Sirvi Autor "Papkov, Mikhail, juhendaja" järgi

Nüüd näidatakse 1 - 5 5

Deblurring of microscopic 3D spheroid images using GANs
(Tartu Ülikool, 2023) Krupovych, Denys; Fishman, Dmytro, juhendaja; Papkov, Mikhail, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Sferoidid on 3D rakkude agregaadid, mis on muutunud vähi ja ravimite avastamise uurimisel üha olulisemaks tänu nende võimele imiteerida reaalseid kasvaja mikrokeskkondi. Kuid sferoidne kujutamine esitab mitmeid väljakutseid nende keerulise struktuuri, ebakorrapärase kuju ja optiliste omaduste tõttu. Käesolevas töös katsetame süvaõppe lähenemisviise, et lahendada neid probleeme ja parandada sferoidipiltide kvaliteeti. Täpsemalt, me kasutame modifitseeritud U-Neti arhitektuuri ja generatiivseid võistlusvõrke (GAN-id), et genereerida kõrge resolutsiooniga sferoidipilte . Hindame oma lähenemist spheroidide andmestikele ja võrdleme juhendatud ja järelevalveta närvivõrgu arhitektuuride toimimist sferodipiltide hävitamiseks. Meie töö annab kasulikku teavet sferoidipiltide analüüsi edasiseks uurimiseks ning sellel on potentsiaalseid rakendusi vähi diagnoosimisel ja ravimite avastamisel.
Fast Fourier Convolutions in Self-Supervised Neural Networks for Image Denoising
(Tartu Ülikool, 2022) Ariva, Joonas; Papkov, Mikhail, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Quality of digital images depends on a multitude of environmental and equipment factors. In many cases our options for optimizing imaging conditions are limited, and the acquired images turn out to be corrupted with noise. Recently, denoising convolutional neural networks (CNN) have started to outperform classical denoising algorithms. If approached naively, these networks require a lot of pairs of noisy and clean images from the particular domain. In some fields (e.g. in biomedical imaging) it is hard to collect such data in abundance. This limitation has accelerated a research for self-supervised networks what can learn denoising just from noisy images alone. However, such networks’ performance could be constrained by the the limited receptive field of regular convolution. To mitigate this problem, a new modification for CNNs was proposed: Fast Fourier Convolution (FFC). Here, a global receptive field is achieved by using Fourier Transform and convolving spectral representation. Global perception field can help CNNs to better capture dependencies in image regions which are far apart. Given the ability of FFC to enhance multiple state-of-the-art classification neural networks, we hypothesize that denoising neural networks could also gain from its use. In this work, we design multiple approaches for incorporating FFC into self-supervised neural networks for image denoising. We evaluate these approaches on three diverse benchmark datasets and compare them with both supervised and self-supervised methods. We empirically show that FFC-enhanced denoising network achieves the state-of-theart results on character dataset and shows comparable level of performance for both grayscale and color natural images.
Improving Microscopy Image Segmentation with Object Detection
(Tartu Ülikool, 2021) Urukov, Dmytro; Papkov, Mikhail, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Automated analysis of microscopy images is an essential part of modern biological research. Recent advances in deep learning have greatly improved its quality and helped decrease the amount of time-consuming manual work during the experiments. Biologists are interested not only in the accurate detection of various objects (whole cells, cell organelles, tissue structures, etc.) but also in the high-quality segmentation of their shape. In this work, we address the problem of obtaining realistic instance segmentation masks from images with high object density. We show that combining segmentation and detection methods into a single image analysis pipeline helps efficiently separate overlapping objects and improves the segmentation quality. To reduce the complexity of this pipeline, we propose a novel CenterUNet multi-task neural network architecture that simultaneously performs object detection and semantic segmentation. We evaluate the performance of this architecture across several microscopy image domains and conduct a thorough ablation study to identify the necessary and sufficient combination of detection subtasks to solve the segmentation problem. We believe that the results of our research provide valuable insights and can help individual practitioners as well as the image analysis industry. Our developed model may improve microscopy image segmentation pipelines at virtually zero computational cost and little integration efforts.
Reducing the Effect of Incomplete Annotations in Object Detection for Histopathology
(Tartu Ülikool, 2023) Kaliuzhnyi, Denys; Papkov, Mikhail, juhendaja; Fishman, Dmytro, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Histopathology is a crucial component of clinical practice involving microscopic tissue examination. Typically, pathologists manually analyse tissue to locate and label structural units, cells, and organoids. The properties and quantity of these objects can indicate a patient’s condition, e.g., the presence of tumours. Recent advancements in artificial intelligence (AI) have created the potential to automate this process. However, AI methods either provide limited accuracy or require a lot of densely annotated data, which is prohibitively time-consuming and expensive in the histopathology domain due to high object density and labelling difficulty. In this study, we address the challenge of training object detection neural networks on histology data with incomplete annotations. We demonstrate that hyperparameter tuning can mitigate the negative effects of sparsely labelled data. Additionally, we propose a novel model component called the Generalised Background Recalibration Loss to further improve detection rates. It can be adapted to a broader class of object detection models than previous solutions. Our results should facilitate the development of object detection neural networks for histology images by demonstrating the efficient use of sparsely labelled data. Our method reduces the impact of missing annotations on detection rates and thereby eases the most time-consuming aspect of data preparation for neural network training.
Self-Supervised Image Denoising Using Transformers
(Tartu Ülikool, 2023) Chizhov, Pavel; Papkov, Mikhail, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Piltide mürapuhastus juhendamata viisil on masinnägemise ülesanne mille puhul ei ole võimalik mudeli treenimiseks kasutada müravabu pilte. Selline meetodika on olululine mitmetes valdkondades nagu näiteks meditsiiniline kujutamine, kus tihti ei ole võimalik müravabu pilte koguda. Juhendamata mürapuhastuse muudabki keeruliseks müravabade pildite puudumine ja seega vajab see mudelispetsiifilist lähenemist. Kaasaegsed mürapuhastus lahendused põhinevad peamiselt sidumnärvivõrkudel ja väga vähe on uuritud kuidas transformerid selle ülesandega hakkama saavad. Sellest lähtuvalt kohandatakse magistritöös olemasolevaid pildi taastamise transformereid juhendamata mürapuhastuse ülesande jaoks ja võrreldakse neid vastavate sidumnärvivõrkudega. Peale selle kirjeldatakse töös uudset autokodeerijaga transformeri arhitektuuri, mis hoolimata müratüübist saavutab stabiilsemaid tulemusi kui muud mudelid. Samuti on see esimene ‘end-to-end’ juhendamata mürapuhastuse närvivõrk, mis ei kasuta ühtegi sidumoperatsiooni. Käesolev magistritöö toob välja transformerite eelised ja puudused mürapuhastuse ülesande kontekstis ja loob kontseptuaalse aluse valdkonna edasiseks arenguks.