Small Organ Segmentation in Whole-Body MRI Using a Two-Stage FCN and Weighting Schemes

Valindria, Vanya V.; Lavdas, Ioannis; Cerrolaza, Juan J.; Aboagye, Eric O.; Rockall, Andrea; Rueckert, Daniel; Glocker, Ben

doi:10.1007/978-3-030-00919-9_40

Cited by 21 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data imbalance is a key obstacle that deteriorates performance in tasks of dense object detection or semantic segmentation. Small organ segmentation in medical imaging is particularly quite challenging due to the large imbalance between the object and background classes [ 32 , 33 ]. Such imbalance also emerges in dose prediction tasks in radiotherapy.…”

Section: Discussionmentioning

confidence: 99%

Sharp loss: a new loss function for radiotherapy dose prediction based on fully convolutional networks

et al. 2021

View full text Add to dashboard Cite

Background Neural-network methods have been widely used for the prediction of dose distributions in radiotherapy. However, the prediction accuracy of existing methods may be degraded by the problem of dose imbalance. In this work, a new loss function is proposed to alleviate the dose imbalance and achieve more accurate prediction results. The U-Net architecture was employed to build a prediction model. Our study involved a total of 110 patients with left-breast cancer, who were previously treated by volumetric-modulated arc radiotherapy. The patient dataset was divided into training and test subsets of 100 and 10 cases, respectively. We proposed a novel ‘sharp loss’ function, and a parameter γ was used to adjust the loss properties. The mean square error (MSE) loss and the sharp loss with different γ values were tested and compared using the Wilcoxon signed-rank test. Results The sharp loss achieved superior dose prediction results compared to those of the MSE loss. The best performance with the MSE loss and the sharp loss was obtained when the parameter γ was set to 100. Specifically, the mean absolute difference values for the planning target volume were 318.87 ± 30.23 for the MSE loss versus 144.15 ± 16.27 for the sharp loss with γ = 100 (p < 0.05). The corresponding values for the ipsilateral lung, the heart, the contralateral lung, and the spinal cord were 278.99 ± 51.68 versus 198.75 ± 61.38 (p < 0.05), 216.99 ± 44.13 versus 144.86 ± 43.98 (p < 0.05), 125.96 ± 66.76 versus 111.86 ± 47.19 (p > 0.05), and 194.30 ± 14.51 versus 168.58 ± 25.97 (p < 0.05), respectively. Conclusions The sharp loss function could significantly improve the accuracy of radiotherapy dose prediction.

show abstract

Section: Discussionmentioning

confidence: 99%

Sharp loss: a new loss function for radiotherapy dose prediction based on fully convolutional networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Therefore we used search terms containing "3D Bounding Box" AND "localization" AND medical -vehicle -"point cloud" (excluding terms "vehicle" and "point cloud") to find relevant papers in public databases and digital libraries. The platforms searched were, IEEE Xplore 1 , ACM 2 , Springer 3 , Google Scholar 4 and WoS 5 . The search was always limited to publications from 2015 to 2020.…”

Section: Methodsmentioning

confidence: 99%

“…The 3D kernel has to convolve over three axes, thus capturing context information between slices, but also requiring far more resources than its 2D counterpart. Recent work has made extensive use of 3D CNNs [5], [6], [7], [8], [9], [10], [11], [12]. 3D versions of Deep Learning architectures like VGGNet( [13]) [14], Faster R-CNN( [15]) [16], [17] and V-Net ( [18]) [19], [20] are very popular.…”

Section: A Fully 3d Implementationsmentioning

confidence: 99%

“…First, the entire image is viewed to roughly locate one or more targets. The resulting sub-optimal segmentation is then utilized to place a BB around the area of interest [32], [33], [34], [29], [5], [31], [19], [20], [39]. Similar to a coarse-segmentation approach, H. Roth et al (2018) [38] implement a 2D pixel-wise probability detection in every image plane direction to obtain confidence heatmaps, which are then used to generate a 3D BB.…”

Section: B Coarse Segmentation / Probability Mapsmentioning

confidence: 99%

See 1 more Smart Citation

3D Bounding Box Detection in Volumetric Medical Image Data: A Systematic Literature Review

Kern¹,

Mastmeyer²

2020

Preprint

View full text Add to dashboard Cite

This paper discusses current methods and trends for 3D bounding box detection in volumetric medical image data. For this purpose, an overview of relevant papers from recent years is given. 2D and 3D implementations are discussed and compared. Multiple identified approaches for localizing anatomical structures are presented. The results show that most research recently focuses on Deep Learning methods, such as Convolutional Neural Networks vs. methods with manual feature engineering, e.g. Random-Regression-Forests. An overview of bounding box detection options is presented and helps researchers to select the most promising approach for their target objects.<br>

show abstract

“…Two abdominal CT datasets containing a total of 90 image volumes were employed to evaluate this approach. The authors of [15] extend organ segmentation in MRI to present a method that combines a MALP with CNN. This approach builds on previous work described in [16] by incorporating weighting schemes to support class imbalance and a specialised organ region-of-interest selection.…”

Section: Introductionmentioning

confidence: 99%

3D Deep Learning for Anatomical Structure Segmentation in Multiple Imaging Modalities

Villarini

Asaturyan

Kurugol

et al. 2021

2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS)

View full text Add to dashboard Cite

Accurate, automated quantitative segmentation of anatomical structures in radiological scans, such as Magnetic Resonance Imaging (MRI) and Computer Tomography (CT), can produce significant biomarkers and can be integrated into computer-aided diagnosis (CADx) systems to support the interpretation of medical images from multi-protocol scanners. However, there are serious challenges towards developing robust automated segmentation techniques, including high variations in anatomical structure and size, varying image spatial resolutions resulting from different scanner protocols, and the presence of blurring artefacts. This paper presents a novel computing approach for automated organ and muscle segmentation in medical images from multiple modalities by harnessing the advantages of deep learning techniques in a two-part process. (1) a 3D encoder-decoder, Rb-UNet, builds a localisation model and a 3D Tiramisu network generates a boundary-preserving segmentation model for each target structure; (2) the fully trained Rb-UNet predicts a 3D bounding box encapsulating the target structure of interest, after which the fully trained Tiramisu model performs segmentation to reveal organ or muscle boundaries for every protrusion and indentation. The proposed approach is evaluated on six different datasets, including MRI, Dynamic Contrast Enhanced (DCE) MRI and CT scans targeting the pancreas, liver, kidneys and iliopsoas muscles. We achieve quantitative measures of mean Dice similarity coefficient (DSC) that surpasses or are comparable with the state-of-the-art and demonstrate statistical stability. A qualitative evaluation performed by two independent experts in radiology and radiography verified the preservation of detailed organ and muscle boundaries.

show abstract

Small Organ Segmentation in Whole-Body MRI Using a Two-Stage FCN and Weighting Schemes

Cited by 21 publications

References 17 publications

Sharp loss: a new loss function for radiotherapy dose prediction based on fully convolutional networks

Sharp loss: a new loss function for radiotherapy dose prediction based on fully convolutional networks

3D Bounding Box Detection in Volumetric Medical Image Data: A Systematic Literature Review

3D Deep Learning for Anatomical Structure Segmentation in Multiple Imaging Modalities

Contact Info

Product

Resources

About