Automatic discovery of image-based signatures for ipilimumab response prediction in malignant melanoma

• Published in: Scientific reports Vol. 9; no. 1; p. 7449
• Main Authors: Harder, Nathalie, Schönmeyer, Ralf, Nekolla, Katharina, Meier, Armin, Brieu, Nicolas, Vanegas, Carolina, Madonna, Gabriele, Capone, Mariaelena, Botti, Gerardo, Ascierto, Paolo A, Schmidt, Günter
• Format: Journal Article
• Language: English
• Published: England Nature Publishing Group 15.05.2019; Nature Publishing Group UK
• Subjects: Adult; Aged; Aged, 80 and over; Biomarkers, Pharmacological; CD8 antigen; Diagnostic tests; Female; Humans; Image processing; Image Processing, Computer-Assisted - methods; Immunotherapy; Ipilimumab - therapeutic use; Learning algorithms; Lymphocytes; Lymphocytes, Tumor-Infiltrating - immunology; Machine Learning; Male; Melanoma; Melanoma - diagnostic imaging; Melanoma - drug therapy; Melanoma, Cutaneous Malignant; Metastases; Middle Aged; Monoclonal antibodies; Precision medicine; Precision Medicine - methods; Retrospective Studies; Signatures; Skin cancer; Skin Neoplasms - diagnostic imaging; Skin Neoplasms - drug therapy; Targeted cancer therapy
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-019-43525-8

In the context of precision medicine with immunotherapies there is an increasing need for companion diagnostic tests to identify potential therapy responders and avoid treatment coming along with severe adverse events for non-responders. Here, we present a retrospective case study to discover image-based signatures for developing a potential companion diagnostic test for ipilimumab (IPI) in malignant melanoma. Signature discovery is based on digital pathology and fully automatic quantitative image analysis using virtual multiplexing as well as machine learning and deep learning on whole-slide images. We systematically correlated the patient outcome data with potentially relevant local image features using a Tissue Phenomics approach with a sound cross validation procedure for reliable performance evaluation. Besides uni-variate models we also studied combinations of signatures in several multi-variate models. The most robust and best performing model was a decision tree model based on relative densities of CD8+ tumor infiltrating lymphocytes in the intra-tumoral infiltration region. Our results are well in agreement with observations described in previously published studies regarding the predictive value of the immune contexture, and thus, provide predictive potential for future development of a companion diagnostic test.