BACKGROUND & AIMS: Patients with hepatocellular carcinoma (HCC) displaying overexpression of immune gene signatures are likely to be more sensitive to immunotherapy, however, the use of such signatures in clinical settings remains challenging. We thus aimed, using artificial intelligence (AI) on whole-slide digital histological images, to develop models able to predict the activation of 6 immune gene signatures. METHODS: AI models were trained and validated in 2 different series of patients with HCC treated by surgical resection. Gene expression was investigated using RNA sequencing or NanoString technology. Three deep learning approaches were investigated: patch-based, classic MIL and CLAM. Pathological reviewing of the most predictive tissue areas was performed for all gene signatures. RESULTS: The CLAM model showed the best overall performance in the discovery series. Its best-fold areas under the receiver operating characteristic curves (AUCs) for the prediction of tumors with upregulation of the immune gene signatures ranged from 0.78 to 0.91. The different models generalized well in the validation dataset with AUCs ranging from 0.81 to 0.92. Pathological analysis of highly predictive tissue areas showed enrichment in lymphocytes, plasma cells, and neutrophils. CONCLUSION: We have developed and validated AI-based pathology models able to predict the activation of several immune and inflammatory gene signatures. Our approach also provides insights into the morphological features that impact the model predictions. This proof-of-concept study shows that AI-based pathology could represent a novel type of biomarker that will ease the translation of our biological knowledge of HCC into clinical practice. LAY SUMMARY: Immune and inflammatory gene signatures may be associated with increased sensitivity to immunotherapy in patients with advanced hepatocellular carcinoma. In the present study, the use of artificial intelligence-based pathology enabled us to predict the activation of these signatures directly from histology.
%0 Journal Article
%1 Zeng2022-tp
%A Zeng, Qinghe
%A Klein, Christophe
%A Caruso, Stefano
%A Maille, Pascale
%A Laleh, Narmin Ghaffari
%A Sommacale, Daniele
%A Laurent, Alexis
%A Amaddeo, Giuliana
%A Gentien, David
%A Rapinat, Audrey
%A Regnault, Hélène
%A Charpy, Cécile
%A Nguyen, Cong Trung
%A Tournigand, Christophe
%A Brustia, Raffaele
%A Pawlotsky, Jean Michel
%A Kather, Jakob Nikolas
%A Maiuri, Maria Chiara
%A Loménie, Nicolas
%A Calderaro, Julien
%D 2022
%I Elsevier BV
%J J. Hepatol.
%K artificial deep gene image immune intelligence; learning; pathology; signatures; slide whole
%N 1
%P 116--127
%T Artificial intelligence predicts immune and inflammatory gene signatures directly from hepatocellular carcinoma histology
%V 77
%X BACKGROUND & AIMS: Patients with hepatocellular carcinoma (HCC) displaying overexpression of immune gene signatures are likely to be more sensitive to immunotherapy, however, the use of such signatures in clinical settings remains challenging. We thus aimed, using artificial intelligence (AI) on whole-slide digital histological images, to develop models able to predict the activation of 6 immune gene signatures. METHODS: AI models were trained and validated in 2 different series of patients with HCC treated by surgical resection. Gene expression was investigated using RNA sequencing or NanoString technology. Three deep learning approaches were investigated: patch-based, classic MIL and CLAM. Pathological reviewing of the most predictive tissue areas was performed for all gene signatures. RESULTS: The CLAM model showed the best overall performance in the discovery series. Its best-fold areas under the receiver operating characteristic curves (AUCs) for the prediction of tumors with upregulation of the immune gene signatures ranged from 0.78 to 0.91. The different models generalized well in the validation dataset with AUCs ranging from 0.81 to 0.92. Pathological analysis of highly predictive tissue areas showed enrichment in lymphocytes, plasma cells, and neutrophils. CONCLUSION: We have developed and validated AI-based pathology models able to predict the activation of several immune and inflammatory gene signatures. Our approach also provides insights into the morphological features that impact the model predictions. This proof-of-concept study shows that AI-based pathology could represent a novel type of biomarker that will ease the translation of our biological knowledge of HCC into clinical practice. LAY SUMMARY: Immune and inflammatory gene signatures may be associated with increased sensitivity to immunotherapy in patients with advanced hepatocellular carcinoma. In the present study, the use of artificial intelligence-based pathology enabled us to predict the activation of these signatures directly from histology.
@article{Zeng2022-tp,
abstract = {BACKGROUND \& AIMS: Patients with hepatocellular carcinoma (HCC) displaying overexpression of immune gene signatures are likely to be more sensitive to immunotherapy, however, the use of such signatures in clinical settings remains challenging. We thus aimed, using artificial intelligence (AI) on whole-slide digital histological images, to develop models able to predict the activation of 6 immune gene signatures. METHODS: AI models were trained and validated in 2 different series of patients with HCC treated by surgical resection. Gene expression was investigated using RNA sequencing or NanoString technology. Three deep learning approaches were investigated: patch-based, classic MIL and CLAM. Pathological reviewing of the most predictive tissue areas was performed for all gene signatures. RESULTS: The CLAM model showed the best overall performance in the discovery series. Its best-fold areas under the receiver operating characteristic curves (AUCs) for the prediction of tumors with upregulation of the immune gene signatures ranged from 0.78 to 0.91. The different models generalized well in the validation dataset with AUCs ranging from 0.81 to 0.92. Pathological analysis of highly predictive tissue areas showed enrichment in lymphocytes, plasma cells, and neutrophils. CONCLUSION: We have developed and validated AI-based pathology models able to predict the activation of several immune and inflammatory gene signatures. Our approach also provides insights into the morphological features that impact the model predictions. This proof-of-concept study shows that AI-based pathology could represent a novel type of biomarker that will ease the translation of our biological knowledge of HCC into clinical practice. LAY SUMMARY: Immune and inflammatory gene signatures may be associated with increased sensitivity to immunotherapy in patients with advanced hepatocellular carcinoma. In the present study, the use of artificial intelligence-based pathology enabled us to predict the activation of these signatures directly from histology.},
added-at = {2024-09-10T11:54:51.000+0200},
author = {Zeng, Qinghe and Klein, Christophe and Caruso, Stefano and Maille, Pascale and Laleh, Narmin Ghaffari and Sommacale, Daniele and Laurent, Alexis and Amaddeo, Giuliana and Gentien, David and Rapinat, Audrey and Regnault, H{\'e}l{\`e}ne and Charpy, C{\'e}cile and Nguyen, Cong Trung and Tournigand, Christophe and Brustia, Raffaele and Pawlotsky, Jean Michel and Kather, Jakob Nikolas and Maiuri, Maria Chiara and Lom{\'e}nie, Nicolas and Calderaro, Julien},
biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/238cb996871c3463db5d20401e83a1d20/scadsfct},
interhash = {d0c003e1b9761bb874a5cb2d1bdcd2d3},
intrahash = {38cb996871c3463db5d20401e83a1d20},
journal = {J. Hepatol.},
keywords = {artificial deep gene image immune intelligence; learning; pathology; signatures; slide whole},
language = {en},
month = jul,
number = 1,
pages = {116--127},
publisher = {Elsevier BV},
timestamp = {2024-09-10T11:54:51.000+0200},
title = {Artificial intelligence predicts immune and inflammatory gene signatures directly from hepatocellular carcinoma histology},
volume = 77,
year = 2022
}