Health is most important of all, so when illness strikes, action needs to be taken as soon as possible, especially if cancer is involved. Early diagnosis can affect the entire course of treatment, which is why we at Brain:IT, together with the St. Elizabeth’s Cancer Institute, have helped to create software that helps pathologists to accurately detect and evaluate the status and progress of tumor growth – proliferative activity.
The St. Elizabeth Oncology Institute is a modern medical facility that serves the needs of oncology patients from all over Slovakia. There are 7 bedded wards in the Oncological Institute of St. Elizabeth: surgical, oncogynecological, maxillo-facial surgery, intensive care, internal medicine, radiotherapy and nuclear medicine. The Institute’s laboratories are one of the few departments in the Slovak Republic accredited for the entire European Union.
The St. Elizabeth Cancer Institute invests in the acquisition of new diagnostic and treatment equipment, as well as in the further improvement of patient care. We at BRAIN:IT are also helping this development to move forward thanks to a project that we have created together with the SEOI.
Lenght of the project
Size of the project
Artificial Intelligence in Digital Pathology
Healthcare is one of the areas where artificial intelligence has a wide range of applications. Wherever objectivity and efficiency in medical data processing is required in evaluation and decision making, there is a suitable place for an AI-enabled support tool.
The anticipated benefit of the research is to improve the quality of the pathologist’s diagnosis. Assisting patients with obtaining the most accurate results in the shortest possible time. Developing software/application that will help pathologists to accurately detect and evaluate the status and progression of tumor growth – proliferative activity. Thus, the developed application will determine the exact percentage of positive tumor cells out of the total number of tumor cells, disregarding elements such as stroma, lymphocytes or other artifacts.
The primary goal of the project is to develop a computer program that, with the help of artificial intelligence, analyzes from a digital photograph taken from a histological specimen the percentage of positive cells in a selected immunohistochemical staining. This program is used by pathologists as a support tool in the quantification of immunohistochemical staining markers in tumor tissue samples, in routine biopsy practice. This will increase the accuracy of the quantitative parameters assessed in immunohistochemical stains as well as relieve the evaluating pathologists from time-consuming processes that are evaluated in seconds with the assistance of artificial intelligence.
These are some of the advantages of our ANNA software to help pathologists with sample evaluation. The results will be faster, more objective and more accurate.
More treated patients
application saves time, allowing pathologists to diagnose more patients
ensures objectivity, as its output is an accurate result and not a subjective estimate
Eliminate error rate
elimination of errors that may affect the final diagnosis
Motivation - the customer's problem
According to a survey of SEOI experts, software solutions already exist for the problem of sample evaluation, but they are very expensive and do not achieve satisfactory results. Therefore, SEOI n cooperation with Brain:IT agreed on a contractual cooperation to develop a computer program/software to solve the problem using artificial intelligence.
- Time-consuming analysis of quantitative parameters evaluated in immunohistochemical staining.
- Poor accuracy for quantitative parameters.
- Counting of mitotic figures in the tumor manually by the pathologist.
- Evaluation of the presence of micrometastases in lymph nodes.
- Screening of cytological samples.
The solution to the problem described above would be fully functional software that helps pathologists determine the stage of cancer. We at Brain:IT have therefore developed the ANNA software, which offers a module for quantitative and semi-quantitative evaluation of immunohistochemical staining of nuclear markers. It can determine the percentage of positive tumor cells from staining, without counting other cellular elements present.
How proliferation activity assessment works
Our ANNA application, which was developed in collaboration with the St. Elisabeth Cancer Institute in Bratislava is a decision support tool that helps the pathologist to accurately detect and evaluate the status and progression of tumor growth – proliferative activity. Assessment of proliferative activity in patient samples is performed by immunohistochemical staining of nuclear markers (assessment of the proliferation index using Ki-67). These pre-processed samples are scanned by a digital microscope into electronic form and the digital image obtained is then processed by artificial intelligence, which detects the presence and quantity of tumour cells in the background. The application thus determines the exact percentage of positive tumour cells out of the total number of tumour cells, disregarding elements that do not belong to tumour cells, such as stroma, lymphocytes or other artefacts.
ANNA – Artifical Neural Nurse Assistant
There are several modules developed for the ANNA system that it can work with. They are:
- ANNA Micro-metastasis – Module for detection of micro-metastases in lymph nodes
- ANNA Mitotic – Module for monitoring mitotic activity in tumours
- ANNA Cytological – Module for evaluation of cytology results
All modules serve similarly as a decision support tool, with the aim of minimizing the tedious manual work of doctors/pathologists, which will increase the efficiency of examinations and bring time savings. The processing and evaluation works in the same way as for proliferation assessment, images/scans are created and further evaluated by artificial intelligence.
- Determination of the exact percentage of positive tumor cells out of the total number of tumor cells from immunohistochemical staining.
- 60% more time saved
- 30% more patients examined
- Large increase in accuracy of quantitative parameters evaluated in immunohistochemical staining
Benefits of ANNA
New approach compared to traditional visual assessment:
- brings objectivity to the assessment
- increases sample processing efficiency
- creates time savings, possibility to diagnose a larger number of patients
- eliminates human error (fatigue, inattention)
- does not require sophisticated hardware