Consensus Based Medical Image Segmentation Using Semi-Supervised Learning And Graph Cuts

Mahapatra, Dwarikanath

doi:10.48550/arxiv.1612.02166

Cited by 2 publications

(2 citation statements)

References 21 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Segmentation of lungs from chest CT scans is a widely explored topic [150], [12], [61], [91], [67], [42], [22] since it facilitates diagnosis and quantification of lung diseases [24]. [36], [110], [66], [59], [64], [5], [83], [84], [48] use support vector machines (SVM) to detect lung nodules from CT scans.Nodule extraction is challenging due to similar appearance with the background. Deep learning algorithms have been able to overcome this challenge by learning powerful discriminative features.…”

Section: A Chest Ct Segmentationmentioning

confidence: 99%

CT Image Synthesis Using Weakly Supervised Segmentation and Geometric Inter-Label Relations For COVID Image Analysis

Mahapatra¹,

Singh²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

While medical image segmentation is an important task for computer aided diagnosis, the high expertise requirement for pixelwise manual annotations makes it a challenging and time consuming task. Since conventional data augmentations do not fully represent the underlying distribution of the training set, the trained models have varying performance when tested on images captured from different sources. Most prior work on image synthesis for data augmentation ignore the interleaved geometric relationship between different anatomical labels. We propose improvements over previous GAN-based medical image synthesis methods by learning the relationship between different anatomical labels. We use a weakly supervised segmentation method to obtain pixel level semantic label map of images which is used learn the intrinsic relationship of geometry and shape across semantic labels. Latent space variable sampling results in diverse generated images from a base image and improves robustness. We use the synthetic images from our method to train networks for segmenting COVID-19 infected areas from lung CT images. The proposed method outperforms state-of-theart segmentation methods on a public dataset. Ablation studies also demonstrate benefits of integrating geometry and diversity.

show abstract

Section: A Chest Ct Segmentationmentioning

confidence: 99%

CT Image Synthesis Using Weakly Supervised Segmentation and Geometric Inter-Label Relations For COVID Image Analysis

Mahapatra¹,

Singh²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, we also observe that GANs tend to misregister local regions with multiple structures. To address this shortcoming, in [7,94,95,96,97,98] we propose a joint registration and segmentation method that incorporates segmentation information into the registration process to achieve better registration performance than conventional methods. The segmentation information is integrated as part of the adversarial loss function and experimental results show its significant contribution in improving registration accuracy.…”

Section: Related Workmentioning

confidence: 99%

Generative Adversarial Networks And Domain Adaptation For Training Data Independent Image Registration

Mahapatra¹

2019

Preprint

Self Cite

View full text Add to dashboard Cite

Medical image registration is an important task in automated analysis of multimodal images and temporal data involving multiple patient visits. Conventional approaches, although useful for different image types, are time consuming. Of late, deep learning (DL) based image registration methods have been proposed that outperform traditional methods in terms of accuracy and time. However, DL based methods are heavily dependent on training data and do not generalize well when presented with images of different scanners or anatomies. We present a DL based approach that can perform medical image registration of one image type despite being trained with images of a different type. This is achieved by unsupervised domain adaptation in the registration process and allows for easier application to different datasets without extensive retraining.To achieve our objective we train a network that transforms the given input image pair to a latent feature space vector using autoencoders. The resultant encoded feature space is used to generate the registered images with the help of generative adversarial networks (GANs). This feature transformation ensures greater invariance to the input image type. Experiments on chest Xray, retinal and brain MR images show that our method, trained on one dataset gives better registration performance for other datasets, outperforming conventional methods that do not incorporate domain adaptation.

show abstract

Consensus Based Medical Image Segmentation Using Semi-Supervised Learning And Graph Cuts

Cited by 2 publications

References 21 publications

CT Image Synthesis Using Weakly Supervised Segmentation and Geometric Inter-Label Relations For COVID Image Analysis

CT Image Synthesis Using Weakly Supervised Segmentation and Geometric Inter-Label Relations For COVID Image Analysis

Generative Adversarial Networks And Domain Adaptation For Training Data Independent Image Registration

Contact Info

Product

Resources

About