Iterative Interaction Training for Segmentation Editing Networks

Bredell, Gustav; Tanner, Christine; Konukoğlu, Ender

doi:10.1007/978-3-030-00919-9_42

Cited by 31 publications

(32 citation statements)

References 17 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although recent deep learning based automatic segmentation engines [16,21,29,34] have achieved impressive performance, they still struggle to achieve sufficiently accurate and robust results for clinical practice, especially in the presence of poor image quality (e.g., noise, low contrast) or highly variable shapes (e.g., anatomical structures). Consequently, interactive segmentation [2,18,27,28,32,33] garners research interests of the medical image analysis community, and recently became the choice in many real-life medical applications.…”

Section: Introductionmentioning

confidence: 99%

Quality-Aware Memory Network for Interactive Volumetric Image Segmentation

Zhou

Bredell

et al. 2021

Medical Image Computing and Computer Assisted Intervention – MICCAI 2021

Self Cite

View full text Add to dashboard Cite

Despite recent progress of automatic medical image segmentation techniques, fully automatic results usually fail to meet the clinical use and typically require further refinement. In this work, we propose a quality-aware memory network for interactive segmentation of 3D medical images. Provided by user guidance on an arbitrary slice, an interaction network is firstly employed to obtain an initial 2D segmentation. The quality-aware memory network subsequently propagates the initial segmentation estimation bidirectionally over the entire volume. Subsequent refinement based on additional user guidance on other slices can be incorporated in the same manner. To further facilitate interactive segmentation, a quality assessment module is introduced to suggest the next slice to segment based on the current segmentation quality of each slice. The proposed network has two appealing characteristics: 1) The memory-augmented network offers the ability to quickly encode past segmentation information, which will be retrieved for the segmentation of other slices; 2) The quality assessment module enables the model to directly estimate the qualities of segmentation predictions, which allows an active learning paradigm where users preferentially label the lowestquality slice for multi-round refinement. The proposed network leads to a robust interactive segmentation engine, which can generalize well to various types of user annotations (e.g., scribbles, boxes). Experimental results on various medical datasets demonstrate the superiority of our approach in comparison with existing techniques.

show abstract

Section: Introductionmentioning

confidence: 99%

Quality-Aware Memory Network for Interactive Volumetric Image Segmentation

Zhou

Bredell

et al. 2021

Medical Image Computing and Computer Assisted Intervention – MICCAI 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, due to the pathological variability, dark lesion areas, as well as the uneven quality of the training data (lacking the consistency between imaging scanners, operators, and annotators), the accuracy of traditional convolutional neural networks (CNNs) type segmentation algorithms usually fail to meet clinical demands Wang et al (2018a,b); Liao et al (2020). To further refine the relatively inaccurate segmentation results, interactive image segmentation algorithms that take advantage of interactive correction information (e.g., clicks, scribbles, or bounding boxes) are introduced Rajchl et al (2016); Xu et al (2016); Lin et al (2016); Wang et al (2018b,a); Bredell et al (2018); Liao et al (2020); Ma et al (2020). The general interactive segmentation process is depicted in Figure 1, which contains two modules, i.e., interactive module and utilization module.…”

Section: Introductionmentioning

confidence: 99%

Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration

Li¹,

Xu²,

Shen³

et al. 2021

Preprint

View full text Add to dashboard Cite

Medical image segmentation is one of the fundamental problems for artificial intelligencebased clinical decision systems. Current automatic medical image segmentation methods are often failed to meet clinical requirements. As such, a series of interactive segmentation algorithms are proposed to utilize expert correction information. However, existing methods suffer from some segmentation refining failure problems after long-term interactions and some cost problems from expert annotation, which hinder clinical applications. This paper proposes an interactive segmentation framework, called interactive MEdical segmentation with self-adaptive Confidence CAlibration (MECCA), by introducing the corrective action evaluation, which combines the actionbased confidence learning and multi-agent reinforcement learning (MARL). The evaluation is established through a novel action-based confidence network, and the corrective actions are obtained from MARL. Based on the confidential information, a self-adaptive reward function is designed to provide more detailed feedback, and a simulated label generation mechanism is proposed on unsupervised data to reduce over-reliance on labeled data. Experimental results on various medical image datasets have shown the significant performance of the proposed algorithm.

show abstract

“… 8 , 9 Pretrained CNNs have been fine-tuned toward the features of one specific image, resulting in better segmentations of that image. 10 , 11 …”

Section: Introductionmentioning

confidence: 99%

Patient-specific fine-tuning of convolutional neural networks for follow-up lesion quantification

et al. 2020

View full text Add to dashboard Cite

. Purpose: Convolutional neural network (CNN) methods have been proposed to quantify lesions in medical imaging. Commonly, more than one imaging examination is available for a patient, but the serial information in these images often remains unused. CNN-based methods have the potential to extract valuable information from previously acquired imaging to better quantify lesions on current imaging of the same patient. Approach: A pretrained CNN can be updated with a patient’s previously acquired imaging: patient-specific fine-tuning (FT). In this work, we studied the improvement in performance of lesion quantification methods on magnetic resonance images after FT compared to a pretrained base CNN. We applied the method to two different approaches: the detection of liver metastases and the segmentation of brain white matter hyperintensities (WMH). Results: The patient-specific fine-tuned CNN has a better performance than the base CNN. For the liver metastases, the median true positive rate increases from 0.67 to 0.85. For the WMH segmentation, the mean Dice similarity coefficient increases from 0.82 to 0.87. Conclusions: We showed that patient-specific FT has the potential to improve the lesion quantification performance of general CNNs by exploiting a patient’s previously acquired imaging.

show abstract

Iterative Interaction Training for Segmentation Editing Networks

Cited by 31 publications

References 17 publications

Quality-Aware Memory Network for Interactive Volumetric Image Segmentation

Quality-Aware Memory Network for Interactive Volumetric Image Segmentation

Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration

Patient-specific fine-tuning of convolutional neural networks for follow-up lesion quantification

Contact Info

Product

Resources

About