A new convolutional neural network based on combination of circlets and wavelets for macular OCT classification.
A new convolutional neural network based on combination of circlets and wavelets for macular OCT classification.
复制标题
DOI：
10.1038/s41598-023-50164-7
复制
发表时间：
2023-12-19
影响因子：
4.6
通讯作者：
Rabbani, Hossein
中科院分区：
文献类型：
--
作者：
Arian, Roya;Vard, Alireza;Kafieh, Rahele;Plonka, Gerlind;Rabbani, Hossein
人工智能（AI）算法，包括机器学习和深度学习，可以帮助眼科医生通过分析视网膜光学相干断层扫描（OCT）图像来早期检测各种眼部异常。尽管这些算法取得了相当大的进展，但在医学成像领域仍然存在一些局限性，其中缺乏数据是一个常见的问题。因此，特定的图像处理技术，如时间-频率变换，可以与AI算法结合使用，以提高诊断精度。本研究探讨了非数据自适应时频变换，特别是X-lets，对OCT B扫描分类的影响。为此，每个B扫描都使用每个考虑的X-let进行变换，所有子带都用作设计的2D卷积神经网络（CNN）的输入，以提取最佳特征，随后将其馈送到分类器。评估每类准确性表明，使用二维离散小波变换（2D-DWT）产生上级的结果，为正常情况下，而circlet变换优于其他的X-lets异常情况下，其特征在于在他们的视网膜结构中的圆圈（由于液体的积累）。因此，我们提出了一种新的变换命名为CircWave通过连接所有的子带从2D-DWT和circlet变换。我们的目标是同时提高正常和异常情况下的每类精度。我们的研究结果表明，基于CircWave变换的分类结果优于那些来自原始图像或任何单独的变换。此外，从CircWave子带重建的B扫描的Grad-CAM类激活可视化突出了异常情况下的圆形形成和正常情况下的直线，而不是原始B扫描中的无关区域。为了评估我们的方法的通用性，我们将其应用于从不同的成像系统获得的另一个数据集。我们在第一和第二个数据集分别实现了94.5%和90%的准确率，这与以前的研究结果相当。基于CircWave子带（即CircWaveNet）的拟议CNN不仅产生了上级结果，而且还提供了更多可解释的结果，重点关注眼科医生的关键特征。
Artificial intelligence (AI) algorithms, encompassing machine learning and deep learning, can assist ophthalmologists in early detection of various ocular abnormalities through the analysis of retinal optical coherence tomography (OCT) images. Despite considerable progress in these algorithms, several limitations persist in medical imaging fields, where a lack of data is a common issue. Accordingly, specific image processing techniques, such as time–frequency transforms, can be employed in conjunction with AI algorithms to enhance diagnostic accuracy. This research investigates the influence of non-data-adaptive time–frequency transforms, specifically X-lets, on the classification of OCT B-scans. For this purpose, each B-scan was transformed using every considered X-let individually, and all the sub-bands were utilized as the input for a designed 2D Convolutional Neural Network (CNN) to extract optimal features, which were subsequently fed to the classifiers. Evaluating per-class accuracy shows that the use of the 2D Discrete Wavelet Transform (2D-DWT) yields superior outcomes for normal cases, whereas the circlet transform outperforms other X-lets for abnormal cases characterized by circles in their retinal structure (due to the accumulation of fluid). As a result, we propose a novel transform named CircWave by concatenating all sub-bands from the 2D-DWT and the circlet transform. The objective is to enhance the per-class accuracy of both normal and abnormal cases simultaneously. Our findings show that classification results based on the CircWave transform outperform those derived from original images or any individual transform. Furthermore, Grad-CAM class activation visualization for B-scans reconstructed from CircWave sub-bands highlights a greater emphasis on circular formations in abnormal cases and straight lines in normal cases, in contrast to the focus on irrelevant regions in original B-scans. To assess the generalizability of our method, we applied it to another dataset obtained from a different imaging system. We achieved promising accuracies of 94.5% and 90% for the first and second datasets, respectively, which are comparable with results from previous studies. The proposed CNN based on CircWave sub-bands (i.e. CircWaveNet) not only produces superior outcomes but also offers more interpretable results with a heightened focus on features crucial for ophthalmologists.
登录
查看更多内容
影响因子：
4.6
作者：
通讯作者：
--
影响因子：
4.4
作者：
Golpardaz, Maryam;Helfroush, Mohammad Sadegh;Danyali, Habibollah
通讯作者：
Danyali, Habibollah
影响因子：
2.4
作者：
Komma, Swetha;Chhablani, Jay;Senthil, Sirisha
通讯作者：
Senthil, Sirisha
影响因子：
3.9
作者：
Das, Vineeta;Prabhakararao, Eedara;Bora, Prabin Kumar
通讯作者：
Bora, Prabin Kumar
影响因子：
3.5
作者：
Kafieh R;Rabbani H;Abramoff MD;Sonka M
通讯作者：
Sonka M