NMNehal Nailesh Mehta

Nehal Nailesh Mehta

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Nehal Nailesh Mehta has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Dropless Pars Plana Vitrectomy Using Intravitreal Decanted Triamcinolone and Moxifloxacin: Safety and Efficacy

    by Amr Lotfy Ali, Daniel Vail, Mohamed Sherif Morsy, Nehal Nailesh Mehta, Soumya Jena, Dirk-Uwe Bartsch, Lingyun Cheng, William R. Freeman

    Purpose: To evaluate the safety and efficacy of a dropless regimen using intravitreal decanted triamcinolone acetonide and moxifloxacin at the conclusion of pars plana vitrectomy (PPV), compared with standard postoperative topical therapy. Methods: This retrospective study included consecutive patients undergoing PPV at a tertiary retina center. The dropless cohort (May-October 2025) received intravitreal decanted triamcinolone (5 mg) and moxifloxacin (500 μg). The control cohort, operated during the preceding 6 months, received topical moxifloxacin 0.5% and prednisolone acetate 1%. Outcomes included intraocular inflammation, intraocular pressure (IOP), central subfield thickness (CST), cystoid macular edema (CME), and best-corrected visual acuity (BCVA). A prespecified subgroup analysis was performed for epiretinal membrane (ERM). Results: 172 eyes were included (87 dropless, 85 topical). The dropless group demonstrated significantly less anterior chamber inflammation at week 2 ( P = 0.0008) and at month 3 ( P = 0.0223). Mean CST was lower at week 2 ( P = 0.001), month 3 ( P = 0.0009), and month 6 ( P = 0.012). CME incidence was reduced ( P < 0.001). BCVA improvement was greater in the dropless group at week 2 (+15 vs –2.5 ETDRS letters; P = 0.0003), month 3 (+25 vs +9.5 letters; P = 0.002), and month 6 (+20 vs +8 letters; P = 0.01). IOP was similar between groups, and no endophthalmitis occurred. Findings were consistent in the ERM subgroup. Conclusion: A dropless intravitreal regimen at the conclusion of PPV can be a safe and effective alternative to topical therapy, with reduced postoperative inflammation and CME and improved visual outcomes.

  • Open Access

    Tunable Wavelet Unit based Convolutional Neural Network in Optical Coherence Tomography Analysis Enhancement for Classifying Type of Epiretinal Membrane Surgery

    by An Le, Nehal Mehta, William Freeman, Ines Nagel, Melanie Tran, Anna Heinke, Akshay Agnihotri, Lingyun Cheng, Dirk-Uwe Bartsch, Hung Nguyen, et al.

    In this study, we developed deep learning-based method to classify the type of surgery performed for epiretinal membrane (ERM) removal, either internal limiting membrane (ILM) removal or ERM-alone removal. Our model, based on the ResNet18 convolutional neural network (CNN) architecture, utilizes postoperative optical coherence tomography (OCT) center scans as inputs. We evaluated the model using both original scans and scans preprocessed with energy crop and wavelet denoising, achieving 72% accuracy on preprocessed inputs, outperforming the 66% accuracy achieved on original scans. To further improve accuracy, we integrated tunable wavelet units with two key adaptations: Orthogonal Lattice-based Wavelet Units (OrthLatt-UwU) and Perfect Reconstruction Relaxation-based Wavelet Units (PR-Relax-UwU). These units allowed the model to automatically adjust filter coefficients during training and were incorporated into downsampling, stride-two convolution, and pooling layers, enhancing its ability to distinguish between ERM-ILM removal and ERM-alone removal, with OrthLattUwU boosting accuracy to 76% and PR-Relax-UwU increasing performance to 78%. Performance comparisons showed that our AI model outperformed a trained human grader, who achieved only 50% accuracy in classifying the removal surgery types from postoperative OCT scans. These findings highlight the potential of CNN based models to improve clinical decision-making by providing more accurate and reliable classifications. To the best of our knowledge, this is the first work to employ tunable wavelets for classifying different types of ERM removal surgery.