[AINews] Midjourney Medical: scan your organs like you step on a scale

2026-06-18 · Source: Latent.Space - Www.latent.space · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Emerging Technologies & Innovation, Robotics & Autonomous Systems · Depth: Advanced, extended

Summary

Midjourney has unveiled a medical imaging initiative, introducing the Midjourney Scanner and an associated Midjourney Spa. The Scanner is a prototype full-body ultrasonic CT system, described as the "first new whole-body medical imaging modality in 50 years," utilizing ultrasound instead of radiation. It features 358,000 ultrasonic elements across 40 systems in a 70 cm ring, capturing data at 17 GB/s for 40 GB per body slice, with reconstruction on 21 servers claiming 2 PFLOPS compute. Currently, Gen 1 scans take around 20 minutes, with a goal of several hundred slices in 60 seconds and 0.5 mm resolution. The first Midjourney Spa, a 25,000 sq ft facility with 9-10 scanners, is slated for a late 2027 opening in San Francisco. Midjourney, self-funded and without investors, is discussing regulatory paths with the FDA, initially focusing on body composition. The long-term vision includes a fleet of 50,000 scanners enabling a billion scans monthly, aiming for frequent, cheap, and preventive health tracking.

Key takeaway

For AI Scientists or Directors of AI/ML evaluating future healthcare infrastructure, Midjourney's ultrasonic CT scanner and spa concept signals a significant, self-funded bet on integrated hardware and AI for physical world sensing. You should recognize this as a potential model for generating vast, longitudinal health data, but also critically assess the substantial regulatory, clinical validation, and data privacy challenges inherent in moving from prototype to widespread diagnostic utility.

Key insights

Midjourney is pioneering a full-body ultrasonic CT system for accessible, frequent personal health monitoring.

Principles

• Ultrasound offers radiation-free, repeatable, data-rich imaging.
• Disruptive innovation can prioritize cost and accessibility over peak fidelity.
• AI-driven healthcare requires new infrastructure for rich bodily data.

Method

A full-body ultrasonic CT system uses 358,000 transducers in a water-immersed ring to capture high-volume data for server-based reconstruction.

In practice

• Track body composition changes over time.
• Enable frequent, preventive health screening.
• Gather longitudinal data for AI-assisted analysis.

Topics

• Medical Imaging
• Ultrasound CT
• AI in Healthcare
• Hardware Innovation
• Preventive Medicine
• Health Data

Best for: AI Scientist, Director of AI/ML, Research Scientist

Related on AIssential

• AI Startup Midjourney Pivots to Health With Ultrasound Machine — Midjourney, known for generative AI art, is pivoting into healthcare with an ultrasound machine.
• Wearables produce huge amounts of health data - and doctors are struggling to keep up — Healthcare's episodic model struggles to integrate the continuous, often unvalidated, data stream from consumer wearables.
• Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming — A novel VLM framework integrates lesion-focused reasoning and uncertainty-aware rewards for improved ultrasound diagnosis.
• From Radiology to Drug Discovery, Survey Reveals AI Is Delivering Clear Return on Investment in Healthcare — Healthcare and life sciences are rapidly moving from AI experimentation to execution, driven by strong ROI and open-source adoption.
• Two Stanford grads raise $11M to build a noninvasive wearable for hormone tracking — Clair Health offers a noninvasive wearable and AI for continuous, multi-biomarker hormone tracking to empower women's health understanding.
• A Chain-of-thought Reasoning Breast Ultrasound Dataset Covering All Histopathology Categories — BUS-CoT is a large, richly annotated breast ultrasound dataset enabling AI development for chain-of-thought reasoning across all histopathology types.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Latent.Space - Www.latent.space.