Incorporating Robustness to Imaging Physics into Radiomic Feature Selection for Breast Cancer Risk Estimation.

Digital mammography has seen an explosion in the number of radiomic features used for risk-assessment modeling. However, having more features is not necessarily beneficial, as some features may be overly sensitive to imaging physics (contrast, noise, and image sharpness). To measure the effects of imaging physics, we analyzed the feature variation across imaging acquisition settings (kV, mAs) using an anthropomorphic phantom. We also analyzed the intra-woman variation (IWV), a measure of how much a feature varies between breasts with similar parenchymal patterns-a woman's left and right breasts. From 341 features, we identified "robust" features that minimized the effects of imaging physics and IWV. We also investigated whether robust features offered better case-control classification in an independent data set of 575 images, all with an overall BI-RADS® assessment of 1 (negative) or 2 (benign); 115 images (cases) were of women who developed cancer at least one year after that screening image, matched to 460 controls. We modeled cancer occurrence via logistic regression, using cross-validated area under the receiver-operating-characteristic curve (AUC) to measure model performance. Models using features from the most-robust quartile of features yielded an AUC = 0.59, versus 0.54 for the least-robust, with p < 0.005 for the difference among the quartiles.

A versatile system for neuromuscular stimulation and recording in the mouse model using a lightweight magnetically coupled headmount.

Neural stimulation and recording in rodents are common methods to better understand the nervous system and improve the quality of life of individuals who are suffering from neurological disorders (e.g., epilepsy), as well as for permanent reduction of chronic pain in patients with neuropathic pain and spinal-cord injury. This method requires a neural interface (e.g., a headmount) to couple the implanted neural device with instrumentation system. The size and the total weight of such headmounts should be designed in a way to minimize its effect on the movement of the animal. This is a crucial factor in gait, kinematic, and behavioral neuroscience studies of freely moving mice. Here we introduce a lightweight 'snap-in' electro-magnetic headmount that is extremely small, and uses strong neodymium magnetics to enable a reliable connection without sacrificing the lightweight of the device. Additionally, the headmount requires minimal surgical intervention during the implantation, resulting in minimal tissue damage. The device has demonstrated itself to be robust, and successfully provided direct electrical stimulation of nerve and electrical muscle stimulation and recording, as well as powering implanted LEDs for optogenetic use scenarios.

O-Net: An Overall Convolutional Network for Segmentation Tasks.

Convolutional neural networks (CNNs) have recently been popular for classification and segmentation through numerous network architectures offering a substantial performance improvement. Their value has been particularly appreciated in the domain of biomedical applications, where even a small improvement in the predicted segmented region (e.g., a malignancy) compared to the ground truth can potentially lead to better diagnosis or treatment planning. Here, we introduce a novel architecture, namely the Overall Convolutional Network (O-Net), which takes advantage of different pooling levels and convolutional layers to extract more deeper local and containing global context. Our quantitative results on 2D images from two distinct datasets show that O-Net can achieve a higher dice coefficient when compared to either a U-Net or a Pyramid Scene Parsing Net. We also look into the stability of results for training and validation sets which can show the robustness of model compared with new datasets. In addition to comparison to the decoder, we use different encoders including simple, VGG Net, and ResNet. The ResNet encoder could help to improve the results in most of the cases.

Calculation of Radiomic Features to Validate the Textural Realism of Physical Anthropomorphic Phantoms for Digital Mammography.

In this paper, radiomic features are used to validate the textural realism of two anthropomorphic phantoms for digital mammography. One phantom was based off a computational breast model; it was 3D printed by CIRS (Computerized Imaging Reference Systems, Inc., Norfolk, VA) under license from the University of Pennsylvania. We investigate how the textural realism of this phantom compares against a phantom derived from an actual patient's mammogram ("Rachel", Gammex 169, Madison, WI). Images of each phantom were acquired at three kV in 1 kV increments using auto-time technique settings. Acquisitions at each technique setting were repeated twice, resulting in six images per phantom. In the raw ("FOR PROCESSING") images, 341 features were calculated; i.e., gray-level histogram, co-occurrence, run length, fractal dimension, Gabor Wavelet, local binary pattern, Laws, and co-occurrence Laws features. Features were also calculated in a negative screening population. For each feature, the middle 95% of the clinical distribution was used to evaluate the textural realism of each phantom. A feature was considered realistic if all six measurements in the phantom were within the middle 95% of the clinical distribution. Otherwise, a feature was considered unrealistic. More features were actually found to be realistic by this definition in the CIRS phantom (305 out of 341 features or 89.44%) than in the phantom derived from a specific patient's mammogram (261 out of 341 features or 76.54%). We conclude that the texture is realistic overall in both phantoms.

Robust Radiomic Feature Selection in Digital Mammography: Understanding the Effect of Imaging Acquisition Physics Using Phantom and Clinical Data Analysis.

Studies have shown that combining calculations of radiomic features with estimates of mammographic density results in an even better assessment of breast cancer risk than density alone. However, to ensure that risk assessment calculations are consistent across different imaging acquisition settings, it is important to identify features that are not overly sensitive to changes in these settings. In this study, digital mammography (DM) images of an anthropomorphic phantom ("Rachel", Gammex 169, Madison, WI) were acquired at various technique settings. We varied kV and mAs, which control contrast and noise, respectively. DM images in women with negative screening exams were also analyzed. Radiomic features were calculated in the raw ("FOR PROCESSING") DM images; i.e., grey-level histogram, co-occurrence, run length, fractal dimension, Gabor Wavelet, local binary pattern, Laws, and co-occurrence Laws features. For each feature, the range of variation across technique settings in phantom images was calculated. This range was scaled against the range of variation in the clinical distribution (specifically, the range corresponding to the middle 90% of the distribution). In order for a radiomic feature to be considered robust, this metric of imaging acquisition variation (IAV) should be as small as possible (approaching zero). An IAV threshold of 0.25 was proposed for the purpose of this study. Out of 341 features, 284 features (83%) met the threshold IAV ≤ 0.25. In conclusion, we have developed a method to identify robust radiomic features in DM.

Adaptation to slope in locomotor-trained spinal cats with intact and self-reinnervated lateral gastrocnemius and soleus muscles.

Sensorimotor training providing motion-dependent somatosensory feedback to spinal locomotor networks restores treadmill weight-bearing stepping on flat surfaces in spinal cats. In this study, we examined if locomotor ability on flat surfaces transfers to sloped surfaces and the contribution of length-dependent sensory feedback from lateral gastrocnemius (LG) and soleus (Sol) to locomotor recovery after spinal transection and locomotor training. We compared kinematics and muscle activity at different slopes (±10° and ±25°) in spinalized cats (n = 8) trained to walk on a flat treadmill. Half of those animals had their right hindlimb LG/Sol nerve cut and reattached before spinal transection and locomotor training, a procedure called muscle self-reinnervation that leads to elimination of autogenic monosynaptic length feedback in spinally intact animals. All spinal animals trained on a flat surface were able to walk on slopes with minimal differences in walking kinematics and muscle activity between animals with/without LG/Sol self-reinnervation. We found minimal changes in kinematics and muscle activity at lower slopes (±10°), indicating that walking patterns obtained on flat surfaces are robust enough to accommodate low slopes. Contrary to results in spinal intact animals, force responses to muscle stretch largely returned in both SELF-REINNERVATED muscles for the trained spinalized animals. Overall, our results indicate that the locomotor patterns acquired with training on a level surface transfer to walking on low slopes and that spinalization may allow the recovery of autogenic monosynaptic length feedback following muscle self-reinnervation.NEW & NOTEWORTHY Spinal locomotor networks locomotor trained on a flat surface can adapt the locomotor output to slope walking, up to ±25° of slope, even with total absence of supraspinal CONTROL. Autogenic length feedback (stretch reflex) shows signs of recovery in spinalized animals, contrary to results in spinally intact animals.

Detection of small bowel tumor in wireless capsule endoscopy images using an adaptive neuro-fuzzy inference system.

Automatic diagnosis tool helps physicians to evaluate capsule endoscopic examinations faster and more accurate. The purpose of this study was to evaluate the validity and reliability of an automatic post-processing method for identifying and classifying wireless capsule endoscopic images, and investigate statistical measures to differentiate normal and abnormal images. The proposed technique consists of two main stages, namely, feature extraction and classification. Primarily, 32 features incorporating four statistical measures (contrast, correlation, homogeneity and energy) calculated from co-occurrence metrics were computed. Then, mutual information was used to select features with maximal dependence on the target class and with minimal redundancy between features. Finally, a trained classifier, adaptive neuro-fuzzy interface system was implemented to classify endoscopic images into tumor, healthy and unhealthy classes. Classification accuracy of 94.2% was obtained using the proposed pipeline. Such techniques are valuable for accurate detection characterization and interpretation of endoscopic images.