Fully automatic scheme for measuring liver volume in 3D MR images

Le, Trong-Ngoc; Huynh,

doi:10.3233/bme-151434

Cited by 13 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A 3D liver model guided by a precomputed probability map was used by Bereciartua et al [4], which achieved a mean Dice of 0.90 for patients with healthy livers. Le et al used a histogram-based liver segmentation with a subsequent geodesic active contour refinement step and reported a mean Dice of 0.91 [5]. Huyhn et al proposed a method based on watershed transformation and active contours, which achieved a mean Dice of 0.91 [6].…”

Section: Introductionmentioning

confidence: 99%

Reducing inter-observer variability and interaction time of MR liver volumetry by combining automatic CNN-based liver segmentation and manual corrections

et al. 2019

View full text Add to dashboard Cite

Purpose To compare manual corrections of liver masks produced by a fully automatic segmentation method based on convolutional neural networks (CNN) with manual routine segmentations in MR images in terms of inter-observer variability and interaction time. Methods For testing, patient’s precise reference segmentations that fulfill the quality requirements for liver surgery were manually created. One radiologist and two radiology residents were asked to provide manual routine segmentations. We used our automatic segmentation method Liver-Net to produce liver masks for the test cases and asked a radiologist assistant and one further resident to correct the automatic results. All observers were asked to measure their interaction time. Both manual routine and corrected segmentations were compared with the reference annotations. Results The manual routine segmentations achieved a mean Dice index of 0.95 and a mean relative error (RVE) of 4.7%. The quality of liver masks produced by the Liver-Net was on average 0.95 Dice and 4.5% RVE. Liver masks resulting from manual corrections of automatically generated segmentations compared to routine results led to a significantly lower inter-observer variability (mean per case absolute RVE difference across observers 0.69%) when compared to manual routine ones (2.75%). The mean interaction time was 2 min for manual corrections and 10 min for manual routine segmentations. Conclusions The quality of automatic liver segmentations is on par with those from manual routines. Using automatic liver masks in the clinical workflow could lead to a reduction of segmentation time and a more consistent liver volume estimation across different observers.

show abstract

Section: Introductionmentioning

confidence: 99%

Reducing inter-observer variability and interaction time of MR liver volumetry by combining automatic CNN-based liver segmentation and manual corrections

et al. 2019

View full text Add to dashboard Cite

show abstract

“…It has been observed that the volume of the liver may be measured with automatic volume measurement methods in recent studies [37][38][39] . In these methods, the measurements may be made by using various measurements.…”

Section: Discussionmentioning

confidence: 99%

Yenidoğan kadavralarında karaciğer hacminin stereolojik olarak hesaplanması

Avnioğlu¹,

Unur²,

Acer³

et al. 2020

Cukurova Medical Journal

View full text Add to dashboard Cite

show abstract

“…Prior to the use of deep learning (DL), segmentation would most frequently be based multi-atlas approaches. [1] uses 3D models of the liver and probability maps, [2] is based on histograms to segment the liver, followed by active contours for refinement, [3] applies watershed together with active contours. Then deep learning-based segmentation revolutionized the field.…”

Section: Related Workmentioning

confidence: 99%

Investigation of Loss Functions for Improving Deep Segmentation of Abdominal Organs from MRI

Furtado¹

2020

Preprint

View full text Add to dashboard Cite

Segmentation of Magnetic Resonance Images (MRI) of abdominal organs is useful for analysis prior to surgical procedures and for further processing. Deep Learning (DL) has become the standard, researchers have proposed improvements that include multiple views, ensembles and voting. Loss function alternatives, while being crucial to guide automated learning, have not been compared in detail. In this work we analyze limitations of popular metrics and their use as loss, study alternative loss variations based on those and other modifications and search for the best approach. An experimental setup was necessary to assess the alternatives. Results for the top scoring network and top scoring loss show improvements between 2 and 11 percentage points (pp) in Jaccard Index (JI), depending on organ and patient (sequence), for a total of 22 pp over 4 organs, all this being obtained just by choosing the best performing loss function instead of cross-entropy or dice. Our results apply directly to MRI of abdominal organs, with important practical implications for other architectures, as they can be applied easily to any of them. They also show the worth of variants of loss function and loss tuning, with future work needed to generalize and test in other contexts.

show abstract

Fully automatic scheme for measuring liver volume in 3D MR images

Cited by 13 publications

References 19 publications

Reducing inter-observer variability and interaction time of MR liver volumetry by combining automatic CNN-based liver segmentation and manual corrections

Reducing inter-observer variability and interaction time of MR liver volumetry by combining automatic CNN-based liver segmentation and manual corrections

Yenidoğan kadavralarında karaciğer hacminin stereolojik olarak hesaplanması

Investigation of Loss Functions for Improving Deep Segmentation of Abdominal Organs from MRI

Contact Info

Product

Resources

About