CoChat
Sign Up
Cited by 147AI in cancer detectionColorectal Cancer Screening and DetectionRadiomics and Machine Learning in Medical Imaging

The DOI matches its Crossref record; 62 of the 62 references it cites were found in a registry or an index.

Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images

Open access
Yu, Gang, Sun, Kai, Xu, Chao, Shi, Xing-Hua, Wu, Chong, Xie, Ting, Meng, Run-Qi, Meng, Xiang-He, Wang, Kuan-Song, Xiao, Hong-Mei, Deng, Hong-Wen·2021·Nature Communications
DOI 10.1038/s41467-021-26643-8PMC PMC8563931

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Machine-assisted pathological recognition has been focused on supervised learning (SL) that suffers from a significant annotation bottleneck. We propose a semi-supervised learning (SSL) method based on the mean teacher architecture using 13,111 whole slide images of colorectal cancer from 8803 subjects from 13 independent centers. SSL (~3150 labeled, ~40,950 unlabeled; ~6300 labeled, ~37,800 unlabeled patches) performs significantly better than the SL. No significant difference is found between SSL (~6300 labeled, ~37,800 unlabeled) and SL (~44,100 labeled) at patch-level diagnoses (area under the curve (AUC): 0.980 ± 0.014 vs. 0.987 ± 0.008, P value = 0.134) and patient-level diagnoses (AUC: 0.974 ± 0.013 vs. 0.980 ± 0.010, P value = 0.117), which is close to human pathologists (average AUC: 0.969). The evaluation on 15,000 lung and 294,912 lymph node images also confirm SSL can achieve similar performance as that of SL with massive annotations. SSL dramatically reduces the annotations, which has great potential to effectively build expert-level pathological artificial intelligence platforms in practice.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41467-021-26643-8

Cites

62 of 62 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 The flow chart of the colorectal cancer study. a Semi-supervised learning (SSL) and supervised learning (SL) are performed on different labeled and unlabeled patches from 70% whole slide images (WSIs) of Dataset-PATT. Model-5%/10%-SSL and Model-5%/10%/70%-SL are obtained. b The patch-level test is performed on the patches from 30% WSIs of Dataset-PATT and whole data set of Dataset-PAT, and the above five models predict whether there is cancer or not in the patches. c The patient-level test and human-AI competition are performed on Dataset-PT and Dataset-HAC, respectively. Each WSI is divided into many patches, and three models infer whether these patches are cancerous or normal individually. The clustering-based method is then used on the WSI. If there is a cluster of four positive patches on a WSI, the WSI is positive. A subject with one or more positive WSIs is cancerous, or the subject is normal.
Fig. 1 The flow chart of the colorectal cancer study. a Semi-supervised learning (SSL) and supervised learning (SL) are performed on different labeled and unlabeled patches from 70% whole slide images (WSIs) of Dataset-PATT. Model-5%/10%-SSL and Model-5%/10%/70%-SL are obtained. b The patch-level test is performed on the patches from 30% WSIs of Dataset-PATT and whole data set of Dataset-PAT, and the above five models predict whether there is cancer or not in the patches. c The patient-level test and human-AI competition are performed on Dataset-PT and Dataset-HAC, respectively. Each WSI is divided into many patches, and three models infer whether these patches are cancerous or normal individually. The clustering-based method is then used on the WSI. If there is a cluster of four positive patches on a WSI, the WSI is positive. A subject with one or more positive WSIs is cancerous, or the subject is normal.CC BY · PubMed Central
Fig. 2 Area under the curve (AUC) distribution of five models at patch level. The boxes indicate the upper and lower quartile values, and the whiskers indicate the minima and maxima values. The horizontal bar in the box indicates the median, while the cross indicates the mean. The circles represent data points, and the scatter dots indicate outliers. * indicates significant difference, and ** indicates no significant difference. a The evaluation of five models on the testing set of Dataset-PATT. Eight versions of each model (number of experiments per model = 8) are tested at their testing sets (number of samples/patches per testing set = ~18,819) independent from their training sets, respectively. The Wilcoxon-signed rank test is then used to evaluate the significant difference of AUCs (sample size/group = 8) between two models. Two-sided P values are reported, and no adjustment is made. The average AUC and standard deviation of Model-5%-SSL and Model-5%-SL: 0.906 ± 0.064 vs. 0.789 ± 0.016, P value = 0.017; Model-10%-SSL and Model-10%-SL: 0.990 ± 0.009 vs. 0.944 ± 0.032, P value = 0.012; Model-10%-SSL and Model-70%-SL: 0.990 ± 0.009 vs. 0.994 ± 0.004, P value = 0.327. b The evaluation of 8 versions of five models on the Dataset-PAT (number of samples/patches per testing set = 100,000). Wilcoxon-signed rank test (sample size/group = 8), and two-sided P values are reported. Model-5%-SSL and Model-5%-SL: 0.948 ± 0.041 vs. 0.898 ± 0.029, P values = 0.017; Model-10%-SSL and Model-10%-SL: 0.970 ± 0.012 vs. 0.908 ± 0.024, P value = 0.012; Model-10%-SSL and Model-70%-SL: 0.970 ± 0.012 vs. 0.979 ± 0.005, P values = 0.263. The AUC values of each model on Dataset-PATT and Dataset-PAT are combined and the Wilcoxon-signed rank test is performed on the combined results (sample size/group = 16), and two-sided P values are reported. Model-5%-SSL and Model-5%-SL: 0.927 ± 0.058 vs. 0.843 ± 0.059, P value = 0.002; Model-10%-SSL and Model-10%-SL: 0.980 ± 0.014 vs. 0.926 ± 0.034, P value = 0.0004; Model-10%-SSL and Model-70%-SL: 0.980 ± 0.014 vs. 0.987 ± 0.008, P value = 0.134.
Fig. 2 Area under the curve (AUC) distribution of five models at patch level. The boxes indicate the upper and lower quartile values, and the whiskers indicate the minima and maxima values. The horizontal bar in the box indicates the median, while the cross indicates the mean. The circles represent data points, and the scatter dots indicate outliers. * indicates significant difference, and ** indicates no significant difference. a The evaluation of five models on the testing set of Dataset-PATT. Eight versions of each model (number of experiments per model = 8) are tested at their testing sets (number of samples/patches per testing set = ~18,819) independent from their training sets, respectively. The Wilcoxon-signed rank test is then used to evaluate the significant difference of AUCs (sample size/group = 8) between two models. Two-sided P values are reported, and no adjustment is made. The average AUC and standard deviation of Model-5%-SSL and Model-5%-SL: 0.906 ± 0.064 vs. 0.789 ± 0.016, P value = 0.017; Model-10%-SSL and Model-10%-SL: 0.990 ± 0.009 vs. 0.944 ± 0.032, P value = 0.012; Model-10%-SSL and Model-70%-SL: 0.990 ± 0.009 vs. 0.994 ± 0.004, P value = 0.327. b The evaluation of 8 versions of five models on the Dataset-PAT (number of samples/patches per testing set = 100,000). Wilcoxon-signed rank test (sample size/group = 8), and two-sided P values are reported. Model-5%-SSL and Model-5%-SL: 0.948 ± 0.041 vs. 0.898 ± 0.029, P values = 0.017; Model-10%-SSL and Model-10%-SL: 0.970 ± 0.012 vs. 0.908 ± 0.024, P value = 0.012; Model-10%-SSL and Model-70%-SL: 0.970 ± 0.012 vs. 0.979 ± 0.005, P values = 0.263. The AUC values of each model on Dataset-PATT and Dataset-PAT are combined and the Wilcoxon-signed rank test is performed on the combined results (sample size/group = 16), and two-sided P values are reported. Model-5%-SSL and Model-5%-SL: 0.927 ± 0.058 vs. 0.843 ± 0.059, P value = 0.002; Model-10%-SSL and Model-10%-SL: 0.980 ± 0.014 vs. 0.926 ± 0.034, P value = 0.0004; Model-10%-SSL and Model-70%-SL: 0.980 ± 0.014 vs. 0.987 ± 0.008, P value = 0.134.CC BY · PubMed Central
Fig. 3 The results of patient-level CRC recognition. Patient-level comparison of a Model-10%-SSL, b Model-10%-SL, and c Model-70%-SL on 12 independent data sets from Dataset-PT. Left: Radar maps illustrate the sensitivity, specificity, and area under the curve (AUC) of three models on 12 centers. Right: Boxplots show the distribution of sensitivity, specificity, accuracy, and AUC of the three models in these centers. The boxes indicate the upper and lower quartile values, and the whiskers indicate the minima and maxima values. The horizontal bar in the box indicates the median, while the cross indicates the mean. The circles represent data points, and the scatter dots indicate outliers. The average AUC and standard deviation (sample size = 12) are calculated for each model, and the Wilcoxon-signed rank test (sample size/group = 12) is then used to evaluate the significant difference of AUCs between two models. Two-sided P values are reported, and no adjustment is made. Model-10%-SSL vs. Model-10%-SL: AUC: 0.974 ± 0.013 vs. 0.819 ± 0.104, P value = 0.002; Model-10%-SSL vs. Model-70%-SL: 0.974 ± 0.013 vs. 0.980 ± 0.010, P value = 0.117. The data points are listed in Supplementary Data 1.
Fig. 3 The results of patient-level CRC recognition. Patient-level comparison of a Model-10%-SSL, b Model-10%-SL, and c Model-70%-SL on 12 independent data sets from Dataset-PT. Left: Radar maps illustrate the sensitivity, specificity, and area under the curve (AUC) of three models on 12 centers. Right: Boxplots show the distribution of sensitivity, specificity, accuracy, and AUC of the three models in these centers. The boxes indicate the upper and lower quartile values, and the whiskers indicate the minima and maxima values. The horizontal bar in the box indicates the median, while the cross indicates the mean. The circles represent data points, and the scatter dots indicate outliers. The average AUC and standard deviation (sample size = 12) are calculated for each model, and the Wilcoxon-signed rank test (sample size/group = 12) is then used to evaluate the significant difference of AUCs between two models. Two-sided P values are reported, and no adjustment is made. Model-10%-SSL vs. Model-10%-SL: AUC: 0.974 ± 0.013 vs. 0.819 ± 0.104, P value = 0.002; Model-10%-SSL vs. Model-70%-SL: 0.974 ± 0.013 vs. 0.980 ± 0.010, P value = 0.117. The data points are listed in Supplementary Data 1.CC BY · PubMed Central
Fig. 4 The Human-AI CRC competition results. Area under the curve (AUC) comparison of Model-10%-SSL(SSL), Model-70%-SL(SL) and six pathologists (a–f) using Dataset-HAC, which consists XH-dataset-HAC, PCH, TXH, HPH, ACL, FUS, GPH, SWH, AMU and SYU. Blue lines indicate the AUCs achieved by Model-10%-SSL. The F pathologist did not attend the competition of SYU, AMU, and SWH data set.
Fig. 4 The Human-AI CRC competition results. Area under the curve (AUC) comparison of Model-10%-SSL(SSL), Model-70%-SL(SL) and six pathologists (a–f) using Dataset-HAC, which consists XH-dataset-HAC, PCH, TXH, HPH, ACL, FUS, GPH, SWH, AMU and SYU. Blue lines indicate the AUCs achieved by Model-10%-SSL. The F pathologist did not attend the competition of SYU, AMU, and SWH data set.CC BY · PubMed Central
Fig. 5 Accuracy distribution of five models on the testing set of LC25000 dataset (number of samples/patches per testing set = 3000; number of experiments per model = 8). The boxes indicate the upper and lower quartile values, and the whiskers indicate the minima and maxima values. The horizontal bar in the box indicates the median, while the cross indicates the mean. The circles represent data points, and the scatter dots indicate outliers. * indicates significant difference, and ** indicates no significant difference. The Wilcoxon-signed rank test (sample size/group = 8) is then used to evaluate the significant difference in the accuracy between two models. Two-sided P values are reported, and no adjustment is made. The average AUC and standard deviation (sample size = 8) are calculated for each model. Lung-5%-SSL vs. Lung-5%-SL: 0.960 ± 0.006 vs. 0.918 ± 0.023, P value = 0.012; Lung-20%-SSL vs. Lung-20%-SL: 0.989 ± 0.003 vs. 0.961 ± 0.022, P value = 0.011; Lung-20%-SSL vs. Lung-80%-SL: 0.989 ± 0.003 vs. 0.993 ± 0.002, P value = 0.093.
Fig. 5 Accuracy distribution of five models on the testing set of LC25000 dataset (number of samples/patches per testing set = 3000; number of experiments per model = 8). The boxes indicate the upper and lower quartile values, and the whiskers indicate the minima and maxima values. The horizontal bar in the box indicates the median, while the cross indicates the mean. The circles represent data points, and the scatter dots indicate outliers. * indicates significant difference, and ** indicates no significant difference. The Wilcoxon-signed rank test (sample size/group = 8) is then used to evaluate the significant difference in the accuracy between two models. Two-sided P values are reported, and no adjustment is made. The average AUC and standard deviation (sample size = 8) are calculated for each model. Lung-5%-SSL vs. Lung-5%-SL: 0.960 ± 0.006 vs. 0.918 ± 0.023, P value = 0.012; Lung-20%-SSL vs. Lung-20%-SL: 0.989 ± 0.003 vs. 0.961 ± 0.022, P value = 0.011; Lung-20%-SSL vs. Lung-80%-SL: 0.989 ± 0.003 vs. 0.993 ± 0.002, P value = 0.093.CC BY · PubMed Central
Fig. 6 Area under the curve (AUC) distribution of five models on the testing set of PatchCamelyon data set (number of samples/patches per testing set = 32,768; number of experiments per model = 8). The boxes indicate the upper and lower quartile values, and the whiskers indicate the minima and maxima values. The horizontal bar in the box indicates the median, while the cross indicates the mean. The circles represent data points, and the scatter dots indicate outliers. * indicates significant difference, and ** indicates no significant difference. The Wilcoxon-signed rank test (sample size/group = 8) is then used to evaluate the significant difference of AUCs between the two models. Two-sided P values are reported, and no adjustment is made. The average AUC and standard deviation (sample size = 8) are calculated for each model. Pcam-1%-SSL vs. Pcam-1%-SL: 0.947 ± 0.008 vs. 0.912 ± 0.008, P value = 0.012; Pcam-5%-SSL vs. Pcam-5%-SL: 0.960 ± 0.002 vs. 0.943 ± 0.009, P value = 0.011; Pcam-5%-SSL vs. Pcam-100%-SL: 0.960 ± 0.002 vs. 0.961 ± 0.004, P value = 0.888.
Fig. 6 Area under the curve (AUC) distribution of five models on the testing set of PatchCamelyon data set (number of samples/patches per testing set = 32,768; number of experiments per model = 8). The boxes indicate the upper and lower quartile values, and the whiskers indicate the minima and maxima values. The horizontal bar in the box indicates the median, while the cross indicates the mean. The circles represent data points, and the scatter dots indicate outliers. * indicates significant difference, and ** indicates no significant difference. The Wilcoxon-signed rank test (sample size/group = 8) is then used to evaluate the significant difference of AUCs between the two models. Two-sided P values are reported, and no adjustment is made. The average AUC and standard deviation (sample size = 8) are calculated for each model. Pcam-1%-SSL vs. Pcam-1%-SL: 0.947 ± 0.008 vs. 0.912 ± 0.008, P value = 0.012; Pcam-5%-SSL vs. Pcam-5%-SL: 0.960 ± 0.002 vs. 0.943 ± 0.009, P value = 0.011; Pcam-5%-SSL vs. Pcam-100%-SL: 0.960 ± 0.002 vs. 0.961 ± 0.004, P value = 0.888.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 60 references

Research works printed but not linked: 2

  1. Prechelt, L. Neural Networks: Tricks of the Trade (Springer Berlin Heidelberg, 1998).
  2. Goodfellow, I., Bengio, Y. & Courville, A. Deep Learning 117 (The MIT Press, 2016).

Cited by

Sorted by citations

Related

See all

Metadata

Authors
Yu, G., Sun, K., Xu, C., Shi, X.-H., Wu, C., Xie, T., Meng, R.-Q., Meng, X.-H., Wang, K.-S., Xiao, H.-M., & Deng, H.-W.
Affiliations
  • Central South University (CN)
  • University of Oklahoma Health Sciences Center (US)
  • Florida State University (US)
  • Tulane University (US)
Corresponding author
  • Wang, Kuan-Song
  • Xiao, Hong-Mei
  • Deng, Hong-Wen
ORCID
Venue
Nature Communications
Publisher
Springer Science and Business Media LLC
Published
2021-11-02
Volume
12
Issue
1
Pages
6311-6311
ISSN
2041-1723 (ISSN-L)
DOI
10.1038/s41467-021-26643-8
PMC
PMC8563931
OpenAlex
W3208123223
Cited by
147
References
60
Citations by year
2026: 22 · 2025: 35 · 2024: 41 · 2023: 33 · 2022: 15 · 2021: 1
FWCI
7.95
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Communications (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • National Natural Science Foundation of China (#81471453, R01MH104680, R01MH107354, R01GM109068, 81972490)
  • Science and Technology Program of Hunan Province (2020YJ004)
  • National Institutes of Health
  • National Institute on Aging (U19AG055373)
  • National Institute of Mental Health (R01MH107354, R01MH104680)
  • National Institute of General Medical Sciences (R01GM109068, P20GM109036)
  • National Institute of Diabetes and Digestive and Kidney Diseases (R01DK115679)
  • National Institute of Arthritis and Musculoskeletal and Skin Diseases (R01AR059781, R01AR069055)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Health Sciences › Medicine › Oncology › Colorectal Cancer Screening and Detection
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
Keywords
colorectal cancer, semi-supervised learning, whole slide images, pathological image classification, lung cancer, digital pathology, artificial intelligence in pathology
MeSH terms
Supervised Machine Learning, Deep Learning, Artificial Intelligence, Humans, Lung Neoplasms, Lymphatic Metastasis, ROC Curve, Colorectal Neoplasms, Neural Networks, Computer

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review