Better&Faster Cancer Diagnosis = Medical Images + Deep Learning
Cancer Center applies deep learning techniques to the field of oncology/radiology. It has amassed a huge training set of medical images along with categorization technology that will allow computers to predict multiple diseases with better-than-human accuracy. Our solutions (API and web platform) is to offer better access to the second and third diagnosis of cancer to medical professionals and directly to patients by providing a data exchange platform stuffed with machine learning algorithms that speed up and improve the accuracy of the medical image analyses.
Don’t waste your time! Let us do the work! We can segment images, find regions of interest, provide statistical descriptions of images, count cells, mitosis or even recognize their kind.
Don’t hesitate, just save lives.
- Machine Learning / Deep Learning
- Automated Medical Image Analysis
- MRI (Magnetic Resonance Imaging)
- PET / CT
- Pathology Images (Whole Slide Imaging)
- General planimetry
MRI, DICOM Analysis
It is one of the most important and most profitable diagnostic tools. Not only this medical imaging modality is not invasive but also can be applied in many different scenarios, obtaining images of pretty much every part of the human body. In case of the prostate cancer, our software/deep learning algorithms can be used to find Region of Interest (ROI), cancer segmentation automatically.
In terms of precision, there are no better methods of seeing a single tissue as… to examine the tissue under the microscope. Every histopathologist would agree that sometimes finding the most descriptive part of the slide is a harder task than it is to make the diagnosis itself. Fortunately it is not a problem for us. We can localize the most important parts of the slide, what is more we can extract the very factors that influence diagnostic models the most.
In oncology, Positron Emission Tomography (PET) imaging is widely used in diagnostics of cancer metastases, in monitoring of progress in course of the cancer treatment, and in planning radiotherapeutic interventions. Accurate and reproducible delineation of the tumor in the PET scans remains a difficult task, despite being crucial for delivering appropriate radiation dose, minimizing adverse side-effects of the therapy, and reliable evaluation of treatment. Our aim is to provide clinicians with intelligent software supporting accurate, efficient and reproducible delineation of the tumor.
Our paper published: Machine learning methods for accurate delineation of tumors in PET images Jakub Czakon, Filip Drapejkowski, Grzegorz Zurek, Piotr Giedziun, Jacek Zebrowski, Witold Dyrka (Submitted on 29 Oct 2016) In oncology, Positron Emission Tomography imaging...
It's good news: Our team won PET segmentation challenge using a data management and processing infrastructure! Automated segmentation of PET images for the delineation of tumor volumes has been the focus of intense research efforts for the last few years. There has...
Our team have released our new software package for tumor delineation in PET images. It can be found at github.com/stermedia/SterSEG. Package has been developed in python.