Deep Learning for Medical Image Segmentation

  title={Deep Learning for Medical Image Segmentation},
  author={Matthew Lai},
Pixel accurate 2-D, 3-D medical image segmentation to identify abnormalities for further analysis is on high demand for computer-aided medical imaging applications. Various segmentation algorithms have been studied and applied in medical imaging for many years, but the problem remains challenging due to growing a large number of variety of applications starting from lung disease diagnosis based on x-ray images, nucleus detection, and segmentation based on microscopic pictures to kidney tumour… 

Figures and Tables from this paper

Accelerating 3D Medical Image Segmentation by Adaptive Small-Scale Target Localization

A new segmentation method with a human-like technique to segment a 3D study by analyzing the image at a small scale to identify areas of interest and then process only relevant feature-map patches that preserves state-of-the-art segmentation quality.

Deep learning based automatic segmentation of metastasis hotspots in thorax bone SPECT images

The built segmentation models are workable on identifying and segmenting hotspots of metastasis in bone SEPCT images, achieving a value of 0.6103 for PA (accuracy), CPA (precision), Rec (recall) and IoU, respectively.

Automated brain tumor segmentation on multi-modal MR image using SegNet

Experimental results demonstrate that using SegNet models with 3D MRI datasets and integrating the four maximum feature maps with pixel intensity values of the original MRI modalities has potential to perform well on brain tumor segmentation.

Pancreas Segmentation in Abdominal CT Scans using Inter-/Intra-Slice Contextual Information with a Cascade Neural Network

  • Zhengzheng YangLei Zhang Yi Lv
  • Computer Science, Medicine
    2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
  • 2019
A new approach for automatic pancreas segmentation of CT images using inter-/intra-slice contextual information with a cascade neural network is proposed and outperforms the state-of-the-arts with an average Dice Similarity Coefficient of 87.72 for NIH dataset with 4-fold cross-validation.

Thickened 2 D Networks for 3 D Medical Image Segmentation

A novel approach which thickens the input of a 2D network, so that the model is expected to enjoy both the stability and efficiency of 2D networks as well as the ability of 3D networks in modeling volumetric contexts.

Improving Semantic Image Segmentation by Object Localization

An end-to-end neural network that improves the segmentation accuracy of FCN by incorporating an object localization unit that performs well despite the high class imbalance and it outperforms existing methods on small object segmentation.

Multi-parametric Magnetic Resonance Imaging Fusion for Automatic Classification of Prostate Cancer

A fully automatic CAD pipeline of PCa using mp-MRI data is presented, and a pipeline that works relatively the best for both diagnostic tasks, two important components of which are stacking three adjacent slices as the input and performing decision-level fusion with specific loss weights are identified.

Thickened 2D Networks for 3D Medical Image Segmentation

A novel approach which thickens the input of a 2D network, so that the model is expected to enjoy both the stability and efficiency of 2D networks as well as the ability of 3D networks in modeling volumetric contexts.

2D-Based Coarse-to-Fine Approaches for Small Target Segmentation in Abdominal CT Scans

  • Yuyin ZhouQihang Yu A. Yuille
  • Computer Science
    Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics
  • 2019
This chapter proposes two coarse-to-fine mechanisms which use prediction from the first (coarse) stage to shrink the input region for the second (fine) stage and inserts a saliency transformation module between the two stages.

Automatic Segmentation of MRI Images for Brain Tumor using unet

A completely programmed strategy for brain tumor division is proposed that is created utilizing U-Net based deep convolutional network for dependable completely programmed division strategy for the brain tumors division.



Deep Feature Learning for Knee Cartilage Segmentation Using a Triplanar Convolutional Neural Network

A novel system for voxel classification integrating three 2D CNNs, which have a one-to-one association with the xy, yz and zx planes of 3D image, respectively, which performs better than a state-of-the-art method using 3D multi-scale features.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

A New 2.5D Representation for Lymph Node Detection Using Random Sets of Deep Convolutional Neural Network Observations

This work operates a preliminary candidate generation stage, towards -100% sensitivity at the cost of high FP levels (-40 per patient), to harvest volumes of interest (VOI), and decomposes any 3D VOI by resampling 2D reformatted orthogonal views N times, via scale, random translations, and rotations with respect to the VOI centroid coordinates.

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures, including FCN and DeconvNet.

Very Deep Convolutional Networks for Large-Scale Image Recognition

This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

A Closed-Form Solution to Natural Image Matting

A closed-form solution to natural image matting that allows us to find the globally optimal alpha matte by solving a sparse linear system of equations and predicts the properties of the solution by analyzing the eigenvectors of a sparse matrix, closely related to matrices used in spectral image segmentation algorithms.

Fully convolutional networks for semantic segmentation

The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.

ImageNet classification with deep convolutional neural networks

A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.

A Survey of Deep Learning-Based Object Detection

This survey provides a comprehensive overview of a variety of object detection methods in a systematic manner, covering the one-stage and two-stage detectors, and lists the traditional and new applications.