Automated segmentation of multiple sclerosis lesions based on convolutional neural networks

Messaoud, Nada Haj; Mansour, A. Ben; Aissi, M.; Ayari, Rim; Frih, M.; Abdallah, Asma Ben; Bedoui, Mohamed Hédi

doi:10.1080/21681163.2022.2129454

Cited by 2 publications

(2 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cropping the framing plans in small patches is the standard practice for deep learningbased methods for semantic segmentation because of the limitations of the GPU memory for accommodating deep learning operations. Therefore, overlapping the predictions patches (Messaoud et al, 2022), averaging (Müller et al, 2020), clipping (Huang et al, 2018) and eliminating the smaller areas (Kestur et al, 2019) in the prediction is used herein during this stage for improving the fi nal prediction. The prediction for the columns model gives an image of 512×512 pixels and then the image is clipped 100 pixels along the four borders of the image, with a fi nal size of 312×312 pixels.…”

Section: Regenerating the Framing Planmentioning

confidence: 99%

“…Using semantic segmentation results for calculating the area ratios for columns and walls makes the result sensitive to the noise in the prediction. The intensity of each pixel in an image is binarized using a threshold of 0.70 (Messaoud et al, 2022). Then, a dilatation kernel is slid over the generated framing plan with a size of tenby-ten pixels, (a kernel size chosen based on experience in this dataset) to fi ll the pixel with pixel value of zero inside the elements (columns, and walls) that did not get fi lled through the pixel-wise prediction.…”

Section: Regenerating the Framing Planmentioning

confidence: 99%

See 1 more Smart Citation

Towards rapid and automated vulnerability classification of concrete buildings

Iturburu

Kwannandar

Dyke

et al. 2023

Earthq. Eng. Eng. Vib.

View full text Add to dashboard Cite

With the overwhelming number of older reinforced concrete buildings that need to be assessed for seismic vulnerability in a city, local governments face the question of how to assess their building inventory. By leveraging engineering drawings that are stored in a digital format, a well-established method for classification reinforced concrete buildings with respect to seismic vulnerability, and machine learning techniques, we have developed a technique to automatically extract quantitative information from the drawings to classify vulnerability. Using this technique, stakeholders will be able to rapidly classify buildings according to their seismic vulnerability and have access to information they need to prioritize a large building inventory. The approach has the potential to have significant impact on our ability to rapidly make decisions related to retrofit and improvements in our communities. In the Los Angeles County alone it is estimated that several thousand buildings of this type exist. The Hassan index is adopted here as the method for automation due to its simple application during the classification of the vulnerable reinforced concrete buildings. This paper will present the technique used for automating information extraction to compute the Hassan index for a large building inventory.

show abstract

Section: Regenerating the Framing Planmentioning

confidence: 99%

Section: Regenerating the Framing Planmentioning

confidence: 99%

Towards rapid and automated vulnerability classification of concrete buildings

Iturburu

Kwannandar

Dyke

et al. 2023

Earthq. Eng. Eng. Vib.

View full text Add to dashboard Cite

show abstract

A deep learning-based approach for Multiple Sclerosis Lesion Segmentation

Abdelali,

Sahnoun,

Sakka

et al. 2024

Preprint

View full text Add to dashboard Cite

Purpose: Multiple Sclerosis (MS) is a chronic disease of the Central Nervous System (CNS), characterized by the presence of disseminated lesions in the brain and Spinal Cord (SC). Magnetic Resonance Imaging (MRI) has become an essential tool for studying the anatomy and functions of the CNS in vivo, enabling not only the identification of brain structures but also the detection of damaged tissue in various neurodegenerative diseases, including MS. The segmentation of lesions on MR images is a crucial step in the diagnosis and monitoring of the disease. However, manual segmentation of MS lesions is a complex and time-consuming task requiring considerable expertise. Methods: This paper proposes a fully automated method for MS lesion segmentation based on a Convolutional Neural Network (CNN) architecture. The model was trained on datasets from the MICCAI 2016 and ISBI 2015 international challenges. FLAIR images from these databases were used as input to the CNN. Results: The results show a significant improvement in the accuracy and robustness of the model, resulting in high-quality segmentation of MS lesions. The model achieved remarkable performance, with a Dice Similarity Coefficient (DSC) of over 89%, outperforming recent methods. Conclusion: These promising results underline the considerable potential for future advances in the automated segmentation of MS lesions.

show abstract

Automated segmentation of multiple sclerosis lesions based on convolutional neural networks

Cited by 2 publications

References 50 publications

Towards rapid and automated vulnerability classification of concrete buildings

Towards rapid and automated vulnerability classification of concrete buildings

A deep learning-based approach for Multiple Sclerosis Lesion Segmentation

Contact Info

Product

Resources

About