Oh totally, I've wondered the exact same thing. I started messing around with that on leerly, and there are a couple articles with a feature called Storybook, where images appear as the user is speaking, to help build the association between the foreign word/sound with an image, rather than the associated word in your target language.

I have no idea if it's effective, I just think it'd be cool to see how it helps with learning grammar. I def want to experiment more with it, but it takes a fair amount of time to add images to all the articles.