Automatic semantic segmentation and detection of vertebras and intervertebral discs by neural networks

: To realize a tool for automatic segmentation and detection of lumbar disc degenerative disease fractures in MRI images using convolutional neural networks. We developed, on one hand, Picture Archiving Communication System (PACS) with DICOM viewer (Digital Imaging Communications Medicine) to extract training data implement 2 CNN networks dedicated the task other analysis simple pathologies hand.Two hundred forty-four scans T2 weighted sagittal were selected at university hospital Pasteur Nice - France.After accomplishing classification all structures interest, we trained two (U-Net++ Yolov5x) segment detect discs vertebras. Neural allowed semantic segmentations good accuracy order 0.96 0.93 DICE index intervertebral vertebral bodies respectively.They are less effective detecting common (degenerative disease, herniation, fractures) an area under precision-recall curve 0.88 0.76 disease. Our work has shown efficiency discs, but progress remains be made discopathy fractures.On this last point, believe that lower performance can attributed lack better performances will achieved increase set our home PACS. also provide regions interest conditions.