• Corpus ID: 239017027

A deep learning pipeline for localization, differentiation, and uncertainty estimation of liver lesions using multi-phasic and multi-sequence MRI

@article{Wang2021ADL,
  title={A deep learning pipeline for localization, differentiation, and uncertainty estimation of liver lesions using multi-phasic and multi-sequence MRI},
  author={Peng Wang and Yuhsuan Wu and Bolin Lai and Xiao-Yun Zhou and Le Lu and Wendi Liu and Hua-bang Zhou and Lingyun Huang and Jing Xiao and Adam P. Harrison and Ning-yang Jia and Heping Hu},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.08817}
}
  • Peng Wang, Yuhsuan Wu, +9 authors Heping Hu
  • Published 17 October 2021
  • Computer Science, Engineering
  • ArXiv
Objectives: to propose a fully-automatic computer-aided diagnosis (CAD) solution for liver lesion characterization, with uncertainty estimation. Methods: we enrolled 400 patients who had either liver resection or a biopsy and was diagnosed with either hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma, or secondary metastasis, from 2006 to 2019. Each patient was scanned with T1WI, T2WI, T1WI venous phase (T2WI-V), T1WI arterial phase (T1WI-A), and DWI MRI sequences. We propose a… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 30 REFERENCES
Deep Learning for Accurate Diagnosis of Liver Tumor Based on Magnetic Resonance Imaging and Clinical Data
TLDR
Deep learning achieves a performance on par with three experienced radiologists on classifying liver tumors in seven categories and has the potential to avoid contrast-related side effects and reduce economic costs associated with current standard MRI inspection practices for liver tumor patients.
Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phasic MRI
TLDR
This preliminary deep learning study demonstrated feasibility for classifying lesions with typical imaging features from six common hepatic lesion types, motivating future studies with larger multi-institutional datasets and more complex imaging appearances.
Extending 2-D Convolutional Neural Networks to 3-D for Advancing Deep Learning Cancer Classification With Application to MRI Liver Tumor Differentiation
TLDR
It is suggested that the proposed 3-D CNN architecture can bring significant benefit in DW-MRI liver discrimination and potentially, in numerous other tissue classification problems based on tomographic data, especially in size-limited, disease-specific clinical datasets.
Differentiation of Hepatocellular Carcinoma from Other Hepatic Malignancies in Patients at Risk: Diagnostic Performance of the Liver Imaging Reporting and Data System Version 2014.
TLDR
Modification of the algorithmic role of tumor in vein and rim arterial phase hyperenhancement improves the diagnostic performance of LI-RADS version 2014 in differentiating HCC from non-HCC malignancy.
Diagnostic confidence of computed tomography and magnetic resonance in focal liver pathology
TLDR
The results indicate that, for expert and intermediate experience observers, the diagnostic confidence using MR with Gd-EOB-DTPA is statistically significantly superior to CT with a multiphase technique.
LI‐RADS (Liver Imaging Reporting and Data System): Summary, discussion, and consensus of the LI‐RADS Management Working Group and future directions
TLDR
Initial discordance of LI‐RADS with American Association for the Study of Liver Diseases and Organ Procurement Transplant Network guidelines is focused on, and how they are being addressed going forward to optimize reporting of CT and MRI findings in patients at risk for HCC.
Radiomics-based classification of hepatocellular carcinoma and hepatic haemangioma on precontrast magnetic resonance images
TLDR
A radiomics signature as an adjunct tool to distinguish HCC and HH is developed and validated by combining in-phase, out- phase, T2W, and DW MR images, which outperformed the less experienced radiologist (2-years experience), and was nearly equal to the experienced radiologists (10- years experience).
LI-RADS: a great opportunity not to be missed
TLDR
The aim of this paper was to critically analyse the LI-RADS, focusing on some interesting issues such as the absence of a clear distinction between two different imaging modalities, the lack of validation of some major features, the assessment of its ancillary features and its complexity.
Exploration of Analysis Methods for Diagnostic Imaging Tests: Problems with ROC AUC and Confidence Scores in CT Colonography
TLDR
Confidence scores recorded in this study violated many assumptions of ROC AUC methods, rendering these methods inappropriate, and sensitivity and specificity were a more reliable and clinically appropriate method to compare diagnostic tests.
Intrahepatic cholangiocarcinoma: expert consensus statement.
TLDR
Surgical resection remains the mainstay of treatment, but survival is worse than in HCC alone, and there are no adequately powered, randomized Phase III trials that can provide definitive recommendations for adjuvant therapy for ICC.
...
1
2
3
...