Trends in female applicants to Canadian ophthalmology residency programs from 1998-2020.

Background: Ophthalmology has historically been a male-dominated specialty. Despite there being a higher proportion of females in Canadian medical schools since the early 2000s, it is unknown if trends in female applicants and those accepted to ophthalmology have followed suit. This study aims to evaluate trends in gender representation of ophthalmology applicants to Canadian residency programs from 1998 to 2020 and to compare those trends to other surgical specialties.

BAE-ViT: An Efficient Multimodal Vision Transformer for Bone Age Estimation.

This research introduces BAE-ViT, a specialized vision transformer model developed for bone age estimation (BAE). This model is designed to efficiently merge image and sex data, a capability not present in traditional convolutional neural networks (CNNs). BAE-ViT employs a novel data fusion method to facilitate detailed interactions between visual and non-visual data by tokenizing non-visual information and concatenating all tokens (visual or non-visual) as the input to the model.

The genomic and clinical consequences of replacing procarbazine with dacarbazine in escalated BEACOPP for Hodgkin lymphoma: a retrospective, observational study.

Background: Procarbazine-containing chemotherapy regimens are associated with cytopenias and infertility, suggesting stem-cell toxicity. When treating Hodgkin lymphoma, procarbazine in escalated-dose bleomycin-etoposide-doxorubicin-cyclophosphamide-vincristine-procarbazine-prednisolone (eBEACOPP) is increasingly replaced with dacarbazine (eBEACOPDac) to reduce toxicity. We aimed to investigate the impact of this drug substitution on the mutation burden in stem cells, patient survival, and toxicity.

Bone-independent extramedullary disease is associated with inferior overall survival in multiple myeloma patients: a single center, real-world experience.

Not available.

Technical Note: Neural Network Architectures for Self-Supervised Body Part Regression Models with Automated Localized Segmentation Application.

The advancement of medical image deep learning necessitates tools that can accurately identify body regions from whole-body scans to serve as an essential pre-processing step for downstream tasks. Typically, these deep learning models rely on labeled data and supervised learning, which is labor-intensive. However, the emergence of self-supervised learning is revolutionizing the field by eliminating the need for labels.