4.5 Article

ALL-Net: Anatomical information lesion-wise loss function integrated into neural network for multiple sclerosis lesion segmentation

Journal

NEUROIMAGE-CLINICAL
Volume 32, Issue -, Pages -

Publisher

ELSEVIER SCI LTD
DOI: 10.1016/j.nicl.2021.102854

Keywords

Multiple sclerosis; Convolutional neural network; Lesion segmentation; MRI; Deep learning

Categories

Funding

  1. National Institute of Health [R01NS105144]
  2. National MS Society [RR-1602-07671]

Ask authors/readers for more resources

The ALL-Net algorithm, based on deep convolutional neural network and anatomic information, achieved significant improvements in both pixel-wise and lesion-wise metrics on the ISBI-2015 challenge dataset and the Cornell MS dataset. This method effectively addressed the challenges of accurately detecting and segmenting MS brain lesions.
Accurate detection and segmentation of multiple sclerosis (MS) brain lesions on magnetic resonance images are important for disease diagnosis and treatment. This is a challenging task as lesions vary greatly in size, shape, location, and image contrast. The objective of our study was to develop an algorithm based on deep convolutional neural network integrated with anatomic information and lesion-wise loss function (ALL-Net) for fast and accurate automated segmentation of MS lesions. Distance transformation mapping was used to construct a convolutional module that encoded lesion-specific anatomical information. To overcome the lesion size imbalance during network training and improve the detection of small lesions, a lesion-wise loss function was developed in which individual lesions were modeled as spheres of equal size. On the ISBI-2015 longitudinal MS lesion segmentation challenge dataset (19 subjects in total), ALL-Net achieved an overall score of 93.32 and was amongst the top performing methods. On the larger Cornell MS dataset (176 subjects in total), ALL-Net significantly improved both voxel-wise metrics (Dice improvement of 3.9% to 35.3% with p-values ranging from p < 0.01 to p < 0.0001, and AUC of voxel-wise precision-recall curve improvement of 2.1% to 29.8%) and lesion wise metrics (lesion-wise F1 score improvement of 12.6% to 29.8% with all p-values p < 0.0001, and AUC of lesion-wise ROC curve improvement of 1.4% to 20.0%) compared to leading publicly available MS lesion segmentation tools.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.5
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available