Andrey V. Matveev

To analyze images in various fields of science and technology, it is often necessary to count observed objects and determine their parameters. This can be quite labor‐intensive and time‐consuming. This article presents DLgram, a universal, user‐friendly cloud service that is developed for this purpose. It is based on deep learning technologies and does not require programming skills. The user labels several objects in the image and uploads it to the cloud where the neural network is trained to recognize the objects being studied. The user receives recognition results, which if necessary, can be corrected, errors removed, or missing objects added. In addition, it is possible to carry out mathematical processing of the data obtained to get information about the sizes, areas, and coordinates of the observed objects. The article describes the service features and discusses examples of its application. The DLgram service allows to reduce significantly the time spent on quantitative image analysis, reduce subjective factor influence, and increase the accuracy of analysis.Research Highlights: DLgram automatically recognizes and counts the number of objects in images and their parameters. DLgram is a universal service, which was created on the basis of the latest deep learning developments and does not require programming skills.

To analyze images in various fields of science and technology, it is often necessary to count observed objects and determine their parameters. This can be quite labor-intensive and time-consuming. This article presents DLgram, a universal, user-friendly cloud service that is developed for this purpose. It is based on deep learning technologies and does not require programming skills. The user labels several objects in the image and uploads it to the cloud where the neural network is trained to recognize the objects being studied. The user receives recognition results which, if necessary, can be corrected, errors removed, or missing objects added. In addition, it is possible to carry out mathematical processing of the data obtained to get information about the sizes, areas, and coordinates of the observed objects. The article describes the service features and discusses examples of its application. The DLgram service allows to reduce significantly the time spent on quantitative image analysis, reduce subjective factor influence, and increase the accuracy of analysis.

Phosphonic acids labeled with beta-emitting radionuclides are promising radiopharmaceutical drugs for palliative therapy of bone metastases. Currently, the possibility of using a new osteotropic compound N,N,N’,N’-ethylenediaminetetrakis (methylene phosphonic acid) with lutetium-177 (177Lu-EDTMP) is being studied. The aim of the work is to develop a compartment mathematical model of the kinetics of 177Lu labeled osteotropic radiopharmaceutical drugs in the body of laboratory animals and calculate their pharmacokinetic and dosimetric characteristics based on it. To assess the stability of 177Lu-EDTMP in vivo, the characteristics of the distribution of free lutetium in the form of 177LuCl3 were also studied. To identify the model parameters and calculate the characteristics of radiopharmaceutical drugs, quantitative data on the bio-distribution of 177Lu-EDTMP and 177LuCl3 in the body of intact Wistar rats were used. A compartment model of kinetics has been developed and two approaches to the identification of its transport constants have been proposed – through the residual functional and using approximation by monoexponential functions. According to pharmacokinetic modeling, it was found that 177Lu-EDTMP is deposited in bone tissues (up to 55% of the administered dose). The calculated value of the apparent volume of distribution of 177Lu-EDTMP is approximately 200 times greater than the volume of blood plasma, the values of biological half-lives from bone tissues are 10-20 times higher than from internal organs. The excretion of 177Lu-EDTMP from the body occurs mainly through renal clearance. Comparative modeling with 177LuCl3 revealed high resistance of 177Lu-EDTMP in vivo. The highest values of absorbed doses are formed in the skeleton and kidneys with minimal radiation load on other internal organs and blood. The results obtained indicate the prospects for further studies of 177Lu-EDTMP and the possibility of its clinical application for the treatment of skeletal metastases.

Recognition and measuring particles on microscopy images is an important part of many scientific studies, including catalytic investigations. In this paper, we present the results of the application of deep learning to the automated recognition of nanoparticles deposited on porous supports (heterogeneous catalysts) on images obtained by transmission electron microscopy (TEM). The Cascade Mask-RCNN neural network was used. During the training, two types of objects were labeled on raw TEM images of ‘real’ catalysts: visible particles and overlapping particle projections. The trained neural network recognized nanoparticles in the test dataset with 0.71 precision and 0.72 recall for both classes of objects and 0.84 precision and 0.79 recall for visible particles. The developed model is integrated into the open-access web service ‘ParticlesNN’, which can be used by any researcher in the world. Instead of hours, TEM data processing per one image analysis is reduced to a maximum of a couple of minutes and the divergence of mean particle size determination is approximately 2% compared to manual analysis. The proposed tool encourages accelerating catalytic research and improving the objectivity and accuracy of analysis.

Исследование материалов методами микроскопии нередко включает стадию подсчета количества наблюдаемых объектов и определения их статистических параметров, для чего необходимо измерять сотни объектов. В работе описан облачный сервис DLgram01, который позволяет специалистам в области материаловедения, не имеющих навыков программирования, выполнять автоматизированную обработку изображений - определять количество и параметры (площадь, размер) изучаемых объектов. Сервис разработан с использованием новейших достижений в области глубокого машинного обучения, для обучения нейронной сети пользователю необходимо разметить несколько изучаемых объектов. Обучение нейронной сети производится автоматически за несколько минут. Важными особенностями сервиса DLgram01 является возможность корректировать результаты предсказания нейронной сети, а также получение детальной информации о всех распознанных объектах. Использование сервиса позволяет существенно сократить временные затраты на количественный анализ изображений, снизить влияние субъективного фактора, повысить точность анализа и его эргоемкость. The study of materials by microscopy often includes counting the number of observed objects and determining their statistical parameters, for which it is necessary to measure hundreds of objects. The created DLgram01 cloud service allows specialists in the field of materials science who do not have programming skills to perform automated image processing - to determine the number and parameters (area, size) of the objects under study. The service is developed using the latest achievements in the field of deep machine learning. To train a neural network, the user needs to label only several objects. The neural network is trained automatically in a few minutes. Important features of the DLgram01 service are the ability to adjust the results of neural network prediction, as well as obtaining detailed information about all recognized objects. Using the service allows to significantly decrease the time for quantitative image analysis, reduce the influence of the subjective factor, increase the accuracy of the analysis and its ergo-intensity.

In various fields of microscopy, a fairly common task is to count and determine the size of the studied objects. Sometimes this is a one-time tedious task that is done by lab personnel without the programming skills. In this paper, we present an approach that allows researchers to perform automated processing of research imaging data using our services and even to train deep neural networks on their own in no code mode.

The task of the objects identification, counting, and measurement is a huge part of scientific investigations and technological applications. Automated methods using traditional processing such as segmentation, edge detection, and so on represented by available software (e.g. CellProfiler) are not flexible, can be used only with images of high-quality, and in addition require setting a part of parameters by hand. This contribution presents the applying the deep learning method for recognition of HeLa cells expressing green fluorescent protein (EGFP) automatically. We used Cascade Mask R-CNN neural networks which has a ResNeXt backbone and deformable convolutional networks layers. Training dataset contained seven pictures with 5754 labeled cells. Three images with 2469 labeled cells were used as test-dataset. The trained neural network showed mAP=0.4.

Identifying, counting and measuring particles is an important component of many research studies. Images with particles are usually processed by hand using a software ruler. Automated processing, based on conventional image processing methods (edge detection, segmentation, etc.) are not universal, can only be used on good-quality images and need to set a number of parameters empirically. In this paper, we present results from the application of deep learning to automated recognition of metal nanoparticles deposited on highly oriented pyrolytic graphite on images obtained by scanning tunneling microscopy (STM). We used the Cascade Mask-RCNN neural network. Training was performed on a dataset containing 23 STM images with 5157 nanoparticles. Three images containing 695 nanoparticles were used for verification. As a result, the trained neural network recognized nanoparticles in the verification set with 0.93 precision and 0.78 recall. Predicted contour refining with 2D Gaussian function was a proposed option. The accuracies for mean particle size calculated from predicted contours compared with ground truth were in the range of 0.87–0.99. The results were compared with outcomes from other generally available software, based on conventional image processing methods. The advantages of deep learning methods for automatic particle recognition were clearly demonstrated. We developed a free open-access web service “ParticlesNN” based on the trained neural network, which can be used by any researcher in the world.

This paper presents the results of laboratory tests and numerical simulation of polymer drilling fluids. The influence of the rotation speed on the values of the pressure ratio and cutting transport is studied. The influence of rheological parameters on the efficiency of cuttings transport is investigated.

Identifying and counting individual particles is an important component of many studies in various explorations. In the paper we present the results of the application of deep learning methods for the automated recognition of platinum nanoparticles deposited on highly oriented pyrolytic graphite (HOPG) on images obtained by scanning tunneling microscopy (STM). We used the neural network CascadeRCNN. The training was performed on a data set containing 10 STM images with 1918 nanoparticles. Five images containing 2052 nanoparticles were used for verification. As a result, the trained neural network recognized nanoparticles in verification set with 50.8% accuracy. Nanoparticles are specified as distinct contours, which are necessary for further determination of the particles dimensions (size, height etc). The obtained results were compared with the possibilities of other software products. The advantage of using deep machine learning methods for automatic particle recognition is clearly shown.