Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation

@article{Raju2020CoHeterogeneousAA,
  title={Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation},
  author={Ashwin Raju and Chi-Tung Cheng and Yu-jia Huo and Jinzheng Cai and Junzhou Huang and Jing Xiao and Le Lu and Chien-Han Liao and Adam P. Harrison},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.13201}
}
In medical imaging, organ/pathology segmentation models trained on current publicly available and fully-annotated datasets usually do not well-represent the heterogeneous modalities, phases, pathologies, and clinical scenarios encountered in real environments. On the other hand, there are tremendous amounts of unlabelled patient imaging scans stored by many modern clinical centers. In this work, we present a novel segmentation strategy, co-heterogenous and adaptive segmentation (CHASe), which… Expand
Learning From Multiple Datasets With Heterogeneous and Partial Labels for Universal Lesion Detection in CT
TLDR
A universal lesion detection algorithm to detect a variety of lesions and proposed strategies to mine missing annotations from partially-labeled datasets by exploiting clinical prior knowledge and cross-dataset knowledge transfer are proposed. Expand
Hetero-Modal Learning and Expansive Consistency Constraints for Semi-Supervised Detection from Multi-Sequence Data
TLDR
This paper introduces mean teacher hetero-modal detection (MTHD), which addresses two important gaps in current semi-supervised detection, and trains and evaluates MTHD on liver lesion detection using the largest MR lesion dataset to date. Expand
Deep Lesion Tracker: Monitoring Lesions in 4D Longitudinal Imaging Studies
TLDR
This work presents deep lesion tracker (DLT), a deep learning approach that uses both appearance- and anatomical-based signals to incorporate anatomical constraints, and proposes an anatomical signal encoder, which prevents lesions being matched with visually similar but spurious regions. Expand
User-Guided Domain Adaptation for Rapid Annotation from User Interactions: A Study on Pathological Liver Segmentation
TLDR
The user-guideddomain adaptation (UGDA) framework, which uses prediction-based adversarial domain adaptation (PADA) to model the combined distribution of UIs and mask predictions, can both learn from unlabelled data and also model the high-level semantic meaning behind different UIs. Expand
Deep Implicit Statistical Shape Models for 3D Medical Image Delineation
TLDR
To reliably fit anatomically plausible shapes to an image, a novel rigid and non-rigid pose estimation pipeline is introduced that is modelled as a Markov decision process (MDP) and outline a training regime that includes inverted episodic training and a deep realization of marginal space learning. Expand
Measure partial liver volumetric variations from paired inspiratory-expiratory chest CT scans
TLDR
A Hierarchical Intra- Patient Organ-specific (HIPO) registration pipeline is proposed to quantify the partial liver volumetric variations with lung pressure from a respiratory cycle, and two paired CT scans with liver deformation from regulated respiratory motions are employed. Expand
A Flexible Three-Dimensional Hetero-phase Computed Tomography Hepatocellular Carcinoma (HCC) Detection Algorithm for Generalizable and Practical HCC Screening
  • Chi-Tung Cheng, Jinzheng Cai, +11 authors Adam P. Harrison
  • Computer Science
  • ArXiv
  • 2021
TLDR
It is demonstrated that a single deep learning algorithm can be effectively applied to diverse HCC detection clinical scenarios and demonstrates performance improvements over more typical and less flexible non hetero-phase detectors. Expand
AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?
  • Jun Ma, Yao Zhang, +14 authors Xiaoping Yang
  • Medicine, Computer Science
  • IEEE transactions on pattern analysis and machine intelligence
  • 2021
TLDR
A large and diverse abdominal CT organ segmentation dataset with more than 1000 (1K) CT scans from 12 medical centers, including multi-phase, multi-vendor, and multi-disease cases is presented and a simple and effective method is developed for each benchmark, which can be used as out-of-the-box methods and strong baselines. Expand
Attention-Guided Supervised Contrastive Learning for Semantic Segmentation
TLDR
This paper proposes an attention-guided supervised contrastive learning approach to highlight a single semantic object every time as the target, and proposes a novel two-stage training strategy to achieve such attention. Expand
Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation
TLDR
For the first time, this work comprehensively evaluates the robustness of existing UDA methods and proposes a robust UDA approach that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. Expand
...
1
2
...

References

SHOWING 1-10 OF 59 REFERENCES
Accurate Weakly-Supervised Deep Lesion Segmentation using Large-Scale Clinical Annotations: Slice-Propagated 3D Mask Generation from 2D RECIST
TLDR
A convolutional neural network based weakly supervised slice-propagated segmentation (WSSS) method is introduced to generate the initial lesion segmentation on the axial RECIST-slice and extrapolate to segment the whole lesion slice by slice to finally obtain a volumetric segmentation. Expand
Automatic Liver Segmentation Using an Adversarial Image-to-Image Network
TLDR
This paper proposes an automatic and efficient algorithm to segment liver from 3D CT volumes using a deep image-to-image network employing a convolutional encoder-decoder architecture combined with multi-level feature concatenation and deep supervision. Expand
Semi-supervised Learning for Network-Based Cardiac MR Image Segmentation
TLDR
A semi-supervised learning approach, in which a segmentation network is trained from both labelled and unlabelled data, which outperforms a state-of-the-art multi-atlas segmentation method by a large margin and the speed is substantially faster. Expand
Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
TLDR
This article provides a detailed review of the solutions above, summarizing both the technical novelties and empirical results, and compares the benefits and requirements of the surveyed methodologies and provides recommended solutions. Expand
Semi-Supervised 3D Abdominal Multi-Organ Segmentation Via Deep Multi-Planar Co-Training
TLDR
Deep Multi-Planar Co-Training is proposed, whose contributions can be divided into two folds: 1) the deep model is learned in a co-training style which can mine consensus information from multiple planes like the sagittal, coronal, and axial planes; 2) Multi-planar fusion is applied to generate more reliable pseudo-labels, which alleviates the errors occurring in the pseudo-Labels and thus can help to train better segmentation networks. Expand
H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes
TLDR
This work proposes a novel hybrid densely connected UNet (H-DenseUNet), which consists of a 2-D Dense UNet for efficiently extracting intra-slice features and a 3-D counterpart for hierarchically aggregating volumetric contexts under the spirit of the auto-context algorithm for liver and tumor segmentation. Expand
Self-learning to detect and segment cysts in lung CT images without manual annotation
TLDR
A very weakly supervised learning method is introduced, for cystic lesion detection and segmentation in lung CT images, without any manual annotation, in a self-learning manner, where segmentation generated in previous steps is used as ground truth for the next level of network learning. Expand
Accurate Esophageal Gross Tumor Volume Segmentation in PET/CT using Two-Stream Chained 3D Deep Network Fusion
TLDR
Extensive 5-fold cross-validation on 110 esophageal cancer patients demonstrates that both the proposed two-stream chained segmentation pipeline and the PSNN model can significantly improve the quantitative performance over the previous state-of-the-art work by 11% in absolute Dice score. Expand
Progressive and Multi-path Holistically Nested Neural Networks for Pathological Lung Segmentation from CT Images
TLDR
This work incorporates the deeply supervised learning framework, but enhance it with a simple, yet effective, progressive multi-path scheme, which more reliably merges outputs from different network stages, which is called progressive holistically-nested networks (P-HNNs). Expand
Light-Weight Hybrid Convolutional Network for Liver Tumor Segmentation
TLDR
The light-weight hybrid convolutional network (LW-HCN) is proposed to segment the liver and its tumors in CT volumes and has a encoder-decoder structure, in which 2D convolutions used at the bottom of the encoder decreases the complexity and 3D Convolutional networks used in other layers explore both spatial and temporal information. Expand
...
1
2
3
4
5
...