LRMT Ltd

For the first time in the world, a unique and innovative method of improving the accuracy of artificial intelligence prediction is proposed by two-stage and repeated training of a number of neural networks. Based on the proposed method, a computer program is proposed to help a radiologist automatically identify patients with asymptomatic, undetected chronic diseases, initiating earlier diagnosis and preventive treatment. This program will achieve stability and accuracy of predictions, even for images with high noise, low contrast and blurred boundaries of the objects being searched for. The pr

TRL 4 – technology validated in lab .
A program based on neural networks has been developed to classify X-ray images to detect straight and lateral projections of the thoracic section. On the direct projection the segmentation of heart and lungs for calculation of cardiothoracic index is carried out, and also presence of atherocalcinosis of carotid arteries is determined. The lateral projection is used to segment the vertebrae of the spine to determine the degree of osteoporosis.
On the basis of the developed technology a number of scientific papers have been published and a doctoral thesis has been defended.
To create a commercial program, certification (as a medical device) and advertising campaign, funding is needed.

The U.S. healthcare AI market is projected to grow from USD 2.9 billion in 2022 to USD 51.3 billion by 2030, at a compound annual growth rate (CAGR) of 43.22%, driven by the need for more efficient healthcare services and potential cost savings.
The global teleradiology market was estimated at USD 8.6 billion in 2023 and is expected to reach USD 29.8 billion by 2033.
The program is intended for medical institutions, enterprises that develop and manufacture X-ray medical diagnostic devices, as well as organizations that provide teleradiology services.

Diagnosis and evaluation of a compression fracture or determination of the cardiothoracic index from chest X-rays requires morphometric studies, which is a very long and laborious work of a radiologist.

The cardiothoracic index is the main indicator of cardiomegaly. If the pathology is not detected in time, the risk of heart failure increases and 50% of patients die within 5 years.

Identification of vertebral compression fractures can provide early treatment, as about 66% of compression fractures go unnoticed or are not recorded in the case of osteoporosis, which affects one in three women over the age of 50 and one in five men worldwide, according to the latest data from the International Osteoporosis Foundation.

Early diagnosis of carotid atherocarcinosis plays an important role in preventing ischemic stroke, which can result in 84-87% of patients dying or becoming disabled.

The proposed program based on artificial intelligence will allow:

- increase the number of patients with early detection of chronic diseases ;

- reduce the cost of treating chronic diseases;

- expand the capabilities of radiologists to quantify the signs of diseases;

- increase the attractiveness of a medical institution through advanced and innovative capabilities.

Company Nanox.AI (Israel) Lunit (South Korea) LRMT (Ukraine)

Type of X-ray
images computed tomography radiography radiography

Human organ
under study
spinal vertebrae , heart, lungs, vertebrae
heart , liver mammary glands of the spine,
heart, carotid
arteries Price of a license for
one year in Europe 49000 - 116000$ 60000$ 6200$
Price of examination
in teleradiology
for one study 1$ 0.6$ 0.12$

Price of a license for
one year in Ukraine - 5800$ 1200$

The developed artificial intelligence algorithm made it possible to achieve stability and accuracy of the neural network's predictions even for X-ray images with high noise, low contrast, and blurred boundaries of the objects to be searched.
This fundamentally distinguishes the developed algorithm from competitors' artificial intelligence algorithms developed for X-ray computed tomography (CT) or magnetic resonance imaging (MRI) images, which are characterized by high contrast and low noise, without overlaying images of human organs on top of each other.
The algorithm of the proposed program is very complex and has been developed over 3 years. The development of the program requires knowledge in the field of medical physics, neural networks and, of course, the ability to program in various computer languages.

Making money can go through three
channels :
- selling the program to medical institutions;
- selling the program as an OEM product to companies that develop and manufacture X-ray medical diagnostic equipment;
- selling the program to organizations that provide teleradiology services.

The team members will be paid $12600 for 6 months of work.
A senior researcher who will develop machine vision and neural network ensemble algorithms will be paid $800 per month.
A senior software engineer who will write the program's code and test it will be paid $800 per month.
The SMM Manager/Disigner, who will design the program's user interface and also run the marketing campaign, will be paid $500 per month.
To develop machine vision algorithms, neural network training, and the user interface, a personal high-performance computer with a large RAM is required. It is planned to spend $1,900 for this purpose.
The ScanAim.AI program is a medical device and therefore needs to be certified. This will cost $3000.
Administrative expenses, including office rent, telephone/internet, website maintenance, salaries for the director ($300 per month) and accountant ($200 per month), will cost $5100.
A marketing campaign (website development, advertising) is planned to cost $2,400.

The program sales strategy will be as follows:

1) The OEM version will be sold, on a one-time basis, to developers and manufacturers of X-ray diagnostic devices at a price of $15,000;
2) the version of the program for medical institutions will be sold in the form of a license for a year at a price of $ 1200. In case of license renewal for the next year, the price of the program will be reduced;
3) for organizations that provide teleradiology services, the price for processing one X-ray image will be $ 0.1.
Promotion channels:
Internet ,
medical exhibitions.
The success of the product will be determined by the number of sales of the program per year.

The team members will be paid $12600 for 6 months of work.
A senior researcher who will develop machine vision and neural network ensemble algorithms will be paid $800 per month.
A senior software engineer who will write the program's code and test it will be paid $800 per month.
The SMM Manager/Disigner, who will design the program's user interface and also run the marketing campaign, will be paid $500 per month.
To develop machine vision algorithms, neural network training, and the user interface, a personal high-performance computer with a large RAM is required. It is planned to spend $1,900 for this purpose.
The ScanAim.AI program is a medical device and therefore needs to be certified. This will cost $3000.
Administrative expenses, including office rent, telephone/internet, website maintenance, salaries for the director ($300 per month) and accountant ($200 per month), will cost $5100.
A marketing campaign (website development, advertising) is planned to cost $2,400.

20% of the company

Military action.

1. Koniukhov, V., Morgun, O. & Nemchenko, K. Impact of Preprocessing and Compar
ison of Neural Network Ensemble Methods for Segmentation of The Thoracic Spine
in X-Ray Images. Radio Electronics, Computer Science, Control, 102–112 (2024).
2. Koniukhov, V., Morgun, O. & Nemchenko, K. Multiple training of neural networks
for automatic spine segmentation. Bulletin of V.N. Karazin Kharkiv National Uni
versity, series Mathematical modeling. Information technology. Automated control
systems 2, 1–9 (2025).