Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

In surgical instrument segmentation, the increasing variety of instruments over time poses a significant challenge for existing neural networks, as they are unable to effectively learn such incremental tasks and suffer from catastrophic forgetting. When learning new data, the model experiences a sharp performance drop on previously learned data. Although several continual learning methods have been proposed for incremental understanding tasks in surgical scenarios, the issue of data imbalance often leads to a strong bias in the segmentation head, resulting in poor performance. Data imbalance can occur in two forms: (i) class imbalance between new and old data, and (ii) class imbalance within the same time point of data. Such imbalances often cause the dominant classes to take over the training process of continual semantic segmentation (CSS). To address this issue, we propose SurgCSS, a novel plug-and-play CSS framework for surgical instrument segmentation under data imbalance. Specifically, we generate realistic surgical backgrounds through inpainting and blend instrument foregrounds with the generated backgrounds in a class-aware manner to balance the data distribution in various scenarios. We further propose the Class Desensitization Loss by employing contrastive learning to correct edge biases caused by data imbalance. Moreover, we dynamically fuse the weight parameters of the old and new models to achieve a better trade-off between the biased and unbiased model weights. To investigate the data imbalance problem in surgical scenarios, we construct a new benchmark for surgical instrument CSS by integrating four public datasets: EndoVis 2017, EndoVis 2018, CholecSeg8k, and SAR-RAPR50. Extensive experiments demonstrate the effectiveness of the proposed framework, achieving significant performance improvement against existing baselines. Our method demonstrates excellent potential for clinical applications. The code is publicly available at github.com/Zzsf11/SurgCSS.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2025.103728DOI Listing

Publication Analysis

Top Keywords

data imbalance
24
surgical instrument
16
instrument segmentation
12
data
10
imbalance
8
surgical scenarios
8
class imbalance
8
surgical
7
instrument
5
segmentation
5

Similar Publications

Nutritional Symbiosis Between Ants and Their Symbiotic Microbes.

Annu Rev Entomol

September 2025

2Department of Entomology and Department of Ecology and Evolutionary Biology, Cornell University, Ithaca, New York, USA; email:

Nutritional symbioses with microorganisms have profoundly shaped the evolutionary success of ants, enabling them to overcome dietary limitations and thrive across diverse ecological niches and trophic levels. These interactions are particularly crucial for ants with specialized diets, where microbial symbionts compensate for dietary imbalances by contributing to nitrogen metabolism, vitamin supplementation, and the catabolism of plant fibers and proteins. This review synthesizes recent advances in our understanding of ant-microbe symbioses, focusing on diversity, functional roles in host nutrition, and mechanisms of transmission of symbiotic microorganisms.

View Article and Find Full Text PDF

Genome imbalance, resulting from varying the dosage of individual chromosomes (aneuploidy), has a more detrimental effect than changes in complete sets of chromosomes (haploidy/polyploidy). This imbalance is likely due to disruptions in stoichiometry and interactions among macromolecular assemblies. Previous research has shown that aneuploidy causes global modulation of protein-coding genes (PCGs), microRNAs, and transposable elements (TEs), affecting both the varied chromosome (cis-located) and unvaried genome regions (trans-located) across various taxa.

View Article and Find Full Text PDF

Objective: The underrepresentation of women in thoracic surgery has been well described worldwide. Women can serve as role models for trainees and advance their careers through academic appointments, leadership positions, and involvement in thoracic societies. We aimed to characterize differences between representation of women in thoracic surgery in the United States and Europe.

View Article and Find Full Text PDF

Purpose: Emerging evidence suggests that an abnormal endometrial microbiota may be a potential factor contributing to recurrent pregnancy loss (RPL). This study aimed to characterize the endometrial microbiota in patients with RPL and to explore its association with miscarriage.

Patients And Methods: Based on specific inclusion and exclusion criteria, EndoMetrial Microbiome Assay (EMMA) data from women attending clinics were collected and categorized into RPL and control groups according to their miscarriage history.

View Article and Find Full Text PDF

Role of in chronic inflammation and the development of oral squamous cell carcinoma.

Cancer Pathog Ther

September 2025

Department of Microbiology, SRM Medical College Hospital and Research Centre, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu, 603203, Tamil Nadu, India.

Oral cancer pathogenesis is significantly influenced by species, especially , through chronic inflammation and cellular dysregulation. Epidemiological studies highlight a strong correlation between persistent infections and oral carcinogenesis. Experimental evidence has identified key biomolecular mechanisms, including biofilm formation, epithelial invasion, and immune evasion.

View Article and Find Full Text PDF