I think this would be a correct way to do so, but I'm not 100% sure. It seems correct from the ROC diagrams:
[x,t] = iris_dataset;
net = patternnet(10);
net = train(net,x,t);
y = net(x);
[tpr,fpr,th] = roc(t,y);
plotroc(t, y)
auc_1 = 1-trapz(tpr{1}, fpr{1});
auc_2 = 1-trapz(tpr{2}, fpr{2});
auc_3 = 1-trapz(tpr{3}, fpr{3});
