The Liver Tumor Segmentation Benchmark (LiTS)

Bilic, Patrick; Christ, Patrick Ferdinand; Vorontsov, Eugene; Chlebus, Grzegorz; Chen, Hao; Dou, Qi; Fu, Chi‐Wing; Han, Xiao; Heng, Pheng‐Ann; Hesser, Jürgen; Kadoury, Samuel; Konopczyński, Tomasz; Le, Miao; Li, Chunming; Li, Xiaomeng; Lipková, Jana; Lowengrub, John; Meine, Hans; Moltz, Jan Hendrik; Pal, Chris; Piraud, Marie; Qi, Xiaojuan; Qi, Jin; Rempfler, Markus; Roth, Karsten; Schenk, Andrea; Sekuboyina, Anjany; Zhou, Ping; Hülsemeyer, Christian; Beetz, Marcel; Ettlinger, Florian; Gruen, Felix; Kaissis, Georgios; Lohöfer, Fabian; Braren, Rickmer; Holch, Julian Walter; Hofmann, Felix; Sommer, Wieland H.; Heinemann, Volker; Jacobs, Colin; Mamani, Gabriel Efrain Humpire; Ginneken, Bram van; Chartrand, Gabriel; Tang, An; Drozdzal, Michal; Ben-Cohen, Avi; Klang, Eyal; Amitai, Michal Marianne; Konen, Eli; Greenspan, Hayit; Moreau, Johan; Hostettler, Alexandre; Soler, Luc; Vivanti, Refael; Szeskin, Adi; Lev‐Cohain, Naama; Sosna, Jacob; Joskowicz, Leo; Menze, Bjoern H.

doi:10.1016/j.media.2022.102680

Cited by 457 publications

(112 citation statements)

References 90 publications

Supporting

Mentioning

111

Contrasting

Order By: Relevance

“…Here, R% denotes the percentage of slices selected from the input scan; and (2) slice‐level prediction identifies phases of each chosen slice amd then uses majority voting to conclude the phase of the given scan. Our experimental results on internal and external (i.e., CTPAC‐CCRCC, 16 LiTS 17 ) datasets showed that the proposed method significantly outperforms the state‐of‐the‐art 3D approaches while requiring less computation time for inference.…”

Section: Introductionmentioning

confidence: 89%

“…Our radiologist team, therefore, classified scans from these datasets into four phase categories. As a result, the LiTS 17 dataset has eight scans of the arterial phase and 123 scans of the venous phase. Meanwhile, CPTAC‐CCRCC 16 contains 57, 69, 53, and 63 scans from four categories noncontrast, venous, arterial, and others, respectively.…”

Section: Methodsmentioning

confidence: 99%

“…To verify the generalization ability of the proposed deep learning model, we evaluated it on two external datasets, including LiTS 17 and CPTAC‐CCRCC 16 . The LiTS 17 dataset contains 131 CT scans in the training set and 70 CT scans in the test set. It was originally developed for the development of liver segmentation methods.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Phase recognition in contrast‐enhanced CT scans based on deep learning and random sampling

Dao¹,

Nguyễn²,

Pham

et al. 2022

Medical Physics

View full text Add to dashboard Cite

A fully automated system for interpreting abdominal computed tomography (CT) scans with multiple phases of contrast enhancement requires an accurate classification of the phases. Current approaches to classify the CT phases are commonly based on three-dimensional (3D) convolutional neural network (CNN) approaches with high computational complexity and high latency. This work aims at developing and validating a precise, fast multiphase classifier to recognize three main types of contrast phases in abdominal CT scans. Methods: We propose in this study a novel method that uses a random sampling mechanism on top of deep CNNs for the phase recognition of abdominal CT scans of four different phases: noncontrast, arterial, venous, and others. The CNNs work as a slicewise phase prediction, while random sampling selects input slices for the CNN models. Afterward, majority voting synthesizes the slicewise results of the CNNs to provide the final prediction at the scan level. Results: Our classifier was trained on 271 426 slices from 830 phase-annotated CT scans, and when combined with majority voting on 30% of slices randomly chosen from each scan, achieved a mean F1 score of 92.09% on our internal test set of 358 scans. The proposed method was also evaluated on two external test sets: CTPAC-CCRCC (N = 242) and LiTS (N = 131), which were annotated by our experts. Although a drop in performance was observed, the model performance remained at a high level of accuracy with a mean F1 scores of 76.79% and 86.94% on CTPAC-CCRCC and LiTS datasets, respectively. Our experimental results also showed that the proposed method significantly outperformed the state-of -the-art 3D approaches while requiring less computation time for inference. Conclusions: In comparison to state-of -the-art classification methods, the proposed approach shows better accuracy with significantly reduced latency. Our study demonstrates the potential of a precise, fast multiphase classifier based on a two-dimensional deep learning approach combined with a random sampling method for contrast phase recognition, providing a valuable tool for extracting multiphase abdomen studies from low veracity, real-world data.

show abstract

Section: Introductionmentioning

confidence: 89%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Phase recognition in contrast‐enhanced CT scans based on deep learning and random sampling

Dao¹,

Nguyễn²,

Pham

et al. 2022

Medical Physics

View full text Add to dashboard Cite

show abstract

“…The metrics employed to evaluate segmentation quantitatively include Dice similarity coefficient (DSC), relative volume difference (RVD), average symmetric surface distance (ASSD), and Hausdorff distance (HD) 43,44 .…”

Section: Experiments and Resultsmentioning

confidence: 99%

Decoupled pyramid correlation network for liver tumor segmentation from CT images

et al. 2022

View full text Add to dashboard Cite

Purpose Automated liver tumor segmentation from computed tomography (CT) images is a necessary prerequisite in the interventions of hepatic abnormalities and surgery planning. However, accurate liver tumor segmentation remains challenging due to the large variability of tumor sizes and inhomogeneous texture. Recent advances based on fully convolutional network (FCN) for medical image segmentation drew on the success of learning discriminative pyramid features. In this paper, we propose a decoupled pyramid correlation network (DPC‐Net) that exploits attention mechanisms to fully leverage both low‐ and high‐level features embedded in FCN to segment liver tumor. Methods We first design a powerful pyramid feature encoder (PFE) to extract multilevel features from input images. Then we decouple the characteristics of features concerning spatial dimension (i.e., height, width, depth) and semantic dimension (i.e., channel). On top of that, we present two types of attention modules, spatial correlation (SpaCor) and semantic correlation (SemCor) modules, to recursively measure the correlation of multilevel features. The former selectively emphasizes global semantic information in low‐level features with the guidance of high‐level ones. The latter adaptively enhance spatial details in high‐level features with the guidance of low‐level ones. Results We evaluate the DPC‐Net on MICCAI 2017 LiTS Liver Tumor Segmentation (LiTS) challenge data set. Dice similarity coefficient (DSC) and average symmetric surface distance (ASSD) are employed for evaluation. The proposed method obtains a DSC of 76.4% and an ASSD of 0.838 mm for liver tumor segmentation, outperforming the state‐of‐the‐art methods. It also achieves a competitive result with a DSC of 96.0% and an ASSD of 1.636 mm for liver segmentation. Conclusions The experimental results show promising performance of DPC‐Net for liver and tumor segmentation from CT images. Furthermore, the proposed SemCor and SpaCor can effectively model the multilevel correlation from both semantic and spatial dimensions. The proposed attention modules are lightweight and can be easily extended to other multilevel methods in an end‐to‐end manner.

show abstract

“…The public dataset from MICCAI 2017 Liver Tumor Segmentation (LiTS) Challenge is employed in this study, 16 which contains 131 samples with labels and 70 samples without a label of contrast‐enhanced 3D abdominal CT scans. The LiTS dataset is acquired by different scanners and protocols from six different clinical sites, with an input size of 512× 512 and a mostly varying in‐plane spacing from 0.55 to 1.0 mm.…”

Section: Methodsmentioning

confidence: 99%

Shift‐channel attention and weighted‐region loss function for liver and dense tumor segmentation

Huang

et al. 2022

Medical Physics

View full text Add to dashboard Cite

Purpose To assist physicians in the diagnosis and treatment planning of tumor, a robust and automatic liver and tumor segmentation method is highly demanded in the clinical practice. Recently, numerous researchers have improved the segmentation accuracy of liver and tumor by introducing multiscale contextual information and attention mechanism. However, this tends to introduce more training parameters and suffer from a heavier computational burden. In addition, the tumor has various sizes, shapes, locations, and numbers, which is the main reason for the poor accuracy of automatic segmentation. Although current loss functions can improve the learning ability of the model for hard samples to a certain extent, these loss functions are difficult to optimize the segmentation effect of small tumor regions when the large tumor regions in the sample are in the majority. Methods We propose a Liver and Tumor Segmentation Network (LiTS‐Net) framework. First, the Shift‐Channel Attention Module (S‐CAM) is designed to model the feature interdependencies in adjacent channels and does not require additional training parameters. Second, the Weighted‐Region (WR) loss function is proposed to emphasize the weight of small tumors in dense tumor regions and reduce the weight of easily segmented samples. Moreover, the Multiple 3D Inception Encoder Units (MEU) is adopted to capture the multiscale contextual information for better segmentation of liver and tumor. Results Efficacy of the LiTS‐Net is demonstrated through the public dataset of MICCAI 2017 Liver Tumor Segmentation (LiTS) challenge, with Dice per case of 96.9%${\bf \%}$ and 75.1%${\bf \%}$, respectively. For the 3D Image Reconstruction for Comparison of Algorithm and DataBase (3Dircadb), Dices are 96.47%${\bf \%}$ for the liver and 74.54%${\bf \%}$ for tumor segmentation. The proposed LiTS‐Net outperforms existing state‐of‐the‐art networks. Conclusions We demonstrated the effectiveness of LiTS‐Net and its core components for liver and tumor segmentation. The S‐CAM is designed to model the feature interdependencies in the adjacent channels, which is characterized by no need to add additional training parameters. Meanwhile, we conduct an in‐depth study of the feature shift proportion of adjacent channels to determine the optimal shift proportion. In addition, the WR loss function can implicitly learn the weights among regions without the need to manually specify the weights. In dense tumor segmentation tasks, WR aims to enhance the weights of small tumor regions and alleviate the problem that small tumor segmentation is difficult to optimize further when large tumor regions occupy the majority. Last but not least, our proposed method outperforms other state‐of‐the‐art methods on both the LiTS dataset and the 3Dircadb dataset.

show abstract

The Liver Tumor Segmentation Benchmark (LiTS)

Cited by 457 publications

References 90 publications

Phase recognition in contrast‐enhanced CT scans based on deep learning and random sampling

Phase recognition in contrast‐enhanced CT scans based on deep learning and random sampling

Decoupled pyramid correlation network for liver tumor segmentation from CT images

Shift‐channel attention and weighted‐region loss function for liver and dense tumor segmentation

Contact Info

Product

Resources

About