Daniel Alexander (@fishpiechicken) 's Twitter Profile
Daniel Alexander

@fishpiechicken

Professor of Computer Science. interests in computational modelling, machine learning, medical imaging, data analysis.

ID: 1140618926000185344

calendar_today17-06-2019 13:55:18

93 Tweet

672 Followers

78 Following

Daniel Alexander (@fishpiechicken) 's Twitter Profile Photo

PhDs in machine learning, imaging, disease modelling within CU-MONDAI project @CmicUCL collaborating with DRC@UCL. 1. bit.ly/46qDw1N . 2. bit.ly/44b4Mz4 . Wellcome Trust stipend +fees for home students. Join i4health CDT @medicalimaging_cdt. DL 3rd July.

Daniel Alexander (@fishpiechicken) 's Twitter Profile Photo

PhD op 1 UCL CMIC @medicalimaging_cdt: Reinforcement learning for brain connectivity mapping bit.ly/46qDw1N . Revolutionise and optimise tractography for modelling and understanding Alzheimer’s disease. Join CU-MONDAI project. Deadline 3rd July.

Daniel Alexander (@fishpiechicken) 's Twitter Profile Photo

PhD op 2 UCL CMIC @medicalimaging_cdt: Computational modelling of disease progression and subtype discovery in Alzheimer’s disease bit.ly/44b4Mz4 using completely new ways to model disease cohorts via unsupervised learning. Join CU-MONDAI project. Deadline 3rd July.

Imaging Neuroscience (@imagingneurosci) 's Twitter Profile Photo

New paper in Imaging Neuroscience The MIT Press @mitpress.bsky.social by @WijDr Peter Wijeratne, Daniel Alexander Daniel Alexander, et al: The temporal event-based model: Learning event timelines in progressive diseases direct.mit.edu/imag/article/d…

New paper in Imaging Neuroscience <a href="/mitpress/">The MIT Press @mitpress.bsky.social</a> by @WijDr Peter Wijeratne, <a href="/fishpiechicken/">Daniel Alexander</a> Daniel Alexander, et al:

The temporal event-based model: Learning event timelines in progressive diseases

direct.mit.edu/imag/article/d…
Arman Eshaghi (@es_arman) 's Twitter Profile Photo

The temporal event-based model: Learning event timelines in progressive diseases led by @WijDr direct.mit.edu/imag/article/d… and code github.com/pawij/tebm . Honoured to have had a small contribution to this important work. UCL CMIC Daniel Alexander

Pearse Keane (@pearsekeane) 's Twitter Profile Photo

1/ 🚨🚨 New paper alert 🚨🚨 Introducing RETFound, a foundation model for ophthalmology We’re super excited about this and hope it will act as a #Cornerstone for global efforts to prevent blindness through #AI UCL Institute of Ophthalmology Moorfields Eye Hospital NHS Foundation Trust #OpenAccess nature nature.com/articles/s4158…

Alex Young (@youngalexl) 's Twitter Profile Photo

Postdoc position available in the UCL POND group UCL CMIC developing machine learning tools to identify mixed pathology in dementia as part of my 8-year Wellcome-funded project. Closing date: 17th Dec. Please share: ucl.ac.uk/work-at-ucl/se…

Neil Oxtoby (Toybox Science) (@neiloxtoby) 's Twitter Profile Photo

D3PMs are an emerging set of interpretable computational tools that infer long-term disease timelines from short-term data. Our review divides D3PMs into phenomenological (higher level disease biomarker models) and pathophysiological (lower level disease mechanism models).

Neil Oxtoby (Toybox Science) (@neiloxtoby) 's Twitter Profile Photo

We provide a single framework for D3PMing that integrates phenomenological and pathophysiological models. D3PMs are directly informed by measured data, but human insight is key to the interpretability of D3PMs, avoiding the black-box nature of many AI systems.

We provide a single framework for D3PMing that integrates phenomenological and pathophysiological models. D3PMs are directly informed by measured data, but human insight is key to the interpretability of D3PMs, avoiding the black-box nature of many AI systems.
Neil Oxtoby (Toybox Science) (@neiloxtoby) 's Twitter Profile Photo

Phenomenological D3PMs include discrete, continuous, spatiotemporal, and subtyping models. Each provides their own unique insight and utility.

Phenomenological D3PMs include discrete, continuous, spatiotemporal, and subtyping models. Each provides their own unique insight and utility.
Neil Oxtoby (Toybox Science) (@neiloxtoby) 's Twitter Profile Photo

Pathophysiological D3PMs include network, dynamical systems and mechanistic combinations models. As with phenomenological D3PMs, each provides their own insight and utility.

Pathophysiological D3PMs include network, dynamical systems and mechanistic combinations models. As with phenomenological D3PMs, each provides their own insight and utility.
Neil Oxtoby (Toybox Science) (@neiloxtoby) 's Twitter Profile Photo

D3PMs have provided insights across a range of conditions (Alzheimer’s and beyond) including disease biomarker timescales, quantitative support for hypothetical biomarker trajectories and disease mechanisms, disease subtype discovery, and novel strategies for clinical trials.

D3PMs have provided insights across a range of conditions (Alzheimer’s and beyond) including disease biomarker timescales, quantitative support for hypothetical biomarker trajectories and disease mechanisms, disease subtype discovery, and novel strategies for clinical trials.
UCL Statistical Science (@stats_ucl) 's Twitter Profile Photo

Exciting Research fellow position at our department, jointly with Computer Science and the EPSRC CHAI Hub, on causal machine learning research for brain disease progression! Deadline: 30 Aug 2024. Details at ucl.ac.uk/work-at-ucl/se…