The Liver Tumor Segmentation Benchmark (LiTS)

Bilic, Patrick; Christ, Patrick Ferdinand; 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, Yongming; Lipková, Jana; Lowengrub, John; Meine, Hans; Moltz, Jan Hendrik; Pal, Chris; Piraud, Marie; Qi, Xiaojuan; Jin, Qi; Rempfler, Markus; Roth, Karsten; Schenk, Andrea; Sekuboyina, Anjany; Vorontsov, Eugene; Zhou, Ping; Hülsemeyer, Christian; Beetz, Marcel; Ettlinger, Florian; Gruen, Felix; Kaissis, Georgios; Lohöfer, Fabian; Braren, Rickmer; Holch, Julian Walter; Hofmann, Felix; Sommer, Wieland H.; 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; Joskowicz, Leo; Menze, Bjoern H.

doi:10.48550/arxiv.1901.04056

Cited by 76 publications

(117 citation statements)

References 0 publications

Supporting

Mentioning

117

Contrasting

Order By: Relevance

“…We choose these tasks because they can benefit from an increased receptive field, yet are prone to overfitting due to limited training examples. For image segmentation, we consider two problems: liver lesion segmentation [4] and Multiple Sclerosis (MS) lesion segmentation [6] (see Figure 2). For reconstruction, we use T1-weighted axial brain MRI images from the ABIDE dataset [12].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Hyper-Convolutions via Implicit Kernels for Medical Imaging

Ma¹,

Wang²,

Dalca³

et al. 2022

Preprint

View full text Add to dashboard Cite

The convolutional neural network (CNN) is one of the most commonly used architectures for computer vision tasks. The key building block of a CNN is the convolutional kernel that aggregates information from the pixel neighborhood and shares weights across all pixels. A standard CNN's capacity, and thus its performance, is directly related to the number of learnable kernel weights, which is determined by the number of channels and the kernel size (support). In this paper, we present the hyperconvolution, a novel building block that implicitly encodes the convolutional kernel using spatial coordinates. Hyperconvolutions decouple kernel size from the total number of learnable parameters, enabling a more flexible architecture design. We demonstrate in our experiments that replacing regular convolutions with hyper-convolutions can improve performance with less parameters, and increase robustness against noise. We provide our code here: https://github.com/tym002/Hyper-Convolution

show abstract

Section: Methodsmentioning

confidence: 99%

“…Data: We use the LiTS dataset [4] for the liver lesion segmentation task, which includes 131 liver Computed Tomography (CT) volumes with ground truth manual segmentations. We randomly split the data: 80 cases for training, 20 for validation, and 31 for testing.…”

Section: Liver Lesion Segmentationmentioning

confidence: 99%

Hyper-Convolutions via Implicit Kernels for Medical Imaging

Ma¹,

Wang²,

Dalca³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…There are 8 organs are annotated by a radiologist. The CT-ORG [30] is an open dataset which contains 140 CT images and 6 organs are annotated, most of these images come from a challenge training set [1]. The AbdomenCT-1K dataset [26] extended five open single-class organs annotation datasets to four classes (with 1062 volumes) and a small clinical dataset (with 50 volumes come from 20 patients).…”

Section: Related Work 21 Abdominal Organs Segmentation Datasetsmentioning

confidence: 99%

WORD: A large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image

Luo¹,

Liao²,

Xiao³

et al. 2021

Preprint

View full text Add to dashboard Cite

“…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: 96%

Phase Recognition in Contrast-Enhanced CT Scans based on Deep Learning and Random Sampling

Dao¹,

Nguyễn²,

Pham

et al. 2022

Preprint

View full text Add to dashboard Cite

Purpose: 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 3D convolutional neural network (CNN) approaches with high computational complexity and high latency. This work aims at developing and validating a precise, fast multi-phase 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: non-contrast, arterial, venous, and others. The CNNs work as a slice-wise phase prediction, while the random sampling selects input slices for the CNN models. Afterward, majority voting synthesizes the slice-wise results of the CNNs, to provide the final prediction at 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 2 external test sets: CTPAC-CCRCC (N = 242) and LiTS (N = 131), which were annotated by our experts. Although a drop in performance has been observed, the model performance remained at a high level of accuracy with a mean F1-score 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 multi-phase classifier based on a 2D deep learning approach combined with a random sampling method for contrast phase recognition, providing a valuable tool for extracting multi-phase abdomen studies from low veracity, real-world data.

show abstract

The Liver Tumor Segmentation Benchmark (LiTS)

Cited by 76 publications

References 0 publications

Hyper-Convolutions via Implicit Kernels for Medical Imaging

Hyper-Convolutions via Implicit Kernels for Medical Imaging

WORD: A large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image

Phase Recognition in Contrast-Enhanced CT Scans based on Deep Learning and Random Sampling

Contact Info

Product

Resources

About