Cargando…

Clinical Interpretability of Deep Learning for Predicting Microvascular Invasion in Hepatocellular Carcinoma by Using Attention Mechanism

Preoperative prediction of microvascular invasion (MVI) is essential for management decision in hepatocellular carcinoma (HCC). Deep learning-based prediction models of MVI are numerous but lack clinical interpretation due to their “black-box” nature. Consequently, we aimed to use an attention-guide...

Descripción completa

Detalles Bibliográficos
Autores principales: You, Huayu, Wang, Jifei, Ma, Ruixia, Chen, Yuying, Li, Lujie, Song, Chenyu, Dong, Zhi, Feng, Shiting, Zhou, Xiaoqi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10451856/
https://www.ncbi.nlm.nih.gov/pubmed/37627833
http://dx.doi.org/10.3390/bioengineering10080948
_version_ 1785095521019363328
author You, Huayu
Wang, Jifei
Ma, Ruixia
Chen, Yuying
Li, Lujie
Song, Chenyu
Dong, Zhi
Feng, Shiting
Zhou, Xiaoqi
author_facet You, Huayu
Wang, Jifei
Ma, Ruixia
Chen, Yuying
Li, Lujie
Song, Chenyu
Dong, Zhi
Feng, Shiting
Zhou, Xiaoqi
author_sort You, Huayu
collection PubMed
description Preoperative prediction of microvascular invasion (MVI) is essential for management decision in hepatocellular carcinoma (HCC). Deep learning-based prediction models of MVI are numerous but lack clinical interpretation due to their “black-box” nature. Consequently, we aimed to use an attention-guided feature fusion network, including intra- and inter-attention modules, to solve this problem. This retrospective study recruited 210 HCC patients who underwent gadoxetate-enhanced MRI examination before surgery. The MRIs on pre-contrast, arterial, portal, and hepatobiliary phases (hepatobiliary phase: HBP) were used to develop single-phase and multi-phase models. Attention weights provided by attention modules were used to obtain visual explanations of predictive decisions. The four-phase fusion model achieved the highest area under the curve (AUC) of 0.92 (95% CI: 0.84–1.00), and the other models proposed AUCs of 0.75–0.91. Attention heatmaps of collaborative-attention layers revealed that tumor margins in all phases and peritumoral areas in the arterial phase and HBP were salient regions for MVI prediction. Heatmaps of weights in fully connected layers showed that the HBP contributed the most to MVI prediction. Our study firstly implemented self-attention and collaborative-attention to reveal the relationship between deep features and MVI, improving the clinical interpretation of prediction models. The clinical interpretability offers radiologists and clinicians more confidence to apply deep learning models in clinical practice, helping HCC patients formulate personalized therapies.
format Online
Article
Text
id pubmed-10451856
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-104518562023-08-26 Clinical Interpretability of Deep Learning for Predicting Microvascular Invasion in Hepatocellular Carcinoma by Using Attention Mechanism You, Huayu Wang, Jifei Ma, Ruixia Chen, Yuying Li, Lujie Song, Chenyu Dong, Zhi Feng, Shiting Zhou, Xiaoqi Bioengineering (Basel) Article Preoperative prediction of microvascular invasion (MVI) is essential for management decision in hepatocellular carcinoma (HCC). Deep learning-based prediction models of MVI are numerous but lack clinical interpretation due to their “black-box” nature. Consequently, we aimed to use an attention-guided feature fusion network, including intra- and inter-attention modules, to solve this problem. This retrospective study recruited 210 HCC patients who underwent gadoxetate-enhanced MRI examination before surgery. The MRIs on pre-contrast, arterial, portal, and hepatobiliary phases (hepatobiliary phase: HBP) were used to develop single-phase and multi-phase models. Attention weights provided by attention modules were used to obtain visual explanations of predictive decisions. The four-phase fusion model achieved the highest area under the curve (AUC) of 0.92 (95% CI: 0.84–1.00), and the other models proposed AUCs of 0.75–0.91. Attention heatmaps of collaborative-attention layers revealed that tumor margins in all phases and peritumoral areas in the arterial phase and HBP were salient regions for MVI prediction. Heatmaps of weights in fully connected layers showed that the HBP contributed the most to MVI prediction. Our study firstly implemented self-attention and collaborative-attention to reveal the relationship between deep features and MVI, improving the clinical interpretation of prediction models. The clinical interpretability offers radiologists and clinicians more confidence to apply deep learning models in clinical practice, helping HCC patients formulate personalized therapies. MDPI 2023-08-09 /pmc/articles/PMC10451856/ /pubmed/37627833 http://dx.doi.org/10.3390/bioengineering10080948 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
You, Huayu
Wang, Jifei
Ma, Ruixia
Chen, Yuying
Li, Lujie
Song, Chenyu
Dong, Zhi
Feng, Shiting
Zhou, Xiaoqi
Clinical Interpretability of Deep Learning for Predicting Microvascular Invasion in Hepatocellular Carcinoma by Using Attention Mechanism
title Clinical Interpretability of Deep Learning for Predicting Microvascular Invasion in Hepatocellular Carcinoma by Using Attention Mechanism
title_full Clinical Interpretability of Deep Learning for Predicting Microvascular Invasion in Hepatocellular Carcinoma by Using Attention Mechanism
title_fullStr Clinical Interpretability of Deep Learning for Predicting Microvascular Invasion in Hepatocellular Carcinoma by Using Attention Mechanism
title_full_unstemmed Clinical Interpretability of Deep Learning for Predicting Microvascular Invasion in Hepatocellular Carcinoma by Using Attention Mechanism
title_short Clinical Interpretability of Deep Learning for Predicting Microvascular Invasion in Hepatocellular Carcinoma by Using Attention Mechanism
title_sort clinical interpretability of deep learning for predicting microvascular invasion in hepatocellular carcinoma by using attention mechanism
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10451856/
https://www.ncbi.nlm.nih.gov/pubmed/37627833
http://dx.doi.org/10.3390/bioengineering10080948
work_keys_str_mv AT youhuayu clinicalinterpretabilityofdeeplearningforpredictingmicrovascularinvasioninhepatocellularcarcinomabyusingattentionmechanism
AT wangjifei clinicalinterpretabilityofdeeplearningforpredictingmicrovascularinvasioninhepatocellularcarcinomabyusingattentionmechanism
AT maruixia clinicalinterpretabilityofdeeplearningforpredictingmicrovascularinvasioninhepatocellularcarcinomabyusingattentionmechanism
AT chenyuying clinicalinterpretabilityofdeeplearningforpredictingmicrovascularinvasioninhepatocellularcarcinomabyusingattentionmechanism
AT lilujie clinicalinterpretabilityofdeeplearningforpredictingmicrovascularinvasioninhepatocellularcarcinomabyusingattentionmechanism
AT songchenyu clinicalinterpretabilityofdeeplearningforpredictingmicrovascularinvasioninhepatocellularcarcinomabyusingattentionmechanism
AT dongzhi clinicalinterpretabilityofdeeplearningforpredictingmicrovascularinvasioninhepatocellularcarcinomabyusingattentionmechanism
AT fengshiting clinicalinterpretabilityofdeeplearningforpredictingmicrovascularinvasioninhepatocellularcarcinomabyusingattentionmechanism
AT zhouxiaoqi clinicalinterpretabilityofdeeplearningforpredictingmicrovascularinvasioninhepatocellularcarcinomabyusingattentionmechanism