Artificial intelligence-based classification of Spitz tumors

Journal of Pathology Informatics, vol. 21, pp. 100650

Abstract

Spitz tumors are diagnostically challenging due to overlap in atypical histological features with conventional melanomas. We investigated to what extent artificial intelligence (AI) models, using histological and/or clinical features, can: (1) distinguish Spitz tumors from conventional melanomas; (2) predict the underlying genetic aberration of Spitz tumors; and (3) predict the diagnostic category of Spitz tumors. The AI models were developed and validated using a retrospective cohort from the University Medical Center Utrecht, the Netherlands. The dataset consisted of 393 Spitz tumors and 379 conventional melanomas. Predictive performance was measured using the area under the receiver operating characteristic curve (AUROC) and the accuracy. The performance of the AI models was compared with that of four experienced pathologists in a reader study. Moreover, a simulation experiment was conducted to investigate the impact of implementing AI-based recommendations for ancillary diagnostic testing on the workflow of the pathology department. The best AI model based on UNI features reached an AUROC of 0.95 (95% CI, 0.92-0.98) and an accuracy of 0.86 (95% CI, 0.81-0.91) in differentiating Spitz tumors from conventional melanomas. The genetic aberration was predicted with an accuracy of 0.55 (95% CI, 0.46-0.64) compared to 0.25 for randomly guessing. The diagnostic category was predicted with an accuracy of 0.51 (95% CI, 0.40-0.60), where random chance-level accuracy equaled 0.33. On all three tasks, the AI models performed better than the four pathologists, although differences were not statistically significant for most individual comparisons. Based on the simulation experiment, implementing AI-based recommendations for ancillary diagnostic testing could reduce material costs, turnaround times, and examinations. In conclusion, the AI models achieved a strong predictive performance in distinguishing between Spitz tumors and conventional melanomas. On the more challenging tasks of predicting the genetic aberration and the diagnostic category of Spitz tumors, the AI models performed better than random chance.

Authors 13

1. Ruben T. Lucassen

   University Medical Center Utrecht · Eindhoven University of Technology

   Affiliation as printed

   Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands

   Department of Pathology, the University Medical Center Utrecht, the Netherlands

2. Marjanna Romers

   University Medical Center Utrecht

   Affiliation as printed

   Department of Pathology, the University Medical Center Utrecht, the Netherlands

3. Chiel F Ebbelaar Aachen Department of Dermatology, Leiden University Medical Center

   Leiden University Medical Center · University Medical Center Utrecht

   Affiliation as printed

   Department of Dermatology, Leiden University Medical Center, Leiden, the Netherlands

   Department of Pathology, the University Medical Center Utrecht, the Netherlands

4. Aia N. Najem

   Radboud University Medical Center · University Medical Center Utrecht

   Affiliation as printed

   Department of Pathology, Radboud University Medical Center, Nijmegen, the Netherlands

   Department of Pathology, the University Medical Center Utrecht, the Netherlands

5. Donal P. Hayes

   Meander Medisch Centrum

   Affiliation as printed

   Department of Pathology, Meander Medical Center, Amersfoort, the Netherlands

6. Antien L. Mooyaart

   Erasmus MC

   Affiliation as printed

   Department of Pathology, Erasmus Medical Center, Rotterdam, the Netherlands

7. Sara Roshani

   Amsterdam UMC Location University of Amsterdam · Amsterdam University Medical Centers

   Affiliation as printed

   Department of Pathology, Amsterdam University Medical Center, Amsterdam, the Netherlands

8. Liliane C.D. Wynaendts

   St. Antonius Ziekenhuis

   Affiliation as printed

   Department of Pathology, St. Antonius Hospital, Nieuwegein, the Netherlands

9. Nikolas Stathonikos

   University Medical Center Utrecht

   Affiliation as printed

   Department of Pathology, the University Medical Center Utrecht, the Netherlands

10. Gerben Eise Breimer

    University Medical Center Utrecht

    Affiliation as printed

    Department of Pathology, the University Medical Center Utrecht, the Netherlands

11. Anne M.L. Jansen

    University Medical Center Utrecht

    Affiliation as printed

    Department of Pathology, the University Medical Center Utrecht, the Netherlands

12. Mitko Veta

    Eindhoven University of Technology

    Affiliation as printed

    Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands

13. Willeke A.M. Blokx

    University Medical Center Utrecht

    Affiliation as printed

    Department of Pathology, the University Medical Center Utrecht, the Netherlands