This study aimed to enhance disease classification accuracy from retinal fundus images by integrating fine-grained image features and global textual context using a novel multimodal deep learning architecture. Existing multimodal large language models (MLLMs) often struggle to capture low-level spatial details critical for diagnosing retinal diseases such as glaucoma, diabetic retinopathy, and retinitis pigmentosa. This model development and validation study was conducted on 1,305 fundus image-text pairs compiled from three public datasets (FIVES, HRF, and StoneRounds), covering acquired and inherited retinal diseases, and evaluated using classification accuracy and F1-score. The MDF-MLLM integrates skip features from four U-Net encoder layers into cross-attention blocks within a LLaMA 3.2 11B MLLM. Vision features are patch-wise projected and fused using scaled cross-attention and FiLM-based U-Net modulation. Baseline MLLM achieved 60% accuracy on the dual-type disease classification task. MDF-MLLM, with both U-Net and MLLM components fully fine-tuned during training, achieved a significantly higher accuracy of 94%, representing a 56% improvement. Recall and F1-scores improved by as much as 67% and 35% over baseline, respectively. Ablation studies confirmed that the multi-depth fusion approach contributed to substantial gains in spatial reasoning and classification, particularly for inherited diseases with rich clinical text. MDF-MLLM presents a generalizable, interpretable, and modular framework for fundus image classification, outperforming traditional MLLM baselines through multi-scale feature fusion. The architecture holds promise for real-world deployment in clinical decision support systems. Future work will explore synchronized training techniques, a larger pool of diseases for more generalizability, and extending the model for segmentation tasks.

Join Destiny Robotic CRO Jason Jordan for an incredible evening as you hang online with 4 other entrepreneurs presenters during the Founders Live happy hour competition. With each presenter given only 99 seconds to pitch their value proposition in front of an eager audience. So bring your friends and coworkers, grab some food and drink, and Let's Go! There are no Judges, The winner is selected by the crowd and will receive the Founders Live winner's package which includes $10,000 in AWS credits as well as the opportunity to continue on to compete in a future Founders Live Prime Time global event. Jason Jordan has designed, developed, and deployed automated test equipment for the automotive and retail appliance industries for the last 25 years, working for industry leaders Lear Corporation, Jideco, U.S. Department of Defense, Mahle, and Whirlpool.

The build towards WWE SummerSlam 2017 hasn't been as entertaining as it's been in recent years, but you might not know that by looking at the card. The pay-per-view is almost being treated like WrestleMania, considering it features 12 advertised matches and could last longer than five hours. The kickoff show starts at 6 p.m. EDT, and the actual pay-per-view gets underway an hour later at 7 p.m. EDT at Barclays Center in Brooklyn. Fans can either watch the SummerSlam with a live stream on the WWE Network, or they can order the PPV for $54.99. A subscription to the network costs $9.99 per month, though new subscribers get the first month free.