Interests

Image processing and analysis, machine learning, computer aided medicine, software

• Google scholar profile

Journal articles

• Andrey Fedorov, Matthew Hancock, David Clunie, Mathias Brochhausen, Jonathan Bona, Justin Kirby, John Freymann, Steve Pieper, Hugo J.W.L. Aerts, Ron Kikinis, Fred Prior. DICOM Re-encoding of Volumetrically Annotated Lung Imaging Data Consortium (LIDC) Nodules. Medical Physics. Aug. 2020. https://doi.org/10.1002/mp.14445
• Matthew C. Hancock, Jerry F. Magnan. Lung nodule malignancy classification using only radiologist quantified image features as inputs to statistical learning algorithms: probing the Lung Image Database Consortium dataset with two statistical learning methods. SPIE Journal of Medical Imaging. Dec. 2016. http://dx.doi.org/10.1117/1.JMI.3.4.044504 - [PDF] - (fine print)

Conference proceedings

• Matthew C. Hancock, Jerry F. Magnan. Predictive capabilities of statistical learning methods for lung nodule malignancy classification using diagnostic image features: an investigation using the Lung Image Database Consortium dataset. SPIE Medical Imaging Symposium, Computer-Aided Diagnosis Conference. Feb 2017. http://dx.doi.org/10.1117/12.2254446 - [PDF] - (fine print)

Pre-prints

• Matthew C. Hancock, Jerry F. Magnan. 2019. Lung nodule segmentation via level set machine learning. arXiv. https://arxiv.org/abs/1910.03191
• Fedorov A, Hancock M, Clunie D, Brochhausen M, Bona J, Kirby J, Freymann J, Pieper S, Aerts H, Kikinis R, Prior F. 2019. Standardized representation of the LIDC annotations using DICOM. PeerJ Preprints 7:e27378v2 doi.org/10.7287/peerj.preprints.27378v2

Slides

• Image segmentation with PDEs - a very light introduction
• Algorithmic lung nodule analysis: a statistical extension of the level set method for image segmentation - an introduction to the LSML (level set machine learning) method for image segmentation with applications to lung nodule segmentation in CT images.
• Predictive capabilities of statistical learning methods for lung nodule malignancy classification using diagnostic image features - these are the slides associated with the talk given at SPIE 2017 Medical Imaging conference proceedings talk above.
• Open Source Python Libraries for Mathematical and Scientific Computing - this was a talk for the mathematics graduate student seminar at FSU. The slides present a number of open python packages for mathematical and scientific computing.
• A survey a of PDE-based methods for image segmentation - a talk presented at the mathematics graduate student seminar.

Posters

• Matthew C. Hancock, Jerry F. Magnan. Lung nodule malignancy classification using diagnostic image features. SIAM SEAS Conference Spring 2017 - [PDF]