Research on deep learning-based pathological image classification of pilonidal sinus_Journal of Biomedical Engineering

Authors：

WANG Qi ^1,2 , BEN Siqi ¹ , LI Xiuyan ^1,2 , MA Qun ¹ , QI Shunli ³ ,  LIU Shifei ³ , LIU Aidong ⁴

1. School of Electronic and Information Engineering, Tiangong University, Tianjin 300387, P. R. China;
2. Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems, Tiangong University, Tianjin 300387, P. R. China;
3. Department of Pathology, Beijing Anorectal Hospital(Beijing Erlong Road Hospital), Beijing 100120, P. R. China;
4. Department of Pathology, Tianjin Hospital, Tianjin 300211, P. R. China;

Corresponding?author：

LIU Shifei, Email: 18201137662@163.com

Keywords：

Pilonidal sinus disease; Histopathological images; Clinical characteristics; Horizontal and vertical distance network; Classifier mode

DOI：

10.7507/1001-5515.202512031

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Pilonidal sinus disease (PSD) is a suppurative inflammatory condition characterized by a sinus tract in the sacrococcygeal gluteal cleft and surrounding skin. Surgical resection is an important treatment for PSD; however, postoperative recurrence occurs in some patients, severely affecting their quality of life. Due to the lack of objective clinical indicators for predicting recurrence, developing an artificial intelligence-based prediction model is an effective approach. In this study, postoperative hematoxylin and eosin (H&E) stained pathological sections from PSD patients were used. The horizontal and vertical distance network (HoVer-Net) deep learning model for automated nuclei segmentation and classification was employed to extract nuclear features from lesion regions. These features were then integrated with multidimensional clinical characteristics to select key features. And then a machine learning classifier was incorporated to construct a recursive feature elimination-balanced random forest (RFE-BalancedRF) ensemble model to predict PSD recurrence. Experimental results demonstrate that the proposed PSD recurrence prediction model achieves an area under the curve of receiver operating characteristic (ROC_AUC) of 0.751 ± 0.048 and an accuracy (Acc) of 0.715 ± 0.066. Furthermore, a correlation exists between multimodal features and the risk of PSD recurrence, confirming the effectiveness of the proposed model in predicting PSD recurrence. This study innovatively integrates radiomics features with clinical characteristics from the dual perspectives of pathological image analysis and multimodal feature fusion to construct a PSD recurrence risk prediction model, potentially providing a new pathway with considerable clinical translation potential for artificial intelligence assisted medicine.

Citation： WANG Qi, BEN Siqi, LI Xiuyan, MA Qun, QI Shunli, LIU Shifei, LIU Aidong. Research on deep learning-based pathological image classification of pilonidal sinus. Journal of Biomedical Engineering, 2026, 43(3): 562-570. doi: 10.7507/1001-5515.202512031 Copy

1.	Luedi M M, Schober P, Stauffer V K, et al. Gender-specific prevalence of pilonidal sinus disease over time: a systematic review and meta-analysis. ANZ J Surg, 2021, 91(7-8): 1582-1587.
2.	Delshad H R, Gattoc L, Haddad R B, et al. The psychological and social burden of pilonidal sinus disease: a mixed-methods study. Dis Colon Rectum, 2023, 66(2): e85-e92.
3.	Doll D, Maak M, M?rsdorf P, et al. Study size impact on accuracy of the worldwide incidence of pilonidal sinus. Alban J Trauma Emerg Surg, 2024, 8(2): 1432-1438.
4.	Darnis B, Tedeschi L, Blanchet M C, et al. Management of pilonidal sinus and recurrences in 2025. J Visc Surg, 2025, 162(2): 117-127.
5.	Oetzmann von Sochaczewski C, Heitmann H, Izbicka K, et al. Altersabh?ngige Ver?nderungen der axialen Haarfestigkeit in der Pathogenese des Pilonidalsinus. Coloproctology, 2025, 47(1): 29-33.
6.	De Kort J, Pronk A A, Van Dijk M R, et al. Etiologic factors in developing sacrococcygeal pilonidal sinus disease in males; a case-control study. Langenbecks Arch Surg, 2025, 410(1): 315.
7.	Tam A, Steen C J, Chua J, et al. Pilonidal sinus: an overview of historical and current management modalities. Updates Surg, 2024, 76(3): 803-810.
8.	Ruch A, Ziegler J. The effectiveness of histopathological analysis in diagnosing pilonidal sinus disease. J Clin Pathol, 2016, 69(2): 135-140.
9.	Iesalnieks I, Ommer A, Petersen S, et al. German national guideline on the management of pilonidal disease. Langenbecks Arch Surg, 2016, 401(5): 599-609.
10.	Segre D, Pozzo M, Perotti P, et al. Histopathological findings in chronic pilonidal sinus disease guide for the clinician. Int Wound J, 2022, 19(5): 1144-1150.
11.	Arslan ?. Pilonidal disease: gaps in the guidelines and future perspectives. Turk J Surg, 2025, 41(3): 216.
12.	Kather J N, Pearson A T, Halama N, et al. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat Med, 2019, 25(7): 1054-1056.
13.	Graham S, Vu Q D, Raza S E A, et al. Hover-net: simultaneous segmentation and classification of nuclei in multi-tissue histology images. Med Image Anal, 2019, 58: 101563.
14.	Panahi M, Hosseini M S. Impact of harmonization on MRI radiomics feature variability across preprocessing methods for Parkinson's disease motor subtype classification. J Imaging Inform Med, 2025, 38(4): 2500-2513.
15.	劉若男, 辛義忠, 李巖. 基于皮爾遜相關系數的動態簽名驗證方法. 儀器儀表學報, 2022, 43(7): 279-287.
16.	Gong H, Li Y, Zhang J, et al. A new filter feature selection algorithm for classification task by ensembling Pearson correlation coefficient and mutual information. Eng Appl Artif Intell, 2024, 131: 107865.
17.	He R L, Yang X Y, Sun H Z, et al. The latest development and prospects of histopathological image analysis methods based on graph features. Front Data Comput, 2024, 6(2): 101-116.
18.	Rangaiah P K B, Kumar B P P, Augustine R. Histopathology-driven prostate cancer identification: a VBIR approach with CLAHE and GLCM insights. Comput Biol Med, 2024, 182: 109213.
19.	Zubair M, Owais M, Mahmood T, et al. Enhanced gastric cancer classification and quantification interpretable framework using digital histopathology images. Sci Rep, 2024, 14(1): 22533.
20.	李森, 陳浩, 王建華, 等. 基于形態學和傅里葉描述子的肝細胞核多級特征提取與分類研究. 中國生物醫學工程學報, 2022, 41(4): 385-394.
21.	張旭, 王莉, 李志剛. 基于遞歸特征消除的支持向量機在基因選擇中的應用. 計算機應用研究, 2020, 37(8): 2338-2341.
22.	Remeseiro B, Bolon-Canedo V. A review of feature selection methods in medical applications. Comput Biol Med, 2019, 112: 103375.
23.	Koziarski M. Radial-based undersampling for imbalanced data classification. Pattern Recognit, 2020, 102: 107262.
24.	Lin K, Hu Y, Kong G. Predicting in-hospital mortality of patients with acute kidney injury in the ICU using random forest model. Int J Med Inform, 2019, 125: 55-61.
25.	Qawqzeha Y. Addressing class imbalance in iot: a comparative analysis of resampling techniques. Am J Smart Technol Solut, 2025, 4(1): 16-24.
26.	王荃, 沈勤, 張澤林, 等. 基于深度學習和組織形態分析的肺癌基因突變預測. 生物醫學工程學雜志, 2020, 37(1): 10-18.
27.	Salma N, Al-Rammahi A H M, Ali M K M. A novel feature selection method for ultra high dimensional survival data. Malays J Fundam Appl Sci, 2024, 20(5): 1149-1171.
28.	Huang S L, Xu X, Zheng L. An information-theoretic approach to unsupervised feature selection for high-dimensional data. IEEE J Sel Areas Inf Theory, 2020, 1(1): 157-166.
29.	Alkahya M A, Alreahan H O, Algamal Z Y. Classification of breast cancer histopathological images using adaptive penalized logistic regression with Wilcoxon rank sum test. Electron J Appl Stat Anal, 2023, 16(3): 507-518.
30.	Chen T, Guestrin C. XGBoost: a scalable tree boosting system//The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco: ACM, 2016: 785-794.
31.	Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. Adv Neural Inf Process Syst, 2017, 30: 5998-6008.
32.	Zhao S, Zhang B, Yang J, et al. Linear discriminant analysis. Nat Rev Methods Primers, 2024, 4(1): 70.
33.	Araveeporn A. Comparing the linear and quadratic discriminant analysis of diabetes disease classification based on data multicollinearity. Int J Math Math Sci, 2022, 2022: 7829795.
34.	Valkenborg D, Rousseau A J, Geubbelmans M, et al. Support vector machines. Am J Orthod Dentofacial Orthop, 2023, 164(5): 754-757.
35.	Abd-elaziem A H, Soliman T H M. A multi-layer perceptron (MLP) neural networks for stellar classification: a review of methods and results. Int J Adv Appl Comput Intell, 2023, 3(10): 54216.
36.	Ke G, Meng Q, Finley T, et al. LightGBM: a highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst, 2017, 30: 3146-3154.
37.	Deepak K V, Bharanidharan R. Osteosarcoma detection in histopathology images using ensemble machine learning techniques. Biomed Signal Process Control, 2023, 86: 105281.

1. Luedi M M, Schober P, Stauffer V K, et al. Gender-specific prevalence of pilonidal sinus disease over time: a systematic review and meta-analysis. ANZ J Surg, 2021, 91(7-8): 1582-1587.
2. Delshad H R, Gattoc L, Haddad R B, et al. The psychological and social burden of pilonidal sinus disease: a mixed-methods study. Dis Colon Rectum, 2023, 66(2): e85-e92.
3. Doll D, Maak M, M?rsdorf P, et al. Study size impact on accuracy of the worldwide incidence of pilonidal sinus. Alban J Trauma Emerg Surg, 2024, 8(2): 1432-1438.
4. Darnis B, Tedeschi L, Blanchet M C, et al. Management of pilonidal sinus and recurrences in 2025. J Visc Surg, 2025, 162(2): 117-127.
5. Oetzmann von Sochaczewski C, Heitmann H, Izbicka K, et al. Altersabh?ngige Ver?nderungen der axialen Haarfestigkeit in der Pathogenese des Pilonidalsinus. Coloproctology, 2025, 47(1): 29-33.
6. De Kort J, Pronk A A, Van Dijk M R, et al. Etiologic factors in developing sacrococcygeal pilonidal sinus disease in males; a case-control study. Langenbecks Arch Surg, 2025, 410(1): 315.
7. Tam A, Steen C J, Chua J, et al. Pilonidal sinus: an overview of historical and current management modalities. Updates Surg, 2024, 76(3): 803-810.
8. Ruch A, Ziegler J. The effectiveness of histopathological analysis in diagnosing pilonidal sinus disease. J Clin Pathol, 2016, 69(2): 135-140.
9. Iesalnieks I, Ommer A, Petersen S, et al. German national guideline on the management of pilonidal disease. Langenbecks Arch Surg, 2016, 401(5): 599-609.
10. Segre D, Pozzo M, Perotti P, et al. Histopathological findings in chronic pilonidal sinus disease guide for the clinician. Int Wound J, 2022, 19(5): 1144-1150.
11. Arslan ?. Pilonidal disease: gaps in the guidelines and future perspectives. Turk J Surg, 2025, 41(3): 216.
12. Kather J N, Pearson A T, Halama N, et al. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat Med, 2019, 25(7): 1054-1056.
13. Graham S, Vu Q D, Raza S E A, et al. Hover-net: simultaneous segmentation and classification of nuclei in multi-tissue histology images. Med Image Anal, 2019, 58: 101563.
14. Panahi M, Hosseini M S. Impact of harmonization on MRI radiomics feature variability across preprocessing methods for Parkinson's disease motor subtype classification. J Imaging Inform Med, 2025, 38(4): 2500-2513.
15. 劉若男, 辛義忠, 李巖. 基于皮爾遜相關系數的動態簽名驗證方法. 儀器儀表學報, 2022, 43(7): 279-287.
16. Gong H, Li Y, Zhang J, et al. A new filter feature selection algorithm for classification task by ensembling Pearson correlation coefficient and mutual information. Eng Appl Artif Intell, 2024, 131: 107865.
17. He R L, Yang X Y, Sun H Z, et al. The latest development and prospects of histopathological image analysis methods based on graph features. Front Data Comput, 2024, 6(2): 101-116.
18. Rangaiah P K B, Kumar B P P, Augustine R. Histopathology-driven prostate cancer identification: a VBIR approach with CLAHE and GLCM insights. Comput Biol Med, 2024, 182: 109213.
19. Zubair M, Owais M, Mahmood T, et al. Enhanced gastric cancer classification and quantification interpretable framework using digital histopathology images. Sci Rep, 2024, 14(1): 22533.
20. 李森, 陳浩, 王建華, 等. 基于形態學和傅里葉描述子的肝細胞核多級特征提取與分類研究. 中國生物醫學工程學報, 2022, 41(4): 385-394.
21. 張旭, 王莉, 李志剛. 基于遞歸特征消除的支持向量機在基因選擇中的應用. 計算機應用研究, 2020, 37(8): 2338-2341.
22. Remeseiro B, Bolon-Canedo V. A review of feature selection methods in medical applications. Comput Biol Med, 2019, 112: 103375.
23. Koziarski M. Radial-based undersampling for imbalanced data classification. Pattern Recognit, 2020, 102: 107262.
24. Lin K, Hu Y, Kong G. Predicting in-hospital mortality of patients with acute kidney injury in the ICU using random forest model. Int J Med Inform, 2019, 125: 55-61.
25. Qawqzeha Y. Addressing class imbalance in iot: a comparative analysis of resampling techniques. Am J Smart Technol Solut, 2025, 4(1): 16-24.
26. 王荃, 沈勤, 張澤林, 等. 基于深度學習和組織形態分析的肺癌基因突變預測. 生物醫學工程學雜志, 2020, 37(1): 10-18.
27. Salma N, Al-Rammahi A H M, Ali M K M. A novel feature selection method for ultra high dimensional survival data. Malays J Fundam Appl Sci, 2024, 20(5): 1149-1171.
28. Huang S L, Xu X, Zheng L. An information-theoretic approach to unsupervised feature selection for high-dimensional data. IEEE J Sel Areas Inf Theory, 2020, 1(1): 157-166.
29. Alkahya M A, Alreahan H O, Algamal Z Y. Classification of breast cancer histopathological images using adaptive penalized logistic regression with Wilcoxon rank sum test. Electron J Appl Stat Anal, 2023, 16(3): 507-518.
30. Chen T, Guestrin C. XGBoost: a scalable tree boosting system//The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco: ACM, 2016: 785-794.
31. Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. Adv Neural Inf Process Syst, 2017, 30: 5998-6008.
32. Zhao S, Zhang B, Yang J, et al. Linear discriminant analysis. Nat Rev Methods Primers, 2024, 4(1): 70.
33. Araveeporn A. Comparing the linear and quadratic discriminant analysis of diabetes disease classification based on data multicollinearity. Int J Math Math Sci, 2022, 2022: 7829795.
34. Valkenborg D, Rousseau A J, Geubbelmans M, et al. Support vector machines. Am J Orthod Dentofacial Orthop, 2023, 164(5): 754-757.
35. Abd-elaziem A H, Soliman T H M. A multi-layer perceptron (MLP) neural networks for stellar classification: a review of methods and results. Int J Adv Appl Comput Intell, 2023, 3(10): 54216.
36. Ke G, Meng Q, Finley T, et al. LightGBM: a highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst, 2017, 30: 3146-3154.
37. Deepak K V, Bharanidharan R. Osteosarcoma detection in histopathology images using ensemble machine learning techniques. Biomed Signal Process Control, 2023, 86: 105281.

Journal of Biomedical Engineering

Research on deep learning-based pathological image classification of pilonidal sinus

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content