10.6084/m9.figshare.9162686.v1 Sergey Klimov Sergey Klimov Islam Miligy Islam Miligy Arkadiusz Gertych Arkadiusz Gertych Yi Jiang Yi Jiang Michael Toss Michael Toss Padmashree Rida Padmashree Rida Ian Ellis Ian Ellis Andrew Green Andrew Green Uma Krishnamurti Uma Krishnamurti Emad Rakha Emad Rakha Ritu Aneja Ritu Aneja Additional file 10: of A whole slide image-based machine learning approach to predict ductal carcinoma in situ (DCIS) recurrence risk Springer Nature 2019 DCIS Digital image analysis Prognosis Machine learning Recurrence prediction Biomarker 2019-07-30 04:16:59 Journal contribution https://springernature.figshare.com/articles/journal_contribution/Additional_file_10_of_A_whole_slide_image-based_machine_learning_approach_to_predict_ductal_carcinoma_in_situ_DCIS_recurrence_risk/9162686 Supplementary Figure S5. Schematic of the logic used to translate risk category of patient slides to patient risk. Patients who possessed multiple resection slides were put into a high-risk subgroup if any of their slides were classified as high-risk by the recurrence classifier. (PDF 328 kb)