Artificial intelligence is getting really, really good. In fact, it has become so technologically advanced that some high-skilled jobs that we once believed were "robot-proof" actually are not. The biomedical profession is ripe for overhaul. Consider a new paper in The Lancet Digital Health. Researchers developed an algorithm with 98% sensitivity and 97% specificity for detecting prostate cancer.
Editor's note: This is one of five profiles of finalists for NVIDIA's 2017 Global Impact Award, which provides $150,000 to researchers using NVIDIA technology for groundbreaking work that addresses social, humanitarian and environmental problems. For more than a century, pathologists have diagnosed cancer by studying stained tissue slides under a microscope. Sethi, a professor at the Indian Institute of Technology (IIT) Guwahati, is creating an AI pathologist to supplement human specialists. This could lead to more accurate diagnoses and more effective treatments for two of the most common types of cancer -- breast cancer among women and prostate cancer among men. "I want patients to get the treatment that's right for them," Sethi said.
Researchers have developed a machine learning model that can classify different types of lung cancer in less than a minute. The model could be used to assist doctors in determining tumour patterns and subtypes, which is an important part of prognosis and so determining the appropriate treatment. The Dartmouth-Hitchcock Medical Center researchers say the machine learning model can perform on par with three practicing pathologists. Machine learning, a subset of AI, is a type of algorithm that trains itself to predict outcomes and learn from successes and failures. In this model, the researchers used unsupervised machine learning, which means the model automatically trawls through millions of training data to identify subtle correlations and so teach itself.
It's obvious that it takes years to train doctors, especially those who handle serious and complicated medical issues – pathologists, cardiologists, dermatologists and the rest, that's why there's always a shortage of these lifesaving experts. Thanks to artificial intelligence because now, machines can be trained to help fill that shortage. In fact, already, we have AI tools that can diagnose pneumonia, fungi, depression and certain eye infections -- all with an average accuracy rate of over 92 percent. And you know what, the list is expanding further! Chinese researchers have managed to develop a new system that diagnoses prostate cancer, as accurately as pathologists do.
A new AI algorithm developed by the University of Pittsburgh has achieved the highest accuracy to date in identifying prostate cancer, with 98% sensitivity and 97% specificity. Prostate biopsy with cancer probability (blue is low, red is high). This case was originally diagnosed as benign but changed to cancer after review by AI. A study published this week in The Lancet Digital Health by University of Pittsburgh researchers demonstrates the highest accuracy to date in recognising and characterising prostate cancer using an artificial intelligence (AI) program. "Humans are good at recognising anomalies, but they have their own biases or past experience," said Rajiv Dhir, Professor of Biomedical Informatics at Pitt. "Machines are detached from the whole story. To train the AI to recognise prostate cancer, Dhir and his colleagues provided images from more than a million parts of stained tissue slides taken from patient biopsies. Expert pathologists labelled each image to teach the AI how to discriminate between healthy and abnormal tissue. The algorithm was then tested on a separate set of 1,600 slides from 100 consecutive patients, seen at the University of Pittsburgh Medical Center (UPMC) for suspected prostate cancer. During testing, the AI demonstrated 98% sensitivity and 97% specificity at detecting prostate cancer – significantly higher than previously reported for algorithms working from tissue slides. Also, this is the first algorithm to extend beyond cancer detection, reporting high performance for tumour grading, sizing and invasion of the surrounding nerves. These are all clinically important features, required as part of the pathology report. The AI flagged six slides that were missed by the expert pathologists. However, Professor Dhir explains that this does not necessarily mean that the machine is superior to humans. For example, while evaluating these cases, a pathologist could have simply seen enough evidence of malignancy elsewhere in that patient's samples to recommend treatment. For less experienced pathologists, though, the algorithm could act as a failsafe to catch cases that might otherwise be missed. "Algorithms like this are especially useful in lesions that are atypical," Dhir said. "A non-specialised person may not be able to make the correct assessment.