CoLiDe: Combinatorial Library Design tool for probing protein sequence space.

Motivation: Current techniques of protein engineering focus mostly on re-designing small targeted regions or defined structural scaffolds rather than constructing combinatorial libraries of versatile compositions and lengths. This is a missed opportunity because combinatorial libraries are emerging as a vital source of novel functional proteins and are of interest in diverse research areas.

Results: Here, we present a computational tool for Combinatorial Library Design (CoLiDe) offering precise control over protein sequence composition, length and diversity.

Convolution kernel and iterative reconstruction affect the diagnostic performance of radiomics and deep learning in lung adenocarcinoma pathological subtypes.

Background: The aim of this study was to investigate the influence of convolution kernel and iterative reconstruction on the diagnostic performance of radiomics and deep learning (DL) in lung adenocarcinomas.

Methods: A total of 183 patients with 215 lung adenocarcinomas were included in this study. All CT imaging data was reconstructed with three reconstruction algorithms (ASiR at 0%, 30%, 60% strength), each with two convolution kernels (bone and standard).

Toward automatic prediction of EGFR mutation status in pulmonary adenocarcinoma with 3D deep learning.

To develop a deep learning system based on 3D convolutional neural networks (CNNs), and to automatically predict EGFR-mutant pulmonary adenocarcinoma in CT images. A dataset of 579 nodules with EGFR mutation status labels of mutant (Mut) or wild-type (WT) was retrospectively analyzed. A deep learning system, namely 3D DenseNets, was developed to process 3D patches of nodules from CT data, and learn strong representations with supervised end-to-end training.

3D Deep Learning from CT Scans Predicts Tumor Invasiveness of Subcentimeter Pulmonary Adenocarcinomas.

: Identification of early-stage pulmonary adenocarcinomas before surgery, especially in cases of subcentimeter cancers, would be clinically important and could provide guidance to clinical decision making. In this study, we developed a deep learning system based on 3D convolutional neural networks and multitask learning, which automatically predicts tumor invasiveness, together with 3D nodule segmentation masks. The system processes a 3D nodule-centered patch of preprocessed CT and learns a deep representation of a given nodule without the need for any additional information.

Which limb is it? Responses to vibrotactile stimulation in early infancy.

This study focuses on how the body schema develops during the first months of life, by investigating infants' motor responses to localized vibrotactile stimulation on their limbs. Vibrotactile stimulation was provided by small buzzers that were attached to the infants' four limbs one at a time. Four age groups were compared cross-sectionally (3-, 4-, 5-, and 6-month-olds).

Fully automated classification of bone marrow infiltration in low-dose CT of patients with multiple myeloma based on probabilistic density model and supervised learning.

This paper presents a fully automated method for the identification of bone marrow infiltration in femurs in low-dose CT of patients with multiple myeloma. We automatically find the femurs and the bone marrow within them. In the next step, we create a probabilistic, spatially dependent density model of normal tissue.

Patient-specific simulation of the intrastromal ring segment implantation in corneas with keratoconus.

Purpose: The purpose of this study was the simulation of the implantation of intrastromal corneal-ring segments for patients with keratoconus. The aim of the study was the prediction of the corneal curvature recovery after this intervention.

Methods: Seven patients with keratoconus diagnosed and treated by implantation of intrastromal corneal-ring segments were enrolled in the study.

Line filtering for surgical tool localization in 3D ultrasound images.

We present a method for automatic surgical tool localization in 3D ultrasound images based on line filtering, voxel classification and model fitting. This could possibly provide assistance for biopsy needle or micro-electrode insertion, or a robotic system performing this insertion. The line-filtering method is first used to enhance the contrast of the 3D ultrasound image, then a classifier is chosen to separate the tool voxels, in order to reduce the number of outliers.

Polynomial Eigenvalue Solutions to Minimal Problems in Computer Vision.

We present a method for solving systems of polynomial equations appearing in computer vision. This method is based on polynomial eigenvalue solvers and is more straightforward and easier to implement than the state-of-the-art Gröbner basis method since eigenvalue problems are well studied, easy to understand, and efficient and robust algorithms for solving these problems are available. We provide a characterization of problems that can be efficiently solved as polynomial eigenvalue problems (PEPs) and present a resultant-based method for transforming a system of polynomial equations to a polynomial eigenvalue problem.

Automatic colposcopy video tissue classification using higher order entropy-based image registration.

Colposcopy is a well-established method to detect and diagnose intraepithelial lesions and uterine cervical cancer in early stages. During the exam color and texture changes are induced by the application of a contrast agent (e.g.

Efficient sequential correspondence selection by cosegmentation.

In many retrieval, object recognition, and wide-baseline stereo methods, correspondences of interest points (distinguished regions) are commonly established by matching compact descriptors such as SIFTs. We show that a subsequent cosegmentation process coupled with a quasi-optimal sequential decision process leads to a correspondence verification procedure that 1) has high precision (is highly discriminative), 2) has good recall, and 3) is fast. The sequential decision on the correctness of a correspondence is based on simple statistics of a modified dense stereo matching algorithm.

Model fitting using RANSAC for surgical tool localization in 3-D ultrasound images.

Ultrasound guidance is used for many surgical interventions such as biopsy and electrode insertion. We present a method to localize a thin surgical tool such as a biopsy needle or a microelectrode in a 3-D ultrasound image. The proposed method starts with thresholding and model fitting using random sample consensus for robust localization of the axis.

Parallel integral projection transform for straight electrode localization in 3-D ultrasound images.

In surgical practice, small metallic instruments are frequently used to perform various tasks inside the human body. We address the problem of their accurate localization in the tissue. Recent experiments using medical ultrasound have shown that this modality is suitable for real-time visualization of anatomical structures as well as the position of surgical instruments.

Parallel image reconstruction using B-spline approximation (PROBER).

A new reconstruction method for parallel MRI called PROBER is proposed. The method PROBER works in an image domain similar to methods based on Sensitivity Encoding (SENSE). However, unlike SENSE, which first estimates the spatial sensitivity maps, PROBER approximates the reconstruction coefficients directly by B-splines.

High-dimensional entropy estimation for finite accuracy data: R-NN entropy estimator.

We address the problem of entropy estimation for high-dimensional finite-accuracy data. Our main application is evaluating high-order mutual information image similarity criteria for multimodal image registration. The basis of our method is an estimator based on k-th nearest neighbor (NN) distances, modified so that only distances greater than some constant R are evaluated.

Computational elastography from standard ultrasound image sequences by global trust region optimization.

A new approach is proposed to estimate the spatial distribution of shear modulus of tissues in-vivo. An image sequence is acquired using a standard medical ultrasound scanner while varying the force applied to the handle. The elastic properties are then recovered simultaneously with the inter-frame displacement fields using a computational procedure based on finite element modeling and trust region constrained optimization.

Generalized head models for MEG/EEG: boundary element method beyond nested volumes.

Accurate geometrical models of the head are necessary for solving the forward and inverse problems of magneto- and electro-encephalography (MEG/EEG). Boundary element methods (BEMs) require a geometrical model describing the interfaces between different tissue types. Classically, head models with a nested volume topology have been used.

Fast multipole acceleration of the MEG/EEG boundary element method.

The accurate solution of the forward electrostatic problem is an essential first step before solving the inverse problem of magneto- and electroencephalography (MEG/EEG). The symmetric Galerkin boundary element method is accurate but cannot be used for very large problems because of its computational complexity and memory requirements. We describe a fast multipole-based acceleration for the symmetric boundary element method (BEM).