Related references
Note: Only part of the references are listed.
Article
Computer Science, Interdisciplinary Applications
Guotai Wang et al.
Summary: The study aims to develop a new deep learning toolkit named PyMIC, which supports annotation-efficient learning for medical image segmentation. It is built on the PyTorch framework and enables the development of semi-supervised, weakly supervised, and noise-robust learning methods. Several illustrative tasks demonstrate its applications in fully supervised learning, semi-supervised learning, weakly supervised learning, and learning from noisy labels.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Computer Science, Hardware & Architecture
Museboyina Sirisha et al.
Summary: This study proposes a transformer-based network framework (TOD-Net) for object detection, which consists of encoders, decoders, transformer, and predictor modules. The predictor model bridges the gap between the encoder and transformer modules and provides better understanding of the local features of the transformer module. Experimentation with the MS COCO dataset using Python programming shows that the proposed method outperforms existing models with a precision of 68.7% and an accuracy improvement of 4%. It establishes a better trade-off compared to different prevailing approaches.
COMPUTERS & ELECTRICAL ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Luca Sestini et al.
Summary: This paper presents a fully unsupervised approach for surgical instrument segmentation, which trains a segmentation model on unlabelled endoscopic videos using motion information and instrument shape-priors. The proposed method achieves almost comparable results to state-of-the-art fully-supervised approaches on three surgical datasets.
MEDICAL IMAGE ANALYSIS
(2023)
Review
Cell Biology
Renxuan Huang et al.
Summary: Ferroptosis is crucial for various brain diseases, including glioma. Gliomas evade ferroptosis through their antioxidant capacity, leading to high malignancy and drug resistance. Targeting ferroptosis could be an effective strategy for glioma therapy, although it may also contribute to the development of drug resistance.
CELLULAR AND MOLECULAR NEUROBIOLOGY
(2022)
Article
Medicine, General & Internal
Peng Zhang et al.
Summary: Shanghai University School of Medicine, established in 2018, focuses on using intelligent medicine as a breakthrough, training graduate students in interdisciplinary medical engineering subjects, and implementing integrated medical curriculum teaching reform.
ANNALS OF MEDICINE
(2022)
Review
Automation & Control Systems
Yan Wang et al.
Summary: This paper focuses on the visual detection and tracking technology of minimally invasive surgical instruments, which analyzes the images transmitted by surgical robot endoscopes to extract the position of the surgical instrument tip for improved surgical navigation. The author summarizes the theoretical basis and related algorithms of this technology, compares their accuracy, speed, and application scenarios, and discusses their advantages and disadvantages. The study shows promising development prospects for this technology in terms of accuracy and real-time improvement.
ROBOTICS AND AUTONOMOUS SYSTEMS
(2022)
Article
Computer Science, Interdisciplinary Applications
Emanuele Colleoni et al.
Summary: This paper proposes a novel method for generating artificial surgical images to train segmentation models for surgical instrument segmentation. By combining robotic instrument simulation and recent domain adaptation techniques, the method integrates attention modules and introduces a new cost function to support supervised training from simulation frames. The authors extensively evaluate the method in terms of segmentation performance and image quality, and also release a new segmentation dataset from real surgeries for research purposes.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Computer Science, Interdisciplinary Applications
Dimitrios Psychogyios et al.
Summary: This paper proposes a learning-based framework for jointly estimating disparity and binary tool segmentation masks. The experimental results show that supervising the segmentation task improves the network's disparity estimation accuracy. The domain adaptation scheme enables domain adaptation of the adjacent disparity task. The best overall multi-task model performs well on the test sets.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Biology
Papangkorn Inkeaw et al.
Summary: This paper introduces a new method for automatically segmenting hemorrhage subtypes in head CT scans based on a deep learning model. The experimental results show that the proposed method outperforms previous studies in terms of segmentation performance for each hemorrhage subtype.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Engineering, Electrical & Electronic
Tamas Haidegger et al.
Summary: Telesurgical robotics has achieved global clinical adoption as the first domain within medicosurgical robotics. However, its market penetration is still relatively low. The adoption of telesurgical robotics has not reached its full potential due to technical complexity and financial burden. Emerging telesurgical technologies, incorporating artificial intelligence and machine learning solutions, offer significant advantages in clinical practice.
PROCEEDINGS OF THE IEEE
(2022)
Article
Chemistry, Analytical
Guillermo Sanchez-Brizuela et al.
Summary: This article presents a hand-labelled dataset with 4003 frames for gauze segmentation and analyzes the performance of several baseline algorithms. The results show that using U-Net for segmentation achieves good accuracy and speed in real-time operation.
Article
Engineering, Biomedical
Xinan Sun et al.
Summary: This paper proposes a method based on Mask R-CNN for accurate instance segmentation of surgical instruments. A novel feature extraction backbone is built to extract both local and global features, and skip fusions are applied to improve the network's generalization ability. The experimental results demonstrate that the proposed method achieves state-of-the-art performance in surgical instrument segmentation tasks, with improved accuracy.
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
(2022)
Article
Computer Science, Interdisciplinary Applications
Ran Gu et al.
Summary: The study presented a comprehensive attention-based CNN (CA-Net) for medical image segmentation, which significantly improved accuracy and explainability. The CA-Net achieved better segmentation results for skin lesions, placenta, and fetal brain compared to the U-Net model, while reducing the model size by approximately 15 times.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Biology
Sue Min Cho et al.
Summary: This study evaluated an automatic tip detection method for surgical instruments in endoscopic surgery, compared two state-of-the-art detection algorithms, RetinaNet and YOLOv2, and validated the robustness with cross-validation.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Computer Science, Interdisciplinary Applications
Cheng Chen et al.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2020)
Article
Engineering, Biomedical
Heewon Chung et al.
IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE
(2018)
Article
Engineering, Biomedical
Thomas Neumuth et al.
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
(2012)
Article
Engineering, Electrical & Electronic
Antonio Torralba et al.
PROCEEDINGS OF THE IEEE
(2010)
Article
Clinical Neurology
H Duffau et al.
JOURNAL OF NEUROLOGY NEUROSURGERY AND PSYCHIATRY
(2003)
Article
Computer Science, Artificial Intelligence
L Breiman