Biomedical and Health Sciences

 Histopathological characterization of colorectal polyps allows to tailor patients' management and follow up with the ultimate aim of avoiding or promptly detecting an invasive carcinoma. Colorectal polyps characterization relies on the histological analysis of tissue samples to determine the polyps malignancy and dysplasia grade. Deep neural networks achieve outstanding accuracy in medical patterns recognition, however they require large sets of annotated training images.


This study presented six datasets for DNA/RNA sequence alignment for one of the most common alignment algorithms, namely, the Needleman–Wunsch (NW) algorithm. This research proposed a fast and parallel implementation of the NW algorithm by using machine learning techniques. This study is an extension and improved version of our previous work . The current implementation achieves 99.7% accuracy using a multilayer perceptron with ADAM optimizer and up to 2912 giga cell updates per second on two real DNA sequences with a of length 4.1 M nucleotides.


Protein molecules are inherently dynamic and modulate their interactions with different molecular partners by accessing different tertiary structures under physiological conditions.Elucidating such structures remains challenging. Current momentum in deep learning and the powerful performance of generative adversarial networks (GANs) in complex domains, such as computer vision, inspires us to investigate GANs on their ability to generate physically-realistic protein tertiary structures.


This dataset presents collisions between a service robot - Qolo - and pedestrian dummies: male adult Hybrid-III (H3) and child model 3-years-old (Q3). We present a set of collision scenarios for the assessment of pedestrian safety, considering possible impacts at the legs for adult pedestrians, and legs, chest and head for children.


This dataset consists of 16 tables of measurements of the evolution of the two arms of women who underwent a mastectomy of one breast at the University Hospitals of Strasbourg (HUS) between 2011 and 2019, and who presented a lymphedema. The measurements correspond to repeated averages of perimeters (in cm) of the arms in different positions from the shoulder (indicated by a number in cm).


The purpose of this data collection was for the validation of a cuffless blood pressure estimation model during activities of daily living. Data were collected on five young healthy individuals (four males, age 28 ± 6.6 yrs) of varied fitness levels, ranging from sedentary to regularly active, and free of cardiovascular and peripheral vascular disease. Arterial blood pressure was continuously measured using finger PPG (Portapres; Finapres Medical Systems, the Netherlands).


Magnetic guidance of cochlear implants is a promising technique to reduce the risk of physical trauma during surgery. In this approach, a magnet attached to the tip of the implant electrode array is guided within the scala tympani using a magnetic field. After surgery, the magnet must be detached from the implant electrode array via localized heating, which may cause thermal trauma, and removed from the scala tympani .


The datasets are related to the findings and results of our investigations of the minimal force thresholds perception in robotic surgical applications. The experimental setup included an indenter-based haptic device acting on the fingertip of a participant and a visual system displays grasping tasks by a surgical grasper. The experiments included the display of a set of presentations in three different modes, namely, visual-alone, haptic-alone, and bimodal (i.e., combined). Sixty participants took part in these experiments and were asked to distinguish between consecutive presentations.


Intracellular organelle networks such as the endoplasmic reticulum (ER) network and the mitochondrial network serve crucial physiological functions. Morphology of these networks plays critical roles in mediating their functions.Accurate image segmentation is required for analyzing morphology of these networks for applications such as disease diagnosis and drug discovery. Deep learning models have shown remarkable advantages in accurate and robust segmentation of these complex network structures.


The PD-BioStampRC21 dataset provides data from a wearable sensor
accelerometry study conducted for studying activity, gait, tremor, and
other motor symptoms in individuals with Parkinson's disease (PD).  In
addition to individuals with PD, the dataset also includes data for
controls that also went through the same study protocol as the PD
participants.  Data were acquired using lightweight MC 10 BioStamp RC
sensors (MC 10 Inc, Lexington, MA), five of which were attached to
each participant for gathering data over a roughly two day