Access to large, annotated samples represents a considerable challenge for training accurate deep-learning models in medical imaging. While current leading-edge transfer learning from pre-trained models can help with cases lacking data, it limits design choices, and generally results in the use of unnecessarily large models. We propose a novel, self-supervised training scheme for obtaining high-quality, pre-trained networks from unlabeled, cross-modal medical imaging data, which will allow for creating accurate and efficient models. We demonstrate this by accurately predicting optical coherence tomography (OCT)-based retinal thickness measurements from simple infrared (IR) fundus images. Subsequently, learned representations outperformed advanced classifiers on a separate diabetic retinopathy classification task in a scenario of scarce training data. Our cross-modal, three-staged scheme effectively replaced 26,343 diabetic retinopathy annotations with 1,009 semantic segmentations on OCT and reached the same classification accuracy using only 25% of fundus images, without any drawbacks, since OCT is not required for predictions. We expect this concept will also apply to other multimodal clinical data-imaging, health records, and genomics data, and be applicable to corresponding sample-starved learning problems.
2.
Pterygium is a benign lesion usually growing from the nasal side of the conjunctiva onto the cornea. Most cases of pterygium does not cause problem or requires specific treatment. The exact cause of pterygium is not clear yet, but some factors are pointed as causes, being the most important the long-term ultraviolet ray exposure. Pterygium surgery is usually considered when there are symptoms that do not respond to conservative treatment. Recurrence is the main complication of the surgery, and much has been done to avoid it. Mitomycin C (MMC) has been used as a fibroblast proliferation inhibitor during the surgery to reduce the chance of recurrence of the pterygium. This review describes the use of MMC as an adjunctive, the optimal dosage, the duration of administration of MMC and possible complications, when used during, after and before the surgery. Most studies suggest that increased exposure (dose or duration) of MMC is associated with a lower recurrence, but with higher risks of complications.
Objective To conduct a data survey on the subject of medical claims involving civil liability in ophthalmology at the São Paulo Court of Appeals.Methods A case law research was carried out on the São Paulo Court of Appeals website searching for the keyword “ophthalmologist” for all years until 2016.Results Of the 65 cases found, 29 were selected. There has been an increase in the number of claims in ophthalmology, especially in surgical procedures on the anterior chamber of the eye. Most lower court judgments were for defendant.Conclusion The study suggested the need for specialists to exercise the required amount of care when treating the patients, so that they may understand the risks inherent to the procedure. Despite the increase in claims, most decisions were favorable for the physician.
Background:Calcifying nonneoplastic pseudoneoplasms of the neuraxis (CAPNON) have been reported in 59 cases in literature, however, they rarely involve the spinal cord. Owing to the advances in immunohistochemical markers, their structure and origin are better understood now.Case Report:We present the case of a 72-year-old female who had longstanding history of low back pain that exacerbated 20 days prior to the presentation to the emergency room with a frank cauda equina syndrome. The lumbar computed tomography scan showed a hyperdense lesion, suggestive of calcified tumor, whereas the magnetic resonance imaging revealed a hypointense lesion on theT1 and T2-weighted images, without contrast enhancement or edema on fluid-attenuated inversion recovery. She underwent an emergent L2-L4 laminectomy and L3-L4 discectomy with resection of L2 intradural tumor, following which she regained normal function.Conclusion:A 72-year-old female presented with a cauda equina syndrome attributed to an L2 intradural CAPNON. Following gross total resection, the patient was neurologically intact.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.