Literature DB >> 32108950

Predicting Survival After Hepatocellular Carcinoma Resection Using Deep Learning on Histological Slides.

Charlie Saillard1, Benoit Schmauch1, Oumeima Laifa1, Matahi Moarii1, Sylvain Toldo1, Mikhail Zaslavskiy1, Elodie Pronier1, Alexis Laurent2,3, Giuliana Amaddeo3,4,5, Hélène Regnault5, Daniele Sommacale2,3,4, Marianne Ziol6,7, Jean-Michel Pawlotsky3,4,8, Sébastien Mulé3,4,9, Alain Luciani3,4,9, Gilles Wainrib1, Thomas Clozel1, Pierre Courtiol1, Julien Calderaro3,4,10.   

Abstract

BACKGROUND AND AIMS: Standardized and robust risk-stratification systems for patients with hepatocellular carcinoma (HCC) are required to improve therapeutic strategies and investigate the benefits of adjuvant systemic therapies after curative resection/ablation. APPROACH AND
RESULTS: In this study, we used two deep-learning algorithms based on whole-slide digitized histological slides (whole-slide imaging; WSI) to build models for predicting survival of patients with HCC treated by surgical resection. Two independent series were investigated: a discovery set (Henri Mondor Hospital, n = 194) used to develop our algorithms and an independent validation set (The Cancer Genome Atlas [TCGA], n = 328). WSIs were first divided into small squares ("tiles"), and features were extracted with a pretrained convolutional neural network (preprocessing step). The first deep-learning-based algorithm ("SCHMOWDER") uses an attention mechanism on tumoral areas annotated by a pathologist whereas the second ("CHOWDER") does not require human expertise. In the discovery set, c-indices for survival prediction of SCHMOWDER and CHOWDER reached 0.78 and 0.75, respectively. Both models outperformed a composite score incorporating all baseline variables associated with survival. Prognostic value of the models was further validated in the TCGA data set, and, as observed in the discovery series, both models had a higher discriminatory power than a score combining all baseline variables associated with survival. Pathological review showed that the tumoral areas most predictive of poor survival were characterized by vascular spaces, the macrotrabecular architectural pattern, and a lack of immune infiltration.
CONCLUSIONS: This study shows that artificial intelligence can help refine the prediction of HCC prognosis. It highlights the importance of pathologist/machine interactions for the construction of deep-learning algorithms that benefit from expert knowledge and allow a biological understanding of their output.
© 2020 by the American Association for the Study of Liver Diseases.

Entities:  

Mesh:

Year:  2020        PMID: 32108950     DOI: 10.1002/hep.31207

Source DB:  PubMed          Journal:  Hepatology        ISSN: 0270-9139            Impact factor:   17.425


  29 in total

Review 1.  Deep learning in histopathology: the path to the clinic.

Authors:  Jeroen van der Laak; Geert Litjens; Francesco Ciompi
Journal:  Nat Med       Date:  2021-05-14       Impact factor: 53.440

Review 2.  Artificial intelligence for the prevention and clinical management of hepatocellular carcinoma.

Authors:  Julien Calderaro; Tobias Paul Seraphin; Tom Luedde; Tracey G Simon
Journal:  J Hepatol       Date:  2022-06       Impact factor: 30.083

3.  LncRNA RNCR3 Promotes the Progression of HCC by Activating the Akt/GSK3β Signaling Pathway.

Authors:  Qi Xie; Tongfa Ju; Chunhua Zhou; Lulu Zhai
Journal:  Evid Based Complement Alternat Med       Date:  2020-09-29       Impact factor: 2.629

4.  Evolutionary Learning-Derived Clinical-Radiomic Models for Predicting Early Recurrence of Hepatocellular Carcinoma after Resection.

Authors:  I-Cheng Lee; Jo-Yu Huang; Ting-Chun Chen; Chia-Heng Yen; Nai-Chi Chiu; Hsuen-En Hwang; Jia-Guan Huang; Chien-An Liu; Gar-Yang Chau; Rheun-Chuan Lee; Yi-Ping Hung; Yee Chao; Shinn-Ying Ho; Yi-Hsiang Huang
Journal:  Liver Cancer       Date:  2021-09-20       Impact factor: 11.740

5.  Communicator-Driven Data Preprocessing Improves Deep Transfer Learning of Histopathological Prediction of Pancreatic Ductal Adenocarcinoma.

Authors:  Raphael M Kronberg; Lena Haeberle; Melanie Pfaus; Haifeng C Xu; Karina S Krings; Martin Schlensog; Tilman Rau; Aleksandra A Pandyra; Karl S Lang; Irene Esposito; Philipp A Lang
Journal:  Cancers (Basel)       Date:  2022-04-13       Impact factor: 6.575

6.  Deep learning predicts postsurgical recurrence of hepatocellular carcinoma from digital histopathologic images.

Authors:  Daniel L Rubin; Jeanne Shen; Rikiya Yamashita; Jin Long; Atif Saleem
Journal:  Sci Rep       Date:  2021-01-21       Impact factor: 4.379

Review 7.  How Do Machines Learn? Artificial Intelligence as a New Era in Medicine.

Authors:  Oliwia Koteluk; Adrian Wartecki; Sylwia Mazurek; Iga Kołodziejczak; Andrzej Mackiewicz
Journal:  J Pers Med       Date:  2021-01-07

Review 8.  State of machine and deep learning in histopathological applications in digestive diseases.

Authors:  Soma Kobayashi; Joel H Saltz; Vincent W Yang
Journal:  World J Gastroenterol       Date:  2021-05-28       Impact factor: 5.742

9.  Prediction of prognostic risk factors in hepatocellular carcinoma with transarterial chemoembolization using multi-modal multi-task deep learning.

Authors:  Qiu-Ping Liu; Xun Xu; Fei-Peng Zhu; Yu-Dong Zhang; Xi-Sheng Liu
Journal:  EClinicalMedicine       Date:  2020-06-07

Review 10.  Application of artificial intelligence in the diagnosis and treatment of hepatocellular carcinoma: A review.

Authors:  Miguel Jiménez Pérez; Rocío González Grande
Journal:  World J Gastroenterol       Date:  2020-10-07       Impact factor: 5.742

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.