Jinfan Zhou

Jinfan Zhou, William Muirhead, Simon C. Williams et al.

Purpose: Microsurgical Aneurysm Clipping Surgery (MACS) carries a high risk for intraoperative aneurysm rupture. Automated recognition of instances when the aneurysm is exposed in the surgical video would be a valuable reference point for neuronavigation, indicating phase transitioning and more importantly designating moments of high risk for rupture. This article introduces the MACS dataset containing 16 surgical videos with frame-level expert annotations and proposes a learning methodology for surgical scene understanding identifying video frames with the aneurysm present in the operating microscope's field-of-view. Methods: Despite the dataset imbalance (80% no presence, 20% presence) and developed without explicit annotations, we demonstrate the applicability of Transformer-based deep learning architectures (MACSSwin-T, vidMACSSwin-T) to detect the aneurysm and classify MACS frames accordingly. We evaluate the proposed models in multiple-fold cross-validation experiments with independent sets and in an unseen set of 15 images against 10 human experts (neurosurgeons). Results: Average (across folds) accuracy of 80.8% (range 78.5%-82.4%) and 87.1% (range 85.1%-91.3%) is obtained for the image- and video-level approach respectively, demonstrating that the models effectively learn the classification task. Qualitative evaluation of the models' class activation maps show these to be localized on the aneurysm's actual location. Depending on the decision threshold, MACSWin-T achieves 66.7% to 86.7% accuracy in the unseen images, compared to 82% of human raters, with moderate to strong correlation.

Aneeq Zia, Kiran Bhattacharyya, Xi Liu et al.

Timely and effective feedback within surgical training plays a critical role in developing the skills required to perform safe and efficient surgery. Feedback from expert surgeons, while especially valuable in this regard, is challenging to acquire due to their typically busy schedules, and may be subject to biases. Formal assessment procedures like OSATS and GEARS attempt to provide objective measures of skill, but remain time-consuming. With advances in machine learning there is an opportunity for fast and objective automated feedback on technical skills. The SimSurgSkill 2021 challenge (hosted as a sub-challenge of EndoVis at MICCAI 2021) aimed to promote and foster work in this endeavor. Using virtual reality (VR) surgical tasks, competitors were tasked with localizing instruments and predicting surgical skill. Here we summarize the winning approaches and how they performed. Using this publicly available dataset and results as a springboard, future work may enable more efficient training of surgeons with advances in surgical data science. The dataset can be accessed from https://console.cloud.google.com/storage/browser/isi-simsurgskill-2021.

Huijie Zhang, Jinfan Zhou, Yifu Lu et al.

In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as "consistent model reproducibility": given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs. We confirm this phenomenon through comprehensive experiments, implying that different diffusion models consistently reach the same data distribution and scoring function regardless of diffusion model frameworks, model architectures, or training procedures. More strikingly, our further investigation implies that diffusion models are learning distinct distributions affected by the training data size. This is supported by the fact that the model reproducibility manifests in two distinct training regimes: (i) "memorization regime", where the diffusion model overfits to the training data distribution, and (ii) "generalization regime", where the model learns the underlying data distribution. Our study also finds that this valuable property generalizes to many variants of diffusion models, including those for conditional use, solving inverse problems, and model fine-tuning. Finally, our work raises numerous intriguing theoretical questions for future investigation and highlights practical implications regarding training efficiency, model privacy, and the controlled generation of diffusion models.

Suttisak Wizadwongsa, Jinfan Zhou, Edward Li et al.

Recent AI-based 3D content creation has largely evolved along two paths: feed-forward image-to-3D reconstruction approaches and 3D generative models trained with 2D or 3D supervision. In this work, we show that existing feed-forward reconstruction methods can serve as effective latent encoders for training 3D generative models, thereby bridging these two paradigms. By reusing powerful pre-trained reconstruction models, we avoid computationally expensive encoder network training and obtain rich 3D latent features for generative modeling for free. However, the latent spaces of reconstruction models are not well-suited for generative modeling due to their unstructured nature. To enable flow-based model training on these latent features, we develop post-processing pipelines, including protocols to standardize the features and spatial weighting to concentrate on important regions. We further incorporate a 2D image space perceptual rendering loss to handle the high-dimensional latent spaces. Finally, we propose a multi-stream transformer-based rectified flow architecture to achieve linear scaling and high-quality text-conditioned 3D generation. Our framework leverages the advancements of feed-forward reconstruction models to enhance the scalability of 3D generative modeling, achieving both high computational efficiency and state-of-the-art performance in text-to-3D generation.

Jinfan Zhou, Lixin Luo, Sungmin Eum et al.

We explore spatiotemporal data augmentation using video foundation models to diversify both camera viewpoints and scene dynamics. Unlike existing approaches based on simple geometric transforms or appearance perturbations, our method leverages off-the-shelf video diffusion models to generate realistic 3D spatial and temporal variations from a given image dataset. Incorporating these synthesized video clips as supplemental training data yields consistent performance gains in low-data settings, such as UAV-captured imagery where annotations are scarce. Beyond empirical improvements, we provide practical guidelines for (i) choosing an appropriate spatiotemporal generative setup, (ii) transferring annotations to synthetic frames, and (iii) addressing disocclusion - regions newly revealed and unlabeled in generated views. Experiments on COCO subsets and UAV-captured datasets show that, when applied judiciously, spatiotemporal augmentation broadens the data distribution along axes underrepresented by traditional and prior generative methods, offering an effective lever for improving model performance in data-scarce regimes.