Data crime detectives - Revision history

MriFranz: Removed from accepted

2025-07-18T09:06:58Z

Removed from accepted

← Older revision		Revision as of 11:06, 18 July 2025
Line 1:		Line 1:
	~~[[Category:Accepted_MS_2025]]~~
	<!--		<!--

MriFranz: Accepted

2025-05-07T12:30:13Z

Accepted

← Older revision		Revision as of 14:30, 7 May 2025
Line 1:		Line 1:
			[[Category:Accepted_MS_2025]]
	<!--		<!--

MoritzZaiss: speakers confirmed

2025-02-24T08:58:19Z

speakers confirmed

← Older revision		Revision as of 10:58, 24 February 2025
Line 34:		Line 34:

	* Introduction ''(10 min)''		* Introduction ''(10 min)''
	* Presentation by Reinhard Heckel ''(15 min) (Confirmed:No)''		* Presentation by Reinhard Heckel ''(15 min) (Confirmed:Yes)''
	* Presentation by Efrat Shimron ''(15 min) (Confirmed: Virtual Yes)''		* Presentation by Efrat Shimron ''(15 min) (Confirmed: Virtual Yes)''
	* Presentation by Moritz Zaiss on Simulations ''(15 min) (Confirmed:Yes)''		* Presentation by Moritz Zaiss on Simulations ''(15 min) (Confirmed:Yes)''
	* Questions and Answers ''(15 min)''		* Questions and Answers ''(15 min)''

MoritzZaiss: confirmed speaker

2025-02-24T08:57:56Z

confirmed speaker

← Older revision		Revision as of 10:57, 24 February 2025
Line 18:		Line 18:
	\| Moderators= Moritz Zaiss, Martin Uecker		\| Moderators= Moritz Zaiss, Martin Uecker
	\| Moderators_Confirmed= MZ confirmed		\| Moderators_Confirmed= MZ confirmed
	\| Speaker1= Reinhard Heckel (15 min) (		\| Speaker1= Reinhard Heckel (15 min)
	\| Speaker1_Confirmed= No		\| Speaker1_Confirmed= Yes
	\| Speaker2= Efrat Shimron (15 min)		\| Speaker2= Efrat Shimron (15 min)
	\|Speaker2_Confirmed=No\|Speaker3=Moritz Zaiss\|Speaker3_confirmed=yes}}		\|Speaker2_Confirmed=No\|Speaker3=Moritz Zaiss\|Speaker3_confirmed=yes}}

MriFranz: Add title to template

2024-12-16T09:58:47Z

Add title to template

← Older revision		Revision as of 11:58, 16 December 2024
Line 12:		Line 12:

	{{Member Session		{{Member Session
			\| title= Data crime detectives
	\| short_text= A session about data crimes in MR recon		\| short_text= A session about data crimes in MR recon
	\| duration= 60m		\| duration= 60m

MoritzZaiss: /* Session description */

2024-12-16T09:20:45Z

Session description

← Older revision		Revision as of 11:20, 16 December 2024
Line 12:		Line 12:

	{{Member Session		{{Member Session
	~~\| title= Example session~~		\| short_text= A session about data crimes in MR recon
	\| short_text= A session about ~~the future of~~ MR
	\| duration= 60m		\| duration= 60m
	\| audience= Physicists, Radiologists		\| audience= Physicists, Radiologists
	\| Moderators= ~~Herman Carr~~, ~~Edward Purcell~~		\| Moderators= Moritz Zaiss, Martin Uecker
	\| Moderators_Confirmed= ~~Carr only~~		\| Moderators_Confirmed= MZ confirmed
	\| Speaker1= ~~Paul Lauterbur~~		\| Speaker1= Reinhard Heckel (15 min) (
	\| Speaker1_Confirmed= ~~Yes~~		\| Speaker1_Confirmed= No
	\| Speaker2= ~~Peter Mansfield~~		\| Speaker2= Efrat Shimron (15 min)
	}}		\|Speaker2_Confirmed=No\|Speaker3=Moritz Zaiss\|Speaker3_confirmed=yes}}

	<!-- Add the full description of the session here below -->		<!-- Add the full description of the session here below -->

MoritzZaiss: description

2024-12-16T09:17:00Z

description

New page

{{Member Session
| title= Example session
| short_text= A session about the future of MR
| duration= 60m
| audience= Physicists, Radiologists
| Moderators= Herman Carr, Edward Purcell
| Moderators_Confirmed= Carr only
| Speaker1= Paul Lauterbur
| Speaker1_Confirmed= Yes
| Speaker2= Peter Mansfield
}}



== Session description ==

This session will be about Data Crimes in MRI reconstructon and how simmulation can help.

Retrospective subsampling, commonly used in developing reconstruction algorithms, introduces challenges that can bias results and hinder reproducibility. When k-space data synthesized from reconstructed images, such as those from public repositories, are subsampled, hidden preprocessing pipelines (e.g., lossy compression) often enhance data sparsity. This artificially boosts algorithm performance during evaluation, leading to overly optimistic results that fail to generalize to raw data (https://doi.org/10.1073/pnas.2117203119). Another challenge emerges in transient sequences, such as MP-RAGE or FLAIR, where signal evolution depends on the history of k-space acquisitions itself. As demonstrated in recent studies (https://doi.org/10.1007/978-3-031-16446-0_67, https://doi.org/10.1007/978-3-031-72104-5_23), retrospective subsampling of these sequences fails to account for altered transient magnetization dynamics. For example, subsampling k-space lines effectively removes excitation or refocusing pulses from the prospective sequence, leading to k-space data corresponding to sharper reconstructed images than those of the original sequence. If not performed with care, this approach can cause data domain shifts or data distribution shifts (https://arxiv.org/pdf/2204.07204) between retrospectively subsampled and prospectively acquired data. To raise awareness of such "data crimes" we want to dedicate this session playing detective in public datasets, papers and hands-on simulations.

The program will be the following:

* Introduction ''(10 min)''
* Presentation by Reinhard Heckel ''(15 min) (Confirmed:No)''
* Presentation by Efrat Shimron ''(15 min) (Confirmed: Virtual Yes)''
* Presentation by Moritz Zaiss on Simulations ''(15 min) (Confirmed:Yes)''
* Questions and Answers ''(15 min)''