The methodologies that clinicians use to decide on a patient's treatment are ever changing. It seems to us that 21st century cancer medicine is much about analysing big data and using AI and statistical learning to extract information that can predict how diseases will evolve and react to therapies. However, the sad fact is that despite ever increasing effort in the field there is no tangible progress in transferring that knowledge into “bedside” practice. To this end, the brAInworks project aims to fill this gap by developing novel AI-driven real-time strategies for knowledge discovery and monitoring human disease progression such as cancer.
- Development of statistical methods to underpin Artificial Intelligence, in particular with applications to personalised medicine.
- Longitudinal and spatio-temporal models for early detection, screening and monitoring of diseases.
- In silico identification of novel therapeutic targets from multi-layered omics data.
- Developing resource-efficient methods to reduce substantial costs of learning from massive datasets.
Keywords: AI, Statistical Learning, Cancer Genomics, In Silico Medicine, Hierarchical Non-Parametric Bayesian Modelling, Longitudinal Modelling, Spatial Modelling, Imaging, Risk Estimation, Early Disease Detection
Research group leader
|His research interests include 1) personalised oncology and therapeutic target prediction in silico using big data analytics and AI, 2) time and spatial modelling of cancer evolution, 3) mutation signatures and genome scaring algorithms and 4) visualization of highly dimensional data.||His research interests are: 1) designing efficient methods to learn from multimodal data streams, where information come as different modalities such as images, text, sensory data, etc.; 2) developing resource-efficient methods to reduce substantial costs of learning from massive datasets; and 3) designing reliable and safe learning algorithms with rigorous guarantees for safety-critical systems.|
|Her research interests include 1) Design of clinical studies and experiments for association studies as well as for development and testing of Artificial Intelligence, 2) Hierarchical statistical modelling for spatial and longitudinal data, including medical images, 3) Quantification of risk and uncertainty and how to use them for decision making.|
Selected recent publications
- Barenboim M, Kovac M, Ameline B, Jones DTW, Witt O, Bielack S, Burdach S, Baumhoer D, Nathrath M. DNA methylation-based classifier and gene expression signatures detect BRCAness in osteosarcoma. PLoS Comput Biol. 2021 Nov 11;17(11):e1009562. doi: 10.1371/journal.pcbi.1009562. PMID: 34762643; PMCID: PMC8584788.
- Krishna Adithya, V., Williams, B.M., Czanner, S., Kavitha, S., Friedman, D.S., Willoughby, C.E., Venkatesh, R., Czanner, G. Effunet-spagen: An efficient and spatial generative approach to glaucoma detection (2021) Journal of Imaging, 7 (6), art. no. 92. DOI: 10.3390/jimaging7060092
- Kovac M, Ameline B, Ribi S, Kovacova M, Cross W, Barenboim M, Witt O, Bielack S, Krieg A, Hartmann W, Nathrath M, Baumhoer D. The early evolutionary landscape of osteosarcoma provides clues for targeted treatment strategies. J Pathol. 2021 Aug;254(5):556-566. doi: 10.1002/path.5699. Epub 2021 May 25. PMID: 33963544; PMCID: PMC8361660.
- Green, J., Czanner, G., Reeves, G., Watson, J., Wise, L., Beral, V. Oral bisphosphonates and risk of cancer of oesophagus, stomach, and colorectum: Case-control analysis within a UK primary care cohort (2010) BMJ, 341 (7772), art. no. c4444, p. 545. Cited 206 times. DOI: 10.1136/bmj.c4444
- I. MacCormick, B. Williams, K. Li, B. Al-Bander, S. Czanner, Y. Zheng, R. Cheeseman, C. Willoughby, G. Czanner, Accurate glaucoma diagnosis with automated spatial analysis of the cup to disc profile, PloS one 14 (1), 2019
- Cross W, Kovac M, Mustonen V, Temko D, Davis H, Baker AM, Biswas S, Arnold R, Chegwidden L, Gatenbee C, Anderson AR, Koelzer VH, Martinez P, Jiang X, Domingo E, Woodcock DJ, Feng Y, Kovacova M, Maughan T; S:CORT Consortium, Jansen M, Rodriguez-Justo M, Ashraf S, Guy R, Cunningham C, East JE, Wedge DC, Wang LM, Palles C, Heinimann K, Sottoriva A, Leedham SJ, Graham TA, Tomlinson IPM. The evolutionary landscape of colorectal tumorigenesis. Nat Ecol Evol. 2018 Oct;2(10):1661-1672. doi: 10.1038/s41559-018-0642-z. Epub 2018 Aug 31. PMID: 30177804; PMCID: PMC6152905.
- Hughes, D.M., Bonnett, L.J., Czanner, G., Komárek, A., Marson, A.G., García-Fiñana, M. Identification of patients who will not achieve seizure remission within 5 years on AEDs (2018) Neurology, 91 (22), pp. E2035-E2044. DOI: 10.1212/WNL.0000000000006564
- I. MacCormick, Y. Zheng, S. Czanner, Y. Zhao, P. Diggle, S. Harding, G. Czanner, Spatial statistical modelling of capillary non-perfusion in the retina, Scientific Reports, Volume 7, Number 1, p:16792, 2017 A. Mölder, J. Persson, Z. El-Schich, S. Czanner, A. Gjörloff-Wingren, Supervised classification of etoposide-treated in vitro adherent cells based on noninvasive imaging morphology, J. Med. Imag. 4(2), 021106 (2017), doi: 10.1117/1.JMI.4.2.021106., 2017
- Findlay JM, Castro-Giner F, Makino S, Rayner E, Kartsonaki C, Cross W, Kovac M, Ulahannan D, Palles C, Gillies RS, MacGregor TP, Church D, Maynard ND, Buffa F, Cazier JB, Graham TA, Wang LM, Sharma RA, Middleton M, Tomlinson I. Differential clonal evolution in oesophageal cancers in response to neo-adjuvant chemotherapy. Nat Commun. 2016 Apr 5;7:11111. doi: 10.1038/ncomms11111. PMID: 27045317; PMCID: PMC4822033.
- Cox, T.F., Czanner, G. A practical divergence measure for survival distributions that can be estimated from Kaplan-Meier curves (2016) Statistics in Medicine, 35 (14), pp. 2406-2421. DOI: 10.1002/sim.6868
- Kovac M, Blattmann C, Ribi S, Smida J, Mueller NS, Engert F, Castro-Giner F, Weischenfeldt J, Kovacova M, Krieg A, Andreou D, Tunn PU, Dürr HR, Rechl H, Schaser KD, Melcher I, Burdach S, Kulozik A, Specht K, Heinimann K, Fulda S, Bielack S, Jundt G, Tomlinson I, Korbel JO, Nathrath M, Baumhoer D. Exome sequencing of osteosarcoma reveals mutation signatures reminiscent of BRCA deficiency. Nat Commun. 2015 Dec 3;6:8940. doi: 10.1038/ncomms9940. PMID: 26632267; PMCID: PMC4686819.
- Czanner, G., Sarma, S.V., Ba, D., Eden, U.T., Wu, W., Eskandar, E., Lim, H.H., Temereanca, S., Suzuki, W.A., Bro wn, E.N. Measuring the signal-to-noise ratio of a neuron. (2015) Proceedings of the National Academy of Sciences of the United States of America, 112 (23), pp. 7141-7146. Cited 21 times. DOI: 10.1073/pnas.1505545112
- A. Mölder, S. Drury, N. Costen, G.M. Hartshorne, S. Czanner, Usage of normalized image variance for feature detection in embryonic imaging. Cytometry Part A 87 (2), pp 119-128, 2015
- Institute of Medical Genetics and Pathology, University Hospital Basel, Switzerland
- Clinical Eye Research Centre at Royal Liverpool University Hospital, UK
- VESELY Ocna Klinika, Slovakia
- University of Edinburgh and University of Oxford (Prof. Ian Tomlinson)
- University of Birmingham (Prof. Andrew Beggs)
- Technical University Munich (Prof. Michaela Nathrath, Dr. Maxim Barenboim)
- University of Basel (Prof. Daniel Baumhoer, Prof. Karl Heinimann)
- University of Liverpool (Prof. Stephen Kaye)
- Ulster University (Prof. Colin Willoughby)
- MIT, Harvard Medical School (Prof. Emery Brown)