“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

IEEE Transactions on Pattern Analysis and Machine Intelligence

Medical Image Computing and Computer-Assisted Intervention

The Martini coarse-grained force field has been successfully used for simulating a wide range of (bio)molecular systems. Recent progress in our ability to test the model against fully atomistic force fields, however, has revealed some shortcomings. Most notable, phenylalanine and proline were too hydrophobic, and dimers formed by polar residues in apolar solvents did not bind strongly enough. Here, we reparametrize these residues either through reassignment of particle types or by introducing embedded charges. The new parameters are tested with respect to partitioning across a lipid bilayer, membrane binding of Wimley–White peptides, and dimerization free energy in solvents of different polarity. In addition, we improve some of the bonded terms in the Martini protein force field that lead to a more realistic length of α-helices and to improved numerical stability for polyalanine and glycine repeats. The new parameter set is denoted Martini version 2.2.

/pdf/improved-parameters-for-the-martini-coarse-grained-protein-4ecsxredvf.pdf

Improved Parameters for the Martini Coarse-Grained Protein Force Field

The Martini model, a coarse-grained force field for biomolecular simulations, has found a broad range of applications since its release a decade ago. Based on a building block principle, the model combines speed and versatility while maintaining chemical specificity. Here we review the current state of the model. We describe recent highlights as well as shortcomings, and our ideas on the further development of the model.

/pdf/perspective-on-the-martini-model-48a9823w5f.pdf

Perspective on the Martini model.

DOSMA: A deep-learning, open-source framework for musculoskeletal MRI analysis

. Unrolled neural networks have enabled state-of-the-art reconstruction performance and fast inference times for the accelerated magnetic resonance imaging (MRI) reconstruction task. However, these approaches depend on fully-sampled scans as ground truth data which is either costly or not possible to acquire in many clinical medical imaging applications; hence, reducing dependence on data is desirable. In this work, we propose modeling the proximal operators of unrolled neural networks with scale-equivariant convolutional neural networks in order to improve the data-eﬃciency and robustness to drifts in scale of the images that might stem from the variability of patient anatomies or change in ﬁeld-of-view across diﬀerent MRI scanners. Our approach demonstrates strong improvements over the state-of-the-art unrolled neural networks under the same memory constraints both with and without data augmentations on both in-distribution and out-of-distribution scaled images without signiﬁcantly increasing the train or inference time.

Scale-Equivariant Unrolled Neural Networks for Data-Efficient Accelerated MRI Reconstruction

Motivation: Traditional image attribution methods struggle to satisfactorily explain predictions of neural networks. Prediction explanation is important, especially in the medical imaging, for avoiding the unintended consequences of deploying AI systems when false positive predictions can impact patient care. Thus, there is a pressing need to develop improved models for model explainability and introspection. 
Specific Problem: A new approach is to transform input images to increase or decrease features which cause the prediction. However, current approaches are difficult to implement as they are monolithic or rely on GANs. These hurdles prevent wide adoption. 
Our approach: Given an arbitrary classifier, we propose a simple autoencoder and gradient update (Latent Shift) that can transform the latent representation of an input image to exaggerate or curtail the features used for prediction. We use this method to study chest X-ray classifiers and evaluate their performance. We conduct a reader study with two radiologists assessing 240 chest X-ray predictions to identify which ones are false positives (half are) using traditional attribution maps or our proposed method. 
Results: We found low overlap with ground truth pathology masks for models with reasonably high accuracy. However, the results from our reader study indicate that these models are generally looking at the correct features. We also found that the Latent Shift explanation allows a user to have more confidence in true positive predictions compared to traditional approaches (0.15$\pm$0.95 in a 5 point scale with p=0.01) with only a small increase in false positive predictions (0.04$\pm$1.06 with p=0.57). 
Accompanying webpage: this https URL
Source code: this https URL

Gifsplanation via Latent Shift: A Simple Autoencoder Approach to Progressive Exaggeration on Chest X-rays.

To develop and validate a method for B0$$ {B}_0 $$ mapping for knee imaging using the quantitative Double‐Echo in Steady‐State (qDESS) exploiting the phase difference ( Δθ$$ \Delta \theta $$ ) between the two echoes acquired. Contrary to a two‐gradient‐echo (2‐GRE) method, Δθ$$ \Delta \theta $$ depends only on the first echo time.

A method for measuring B0 field inhomogeneity using quantitative double‐echo in steady‐state

Deep learning (DL) has shown promise for faster, high quality accelerated MRI reconstruction. However, standard supervised DL methods depend on extensive amounts of fully-sampled ground-truth data and are sensitive to out-of-distribution (OOD) shifts, in particular for low signal-to-noise ratio (SNR) acquisitions. To alleviate this challenge, we propose a semi-supervised, consistency-based framework (termed Noise2Recon) for joint MR reconstruction and denoising. Our method enables the usage of a limited number of fully-sampled and a large number of undersampled-only scans. We compare our method to augmentation-based supervised techniques and fine-tuned denoisers. Results demonstrate that even with minimal ground-truth data, Noise2Recon (1) achieves high performance on in-distribution (low-noise) scans and (2) improves generalizability to OOD, noisy scans.

Akshay S. Chaudhari

Papers

DOSMA: A deep-learning, open-source framework for musculoskeletal MRI analysis

Scale-Equivariant Unrolled Neural Networks for Data-Efficient Accelerated MRI Reconstruction

Gifsplanation via Latent Shift: A Simple Autoencoder Approach to Progressive Exaggeration on Chest X-rays.

A method for measuring B0 field inhomogeneity using quantitative double‐echo in steady‐state

Noise2Recon: A Semi-Supervised Framework for Joint MRI Reconstruction and Denoising.