Multiple sclerosis is the most common immune-mediated disorder. It directly affects the central nervous system. MS is a demyelinating disease in which the insulating covers of nerve cells in the brain and spinal cord heavily get damaged.
Multiple sclerosis is usually begun between the ages of 20 and 50 and it is twice as common in women as in men. The causes of Multiple sclerosis is not clear yet. It’s considered an autoimmune disease in which the body’s immune system attacks its own tissues.
Multiple sclerosis is an incurable disease. In 2015 about 2.3 million people were affected globally. That year about 18,900 people died from MS. Treatments can help to speed up the recovery process after an attack and prevent the next attack, but it can’t cure it.
Medications used to treat MS, while modestly effective, can have side effects and be poorly tolerated.
Now a team of researchers has developed a deep learning system to detect multiple sclerosis (MS) lesions in the spinal cord and intramedullary from conventional MRI data. Researcher builds a neural network called a convolutional neural network.
CNN’s is made up of neurons with learnable weights and biases and most commonly applied to analyzing visual imagery.
It is created by the University of Montreal, San Francisco General Hospital, Massachusetts General Hospital, the National Institute of Health (NIH), Stanford University, Vanderbilt University, Harvard Medical School, and many other institutions.
“Segmentation of the spinal cord and lesions from MRI data provides measures of atrophy and lesion burden, which are key criteria for the diagnosis, prognosis and longitudinal monitoring in MS.
Achieving robust and reliable segmentation across multi-center spinal cord data is challenging because of the large variability related to acquisition parameters and image artifacts,” the researchers wrote in their research paper. “There is a need for robust and automatic segmentation tools for the spinal cord and the MS lesions within.”
The goal of this study was to develop a fully-automatic framework, robust to variability in both image parameters and clinical condition, for segmentation of the spinal cord and intramedullary MS lesions from conventional MRI data.
The most challenging task for the researcher was the segmentation of the spinal cord across multi-center, because of the large variability related to acquisition parameters and image artifacts.
The researcher trained the convolutional neural network on MRI images of adult subjects (459 healthy controls, 471 MS patients, and 112 with other spinal pathologies) to automatically detect lesions in both the spinal cord and intramedullary.
Data spanned has 3 contrasts (T1-, T2- and T2*-weighted) for a total of 1943 volumes and featured large heterogeneity in terms of resolution, orientation, coverage and clinical conditions. They use NVIDIA Tesla P100 GPUs, and the cuDNN-accelerated Keras and TensorFlow deep learning frameworks.
The proposed cord and lesion automatic segmentation approach is based on a cascade of two Convolutional Neural Networks (CNN): a first CNN with 2D dilated convolutions detects the spinal cord centerline followed by a second 3D CNN that segments the spinal cord and lesions.
“When compared to a state-of-the-art spinal cord segmentation method (PropSeg), our CNN-based approach showed a median Dice of 95% vs. 88% for PropSeg. Regarding lesion segmentation, our framework, when compared with manual segmentation of MS patients, provided a lesion-wise detection sensitivity of 83%, a precision of 77%, a relative volume difference of 15%, and a Dice of 60%” the researchers said.
The proposed framework is open-source and available in the Spinal Cord Toolbox.
The research was published and was submitted on the NeuroImage Journal.
More in AI :