Abstract
Background
Microvascular invasion (MVI) is a risk factor for early recurrence and poor prognosis
of hepatocellular carcinoma (HCC). Preoperative assessment of MVI status is beneficial
for clinical therapy and prognosis evaluation.
Methods
A total of 305 surgically resected patients were included retrospectively. All recruited
patients underwent plain and contrast-enhanced abdominal CT. They were then randomly
divided into training and validation sets in a ratio of 8:2. Self-attention-based
ViT-B/16 and ResNet-50 analyzed CT images to predict MVI status preoperatively. Then,
Grad-CAM was used to generate an attention map showing the high-risk MVI patches.
Using five-fold cross validation, the performance of each model was evaluated.
Results
Among 305 HCC patients, 99 patients were pathologically MVI-positive and 206 were
MVI-negative. ViT-B/16 with fusion phase predicted the MVI status with an AUC of 0.882
and an accuracy of 86.8% in the validation set, which is similar to ResNet-50 with
an AUC of 0.875 and an accuracy of 87.2%. The fusion phase improved performance a
bit as compared to the single phase used for MVI prediction. The influence of peritumoral
tissue on predictive ability was limited. A color visualization of the suspicious
patches where microvascular has invaded was presented by attention maps.
Conclusion
ViT-B/16 model can predict preoperative MVI status in CT images of HCC patients. Assisted
by attention maps, it can assist patients in making tailored treatment decisions.
Abbreviations:
MVI (microvascular invasion), HCC (hepatocellular carcinoma), CAD (computer-assisted diagnosis), CNN (convolutional neural network), ViT (Vision Transformer), PFS (progression free survival), OS (overall survival), GRAD-CAM (gradient-weighted class activation mapping), ROI (region of interest), RFA (radiofrequency ablation), CT (computed tomography), MRI (magnetic resonance imaging), AUC (area under curve), NLP (natural language processing), SOTA (State-of-the-Art), AP (arterial phase), VP (venous phase), DP (delay phase), PACS (Picture Archiving and Communication Systems), LR (learning rate), ROC (receiver operating characteristic), CV (computer vision)To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to HPBAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries.CA A Cancer J Clin. 2018 Nov; 68: 394-424
- Electronic address: [email protected], European association for the study of the liver. EASL clinical practice guidelines: management of hepatocellular carcinoma.J Hepatol. 2018 Jul; 69: 182-236
- Microvascular invasion is a better predictor of tumor recurrence and overall survival following surgical resection for hepatocellular carcinoma compared to the Milan criteria.Ann Surg. 2011 Jul; 254: 108-113
- Adjuvant transarterial chemoembolization improves survival outcomes in hepatocellular carcinoma with microvascular invasion: a systematic review and meta-analysis.Eur J Surg Oncol J Eur Soc Surg Oncol Br Assoc Surg Oncol. 2019 Nov; 45: 2188-2196
- The impact of resection margin and microvascular invasion on long-term prognosis after curative resection of hepatocellular carcinoma: a multi-institutional study.HPB. 2019 Aug; 21: 962-971
- Can current preoperative imaging Be used to detect microvascular invasion of hepatocellular carcinoma?.Radiology. 2016 May; 279: 432-442
- Nomogram for preoperative estimation of microvascular invasion risk in hepatitis B virus–related hepatocellular carcinoma within the milan criteria.JAMA Surg. 2016 Apr 1; 151: 356
- Radiomics: the bridge between medical imaging and personalized medicine.Nat Rev Clin Oncol. 2017 Dec; 14: 749-762
- Radiomic analysis of contrast-enhanced CT predicts microvascular invasion and outcome in hepatocellular carcinoma.J Hepatol. 2019 Jun; 70: 1133-1144
- Preoperative prediction of microvascular invasion in hepatocellular cancer: a radiomics model using Gd-EOB-DTPA-enhanced MRI.Eur Radiol. 2019 Sep; 29: 4648-4659
- Predicting EGFR mutation status in lung adenocarcinoma on computed tomography image using deep learning.Eur Respir J. 2019 Mar; 531800986
- A liver fibrosis staging method using cross-contrast network.Expert Syst Appl. 2019 Sep; 130: 124-131
- Deep convolutional neural network-aided detection of portal hypertension in patients with cirrhosis.Clin Gastroenterol Hepatol. 2020 Dec; 18: 2998-3007.e5
- Deep residual learning for image recognition.Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778
- Prediction of microvascular invasion in hepatocellular carcinoma via deep learning: a multi-center and prospective validation study.Cancers. 2021 May 14; 13: 2368
- Attention is all you need.([Internet])in: Advances in neural information processing systems. Curran Associates, Inc., 2017 ([cited 2022 Oct 1]. Available from:)
- An image is worth 16x16 words: transformers for image recognition at scale.arXiv e-prints. 2020; (arXiv: 2010.11929)
- Cervical lesion classification method based on cross-validation decision fusion method of vision transformer and DenseNet.J Healthc Eng. 2022; 20223241422
- COVID-transformer: interpretable COVID-19 detection using vision transformer for Healthcare.Int J Environ Res Publ Health. 2021 Oct 21; 1811086
- Practice guidelines for the pathological diagnosis of primary liver cancer: 2015 update.World J Gastroenterol. 2016 Nov 14; 22: 9279-9287
- Grad-CAM: visual explanations from deep networks via gradient-based localization.Int J Comput Vis. 2020 Feb; 128: 336-359
- Is it time to replace CNNs with transformers for medical images?.arXiv preprint. 2021; (arXiv:2108.09038)
- Predicting microvascular invasion in hepatocellular carcinoma: a deep learning model validated across hospitals.Cancer Imag. 2021 Dec; 21: 56
- Deep learning with 3D convolutional neural network for noninvasive prediction of microvascular invasion in hepatocellular carcinoma.J Magn Reson Imag. 2021 Jul; 54: 134-143
- Prediction of microvascular invasion of hepatocellular carcinoma based on contrast-enhanced MR and 3D convolutional neural networks.Front Oncol. 2021 Mar 4; 11588010
- Preoperative identification of microvascular invasion in hepatocellular carcinoma by XGBoost and deep learning.J Cancer Res Clin Oncol. 2021 Mar; 147: 821-833
- A computed tomography radiogenomic biomarker predicts microvascular invasion and clinical outcomes in hepatocellular carcinoma.Hepatol Baltim Md. 2015 Sep; 62: 792-800
- Noninvasive KRAS mutation estimation in colorectal cancer using a deep learning method based on CT imaging.BMC Med Imag. 2020 Jun 1; 20: 59
- Noninvasive prediction of occult peritoneal metastasis in gastric cancer using deep learning.JAMA Netw Open. 2021 Jan 5; 4e2032269
- Deep learning radiomics based on contrast enhanced computed tomography predicts microvascular invasion and survival outcome in early stage hepatocellular carcinoma.Eur J Surg Oncol. 2022 May; 48: 1068-1077
- CT image-based texture analysis to predict microvascular invasion in primary hepatocellular carcinoma.J Digit Imag. 2020 Dec; 33: 1365-1375
- Diagnostic accuracy of artificial intelligence based on imaging data for preoperative prediction of microvascular invasion in hepatocellular carcinoma: a systematic review and meta-analysis.Front Oncol. 2022 Feb 24; 12763842
- Using deep learning to predict microvascular invasion in hepatocellular carcinoma based on dynamic contrast-enhanced MRI combined with clinical parameters.J Cancer Res Clin Oncol. 2021 Dec; 147: 3757-3767
Article info
Publication history
Published online: February 02, 2023
Accepted:
January 30,
2023
Received:
August 23,
2022
Publication stage
In Press Corrected ProofFootnotes
The paper is not based on a previous communication to a society or meeting.
Identification
Copyright
© 2023 International Hepato-Pancreato-Biliary Association Inc. Published by Elsevier Ltd. All rights reserved.
