Connection between prob output LogisticReg/SVM and ROC

I have the following ROC generated using LPOCV and Logistic regression or SVM (l2 norm). Now, let's say I have a test set containing 10 patients and I get that the probabilities of those patients to be sick range from 0-100% (of course). What I want is to define a point in the ROC curve (i.e. have a sensitivity specificity pair) which will give me a threshold for the probability used to classify a patient as 0 or 1 (or the other way around, choose a probability, say 60%, and use that probability to calculate the sensitivity and specificity given by my ROC).

Thanks