CAG-VLM: Fine-Tuning of a Large-Scale Model to Recognize Angiographic Images for Next-Generation Diagnostic Systems

Coronary angiography (CAG) is the gold-standard imaging modality for evaluating coronary artery disease, but its interpretation and subsequent treatment planning rely heavily on expert cardiologists. To enable AI-based decision support, we introduce a two-stage, physician-curated pipeline and a bilingual (Japanese/English) CAG image-report dataset. First, we sample 14,686 frames from 539 exams and annotate them for key-frame detection and left/right laterality; a ConvNeXt-Base CNN trained on this data achieves 0.96 F1 on laterality classification, even on low-contrast frames. Second, we apply the CNN to 243 independent exams, extract 1,114 key frames, and pair each with its pre-procedure report and expert-validated diagnostic and treatment summary, yielding a parallel corpus. We then fine-tune three open-source VLMs (PaliGemma2, Gemma3, and ConceptCLIP-enhanced Gemma3) via LoRA and evaluate them using VLScore and cardiologist review. Although PaliGemma2 w/LoRA attains the highest VLScore, Gemma3 w/LoRA achieves the top clinician rating (mean 7.20/10); we designate this best-performing model as CAG-VLM. These results demonstrate that specialized, fine-tuned VLMs can effectively assist cardiologists in generating clinical reports and treatment recommendations from CAG images.

Video CLIP Model for Multi-View Echocardiography Interpretation

Echocardiography involves recording videos of the heart using ultrasound, enabling clinicians to evaluate its condition. Recent advances in large-scale vision-language models (VLMs) have garnered attention for automating the interpretation of echocardiographic videos. However, most existing VLMs proposed for medical interpretation thus far rely on single-frame (i.e., image) inputs. Consequently, these image-based models often exhibit lower diagnostic accuracy for conditions identifiable through cardiac motion. Moreover, echocardiographic videos are recorded from various views that depend on the direction of ultrasound emission, and certain views are more suitable than others for interpreting specific conditions. Incorporating multiple views could potentially yield further improvements in accuracy. In this study, we developed a video-language model that takes five different views and full video sequences as input, training it on pairs of echocardiographic videos and clinical reports from 60,747 cases. Our experiments demonstrate that this expanded approach achieves higher interpretation accuracy than models trained with only single-view videos or with still images.

Enhancing Reusability of Learned Skills for Robot Manipulation via Gaze and Bottleneck

Autonomous agents capable of diverse object manipulations should be able to acquire a wide range of manipulation skills with high reusability. Although advances in deep learning have made it increasingly feasible to replicate the dexterity of human teleoperation in robots, generalizing these acquired skills to previously unseen scenarios remains a significant challenge. In this study, we propose a novel algorithm, Gaze-based Bottleneck-aware Robot Manipulation (GazeBot), which enables high reusability of the learned motions even when the object positions and end-effector poses differ from those in the provided demonstrations. By leveraging gaze information and motion bottlenecks, both crucial features for object manipulation, GazeBot achieves high generalization performance compared with state-of-the-art imitation learning methods, without sacrificing its dexterity and reactivity. Furthermore, the training process of GazeBot is entirely data-driven once a demonstration dataset with gaze data is provided. Videos and code are available at https://crumbyrobotics.github.io/gazebot.

Understanding via Gaze: Gaze-based Task Decomposition for Imitation Learning of Robot Manipulation

In imitation learning for robotic manipulation, decomposing object manipulation tasks into multiple semantic actions is essential. This decomposition enables the reuse of learned skills in varying contexts and the combination of acquired skills to perform novel tasks, rather than merely replicating demonstrated motions. Gaze, an evolutionary tool for understanding ongoing events, plays a critical role in human object manipulation, where it strongly correlates with motion planning. In this study, we propose a simple yet robust task decomposition method based on gaze transitions. We hypothesize that an imitation agent's gaze control, fixating on specific landmarks and transitioning between them, naturally segments demonstrated manipulations into sub-tasks. Notably, our method achieves consistent task decomposition across all demonstrations, which is desirable in contexts such as machine learning. Using teleoperation, a common modality in imitation learning for robotic manipulation, we collected demonstration data for various tasks, applied our segmentation method, and evaluated the characteristics and consistency of the resulting sub-tasks. Furthermore, through extensive testing across a wide range of hyperparameter variations, we demonstrated that the proposed method possesses the robustness necessary for application to different robotic systems.