Connectionists: CFP- Special issue on Machine Learning Models in Medical Imaging - Physics in Medicine & Biology

[Alba García]

Focus on Machine Learning Models in Medical ImagingGuest Editors

*Dr Giorgos Papanastasiou*, University of Essex, UK
*Dr Alba García Seco de Herrera*, University of Essex, UK
*Dr Chengjia Wang*, University of Edinburgh, UK
*Prof Heye Zhang*, Sun Yat-sen University, China
*Dr Guang Yang*, Imperial College London, UK
*Prof Ge Wang*, Rensselaer Polytechnic Institute, USA
Scope

Computational medical imaging techniques aim to enhance the diagnostic
performance of visual assessments in medical imaging, improving the early
diagnosis of various diseases and helping to obtain a deeper understanding
of physiology and pathology.

Machine Learning (ML) models revolutionised multiple tasks in medical image
computing, such as image segmentation, registration and synthesis, through
the extensive analysis of big imaging data. Although ML models outperform
classic approaches on these tasks, they remain to a large extend implicit
in terms of describing the data under investigation. This limits ML model
interpretability, which is one of the main barriers towards ML-based
pathology detection and generalised single- or multi-modal ML analysis in
medical imaging. In modern clinical practices, detailed explanations of the
model behaviours are increasingly required to support reliability towards
improving clinical decision making. Moreover, being of the most promising
topics in ML/medical imaging research, the main challenge for developing
explainable models is to offer insights and rationales whilst maintaining
high learning performance.

With this joint focus issue, between *Physics in Medicine and Biology*
<https://iopscience.iop.org/journal/0031-9155> and the multidisciplinary
open access journal *Machine Learning: Science and Technology*
<https://iopscience.iop.org/journal/2632-2153>, we aim to attract original
high-quality research and survey articles that reflect the most recent
advances on ML models in medical imaging (MRI, CT, PET, SPECT, Ultrasound
and other), by investigating novel methodologies either through
interpreting algorithm components and/or exploring algorithm-data
relationships.

Articles will be published in one of two participating journals and we are
happy to let authors choose which journal to submit to based on the
criteria below. If an article submitted to one journal is found to be
unsuitable for consideration, but suitable for the other, the assessing
Editor will offer the author an opportunity to transfer their article. This
means that duplication of peer review effort can be largely eliminated as a
service to our authors.

*Physics in Medicine and Biology* encourages the submission of papers that
focus on the medical interpretation, clinical impact, applications and
modalities and *Machine Learning: Science and Technology* encourages the
submission of papers that focus on the methodology and physics-based
interpretation of the technical aspects of machine learning models.
Topics:

We welcome researchers from academia, clinics and industry, to present
their state-of-the-art scientific developments covering all aspects of ML
model in medical imaging.

Potential topics include but are not limited to:

·         Develop and interpret ML models in single- or multi-modal (MRI,
CT, Ultrasound, PET, SPECT) imaging

·         Multi-task learning on multi-modality medical images

·         Solidify explainability in cross-domain image synthesis between
different imaging modalities or sequences (e.g. from different MRI
sequences, or MRI and CT, etc.)

·         Transfer learning for single- or multi-modality medical images

·         ML model explainability in semi-supervised, weakly-supervised and
unsupervised learning in medical imaging

·         Enhance explainability through developing ML models to detect or
predict pathology versus healthy statuses

·         To improve explainability, combine ML with biophysical modelling
and/or visual assessments from additional/complementary imaging modalities
(e.g., multiple sequences in MRI, or combining MRI with Ultrasound, CT, PET
or SPECT)

·         To improve explainability, combine ML with other types of
"reference standard" input data (e.g. clinical data, electrophysiology
signals, molecular analysis, invasive methods) that can enhance ML
interpretability in medical imaging

·         Explain strengths and weaknesses of ML models through
quantitative evaluation and interpretation of algorithm performance,
especially mechanisms of adversarial attacks and associated solutions
Deadline for submissions

Submissions will be accepted until *31 August 2021* however submissions
earlier than this date are encouraged.


More information

Submissions will be
https://iopscience.iop.org/journal/0031-9155/page/Focus%20on%20Machine%20Learning%20Models%20in%20Medical%20Imaging
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20210407/42646bcf/attachment.html>