In recent years we have seen experimental evidence suggesting that neural networks are able to detect skin cancer via dermatoscopic and clinical images.1-4 Most studies used preprocessed and cropped images, in which parts of the background have been removed to fit to a predefined size. Custom preparation of images, however, is not feasible for laypersons or nonspecialists. In this issue of JAMA Dermatology, Han et al5 are opening the stage of automated skin cancer recognition without the need for this type of preprocessing. They applied a technique called object detection on a large data set including a variety of skin diseases.
Identify all potential conflicts of interest that might be relevant to your comment.
Conflicts of interest comprise financial interests, activities, and relationships within the past 3 years including but not limited to employment, affiliation, grants or funding, consultancies, honoraria or payment, speaker's bureaus, stock ownership or options, expert testimony, royalties, donation of medical equipment, or patents planned, pending, or issued.
Err on the side of full disclosure.
If you have no conflicts of interest, check "No potential conflicts of interest" in the box below. The information will be posted with your response.
Not all submitted comments are published. Please see our commenting policy for details.
Tschandl P. Problems and Potentials of Automated Object Detection for Skin Cancer Recognition. JAMA Dermatol. 2020;156(1):23–24. doi:10.1001/jamadermatol.2019.3360
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: