Spatio-temporal Learning from Longitudinal Data for Multiple Sclerosis Lesion Segmentation

@article{Denner2020SpatiotemporalLF,
  title={Spatio-temporal Learning from Longitudinal Data for Multiple Sclerosis Lesion Segmentation},
  author={Stefan Denner and Ashkan Khakzar and Moiz Sajid and Mahdi Saleh and Žiga {\vS}piclin and S. T. Kim and Nassir Navab},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.03675}
}
Segmentation of Multiple Sclerosis (MS) lesions in longitudinal brain MR scans is performed for monitoring the progression of MS lesions. In order to improve segmentation, we use spatio-temporal cues in longitudinal data. To that end, we propose two approaches: Our longitudinal segmentation architecture which is grounded upon early-fusion of longitudinal data. And complementary to the longitudinal architecture, we propose a novel multi-task learning approach by defining an auxiliary self… 

Multiple Sclerosis Lesion Segmentation - A Survey of Supervised CNN-Based Methods

TLDR
This survey investigates the supervised CNN-based methods for MS lesion segmentation and decouple these reviewed works into their algorithmic components and reports comparisons between their results.

Cross-Organ, Cross-Modality Transfer Learning: Feasibility Study for Segmentation and Classification

TLDR
XTL using mammograms improves the network performance compared to traditional TL, despite the difference in image characteristics, and is shown to match the target image types (volumetric) and tasks (segmentation and classification).

Longitudinal Quantitative Assessment of COVID-19 Infection Progression from Chest CTs

TLDR
A new framework to identify infection at a voxel level (identification of healthy lung, consolidation, and ground-glass opacity) and visualize the progression of COVID-19 using sequential low-dose non-contrast CT scans is proposed and a longitudinal segmentation network is devised that utilizes the reference scan information to improve the performance of disease identification.

Influence of inputs for bone lesion segmentation in longitudinal 18F-FDG PET/CT imaging studies

TLDR
A completely automatic method to detect and segment these metastases on longitudinal 18F-FDG PET/CT images in the context of metastatic breast cancer is proposed and proposed.

Recent advances in the longitudinal segmentation of multiple sclerosis lesions on magnetic resonance imaging: a review

TLDR
The main objective of longitudinal segmentation approaches is to more accurately detect the presence of new MS lesions and the growth or remission of existing lesions, which may be effective biomarkers of disease progression and treatment response.

An Open-Source Tool for Longitudinal Whole-Brain and White Matter Lesion Segmentation

TLDR
The results indicate that the method attains a higher test-retest reliability, while being more sensitive to longitudinal disease, and is extended with subject-specific latent variables that encourage temporal consistency between its segmentation results, enabling it to better track subtle morphological changes in dozens of neuroanatomical structures and white matter lesions.

Longitudinal Self-Supervision for COVID-19 Pathology Quantification

TLDR
Experimental results show that the proposed self-supervised learning method to effectively train longitudinal networks for the quantification of COVID-19 infections is effective, helping the model better exploit the semantics of longitudinal data and improve two CO VID-19 quantification tasks.

Temporal-Spatial Graph Attention Networks for DCE-MRI Breast Tumor Segmentation

TLDR
A novel end-to-end temporal-spatial graph attention network ( TSGAN) is proposed, which precisely segments tumor of 4D (volume space, time) DCE-MRI images by conjointly exploiting the spatial contextual dependency of inter-slice and temporal contextual dependencyof inter-sequence.

Automatic Segmentation of Metastatic Breast Cancer Lesions on 18F-FDG PET/CT Longitudinal Acquisitions for Treatment Response Assessment

TLDR
This is the first study to date evaluating the use of automatic segmentation to obtain imaging biomarkers that can be used to assess treatment response in patients with metastatic breast cancer and proposes networks to segment breast cancer metastatic lesions on longitudinal whole-body PET/CT.

References

SHOWING 1-10 OF 29 REFERENCES

Longitudinal Multiple Sclerosis Lesion Segmentation Using Multi-view Convolutional Neural Networks

TLDR
The proposed method uses MR intensities and White Matter priors for extraction of candidate lesion voxels and uses Convolutional Neural Networks for false positive reduction and networks process longitudinal data, a novel contribution in the domain of MS lesion analysis.

Automated Segmentation of Multiple Sclerosis Lesions Using Multi-dimensional Gated Recurrent Units

TLDR
It is demonstrated that using data augmentation, selective sampling, residual learning and/or DropConnect on the RNN state can produce better segmentation results, and it is shown that a setup which combines these techniques can outperform the state of the art in automated lesion segmentation.

Multiple Sclerosis Lesion Segmentation with Tiramisu and 2.5D Stacked Slices

TLDR
A fully convolutional densely connected network (Tiramisu) for multiple sclerosis (MS) lesion segmentation using stacked slices from all three anatomical planes to achieve a 2.5D method that can make more accurate segmentation by combining information of different forms.

A Novel Public MR Image Dataset of Multiple Sclerosis Patients With Lesion Segmentations Based on Multi-rater Consensus

TLDR
The obtained intra-consensus variability was substantially lower compared to the intra- and inter-rater variabilities, showing improved reliability of lesion segmentation by the proposed protocol, and may represent a more precise target to evaluate, compare against and also train, the automatic segmentations.

Geodesic Information Flows: Spatially-Variant Graphs and Their Application to Segmentation and Fusion

TLDR
A novel framework to propagate voxel-wise annotations between morphologically dissimilar images by diffusing and mapping the available examples through intermediate steps is explored, enabling the gradual diffusion of information to all the subjects, even in the presence of large-scale morphological variability.