Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Pathology Pathology

Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation

ArXiv Preprint

In medical imaging, organ/pathology segmentation models trained on current publicly available and fully-annotated datasets usually do not well-represent the heterogeneous modalities, phases, pathologies, and clinical scenarios encountered in real environments. On the other hand, there are tremendous amounts of unlabelled patient imaging scans stored by many modern clinical centers. In this work, we present a novel segmentation strategy, co-heterogenous and adaptive segmentation (CHASe), which only requires a small labeled cohort of single phase imaging data to adapt to any unlabeled cohort of heterogenous multi-phase data with possibly new clinical scenarios and pathologies. To do this, we propose a versatile framework that fuses appearance based semi-supervision, mask based adversarial domain adaptation, and pseudo-labeling. We also introduce co-heterogeneous training, which is a novel integration of co-training and hetero modality learning. We have evaluated CHASe using a clinically comprehensive and challenging dataset of multi-phase computed tomography (CT) imaging studies (1147 patients and 4577 3D volumes). Compared to previous state-of-the-art baselines, CHASe can further improve pathological liver mask Dice-Sorensen coefficients by ranges of $4.2\% \sim 9.4\%$, depending on the phase combinations: e.g., from $84.6\%$ to $94.0\%$ on non-contrast CTs.

Ashwin Raju, Chi-Tung Cheng, Yunakai Huo, Jinzheng Cai, Junzhou Huang, Jing Xiao, Le Lu, ChienHuang Liao, Adam P Harrison


General General

Generalized norm for existence, uniqueness and stability of Hopfield neural networks with discrete and distributed delays.

In Neural networks : the official journal of the International Neural Network Society

In this paper, the existence, uniqueness and stability criteria of solutions for Hopfield neural networks with discrete and distributed delays (DDD HNNs) are investigated by the definitions of three kinds of generalized norm (ξ-norm). A general DDD HNN model is firstly introduced, where the discrete delays τpq(t) are asynchronous time-varying delays. Then, {ξ,1}-norm, {ξ,2}-norm and {ξ,∞}-norm are successively used to derive the existence, uniqueness and stability criteria of solutions for the DDD HNNs. In the proof of theorems, special functions and assumptions are given to deal with discrete and distributed delays. Furthermore, a corollary is concluded for the existence and stability criteria of solutions. The methods given in this paper can also be used to study the synchronization and μ-stability of different DDD NNs. Finally, two numerical examples and their simulation figures are given to illustrate the effectiveness of these results.

Wang Huamin, Wei Guoliang, Wen Shiping, Huang Tingwen


-norm, Discrete-distributed delays, Exponential stability, Hopfield neural networks

General General

Uni-image: Universal image construction for robust neural model.

In Neural networks : the official journal of the International Neural Network Society

Deep neural networks have shown high performance in prediction, but they are defenseless when they predict on adversarial examples which are generated by adversarial attack techniques. In image classification, those attack techniques usually perturb the pixel of an image to fool the deep neural networks. To improve the robustness of the neural networks, many researchers have introduced several defense techniques against those attack techniques. To the best of our knowledge, adversarial training is one of the most effective defense techniques against the adversarial examples. However, the defense technique could fail against a semantic adversarial image that performs arbitrary perturbation to fool the neural networks, where the modified image semantically represents the same object as the original image. Against this background, we propose a novel defense technique, Uni-Image Procedure (UIP) method. UIP generates a universal-image (uni-image) from a given image, which can be a clean image or a perturbed image by some attacks. The generated uni-image preserves its own characteristics (i.e. color) regardless of the transformations of the original image. Note that those transformations include inverting the pixel value of an image, modifying the saturation, hue, and value of an image, etc. Our experimental results using several benchmark datasets show that our method not only defends well known adversarial attacks and semantic adversarial attack but also boosts the robustness of the neural network.

Ho Jiacang, Lee Byung-Gook, Kang Dae-Ki


Adversarial machine learning, Defense technique, Image classification, Semantic adversarial example, Uni-Image Procedure

General General

Active source localization in wave guides based on machine learning.

In Ultrasonics

In the present work, an active source localization strategy is proposed. The presence of active sources in a waveguide can have several reasons, such as crack initiation or internal friction. In this study, the active source is represented by an impact event. A steel ball is dropped on an aluminum plate at different positions. Elastic waves are excited and will propagate through the plate. The wave response is acquired by a piezoelectric sensor network, which is attached to the plate. After performing numerical and physical experiments, enough data are collected in order to train an artificial neural network and a support vector machine. Those machine learning algorithms will predict the impact position based on the wave response of each sensor, while only numerical data from the finite element simulations are used to train both methods. After the training process is completed, the algorithms are applied to experimental data. A good agreement between reference and predicted results proves that the wave responses at the piezoelectric transducers contain sufficient information in order to localize the impact position precisely.

Hesser Daniel Frank, Kocur Georg Karl, Markert Bernd


Artificial neural network, Computational intelligence, Guided elastic waves, Impact dynamics, Structural health monitoring

General General

CHEER: hierarCHical taxonomic classification for viral mEtagEnomic data via deep leaRning.

In Methods (San Diego, Calif.)

The fast accumulation of viral metagenomic data has contributed significantly to new RNA virus discovery. However, the short read size, complex composition, and large data size can all make taxonomic analysis difficult. In particular, commonly used alignment-based methods are not ideal choices for detecting new viral species. In this work, we present a novel hierarchical classification model named CHEER, which can conduct read-level taxonomic classification from order to genus for new species. By combining k-mer embedding-based encoding, hierarchically organized CNNs, and carefully trained rejection layer, CHEER is able to assign correct taxonomic labels for reads from new species. We tested CHEER on both simulated and real sequencing data. The results show that CHEER can achieve higher accuracy than popular alignment-based and alignment-free taxonomic assignment tools. The source code, scripts, and pre-trained parameters for CHEER are available via GitHub:

Shang Jiayu, Sun Yanni


Convolutional Neural Network, Deep learning, RNA virus, Taxonomic classification, Viral metagenomic data

General General

The interplay between multisensory integration and perceptual decision making.

In NeuroImage ; h5-index 117.0

Facing perceptual uncertainty, the brain combines information from different senses to make optimal perceptual decisions and to guide behavior. However, decision making has been investigated mostly in unimodal contexts. Thus, how the brain integrates multisensory information during decision making is still unclear. Two opposing, but not mutually exclusive, scenarios are plausible: either the brain thoroughly combines the signals from different modalities before starting to build a supramodal decision, or unimodal signals are integrated during decision formation. To answer this question, we devised a paradigm mimicking naturalistic situations where human participants were exposed to continuous cacophonous audiovisual inputs containing an unpredictable signal cue in one or two modalities and had to perform a signal detection task or a cue categorization task. First, model-based analyses of behavioral data indicated that multisensory integration takes place alongside perceptual decision making. Next, using supervised machine learning on concurrently recorded EEG, we identified neural signatures of two processing stages: sensory encoding and decision formation. Generalization analyses across experimental conditions and time revealed that multisensory cues were processed faster during both stages. We further established that acceleration of neural dynamics during sensory encoding and decision formation was directly linked to multisensory integration. Our results were consistent across both signal detection and categorization tasks. Taken together, the results revealed a continuous dynamic interplay between multisensory integration and decision making processes (mixed scenario), with integration of multimodal information taking place both during sensory encoding as well as decision formation.

Mercier Manuel R, Cappe Celine


Drift Diffusion Model, EEG decoding, Multisensory integration, Perceptual decision making, Race model, Supervised machine learning