How it works

Artificial Intelligence

Image classification and testing is performed with high specificity and precision

Fast response time

The analysis takes only 3 minutes, as it is performed on our HPE Memory Driven Computing server

Large database for clinical studies

Radiolytx represents one of the largest currently available databases for the study of advanced clinical images.

Extendable

Radiolytx is currently focusing on lung cancer, prostate cancer and Alzheimer's Disease. However, the AI based on Neural Networks can be trained for the classification of other cancer types, provided a sufficient training sample is available.

1.

The user uploads the image (PET, CT, MRI) in DICOM format.

2.

Region Of Interest selection tools are available for a proper segmentation.

3.

Biomarkers are extracted for clinical applications and follow up

4.

Within few minutes images are compared with the ones already available in the RADIOLYTX database

5.

Identify the staging of the cancers, the probability of methastasis or the early diagnosis of Alzheimer's Disease

RADIOLYTX is a new clinical tool

Our software includes all the features of the common frameworks used nowadays by specialists clinicians dealing with medical images, allowing a visualization of the patients in a user-friendly environment. It naturally adds the radiomics analysis to the platform, visualizing these features which are not identifiable with the doctor’s eye. The radiomics parameters are extended with blood biomarkers and digital health records in a unique digital ID, the Radyolitx Patient ID.

CLINICAL EXPERIENCE

Bring radiomics at reach of the clinicians

Personalized diagnosis

For each patient a personalized diagnostic path

A new market

Radiomics for new digital imaging biomarkers

Creative Solution

Artificial Intelligence modeling for early diagnosis

Is Radiolytx right for your clinics?

A series of keywords are extracted from the anamnesis text.

A series of 630 metabolomic quantities are extracted from blood analysis

A Convolutional Neural Network (CNN) with inputs the key-words and the selected principal components is used as a classifier of patients with risk of PD. We identify possible patterns in the data of subclinical patients in common with early PD subjects.

If NO Risk for PD is detected, the medical doctor can take as granted the result for further diagnosis

If a risk for PD is detected, [18F]-DOPA PET scan is recommended. We extract textural features from the PET image and We identify possible patterns in the data of subclinical patients in common with early PD subjects.

The final result is a risk assessment for PD for a patient in subclinical condition, showing only generic non-specific symptoms (keywords).