Cross-attention enables deep learning on limited omics-imaging-clinical data of 130 lung cancer patients.

Deep-learning tools that extract prognostic factors derived from multi-omics data have recently contributed to individualized predictions of survival outcomes. However, the limited size of integrated omics-imaging-clinical datasets poses challenges. Here, we propose two biologically interpretable and robust deep-learning architectures for survival prediction of non-small cell lung cancer (NSCLC) patients, learning simultaneously from computed tomography (CT) scan images, gene expression data, and clinical information. The proposed models integrate patient-specific clinical, transcriptomic, and imaging data and incorporate Kyoto Encyclopedia of Genes and Genomes (KEGG) and Reactome pathway information, adding biological knowledge within the learning process to extract prognostic gene biomarkers and molecular pathways. While both models accurately stratify patients in high- and low-risk groups when trained on a dataset of only 130 patients, introducing a cross-attention mechanism in a sparse autoencoder significantly improves the performance, highlighting tumor regions and NSCLC-related genes as potential biomarkers and thus offering a significant methodological advancement when learning from small imaging-omics-clinical samples.

Adolescent hallux valgus deformity with bilateral absence of the hallucal sesamoids: a case report.

The absence of the hallucal sesamoid is a rare condition. Rarer still is the presentation of adolescent hallux valgus with the absence of both hallucal sesamoid. Seven cases of absence of the tibial sesamoid bone and 3 cases of absence of the fibular sesamoid bone have been found in the literature, and only a single case of bilateral absence of both sesamoid bones with hallux varus has been reported. We would like to present a unique case of bilateral absence of the hallucal sesamoid in an 18-year-old woman with severe adolescent hallux valgus but no other apparent congenital deformity.

Functional outcome of PFC Sigma fixed and rotating-platform total knee arthroplasty. A prospective randomised controlled trial.

The aim of this study was to determine whether there is a difference in functional outcome between the PFC Sigma fixed-bearing and rotating-platform total knee replacement systems. One hundred twenty patients were randomised to receive either a fixed-bearing or rotating-platform PFC Sigma total knee replacement. Range of movement (ROM), Oxford knee score (OKS) and Knee Society score (KSS) were assessed independently before and one year after surgery. Weight-bearing X-rays were taken immediately and one year post surgery to determine the incidence of osteolysis and loosening. At a mean follow-up of 13.4 months there was no statistically significant difference in mean ROM, OKS and KSS between the two groups. There was no evidence of osteolysis or loosening in either of the groups and no revision for infection or implant failure. This study shows that there is no statistically significant difference in functional outcome between the two types of implants at short-term follow-up.