Learning objectives
A small introduction to Python programming and getting acquainted with basics of programming language
Learning basic DICOM operations with Python and how data can be extracted from DICOM files.
Getting Introduction to the versatility and simplicity of python and usefulness in data science.
To invoke interest among radiologists in python programming for its unlimited applicability for daily tasks
Background
What makes humans including radiologists different from computers is that we have the ability to think and make reasoned decisions.
In this era of emerging artificial intelligence (AI),
computers can learn and make some decisions learnt by given data without being taught.
Well known example for this is Google’s Deepmind. Part of AI is used in various forms in our daily life as Google’s voice recognition by,
Apple’s Siri,
various email spam managers etc.
‘Artificial intelligence’,
‘machine learning’ and ‘deep learning’ terms are sometimes used...
Findings and procedure details
How computers work:
In the first instance,
computers appear extremely smart.
However,
computers cannot think or reason.
They outperform in repetitive tasks like counting,
calculating,
assigning and remembering values.
However,
computers need to be instructed at each step in solving a problem.
For a computer to perform a particular task,
we have to provide necessary commands on what is to be done and the given data is to be handled.
Imagine a cook and a computer were given a task of making a sandwich and...
Conclusion
Python is easy to learn.
It is a portal of understanding to machine learning.
Extracting useful information from the enormous data of radiologic and clinical information requires automation.
Python is best suited for these repetitive tasks and so,
has become a popular language in the field of machine learning.
Understanding the underlying logical basics,
as well as first-hand experience of various operations involving Python will help in better understanding of the machine learning process.
Further,
advanced Python algorithms can be used to Radiomics research collaborating...
Personal information
Frist and corresponding author:
Dr.
Santhosh Kumar G V,
Department of Radio-diagnosis,
Tata Memorial Hospital,
Parel,
Mumbai,
India.
Consultant Radiologist,
Radneast Imaging Solutions,
Bengaluru,
India.
email: skgv1024 at gmail.com
References
Lecun Y,
Bengio Y,
Hinton G.
Deep learning.
Vol.
521,
Nature.
2015.
p.
436–44.
Obermeyer Z,
Emanuel EJ.
Predicting the Future — Big Data,
Machine Learning,
and Clinical Medicine.
N Engl J Med.
2016;375(13):1216–9.
Gillies RJ,
Kinahan PE,
Hricak H.
Radiomics: Images Are More than Pictures,
They Are Data.
Radiology .
2016;278(2):563–77.
Van Griethuysen JJM,
Fedorov A,
Parmar C,
Hosny A,
Aucoin N,
Narayan V,
et al.
Computational radiomics system to decode the radiographic phenotype.
Cancer Res.
2017;77(21):e104–7.