AI-driven eyelid tumor classification in ocular oncology using proteomic data

Linyan Wang; Xizhe Dai; Zicheng Liu; Yaxing Zhao; Yaoting Sun; Bangxun Mao; Shuohan Wu; Tiansheng Zhu; Fengbo Huang; Nuliqiman Maimaiti; Xue Cai; Stan Z Li; Jianpeng Sheng; Tiannan Guo; Juan Ye

doi:10.1038/s41698-024-00767-8

AI-driven eyelid tumor classification in ocular oncology using proteomic data

NPJ Precis Oncol. 2024 Dec 23;8(1):289. doi: 10.1038/s41698-024-00767-8.

Authors

Linyan Wang^#^{1

2

3}, Xizhe Dai^#^{4

5}, Zicheng Liu^#⁶, Yaxing Zhao^#^{7

8

9}, Yaoting Sun^{10

11

12}, Bangxun Mao¹³, Shuohan Wu¹⁴, Tiansheng Zhu^{10

11

12}, Fengbo Huang¹⁵, Nuliqiman Maimaiti^#^{1

2}, Xue Cai^{10

11

12}, Stan Z Li¹⁶, Jianpeng Sheng^{17

18

19}, Tiannan Guo^{20

21

22}, Juan Ye²³

Affiliations

¹ Eye Center, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, Zhejiang, China.
² Zhejiang Provincial Key Laboratory of Ophthalmology, Zhejiang Provincial Clinical Research Center for Eye Diseases, Zhejiang Provincial Engineering Institute on Eye Diseases, Hangzhou, Zhejiang, China.
³ Department of Ophthalmology, University of California, San Francisco, CA, USA.
⁴ Department of Ophthalmology, The Children's Hospital, School of Medicine, Zhejiang University, Hangzhou, Zhejiang, China.
⁵ National Clinical Research Center for Child Health, Hangzhou, Zhejiang, China.
⁶ AI Lab, Research Center for Industries of the Future, Westlake University, Hangzhou, Zhejiang, China.
⁷ Department of Hepatobiliary and Pancreatic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
⁸ Zhejiang Provincial Key Laboratory of Pancreatic Disease, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
⁹ Zhejiang University Cancer Center, Zhejiang University, Hangzhou, China.
¹⁰ Westlake Center for Intelligent Proteomics, Westlake Laboratory of Life Sciences and Biomedicine, Hangzhou, Zhejiang Province, China.
¹¹ Key Laboratory of Structural Biology of Zhejiang Province, School of Life Sciences, Westlake University, Hangzhou, Zhejiang Province, China.
¹² Research Center for Industries of the Future, Westlake University, Hangzhou, Zhejiang, China.
¹³ Department of Ophthalmology, The Fifth Affiliated Hospital of Wenzhou Medical University, Lishui, Zhejiang, China.
¹⁴ School of Life Sciences, Lanzhou University, Lanzhou, Gansu, China.
¹⁵ Department of Pathology, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, Zhejiang, China.
¹⁶ AI Lab, Research Center for Industries of the Future, Westlake University, Hangzhou, Zhejiang, China. [email protected].
¹⁷ Department of Hepatobiliary and Pancreatic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. [email protected].
¹⁸ Zhejiang Provincial Key Laboratory of Pancreatic Disease, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. [email protected].
¹⁹ Zhejiang University Cancer Center, Zhejiang University, Hangzhou, China. [email protected].
²⁰ Westlake Center for Intelligent Proteomics, Westlake Laboratory of Life Sciences and Biomedicine, Hangzhou, Zhejiang Province, China. [email protected].
²¹ Key Laboratory of Structural Biology of Zhejiang Province, School of Life Sciences, Westlake University, Hangzhou, Zhejiang Province, China. [email protected].
²² Research Center for Industries of the Future, Westlake University, Hangzhou, Zhejiang, China. [email protected].
²³ Eye Center, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, Zhejiang, China. [email protected].

^# Contributed equally.

Abstract

Eyelid tumors pose diagnostic challenges due to their diverse pathological types and limited biopsy materials. This study aimed to develop an artificial intelligence (AI) diagnostic system for accurate classification of eyelid tumors. Utilizing mass spectrometry-based proteomics, we analyzed proteomic data from eight tissue types and identified eighteen novel biomarkers based on 233 formalin-fixed, paraffin-embedded (FFPE) samples from 150 patients. The 18-protein model, validated by an independent cohort (99 samples from 60 patients), exhibited high accuracy (84.8%), precision (86.2%), and recall (84.8%) in multi-class classification. The model demonstrated distinct clustering of different lesion types, as visualized through UMAP plots. Receiver operator characteristic (ROC) curve analysis revealed strong predictive ability with area under the curve (AUC) values ranging from 0.80 to 1.00. This AI-based diagnostic system holds promise for improving the efficiency and precision of eyelid tumor diagnosis, addressing the limitations of traditional pathological methods.