Mikhail Belyaev

Mikhail Goncharov, Vera Soboleva, Anvar Kurmukov et al.

This paper introduces vox2vec - a contrastive method for self-supervised learning (SSL) of voxel-level representations. vox2vec representations are modeled by a Feature Pyramid Network (FPN): a voxel representation is a concatenation of the corresponding feature vectors from different pyramid levels. The FPN is pre-trained to produce similar representations for the same voxel in different augmented contexts and distinctive representations for different voxels. This results in unified multi-scale representations that capture both global semantics (e.g., body part) and local semantics (e.g., different small organs or healthy versus tumor tissue). We use vox2vec to pre-train a FPN on more than 6500 publicly available computed tomography images. We evaluate the pre-trained representations by attaching simple heads on top of them and training the resulting models for 22 segmentation tasks. We show that vox2vec outperforms existing medical imaging SSL techniques in three evaluation setups: linear and non-linear probing and end-to-end fine-tuning. Moreover, a non-linear head trained on top of the frozen vox2vec representations achieves competitive performance with the FPN trained from scratch while having 50 times fewer trainable parameters. The code is available at https://github.com/mishgon/vox2vec .

Ekaterina Kondrateva, Polina Druzhinina, Alexandra Dalechina et al.

Magnetic resonance imaging (MRI) data is heterogeneous due to differences in device manufacturers, scanning protocols, and inter-subject variability. A conventional way to mitigate MR image heterogeneity is to apply preprocessing transformations such as anatomy alignment, voxel resampling, signal intensity equalization, image denoising, and localization of regions of interest. Although a preprocessing pipeline standardizes image appearance, its influence on the quality of image segmentation and on other downstream tasks in deep neural networks has never been rigorously studied. We conduct experiments on three publicly available datasets and evaluate the effect of different preprocessing steps in intra- and inter-dataset training scenarios. Our results demonstrate that most popular standardization steps add no value to the network performance; moreover, preprocessing can hamper model performance. We suggest that image intensity normalization approaches do not contribute to model accuracy because of the reduction of signal variance with image standardization. Finally, we show that the contribution of skull-stripping in data preprocessing is almost negligible if measured in terms of estimated tumor volume. We show that the only essential transformation for accurate deep learning analysis is the unification of voxel spacing across the dataset. In contrast, inter-subjects anatomy alignment in the form of non-rigid atlas registration is not necessary and intensity equalization steps (denoising, bias-field correction and histogram matching) do not improve models' performance. The study code is accessible online https://github.com/MedImAIR/brain-mri-processing-pipeline

Mikhail Goncharov, Valentin Samokhin, Eugenia Soboleva et al.

We propose a self-supervised model producing 3D anatomical positional embeddings (APE) of individual medical image voxels. APE encodes voxels' anatomical closeness, i.e., voxels of the same organ or nearby organs always have closer positional embeddings than the voxels of more distant body parts. In contrast to the existing models of anatomical positional embeddings, our method is able to efficiently produce a map of voxel-wise embeddings for a whole volumetric input image, which makes it an optimal choice for different downstream applications. We train our APE model on 8400 publicly available CT images of abdomen and chest regions. We demonstrate its superior performance compared with the existing models on anatomical landmark retrieval and weakly-supervised few-shot localization of 13 abdominal organs. As a practical application, we show how to cheaply train APE to crop raw CT images to different anatomical regions of interest with 0.99 recall, while reducing the image volume by 10-100 times. The code and the pre-trained APE model are available at https://github.com/mishgon/ape .

Alexey Zakharov, Maxim Pisov, Alim Bukharaev et al.

Vertebral body compression fractures are early signs of osteoporosis. Though these fractures are visible on Computed Tomography (CT) images, they are frequently missed by radiologists in clinical settings. Prior research on automatic methods of vertebral fracture classification proves its reliable quality; however, existing methods provide hard-to-interpret outputs and sometimes fail to process cases with severe abnormalities such as highly pathological vertebrae or scoliosis. We propose a new two-step algorithm to localize the vertebral column in 3D CT images and then detect individual vertebrae and quantify fractures in 2D simultaneously. We train neural networks for both steps using a simple 6-keypoints based annotation scheme, which corresponds precisely to the current clinical recommendation. Our algorithm has no exclusion criteria, processes 3D CT in 2 seconds on a single GPU, and provides an interpretable and verifiable output. The method approaches expert-level performance and demonstrates state-of-the-art results in vertebrae 3D localization (the average error is 1 mm), vertebrae 2D detection (precision and recall are 0.99), and fracture identification (ROC AUC at the patient level is up to 0.96). Our anchor-free vertebra detection network shows excellent generalizability on a new domain by achieving ROC AUC 0.95, sensitivity 0.85, specificity 0.9 on a challenging VerSe dataset with many unseen vertebra types.

Farukh Yaushev, Daria Nogina, Valentin Samokhin et al.

Understanding body part geometry is crucial for precise medical diagnostics. Curves effectively describe anatomical structures and are widely used in medical imaging applications related to cardiovascular, respiratory, and skeletal diseases. Traditional curve detection methods are often task-specific, relying heavily on domain-specific features, limiting their broader applicability. This paper introduces a novel approach for detecting non-branching curves, which does not require prior knowledge of the object's orientation, shape, or position. Our method uses neural networks to predict (1) an attraction field, which offers subpixel accuracy, and (2) a closeness map, which limits the region of interest and essentially eliminates outliers far from the desired curve. We tested our curve detector on several clinically relevant tasks with diverse morphologies and achieved impressive subpixel-level accuracy results that surpass existing methods, highlighting its versatility and robustness. Additionally, to support further advancements in this field, we provide our private annotations of aortic centerlines and masks, which can serve as a benchmark for future research. The dataset can be found at https://github.com/neuro-ml/curve-detection.

Anton Vasiliuk, Daria Frolova, Mikhail Belyaev et al.

Detecting out-of-distribution (OOD) samples for trusted medical image segmentation remains a significant challenge. The critical issue here is the lack of a strict definition of abnormal data, which often results in artificial problem settings without measurable clinical impact. In this paper, we redesign the OOD detection problem according to the specifics of volumetric medical imaging and related downstream tasks (e.g., segmentation). We propose using the downstream model's performance as a pseudometric between images to define abnormal samples. This approach enables us to weigh different samples based on their performance impact without an explicit ID/OOD distinction. We incorporate this weighting in a new metric called Expected Performance Drop (EPD). EPD is our core contribution to the new problem design, allowing us to rank methods based on their clinical impact. We demonstrate the effectiveness of EPD-based evaluation in 11 CT and MRI OOD detection challenges.

Anton Vasiliuk, Daria Frolova, Mikhail Belyaev et al.

When applying a Deep Learning model to medical images, it is crucial to estimate the model uncertainty. Voxel-wise uncertainty is a useful visual marker for human experts and could be used to improve the model's voxel-wise output, such as segmentation. Moreover, uncertainty provides a solid foundation for out-of-distribution (OOD) detection, improving the model performance on the image-wise level. However, one of the frequent tasks in medical imaging is the segmentation of distinct, local structures such as tumors or lesions. Here, the structure-wise uncertainty allows more precise operations than image-wise and more semantic-aware than voxel-wise. The way to produce uncertainty for individual structures remains poorly explored. We propose a framework to measure the structure-wise uncertainty and evaluate the impact of OOD data on the model performance. Thus, we identify the best UE method to improve the segmentation quality. The proposed framework is tested on three datasets with the tumor segmentation task: LIDC-IDRI, LiTS, and a private one with multiple brain metastases cases.

Stanislav Shimovolos, Andrey Shushko, Mikhail Belyaev et al.

Deep learning methods provide significant assistance in analyzing coronavirus disease (COVID-19) in chest computed tomography (CT) images, including identification, severity assessment, and segmentation. Although the earlier developed methods address the lack of data and specific annotations, the current goal is to build a robust algorithm for clinical use, having a larger pool of available data. With the larger datasets, the domain shift problem arises, affecting the performance of methods on the unseen data. One of the critical sources of domain shift in CT images is the difference in reconstruction kernels used to generate images from the raw data (sinograms). In this paper, we show a decrease in the COVID-19 segmentation quality of the model trained on the smooth and tested on the sharp reconstruction kernels. Furthermore, we compare several domain adaptation approaches to tackle the problem, such as task-specific augmentation and unsupervised adversarial learning. Finally, we propose the unsupervised adaptation method, called F-Consistency, that outperforms the previous approaches. Our method exploits a set of unlabeled CT image pairs which differ only in reconstruction kernels within every pair. It enforces the similarity of the network hidden representations (feature maps) by minimizing mean squared error (MSE) between paired feature maps. We show our method achieving 0.64 Dice Score on the test dataset with unseen sharp kernels, compared to the 0.56 Dice Score of the baseline model. Moreover, F-Consistency scores 0.80 Dice Score between predictions on the paired images, which almost doubles the baseline score of 0.46 and surpasses the other methods. We also show F-Consistency to better generalize on the unseen kernels and without the specific semantic content, e.g., presence of the COVID-19 lesions.

Daria Frolova, Anton Vasiliuk, Mikhail Belyaev et al.

Deep Learning (DL) models tend to perform poorly when the data comes from a distribution different from the training one. In critical applications such as medical imaging, out-of-distribution (OOD) detection helps to identify such data samples, increasing the model's reliability. Recent works have developed DL-based OOD detection that achieves promising results on 2D medical images. However, scaling most of these approaches on 3D images is computationally intractable. Furthermore, the current 3D solutions struggle to achieve acceptable results in detecting even synthetic OOD samples. Such limited performance might indicate that DL often inefficiently embeds large volumetric images. We argue that using the intensity histogram of the original CT or MRI scan as embedding is descriptive enough to run OOD detection. Therefore, we propose a histogram-based method that requires no DL and achieves almost perfect results in this domain. Our proposal is supported two-fold. We evaluate the performance on the publicly available datasets, where our method scores 1.0 AUROC in most setups. And we score second in the Medical Out-of-Distribution challenge without fine-tuning and exploiting task-specific knowledge. Carefully discussing the limitations, we conclude that our method solves the sample-level OOD detection on 3D medical images in the current setting.

Boris Shirokikh, Anvar Kurmukov, Mariia Donskova et al.

Domain shift presents a significant challenge in applying Deep Learning to the segmentation of 3D medical images from sources like Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). Although numerous Domain Adaptation methods have been developed to address this issue, they are often evaluated under impractical data shift scenarios. Specifically, the medical imaging datasets used are often either private, too small for robust training and evaluation, or limited to single or synthetic tasks. To overcome these limitations, we introduce a M3DA /"mEd@/ benchmark comprising four publicly available, multiclass segmentation datasets. We have designed eight domain pairs featuring diverse and practically relevant distribution shifts. These include inter-modality shifts between MRI and CT and intra-modality shifts among various MRI acquisition parameters, different CT radiation doses, and presence/absence of contrast enhancement in images. Within the proposed benchmark, we evaluate more than ten existing domain adaptation methods. Our results show that none of them can consistently close the performance gap between the domains. For instance, the most effective method reduces the performance gap by about 62% across the tasks. This highlights the need for developing novel domain adaptation algorithms to enhance the robustness and scalability of deep learning models in medical imaging. We made our M3DA benchmark publicly available: https://github.com/BorisShirokikh/M3DA.

Boris Shirokikh, Alexey Shevtsov, Anvar Kurmukov et al.

Target imbalance affects the performance of recent deep learning methods in many medical image segmentation tasks. It is a twofold problem: class imbalance - positive class (lesion) size compared to negative class (non-lesion) size; lesion size imbalance - large lesions overshadows small ones (in the case of multiple lesions per image). While the former was addressed in multiple works, the latter lacks investigation. We propose a loss reweighting approach to increase the ability of the network to detect small lesions. During the learning process, we assign a weight to every image voxel. The assigned weights are inversely proportional to the lesion volume, thus smaller lesions get larger weights. We report the benefit from our method for well-known loss functions, including Dice Loss, Focal Loss, and Asymmetric Similarity Loss. Additionally, we compare our results with other reweighting techniques: Weighted Cross-Entropy and Generalized Dice Loss. Our experiments show that inverse weighting considerably increases the detection quality, while preserves the delineation quality on a state-of-the-art level. We publish a complete experimental pipeline for two publicly available datasets of CT images: LiTS and LUNA16 (https://github.com/neuro-ml/inverse_weighting). We also show results on a private database of MR images for the task of multiple brain metastases delineation.

Valentin Samokhin, Boris Shirokikh, Mikhail Goncharov et al.

Radiography Report Generation (RRG) has gained significant attention in medical image analysis as a promising tool for alleviating the growing workload of radiologists. However, despite numerous advancements, existing methods have yet to achieve the quality required for deployment in real-world clinical settings. Meanwhile, large Visual Language Models (VLMs) have demonstrated remarkable progress in the general domain by adopting training strategies originally designed for Large Language Models (LLMs), such as alignment techniques. In this paper, we introduce a model-agnostic framework to enhance RRG accuracy using Direct Preference Optimization (DPO). Our approach leverages random contrastive sampling to construct training pairs, eliminating the need for reward models or human preference annotations. Experiments on supplementing three state-of-the-art models with our Random DPO show that our method improves clinical performance metrics by up to 5%, without requiring any additional training data.

Mikhail Goncharov, Eugenia Soboleva, Mariia Donskova et al.

Accurate detection of all pathological findings in 3D medical images remains a significant challenge, as supervised models are limited to detecting only the few pathology classes annotated in existing datasets. To address this, we frame pathology detection as an unsupervised visual anomaly segmentation (UVAS) problem, leveraging the inherent rarity of pathological patterns compared to healthy ones. We enhance the existing density-based UVAS framework with two key innovations: (1) dense self-supervised learning for feature extraction, eliminating the need for supervised pretraining, and (2) learned, masking-invariant dense features as conditioning variables, replacing hand-crafted positional encodings. Trained on over 30,000 unlabeled 3D CT volumes, our fully self-supervised model, Screener, outperforms existing UVAS methods on four large-scale test datasets comprising 1,820 scans with diverse pathologies. Furthermore, in a supervised fine-tuning setting, Screener surpasses existing self-supervised pretraining methods, establishing it as a state-of-the-art foundation for pathology segmentation. The code and pretrained models will be made publicly available.

David Li, Anvar Kurmukov, Mikhail Goncharov et al.

Recent advances in deep learning have shown that learning robust feature representations is critical for the success of many computer vision tasks, including medical image segmentation. In particular, both transformer and convolutional-based architectures have benefit from leveraging pretext tasks for pretraining. However, the adoption of pretext tasks in 3D medical imaging has been less explored and remains a challenge, especially in the context of learning generalizable feature representations. We propose a novel pretraining strategy using diffusion models with anatomical guidance, tailored to the intricacies of 3D medical image data. We introduce an auxiliary diffusion process to pretrain a model that produce generalizable feature representations, useful for a variety of downstream segmentation tasks. We employ an additional model that predicts 3D universal body-part coordinates, providing guidance during the diffusion process and improving spatial awareness in generated representations. This approach not only aids in resolving localization inaccuracies but also enriches the model's ability to understand complex anatomical structures. Empirical validation on a 13-class organ segmentation task demonstrate the effectiveness of our pretraining technique. It surpasses existing restorative pretraining methods in 3D medical image segmentation by $7.5\%$, and is competitive with the state-of-the-art contrastive pretraining approach, achieving an average Dice coefficient of 67.8 in a non-linear evaluation scenario.

Anvar Kurmukov, Valeria Chernina, Regina Gareeva et al.

Interpretation of chest computed tomography (CT) is time-consuming. Previous studies have measured the time-saving effect of using a deep-learning-based aid (DLA) for CT interpretation. We evaluated the joint impact of a multi-pathology DLA on the time and accuracy of radiologists' reading. 40 radiologists were randomly split into three experimental arms: control (10), who interpret studies without assistance; informed group (10), who were briefed about DLA pathologies, but performed readings without it; and the experimental group (20), who interpreted half studies with DLA, and half without. Every arm used the same 200 CT studies retrospectively collected from BIMCV-COVID19 dataset; each radiologist provided readings for 20 CT studies. We compared interpretation time, and accuracy of participants diagnostic report with respect to 12 pathological findings. Mean reading time per study was 15.6 minutes [SD 8.5] in the control arm, 13.2 minutes [SD 8.7] in the informed arm, 14.4 [SD 10.3] in the experimental arm without DLA, and 11.4 minutes [SD 7.8] in the experimental arm with DLA. Mean sensitivity and specificity were 41.5 [SD 30.4], 86.8 [SD 28.3] in the control arm; 53.5 [SD 22.7], 92.3 [SD 9.4] in the informed non-assisted arm; 63.2 [SD 16.4], 92.3 [SD 8.2] in the experimental arm without DLA; and 91.6 [SD 7.2], 89.9 [SD 6.0] in the experimental arm with DLA. DLA speed up interpretation time per study by 2.9 minutes (CI95 [1.7, 4.3], p<0.0005), increased sensitivity by 28.4 (CI95 [23.4, 33.4], p<0.0005), and decreased specificity by 2.4 (CI95 [0.6, 4.3], p=0.13). Of 20 radiologists in the experimental arm, 16 have improved reading time and sensitivity, two improved their time with a marginal drop in sensitivity, and two participants improved sensitivity with increased time. Overall, DLA introduction decreased reading time by 20.6%.

Aleksei Leonov, Aleksei Zakharov, Sergey Koshelev et al.

Automatic ribs segmentation and numeration can increase computed tomography assessment speed and reduce radiologists mistakes. We introduce a model for multilabel ribs segmentation with hierarchical loss function, which enable to improve multilabel segmentation quality. Also we propose postprocessing technique to further increase labeling quality. Our model achieved new state-of-the-art 98.2% label accuracy on public RibSeg v2 dataset, surpassing previous result by 6.7%.

Boris Shirokikh, Alexandra Dalechina, Alexey Shevtsov et al.

We systematically evaluate a Deep Learning (DL) method in a 3D medical image segmentation task. Our segmentation method is integrated into the radiosurgery treatment process and directly impacts the clinical workflow. With our method, we address the relative drawbacks of manual segmentation: high inter-rater contouring variability and high time consumption of the contouring process. The main extension over the existing evaluations is the careful and detailed analysis that could be further generalized on other medical image segmentation tasks. Firstly, we analyze the changes in the inter-rater detection agreement. We show that the segmentation model reduces the ratio of detection disagreements from 0.162 to 0.085 (p < 0.05). Secondly, we show that the model improves the inter-rater contouring agreement from 0.845 to 0.871 surface Dice Score (p < 0.05). Thirdly, we show that the model accelerates the delineation process in between 1.6 and 2.0 times (p < 0.05). Finally, we design the setup of the clinical experiment to either exclude or estimate the evaluation biases, thus preserve the significance of the results. Besides the clinical evaluation, we also summarize the intuitions and practical ideas for building an efficient DL-based model for 3D medical image segmentation.

Talgat Saparov, Anvar Kurmukov, Boris Shirokikh et al.

Domain shift is one of the most salient challenges in medical computer vision. Due to immense variability in scanners' parameters and imaging protocols, even images obtained from the same person and the same scanner could differ significantly. We address variability in computed tomography (CT) images caused by different convolution kernels used in the reconstruction process, the critical domain shift factor in CT. The choice of a convolution kernel affects pixels' granularity, image smoothness, and noise level. We analyze a dataset of paired CT images, where smooth and sharp images were reconstructed from the same sinograms with different kernels, thus providing identical anatomy but different style. Though identical predictions are desired, we show that the consistency, measured as the average Dice between predictions on pairs, is just 0.54. We propose Filtered Back-Projection Augmentation (FBPAug), a simple and surprisingly efficient approach to augment CT images in sinogram space emulating reconstruction with different kernels. We apply the proposed method in a zero-shot domain adaptation setup and show that the consistency boosts from 0.54 to 0.92 outperforming other augmentation approaches. Neither specific preparation of source domain data nor target domain data is required, so our publicly released FBPAug can be used as a plug-and-play module for zero-shot domain adaptation in any CT-based task.

Ivan Zakazov, Boris Shirokikh, Alexey Chernyavskiy et al.

Domain Adaptation (DA) methods are widely used in medical image segmentation tasks to tackle the problem of differently distributed train (source) and test (target) data. We consider the supervised DA task with a limited number of annotated samples from the target domain. It corresponds to one of the most relevant clinical setups: building a sufficiently accurate model on the minimum possible amount of annotated data. Existing methods mostly fine-tune specific layers of the pretrained Convolutional Neural Network (CNN). However, there is no consensus on which layers are better to fine-tune, e.g. the first layers for images with low-level domain shift or the deeper layers for images with high-level domain shift. To this end, we propose SpotTUnet - a CNN architecture that automatically chooses the layers which should be optimally fine-tuned. More specifically, on the target domain, our method additionally learns the policy that indicates whether a specific layer should be fine-tuned or reused from the pretrained network. We show that our method performs at the same level as the best of the nonflexible fine-tuning methods even under the extreme scarcity of annotated data. Secondly, we show that SpotTUnet policy provides a layer-wise visualization of the domain shift impact on the network, which could be further used to develop robust domain generalization methods. In order to extensively evaluate SpotTUnet performance, we use a publicly available dataset of brain MR images (CC359), characterized by explicit domain shift. We release a reproducible experimental pipeline.

Daniil Stepanov, Marat Akhin, Mikhail Belyaev

Kotlin is a relatively new programming language from JetBrains: its development started in 2010 with release 1.0 done in early 2016. The Kotlin compiler, while slowly and steadily becoming more and more mature, still crashes from time to time on the more tricky input programs, not least because of the complexity of its features and their interactions. This makes it a great target for fuzzing, even the basic forms of which can find a significant number of Kotlin compiler crashes. There is a problem with fuzzing, however, closely related to the cause of the crashes: generating a random, non-trivial and semantically valid Kotlin program is hard. In this paper, we talk about type-centric compiler fuzzing in the form of type-centric enumeration, an approach inspired by skeletal program enumeration and based on a combination of generative and mutation-based fuzzing, which solves this problem by focusing on program types. After creating the skeleton program, we fill the typed holes with fragments of suitable type, created via generation and enhanced by semantic-aware mutation. We implemented this approach in our Kotlin compiler fuzzing framework called Backend Bug Finder (BBF) and did an extensive evaluation, not only testing the real-world feasibility of our approach, but also comparing it to other compiler fuzzing techniques. The results show our approach to be significantly better compared to other fuzzing approaches at generating semantically valid Kotlin programs, while creating more interesting crash-inducing inputs at the same time. We managed to find more than 50 previously unknown compiler crashes, of which 18 were considered important after their triage by the compiler team.

Boris Shirokikh, Ivan Zakazov, Alexey Chernyavskiy et al.

MRI scans appearance significantly depends on scanning protocols and, consequently, the data-collection institution. These variations between clinical sites result in dramatic drops of CNN segmentation quality on unseen domains. Many of the recently proposed MRI domain adaptation methods operate with the last CNN layers to suppress domain shift. At the same time, the core manifestation of MRI variability is a considerable diversity of image intensities. We hypothesize that these differences can be eliminated by modifying the first layers rather than the last ones. To validate this simple idea, we conducted a set of experiments with brain MRI scans from six domains. Our results demonstrate that 1) domain-shift may deteriorate the quality even for a simple brain extraction segmentation task (surface Dice Score drops from 0.85-0.89 even to 0.09); 2) fine-tuning of the first layers significantly outperforms fine-tuning of the last layers in almost all supervised domain adaptation setups. Moreover, fine-tuning of the first layers is a better strategy than fine-tuning of the whole network, if the amount of annotated data from the new domain is strictly limited.

Mikhail Goncharov, Maxim Pisov, Alexey Shevtsov et al.

The current COVID-19 pandemic overloads healthcare systems, including radiology departments. Though several deep learning approaches were developed to assist in CT analysis, nobody considered study triage directly as a computer science problem. We describe two basic setups: Identification of COVID-19 to prioritize studies of potentially infected patients to isolate them as early as possible; Severity quantification to highlight studies of severe patients and direct them to a hospital or provide emergency medical care. We formalize these tasks as binary classification and estimation of affected lung percentage. Though similar problems were well-studied separately, we show that existing methods provide reasonable quality only for one of these setups. We employ a multitask approach to consolidate both triage approaches and propose a convolutional neural network to combine all available labels within a single model. In contrast with the most popular multitask approaches, we add classification layers to the most spatially detailed upper part of U-Net instead of the bottom, less detailed latent representation. We train our model on approximately 2000 publicly available CT studies and test it with a carefully designed set consisting of 32 COVID-19 studies, 30 cases with bacterial pneumonia, 31 healthy patients, and 30 patients with other lung pathologies to emulate a typical patient flow in an out-patient hospital. The proposed multitask model outperforms the latent-based one and achieves ROC AUC scores ranging from 0.87+-01 (bacterial pneumonia) to 0.97+-01 (healthy controls) for Identification of COVID-19 and 0.97+-01 Spearman Correlation for Severity quantification. We release all the code and create a public leaderboard, where other community members can test their models on our test dataset.

Maxim Pisov, Vladimir Kondratenko, Alexey Zakharov et al.

Vertebral body compression fractures are reliable early signs of osteoporosis. Though these fractures are visible on Computed Tomography (CT) images, they are frequently missed by radiologists in clinical settings. Prior research on automatic methods of vertebral fracture classification proves its reliable quality; however, existing methods provide hard-to-interpret outputs and sometimes fail to process cases with severe abnormalities such as highly pathological vertebrae or scoliosis. We propose a new two-step algorithm to localize the vertebral column in 3D CT images and then to simultaneously detect individual vertebrae and quantify fractures in 2D. We train neural networks for both steps using a simple 6-keypoints based annotation scheme, which corresponds precisely to current medical recommendation. Our algorithm has no exclusion criteria, processes 3D CT in 2 seconds on a single GPU, and provides an intuitive and verifiable output. The method approaches expert-level performance and demonstrates state-of-the-art results in vertebrae 3D localization (the average error is 1 mm), vertebrae 2D detection (precision is 0.99, recall is 1), and fracture identification (ROC AUC at the patient level is 0.93).

Artem Pimkin, Alexander Samoylenko, Natalia Antipina et al.

Recent CT Metal Artifacts Reduction (MAR) methods are often based on image-to-image convolutional neural networks for adjustment of corrupted sinograms or images themselves. In this paper, we are exploring the capabilities of a multi-domain method which consists of both sinogram correction (projection domain step) and restored image correction (image-domain step). Moreover, we propose a formulation of the first step problem as sinogram inpainting which allows us to use methods of this specific field such as partial convolutions. The proposed method allows to achieve state-of-the-art (-75% MSE) improvement in comparison with a classic benchmark - Li-MAR.

Daniil Stepanov, Marat Akhin, Mikhail Belyaev

Bug localization is well-known to be a difficult problem in software engineering, and specifically in compiler development, where it is beneficial to reduce the input program to a minimal reproducing example; this technique is more commonly known as delta debugging. What additionally contributes to the problem is that every new programming language has its own unique quirks and foibles, making it near impossible to reuse existing tools and approaches with full efficiency. In this experience paper we tackle the delta debugging problem w.r.t. Kotlin, a relatively new programming language from JetBrains. Our approach is based on a novel combination of program slicing, hierarchical delta debugging and Kotlin-specific transformations, which are synergistic to each other. We implemented it in a prototype called ReduKtor and did extensive evaluation on both synthetic and real Kotlin programs; we also compared its performance with classic delta debugging techniques. The evaluation results support the practical usability of our approach to Kotlin delta debugging and also shows the importance of using both language-agnostic and language-specific techniques to achieve best reduction efficiency and performance.

Boris Shirokikh, Alexandra Dalechina, Alexey Shevtsov et al.

Stereotactic radiosurgery is a minimally-invasive treatment option for a large number of patients with intracranial tumors. As part of the therapy treatment, accurate delineation of brain tumors is of great importance. However, slice-by-slice manual segmentation on T1c MRI could be time-consuming (especially for multiple metastases) and subjective. In our work, we compared several deep convolutional networks architectures and training procedures and evaluated the best model in a radiation therapy department for three types of brain tumors: meningiomas, schwannomas and multiple brain metastases. The developed semiautomatic segmentation system accelerates the contouring process by 2.2 times on average and increases inter-rater agreement from 92.0% to 96.5%.

Maxim Pisov, Mikhail Goncharov, Nadezhda Kurochkina et al.

Midline shift (MLS) is a well-established factor used for outcome prediction in traumatic brain injury, stroke and brain tumors. The importance of automatic estimation of MLS was recently highlighted by ACR Data Science Institute. In this paper we introduce a novel deep learning based approach for the problem of MLS detection, which exploits task-specific structural knowledge. We evaluate our method on a large dataset containing heterogeneous images with significant MLS and show that its mean error approaches the inter-expert variability. Finally, we show the robustness of our approach by validating it on an external dataset, acquired during routine clinical practice.

Hugo J. Kuijf, J. Matthijs Biesbroek, Jeroen de Bresser et al.

Quantification of cerebral white matter hyperintensities (WMH) of presumed vascular origin is of key importance in many neurological research studies. Currently, measurements are often still obtained from manual segmentations on brain MR images, which is a laborious procedure. Automatic WMH segmentation methods exist, but a standardized comparison of the performance of such methods is lacking. We organized a scientific challenge, in which developers could evaluate their method on a standardized multi-center/-scanner image dataset, giving an objective comparison: the WMH Segmentation Challenge (https://wmh.isi.uu.nl/). Sixty T1+FLAIR images from three MR scanners were released with manual WMH segmentations for training. A test set of 110 images from five MR scanners was used for evaluation. Segmentation methods had to be containerized and submitted to the challenge organizers. Five evaluation metrics were used to rank the methods: (1) Dice similarity coefficient, (2) modified Hausdorff distance (95th percentile), (3) absolute log-transformed volume difference, (4) sensitivity for detecting individual lesions, and (5) F1-score for individual lesions. Additionally, methods were ranked on their inter-scanner robustness. Twenty participants submitted their method for evaluation. This paper provides a detailed analysis of the results. In brief, there is a cluster of four methods that rank significantly better than the other methods, with one clear winner. The inter-scanner robustness ranking shows that not all methods generalize to unseen scanners. The challenge remains open for future submissions and provides a public platform for method evaluation.

Spyridon Bakas, Mauricio Reyes, Andras Jakab et al.

Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multi-parametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumor is a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in pre-operative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST/RANO criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that underwent gross total resection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset.

Maxim Pisov, Gleb Makarchuk, Valery Kostjuchenko et al.

Classification-based image retrieval systems are built by training convolutional neural networks (CNNs) on a relevant classification problem and using the distance in the resulting feature space as a similarity metric. However, in practical applications, it is often desirable to have representations which take into account several aspects of the data (e.g., brain tumor type and its localization). In our work, we extend the classification-based approach with multitask learning: we train a CNN on brain MRI scans with heterogeneous labels and implement a corresponding tumor image retrieval system. We validate our approach on brain tumor data which contains information about tumor types, shapes and localization. We show that our method allows us to build representations that contain more relevant information about tumors than single-task classification-based approaches.

Egor Krivov, Valery Kostjuchenko, Alexandra Dalechina et al.

Deep learning methods are actively used for brain lesion segmentation. One of the most popular models is DeepMedic, which was developed for segmentation of relatively large lesions like glioma and ischemic stroke. In our work, we consider segmentation of brain tumors appropriate to stereotactic radiosurgery which limits typical lesion sizes. These differences in target volumes lead to a large number of false negatives (especially for small lesions) as well as to an increased number of false positives for DeepMedic. We propose a new patch-sampling procedure to increase network performance for small lesions. We used a 6-year dataset from a stereotactic radiosurgery center. To evaluate our approach, we conducted experiments with the three most frequent brain tumors: metastasis, meningioma, schwannoma. In addition to cross-validation, we estimated quality on a hold-out test set which was collected several years later than the train one. The experimental results show solid improvements in both cases.

Yaroslav Shmulev, Mikhail Belyaev

Nowadays, a lot of scientific efforts are concentrated on the diagnosis of Alzheimer's Disease (AD) applying deep learning methods to neuroimaging data. Even for 2017, there were published more than a hundred papers dedicated to AD diagnosis, whereas only a few works considered a problem of mild cognitive impairments (MCI) conversion to the AD. However, the conversion prediction is an important problem since approximately 15% of patients with MCI converges to the AD every year. In the current work, we are focusing on the conversion prediction using brain Magnetic Resonance Imaging and clinical data, such as demographics, cognitive assessments, genetic, and biochemical markers. First of all, we applied state-of-the-art deep learning algorithms on the neuroimaging data and compared these results with two machine learning algorithms that we fit using the clinical data. As a result, the models trained on the clinical data outperform the deep learning algorithms applied to the MR images. To explore the impact of neuroimaging further, we trained a deep feed-forward embedding using similarity learning with Histogram loss on all available MRIs and obtained 64-dimensional vector representation of neuroimaging data. The use of learned representation from the deep embedding allowed to increase the quality of prediction based on the neuroimaging. Finally, the current results on this dataset show that the neuroimaging does affect conversion prediction, however, cannot noticeably increase the quality of the prediction. The best results of predicting MCI-to-AD conversion are provided by XGBoost algorithm trained on the clinical and embedding data. The resulting accuracy is 0.76 +- 0.01 and the area under the ROC curve - 0.86 +- 0.01.

Gleb Makarchuk, Vladimir Kondratenko, Maxim Pisov et al.

In the last years, neural networks have proven to be a powerful framework for various image analysis problems. However, some application domains have specific limitations. Notably, digital pathology is an example of such fields due to tremendous image sizes and quite limited number of training examples available. In this paper, we adopt state-of-the-art convolutional neural networks (CNN) architectures for digital pathology images analysis. We propose to classify image patches to increase effective sample size and then to apply an ensembling technique to build prediction for the original images. To validate the developed approaches, we conducted experiments with \textit{Breast Cancer Histology Challenge} dataset and obtained 90\% accuracy for the 4-class tissue classification task.

Dmitry Petrov, Boris Gutman, Alexander Ivanov et al.

In this work, we study the extent to which structural connectomes and topological derivative measures are unique to individual changes within human brains. To do so, we classify structural connectome pairs from two large longitudinal datasets as either belonging to the same individual or not. Our data is comprised of 227 individuals from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and 226 from the Parkinson's Progression Markers Initiative (PPMI). We achieve 0.99 area under the ROC curve score for features which represent either weights or network structure of the connectomes (node degrees, PageRank and local efficiency). Our approach may be useful for eliminating noisy features as a preprocessing step in brain aging studies and early diagnosis classification problems.

Sergey Korolev, Amir Safiullin, Mikhail Belyaev et al.

In the recent years there have been a number of studies that applied deep learning algorithms to neuroimaging data. Pipelines used in those studies mostly require multiple processing steps for feature extraction, although modern advancements in deep learning for image classification can provide a powerful framework for automatic feature generation and more straightforward analysis. In this paper, we show how similar performance can be achieved skipping these feature extraction steps with the residual and plain 3D convolutional neural network architectures. We demonstrate the performance of the proposed approach for classification of Alzheimer's disease versus mild cognitive impairment and normal controls on the Alzheimer's Disease National Initiative (ADNI) dataset of 3D structural MRI brain scans.

Yulia Dodonova, Mikhail Belyaev, Anna Tkachev et al.

In this paper, we tackle a problem of predicting phenotypes from structural connectomes. We propose that normalized Laplacian spectra can capture structural properties of brain networks, and hence graph spectral distributions are useful for a task of connectome-based classification. We introduce a kernel that is based on earth mover's distance (EMD) between spectral distributions of brain networks. We access performance of an SVM classifier with the proposed kernel for a task of classification of autism spectrum disorder versus typical development based on a publicly available dataset. Classification quality (area under the ROC-curve) obtained with the EMD-based kernel on spectral distributions is 0.71, which is higher than that based on simpler graph embedding methods.

Mikhail Belyaev, Evgeny Burnaev, Ermek Kapushev et al.

We describe GTApprox - a new tool for medium-scale surrogate modeling in industrial design. Compared to existing software, GTApprox brings several innovations: a few novel approximation algorithms, several advanced methods of automated model selection, novel options in the form of hints. We demonstrate the efficiency of GTApprox on a large collection of test problems. In addition, we describe several applications of GTApprox to real engineering problems.