# Surgical Text-to-Image Generation

arXiv: https://arxiv.org/abs/2407.09230 · HTML: https://mlsanity.com/paper/2407.09230/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 12 Jul 2024.

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [Brain Imaging Generation with Latent Diffusion Models](https://mlsanity.com/paper/2209.07162/) (2022)
- [Holistic Evaluation of Text-To-Image Models](https://mlsanity.com/paper/2311.04287/) (2023)
- [Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos](https://mlsanity.com/paper/2109.03223/) (2021)
- [Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domains](https://mlsanity.com/paper/2210.04133/) (2022)
- [Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets](https://mlsanity.com/paper/2007.05405/) (2020)
- [CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer Assisted Interventions](https://mlsanity.com/paper/1910.09031/) (2019)
- [Generating large labeled data sets for laparoscopic image processing tasks using unpaired image-to-image translation](https://mlsanity.com/paper/1907.02882/) (2019)
- [Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic Videos](https://mlsanity.com/paper/1812.01366/) (2018)
- [A Study on the Evaluation of Generative Models](https://mlsanity.com/paper/2206.10935/) (2022)
- [Mutually improved endoscopic image synthesis and landmark detection in unpaired image-to-image translation](https://mlsanity.com/paper/2107.06941/) (2021)
- [Navigating the Synthetic Realm: Harnessing Diffusion-based Models for Laparoscopic Text-to-Image Generation](https://mlsanity.com/paper/2312.03043/) (2023)
- [SurgiTrack: Fine-Grained Multi-Class Multi-Tool Tracking in Surgical Videos](https://mlsanity.com/paper/2405.20333/) (2024)

## Built on by (most cited first, 6 of 6)

- [SurGen: Text-Guided Diffusion Model for Surgical Video Generation](https://mlsanity.com/paper/2408.14028/) (2024)
- [SurgSora: Object-Aware Diffusion Model for Controllable Surgical Video Generation](https://mlsanity.com/paper/2412.14018/) (2024)
- [CoSimGen: Controllable Diffusion Model for Simultaneous Image and Mask Generation](https://mlsanity.com/paper/2503.19661/) (2025)
- [Mitigating Surgical Data Imbalance with Dual-Prediction Video Diffusion Model](https://mlsanity.com/paper/2510.07345/) (2025)
- [Multi-scale Temporal Prediction via Incremental Generation and Multi-agent Collaboration](https://mlsanity.com/paper/2509.17429/) (2025)
- [Towards Application Aligned Synthetic Surgical Image Synthesis](https://mlsanity.com/paper/2509.18796/) (2025)

## Abstract (arXiv)

Acquiring surgical data for research and development is significantly hindered by high annotation costs and practical and ethical constraints. Utilizing synthetically generated images could offer a valuable alternative. In this work, we explore adapting text-to-image generative models for the surgical domain using the CholecT50 dataset, which provides surgical images annotated with action triplets (instrument, verb, target). We investigate several language models and find T5 to offer more distinct features for differentiating surgical actions on triplet-based textual inputs, and showcasing stronger alignment between long and triplet-based captions. To address challenges in training text-to-image models solely on triplet-based captions without additional inputs and supervisory signals, we discover that triplet text embeddings are instrument-centric in the latent space. Leveraging this insight, we design an instrument-based class balancing technique to counteract data imbalance and skewness, improving training convergence. Extending Imagen, a diffusion-based generative model, we develop Surgical Imagen to generate photorealistic and activity-aligned surgical images from triplet-based textual prompts. We assess the model on quality, alignment, reasoning, and knowledge, achieving FID and CLIP scores of 3.7 and 26.8% respectively. Human expert survey shows that participants were highly challenged by the realistic characteristics of the generated samples, demonstrating Surgical Imagen's effectiveness as a practical alternative to real data collection.