EchoTab: Learning Measurement-Grounded Representations for Echocardiographic Diagnosis through Tabular Reconstruction

Michelle Espranita Liman; Ioana Ionac; Alexander Müller; Eimo Martens; Daniel Rueckert; Philip Müller

cs.LGOct 9, 2026

EchoTab: Learning Measurement-Grounded Representations for Echocardiographic Diagnosis through Tabular Reconstruction

Authors: Michelle Espranita Liman, Ioana Ionac, Alexander Müller, Eimo Martens, Daniel Rueckert, Philip Müller

Organizations: Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, Munich, Germany · Department of Cardiology, TUM University Hospital, Munich, Germany · Department of Computing, Imperial College London, London, UK · Munich Center for Machine Learning (MCML), Munich, Germany

Abstract

Diagnostic information in multi-view medical imaging studies, like echocardiography, is distributed across views, each capturing different aspects of cardiac structure and function. In clinical practice, these views are first interpreted through quantitative measurements, which then support specific diagnoses. However, existing echo representation learning methods do not explicitly model measurements as an intermediate representation between views and diagnosis. As a result, individual measurements are not explicitly represented in a form that downstream diagnostic tasks can selectively use, hindering accurate diagnosis. Inspired by this hierarchical clinical workflow, we introduce EchoTab, a measurement-grounded representation learning framework that represents multi-view echocardiography studies using measurement-specific tokens as an intermediate representation between echo views and diagnosis. Each measurement token selectively attends to the views relevant to its estimation and is trained through tabular reconstruction to predict the corresponding measurement value. The resulting tokens form a factorized echo representation, which encode clinically meaningful structural and functional properties and can be selectively used for downstream diagnosis. Unlike the commonly used contrastive approaches, EchoTab does not require negative samples or large batch sizes. Experiments on two datasets demonstrate that EchoTab learns effective measurement-grounded representations that improve diagnosis classification in multi-view echocardiography and its learned attention aligns with established measurement-view relationships used by cardiologists. Our code is accessible at https://github.com/michelleespranita/EchoTab.

Figures & tables

Figure 1: Overview of EchoTab , our measurement-grounded representation learning framework for multi-view echo studies. (1) Given an echo study, each individual view is first encoded by the echo encoder. Next, a tabular decoder lets each measurement query selectively pull information from the echo views that are relevant for estimating that measurement. This results in a set of measurement-factorized tokens for the echo study, which the prediction head uses to predict measurement values. EchoTab is trained with a tabular reconstruction objective, in which the MSE loss between available ground-truth and predicted measurements is calculated. (2) EchoTab ’s measurement-factorized tokens enables accurate diagnosis by using only the measurement tokens that are relevant for the downstream diagnosis.

Figure 2: Variants of the prediction head used in EchoTab . The prediction head is used during the tabular reconstruction of continuous measurements from their corresponding measurement-specific representations. We compare different degrees of parameter sharing to assess the trade-off between shared and measurement-specific components of the prediction function. (1) Independent heads : each measurement token has its own MLP head, enabling fully measurement-specific parameters. (2) Shared head : all measurement tokens share the same MLP head, enforcing fully shared parameters. (3) Partially shared head : all measurement tokens share the base weights of the MLP head, while a hypernetwork generates measurement-specific parameter updates, providing a compromise between shared and measurement-specific parameters. Biases are omitted for clarity.

Table 1: EchoTab ’s measurement-specific representations enable accurate diagnosis for multi-view echocardiography. By enabling diagnosis-specific selection of relevant measurement tokens, EchoTab consistently outperforms echo foundation models, as well as study- and view-level contrastive and MLP baselines, across downstream diagnosis classification tasks. Unlike contrastive approaches, EchoTab does not require large batch sizes, enabling efficient training. Bold and underlined values denote the best and second-best results.

Figure 3: Comparison of the echo views a cardiologist (left) and EchoTab (right) rely on when deriving measurements on MIMIC. EchoTab matches the cardiologist’s view in 16 of 20 (80%) measurement-view pairs, indicating it learns clinically meaningful measurement-view associations.

Method	Echo encoder	Tabular decoder	Tabular decoder queries	Prediction head	MIMIC		Internal
					Diag. clf.	Meas. pred.	Diag. clf.	Meas. pred.
MLP	✓	✗	–	Independent	.697	.392	.761	.446
				Shared	.683	-16.944	.648	-14.799
	✓	✓	Single	Independent	.720	.380	.766	.422
				Shared	.628	-16.987	.624	-14.902
EchoTab	✓	✓	Measurement	Independent	.709	.401	.764	.415

Table 2: Ablation of tabular decoder, queries, and prediction head in EchoTab . Bold and underlined values denote the best and second-best results. Diagnosis classification is measured by AUC averaged across diagnoses and measurement prediction by

R^{2}

averaged across measurements. In EchoTab , a partially shared head makes the resulting measurement tokens most effective, balancing cross-measurement representation alignment with measurement-specific representational flexibility. As a result, it achieves the best diagnosis performance on both datasets.

Measurement tokens	MIMIC	Internal
Diagnosis-relevant	.748	.778
All	.693	.751
Incorrect	.687	.757

Table 3: Ablation of the measurement tokens used for diagnosis classification (avg. AUC). Choosing diagnosis-relevant measurement tokens is essential for accurate diagnosis.

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Step	Internal	MIMIC
Initial measurements	647	302
Remove all-missing measurements	221	300
Remove stress-echo measurements	–	233
Remove non-measurement fields (demographics, hemodynamics)	–	195
Remove diagnostic labels (to be used for downstream tasks)	–	0 99
Remove all-missing measurements (second pass)	–	0 71

Appendix

Table 4: Number of measurements remaining after each filtering step. Dashes indicate steps that do not apply to the given dataset.

	Internal (patients / studies)	MIMIC (patients / studies)
Train	6,272 / 7,690	3,612 / 5,610
Validation	565 / 0 879	450 / 0 723
Test	566 / 0 861	452 / 0 730
Total	7,403 / 9,430	4,514 / 7,063

Appendix

Table 5: Dataset splits, reported as number of patients and number of echo studies.

Table 6: EchoTab still outperforms baselines when both are given diagnosis-specific prior. Baselines and reference foundation models use only diagnosis-relevant views, whereas EchoTab uses all views with diagnosis-relevant measurement tokens. Bold and underlined values denote the best and second-best results.

Views	Measurement tokens	MIMIC	Internal
All	Diagnosis-relevant	.748	.778
Diagnosis-relevant	Diagnosis-relevant	.725	.753

Appendix

Table 7: Ablation of the echo views used by EchoTab for diagnosis classification (average AUC). Restricting EchoTab to diagnosis-relevant views lowers performance on both datasets, indicating that the tabular decoder benefits from access to all views rather than a defined set of relevant views.

Task	N	T	Mi	Mi-Mo	Mo	Mo-S	S
Train
Aortic stenosis (AS)	115	-	112	-	114	-	112
Aortic regurgitation (AR)	-	9	8	9	9	9	9
Mitral regurgitation (MR)	73	75	74	75	74	73	74
Left atrium size (LA)	417	-	413	-	417	-	-
Right atrium size (RA)	152	-	153	-	152	-	149

Appendix

Table 8: Class distribution of the downstream diagnosis classification tasks of the MIMIC dataset ( N ormal, T race, Mi ld, Mi-Mo mild-to-moderate, Mo derate, Mo-S moderate-to-severe, S evere).

	Train				Val				Test
Task	N	Mi	Mo	S	N	Mi	Mo	S	N	Mi	Mo	S
Aortic stenosis (AS)	96	96	96	96	724	28	21	10	736	21	22	20
Mitral regurgitation (MR)	37	37	37	37	557	176	40	10	552	202	35	10
Left atrium size (LA)	113	113	113	113	626	47	79	26	658	46	58	24
Right atrium size (RA)	73	73	73	73	704	29	27	19	738	15	21	17
Left ventricle size (LV)	22	22	22	22	714	12	19	9	711	14	14	6

Appendix

Table 9: Class distribution of the downstream diagnosis classification tasks of our internal dataset ( N ormal, Mi ld, Mo derate, S evere).

Diagnosis	Measurements	Views
Aortic regurgitation (AR)	ar_pr_halftime	Apical Doppler
Aortic stenosis (AS)	av_mean_grad , av_pk_grad , av_pk_vel , av_area_continuity , av_vti , lvot_diam , lvot_pk_vel , lvot_vti	Apical Doppler, PLAX
Mitral regurgitation (MR)	mv_e_decel	Apical Doppler
Left atrium size (LA)	la_dimen , la_4ch_length , la_vol	PLAX, A4C, A2C
Right atrium size (RA)	ra_length	A4C
Left ventricle size (LV)	lvedd , lvesd , biplane_lvedv , biplane_lvesv	PLAX, A2C, A4C

Appendix

Table 10: Diagnosis

\rightarrow

Measurement

\rightarrow

View mapping for the MIMIC dataset, as defined by a cardiologist.

Diagnosis	Measurements	Views
Aortic stenosis (AS)	AV_Pmean , AV_Pmax , AV_Vmax , AV_VTI , AV_COA_Vmax , LVOT_Pmax , LVOT_Pmean , LVOT_VTI , LVOT_SV_D , LVOT_Vmax , LVOT_Vmean , LVOTd_2D	Apical Doppler, PLAX
Mitral regurgitation (MR)	MV_DT	Apical Doppler
Left atrium size (LA)	LADs_AC4 , LAESV_MODBP , LAAs_MOD4	PLAX, A4C, A2C
Right atrium size (RA)	RAA_2D , RAD_l_2D , RAV_A4C	A4C
Left ventricle size (LV)	LVDd_2D , LVDs_2D , LVEDV_MODBP , LVESV_MODBP	PLAX, A2C, A4C
Right ventricle size (RV)	RVDd_2D	A4C

Appendix

Table 11: Diagnosis

\rightarrow

Measurement

\rightarrow

View mapping for our internal dataset, as defined by a cardiologist.

Figure 4: Distribution of echo studies by view and data split (train/val/test) for the MIMIC and internal cohort datasets.

Token type	Remove background tokens	AUROC	Accuracy
Global (CLS)	-	0.752	0.456
Local	$\times$	0.792	0.554
Local	$\checkmark$	0.805	0.583

Appendix

Table 12:

k

-NN (

k=5

) performance on echo view classification using different configurations of echo tokens from EchoPrime. We use the configuration in the last row for all models that use EchoPrime: local tokens, excluding those that correspond to the background.

Panel of Figure 5 — Figure 5: List of measurements used from the MIMIC dataset (45 total).

Panel of Figure 6 — Figure 6: List of measurements used from our internal dataset (67 total).

Hypernetwork variant	# passes	h1w_head output dim.
L	$1$	$2rd=12288$
M	$2$	$rd=6144$
S	$2r=16$	$d=768$

Appendix

Figure 8: Hypernetwork variants used in the partially shared prediction head of EchoTab . Assume

r=8

and

d=768

. Every other module of the hypernetwork is identical across variants ( Figure 7 ).

Hypernetwork variant	Diag. clf. (avg. AUC)	Meas. pred. (avg. $R^{2}$ )
L	.735	.405
M	.748	.418
S	.743	.395

Appendix

Table 13: Ablation of the hypernetwork variants used in the partially shared prediction head of EchoTab on the MIMIC dataset. By default, our model uses the M variant.

Figure 9: Per-measurement $R^{2}$ by EchoTab on the MIMIC dataset.

Figure 10: Per-section $R^{2}$ by EchoTab on the MIMIC dataset.

Explore similar work

EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography
Jun 26, 2026Darya Taratynova, Ahmed Aly, Numan Saeed +1Medical Report Generation Echocardiography
Division of Computing and Mathematical Sciences, Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE
Beyond Independent Frames: Latent Attention Masked Autoencoders for Multi-View Echocardiography
Apr 16, 2026Simon Böhi, Irene Cannistraci, Sergio Muñoz Gonzalez +8Medical Imaging Foundation Models Masked Autoencoders
Department of Biomedical Engineering, University of Basel, Switzerland · Department of Computer Science, ETH Zurich, Switzerland
Echo2ECG: Enhancing ECG Representations with Cardiac Morphology from Multi-View Echos
Mar 9, 2026Michelle Espranita Liman, Özgün Turgut, Alexander Müller +3Multimodal Learning Electrocardiogram Classification
Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, Germany · Department of Cardiology, TUM University Hospital, Germany · Department of Computing, Imperial College London, UK +1

Jun 26, 2026J/K move · Enter open · S save

EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography

Darya Taratynova, Ahmed Aly, Numan Saeed, Mohammad Yaqub

Division of Computing and Mathematical Sciences, Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE

Medical Report Generation Echocardiography Medical VLMs Explainable Medical Image Analysis

Open paper AskPDF arXiv

Echocardiography is the most widely used non-invasive cardiac imaging modality, providing essential information for cardiovascular diagnosis. Interpreting an echocardiogram requires synthesizing complementary evidence across multiple heart views to identify abnormalities and produce structured clinical reports. While recent efforts focus on improving classification performance, most models lack explicit diagnostic reasoning and spatially grounded anatomical evidence, limiting clinician trust. We present EchoSonar-R, a multi-view reasoning-enabled vision-language model that jointly performs multi-label disease classification and report generation from echocardiography studies. EchoSonar-R combines a spatiotemporal video encoder with a structure-aware cardiac detector that provides spatially grounded anatomical cues to improve interpretability and clinician trust during cross-view reasoning. EchoSonar-R is trained in two stages: supervised fine-tuning (SFT) on reasoning-annotated targets, followed by Group Relative Policy Optimization (GRPO) with task-specific rewards that jointly align classification and report generation within a unified reinforcement-learning framework. Across a private multi-view dataset and two public benchmarks, EchoSonar-R improves macro balanced accuracy by 17.1% on the private set and 6.1% on MIMICEchoQA over the strongest baseline, achieves a GREEN clinical faithfulness score of 0.800, and produces interpretable reasoning traces grounded in multi-view visual evidence.

Abstract

Explore similar work

EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography

Beyond Independent Frames: Latent Attention Masked Autoencoders for Multi-View Echocardiography

Echo2ECG: Enhancing ECG Representations with Cardiac Morphology from Multi-View Echos