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

General General

Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsules.

In IEEE transactions on image processing : a publication of the IEEE Signal Processing Society

Learning discriminative shape representation directly on point clouds is still challenging in 3D shape analysis and understanding. Recent studies usually involve three steps: first splitting a point cloud into some local regions, then extracting the corresponding feature of each local region, and finally aggregating all individual local region features into a global feature as shape representation using simple max-pooling. However, such pooling-based feature aggregation methods do not adequately take the spatial relationships (e.g. the relative locations to other regions) between local regions into account, which greatly limits the ability to learn discriminative shape representation. To address this issue, we propose a novel deep learning network, named Point2SpatialCapsule, for aggregating features and spatial relationships of local regions on point clouds, which aims to learn more discriminative shape representation. Compared with the traditional max-pooling based feature aggregation networks, Point2SpatialCapsule can explicitly learn not only geometric features of local regions but also the spatial relationships among them. Point2SpatialCapsule consists of two main modules. To resolve the disorder problem of local regions, the first module, named geometric feature aggregation, is designed to aggregate the local region features into the learnable cluster centers, which explicitly encodes the spatial locations from the original 3D space. The second module, named spatial relationship aggregation, is proposed for further aggregating the clustered features and the spatial relationships among them in the feature space using the spatial-aware capsules developed in this paper. Compared to the previous capsule network based methods, the feature routing on the spatial-aware capsules can learn more discriminative spatial relationships among local regions for point clouds, which establishes a direct mapping between log priors and the spatial locations through feature clusters. Experimental results demonstrate that Point2SpatialCapsule outperforms the state-of-the-art methods in the 3D shape classification, retrieval and segmentation tasks under the well-known ModelNet and ShapeNet datasets.

Wen Xin, Han Zhizhong, Liu Xinhai, Liu Yu-Shen

2020-Sep-07

General General

Deep Learning for Automatic Segmentation of Hybrid Optoacoustic Ultrasound (OPUS) Images.

In IEEE transactions on ultrasonics, ferroelectrics, and frequency control

The highly complementary information provided by multispectral optoacoustics and pulse-echo ultrasound have recently prompted development of hybrid imaging instruments bringing together the unique contrast advantages of both modalities. In the hybrid optoacoustic ultrasound (OPUS) combination, images retrieved by one modality may further be used to improve the reconstruction accuracy of the other. In this regard, image segmentation plays a major role as it can aid improving the image quality and quantification abilities by facilitating modeling of light and sound propagation through the imaged tissues and surrounding coupling medium. Here we propose an automated approach for surface segmentation in whole-body mouse OPUS imaging using a deep convolutional neural network (CNN). The method has shown robust performance, attaining accurate segmentation of the animal boundary in both optoacoustic and pulseecho ultrasound images, as evinced by quantitative performance evaluation using Dice coefficient metrics.

Lafci Berkan, Mercep Elena, Morscher Stefan, Dean-Ben Xose Luis, Razansky Daniel

2020-Sep-07

General General

Multi-view Separable Pyramid Network for AD Prediction at MCI Stage by 18F-FDG Brain PET Imaging.

In IEEE transactions on medical imaging ; h5-index 74.0

Alzheimer's Disease (AD), one of the main causes of death in elderly people, is characterized by Mild Cognitive Impairment (MCI) at prodromal stage. Nevertheless, only part of MCI subjects could progress to AD. The main objective of this paper is thus to identify those who will develop a dementia of AD type among MCI patients. 18F-FluoroDeoxyGlucose Positron Emission Tomography (18F-FDG PET) serves as a neuroimaging modality for early diagnosis as it can reflect neural activity via measuring glucose uptake at resting-state. In this paper, we design a deep network on 18F-FDG PET modality to address the problem of AD identification at early MCI stage. To this end, a Multi-view Separable Pyramid Network (MiSePyNet) is proposed, in which representations are learned from axial, coronal and sagittal views of PET scans so as to offer complementary information and then combined to make a decision jointly. Different from the widely and naturally used 3D convolution operations for 3D images, the proposed architecture is deployed with separable convolution from slice-wise to spatial-wise successively, which can retain the spatial information and reduce training parameters compared to 2D and 3D networks, respectively. Experiments on ADNI dataset show that the proposed method can yield better performance than both traditional and deep learning-based algorithms for predicting the progression of Mild Cognitive Impairment, with a classification accuracy of 83.05%.

Pan Xiaoxi, Phan Trong-Le, Adel Mouloud, Fossati Caroline, Gaidon Thierry, Wojak Julien, Guedj Eric

2020-Sep-07

General General

Lesion-Harvester: Iteratively Mining Unlabeled Lesions and Hard-Negative Examples at Scale.

In IEEE transactions on medical imaging ; h5-index 74.0

The acquisition of large-scale medical image data, necessary for training machine learning algorithms, is hampered by associated expert-driven annotation costs. Mining hospital archives can address this problem, but labels often incomplete or noisy, e.g., 50% of the lesions in DeepLesion are left unlabeled. Thus, effective label harvesting methods are critical. This is the goal of our work, where we introduce Lesion-Harvester-a powerful system to harvest missing annotations from lesion datasets at high precision. Accepting the need for some degree of expert labor, we use a small fully-labeled image subset to intelligently mine annotations from the remainder. To do this, we chain together a highly sensitive lesion proposal generator (LPG) and a very selective lesion proposal classifier (LPC). Using a new hard negative suppression loss, the resulting harvested and hard-negative proposals are then employed to iteratively finetune our LPG. While our framework is generic, we optimize our performance by proposing a new 3D contextual LPG and by using a global-local multi-view LPC. Experiments on DeepLesion demonstrate that Lesion- Harvester can discover an additional 9; 805 lesions at a precision of 90%. We publicly release the harvested lesions, along with a new test set of completely annotated DeepLesion volumes. We also present a pseudo 3D IoU evaluation metric that corresponds much better to the real 3D IoU than current DeepLesion evaluation metrics. To quantify the downstream benefits of Lesion-Harvester we show that augmenting the DeepLesion annotations with our harvested lesions allows state-of-the-art detectors to boost their average precision by 7 to 10%.

Cai Jinzheng, Harrison Adam P, Zheng Youjing, Yan Ke, Huo Yuankai, Xiao Jing, Yang Lin, Lu Le

2020-Sep-07

General General

Generative Imputation and Stochastic Prediction.

In IEEE transactions on pattern analysis and machine intelligence ; h5-index 127.0

In many machine learning applications, we are faced with incomplete datasets. In the literature, missing data imputation techniques have been mostly concerned with filling missing values. However, the existence of missing values is synonymous with uncertainties not only over the distribution of missing values but also over target class assignments that require careful consideration. In this paper, we propose a simple and effective method for imputing missing features and estimating the distribution of target assignments given incomplete data. In order to make imputations, we train a simple and effective generator network to generate imputations that a discriminator network is tasked to distinguish. Following this, a predictor network is trained using the imputed samples from the generator network to capture the classification uncertainties and make predictions accordingly. The proposed method is evaluated on CIFAR-10 and MNIST image datasets as well as five real-world tabular classification datasets, under different missingness rates and structures. Our experimental results show the effectiveness of the proposed method in generating imputations as well as providing estimates for the class uncertainties in a classification task when faced with missing values.

Kachuee Mohammad, Karkkainen Kimmo, Goldstein Orpaz, Darabi Sajad, Sarrafzadeh Majid

2020-Sep-07

General General

Glial Modulation of Electrical Rhythms in a Neuroglial Network Model of Epilepsy.

In IEEE transactions on bio-medical engineering

OBJECTIVE : An important EEG-based biomarker for epilepsy is the phase-amplitude cross-frequency coupling (PAC) of electrical rhythms; however, the underlying pathways of these pathologic markers are not always clear. Since glial cells have been shown to play an active role in neuroglial networks, it is likely that some of these PAC markers are modulated via glial effects.

METHODS : We developed a 4-unit hybrid model of a neuroglial network, consisting of 16 sub-units, that combines a mechanistic representation of neurons with an oscillator- based Cognitive Rhythm Generator (CRG) representation of glial cells astrocytes and microglia. The model output was compared with recorded generalized tonic-clonic patient data, both in terms of PAC features, and state classification using an unsupervised hidden Markov model (HMM).

RESULTS : The neuroglial model output showed PAC features similar to those observed in epileptic seizures. These generated PAC features were able to accurately identify spontaneous epileptiform discharges (SEDs) as seizure- like states, as well as a postictal-like state following the long- duration SED, when applied to the HMM machine learning algorithm trained on patient data. The evolution profile of the maximal PAC during the SED compared well with patient data, showing similar association with the duration of the postictal state.

CONCLUSION : The hybrid neuroglial network model was able to generate PAC features similar to those observed in ictal and postictal epileptic states, which has been used for state classification and postictal state duration prediction.

SIGNIFICANCE : Since PAC biomarkers are important for epilepsy research and postictal state duration has been linked with risk of sudden unexplained death in epilepsy, this model suggests glial synaptic effects as potential targets for further analysis and treatment.

Grigorovsky Vasily, Breton Vanessa, Bardakjian Berj L

2020-Sep-07