Connecting cohorts of Finnish biobanks creates a research resource for the study of healthy ageing

AIMS

Connecting cohorts with biobanks is a Finnish biobank collaboration, creating an infrastructure for the study of healthy ageing. We aimed to develop a model for data integration and harmonisation between different biobanks with procedures for joint access.

METHODS

The heart of the collaboration is the integrated datasets formed by using data from three biobanks: (a) Arctic Biobank, hosting regional birth cohorts and cohorts of elderly; (b) hospital-affiliated Borealis Biobank of Northern Finland; and (c) THL Biobank, hosting population-based cohorts. The datasets were created by developing a data dictionary, harmonising cohort data and with a joint pseudonymisation process.

RESULTS

The connecting cohorts with biobanks resource at its widest consists altogether of almost 1.4 million individuals from collaborating biobanks. Utilising data from 107,000 cohort participants, we created harmonised datasets that contain attributes describing metabolic risk and frailty for studies of healthy ageing. These data can be complemented with medical data available from Biobank Borealis and with samples taken at hospital settings for approximately 38,000 cohort participants. In addition, the harmonised connecting cohorts with biobanks datasets can be expanded with supplementary data and samples from the collaborating biobanks.

CONCLUSIONS

The connecting cohorts with biobanks datasets provide a unique resource for research on ageing-related personalised healthcare and for real-world evidence studies. Following the FAIR principles on findability, accessibility, interoperability, and reusability, the reused and harmonised datasets are findable and made accessible for researchers. The same approach can be further utilised to develop additional datasets for other research topics.

Invasion depth estimation of carcinoma cells using adaptive stain normalization to improve epidermis segmentation accuracy

Submucosal invasion depth is a significant prognostic factor when assessing lymph node metastasis and cancer itself to plan proper treatment for the patient. Conventionally, oncologists measure the invasion depth by hand which is a laborious, subjective, and time-consuming process. The manual pathological examination by measuring accurate carcinoma cell invasion with considerable inter-observer and intra-observer variations is still challenging. The increasing use of medical imaging and artificial intelligence reveals a significant role in clinical medicine and pathology. In this paper, we propose an approach to study invasive behavior and measure the invasion depth of carcinoma from stained histopathology images. Specifically, our model includes adaptive stain normalization, color decomposition, and morphological reconstruction with adaptive thresholding to separate the epithelium with blue ratio image. Our method splits the image into multiple non-overlapping meaningful segments and successfully finds the homogeneous segments to measure accurate invasion depth. The invasion depths are measured from the inner epithelium edge to outermost pixels of the deepest part of particles in image. We conduct our experiments on skin melanoma tissue samples as well as on organotypic invasion model utilizing myoma tissue and oral squamous cell carcinoma. The performance is experimentally compared to three closely related reference methods and our method provides a superior result in measuring invasion depth. This computational technique will be beneficial for the segmentation of epithelium and other particles for the development of novel computer-aided diagnostic tools in biobank applications.

Optimized detection and segmentation of nuclei in gastric cancer images using stain normalization and blurred artifact removal

Histological analysis with microscopy is the gold standard to diagnose and stage cancer, where slides or whole slide images are analyzed for cell morphological and spatial features by pathologists. The nuclei of cancerous cells are characterized by nonuniform chromatin distribution, irregular shapes, and varying size. As nucleus area and shape alone carry prognostic value, detection and segmentation of nuclei are among the most important steps in disease grading. However, evaluation of nuclei is a laborious, time-consuming, and subjective process with large variation among pathologists. Recent advances in digital pathology have allowed significant applications in nuclei detection, segmentation, and classification, but automated image analysis is greatly affected by staining factors, scanner variability, and imaging artifacts, requiring robust image preprocessing, normalization, and segmentation methods for clinically satisfactory results. In this paper, we aimed to evaluate and compare the digital image analysis techniques used in clinical pathology and research in the setting of gastric cancer. A literature review was conducted to evaluate potential methods of improving nuclei detection. Digitized images of 35 patients from a retrospective cohort of gastric adenocarcinoma at Oulu University Hospital in 1987-2016 were annotated for nuclei (n = 9085) by expert pathologists and 14 images of different cancer types from public TCGA dataset with annotated nuclei (n = 7000) were used as a comparison to evaluate applicability in other cancer types. The detection and segmentation accuracy with the selected color normalization and stain separation techniques were compared between the methods. The extracted information can be supplemented by patient's medical data and fed to the existing statistical clinical tools or subjected to subsequent AI-assisted classification and prediction models. The performance of each method is evaluated by several metrics against the annotations done by expert pathologists. The F1-measure of 0.854 ± 0.068 is achieved with color normalization for the gastric cancer dataset, and 0.907 ± 0.044 with color deconvolution for the public dataset, showing comparable results to the earlier state-of-the-art works. The developed techniques serve as a basis for further research on application and interpretability of AI-assisted tools for gastric cancer diagnosis.

SAM: Self-augmentation mechanism for COVID-19 detection using chest X-ray images

COVID-19 is a rapidly spreading viral disease and has affected over 100 countries worldwide. The numbers of casualties and cases of infection have escalated particularly in countries with weakened healthcare systems. Recently, reverse transcription-polymerase chain reaction (RT-PCR) is the test of choice for diagnosing COVID-19. However, current evidence suggests that COVID-19 infected patients are mostly stimulated from a lung infection after coming in contact with this virus. Therefore, chest X-ray (i.e., radiography) and chest CT can be a surrogate in some countries where PCR is not readily available. This has forced the scientific community to detect COVID-19 infection from X-ray images and recently proposed machine learning methods offer great promise for fast and accurate detection. Deep learning with convolutional neural networks (CNNs) has been successfully applied to radiological imaging for improving the accuracy of diagnosis. However, the performance remains limited due to the lack of representative X-ray images available in public benchmark datasets. To alleviate this issue, we propose a self-augmentation mechanism for data augmentation in the feature space rather than in the data space using reconstruction independent component analysis (RICA). Specifically, a unified architecture is proposed which contains a deep convolutional neural network (CNN), a feature augmentation mechanism, and a bidirectional LSTM (BiLSTM). The CNN provides the high-level features extracted at the pooling layer where the augmentation mechanism chooses the most relevant features and generates low-dimensional augmented features. Finally, BiLSTM is used to classify the processed sequential information. We conducted experiments on three publicly available databases to show that the proposed approach achieves the state-of-the-art results with accuracy of 97%, 84% and 98%. Explainability analysis has been carried out using feature visualization through PCA projection and t-SNE plots.

Retinex model based stain normalization technique for whole slide image analysis

Medical imaging provides the means for diagnosing many of the medical phenomena currently studied in clinical medicine and pathology. The variations of color and intensity in stained histological slides affect the quantitative analysis of the histopathological images. Moreover, stain normalization utilizing color for the classification of pixels into different stain components is challenging. The staining also suffers from variability, which complicates the automatization of tissue area segmentation with different staining and the analysis of whole slide images. We have developed a Retinex model based stain normalization technique in terms of area segmentation from stained tissue images to quantify the individual stain components of the histochemical stains for the ideal removal of variability. The performance was experimentally compared to reference methods and tested on organotypic carcinoma model based on myoma tissue and our method consistently has the smallest standard deviation, skewness value, and coefficient of variation in normalized median intensity measurements. Our method also achieved better quality performance in terms of Quaternion Structure Similarity Index Metric (QSSIM), Structural Similarity Index Metric (SSIM), and Pearson Correlation Coefficient (PCC) by improving robustness against variability and reproducibility. The proposed method could potentially be used in the development of novel research as well as diagnostic tools with the potential improvement of accuracy and consistency in computer aided diagnosis in biobank applications.

Joint Image Encryption and Screen-Cam Robust Two Watermarking Scheme

This paper proposes a joint encryption and screen-cam robust watermarking scheme. This method combines the advantages of smartphone, encryption and watermarking technologies, thereby achieving watermark extraction with a smartphone, partial decryption and tracking leakage from sneak shots. We design a dual watermarking algorithm to achieve watermark detection from both encrypted and decrypted images. First, a watermark is embedded in the discrete Fourier transform (DFT) domain to enable leakage tracking. Then, a second watermark is generated based on QR (Quick response) code encoding and inverse DFT to achieve high watermark capacity and error correction ability, where the secret key for decryption is included in the watermark message. By hiding this message carrying the watermark for the encrypted image in the changes caused by embedding the first watermark, we can improve imperceptibility and will not affect the effectiveness of the proposed scheme. Finally, to enhance the robustness of watermark after encryption, a chaotic mapping-based segment encryption algorithm is proposed. In the process of watermark detection, to cope with perspective correction, a frame locating based algorithm is employed to achieve watermark synchronization from a recaptured picture of the encrypted image. Considering the severe quality degradation, we use a noise component and local statistic feature-based method to extract the message bits. The experimental results show that the proposed scheme is secure, and highly robust, to screen-cam the process for both before and after decryption. Additionally, after decryption, the proposed scheme also has high robustness against common image processing attacks.

Speeding up the file access of large compressed NIfTI neuroimaging data

A method and implementation are presented to achieve a thousand fold speed-up for seeking of large files in a commonly used compressed neuroimaging data format NIfTI. Such technologies are not currently available in this research field while they would make the everyday work for hundreds of researchers and experts much smoother and faster. The method includes the creation of a novel index structure for the compressed data in order to achieve the speed-up. With random seek simulations, we demonstrate that a speed-up of over hundred up to even five thousand can be reached compared to the currently available implementations. By configuring the index structure properly, one can set an operating point which optimizes the efficiency as speed-up versus index size according to the requirements by the user. For example, a thousand fold speed-up can be achieved with an index size of only about two percent of the original compressed data.

Detection of short-term activity avalanches in human brain default mode network with ultrafast MR encephalography

Recent studies pinpoint visually cued networks of avalanches with MEG/EEG data. Co-activation pattern (CAP) analysis can be used to detect single brain volume activity profiles and hemodynamic fingerprints of neuronal avalanches as sudden high signal activity peaks in classical fMRI data. In this study, we aimed to detect dynamic patterns of brain activity spreads with the use of ultrafast MR encephalography (MREG). MREG achieves 10 Hz whole brain sampling, allowing the estimation of spatial spread of an avalanche, even with the inherent hemodynamic delay of the BOLD signal. We developed a novel computational method to separate avalanche type fast activity spreads from motion artifacts, vasomotor fluctuations, and cardio-respiratory noise in human brain default mode network (DMN). Reproducible and classical DMN sources were identified using spatial ICA prior to advanced noise removal in order to assure that ICA converges to reproducible networks. Brain activity peaks were identified from parts of the DMN, and normalized MREG data around each peak were extracted individually to show dynamic avalanche type spreads as video clips within the DMN. Individual activity spread video clips of specific parts of the DMN were then averaged over the group of subjects. The experiments show that the high BOLD values around the peaks are mostly spreading along the spatial pattern of the particular DMN segment detected with ICA. With also the spread size and lifetime resembling the expected power law distributions, this indicates that the detected peaks are parts of activity avalanches, starting from (or crossing) the DMN. Furthermore, the split, one-sided sub-networks of the DMN show different spread directions within the same DMN framework. The results open possibilities to follow up brain activity avalanches in the hope to understand more about the system wide properties of diseases related to DMN dysfunction.