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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Le, An, Mehta, Nehal, Freeman, William, Nagel, Ines, Tran, Melanie, Heinke, Anna, Agnihotri, Akshay, Cheng, Lingyun, Bartsch, Dirk-Uwe, Nguyen, Hung, Nguyen, Truong, An, Cheolhong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913921325072384
author Le, An
Mehta, Nehal
Freeman, William
Nagel, Ines
Tran, Melanie
Heinke, Anna
Agnihotri, Akshay
Cheng, Lingyun
Bartsch, Dirk-Uwe
Nguyen, Hung
Nguyen, Truong
An, Cheolhong
author_facet Le, An
Mehta, Nehal
Freeman, William
Nagel, Ines
Tran, Melanie
Heinke, Anna
Agnihotri, Akshay
Cheng, Lingyun
Bartsch, Dirk-Uwe
Nguyen, Hung
Nguyen, Truong
An, Cheolhong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_00743
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Tunable Wavelet Unit based Convolutional Neural Network in Optical Coherence Tomography Analysis Enhancement for Classifying Type of Epiretinal Membrane Surgery
Le, An
Mehta, Nehal
Freeman, William
Nagel, Ines
Tran, Melanie
Heinke, Anna
Agnihotri, Akshay
Cheng, Lingyun
Bartsch, Dirk-Uwe
Nguyen, Hung
Nguyen, Truong
An, Cheolhong
Image and Video Processing
Computer Vision and Pattern Recognition
Signal Processing
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.
title Tunable Wavelet Unit based Convolutional Neural Network in Optical Coherence Tomography Analysis Enhancement for Classifying Type of Epiretinal Membrane Surgery
topic Image and Video Processing
Computer Vision and Pattern Recognition
Signal Processing
url https://arxiv.org/abs/2507.00743