# Active inference and deep generative modeling for cognitive ultrasound

arXiv: https://arxiv.org/abs/2410.13310 · HTML: https://mlsanity.com/paper/2410.13310/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 45 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Builds on (most cited first, 18 of 18)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)
- [Generative Adversarial Networks: An Overview](https://mlsanity.com/paper/1710.07035/) (2017)
- [Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography](https://mlsanity.com/paper/1908.06948/) (2019)
- [Advances in Variational Inference](https://mlsanity.com/paper/1711.05597/) (2017)
- [Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models](https://mlsanity.com/paper/2307.00619/) (2023)
- [Revisiting Active Perception](https://mlsanity.com/paper/1603.02729/) (2016)
- [Dehazing Ultrasound using Diffusion Models](https://mlsanity.com/paper/2307.11204/) (2023)
- [Removing Structured Noise with Diffusion Models](https://mlsanity.com/paper/2302.05290/) (2023)
- [Deep Ultrasound Denoising Using Diffusion Probabilistic Models](https://mlsanity.com/paper/2306.07440/) (2023)
- [Ultrasound Image Reconstruction with Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2307.15990/) (2023)
- [Info-Greedy sequential adaptive compressed sensing](https://mlsanity.com/paper/1407.0731/) (2014)
- [Active Diffusion Subsampling](https://mlsanity.com/paper/2406.14388/) (2024)
- [Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop](https://mlsanity.com/paper/1806.08083/) (2018)
- [Fast Sampling generative model for Ultrasound image reconstruction](https://mlsanity.com/paper/2312.09510/) (2023)
- [Optimization of array encoding for ultrasound imaging](https://mlsanity.com/paper/2403.00289/) (2024)

## Built on by (most cited first, 4 of 4)

- [Ultrasound Image Generation using Latent Diffusion Models](https://mlsanity.com/paper/2502.08580/) (2025)
- [High Volume Rate 3D Ultrasound Reconstruction with Diffusion Models](https://mlsanity.com/paper/2505.22090/) (2025)
- [Adaptive Bayesian Single-Shot Quantum Sensing](https://mlsanity.com/paper/2507.16477/) (2025)
- [Deep Bayesian REFoCUS](https://mlsanity.com/paper/2610.03419/) (2026)

## Abstract (arXiv)

Ultrasound (US) has the unique potential to offer access to medical imaging to anyone, everywhere. Devices have become ultra-portable and cost-effective, akin to the stethoscope. Nevertheless US image quality and diagnostic efficacy are still highly operator- and patient-dependent. In difficult-to-image patients, image quality is often insufficient for reliable diagnosis. In this paper, we put forth that US imaging systems can be recast as information-seeking agents that engage in reciprocal interactions with their anatomical environment. Such agents autonomously adapt their transmit-receive sequences to fully personalize imaging and actively maximize information gain in-situ. To that end, we will show that the sequence of pulse-echo experiments that a US system performs can be interpreted as a perception-action loop: the action is the data acquisition, probing tissue with acoustic waves and recording reflections at the detection array, and perception is the inference of the anatomical and or functional state, potentially including associated diagnostic quantities. We then equip systems with a mechanism to actively reduce uncertainty and maximize diagnostic value across a sequence of experiments, treating action and perception jointly using Bayesian inference given generative models of the environment and action-conditional pulse-echo observations. Since the representation capacity of the generative models dictates both the quality of inferred anatomical states and the effectiveness of inferred sequences of future imaging actions, we will be greatly leveraging the enormous advances in deep generative modelling that are currently disrupting many fields and society at large. Finally, we show some examples of cognitive, closed-loop, US systems that perform active beamsteering and adaptive scanline selection, based on deep generative models that track anatomical belief states.