Designing and making an open source, 3D-printed, punctal plug with drug delivery system

With the advancement in the study of keratoconjunctivitis sicca and the scope of its treatment, punctal plugs are being widely used for the therapeutic management of dry eye disease. With the emergence of 3D printing in medicine, 3D printing of punctal plugs that have an inbuilt drug delivery system and also that can be personalized from patient to patient according to their punctum size can be a great therapeutic option. Another benefit of the device is that its printing takes a short period of time and is cost-effective. This study aimed at making an open source design and 3D printing an efficient model of a punctal plug with an inbuilt drug delivery system that can be eventually used for the treatment of various ocular diseases that require frequent drug instillation or blockage of the nasolacrimal pathway. The 3D design for the punctal plug was made using the open source application, FreeCAD, and slicing was done using the application ChituBox. After that, the plugs were printed using the LCD printer Crealty LD-002R. The material used was resin that was compatible with the Crealty LD-002R. Punctal plugs with satisfactory results were printed using the LCD printer. The punctal plugs showed suitable structure and were also easily reproduced in the 3D printer without any complications or setbacks.

Identification of glaucoma from fundus images using deep learning techniques

Purpose

Glaucoma is one of the preeminent causes of incurable visual disability and blindness across the world due to elevated intraocular pressure within the eyes. Accurate and timely diagnosis is essential for preventing visual disability. Manual detection of glaucoma is a challenging task that needs expertise and years of experience.

Methods

In this paper, we suggest a powerful and accurate algorithm using a convolutional neural network (CNN) for the automatic diagnosis of glaucoma. In this work, 1113 fundus images consisting of 660 normal and 453 glaucomatous images from four databases have been used for the diagnosis of glaucoma. A 13-layer CNN is potently trained from this dataset to mine vital features, and these features are classified into either glaucomatous or normal class during testing. The proposed algorithm is implemented in Google Colab, which made the task straightforward without spending hours installing the environment and supporting libraries. To evaluate the effectiveness of our algorithm, the dataset is divided into 70% for training, 20% for validation, and the remaining 10% utilized for testing. The training images are augmented to 12012 fundus images.

Results

Our model with SoftMax classifier achieved an accuracy of 93.86%, sensitivity of 85.42%, specificity of 100%, and precision of 100%. In contrast, the model with the SVM classifier achieved accuracy, sensitivity, specificity, and precision of 95.61, 89.58, 100, and 100%, respectively.

Conclusion

These results demonstrate the ability of the deep learning model to identify glaucoma from fundus images and suggest that the proposed system can help ophthalmologists in a fast, accurate, and reliable diagnosis of glaucoma.