Cross-Dataset Adaptation for Instrument Classification in Cataract Surgery Videos

• URL: http://arxiv.org/abs/2308.04035v1
• Date: Mon, 31 Jul 2023 18:14:18 GMT
• Title: Cross-Dataset Adaptation for Instrument Classification in Cataract Surgery Videos
• Authors: Jay N. Paranjape, Shameema Sikder, Vishal M. Patel, S. Swaroop Vedula
• Abstract summary: State-of-the-art models, which perform this task well on a particular dataset, perform poorly when tested on another dataset. We propose a novel end-to-end Unsupervised Domain Adaptation (UDA) method called the Barlow Adaptor. In addition, we introduce a novel loss called the Barlow Feature Alignment Loss (BFAL) which aligns features across different domains.
• Score: 54.1843419649895
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Surgical tool presence detection is an important part of the intra-operative and post-operative analysis of a surgery. State-of-the-art models, which perform this task well on a particular dataset, however, perform poorly when tested on another dataset. This occurs due to a significant domain shift between the datasets resulting from the use of different tools, sensors, data resolution etc. In this paper, we highlight this domain shift in the commonly performed cataract surgery and propose a novel end-to-end Unsupervised Domain Adaptation (UDA) method called the Barlow Adaptor that addresses the problem of distribution shift without requiring any labels from another domain. In addition, we introduce a novel loss called the Barlow Feature Alignment Loss (BFAL) which aligns features across different domains while reducing redundancy and the need for higher batch sizes, thus improving cross-dataset performance. The use of BFAL is a novel approach to address the challenge of domain shift in cataract surgery data. Extensive experiments are conducted on two cataract surgery datasets and it is shown that the proposed method outperforms the state-of-the-art UDA methods by 6%. The code can be found at https://github.com/JayParanjape/Barlow-Adaptor

Related papers

• Dual-Reference Source-Free Active Domain Adaptation for Nasopharyngeal Carcinoma Tumor Segmentation across Multiple Hospitals [9.845637899896365]
  Nasopharyngeal carcinoma (NPC) is a prevalent and clinically significant malignancy that predominantly impacts the head and neck area. We propose a novel Sourece-Free Active Domain Adaptation (SFADA) framework to facilitate domain adaptation for the Gross Tumor Volume (GTV) segmentation task. We collect a large-scale clinical dataset comprising 1057 NPC patients from five hospitals to validate our approach.
  arXiv  Detail & Related papers  (2023-09-23T15:26:27Z)
• Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning [57.43322536718131]
  We present a two-stage source-free domain adaptation (SFDA) framework for medical image segmentation. In the prototype-anchored feature alignment stage, we first utilize the weights of the pre-trained pixel-wise classifier as source prototypes. Then, we introduce the bi-directional transport to align the target features with class prototypes by minimizing its expected cost.
  arXiv  Detail & Related papers  (2023-07-19T06:07:12Z)
• Semantic segmentation of surgical hyperspectral images under geometric domain shifts [69.91792194237212]
  We present the first analysis of state-of-the-art semantic segmentation networks in the presence of geometric out-of-distribution (OOD) data. We also address generalizability with a dedicated augmentation technique termed "Organ Transplantation" Our scheme improves on the SOA DSC by up to 67 % (RGB) and 90 % (HSI) and renders performance on par with in-distribution performance on real OOD test data.
  arXiv  Detail & Related papers  (2023-03-20T09:50:07Z)
• SUPRA: Superpixel Guided Loss for Improved Multi-modal Segmentation in Endoscopy [1.1470070927586016]
  Domain shift is a well-known problem in the medical imaging community. In this paper, we explore the domain generalisation technique to enable DL methods to be used in such scenarios. We show that our method yields an improvement of nearly 20% in the target domain set compared to the baseline.
  arXiv  Detail & Related papers  (2022-11-09T03:13:59Z)
• Dispensed Transformer Network for Unsupervised Domain Adaptation [21.256375606219073]
  A novel unsupervised domain adaptation (UDA) method named dispensed Transformer network (DTNet) is introduced in this paper. Our proposed network achieves the best performance in comparison with several state-of-the-art techniques.
  arXiv  Detail & Related papers  (2021-10-28T08:27:44Z)
• Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation [64.59521853145368]
  Early and accurate severity assessment of Coronavirus disease 2019 (COVID-19) based on computed tomography (CT) images offers a great help to the estimation of intensive care unit event. To augment the labeled data and improve the generalization ability of the classification model, it is necessary to aggregate data from multiple sites. This task faces several challenges including class imbalance between mild and severe infections, domain distribution discrepancy between sites, and presence of heterogeneous features.
  arXiv  Detail & Related papers  (2021-09-08T07:56:51Z)
• Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report Generation [12.757176743817277]
  We propose class-incremental domain adaptation (CIDA) to tackle the new classes and domain shift in the target domain to generate surgical reports during robotic surgery. To generate caption from the extracted feature, curriculum by one-dimensional gaussian smoothing (CBS) is integrated with a multi-layer transformer-based caption prediction model. We observe that domain invariant feature learning and the well-calibrated network improves the surgical report generation performance in both source and target domain.
  arXiv  Detail & Related papers  (2021-07-23T09:08:26Z)
• Co-Generation and Segmentation for Generalized Surgical Instrument Segmentation on Unlabelled Data [49.419268399590045]
  Surgical instrument segmentation for robot-assisted surgery is needed for accurate instrument tracking and augmented reality overlays. Deep learning-based methods have shown state-of-the-art performance for surgical instrument segmentation, but their results depend on labelled data. In this paper, we demonstrate the limited generalizability of these methods on different datasets, including human robot-assisted surgeries.
  arXiv  Detail & Related papers  (2021-03-16T18:41:18Z)
• Fader Networks for domain adaptation on fMRI: ABIDE-II study [68.5481471934606]
  We use 3D convolutional autoencoders to build the domain irrelevant latent space image representation and demonstrate this method to outperform existing approaches on ABIDE data.
  arXiv  Detail & Related papers  (2020-10-14T16:50:50Z)
• Segmentation of Surgical Instruments for Minimally-Invasive Robot-Assisted Procedures Using Generative Deep Neural Networks [17.571763112459166]
  This work proves that semantic segmentation on minimally invasive surgical instruments can be improved by using training data. To achieve this, a CycleGAN model is used, which transforms a source dataset to approximate the domain distribution of a target dataset. This newly generated data with perfect labels is utilized to train a semantic segmentation neural network, U-Net.
  arXiv  Detail & Related papers  (2020-06-05T14:39:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.