Liver fibrosis staging by deep learning: a visual-based explanation of diagnostic decisions of the model

Abstract Objectives Deep learning has been proven to be able to stage liver fibrosis based on contrast-enhanced CT images. However, until now, the algorithm is used as a black box and lacks transparency. This study aimed to provide a visual-based explanation of the diagnostic decisions made by deep learning. Methods The liver fibrosis staging network (LFS network) was developed at contrast-enhanced CT images in the portal venous phase in 252 patients with histologically proven liver fibrosis stage. To give a visual explanation of the diagnostic decisions made by the LFS network, Gradient-weighted Class Activation Mapping (Grad-cam) was used to produce location maps indicating where the LFS network focuses on when predicting liver fibrosis stage. Results The LFS network had areas under the receiver operating characteristic curve of 0.92, 0.89, and 0.88 for staging significant fibrosis (F2–F4), advanced fibrosis (F3–F4), and cirrhosis (F4), respectively, on the test set. The location maps indicated that the LFS network had more focus on the liver surface in patients without liver fibrosis (F0), while it focused more on the parenchyma of the liver and spleen in case of cirrhosis (F4). Conclusions Deep learning methods are able to exploit CT-based information from the liver surface, liver parenchyma, and extrahepatic information to predict liver fibrosis stage. Therefore, we suggest using the entire upper abdomen on CT images when developing deep learning–based liver fibrosis staging algorithms. Key Points • Deep learning algorithms can stage liver fibrosis using contrast-enhanced CT images, but the algorithm is still used as a black box and lacks transparency. • Location maps produced by Gradient-weighted Class Activation Mapping can indicate the focus of the liver fibrosis staging network. • Deep learning methods use CT-based information from the liver surface, liver parenchyma, and extrahepatic information to predict liver fibrosis stage.

Download Full-text

A deep learning approach to generate contrast-enhanced computerised tomography angiograms without the use of intravenous contrast agents

European Heart Journal ◽

10.1093/ehjci/ehaa946.0156 ◽

2020 ◽

Vol 41 (Supplement_2) ◽

Author(s):

A Chandrashekar ◽

N Shivakumar ◽

P Lapolla ◽

A Handa ◽

V Grau ◽

...

Keyword(s):

Deep Learning ◽

Soft Tissue ◽

Contrast Agents ◽

Ct Images ◽

Learning Methods ◽

Intravenous Contrast ◽

Contrast Enhanced Ct ◽

Contrast Enhanced ◽

Enhanced Ct ◽

Contrast Ct

Abstract Introduction Contrast-enhanced computerised tomographic (CT) angiograms are widely used in cardiovascular imaging to obtain a non-invasive view of arterial structures. In aortic aneurysmal disease (AAA), CT angiograms are required prior to surgical intervention to differentiate between blood and the intra-luminal thrombus, which is present in 95% of cases. However, contrast agents are associated with complications at the injection site as well as renal toxicity leading to contrast-induced nephropathy (CIN) and renal failure. Purpose We hypothesised that the raw data acquired from a non-contrast CT contains sufficient information to differentiate blood and other soft tissue components. Therefore, we utilised deep learning methods to define the subtleties between the various components of soft tissue in order to simulate contrast enhanced CT images without the need of contrast agents. Methods Twenty-six AAA patients with paired non-contrast and contrast-enhanced CT images were randomly selected from an ethically approved ongoing study (Ethics Ref 13/SC/0250) and used for model training and evaluation (13/13). Non-contrast axial slices within the aneurysmal region from 10 patients (n=100) were sampled for the underlying Hounsfield unit (HU) distribution at the lumen, intra-luminal thrombus and interface locations, identified from their paired contrast axial slices. Subsequently, paired axial slices within the training cohort were augmented in a ratio of 10:1 to produce a total of 23,551 2-D images. We trained a 2-D Cycle Generative Adversarial Network (cycleGAN) for this non-contrast to contrast transformation task. Model output was assessed by comparison to the contrast image, which serves as a gold standard, using image similarity metrics (ex. SSIM Index). Results Sampling HUs within the non-contrast CT scan across multiple axial slices (Figure 1A) revealed significant differences between the blood flow lumen (yellow), blood/thrombus interface (red), and thrombus (blue) regions (p<0.001 for all comparisons). This highlighted the intrinsic differences between the regions and established the foundation for subsequent deep learning methods. The Non-Contrast-to-Contrast (NC2C)-cycleGAN was trained with a learning rate of 0.0002 for 200 epochs on 256 x 256 images centred around the aorta. Figure 1B depicts “contrast-enhanced” images generated from non-contrast CT images across the aortic length from the testing cohort. This preliminary model is able to differentiate between the lumen and intra-luminal thrombus of aneurysmal sections with reasonable resemblance to the ground truth. Conclusion This study describes, for the first time, the ability to differentiate between visually incoherent soft tissue regions in non-contrast CT images using deep learning methods. Ultimately, refinement of this methodology may negate the use of intravenous contrast and prevent related complications. CTA Generation from Non-Contrast CTs Funding Acknowledgement Type of funding source: Foundation. Main funding source(s): Clarendon

Download Full-text

Editorial Comment on “Liver Steatosis Categorization on Contrast-Enhanced CT Using a Fully-Automated Deep Learning Volumetric Segmentation Tool: Evaluation in 1,204 Heathy Adults Using Unenhanced CT as Reference Standard”

American Journal of Roentgenology ◽

10.2214/ajr.20.24764 ◽

2020 ◽

Author(s):

Amir A. Borhani

Keyword(s):

Deep Learning ◽

Editorial Comment ◽

Liver Steatosis ◽

Reference Standard ◽

Unenhanced Ct ◽

Tool Evaluation ◽

Contrast Enhanced Ct ◽

Contrast Enhanced ◽

Enhanced Ct ◽

Volumetric Segmentation

Download Full-text

Multi-factorial considerations for intra-thoracic lymph node evaluations of healthy cats on computed tomographic images

BMC Veterinary Research ◽

10.1186/s12917-021-02771-7 ◽

2021 ◽

Vol 17 (1) ◽

Author(s):

Ninlawan Thammasiri ◽

Chutimon Thanaboonnipat ◽

Nan Choisunirachon ◽

Damri Darawiroj

Keyword(s):

Lymph Node ◽

Lymph Nodes ◽

Ct Images ◽

Slice Thickness ◽

Maximum Width ◽

Post Contrast ◽

Computed Tomographic ◽

Contrast Enhanced Ct ◽

Contrast Enhanced ◽

Enhanced Ct

Abstract Background It is difficult to examine mild to moderate feline intra-thoracic lymphadenopathy via and thoracic radiography. Despite previous information from computed tomographic (CT) images of intra-thoracic lymph nodes, some factors from animals and CT setting were less elucidated. Therefore, this study aimed to investigate the effect of internal factors from animals and external factors from the CT procedure on the feasibility to detect the intra-thoracic lymph nodes. Twenty-four, client-owned, clinically healthy cats were categorized into three groups according to age. They underwent pre- and post-contrast enhanced CT for whole thorax followed by inter-group evaluation and comparison of sternal, cranial mediastinal, and tracheobronchial lymph nodes. Results Post contrast-enhanced CT appearances revealed that intra-thoracic lymph nodes of kittens were invisible, whereas the sternal, cranial mediastinal, and tracheobronchial nodes of cats aged over 7 months old were detected (6/24, 9/24 and 7/24, respectively). Maximum width of these lymph nodes were 3.93 ± 0.74 mm, 4.02 ± 0.65 mm, and 3.51 ± 0.62 mm, respectively. By age, lymph node sizes of these cats were not significantly different. Transverse lymph node width of males was larger than that of females (P = 0.0425). Besides, the detection score of lymph nodes was affected by slice thickness (P < 0.01) and lymph node width (P = 0.0049). Furthermore, an irregular, soft tissue structure, possibly the thymus, was detected in all juvenile cats and three mature cats. Conclusions Despite additional information on intra-thoracic lymph nodes in CT images, which can be used to investigate lymphatic-related abnormalities, age, sex, and slice thickness of CT images must be also considered.

Download Full-text

Value of contrast-enhanced CT texture analysis in predicting IDH mutation status of intrahepatic cholangiocarcinoma

Scientific Reports ◽

10.1038/s41598-021-86497-4 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Yong Zhu ◽

Yingfan Mao ◽

Jun Chen ◽

Yudong Qiu ◽

Yue Guan ◽

...

Keyword(s):

Texture Analysis ◽

Ct Images ◽

Textural Features ◽

Mutation Status ◽

Portal Venous Phase ◽

Contrast Enhanced Ct ◽

Contrast Enhanced ◽

Enhanced Ct ◽

Venous Phase ◽

Ct Texture Analysis

AbstractTo explore the value of contrast-enhanced CT texture analysis in predicting isocitrate dehydrogenase (IDH) mutation status of intrahepatic cholangiocarcinomas (ICCs). Institutional review board approved this study. Contrast-enhanced CT images of 138 ICC patients (21 with IDH mutation and 117 without IDH mutation) were retrospectively reviewed. Texture analysis was performed for each lesion and compared between ICCs with and without IDH mutation. All textural features in each phase and combinations of textural features (p < 0.05) by Mann–Whitney U tests were separately used to train multiple support vector machine (SVM) classifiers. The classification generalizability and performance were evaluated using a tenfold cross-validation scheme. Among plain, arterial phase (AP), portal venous phase (VP), equilibrium phase (EP) and Sig classifiers, VP classifier showed the highest accuracy of 0.863 (sensitivity, 0.727; specificity, 0.885), with a mean area under the receiver operating characteristic curve of 0.813 in predicting IDH mutation in validation cohort. Texture features of CT images in portal venous phase could predict IDH mutation status of ICCs with SVM classifier preoperatively.

Download Full-text