MOZI TPS
Overview
MOZI TPS (MOZI Treatment Planning System) is a next-generation AI-powered software solution designed for radiation oncology. It combines precision, speed, and adaptability for radiotherapy treatment planning. The system features a Monte Carlo Dose Engine for high-precision dosing, GPU-powered computation for fast processing, and vendor independence, supporting multiple accelerator types. MOZI TPS offers seamless automation, including AI-driven automated contouring and planning, and revolutionary on-line adaptive planning for real-time adaptation to patient anatomical changes. It supports various treatment techniques such as 3D-CRT, IMRT, VMAT, SBRT, and CBCT/MRI-guided on-line adaptation. Its core functions encompass image processing, structure delineation, plan design, optimization, and evaluation for patients with malignant or benign diseases requiring external beam irradiation with photon beams.
Reviewed by Pouyan Golshani, MD — Interventional Radiologist
Key Features
- Monte Carlo Dose Engine
- GPU-powered Computation
- Vendor Independence (supports multiple accelerator types)
- Seamless Automation (automated contouring and planning)
- Revolutionary On-line Adaptive Planning (real-time adaptation)
- Multi-Scenario Support (3DCRT, IMRT, VMAT, SBRT, On-line Adaptive)
- Deep Learning based Auto-Planning
- Image Processing
- Structure Delineation
- Plan Design, Optimization, and Evaluation
Use Cases
- Radiotherapy treatment planning for malignant diseases
- Radiotherapy treatment planning for benign diseases
- External beam irradiation with photon beams
- On-line Adaptive Radiation Therapy (ART) workflow
- Automated contouring of anatomical structures
- Dose calculation and optimization
What Physicians Need to Know
MOZI TPS offers significant advantages for radiation oncologists seeking to implement or enhance adaptive radiotherapy. Its AI-driven auto-contouring and auto-planning features can substantially reduce planning time, allowing for more efficient workflows. The ability to perform online adaptive radiotherapy (oART) using existing linear accelerators, without requiring new hardware, is a key benefit for institutions looking to upgrade their capabilities cost-effectively. Physicians should leverage the system's ability to adapt treatment plans session-by-session based on daily anatomical changes to personalize treatments and potentially improve patient outcomes, especially in cases requiring high precision or hypofractionated protocols.
MOZI TPS is designed as a vendor-independent and fully interoperable system, facilitating integration into diverse existing radiotherapy environments. It supports standard TPS integration, offers a Cloud API for broader connectivity, and includes direct Linac integration. This flexibility allows it to seamlessly fit into various clinical setups without being tied to specific hardware vendors.
Details
| Category | Oncology AI, Surgical AI |
| Pricing | Contact for pricing |
| Deployment | Standalone software |
| Compliance | |
| BAA Available | Unknown |
| HIPAA Compliant | Unknown |
| FDA Status | Cleared AI-estimated |
| Integrations | |
| EHR | Not specified |
| Specialties | Oncology |
What the Web Says
MOZI TPS by Manteia is a next-generation treatment planning system for radiation therapy, utilizing AI and deep learning to enhance precision, speed, and adaptability in cancer treatment. It aims to streamline workflows through features like automated contouring and planning, and supports various treatment techniques. The system has received regulatory approvals, including FDA clearance, and is designed to be vendor-independent.
Overall: MixedStrengths
- Combines precision, speed, and adaptability in treatment planning.
- Utilizes AI and deep learning for automated contouring and planning, enhancing efficiency.
- Supports multiple auto-planning methods for full workflow automation from dose prediction to final plan generation.
- Features a Monte Carlo dose engine for high-precision dosing in complex cases.
- Offers GPU-powered computation for lightning-fast processing.
- Vendor-independent and interoperable, integrating into existing workflows and supporting various accelerator types.
Limitations
- Relies on accurate input data and requires skilled operation by medical professionals.
- System compatibility with specific imaging devices can be a limitation.
- Adapting AI and machine learning algorithms to complex clinical scenarios presents inherent challenges.
- No peer-reviewed publications evaluating the marketed MOZI TPS were identified as of September 2026, impacting evidence rigor.
- Dose-prediction model details are vendor-provided and not publicly published, requiring local validation before clinical use.
- The Smart Optimization Engine's technical evaluation covers only conventionally fractionated IMRT and VMAT plans, with stricter review advised for other plan types.
Based on reviews from: amegroups.cn, nih.gov, healthaidb.com, manteiamedical.com, oxfordscientific.com.au, medicalnewsobserver.com, dlinrt.eu, healthairegister.com, fda.gov, parikhradiology.com
Last updated: 2026-10-30
Ratings & Reviews
No reviews yet. Be the first to review this tool!
Rate MOZI TPS
Press & Coverage
Videos
Product demos, reviews, and walkthroughs for MOZI TPS.
Office Hours with David Pudwill - UCSD Regulatory Submissions for Medical Devices on June 29, 2024
