News: Man against machine. Can AI outperform dermatologists when diagnosing skin cancer?

Researchers have shown for the first time that artificial intelligence is better than highly-trained humans when detecting skin cancer. A study conducted by an international team of researchers pitted experienced dermatologists against a machine learning system, known as a deep learning convolutional neural network, or CNN, to find out who is better at detecting malignant melanomas.

In machine learning, a convolutional neural network (CNN, or ConvNet) is a class of deep, feed-forward artificial neural networks, most commonly applied to analyzing visual imagery.

CNNs use a variation of multilayer perceptrons designed to require minimal preprocessing. They are also known as shift invariant or space invariant artificial neural networks (SIANN), based on their shared-weights architecture and translation invariance characteristics.

Convolutional networks were inspired by biological processes in that the connectivity pattern between neurons resembles the organization of the animal visual cortex. Individual cortical neurons respond to stimuli only in a restricted region of the visual field known as the receptive field. The receptive fields of different neurons partially overlap such that they cover the entire visual field.

According to American Cancer Society key statistics for melanoma skin cancer are as follows:

Cancer of the skin is by far the most common of all cancers. Melanoma accounts for only about 1% of skin cancers but causes a large majority of skin cancer deaths.

The American Cancer Society’s estimates for melanoma in the United States for 2018 are:

  • About 91,270 new melanomas will be diagnosed (about 55,150 in men and 36,120 in women).
  • About 9,320 people are expected to die of melanoma (about 5,990 men and 3,330 women).

The rates of melanoma have been rising for the last 30 years.

Melanoma is more than 20 times more common in whites than in African Americans. Overall, the lifetime risk of getting melanoma is about 2.6% (1 in 38) for whites, 0.1% (1 in 1,000) for blacks, and 0.58% (1 in 172) for Hispanics.

The risk of melanoma increases as people age. The average age of people when it is diagnosed is 63. But melanoma is not uncommon even among those younger than 30. In fact, it’s one of the most common cancers in young adults (especially young women).

One of the authors of the neural network ( Professor Holger Haenssle, senior managing physician at the Department of Dermatology, University of Heidelberg, Germany) explains how a CNN works in simple words:

The CNN works like the brain of a child. To train it, we showed the CNN more than 100,000 images of malignant and benign skin cancers and moles and indicated the diagnosis for each image. Only dermoscopic images were used, that is lesions that were imaged at a 10-fold magnification. With each training image, the CNN improved its ability to differentiate between benign and malignant lesions.

After finishing the training, we created two test sets of images from the Heidelberg library that had never been used for training and therefore were unknown to the CNN. One set of 300 images was built to solely test the performance of the CNN. Before doing so, 100 of the most difficult lesions were selected to test real dermatologists in comparison to the results of the CNN.

Fifty-eight dermatologists from 17 countries around the world participated in the study. More than fifty percent of the doctors were considered as experts in this field with more than five years’ experience. Nineteen percent said they had between two to five years’ experience, and 29% had less than two years’ experience.

The doctors were shown 100 images of skin lesions and asked to make a diagnosis, using their judgment about whether it was a malignant melanoma or benign mole. They were also asked to make a decision about how to manage the condition, such as surgery, short-term follow-up, or no action needed. Four weeks later, the researchers gave the dermatologists clinical information about the patient, including age, sex, and the position of the lesion, and close-up images of the same cases. Once again, they were asked to make diagnoses and management decisions.

The results were as follows: dermatologists correctly diagnosed an average of 87% of melanomas and 73% of non-maligant lesions. The results for CNN were 95% for melanomas detection.

Things were little better when doctors received information about the patients. In this case they could diagnose 89% of malignant melanomas and 76 percent of benign moles.

But still they were outperformed by an AI, which worked only with images.

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.

These findings show us that deep learning convolutional neural networks are capable of out-performing dermatologists, including extensively trained experts, in the task of detecting melanomas. Irrespective of any physicians’ experience, they may benefit from assistance by a CNN’s image classification.

We believe that AI promises a more standardized level of diagnostic accuracy, such that all people, regardless of where they live or which doctor they see, will be able to access reliable diagnostic assessment.

Article is written with the information provided by: Science Daily, CBS news, The Newyorker and Annals of Oncology

Join Skychain on social media: Twitter, Facebook, Telegram

Egor Chertov, Skychain team

Blockchain infrastructure aimed to host, train and use artificial intelligence (AI) in healthcare. Our website: