EchoChat is a generative multimodal vision‑language model that performs comprehensive echocardiographic analysis, emulating a cardiologist’s cognitive workflow. Trained on 46,358 examinations, it achieves state‑of‑the‑art performance across 33 cardiac conditions, including 15 new ones, and outperforms existing foundation models in both recognition and quantification tasks. In a blinded reader study, reports co‑generated with EchoChat were rated higher in diagnostic accuracy and completeness, improving F1 score from 72.78% to 82.75%.
By Yi Qin, Marawan Elbatel, Shanshan Song, Taoran Huang, Jiarong Guo, Ningshu Li, Lehan Wang, Chenxu Zhao, Jiexin He, Machteld J. Boonstra, Stephan van der Zwaard, Marielle C. van de Veerdonk, Pere Lopez-Gutierrez, Lydia Dux-Santoy, Andrea Guala, Enrique Almar-Munoz, Sebastian Johannes Reinstadler, Radek Debiec, Yi-Hang Zhu, Huiyu Zhou, Adrian P Cheong, Yike Guo, Agnes Mayr, Karim Lekadir, Yong Jiang, Nilesh J. Samani, Dacheng Tao, Folkert W. Asselbergs, Hongwen Fei, Alex PW Lee, Xiaomeng Li
arXiv:2607. 15380v1 Announce Type: cross Abstract: Electronic health records combine free-text clinical narratives with structured measurements such as vital signs, laboratory values, and comorbidities.
By Ajay Madhavan Ravichandran, Bilgin Osmandoja, Klemens Budde, Klaus Netter, Tobias Strapatsas, Aljoscha Burchardt, Sebastian M\"oller, Roland Roller
The paper introduces the first publicly available dataset of over 25,000 parasternal long‑axis (PLAX) echocardiography videos labeled for left ventricular ejection fraction (EF), created through a novel data‑generation strategy that links clinical notes to video data. Using this dataset, the authors train a reproducible PLAX‑based EF model that achieves a mean absolute error (MAE) of 6.86%, comparable to the clinical standard of apical four‑chamber (A4C) methods. They further show that simple late fusion of PLAX and A4C predictions reduces MAE to 6.37%, highlighting the benefit of multi‑view integration, and release the dataset, models, and demos publicly.
By Zhiyuan Gao, Dominic Yurk, Yaser S. Abu-Mostafa
The paper introduces the first publicly available dataset for predicting left ventricular ejection fraction (EF) from parasternal long-axis (PLAX) echocardiography, comprising over 25,000 labeled videos generated through a novel data‑generation strategy that correlates clinical notes with echocardiographic videos. Using this dataset, the authors train a reproducible PLAX‑EF model that achieves a mean absolute error (MAE) of 6.86%, comparable to the clinical standard of apical four‑chamber (A4C) methods. They further show that combining PLAX and A4C predictions via simple late fusion reduces MAE to 6.37%, highlighting the benefit of multi‑view integration, and they release the dataset, models, and demos for community use.
arXiv:2606. 28164v1 Announce Type: cross Abstract: Echocardiography is the most widely used non-invasive cardiac imaging modality, providing essential information for cardiovascular diagnosis.
By Darya Taratynova, Ahmed Aly, Numan Saeed, Mohammad Yaqub
Breast ultrasound (BUS) is widely used for breast cancer diagnosis yet remains operator-dependent. While deep learning shows promise, ensuring diagnostic reliability and interpretability is challengin...
The paper presents a two‑stage framework for prenatal congenital heart disease (CHD) screening that operates directly on whole fetal ultrasound studies. It first learns transferable frame representations via self‑supervised masked‑autoencoder pre‑training, then identifies cardiac frames with a disease‑robust module and aggregates them using a transformer‑based multiple instance learning model to produce a case‑level diagnosis. The approach achieves high performance (AUC 0.985, specificity 0.990) on an internal test set and, after label‑free CORAL adaptation, improves to an AUC of 0.944 on an external cohort, outperforming existing baselines.
By Mohamed Azzam, Ruobing Liu, Esther C. Ugwueke, Ziyang Xu, Shibiao Wan, Alex Foy, Abraham Zabih, Jason Christensen, Neil Hamill, Ling Li, Jieqiong Wang
arXiv:2606. 17437v1 Announce Type: cross Abstract: Automated classification of standard echocardiographic views is crucial for efficient clinical workflow but faces three main challenges.
By Bo Gou, Jicheng Zhang, Jianlong Xiong, Tao He, Bentian Liu, Hai Wu, Yijiao Wang, Yu Zhang, Yujia Yang, Yun Dai, Jian Liu, Jie Wang
EchoTab is a representation learning framework for multi‑view echocardiography that uses measurement‑specific tokens as an intermediate representation between echo views and diagnosis. Each token attends to the views relevant to its measurement and is trained via tabular reconstruction to predict the measurement value, producing a factorized representation that encodes clinically meaningful structural and functional properties. Experiments on two datasets show that EchoTab improves diagnosis classification and that its learned attention aligns with cardiologists’ established measurement‑view relationships.
By Michelle Espranita Liman, Ioana Ionac, Alexander M\"uller, Eimo Martens, Daniel Rueckert, Philip M\"uller
The paper introduces the Boot-and-Feedback (BooF) framework, which facilitates collaboration between multimodal large language models (MLLMs) and expert vision models for breast ultrasound (BUS) diagnosis. In the Boot Stage, the MLLM is guided by the BI-RADS lexicon and preliminary expert predictions to generate reliable textual descriptions, while the Feedback Stage fuses these descriptions with visual features using an Attention-Gated Cross-Modality Fusion Module, allowing the expert model to incorporate textual insights and filter out noise. Experiments on multiple BUS datasets show that BooF improves both diagnostic accuracy and interpretability compared to existing methods.
By Ming Cheng, Hongyu Sun, Zhaolin Chen, Jun Liu, Hossein Rahmani, Qiuhong Ke
arXiv:2606. 19183v1 Announce Type: cross Abstract: Large language models (LLMs) can make clinical decision support more accessible by interpreting free-text documentation, but their direct use as diagnostic engines is limited by sensitivity to prompts, information order, and plausible but incorrect outputs.
By Soheyl Bateni, Maryam Abdolali
The paper introduces CAST, a concept-guided artifact suppression tuning framework that uses sparse autoencoders to identify and suppress note-specific artifacts in clinical language models. CAST labels latent features with an LLM-assisted pipeline and ICD‑10 constraints, then fine‑tunes the model while providing post‑hoc per‑concept attributions for auditability. In experiments on MIMIC‑IV discharge‑note mortality prediction, CAST outperforms standard fine‑tuned encoders and competes with strong LLM baselines while offering a feature‑level audit trail of clinical concepts and suppressed artifacts.
By Jin Mu, Guanhua Chen