Literature DB >> 36268072

Improving feature extraction from histopathological images through a fine-tuning ImageNet model.

Xingyu Li1, Min Cen1, Jinfeng Xu2, Hong Zhang1, Xu Steven Xu3.   

Abstract

Background: Due to lack of annotated pathological images, transfer learning has been the predominant approach in the field of digital pathology. Pre-trained neural networks based on ImageNet database are often used to extract "off-the-shelf" features, achieving great success in predicting tissue types, molecular features, and clinical outcomes, etc. We hypothesize that fine-tuning the pre-trained models using histopathological images could further improve feature extraction, and downstream prediction performance.
Methods: We used 100 000 annotated H&E image patches for colorectal cancer (CRC) to fine-tune a pre-trained Xception model via a 2-step approach. The features extracted from fine-tuned Xception (FTX-2048) model and Image-pretrained (IMGNET-2048) model were compared through: (1) tissue classification for H&E images from CRC, same image type that was used for fine-tuning; (2) prediction of immune-related gene expression, and (3) gene mutations for lung adenocarcinoma (LUAD). Five-fold cross validation was used for model performance evaluation. Each experiment was repeated 50 times. Findings: The extracted features from the fine-tuned FTX-2048 exhibited significantly higher accuracy (98.4%) for predicting tissue types of CRC compared to the "off-the-shelf" features directly from Xception based on ImageNet database (96.4%) (P value = 2.2 × 10-6). Particularly, FTX-2048 markedly improved the accuracy for stroma from 87% to 94%. Similarly, features from FTX-2048 boosted the prediction of transcriptomic expression of immune-related genes in LUAD. For the genes that had significant relationships with image features (P < 0.05, n = 171), the features from the fine-tuned model improved the prediction for the majority of the genes (139; 81%). In addition, features from FTX-2048 improved prediction of mutation for 5 out of 9 most frequently mutated genes (STK11, TP53, LRP1B, NF1, and FAT1) in LUAD. Conclusions: We proved the concept that fine-tuning the pretrained ImageNet neural networks with histopathology images can produce higher quality features and better prediction performance for not only the same-cancer tissue classification where similar images from the same cancer are used for fine-tuning, but also cross-cancer prediction for gene expression and mutation at patient level.
© 2022 The Authors.

Entities:  

Keywords:  Colorectal cancer; Deep learning; Fine-tuning; Gene-mutation; H&E image; Lung adenocarcinoma; RNA-seq expression; TCGA dataset; Whole slide images

Year:  2022        PMID: 36268072      PMCID: PMC9577036          DOI: 10.1016/j.jpi.2022.100115

Source DB:  PubMed          Journal:  J Pathol Inform


  26 in total

1.  Fine-Tuning and training of densenet for histopathology image representation using TCGA diagnostic slides.

Authors:  Abtin Riasatian; Morteza Babaie; Danial Maleki; Shivam Kalra; Mojtaba Valipour; Sobhan Hemati; Manit Zaveri; Amir Safarpoor; Sobhan Shafiei; Mehdi Afshari; Maral Rasoolijaberi; Milad Sikaroudi; Mohd Adnan; Sultaan Shah; Charles Choi; Savvas Damaskinos; Clinton Jv Campbell; Phedias Diamandis; Liron Pantanowitz; Hany Kashani; Ali Ghodsi; H R Tizhoosh
Journal:  Med Image Anal       Date:  2021-03-10       Impact factor: 8.545

2.  Deep learning for prediction of colorectal cancer outcome: a discovery and validation study.

Authors:  Ole-Johan Skrede; Sepp De Raedt; Andreas Kleppe; Tarjei S Hveem; Knut Liestøl; John Maddison; Hanne A Askautrud; Manohar Pradhan; John Arne Nesheim; Fritz Albregtsen; Inger Nina Farstad; Enric Domingo; David N Church; Arild Nesbakken; Neil A Shepherd; Ian Tomlinson; Rachel Kerr; Marco Novelli; David J Kerr; Håvard E Danielsen
Journal:  Lancet       Date:  2020-02-01       Impact factor: 79.321

3.  Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks.

Authors:  Jiawen Yao; Xinliang Zhu; Jitendra Jonnagaddala; Nicholas Hawkins; Junzhou Huang
Journal:  Med Image Anal       Date:  2020-07-19       Impact factor: 8.545

4.  Learning Facial Action Units from Web Images with Scalable Weakly Supervised Clustering.

Authors:  Kaili Zhao; Wen-Sheng Chu; Aleix M Martinez
Journal:  Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit       Date:  2018-12-17

5.  Deep-Learning Convolutional Neural Networks Accurately Classify Genetic Mutations in Gliomas.

Authors:  P Chang; J Grinband; B D Weinberg; M Bardis; M Khy; G Cadena; M-Y Su; S Cha; C G Filippi; D Bota; P Baldi; L M Poisson; R Jain; D Chow
Journal:  AJNR Am J Neuroradiol       Date:  2018-05-10       Impact factor: 3.825

Review 6.  Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology.

Authors:  Kaustav Bera; Kurt A Schalper; David L Rimm; Vamsidhar Velcheti; Anant Madabhushi
Journal:  Nat Rev Clin Oncol       Date:  2019-08-09       Impact factor: 66.675

7.  Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study.

Authors:  Jakob Nikolas Kather; Johannes Krisam; Pornpimol Charoentong; Tom Luedde; Esther Herpel; Cleo-Aron Weis; Timo Gaiser; Alexander Marx; Nektarios A Valous; Dyke Ferber; Lina Jansen; Constantino Carlos Reyes-Aldasoro; Inka Zörnig; Dirk Jäger; Hermann Brenner; Jenny Chang-Claude; Michael Hoffmeister; Niels Halama
Journal:  PLoS Med       Date:  2019-01-24       Impact factor: 11.069

8.  Mapping Driver Mutations to Histopathological Subtypes in Papillary Thyroid Carcinoma: Applying a Deep Convolutional Neural Network.

Authors:  Peiling Tsou; Chang-Jiun Wu
Journal:  J Clin Med       Date:  2019-10-14       Impact factor: 4.241

9.  How much off-the-shelf knowledge is transferable from natural images to pathology images?

Authors:  Xingyu Li; Konstantinos N Plataniotis
Journal:  PLoS One       Date:  2020-10-14       Impact factor: 3.240

10.  Image-based consensus molecular subtype (imCMS) classification of colorectal cancer using deep learning.

Authors:  Jens Rittscher; Viktor H Koelzer; Korsuk Sirinukunwattana; Enric Domingo; Susan D Richman; Keara L Redmond; Andrew Blake; Clare Verrill; Simon J Leedham; Aikaterini Chatzipli; Claire Hardy; Celina M Whalley; Chieh-Hsi Wu; Andrew D Beggs; Ultan McDermott; Philip D Dunne; Angela Meade; Steven M Walker; Graeme I Murray; Leslie Samuel; Matthew Seymour; Ian Tomlinson; Phil Quirke; Timothy Maughan
Journal:  Gut       Date:  2020-07-20       Impact factor: 23.059

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.