin American cohort using magnetic resonance imaging (MRI) and compared these with other studies reported in the literature. Methods We retrospectively included consecutive patients who had undergone multiplanar knee MRI at a radiology department in Lima, Peru. The MRI protocol included coronal T1 weighted, axial, sagittal and coronal proton density fat-saturated (PDFS) and sagittal T2 weighted images. Two experienced radiologists assessed all images and were blinded to each other’s findings. The frequency of the AATA was compared to previous cohorts. A scoping review was undertaken to provide an overview of previously published data on the prevalence of ATAA. Results We analyzed 280 knee MRI examinations of 253 patients (median age 41 years (IQR 31–52), 53.8% male). The aberrant anterior tibial artery variant was present in 8 of 280 (2.9%) evaluated knees, resulting in a prevalence of 3.2% in our study population. The PDFS sequence in the axial or sagittal orientation was most effective to identify AATA. The frequency of AATA in the reviewed literature using different radiological modalities ranged from 0.4 to 6% (median 1%, IQR (0.5–2.3%). Conclusions The AATA is a frequent vascular variant that can be detected by MRI in the preparation of invasive interventions of the lower leg.

Incidence Rates of Surgery After Knee MRI: Association According to Referring Physician Type and Patient’s Age and Sex

Background: The utility of magnetic resonance imaging (MRI) in the primary care setting is uncertain, with a perception that there is less likelihood for surgery after MRI ordered by general practitioners (GPs) when compared with orthopaedic surgeons and sports medicine physicians. Additionally, the influence of patient age and sex on subsequent surgical intervention is currently unknown. Purpose/Hypothesis: The purpose of this study was to compare surgical incidence after MRI referrals by orthopaedic surgeons, GPs, and sports medicine physicians, including a subset analysis for GP patients based on type of approval given by the radiologist. The authors also wanted to explore the association of age and sex on subsequent surgical intervention. They hypothesized that surgical incidence after MRI ordered by orthopaedic surgeons and sports medicine physicians would be higher than after MRI ordered by GPs. Study Design: Cohort study; Level of evidence, 3. Methods: Knee MRI referrals by the 3 physician cohorts during May to December 2017 were assessed. For GP patients, the types of approval or recommendation from a radiologist were categorized. Subsequent surgical intervention status was then compared among referral groups up to 2 years after MRI. Associations of age and sex with surgical occurrence were also assessed. Chi-square test, analysis of variance, and univariate/multivariable logistic regression were used for statistical analysis. Results: Overall, 407 referrals were evaluated (GP, n = 173; orthopaedic, n = 176; sports medicine, n = 58). Surgical incidence was not significantly higher for orthopaedic and sports medicine than GP referrals at 3 months (10%, 3%, and 6%, respectively; P = .23), 6 months (20%, 17%, and 15%; P = .49), and 2 years (30%, 35%, and 24%; P = .25). Surgical incidence for GP patients was higher after discussion with a radiologist or when evaluating specific pathology on prior imaging versus less defined reasons (30.4% vs 15.7%, respectively; P = .03). Surgical incidence was lower for older patients (11% vs 31% for >60 years vs all other age groups combined; P = .002), and women were less likely to undergo surgery than men (22% vs 35%, respectively; P = .008). Conclusion: Surgical incidence after MRI was likely appropriately lower for older patients. Lower incidence for female patients is of uncertain cause and warrants further study.

How to Report: Knee MRI

The knee is the most commonly examined joint with magnetic resonance imaging (MRI) and, as such, it is the joint that most trainee radiologists start reporting. This article addresses the main pathologies encountered on MRI examination of the knee, outlining the key features to note and report, as well as providing examples of terminology used to describe these findings.

Creation and Validation of a Shorthand Knee MRI Bone Age Assessment Tool as an Alternative for Skeletal Maturity Assessment (203)

Objectives: In managing pediatric knee conditions, an accurate bone age assessment is often critical for diagnostic, prognostic, and treatment purposes. Historically, the Greulich and Pyle Atlas (hand atlas) has been the gold standard bone age assessment tool. In 2013, a shorthand bone age assessment tool based on this atlas (hand shorthand) was established as a simpler and more efficient alternative. Recently, a knee MRI bone age atlas (MRI atlas) was created potentially to circumvent the need for a left hand radiograph. Our objective is to create a shorthand version of the magnetic resonance imaging atlas. Methods: A shorthand bone age method (Figure 1) was created utilizing the previously published MRI atlas, which utilizes several criteria that are visualized across a series of images. The MRI shorthand draws on the most characteristic criteria for each age that is best observed on a single MR image. For validation, we performed a retrospective assessment of skeletally immature patients that had a knee MRI and left hand radiograph within four weeks. Four readers who were familiar with the hand atlas, hand shorthand, MRI atlas, and MRI shorthand read each of the images in a blinded fashion. Inter- and intra-observer reliability was evaluated using intraclass correlation coefficient (ICC), variability among observers was evaluated using percent agreement. Results: 26 patients with a mean age of 13.6 years (range 9.0-16.9) met the inclusion criteria. The intra- and inter-observer reliability of all four assessment tools was excellent (ICC ≥ 0.8, p<0.001) (Table 1). When comparing the MRI shorthand to the MRI atlas, there was excellent agreement (ICC = 0.974), whereas the hand shorthand compared to the hand atlas had good agreement (ICC = 0.765). The MRI shorthand also had perfect agreement in 58% of reads among all four readers and 96% of reads had agreement within 1 year, whereas the hand shorthand had perfect agreement in 32% of reads and 77% agreement within 1 year (Table 2). Conclusions: The MRI shorthand is a simple and efficient means of assessing skeletal maturity of adolescent patients with a knee MRI. This bone age assessment technique has inter-observer and intra-observer reliability equivalent or better than the standard means utilizing a left hand radiograph.