Lumbar Spinal Stenosis Analysis with Deep Learning Based Decision Support Systems

Abstract

Lumbar spinal stenosis is a disease with negative consequences and usually occurs in 3 vertebrae, disc and canal located in the lower back. In this region, the nerves in the canal can be exposed to pressure for various reasons, and diseases occur. Surgical operation is required to treat canal narrowing, and the exact location and size of the spinal stenosis is vital importance for the operation. The UNet model, which is an example of this network, can be further deeper using different deep learning networks. In this study, it is aimed to be the basis for the creation of a system that helps in the diagnosis of canal stenosis by using a deeper network. The ResUNET model, in which ResNet is used as the backbone, achieved an average IoU of 0.987. This result reveals that MR images can be used in segmentation for the diagnosis of Lumbar spinal stenosis.

Nerve Root Compression Analysis to Find Lumbar Spine Stenosis on MRI Using CNN

“…The area under the receiver operator characteristic curve (AUROC) values used for the binary classification of facet and neural foraminal stenosis were 0.92 and 0.93, respectively. Sinan et al [37] proposed an LSS-VGG16 and U-Net model that detects LSS in MR and CT images and achieved 87.70% classification accuracy on VGG16. A total of 1560 MR images were used with U-Net, with a 0.93 DICE score.…”

“…For example, the methods proposed in [22,35] both use a CNN model for LSS detection, obtaining accuracies of 87.75% and 84.5%, respectively. Pretrained models have also been deployed, such as ResNet in [36] and VGG16 in [37]. Higher performance was reported in [38], with 94% accuracy, while the authors of [39] recently reported 95% accuracy.…”

Görme engelliler için nesne tanıma ve resim altyazısını derin öğrenme teknikleriyle entegre eden verimli bir aktivite tanıma modeli

“…Her LSTM yapısı, bilginin hangi kısımlarının unutulacağını veya hatırlanacağını, bir sonraki aşamaya geçilip geçilmeyeceği bilgisini içeren unutma, giriş ve çıkış kapılarından meydana gelmektedir. Uzun kısa dönem hafıza ağlarının metin sınıflandırma [31][32], hastalık tespiti [33], zaman serisi analizi [34,35], görüntü tanıma [36][37], finansal ürünlerin fiyat tahmini [38], satış tahmini [39] gibi alanlarda uygulamaları bulunmaktadır. Bu çalışmada, uzun kısa dönem hafıza ağları (LSTM) modeli görüntü altyazısı oluşturma amacıyla kullanılmıştır.…”