Artificial intelligence (AI) can be trained to detect whether or not a tissue picture contains a tumour. However, until recently, it has remained a mystery as to how it makes its judgement. A team from Ruhr-Universitat Bochum’s Research Center for Protein Diagnostics (PRODI) is working on a new approach that will make an AI’s judgement clear and hence trustworthy. The researchers led by Professor Axel Mosig describe the approach in the journal Medical Image Analysis. For the study, bioinformatics scientist Axel Mosig cooperated with Professor Andrea Tannapfel, head of the Institute of Pathology, oncologist Professor Anke Reinacher-Schick from the Ruhr-Universitat’s St. Josef Hospital, and biophysicist and PRODI founding director Professor Klaus Gerwert. The group developed a neural network, i.e. an AI, that can classify whether a tissue sample contains tumour or not. To this end, they fed the AI a large number of microscopic tissue images, some of which contained tumours, while others were tumour-free. “Neural networks are initially a black box: it’s unclear which identifying features a network learns from the training data,” explains Axel Mosig. Unlike human experts, they lack the ability to explain their decisions. “However, for medical applications in particular, it’s important that the AI is capable of explanation and thus trustworthy,” adds bioinformatics scientist David Schuhmacher, who collaborated on the study. The Bochum team’s explainable AI is therefore based on the only kind of meaningful statements known to science: on falsifiable hypotheses. If a hypothesis is false, this fact must be demonstrable through an experiment. Artificial intelligence usually follows the principle of inductive reasoning: using concrete observations, i.e. the training data, the AI creates a general model on the basis of which it evaluates all further observations. The underlying problem had been described by philosopher David Hume 250 years ago and can be easily illustrated: No matter how many white swans we observe, we could never conclude from this data that all swans are white and that no black swans exist whatsoever. Science therefore makes use of so-called deductive logic. In this approach, a general hypothesis is the starting point. For example, the hypothesis that all swans are white is falsified when a black swan is spotted. Source: ANI
Related Articles
Bollywood
Rocky Aur Rani Kii Prem Kahaani: Ranveer, Alia shine bright like diamonds
Rocky Aur Rani Kii Prem Kahaani is the perfect antidote to the troll culture that has seeped into the crevices of the film industry. Karan Johar returns to the big screen as a director with […]
India
Supreme Court refuses to stay delimitation process in J&K
New Delhi (TIP)- The Supreme court on Friday refused to stay the ongoing delimitation process in the Union Territory of Jammu and Kashmir. Two Kashmir residents had challenged the government’s decision to constitute a delimitation […]
Business & Economics
Gap between US income taxes owed and paid is set to keep growing, IRS says
NEW YORK (TIP)- The amount of tax money owed but not paid to the IRS is set to keep growing, according to projections published by the federal tax collection agency on Thursday, October 12. For […]

Be the first to comment