We build applications based on Artificial Intelligence for healthcare, making technology more efficient for human well-being.
Who we are
Sentic Lab is an applied scientific research company with its headquarter in Iasi (Romania). Thanks to our talented team comprised of data scientists, front-end and back-end developers and scientific consultants from the academia, we conduct cutting-edge research and develop innovative medical diagnosis software. We closely collaborate with "Alexandru Ioan Cuza" University from Iasi which has a long term tradition in promoting excellence and innovation in education and research domains. Medical expertise is provided by highly experimented radiologists and surgeons from the Regional Institute of Oncology and the Neurosurgery Hospital “Prof. dr. Nicolae Oblu” from Iasi. Internationally we closely collaborate with the University of Palermo on research in AI4Healthcare.
Our team
We offer innovative tools that apply Artificial Intelligence to healthcare, bringing substantial improvements in terms of quality and effectiveness of diagnosis for people's health.

Our business core is AI4HealthCare, a software capable of extracting meta data and making classifications starting from the analysis of medical reports and images, to offer significant support for the diagnosis and identification of therapies already applied in similar cases.
Use cases
We use AI assisted diagnosis in volumetric medical images like Lung lesions detection and classification, Brain tumour segmentation and survival estimation, Liver tumour segmentation, Colorectal tumour segmentation. and Advance Alzheimer’s Research with Stall Catchers
See use cases
A space dedicated to dissemination, training, inspiration. Follow our magazine to stay up to date on Artificial Intelligence and the new fields of digital technology.
R. Miron, M. Breaban
Revitalizing regression tasks through modern training procedures. Applications in Medical Image Analysis

This work describes an approach to estimate the percentage of COVID-19 specific infection within the lung tissue.

New achievements for SenticLab in lung cancer recognition

Senticlab has developed an AI-based solution to recognize tumoral nodules from chest radiographs, obtaining one of the best results in the NODE21 competition.

Another great result for SenticLab in the MIA-COV19D competition at ICCV 2021

SenticLab is the runner-up in the MIA-COV19D competition, thanks to a novel AI-based solution for detecting COVID-19 in CT images.

synbrAIn acquires SenticLab

After several years of collaboration, synbrAIn has acquired SenticLab, with the goal of supporting further growth of the entire company group.

R. Miron, C. Moisii, S. Dinu, M. Breaban
COVID Detection in Chest CTs: Improving the Baseline on COV19-CT-DB

This work presents a comparative analysis of three distinct approaches based on deep learning for COVID-19 detection in chest CTs.

SenticLab wins the ImageCLEFmed Tuberculosis competition!

SenticLab developed the best (and winning) solution for identifying tubercolosis within CT scans.

V. Gentile, M. Khamis, F. Milazzo, S. Sorce, A. Malizia, F. Alt
Predicting Mid-Air Gestural Interaction with Public Displays based on Audience Behaviour

This work shows how to build predictor models to forecast users’ interaction duration and distance when interacting via touchless mid-air gestures in public.

A. Chella, A. Pipitone, A. Morin, F. Racy
Developing Self-Awareness in Robots via Inner Speech

This article includes a review of psychological models for inner speech, and a cognitive architecture to implement such capability in robots.

C. Padurariu, M. E. Breaban
Dealing with Data Imbalance in Text Classification

This work investigates classification algorithms, text vectorization and schemes to deal with data imbalance, proposing a novel cost sensitive approach.

A. Pipino, F. Resta, L. Mangiagalli, M. De Matteis, H. Kroha, R. Richter, O. Kortner, A. Baschirotto
A 28 nm Bulk-CMOS Analog Front-End for High-Rate ATLAS Muon Drift-Tube Detectors

This work describes a 28nm Complementary Metal Oxide Semiconductor Analog Front-End for fast-tracking small-diameter Muon Drift-Tube detectors.

A. Chella, A. Pipitone
A cognitive architecture for inner speech

This work presents a novel cognitive architecture for inner speech, based on the Standard Model of Mind, integrated with modules for self-talking.

F. Milazzo, A. Augello, G. Pilato, V. Gentile, A. Gentile, S. Sorce
Exploiting Correlation between Body Gestures and Spoken Sentences for Real-time Emotion Recognition

This word exploits the correlation between user's affective state and the simultaneous body expressions, to automatically recognize emotions from gestures.

A. Pipitone, A. Chella
A Calculus for Robot Inner Speech and Self-Awareness

This work presents a calculus based on a first-order modal logic, attempting to make the existing inner speech theories suitable for robot.

C. Frăsinaru, M. Răschip
Greedy Best-First Search for the Optimal-Size Sorting Network Problem

This works consists in an effective algorithm for creating minimal-size sorting networks, based on incrementally constructing sets of sorting networks.

A. Muraro, G. Claps, G. Croci, F. Cordella, G. Gorini, G. Grosso, Z. Hu, L. Mangiagalli, O. McCormack, F. Murtasd, M. Nocentee, E. Perelli Cippoa, E. Panontine, M. Pedronia, M. Rebaia, D. Rigamontia, M. Tardocchia, D. Pacella
Development and characterization of a new soft x-ray diagnostic concept for tokamaks

This work describes a new SXR diagnostic system called EXODUS, based on the Gas Electron Multiplier technology coupled with a novel data acquisition system.

E. Rubegni, V. Gentile, A. Malizia, S. Sorce, N. Kargas
Child-display Interaction: Exploring Avatar-based Touchless Gestural Interfaces

This work studies children's interactions with large display via touchless avatar-based interface, investigating the impact of interactiong on learning.

V. I. Lupoaie, I. A. Chili, M. E. Breaban, M. Raschip
SOM-Guided Evolutionary Search for Solving MinMax Multiple-TSP

This paper uses Self Organizing Maps, Evolutionary Algorithms and Ant Colony Systems to tackle the MinMax formulation of the Single-Depot Multiple-TSP

V. Gentile, D. Fundarò, S. Sorce
Elicitation and evaluation of zoom gestures for touchless interaction with desktop displays

This work describes a touchless gesture elicitation and usability study to understand how to perform zoom actions while interacting with desktop displays.

S. Sorce, V. Gentile, D. Cascio, A. Giuliano, M. Tabacchi, V. Taormina, D. Tegolo, C. Valenti, G. Raso
A REST-based Framework to Support Non-Invasive and Early Coeliac Disease Diagnosis

This framework provides a web API to access and process data from coeliac patients, to be used also as a basis for diagnostic decision support systems.

V. Gentile, P. Elagroudy, E. Ergin, S. Clinch
Pervasive Displays Research: What's Next?

An overview of novel areas of interest in pervasive displays research, based on the works presented during the 7th ACM Intl. Symposium on Pervasive Displays.

C. Frăsinaru, M. Răschip
An Improved Subsumption Testing Algorithm for the Optimal-Size Sorting Network Problem

This work presents a new method that uses a bipartite graph for checking the subsumption relation for the optimal-size sorting network problem.

I. Pistol, D. Trandabăț, M. Răschip
Medi-Test: Generating Tests from Medical Reference Texts

Using medical reference texts supported by a specific ontology, we developed Medi-test, a system to generate medical questionnaires in Romanian language.

A. Pipitone, G. Tirone, R. Pirrone
Named Entity Recognition and Linking in Tweets Based on Linguistic Similarity

This work proposes a novel approach in Named Entity rEcognition and Linking (NEEL) in tweets, applying similar strategies used for Question Answering (QA).

V. Gentile
Touchless solutions for tertiary prevention

Touchless systems allow higher accessibility to information provision systems for patients with reduced mobility, thus improving tertiary prevention.

F. Milazzo, V. Gentile, A. Gentile, S. Sorce
KIND-DAMA: A modular middleware for Kinect-like device data management

KIND‐DAMA is a modular middleware for easing the development of interactive applications based on gestural input, applicable in a plethora of scenarios.

F. Milazzo, V. Gentile, S. Sorce, A. Gentile
Real-Time Body Gestures Recognition Using Training Set Constrained Reduction

This work presents a system able to recognize human body gestures implementing a constrained training set reduction technique, allowing for real-time execution.

M. Giardina, S. Tramonte, V. Gentile, S. Vinanzi, A. Chella, S. Sorce, R. Sorbello
Conveying Audience Emotions Through Humanoid Robot Gestures to an Orchestra During a Live Musical Exhibition

This work describes a system for conveying audience emotions during live musical exhibitions, controlling a humanoid robot based on mobile apps.

S. Timofeiov, M. Marinca, C. Bar, M. E. Breaban, V. Drug, V. Scripcariu
Conversion Rate to Resectability in Colorectal Cancer Liver Metastases: Need for Criteria Adapted to Current Therapy

This work aims at identifying the post-treatment time frame for confirming resectability or permanent unresectability in colorectal cancer liver metastases.

A. Pipitone, V. Cannella, R. Pirrone
I-ChatbIT : an intelligent chatbot for the Italian Language

This work presents a novel chatbot architecture for the Italian language, implementing cognitive understanding of queries and a suitable disambiguation strategy

S. Sorce, V. Gentile, A. Gentile
Real-Time Hand Pose Recognition Based on a Neural Network Using Microsoft Kinect

This paper describes how to use neural networks to detect in real time hand poses, based on data gathered from a Microsoft Kinect RGB-D sensor.

M. Breaban, H. Luchian
A unifying criterion for unsupervised clustering and feature selection

This work introduces an objective function for unsupervised clustering able to guide the search for significant features and optimal partitions.

A. Pipitone, R. Pirrone
A framework for automatic semantic annotation of Wikipedia articles

This paper presents a hierarchical framework for automatic semantic annotation of plain text, with the goal of converting wiki pages into semantic wikis.

M. Ionita, M. Breaban, C. Croitoru
A new scheme of using inference inside evolutionary computation techniques to solve CSPs

This work presents a general scheme based on a genetic algorithm and the particle swarm optimization heuristic to solve constraint satisfaction problems.

Go to Magazine
Where we are
You can find us in Iași, a university city located in the beating heart of Romania. A cultural center of excellence for the country, a privileged center for the study and development of advanced technologies.

Research is capable of aiming towards a future which we are currently building.
Come visit us!
Work with us
Technical skills are essential, but they are not enough for us.
We are looking for enthusiastic and persevering people who want to achieve high goals and change the world for the better through technology. Are you ready to join Sentic Lab? Fill in the form to send your application.