Surgical Text-to-Image Generation

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 conduct an in-depth analysis on adapting text-to-image generative models for the surgical domain, leveraging the CholecT50 dataset, which provides surgical images annotated with surgical action triplets (instrument, verb, target). We investigate various language models and find T5 to offer more distinct features for differentiating surgical actions based on triplet-based textual inputs. Our analysis demonstrates strong alignment between long and triplet-based captions, supporting the use of triplet-based labels. We address the challenges in training text-to-image models on triplet-based captions without additional input signals by uncovering that triplet text embeddings are instrument-centric in the latent space and then, by designing an instrument-based class balancing technique to counteract the imbalance and skewness in the surgical data, 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 evaluate our model using diverse metrics, including human expert surveys and automated methods like FID and CLIP scores. We assess the model performance on key aspects: quality, alignment, reasoning, knowledge, and robustness, demonstrating the effectiveness of our approach in providing a realistic alternative to real data collection.

CycleSAM: One-Shot Surgical Scene Segmentation using Cycle-Consistent Feature Matching to Prompt SAM

The recently introduced Segment-Anything Model (SAM) has the potential to greatly accelerate the development of segmentation models. However, directly applying SAM to surgical images has key limitations including (1) the requirement of image-specific prompts at test-time, thereby preventing fully automated segmentation, and (2) ineffectiveness due to substantial domain gap between natural and surgical images. In this work, we propose CycleSAM, an approach for one-shot surgical scene segmentation that uses the training image-mask pair at test-time to automatically identify points in the test images that correspond to each object class, which can then be used to prompt SAM to produce object masks. To produce high-fidelity matches, we introduce a novel spatial cycle-consistency constraint that enforces point proposals in the test image to rematch to points within the object foreground region in the training image. Then, to address the domain gap, rather than directly using the visual features from SAM, we employ a ResNet50 encoder pretrained on surgical images in a self-supervised fashion, thereby maintaining high label-efficiency. We evaluate CycleSAM for one-shot segmentation on two diverse surgical semantic segmentation datasets, comprehensively outperforming baseline approaches and reaching up to 50% of fully-supervised performance.

Self-supervised Learning via Cluster Distance Prediction for Operating Room Context Awareness

Semantic segmentation and activity classification are key components to creating intelligent surgical systems able to understand and assist clinical workflow. In the Operating Room, semantic segmentation is at the core of creating robots aware of clinical surroundings, whereas activity classification aims at understanding OR workflow at a higher level. State-of-the-art semantic segmentation and activity recognition approaches are fully supervised, which is not scalable. Self-supervision can decrease the amount of annotated data needed. We propose a new 3D self-supervised task for OR scene understanding utilizing OR scene images captured with ToF cameras. Contrary to other self-supervised approaches, where handcrafted pretext tasks are focused on 2D image features, our proposed task consists of predicting the relative 3D distance of image patches by exploiting the depth maps. Learning 3D spatial context generates discriminative features for our downstream tasks. Our approach is evaluated on two tasks and datasets containing multi-view data captured from clinical scenarios. We demonstrate a noteworthy improvement of performance on both tasks, specifically on low-regime data where utility of self-supervised learning is the highest.

SurgiTrack: Fine-Grained Multi-Class Multi-Tool Tracking in Surgical Videos

Accurate tool tracking is essential for the success of computer-assisted intervention. Previous efforts often modeled tool trajectories rigidly, overlooking the dynamic nature of surgical procedures, especially tracking scenarios like out-of-body and out-of-camera views. Addressing this limitation, the new CholecTrack20 dataset provides detailed labels that account for multiple tool trajectories in three perspectives: (1) intraoperative, (2) intracorporeal, and (3) visibility, representing the different types of temporal duration of tool tracks. These fine-grained labels enhance tracking flexibility but also increase the task complexity. Re-identifying tools after occlusion or re-insertion into the body remains challenging due to high visual similarity, especially among tools of the same category. This work recognizes the critical role of the tool operators in distinguishing tool track instances, especially those belonging to the same tool category. The operators' information are however not explicitly captured in surgical videos. We therefore propose SurgiTrack, a novel deep learning method that leverages YOLOv7 for precise tool detection and employs an attention mechanism to model the originating direction of the tools, as a proxy to their operators, for tool re-identification. To handle diverse tool trajectory perspectives, SurgiTrack employs a harmonizing bipartite matching graph, minimizing conflicts and ensuring accurate tool identity association. Experimental results on CholecTrack20 demonstrate SurgiTrack's effectiveness, outperforming baselines and state-of-the-art methods with real-time inference capability. This work sets a new standard in surgical tool tracking, providing dynamic trajectories for more adaptable and precise assistance in minimally invasive surgeries.

HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition

Natural language could play an important role in developing generalist surgical models by providing a broad source of supervision from raw texts. This flexible form of supervision can enable the model's transferability across datasets and tasks as natural language can be used to reference learned visual concepts or describe new ones. In this work, we present HecVL, a novel hierarchical video-language pretraining approach for building a generalist surgical model. Specifically, we construct a hierarchical video-text paired dataset by pairing the surgical lecture video with three hierarchical levels of texts: at clip-level, atomic actions using transcribed audio texts; at phase-level, conceptual text summaries; and at video-level, overall abstract text of the surgical procedure. Then, we propose a novel fine-to-coarse contrastive learning framework that learns separate embedding spaces for the three video-text hierarchies using a single model. By disentangling embedding spaces of different hierarchical levels, the learned multi-modal representations encode short-term and long-term surgical concepts in the same model. Thanks to the injected textual semantics, we demonstrate that the HecVL approach can enable zero-shot surgical phase recognition without any human annotation. Furthermore, we show that the same HecVL model for surgical phase recognition can be transferred across different surgical procedures and medical centers.

On-the-Fly Point Annotation for Fast Medical Video Labeling

Purpose: In medical research, deep learning models rely on high-quality annotated data, a process often laborious and timeconsuming. This is particularly true for detection tasks where bounding box annotations are required. The need to adjust two corners makes the process inherently frame-by-frame. Given the scarcity of experts' time, efficient annotation methods suitable for clinicians are needed. Methods: We propose an on-the-fly method for live video annotation to enhance the annotation efficiency. In this approach, a continuous single-point annotation is maintained by keeping the cursor on the object in a live video, mitigating the need for tedious pausing and repetitive navigation inherent in traditional annotation methods. This novel annotation paradigm inherits the point annotation's ability to generate pseudo-labels using a point-to-box teacher model. We empirically evaluate this approach by developing a dataset and comparing on-the-fly annotation time against traditional annotation method. Results: Using our method, annotation speed was 3.2x faster than the traditional annotation technique. We achieved a mean improvement of 6.51 +- 0.98 AP@50 over conventional method at equivalent annotation budgets on the developed dataset. Conclusion: Without bells and whistles, our approach offers a significant speed-up in annotation tasks. It can be easily implemented on any annotation platform to accelerate the integration of deep learning in video-based medical research.

SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation

We present a new self-supervised approach, SelfPose3d, for estimating 3d poses of multiple persons from multiple camera views. Unlike current state-of-the-art fully-supervised methods, our approach does not require any 2d or 3d ground-truth poses and uses only the multi-view input images from a calibrated camera setup and 2d pseudo poses generated from an off-the-shelf 2d human pose estimator. We propose two self-supervised learning objectives: self-supervised person localization in 3d space and self-supervised 3d pose estimation. We achieve self-supervised 3d person localization by training the model on synthetically generated 3d points, serving as 3d person root positions, and on the projected root-heatmaps in all the views. We then model the 3d poses of all the localized persons with a bottleneck representation, map them onto all views obtaining 2d joints, and render them using 2d Gaussian heatmaps in an end-to-end differentiable manner. Afterwards, we use the corresponding 2d joints and heatmaps from the pseudo 2d poses for learning. To alleviate the intrinsic inaccuracy of the pseudo labels, we propose an adaptive supervision attention mechanism to guide the self-supervision. Our experiments and analysis on three public benchmark datasets, including Panoptic, Shelf, and Campus, show the effectiveness of our approach, which is comparable to fully-supervised methods. Code is available at \url{https://github.com/CAMMA-public/SelfPose3D}

Enhancing Gait Video Analysis in Neurodegenerative Diseases by Knowledge Augmentation in Vision Language Model

We present a knowledge augmentation strategy for assessing the diagnostic groups and gait impairment from monocular gait videos. Based on a large-scale pre-trained Vision Language Model (VLM), our model learns and improves visual, textual, and numerical representations of patient gait videos, through a collective learning across three distinct modalities: gait videos, class-specific descriptions, and numerical gait parameters. Our specific contributions are two-fold: First, we adopt a knowledge-aware prompt tuning strategy to utilize the class-specific medical description in guiding the text prompt learning. Second, we integrate the paired gait parameters in the form of numerical texts to enhance the numeracy of the textual representation. Results demonstrate that our model not only significantly outperforms state-of-the-art (SOTA) in video-based classification tasks but also adeptly decodes the learned class-specific text features into natural language descriptions using the vocabulary of quantitative gait parameters. The code and the model will be made available at our project page.

Optimizing Latent Graph Representations of Surgical Scenes for Zero-Shot Domain Transfer

Purpose: Advances in deep learning have resulted in effective models for surgical video analysis; however, these models often fail to generalize across medical centers due to domain shift caused by variations in surgical workflow, camera setups, and patient demographics. Recently, object-centric learning has emerged as a promising approach for improved surgical scene understanding, capturing and disentangling visual and semantic properties of surgical tools and anatomy to improve downstream task performance. In this work, we conduct a multi-centric performance benchmark of object-centric approaches, focusing on Critical View of Safety assessment in laparoscopic cholecystectomy, then propose an improved approach for unseen domain generalization. Methods: We evaluate four object-centric approaches for domain generalization, establishing baseline performance. Next, leveraging the disentangled nature of object-centric representations, we dissect one of these methods through a series of ablations (e.g. ignoring either visual or semantic features for downstream classification). Finally, based on the results of these ablations, we develop an optimized method specifically tailored for domain generalization, LG-DG, that includes a novel disentanglement loss function. Results: Our optimized approach, LG-DG, achieves an improvement of 9.28% over the best baseline approach. More broadly, we show that object-centric approaches are highly effective for domain generalization thanks to their modular approach to representation learning. Conclusion: We investigate the use of object-centric methods for unseen domain generalization, identify method-agnostic factors critical for performance, and present an optimized approach that substantially outperforms existing methods.

Overcoming Dimensional Collapse in Self-supervised Contrastive Learning for Medical Image Segmentation

Self-supervised learning (SSL) approaches have achieved great success when the amount of labeled data is limited. Within SSL, models learn robust feature representations by solving pretext tasks. One such pretext task is contrastive learning, which involves forming pairs of similar and dissimilar input samples, guiding the model to distinguish between them. In this work, we investigate the application of contrastive learning to the domain of medical image analysis. Our findings reveal that MoCo v2, a state-of-the-art contrastive learning method, encounters dimensional collapse when applied to medical images. This is attributed to the high degree of inter-image similarity shared between the medical images. To address this, we propose two key contributions: local feature learning and feature decorrelation. Local feature learning improves the ability of the model to focus on the local regions of the image, while feature decorrelation removes the linear dependence among the features. Our experimental findings demonstrate that our contributions significantly enhance the model's performance in the downstream task of medical segmentation, both in the linear evaluation and full fine-tuning settings. This work illustrates the importance of effectively adapting SSL techniques to the characteristics of medical imaging tasks. The source code will be made publicly available at: https://github.com/CAMMA-public/med-moco