MS-Net: Mixed-Supervision Fully-Convolutional Networks for Full-Resolution Segmentation

Shah, Meet; Merchant, S. N.; Awate, Suyash P.

doi:10.1007/978-3-030-00937-3_44

Cited by 37 publications

(45 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…as a regularization in supervised-only learning) to the segmentation performance; 2) the contribution of adding different amounts of unlabeled data into the equivariance learning; 3) how these contributions vary with the size of the labeled portion of the training set. We compare the proposed method trained in the small data (20 labeled images) and full supervision regimes with state-of-the-art methods [14,3,8,4] and the inter-observer agreement [16]. and t out 2 .…”

Section: Introductionmentioning

confidence: 99%

Semi-supervised Medical Image Segmentation via Learning Consistency Under Transformations

Bortsova

Dubost

Hogeweg³

et al. 2019

Lecture Notes in Computer Science

156

113

View full text Add to dashboard Cite

The scarcity of labeled data often limits the application of supervised deep learning techniques for medical image segmentation. This has motivated the development of semi-supervised techniques that learn from a mixture of labeled and unlabeled images. In this paper, we propose a novel semi-supervised method that, in addition to supervised learning on labeled training images, learns to predict segmentations consistent under a given class of transformations on both labeled and unlabeled images. More specifically, in this work we explore learning equivariance to elastic deformations. We implement this through: 1) a Siamese architecture with two identical branches, each of which receives a differently transformed image, and 2) a composite loss function with a supervised segmentation loss term and an unsupervised term that encourages segmentation consistency between the predictions of the two branches. We evaluate the method on a public dataset of chest radiographs with segmentations of anatomical structures using 5-fold crossvalidation. The proposed method reaches significantly higher segmentation accuracy compared to supervised learning. This is due to learning transformation consistency on both labeled and unlabeled images, with the latter contributing the most. We achieve the performance comparable to state-of-the-art chest X-ray segmentation methods while using substantially fewer labeled images.

show abstract

Section: Introductionmentioning

confidence: 99%

Semi-supervised Medical Image Segmentation via Learning Consistency Under Transformations

Bortsova

Dubost

Hogeweg³

et al. 2019

Lecture Notes in Computer Science

156

113

View full text Add to dashboard Cite

show abstract

“…Methods able to exploit weaker forms of annotations (bounding boxes, slice-level labels) for training of segmentation models are therefore of interest. In particular, methods combining weakly-annotated and fully-annotated training images were recently proposed in [35,47]. As our system was able to produce accurate segmentations in a large majority of cases and the rare observed errors were mainly on boundaries of organs, the system could be used for generation of bounding boxes (subsequently verified by a human) which could be used to train segmentation models which are able to exploit this type of annotations.…”

Section: Discussionmentioning

confidence: 99%

Anatomically consistent CNN-based segmentation of organs-at-risk in cranial radiotherapy

et al. 2020

View full text Add to dashboard Cite

Planning of radiotherapy involves accurate segmentation of a large number of organs at risk, i.e. organs for which irradiation doses should be minimized to avoid important side effects of the therapy. We propose a deep learning method for segmentation of organs at risk inside the brain region, from Magnetic Resonance (MR) images. Our system performs segmentation of eight structures: eye, lens, optic nerve, optic chiasm, pituitary gland, hippocampus, brainstem and brain. We propose an efficient algorithm to train neural networks for an end-to-end segmentation of multiple and nonexclusive classes, addressing problems related to computational costs and missing ground truth segmentations for a subset of classes. We enforce anatomical consistency of the result in a postprocessing step, in particular we introduce a graph-based algorithm for segmentation of the optic nerves, enforcing the connectivity between the eyes and the optic chiasm. We report cross-validated quantitative results on a database of 44 contrast-enhanced T1-weighted MRIs with provided segmentations of the considered organs at risk, which were originally used for radiotherapy planning. In addition, the segmentations produced by our model on an independent test set of 50 MRIs are evaluated by an experienced radiotherapist in order to qualitatively assess their accuracy. The mean distances between produced segmentations and the ground truth ranged from 0.1 mm to 0.7 mm across different organs. A vast majority (96 %) of the produced segmentations were found acceptable for radiotherapy planning.

show abstract

“…For the U-Net+Unary sSE, Unary sSE module is added after every convolution stage. For the Variant MS-Net, we follow the thought of MS-Net [8] and build a multi-stream network based on U-Net, where all features from the Decoder are taken into the detection stream DU. We also compare to a reduced version of our model (MSDN-), where we remove the DU and only preserve the U-NET and the Binary sSE modules.…”

Section: Methodsmentioning

confidence: 99%

Mixed-Supervised Dual-Network for Medical Image Segmentation

Wang

Ben‐Shlomo

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Deep learning based medical image segmentation models usually require large datasets with high-quality dense segmentations to train, which are very time-consuming and expensive to prepare. One way to tackle this challenge is using the mixed-supervised learning framework, in which only a part of data is densely annotated with segmentation label and the rest is weakly labeled with bounding boxes. The model is trained jointly in a multi-task learning setting. In this paper, we propose Mixed-Supervised Dual-Network (MSDN), a novel architecture which consists of two separate networks for the detection and segmentation tasks respectively, and a series of connection modules between the layers of the two networks. These connection modules are used to transfer useful information from the auxiliary detection task to help the segmentation task. We propose to use a recent technique called Squeeze and Excitation in the connection module to boost the transfer. We conduct experiments on two medical image segmentation datasets. The proposed MSDN model outperforms multiple baselines.

show abstract

MS-Net: Mixed-Supervision Fully-Convolutional Networks for Full-Resolution Segmentation

Cited by 37 publications

References 9 publications

Semi-supervised Medical Image Segmentation via Learning Consistency Under Transformations

Semi-supervised Medical Image Segmentation via Learning Consistency Under Transformations

Anatomically consistent CNN-based segmentation of organs-at-risk in cranial radiotherapy

Mixed-Supervised Dual-Network for Medical Image Segmentation

Contact Info

Product

Resources

About