MS-UNet: A multi-scale UNet with feature recalibration approach for automatic liver and tumor segmentation in CT images

Kushnure, Devidas T.; Talbar, Sanjay N.

doi:10.1016/j.compmedimag.2021.101885

Cited by 97 publications

(34 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we developed deep learning structures to automatically segment the PA region using MRI T1 and T2 images. Recently, there were abundant reported studies developing AI algorithms for segmentation of abdominal organs or structures including pancreas (16), liver (17,18), spleen (35,36), gallbladder (37), kidney (38,39), the local lesions of stomach (40), etc. However, there is no report of PA region segmentation using AI algorithms.…”

Section: Discussionmentioning

confidence: 99%

“…In the analysis of medical images of MRI, computed tomography (CT), X-ray, microscopy, and other images, deep learning shows promising performance in tasks like classification, segmentation, detection, and registration (15). Recently, considerable literature has grown up in analyzing image segmentation of different human organs using deep learning, such as pancreas (16), liver (17,18), heart (19), brain (20,21), etc. However, the PA region remains largely underexplored in medical image analysis based on advanced deep learning algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identifying Periampullary Regions in MRI Images Using Deep Learning

et al. 2021

View full text Add to dashboard Cite

BackgroundDevelopment and validation of a deep learning method to automatically segment the peri-ampullary (PA) region in magnetic resonance imaging (MRI) images.MethodsA group of patients with or without periampullary carcinoma (PAC) was included. The PA regions were manually annotated in MRI images by experts. Patients were randomly divided into one training set, one validation set, and one test set. Deep learning methods were developed to automatically segment the PA region in MRI images. The segmentation performance of the methods was compared in the validation set. The model with the highest intersection over union (IoU) was evaluated in the test set.ResultsThe deep learning algorithm achieved optimal accuracies in the segmentation of the PA regions in both T1 and T2 MRI images. The value of the IoU was 0.68, 0.68, and 0.64 for T1, T2, and combination of T1 and T2 images, respectively.ConclusionsDeep learning algorithm is promising with accuracies of concordance with manual human assessment in segmentation of the PA region in MRI images. This automated non-invasive method helps clinicians to identify and locate the PA region using preoperative MRI scanning.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Identifying Periampullary Regions in MRI Images Using Deep Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…At the same time, we apply a classifier to identify the texture types of nodules (i.e., GGN, solid, part-solid (PS)). In specific, two popular CT datasets LUNA16 [16] and LNDb [13] are used to train our models, in which the detector for ROI identification is a 3D variant of the CenterNet [28], the segmenter for lesion segmentation is a multi-scale 3D UNet [9,15], and the classifier is the variant of the segmenter attaching a fully-connected layer.…”

Section: Nlstt Dataset Acquisitionmentioning

confidence: 99%

Siamese Encoder-based Spatial-Temporal Mixer for Growth Trend Prediction of Lung Nodules on CT Scans

Fang¹,

Wang²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

In the management of lung nodules, we are desirable to predict nodule evolution in terms of its diameter variation on Computed Tomography (CT) scans and then provide a follow-up recommendation according to the predicted result of the growing trend of the nodule. In order to improve the performance of growth trend prediction for lung nodules, it is vital to compare the changes of the same nodule in consecutive CT scans. Motivated by this, we screened out 4,666 subjects with more than two consecutive CT scans from the National Lung Screening Trial (NLST) dataset to organize a temporal dataset called NLSTt. In specific, we first detect and pair regions of interest (ROIs) covering the same nodule based on registered CT scans. After that, we predict the texture category and diameter size of the nodules through models. Last, we annotate the evolution class of each nodule according to its changes in diameter. Based on the built NLSTt dataset, we propose a siamese encoder to simultaneously exploit the discriminative features of 3D ROIs detected from consecutive CT scans. Then we novelly design a spatial-temporal mixer (STM) to leverage the interval changes of the same nodule in sequential 3D ROIs and capture spatial dependencies of nodule regions and the current 3D ROI. According to the clinical diagnosis routine, we employ hierarchical loss to pay more attention to growing nodules. The extensive experiments on our organized dataset demonstrate the advantage of our proposed method. We also conduct experiments on an in-house dataset to evaluate the clinical utility of our method by comparing it against skilled clinicians. STM code and NLSTt dataset are available at https://github.com/liaw05/STMixer.

show abstract

“…They classify them into three classes-interior liver, liver boundary, and nonliver background-and utilized the CNN to predict the liver boundary. Kushnure et al [22] proposed introducing multiscale features in the CNN that extract global and local features at a more granular level. Chlebus et al [23] used a U-Net (architecture based on a FCN) in two models and filtered the false positives of tumor segmentation results by a random forest classifier.…”

Section: Liver Volume Segmentationmentioning

confidence: 99%

Segmentation of Liver Anatomy by Combining 3D U-Net Approaches

et al. 2021

View full text Add to dashboard Cite

Accurate liver vessel segmentation is of crucial importance for the clinical diagnosis and treatment of many hepatic diseases. Recent state-of-the-art methods for liver vessel reconstruction mostly utilize deep learning methods, namely, the U-Net model and its variants. However, to the best of our knowledge, no comparative evaluation has been proposed to compare these approaches in the liver vessel segmentation task. Moreover, most research works do not consider the liver volume segmentation as a preprocessing step, in order to keep only inner hepatic vessels, for Couinaud representation for instance. For these reasons, in this work, we propose using accurate Dense U-Net liver segmentation and conducting a comparison between 3D U-Net models inside the obtained volumes. More precisely, 3D U-Net, Dense U-Net, and MultiRes U-Net are pitted against each other in the vessel segmentation task on the IRCAD dataset. For each model, three alternative setups that allow adapting the selected CNN architectures to volumetric data are tested, namely, full 3D, slab-based, and box-based setups are considered. The results showed that the most accurate setup is the full 3D process, providing the highest Dice for most of the considered models. However, concerning the particular models, the slab-based MultiRes U-Net provided the best score. With our accurate vessel segmentations, several medical applications can be investigated, such as automatic and personalized Couinaud zoning of the liver.

show abstract

MS-UNet: A multi-scale UNet with feature recalibration approach for automatic liver and tumor segmentation in CT images

Cited by 97 publications

References 21 publications

Identifying Periampullary Regions in MRI Images Using Deep Learning

Identifying Periampullary Regions in MRI Images Using Deep Learning

Siamese Encoder-based Spatial-Temporal Mixer for Growth Trend Prediction of Lung Nodules on CT Scans

Segmentation of Liver Anatomy by Combining 3D U-Net Approaches

Contact Info

Product

Resources

About