Combining CNN-based histologic whole slide image analysis and patient data to improve skin cancer classification. (May 2021)

• Record Type: Journal Article
• Authors: Höhn, Julia; Krieghoff-Henning, Eva; Jutzi, Tanja B.; von Kalle, Christof; Utikal, Jochen S.; Meier, Friedegund; Gellrich, Frank F.; Hobelsberger, Sarah; Hauschild, Axel; Schlager, Justin G.; French, Lars; Heinzerling, Lucie; Schlaak, Max; Ghoreschi, Kamran; Hilke, Franz J.; Poch, Gabriela; Kutzner, Heinz; Heppt, Markus V.; Haferkamp, Sebastian; Sondermann, Wiebke; Schadendorf, Dirk; Schilling, Bastian; Goebeler, Matthias; Hekler, Achim; Fröhling, Stefan; Lipka, Daniel B.; Kather, Jakob N.; Krahl, Dieter; Ferrara, Gerardo; Haggenmüller, Sarah; Brinker, Titus J.;
• Is Part Of: European journal of cancer. Volume 149(2021)
• Page Start: 94
• Page End: 101
• Publication Date: 2021-05
• Subjects: Histologic whole slide images -- Convolutional neural networks -- Data fusion -- Patient data -- Skin cancer classification; Cancer -- Periodicals; Neoplasms -- Periodicals; Cancer -- Périodiques; Cancer; Tumors; Electronic journals; Periodicals; Electronic journals; 616.994
• DOI: 10.1016/j.ejca.2021.02.032
• Languages: English
• ISSNs: 0959-8049

Abstract

Abstract: Background: Clinicians and pathologists traditionally use patient data in addition to clinical examination to support their diagnoses. Objectives: We investigated whether a combination of histologic whole slides image (WSI) analysis based on convolutional neural networks (CNNs) and commonly available patient data (age, sex and anatomical site of the lesion) in a binary melanoma/nevus classification task could increase the performance compared with CNNs alone. Methods: We used 431 WSIs from two different laboratories and analysed the performance of classifiers that used the image or patient data individually or three common fusion techniques. Furthermore, we tested a naive combination of patient data and an image classifier: for cases interpreted as 'uncertain' (CNN output score <0.7), the decision of the CNN was replaced by the decision of the patient data classifier. Results: The CNN on its own achieved the best performance (mean ± standard deviation of five individual runs) with AUROC of 92.30% ± 0.23% and balanced accuracy of 83.17% ± 0.38%. While the classification performance was not significantly improved in general by any of the tested fusions, naive strategy of replacing the image classifier with the patient data classifier on slides with low output scores improved balanced accuracy to 86.72% ± 0.36%. Conclusion: In most cases, the CNN on its own was so accurate that patient data integration did not provide any benefit. However, incorporating patient data for lesions that were classified by the CNN with low 'confidence' improved balanced accuracy. Highlights: Pathologists incorporate patient data in addition to clinical examination. They put more emphasis on patient data if they are uncertain. We investigated fusing histologic image/patient data within CNN-based classifiers. State-of-the-art fusing approaches in general did not yield a performance benefit. Mimicking humans by fusing patient data only if CNN was uncertain raised accuracy.