Ocular surface tumors (OSTs) are rare but potentially life-threatening neoplasms encompassing entities such as ocular surface squamous neoplasia (OSSN), conjunctival melanoma, and lymphoma. Accurate diagnosis often requires expert ophthalmologists and pathologists, compounded by the reliance on advanced imaging modalities, with excisional biopsy being the gold standard. These limitations underscore the need for less invasive, accessible diagnostic approaches, where artificial intelligence (AI) holds significant promise. This review provides a comprehensive overview of AI advancements in OST management. It begins with definitions of AI and its key branches, followed by an examination of AI models applied to ophthalmic tumors using imaging data. Current developments in AI-related diagnostic tools for OSTs are discussed, highlighting their potential to enhance patient management, with classifications based on imaging modalities and specific OST types. Finally, the review addresses main challenges in AI implementation, including data limitations and ethical considerations, while outlining future directions to integrate AI into clinical ophthalmology practice. By bridging technological innovation with clinical needs, AI shows promise in OST diagnosis and management, ultimately improving outcomes in this challenging condition.
Accurate and reliable estimation of the pelvic tilt is one of the essential pre-planning factors for total hip arthroplasty to prevent common post-operative complications such as implant impingement and dislocation. Inspired by the latest advances in deep learning-based systems, our focus in this paper has been to present an innovative and accurate method for estimating the functional pelvic tilt (PT) from a standing anterior–posterior (AP) radiography image. We introduce an encoder–decoder-style network based on a concurrent learning approach called VGG-UNET (VGG embedded in U-NET), where a deep fully convolutional network known as VGG is embedded at the encoder part of an image segmentation network, i.e., U-NET. In the bottleneck of the VGG-UNET, in addition to the decoder path, we use another path utilizing light-weight convolutional and fully connected layers to combine all extracted feature maps from the final convolution layer of VGG and thus regress PT. In the test phase, we exclude the decoder path and consider only a single target task i.e., PT estimation. The absolute errors obtained using VGG-UNET, VGG, and Mask R-CNN are 3.04 ± 2.49, 3.92 ± 2.92, and 4.97 ± 3.87, respectively. It is observed that the VGG-UNET leads to a more accurate prediction with a lower standard deviation (STD). Our experimental results demonstrate that the proposed multi-task network leads to a significantly improved performance compared to the best-reported results based on cascaded networks.