Ruohua Shi

Mrs. Ruohua Shi


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2021 in Medical Image Analysis
Verified
Journal Article
Open access
TRTobias Roß
Tobias Roß
ARAnnika Reinke
Annika Reinke
PFPeter M. Full
Peter M. Full
MWMartin Wagner
Martin Wagner
HKHannes Kenngott
Hannes Kenngott
LMLena Maier-Hein
Lena Maier-Hein
Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods for detecting, segmenting and tracking of medical instruments based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, the reliable performance of state-of-the-art methods when run on challenging images (e.g. in the presence of blood, smoke or motion artifacts). Secondly, generalization; algorithms trained for a specific intervention in a specific hospital should generalize to other interventions or institutions. In an effort to promote solutions for these limitations, we organized the Robust Medical Instrument Segmentation (ROBUST-MIS) challenge as an international benchmarking competition with a specific focus on the robustness and generalization capabilities of algorithms. For the first time in the field of endoscopic image processing, our challenge included a task on binary segmentation and also addressed multi-instance detection and segmentation. The challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures from three different types of surgery. The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap. While the average detection and segmentation quality of the best-performing algorithms is high, future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts).

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
RSRuohua Shi
Ruohua Shi
LDLingyu Duan
Lingyu Duan
THTiejun Huang
Tiejun Huang
TJTingting Jiang
Tingting Jiang
Recent advances in deep learning have greatly improved the segmentation of mitochondria from Electron Microscopy (EM) images. However, suffering from variations in mitochondrial morphology, imaging conditions, and image noise, existing methods still exhibit high uncertainty in their predictions. Moreover, in view of our findings, predictions with high levels of uncertainty are often accompanied by inaccuracies such as ambiguous boundaries and amount of false positive segments. To deal with the above problems, we propose a novel approach for mitochondria segmentation in 3D EM images that leverages evidential uncertainty estimation, which for the first time integrates evidential uncertainty to enhance the performance of segmentation. To be more specific, our proposed method not only provides accurate segmentation results, but also estimates associated uncertainty. Then, the estimated uncertainty is used to help improve the segmentation performance by an uncertainty rectification module, which leverages uncertainty maps and multi-scale information to refine the segmentation. Extensive experiments conducted on four challenging benchmarks demonstrate the superiority of our proposed method over existing approaches.


19 April 2025 in bioRxiv
Verified
Preprint
Open access
PDF file
LHLiuyuan He
Liuyuan He
RSRuohua Shi
Ruohua Shi
WWWenyao Wang
Wenyao Wang
GFGuanchen Fang
Guanchen Fang
YCYu Cai
Yu Cai
LMLei Ma
Lei Ma
Accurate analysis of electron microscopy (EM) images is essential for exploring nanoscale biological structures, yet data heterogeneity and fragmented workflows hinder scalable insights. Pretrained on large, diverse datasets, image foundation models provide a robust framework for learning transferable representations across tasks. Here, we introduce EM-DINO, the first EM image foundational model pretrained on EM-5M, a large curated and standardized EM corpus (5 million images) encompassing multiple species, tissues, protocols, and resolutions. EM-DINO’s multi-scale embeddings capture rich image features that support multiple applications, including organ-specific pattern recognition, image deduplication, and high quality image restoration. Building on these representations, we developed OmniEM, a U-shaped architecture for unified dense prediction that achieves superior performance compared with task-specific models in both image restoration and segmentation. In restoration benchmarks, OmniEM matches the performance of the EM-specific diffusion model while reducing spurious structural artifacts that could mislead interpretation. It also outperforms previous methods across 2D and 3D mitochondrial segmentation, as well as multi-class organelle segmentation tasks. Furthermore, we demonstrate OmniEM’s integrated capability to generate high-resolution segmentations from low-resolution inputs, offering the potential to enable fine-scale subcellular analysis in legacy and high-throughput EM datasets. Together, EM-5M, EM-DINO, OmniEM, and an integrated Napari plugin comprise a comprehensive end-to-end toolkit for standardized EM analysis, advancing cellular and subcellular understanding and accelerating the discovery of novel organelle morphologies and disease-related alterations.

3 June 2025 in Sensing and Imaging
Verified
Journal Article
Closed access
PDF file
RSRuohua Shi
Ruohua Shi
ZLZhaochen Liu
Zhaochen Liu
LDLingyu Duan
Lingyu Duan
TJTingting Jiang
Tingting Jiang

28 July 2023 in Bioinformatics
Verified
Journal Article
Open access
PDF file
RSRuohua Shi
Ruohua Shi
KBKeyan Bi
Keyan Bi
KDKai Du
Kai Du
LMLei Ma
Lei Ma
FFFang Fang
Fang Fang
THTiejun Huang
Tiejun Huang
Motivation: Cell membrane segmentation in electron microscopy (EM) images is a crucial step in EM image processing. However, while popular approaches have achieved performance comparable to that of humans on low-resolution EM datasets, they have shown limited success when applied to high-resolution EM datasets. The human visual system, on the other hand, displays consistently excellent performance on both low and high resolutions. To better understand this limitation, we conducted eye movement and perceptual consistency experiments. Our data showed that human observers are more sensitive to the structure of the membrane while tolerating misalignment, contrary to commonly used evaluation criteria. Additionally, our results indicated that the human visual system processes images in both global–local and coarse-to-fine manners. Results: Based on these observations, we propose a computational framework for membrane segmentation that incorporates these characteristics of human perception. This framework includes a novel evaluation metric, the perceptual Hausdorff distance (PHD), and an end-to-end network called the PHD-guided segmentation network (PS-Net) that is trained using adaptively tuned PHD loss functions and a multiscale architecture. Our subjective experiments showed that the PHD metric is more consistent with human perception than other criteria, and our proposed PS-Net outperformed state-of-the-art methods on both low- and high-resolution EM image datasets as well as other natural image datasets. Availability and implementation: The code and dataset can be found at https://github.com/EmmaSRH/PS-Net.