arXiv (Cornell University) · 2021 · 20 citations · 12 references
ComputingBiomedical EngineeringComputer ScienceComputer VisionMachine LearningUltrasonographyDeep LearningMedical Image AnalysisMedical ImagingTransfer LearningVolume SegmentationConvolutional Neural Network SegmentationConvolutional Neural NetworksData AugmentationDiceMask PredictionMedical Image SegmentationUltrasound Image Segmentation
Transfer learning (TL) for medical image segmentation helps deep learning models achieve more accurate performances when there are scarce medical images. This study focuses on completing segmentation of the ribs from lung ultrasound images and finding the best TL technique with U-Net, a convolutional neural network for precise and fast image segmentation. Two approaches of TL were used, using a pre-trained VGG16 model to build the U-Net (V-Unet) and pre-training U-Net network with grayscale natural salient object dataset (X-Unet). Visual results and dice coefficients (DICE) of the models were compared. X-Unet showed more accurate and artifact-free visual performances on the actual mask prediction, despite its lower DICE than V-Unet. A partial-frozen network fine-tuning (FT) technique was also applied to X-Unet to compare results between different FT strategies, which FT all layers slightly outperformed freezing part of the network. The effect of dataset sizes was also evaluated, showing the importance of the combination between TL and data augmentation.
12
Fully convolutional networks for semantic segmentation
Jonathan Long, Evan Shelhamer, Trevor Darrell · 2015 · 36.9K citations
NAS-Unet: Neural Architecture Search for Medical Image Segmentation
Yu Weng, Tianbao Zhou, Yujie Li et al. · IEEE Access · 2019 · 495 citations · Full text
A deep learning-based algorithm for 2-D cell segmentation in microscopy images
Yousef Al‐Kofahi, Alla Zaltsman, Robert J. Graves et al. · BMC Bioinformatics · 2018 · 242 citations · Full text
Computing, Biology, Computer Science +15
Image Segmentation Algorithms Overview
Yuheng Song · arXiv (Cornell University) · 2017 · 128 citations · Full text