Automated classification of fat-infiltrated axillary lymph nodes on screening mammograms.

OBJECTIVE: Fat-infiltrated axillary lymph nodes (LNs) are unique sites for ectopic fat deposition. Early studies showed a strong correlation between fatty LNs and obesity-related diseases. Confirming this correlation requires large-scale studies, hindered by scarce labeled data. With the long-term goal of developing a rapid and generalizable tool to aid data labeling, we developed an automated deep learning (DL)-based pipeline to classify the status of fatty LNs on screening mammograms. METHODS: Our internal data set included 886 mammograms from a tertiary academic medical institution, with a binary status of the fat-infiltrated LNs based on the size and morphology of the largest visible axillary LN. A two-stage DL model training and fine-tuning pipeline was developed to classify the fat-infiltrated LN status using the internal training and development data set. The model was evaluated on a held-out internal test set and a subset of the Digital Database for Screening Mammography. RESULTS: Our model achieved 0.97 (95% CI: 0.94-0.99) accuracy and 1.00 (95% CI: 1.00-1.00) area under the receiver operator characteristic curve on 264 internal testing mammograms, and 0.82 (95% CI: 0.77-0.86) accuracy and 0.87 (95% CI: 0.82-0.91) area under the receiver operator characteristic curve on 70 external testing mammograms. CONCLUSION: This study confirmed the feasibility of using a DL model for fat-infiltrated LN classification. The model provides a practical tool to identify fatty LNs on mammograms and to allow for future large-scale studies to evaluate the role of fatty LNs as an imaging biomarker of obesity-associated pathologies. ADVANCES IN KNOWLEDGE: Our study is the first to classify fatty LNs using an automated DL approach.

Repair of Proximal Hamstring Tear Utilizing a Suture Bridge Knotless Construct.

Proximal hamstring tendon injuries occur frequently in the athletic population resulting in varying degrees of functional disability depending on severity of injury. The purpose of our case vignette is to describe a surgical technique and clinical outcome for open proximal hamstring tendon repair with a confirmed biomechanically sound construct. We also describe and summarize the current literature recommendations for proximal hamstring injuries. We present a case and surgical technique report on a 27-year-old male who suffered a proximal hamstring tendon rupture. Utilizing a double row all-knotless suture bridge construct with a total of four anchors and six suture limbs allowed for anatomic footprint coverage and strength. Two years of clinical follow-up was obtained evaluating hip and knee range of motion, strength, and functional ability. Our patient underwent uncomplicated open surgical repair and returned to all activity at four months following surgery. Range of motion and strength returned to preoperative levels at the four-month postoperative mark. The use of a reproducible double row all-knotless suture bridge technique provided adequate strength and stability in the setting of a proximal hamstring tendon rupture. Open and endoscopic surgical techniques performed acutely both show positive postoperative subjective outcomes as well as a high likelihood of returning to sport. Controversy remains present in regard to the repair technique as well as postoperative bracing and physical therapy recommendations.

The relationship between patellar lateralization diagnostic imaging markers and non-contact internal knee derangements.

BACKGROUND: To investigate differences in the tibial tubercle-trochlear groove (TT-TG) and patellar tendon-posterior cruciate ligament (PT-PCL) distances in symptomatic patients with non-contact internal knee derangements (IKD) and symptomatic patients with internally intact knees (control). METHODS: A retrospective review of MRI studies was completed by comparing 78 patients with meniscal and ligamentous derangements of the knee to 63 internally intact knees (age range, 13 to 50 years). MRI findings were reviewed independently by two board-certified radiologists to assess for agreement. TT-TG and PT-PCL distances were measured on proton density-weighted axial images by two independent observers blinded to the MRI and arthroscopic findings. Independent t tests were used to determine differences in TT-TG distance between the internal derangement and control groups. Chi-square tests were used to compare categorical variables for distributional equality between study groups. RESULTS: The mean TT-TG distance averaged across the two raters in the IKD group was 11.5 mm (95% confidence interval [CI], 10.6-12.4), compared to 8.3 mm (95% CI, 7.6-9.0) in the control group (p < 0.001). The mean PT-PCL distance similarly averaged across both raters was 20.6 mm (95% CI, 19.7-21.5) for the IKD group compared to 18.2 mm (95% CI, 17.2-19.2) for the control group (p < 0.001). Among the IKD group, there were 51 meniscal tears, 12 cruciate ligament tears, and 15 tears with a combination of meniscal and cruciate findings. IKD was significantly correlated with greater TT-TG distance (p < 0.001) and greater PT-PCL distance (p < 0.003) when compared with control. CONCLUSIONS: Increased TT-TG distances and PT-PCL distances are associated with both cartilaginous and ligamentous internal knee injuries in the present study, with TT-TG distances greater than the 12 mm representing a new threshold for concern.