Umeå University's logo

umu.sePublications
Change search
Link to record
Permanent link

Direct link
Publications (10 of 197) Show all publications
Machleid, R., Hoehse, M., Scholze, S., Mazarakis, K., Nilsson, D., Johansson, E., . . . Surowiec, I. (2024). Feasibility and performance of cross-clone Raman calibration models in CHO cultivation. Biotechnology Journal, 19(1), Article ID 2300289.
Open this publication in new window or tab >>Feasibility and performance of cross-clone Raman calibration models in CHO cultivation
Show others...
2024 (English)In: Biotechnology Journal, ISSN 1860-6768, E-ISSN 1860-7314, Vol. 19, no 1, article id 2300289Article in journal (Refereed) Published
Abstract [en]

Raman spectroscopy is widely used in monitoring and controlling cell cultivations for biopharmaceutical drug manufacturing. However, its implementation for culture monitoring in the cell line development stage has received little attention. Therefore, the impact of clonal differences, such as productivity and growth, on the prediction accuracy and transferability of Raman calibration models is not yet well described. Raman OPLS models were developed for predicting titer, glucose and lactate using eleven CHO clones from a single cell line. These clones exhibited diverse productivity and growth rates. The calibration models were evaluated for clone-related biases using clone-wise linear regression analysis on cross validated predictions. The results revealed that clonal differences did not affect the prediction of glucose and lactate, but titer models showed a significant clone-related bias, which remained even after applying variable selection methods. The bias was associated with clonal productivity and lead to increased prediction errors when titer models were transferred to cultivations with productivity levels outside the range of their training data. The findings demonstrate the feasibility of Raman-based monitoring of glucose and lactate in cell line development with high accuracy. However, accurate titer prediction requires careful consideration of clonal characteristics during model development.

Place, publisher, year, edition, pages
John Wiley & Sons, 2024
Keywords
bioprocess development, bioprocess engineering, bioprocess monitoring, CHO cells
National Category
Analytical Chemistry
Identifiers
urn:nbn:se:umu:diva-218135 (URN)10.1002/biot.202300289 (DOI)38015079 (PubMedID)2-s2.0-85178957570 (Scopus ID)
Available from: 2023-12-18 Created: 2023-12-18 Last updated: 2024-04-30Bibliographically approved
Abbasi, A. F., Asim, M. N., Trygg, J., Dengel, A. & Ahmed, S. (2023). Deep learning architectures for the prediction of YY1-mediated chromatin loops. In: Xuan Guo; Serghei Mangul; Murray Patterson; Alexander Zelikovsky (Ed.), Bioinformatics research and applications: 19th international symposium, ISBRA 2023, Wrocław, Poland, October 9–12, 2023, proceedings. Paper presented at 19th International Symposium on Bioinformatics Research and Applications, ISBRA 2023 (pp. 72-84). Springer
Open this publication in new window or tab >>Deep learning architectures for the prediction of YY1-mediated chromatin loops
Show others...
2023 (English)In: Bioinformatics research and applications: 19th international symposium, ISBRA 2023, Wrocław, Poland, October 9–12, 2023, proceedings / [ed] Xuan Guo; Serghei Mangul; Murray Patterson; Alexander Zelikovsky, Springer, 2023, p. 72-84Conference paper, Published paper (Refereed)
Abstract [en]

YY1-mediated chromatin loops play substantial roles in basic biological processes like gene regulation, cell differentiation, and DNA replication. YY1-mediated chromatin loop prediction is important to understand diverse types of biological processes which may lead to the development of new therapeutics for neurological disorders and cancers. Existing deep learning predictors are capable to predict YY1-mediated chromatin loops in two different cell lines however, they showed limited performance for the prediction of YY1-mediated loops in the same cell lines and suffer significant performance deterioration in cross cell line setting. To provide computational predictors capable of performing large-scale analyses of YY1-mediated loop prediction across multiple cell lines, this paper presents two novel deep learning predictors. The two proposed predictors make use of Word2vec, one hot encoding for sequence representation and long short-term memory, and a convolution neural network along with a gradient flow strategy similar to DenseNet architectures. Both of the predictors are evaluated on two different benchmark datasets of two cell lines HCT116 and K562. Overall the proposed predictors outperform existing DEEPYY1 predictor with an average maximum margin of 4.65%, 7.45% in terms of AUROC, and accuracy, across both of the datases over the independent test sets and 5.1%, 3.2% over 5-fold validation. In terms of cross-cell evaluation, the proposed predictors boast maximum performance enhancements of up to 9.5% and 27.1% in terms of AUROC over HCT116 and K562 datasets.

Place, publisher, year, edition, pages
Springer, 2023
Series
Lecture Notes in Computer Science (LNBI), ISSN 0302-9743, E-ISSN 1611-3349 ; 14248
Keywords
Chromatin loops, Convolutional Networks, Gene regulation, LSTM, One hot encoding, Word2vec, YY1
National Category
Bioinformatics (Computational Biology)
Identifiers
urn:nbn:se:umu:diva-215831 (URN)10.1007/978-981-99-7074-2_6 (DOI)2-s2.0-85174274462 (Scopus ID)9789819970735 (ISBN)9789819970742 (ISBN)
Conference
19th International Symposium on Bioinformatics Research and Applications, ISBRA 2023
Available from: 2023-11-06 Created: 2023-11-06 Last updated: 2023-11-06Bibliographically approved
Alinaghi, M., Nilsson, D., Singh, N., Höjer, A., Saedén, K. H. & Trygg, J. (2023). Near-infrared hyperspectral image analysis for monitoring the cheese-ripening process. Journal of Dairy Science, 106(11), 7407-7418
Open this publication in new window or tab >>Near-infrared hyperspectral image analysis for monitoring the cheese-ripening process
Show others...
2023 (English)In: Journal of Dairy Science, ISSN 0022-0302, E-ISSN 1525-3198, Vol. 106, no 11, p. 7407-7418Article in journal (Refereed) Published
Abstract [en]

Ripening is the most crucial process step in cheese manufacturing and constitutes multiple biochemical alterations that describe the final cheese quality and its perceived sensory attributes. The assessment of the cheese-ripening process is challenging and requires the effective analysis of a multitude of biochemical changes occurring during the process. This study monitored the biochemical and sensory attribute changes of paraffin wax-covered long-ripening hard cheeses (n = 79) during ripening by collecting samples at different stages of ripening. Near-infrared hyperspectral (NIR-HS) imaging, together with free amino acid, chemical composition, and sensory attributes, was studied to monitor the biochemical changes during the ripening process. Orthogonal projection-based multivariate calibration methods were used to characterize ripening-related and orthogonal components as well as the distribution map of chemical components. The results approve the NIR-HS imaging as a rapid tool for monitoring cheese maturity during ripening. Moreover, the pixelwise evaluation of images shows the homogeneity of cheese maturation at different stages of ripening. Among the chemical compositions, fat content and moisture are the most important variables correlating to NIR-HS images during the ripening process.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
cheese maturation, free amino acids, homogeneity distribution, near-infrared hyperspectral imaging, sensory analysis
National Category
Food Science Bioprocess Technology
Identifiers
urn:nbn:se:umu:diva-215833 (URN)10.3168/jds.2023-23377 (DOI)37641350 (PubMedID)2-s2.0-85174425331 (Scopus ID)
Available from: 2023-11-03 Created: 2023-11-03 Last updated: 2023-11-03Bibliographically approved
Khalid, N., Froes, T. C., Caroprese, M., Lovell, G., Trygg, J., Dengel, A. & Ahmed, S. (2023). PACE: point annotation-based cell segmentation for efficient microscopic image analysis. In: Lazaros Iliadis; Antonios Papaleonidas; Plamen Angelov; Chrisina Jayne (Ed.), Artificial Neural Networks and Machine Learning – ICANN 2023: 32nd International Conference on Artificial Neural Networks, Heraklion, Crete, Greece, September 26–29, 2023, Proceedings, Part II. Paper presented at 32nd International Conference on Artificial Neural Networks, ICANN 2023, Harklion, Crete, Greece, September 26-29, 2023 (pp. 545-557). Springer Nature
Open this publication in new window or tab >>PACE: point annotation-based cell segmentation for efficient microscopic image analysis
Show others...
2023 (English)In: Artificial Neural Networks and Machine Learning – ICANN 2023: 32nd International Conference on Artificial Neural Networks, Heraklion, Crete, Greece, September 26–29, 2023, Proceedings, Part II / [ed] Lazaros Iliadis; Antonios Papaleonidas; Plamen Angelov; Chrisina Jayne, Springer Nature, 2023, p. 545-557Conference paper, Published paper (Refereed)
Abstract [en]

Cells are essential to life because they provide the functional, genetic, and communication mechanisms essential for the proper functioning of living organisms. Cell segmentation is pivotal for any biological hypothesis validation/analysis i.e., to get valuable insights into cell behavior, function, diagnosis, and treatment. Deep learning-based segmentation methods have high segmentation precision, however, need fully annotated segmentation masks for each cell annotated manually by the experts, which is very laborious and costly. Many approaches have been developed in the past to reduce the effort required to annotate the data manually and even though these approaches produce good results, there is still a noticeable difference in performance when compared to fully supervised methods. To fill that gap, a weakly supervised approach, PACE, is presented, which uses only the point annotations and the bounding box for each cell to perform cell instance segmentation. The proposed approach not only achieves 99.8% of the fully supervised performance, but it also surpasses the previous state-of-the-art by a margin of more than 4%.

Place, publisher, year, edition, pages
Springer Nature, 2023
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 14255
Keywords
cell segmentation, deep learning, point annotation, weakly supervised
National Category
Computer Sciences
Identifiers
urn:nbn:se:umu:diva-215927 (URN)10.1007/978-3-031-44210-0_44 (DOI)2-s2.0-85174618633 (Scopus ID)978-3-031-44209-4 (ISBN)978-3-031-44210-0 (ISBN)
Conference
32nd International Conference on Artificial Neural Networks, ICANN 2023, Harklion, Crete, Greece, September 26-29, 2023
Available from: 2023-11-02 Created: 2023-11-02 Last updated: 2023-12-04Bibliographically approved
Asim, M. N., Ibrahim, M. A., Zehe, C., Trygg, J., Dengel, A. & Ahmed, S. (2022). BoT-Net: a lightweight bag of tricks-based neural network for efficient LncRNA–miRNA interaction prediction. Interdisciplinary Sciences: Computational Life Sciences, 14(4), 841-862
Open this publication in new window or tab >>BoT-Net: a lightweight bag of tricks-based neural network for efficient LncRNA–miRNA interaction prediction
Show others...
2022 (English)In: Interdisciplinary Sciences: Computational Life Sciences, ISSN 1913-2751, Vol. 14, no 4, p. 841-862Article in journal (Refereed) Published
Abstract [en]

Background and objective: Interactions of long non-coding ribonucleic acids (lncRNAs) with micro-ribonucleic acids (miRNAs) play an essential role in gene regulation, cellular metabolic, and pathological processes. Existing purely sequence based computational approaches lack robustness and efficiency mainly due to the high length variability of lncRNA sequences. Hence, the prime focus of the current study is to find optimal length trade-offs between highly flexible length lncRNA sequences.

Method: The paper at hand performs in-depth exploration of diverse copy padding, sequence truncation approaches, and presents a novel idea of utilizing only subregions of lncRNA sequences to generate fixed-length lncRNA sequences. Furthermore, it presents a novel bag of tricks-based deep learning approach “Bot-Net” which leverages a single layer long-short-term memory network regularized through DropConnect to capture higher order residue dependencies, pooling to retain most salient features, normalization to prevent exploding and vanishing gradient issues, learning rate decay, and dropout to regularize precise neural network for lncRNA–miRNA interaction prediction.

Results: BoT-Net outperforms the state-of-the-art lncRNA–miRNA interaction prediction approach by 2%, 8%, and 4% in terms of accuracy, specificity, and matthews correlation coefficient. Furthermore, a case study analysis indicates that BoT-Net also outperforms state-of-the-art lncRNA–protein interaction predictor on a benchmark dataset by accuracy of 10%, sensitivity of 19%, specificity of 6%, precision of 14%, and matthews correlation coefficient of 26%.

Conclusion: In the benchmark lncRNA–miRNA interaction prediction dataset, the length of the lncRNA sequence varies from 213 residues to 22,743 residues and in the benchmark lncRNA–protein interaction prediction dataset, lncRNA sequences vary from 15 residues to 1504 residues. For such highly flexible length sequences, fixed length generation using copy padding introduces a significant level of bias which makes a large number of lncRNA sequences very much identical to each other and eventually derail classifier generalizeability. Empirical evaluation reveals that within 50 residues of only the starting region of long lncRNA sequences, a highly informative distribution for lncRNA–miRNA interaction prediction is contained, a crucial finding exploited by the proposed BoT-Net approach to optimize the lncRNA fixed length generation process.

Place, publisher, year, edition, pages
Springer, 2022
Keywords
Bag of tricks, Deep learning, Deep learning strategies, Lightweight neural network, lncRNA–miRNA interaction prediction, Long non-coding RNA, Micro-RNA, Robust interaction predictor
National Category
Medical Genetics Computer and Information Sciences
Identifiers
urn:nbn:se:umu:diva-198927 (URN)10.1007/s12539-022-00535-x (DOI)000838462900001 ()35947255 (PubMedID)2-s2.0-85135822586 (Scopus ID)
Projects
DEAL
Available from: 2022-09-16 Created: 2022-09-16 Last updated: 2023-03-24Bibliographically approved
Khalid, N., Koochali, M., Rajashekar, V., Munir, M., Edlund, C., Jackson, T. R., . . . Ahmed, S. (2022). DeepMuCS: A framework for co-culture microscopic image analysis: from generation to segmentation. In: 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI): . Paper presented at 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2022, September 27-30, 2022 (pp. 1-4). IEEE
Open this publication in new window or tab >>DeepMuCS: A framework for co-culture microscopic image analysis: from generation to segmentation
Show others...
2022 (English)In: 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), IEEE, 2022, p. 1-4Conference paper, Published paper (Refereed)
Abstract [en]

Discrimination between cell types in the co-culture environment with multiple cell lines can assist in examining the interaction between different cell populations. Identifying different cell cultures in addition to cell segmentation in co-culture is essential for understanding the cellular mechanisms associated with disease states. In drug development, biologists are more interested in co-culture models because they replicate the tumor environment in vivo better than the monoculture models. Additionally, they have a measurable effect on cancer cell response to treatment. Co-culture models are critical for designing a drug with maximum efficacy on cancer while minimizing harm to the rest of the body. In the past, there existed minimal progress related to cell-type aware segmentation in the monoculture and no development whatsoever for the co-culture. The introduction of the LIVECell dataset has allowed us to perform experiments for cell-type-aware segmentation. However, it is composed of microscopic images in a monoculture environment. This paper presents a framework for co-culture microscopic image data generation, where each image can contain multiple cell cultures. The framework also presents a pipeline for culture-dependent cell segmentation in co-culture microscopic images. The extensive evaluation revealed that it is possible to achieve cell-type aware segmentation in co-culture microscopic images with good precision.

Place, publisher, year, edition, pages
IEEE, 2022
Keywords
biomedical, cell segmentation, co-culture, deep learning, healthcare
National Category
Medical Biotechnology (with a focus on Cell Biology (including Stem Cell Biology), Molecular Biology, Microbiology, Biochemistry or Biopharmacy)
Identifiers
urn:nbn:se:umu:diva-201641 (URN)10.1109/BHI56158.2022.9926936 (DOI)000895865900089 ()2-s2.0-85143072914 (Scopus ID)9781665487917 (ISBN)
Conference
2022 IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2022, September 27-30, 2022
Available from: 2022-12-13 Created: 2022-12-13 Last updated: 2023-09-05Bibliographically approved
Asim, M. N., Ibrahim, M. A., Malik, M. I., Zehe, C., Cloarec, O., Trygg, J., . . . Ahmed, S. (2022). EL-RMLocNet: An explainable LSTM network for RNA-associated multi-compartment localization prediction. Computational and Structural Biotechnology Journal, 20, 3986-4002
Open this publication in new window or tab >>EL-RMLocNet: An explainable LSTM network for RNA-associated multi-compartment localization prediction
Show others...
2022 (English)In: Computational and Structural Biotechnology Journal, E-ISSN 2001-0370, Vol. 20, p. 3986-4002Article in journal (Refereed) Published
Abstract [en]

Subcellular localization of Ribonucleic Acid (RNA) molecules provide significant insights into the functionality of RNAs and helps to explore their association with various diseases. Predominantly developed single-compartment localization predictors (SCLPs) lack to demystify RNA association with diverse biochemical and pathological processes mainly happen through RNA co-localization in multiple compartments. Limited multi-compartment localization predictors (MCLPs) manage to produce decent performance only for target RNA class of particular sub-type. Further, existing computational approaches have limited practical significance and potential to optimize therapeutics due to the poor degree of model explainability. The paper in hand presents an explainable Long Short-Term Memory (LSTM) network “EL-RMLocNet”, predictive performance and interpretability of which are optimized using a novel GeneticSeq2Vec statistical representation learning scheme and attention mechanism for accurate multi-compartment localization prediction of different RNAs solely using raw RNA sequences. GeneticSeq2Vec generates optimized statistical vectors of raw RNA sequences by capturing short and long range relations of nucleotide k-mers. Using sequence vectors generated by GeneticSeq2Vec scheme, Long Short Term Memory layers extract most informative features, weighting of which on the basis of discriminative potential for accurate multi-compartment localization prediction is performed using attention layer. Through reverse engineering, weights of statistical feature space are mapped to nucleotide k-mers patterns to make multi-compartment localization prediction decision making transparent and explainable for different RNA classes and species. Empirical evaluation indicates that EL-RMLocNet outperforms state-of-the-art predictor for subcellular localization prediction of 4 different RNA classes by an average accuracy figure of 8% for Homo Sapiens species and 6% for Mus Musculus species. EL-RMLocNet is freely available as a web server at (https://sds_genetic_analysis.opendfki.de/subcellular_loc/).

Place, publisher, year, edition, pages
Elsevier, 2022
Keywords
Attention mechanism, Deep learning, Explainable, GeneticSeq2Vec, Human, LSTM, Mouse, Multi-class, Multi-label, Neural tricks, RNA subcellular localization prediction, Single or multi compartment
National Category
Bioinformatics (Computational Biology)
Identifiers
urn:nbn:se:umu:diva-198571 (URN)10.1016/j.csbj.2022.07.031 (DOI)000889723800009 ()2-s2.0-85135296076 (Scopus ID)
Available from: 2022-08-12 Created: 2022-08-12 Last updated: 2023-09-05Bibliographically approved
Alinaghi, M., Surowiec, I., Scholze, S., McCready, C., Zehe, C., Johansson, E., . . . Cloarec, O. (2022). Hierarchical time-series analysis of dynamic bioprocess systems. Biotechnology Journal, 17(12), Article ID 2200237.
Open this publication in new window or tab >>Hierarchical time-series analysis of dynamic bioprocess systems
Show others...
2022 (English)In: Biotechnology Journal, ISSN 1860-6768, E-ISSN 1860-7314, Vol. 17, no 12, article id 2200237Article in journal (Refereed) Published
Abstract [en]

Background: Monoclonal antibodies (mAbs) are leading types of ‘blockbuster’ biotherapeutics worldwide; they have been successfully used to treat various cancers and chronic inflammatory and autoimmune diseases. Biotherapeutics process development and manufacturing are complicated due to lack of understanding the factors that impact cell productivity and product quality attributes. Understanding complex interactions between cells, media, and process parameters on the molecular level is essential to bring biomanufacturing to the next level. This can be achieved by analyzing cell culture metabolic levels connected to vital process parameters like viable cell density (VCD). However, VCD and metabolic profiles are dynamic parameters and inherently correlated with time, leading to a significant correlation without actual causality. Many time-series methods deal with such issues. However, with metabolic profiling, the number of measured variables vastly exceeds the number of experiments, making most of existing methods ill-suited and hard to interpret. Methods and Major

Results: Here we propose an alternative workflow using hierarchical dimension reduction to visualize and interpret the relation between evolution of metabolic profiles and dynamic process parameters. The first step of proposed method is focused on finding predictive relation between metabolic profiles and process parameter at all time points using OPLS regression. For each time point, the p(corr) obtained from OPLS model is considered as a differential metabogram and is further assessed using principal components analysis (PCA).

Conclusions: Compared to traditional batch modeling, applying proposed methodology on metabolic data from Chinese Hamster Ovary (CHO) antibody production characterized the dynamic relation between metabolic profiles and critical process parameters.

Place, publisher, year, edition, pages
John Wiley & Sons, 2022
Keywords
bioprocess data, dynamic system, hierarchical analysis, meta-analysis, metabolomics data, time-series analysis, viable cell density (VCD)
National Category
Biochemistry and Molecular Biology
Identifiers
urn:nbn:se:umu:diva-201242 (URN)10.1002/biot.202200237 (DOI)000878861900001 ()36266999 (PubMedID)2-s2.0-85141350637 (Scopus ID)
Available from: 2022-12-05 Created: 2022-12-05 Last updated: 2022-12-30Bibliographically approved
Norman, M., Nilsson, D., Trygg, J. & Håkansson, S. (2022). Perinatal risk factors for mortality in very preterm infants: A nationwide, population-based discriminant analysis. Acta Paediatrica, 111(8), 1526-1535
Open this publication in new window or tab >>Perinatal risk factors for mortality in very preterm infants: A nationwide, population-based discriminant analysis
2022 (English)In: Acta Paediatrica, ISSN 0803-5253, E-ISSN 1651-2227, Vol. 111, no 8, p. 1526-1535Article in journal (Refereed) Published
Abstract [en]

Aim: To assess the strength of associations between interrelated perinatal risk factors and mortality in very preterm infants.

Methods: Information on all live-born infants delivered in Sweden at 22–31 weeks of gestational age (GA) from 2011 to 2019 was gathered from the Swedish Neonatal Quality Register, excluding infants with major malformations or not resuscitated because of anticipated poor prognosis. Twenty-seven perinatal risk factors available at birth were exposures and in-hospital mortality outcome. Orthogonal partial least squares discriminant analysis was applied to assess proximity between individual risk factors and mortality, and receiver operating characteristic (ROC) curves were used to estimate discriminant ability.

Results: In total, 638 of 8,396 (7.6%) infants died. Thirteen risk factors discriminated reduced mortality; the most important were higher Apgar scores at 5 and 10 min, GA and birthweight. Restricting the analysis to preterm infants <28 weeks’ GA (n = 2939, 16.9% mortality) added antenatal corticosteroid therapy as significantly associated with lower mortality. The area under the ROC curve (the C-statistic) using all risk factors was 0.86, as determined after both internal and external validation.

Conclusion: Apgar scores, gestational age and birthweight show stronger associations with mortality in very preterm infants than several other perinatal risk factors available at birth.

Place, publisher, year, edition, pages
John Wiley & Sons, 2022
Keywords
infant mortality, orthogonal partial least squares discriminant analysis, preterm infant
National Category
Pediatrics Obstetrics, Gynecology and Reproductive Medicine
Research subject
Pediatrics
Identifiers
urn:nbn:se:umu:diva-193971 (URN)10.1111/apa.16356 (DOI)000782490500001 ()35397189 (PubMedID)2-s2.0-85128063703 (Scopus ID)
Available from: 2022-05-03 Created: 2022-05-03 Last updated: 2022-11-30Bibliographically approved
Khalid, N., Schmeisser, F., Koochali, M., Munir, M., Edlund, C., Jackson, T. R., . . . Ahmed, S. (2022). Point2Mask: A Weakly Supervised Approach for Cell Segmentation Using Point Annotation. In: Guang Yang; Angelica Aviles-Rivero; Michael Roberts; Carola-Bibiane Schönlieb (Ed.), Medical image understanding and analysis: 26th annual conference, MIUA 2022, Cambridge, UK, July 27–29, 2022, proceedings. Paper presented at 26th Annual Conference on Medical Image Understanding and Analysis, MIUA 2022, Cambridge, July 27-29, 2022. (pp. 139-153). Springer
Open this publication in new window or tab >>Point2Mask: A Weakly Supervised Approach for Cell Segmentation Using Point Annotation
Show others...
2022 (English)In: Medical image understanding and analysis: 26th annual conference, MIUA 2022, Cambridge, UK, July 27–29, 2022, proceedings / [ed] Guang Yang; Angelica Aviles-Rivero; Michael Roberts; Carola-Bibiane Schönlieb, Springer, 2022, p. 139-153Conference paper, Published paper (Refereed)
Abstract [en]

Identifying cells in microscopic images is a crucial step toward studying image-based cell biology research. Cell instance segmentation provides an opportunity to study the shape, structure, form, and size of cells. Deep learning approaches for cell instance segmentation rely on the instance segmentation mask for each cell, which is a labor-intensive and expensive task. An ample amount of unlabeled microscopic data is available in the cell biology domain, but due to the tedious and exorbitant nature of the annotations needed for the cell instance segmentation approaches, the full potential of the data is not explored. This paper presents a weakly supervised approach, which can perform cell instance segmentation by using only point and bounding box-based annotation. This enormously reduces the annotation efforts. The proposed approach is evaluated on a benchmark dataset i.e., LIVECell, whereby only using a bounding box and randomly generated points on each cell, it achieved the mean average precision score of 43.53% which is as good as the full supervised segmentation method trained with complete segmentation mask. In addition, it is 3.71 times faster to annotate with a bounding box and point in comparison to full mask annotation.

Place, publisher, year, edition, pages
Springer, 2022
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 13413
Keywords
Cell segmentation, Deep learning, Point annotation, Weakly supervised
National Category
Computer Sciences
Identifiers
urn:nbn:se:umu:diva-198916 (URN)10.1007/978-3-031-12053-4_11 (DOI)000883331000011 ()2-s2.0-85135942969 (Scopus ID)978-3-031-12052-7 (ISBN)978-3-031-12053-4 (ISBN)
Conference
26th Annual Conference on Medical Image Understanding and Analysis, MIUA 2022, Cambridge, July 27-29, 2022.
Available from: 2022-09-19 Created: 2022-09-19 Last updated: 2023-09-05Bibliographically approved
Projects
Dynamic modeling in Poplar using a Systems Biology approach [2008-03588_VR]; Umeå UniversityGlobal data integration in metabolomics and systems biology [2011-06044_VR]; Umeå UniversitySSC13 - 13th Scandinavian Symposium on Chemometrics 17-20 June, Stockholm, Sweden [2013-00219_VR]; Umeå UniversitySystems analysis of wine, from the Vineyard and beyond [2016-04376_VR]; Umeå University
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-3799-6094

Search in DiVA

Show all publications