CoChat
Sign Up
Cited by 11AI in cancer detectionNonmelanoma Skin Cancer StudiesMedical Image Segmentation Techniques

The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.

Differentiation and risk stratification of basal cell carcinoma with deep learning on histopathologic images and measuring nuclei and tumor microenvironment features

Open access
Lan, Xuemei, Guo, Guanchen, Wang, Xiaopo, Yan, Qiao, Xue, Ruzeng, Li, Yufen, Zhu, Jiaping, Dong, Zhengbang, Wang, Fei, Li, Guomin, Wang, Xiangxue, Xu, Jun, Jiang, Yiqun·2024·Skin Research and Technology
DOI 10.1111/srt.13571PMC PMC10776893
Open this paper in CoChat — free accountOpen PDF

Abstract

BACKGROUND: Nuclear pleomorphism and tumor microenvironment (TME) play a critical role in cancer development and progression. Identifying most predictive nuclei and TME features of basal cell carcinoma (BCC) may provide insights into which characteristics pathologists can use to distinguish and stratify this entity. OBJECTIVES: To develop an automated workflow based on nuclei and TME features from basaloid cell tumor regions to differentiate BCC from trichoepithelioma (TE) and stratify BCC into high-risk (HR) and low-risk (LR) subtypes, and to identify the nuclear and TME characteristics profile of different basaloid cell tumors. METHODS: The deep learning systems were trained on 161 H&E -stained sections which contained 51 sections of HR-BCC, 50 sections of LR-BCC and 60 sections of TE from one institution (D1), and externally and independently validated on D2 (46 sections) and D3 (76 sections), from 2015 to 2022. 60%, 20% and 20% of D1 data were randomly splitted for training, validation and testing, respectively. The framework comprised four stages: tumor regions identification by multi-head self-attention (MSA) U-Net, nuclei segmentation by HoVer-Net, quantitative feature by handcrafted extraction, and differentiation and risk stratification classifier construction. Pixel accuracy, precision, recall, dice score, intersection over union (IoU) and area under the curve (AUC) were used to evaluate the performance of tumor segmentation model and classifiers. RESULTS: MSA-U-Net model detected tumor regions with 0.910 precision, 0.869 recall, 0.889 dice score and 0.800 IoU. The differentiation classifier achieved 0.977 ± 0.0159, 0.955 ± 0.0181, 0.885 ± 0.0237 AUC in D1, D2 and D3, respectively. The most discriminative features between BCC and TE contained Homogeneity, Elongation, T-T_meanEdgeLength, T-T_Nsubgraph, S-T_HarmonicCentrality, S-S_Degrees. The risk stratification model can well predict HR-BCC and LR-BCC with 0.920 ± 0.0579, 0.839 ± 0.0176, 0.825 ± 0.0153 AUC in D1, D2 and D3, respectively. The most discriminative features between HR-BCC and LR-BCC comprised IntensityMin, Solidity, T-T_minEdgeLength, T-T_Coreness, T-T_Degrees, T-T_Betweenness, S-T_Degrees. CONCLUSIONS: This framework hold potential for future use as a second opinion helping inform diagnosis of BCC, and identify nuclei and TME features related with malignancy and tumor risk stratification.

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 · 10.1111/srt.13571

Cites

27 of 27 references verified0 citation errors · 0 not checkable

Statistics

Figures

FIGURE 1 Experimental workflow. (A) Four classes MSA U‐Net based segmentation model (B) Tumor regions identification, nuclear features extraction and selection, and classifier construction. (C) The differentiation classifier generated patch‐level prediction, then compared the probability of BCC and TE, and finally assigned the type with the larger probability. (D) If differentiation classifier predicted the case as BCC, it would transfer to risk stratification classifier for further analysis. BCC, basal cell carcinoma; MSA, multi‐head self‐attention; TE, trichoepithelioma.
FIGURE 1 Experimental workflow. (A) Four classes MSA U‐Net based segmentation model (B) Tumor regions identification, nuclear features extraction and selection, and classifier construction. (C) The differentiation classifier generated patch‐level prediction, then compared the probability of BCC and TE, and finally assigned the type with the larger probability. (D) If differentiation classifier predicted the case as BCC, it would transfer to risk stratification classifier for further analysis. BCC, basal cell carcinoma; MSA, multi‐head self‐attention; TE, trichoepithelioma.CC BY-NC-ND · PubMed Central
FIGURE 2 Performance of the differentiation and risk stratification classifier on three independent datasets. (A) The differentiation classifier achieved 0.977 ± 0.0159, 0.955 ± 0.0181, 0.885 ± 0.0237 AUC on D1 (blue), D2 (green), and D3 (red), respectively. The dashed line represents the random prediction 0.5. (B) The risk stratification classifier obtained 0.920 ± 0.0.0579, 0.839 ± 0.0579, 0.825 ± 0.0153 on D1(blue), D2 (green), and D3 (red), respectively.
FIGURE 2 Performance of the differentiation and risk stratification classifier on three independent datasets. (A) The differentiation classifier achieved 0.977 ± 0.0159, 0.955 ± 0.0181, 0.885 ± 0.0237 AUC on D1 (blue), D2 (green), and D3 (red), respectively. The dashed line represents the random prediction 0.5. (B) The risk stratification classifier obtained 0.920 ± 0.0.0579, 0.839 ± 0.0579, 0.825 ± 0.0153 on D1(blue), D2 (green), and D3 (red), respectively.CC BY-NC-ND · PubMed Central
FIGURE 3 Discriminative features of the differentiation classifier. (A) Top 1 to top 10 nuclear features. (B) Top 11 to top 20 features. Violin plots are used to visualize and compare features expression between BCC and TE. These 20 dimensions nuclear features were statistically different between BCC (orange) and TE (green) (p < 0.05). BCC, basal cell carcinoma; TE, trichoepithelioma.
FIGURE 3 Discriminative features of the differentiation classifier. (A) Top 1 to top 10 nuclear features. (B) Top 11 to top 20 features. Violin plots are used to visualize and compare features expression between BCC and TE. These 20 dimensions nuclear features were statistically different between BCC (orange) and TE (green) (p < 0.05). BCC, basal cell carcinoma; TE, trichoepithelioma.CC BY-NC-ND · PubMed Central
FIGURE 4 Discriminative features of the risk grading classifier. (A) Top 1 to top 10 nuclear features. (B) Top 11 to top 20 features. Violin plots are used to visualize and compare features expression between HR‐BCC and LR‐BCC. These 20 dimensions nuclear features were statistically different between HR‐BCC (green) and LR‐BCC (orange) (p < 0.05). BCC, basal cell carcinoma; HR, high‐risk; LR, low‐risk.
FIGURE 4 Discriminative features of the risk grading classifier. (A) Top 1 to top 10 nuclear features. (B) Top 11 to top 20 features. Violin plots are used to visualize and compare features expression between HR‐BCC and LR‐BCC. These 20 dimensions nuclear features were statistically different between HR‐BCC (green) and LR‐BCC (orange) (p < 0.05). BCC, basal cell carcinoma; HR, high‐risk; LR, low‐risk.CC BY-NC-ND · 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

Cited by

Sorted by citations

See all 11

Related

See all

Metadata

Authors
Lan, X., Guo, G., Wang, X., Yan, Q., Xue, R., Li, Y., Zhu, J., Dong, Z., Wang, F., Li, G., Wang, X., Xu, J., & Jiang, Y.
Affiliations
  • Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
  • Nanjing University of Information Science and Technology (CN)
  • Zhongda Hospital Southeast University (CN)
  • Southern Medical University (CN)
Corresponding author
  • Wang, Xiangxue
  • Xu, Jun
  • Jiang, Yiqun
ORCID
Venue
Skin Research and Technology
Publisher
Wiley
Published
2024-01
Volume
30
Issue
1
Pages
e13571-e13571
ISSN
  • 0909-752X (ISSN-L)
  • 1600-0846
DOI
10.1111/srt.13571
PMC
PMC10776893
OpenAlex
W4390699781
Cited by
11
References
27
Citations by year
2026: 3 · 2025: 4 · 2024: 4
FWCI
1.62
Type
journal article
Language
en
Open access
Licence
Locations
  • Skin Research and Technology (publishedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
Funders
National Natural Science Foundation of China (62171230, 92159301, 91959207, 62301265)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Health Sciences › Medicine › Dermatology › Nonmelanoma Skin Cancer Studies
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
Keywords
basal cell carcinoma, trichoepithelioma, tumor differentiation, risk stratification, tumor microenvironment, deep learning, nuclei segmentation, H&E histopathology, automated histopathology, high-risk basal cell carcinoma, tumor segmentation
MeSH terms
Deep Learning, Carcinoma, Basal Cell, Basal Cell Carcinoma, Humans, Skin Neoplasms, Risk Assessment, Tumor Microenvironment

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