Current AI technologies for medical imaging and ethical dilemmas created by them
Lundegård, Zandra (2019)
Lundegård, Zandra
Åbo Akademi
2019
Julkaisu on tekijänoikeussäännösten alainen. Teosta voi lukea ja tulostaa henkilökohtaista käyttöä varten. Käyttö kaupallisiin tarkoituksiin on kielletty.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe201901091805
https://urn.fi/URN:NBN:fi-fe201901091805
Tiivistelmä
Extensive amount of data is collected and documented every day in medical practice, but only a fraction of that data is analyzed and utilized for e.g. diagnosis and treatment plans. Due to the limited capacity of the human brain and lack of time the medical doctors are unable to analyze all the data. Artificial intelligence has the capacity to analyze large datasets.
The aim of this research was to investigate how medical imaging AI could be used in clinical practice and if the technology is reliable and accurate enough to be used in healthcare systems without further development. The ethical concerns of using AI in decision making and diagnosis in medical practice were studied. The results showed that classification, segmentation, and detection built on convolutional neural networks would be a good starting point for implementing artificial intelligence in medical imaging in the future. The findings revealed that the ethical concerns are important to acknowledge and need to be further investigated. Further research within this field could focus on how to develop an ethical framework for AI in medical practice.
The aim of this research was to investigate how medical imaging AI could be used in clinical practice and if the technology is reliable and accurate enough to be used in healthcare systems without further development. The ethical concerns of using AI in decision making and diagnosis in medical practice were studied. The results showed that classification, segmentation, and detection built on convolutional neural networks would be a good starting point for implementing artificial intelligence in medical imaging in the future. The findings revealed that the ethical concerns are important to acknowledge and need to be further investigated. Further research within this field could focus on how to develop an ethical framework for AI in medical practice.