Total Variation meets Sparsity: statistical learning with segmenting penalties

Abstract : Prediction from medical images is a valuable aid to diagnosis. For instance, anatomical MR images can reveal certain disease conditions, while their functional counterparts can predict neuropsychi-atric phenotypes. However, a physician will not rely on predictions by black-box models: understanding the anatomical or functional features that underpin decision is critical. Generally, the weight vectors of clas-sifiers are not easily amenable to such an examination: Often there is no apparent structure. Indeed, this is not only a prediction task, but also an inverse problem that calls for adequate regularization. We address this challenge by introducing a convex region-selecting penalty. Our penalty combines total-variation regularization, enforcing spatial conti-guity, and 1 regularization, enforcing sparsity, into one group: Voxels are either active with non-zero spatial derivative or zero with inactive spatial derivative. This leads to segmenting contiguous spatial regions (inside which the signal can vary freely) against a background of zeros. Such segmentation of medical images in a target-informed manner is an important analysis tool. On several prediction problems from brain MRI, the penalty shows good segmentation. Given the size of medical images, computational efficiency is key. Keeping this in mind, we contribute an efficient optimization scheme that brings significant computational gains.
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal.inria.fr/hal-01170619
Contributor : Michael Eickenberg <>
Submitted on : Tuesday, July 21, 2015 - 9:54:58 AM
Last modification on : Friday, March 8, 2019 - 1:20:05 AM
Long-term archiving on : Thursday, October 22, 2015 - 10:10:55 AM

File

paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01170619, version 1

Citation

Michael Eickenberg, Elvis Dohmatob, Bertrand Thirion, Gaël Varoquaux. Total Variation meets Sparsity: statistical learning with segmenting penalties. Medical Image Computing and Computer Aided Intervention (MICCAI), Oct 2015, München, Germany. ⟨hal-01170619⟩

Share

Metrics

Record views

1338

Files downloads

984