Comparison of the Iowa Reference Algorithm to the Heidelberg Spectralis optical coherence tomography segmentation algorithm

Abstract

For spectral-domain optical coherence tomography (SD-OCT) studies of neurodegeneration, it is important to understand how segmentation algorithms differ in retinal layer thickness measurements, segmentation error locations and the impact of manual correction. Using macular SD-OCT images of frontotemporal degeneration patients and controls, we compare the individual and aggregate retinal layer thickness measurements provided by two commonly used algorithms, the Iowa Reference Algorithm and Heidelberg Spectralis, with manual correction of significant segmentation errors. We demonstrate small differences of most retinal layer thickness measurements between these algorithms. Outer sectors of the Early Treatment Diabetic Retinopathy Study grid require a greater percent of eyes to be corrected than inner sectors of the retinal nerve fiber layer (RNFL). Manual corrections affect thickness measurements mildly, resulting in at most a 5% change in RNFL thickness. Our findings can inform researchers how to best use different segmentation algorithms when comparing retinal layer thicknesses. K E Y W O R D S frontotemporal degeneration, Iowa Reference Algorithm, optical coherence tomography, retinal layer thickness, segmentation algorithms, Spectralis

Optical Coherence Tomography for Three-Dimensional Imaging in the Biomedical Field: A Review

“…However, computer-aided diagnosis has a much higher resolution than the human eye and can accurately analyze and judge the hidden information in the OCT image. Some segmentation algorithms such as Iowa Reference Algorithm could avoid the error caused by manual segmentation [103], thus achieving a more accurate diagnosis. With the continuous development of machine learning [54,57], computer-aided diagnosis is expected to realize automatic image reading and change the diagnostic model of traditional medicine in the future, which can not only reduce the workload of doctors but also may alleviate the shortage of medical resources to a certain extent.…”

Advances in Photoreceptor and Retinal pigment epithelium Quantifications in intermediate AMD: High-Res versus Standard SPECTRALIS OCT

“…For the presegmentation of the RPE layer, the IOWA Reference Algorithm (Retinal Image Analysis Lab, Iowa Institute for Biomedical Imaging, Iowa City, IA) was used. 13 The borders of the RPE layer were defined as the inner and outer boundary of the RPE. Drusen and nondrusen areas were sectioned using a deep learning algorithm featuring multiple decoding branches.…”