The test results are interesting. When pitted against 58 international dermatologists, the neural network was better at detecting melanomas and reported fewer false positives. The dermatologists that participated in the trial were able to accurately recognize 88.9 percent of malignant melanomas, while the neural network was able to spot 95 percent of melanomas:
The dermatologists were asked to first make a diagnosis of malignant melanoma or benign mole just from the dermoscopic images (level I) and make a decision about how to manage the condition (surgery, short-term follow-up, or no action needed). Then, four weeks later they were given clinical information about the patient (including age, sex and position of the lesion) and close-up images of the same 100 cases (level II) and asked for diagnoses and management decisions again.Full details can be read at Eurekalert.
In level I, the dermatologists accurately detected an average of 86.6% of melanomas, and correctly identified an average of 71.3% of lesions that were not malignant. However, when the CNN was tuned to the same level as the physicians to correctly identify benign moles (71.3%), the CNN detected 95% of melanomas. At level II, the dermatologists improved their performance, accurately diagnosing 88.9% of malignant melanomas and 75.7% that were not cancer.
"The CNN missed fewer melanomas, meaning it had a higher sensitivity than the dermatologists, and it misdiagnosed fewer benign moles as malignant melanoma, which means it had a higher specificity; this would result in less unnecessary surgery," said Professor Haenssle.
"When dermatologists received more clinical information and images at level II, their diagnostic performance improved. However, the CNN, which was still working solely from the dermoscopic images with no additional clinical information, continued to out-perform the physicians' diagnostic abilities."