Federated Learning for Medical Imaging: An Updated State of the Art

Mouhni, Naoual; Elkalay, Abderrafiaa; Chakraoui, Mohamed; Abdali, Abdelmounaïm; Ammoumou, Abdelkarim; Amalou, Ibtissam

doi:10.18280/isi.270117

Cited by 11 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed model achieved a Precision rate of 86.7%. Mouhni et al [7] highlight the recent surge in using Deep Neural Network algorithms, particularly CNNs, for medical imaging. They point out the challenge of acquiring large datasets, especially for rare diseases.…”

Section: Introductionmentioning

confidence: 99%

ESP-UNet: Encoder-Decoder Convolutional Neural Network with Edge-Enhanced Features for Liver Segmentation

Napte,

Mahajan,

Urooj

2023

View full text Add to dashboard Cite

Precise liver segmentation in Computed Tomography (CT) scans plays a pivotal role in numerous biomedical applications, spanning surgical planning, postoperative assessment, and pathological detection of hepatic diseases. The task, however, is fraught with challenges due to the inherent complexities of liver morphology, including indistinct boundaries, irregular shapes, and complex architecture. Consequences of under-segmentation and oversegmentation of the liver in CT images can lead to inaccurate localizations and diagnoses of liver diseases, underscoring the necessity for accurate segmentation. This study introduces an Encoder-Decoder Convolutional Neural Network, termed ESP-UNet, which is designed to reduce under-segmentation and over-segmentation, thereby enhancing the accuracy of liver segmentation. The proposed ESP-UNet employs Kirsch's filter to bolster the texture and edge information of liver images, thus aiding in improved segmentation performance. The efficacy of the ESP-UNet segmentation technique was evaluated using the LiTS dataset, with performance metrics including accuracy, Dice Score Coefficient (DSC), Volume Overlapping Error (VOE), and Relative Volume Difference (RVD). The algorithm yielded impressive results, with a Dice Score of 0.959, a VOE of 0.089, a Jaccard Index (JI) of 0.921, and an RVD of 0.09. Despite requiring a larger number of trainable parameters and an increased network complexity due to the parallel UNet, the proposed ESP-UNet not only enhances liver segmentation but also has the potential to improve the detection of liver cancer at the image borders. A comparison with existing state-of-the-art liver segmentation techniques revealed that ESP-UNet offers superior performance, validating its potential as a useful tool in the diagnosis and treatment of liver diseases.

show abstract

Section: Introductionmentioning

confidence: 99%

ESP-UNet: Encoder-Decoder Convolutional Neural Network with Edge-Enhanced Features for Liver Segmentation

Napte,

Mahajan,

Urooj

2023

View full text Add to dashboard Cite

show abstract

“…In this digital and information-driven era, the expansion and diversification of digital image processing techniques have been observed. These techniques now permeate various sectors, encompassing medical diagnostics, aerospace, industrial inspection, and notably, urban infrastructure maintenance [1][2][3][4]. Within this realm, bridges -crucial components of urban transport networks -play an indispensable role.…”

Section: Introductionmentioning

confidence: 99%

Utilizing Deep Learning-Based Fusion of Laser Point Cloud Data and Imagery for Digital Measurement in Steel Truss Member Applications

Li,

Liu

2023

View full text Add to dashboard Cite

In efforts to refine the digital measurement accuracy of steel truss bridge rods, a novel methodology was proposed, integrating laser point cloud technology with advanced image processing. Point cloud data, derived from stationary and handheld scanners, was meticulously fused with image datasets to produce precise rod models. Specialised algorithms tailored for point cloud data segmentation, edge detection, and geometric feature extraction were employed to derive accurate geometric attributes of the rods. Furthermore, deep learning techniques were harnessed for image segmentation and feature extraction, predicting potential deformations and delineating damage areas, significantly enhancing the accuracy of feature recognition. Through finite element analysis, errors introduced from non-fixed deformations during the scanning phase were meticulously rectified. Validations suggest that this innovative digital measurement approach, blending laser point cloud and sophisticated image processing, notably outperforms conventional methodologies in terms of precision and efficiency, offering promising avenues for subsequent research and applications in the realm of digital measurements.

show abstract

“…In the medical domain, a massive volume of image data is generated daily, attributed to the rapid advancements in medical imaging technologies. This data, sourced from an array of medical imaging equipment including MRI, CT, and X-rays [1][2][3], offers invaluable insights into patient conditions and holds significant implications for disease diagnosis and treatment [4,5]. Nevertheless, the multi-modal, highdimensionality, and intricate structure of these medical images have rendered their management and interpretation particularly challenging, especially when engaging in image matching and retrieval tasks [6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Multi-Modal Medical Image Matching Based on Multi-Task Learning and Semantic-Enhanced Cross-Modal Retrieval

Zhang

2023

View full text Add to dashboard Cite

With the continuous advancement of medical imaging technology, a vast amount of multi-modal medical image data has been extensively utilized for disease diagnosis, treatment, and research. Effective management and utilization of these data becomes a pivotal challenge, particularly when undertaking image matching and retrieval. Although numerous methods for medical image matching and retrieval exist, they primarily rely on traditional image processing techniques, often limited to manual feature extraction and singular modality handling. To address these limitations, this study introduces an algorithm for medical image matching grounded in multi-task learning, further investigating a semantic-enhanced technique for cross-modal medical image retrieval. By deeply exploring complementary semantic information between different modality medical images, these methods offer novel perspectives and tools for the domain of medical image matching and retrieval.

show abstract

Federated Learning for Medical Imaging: An Updated State of the Art

Cited by 11 publications

References 0 publications

ESP-UNet: Encoder-Decoder Convolutional Neural Network with Edge-Enhanced Features for Liver Segmentation

ESP-UNet: Encoder-Decoder Convolutional Neural Network with Edge-Enhanced Features for Liver Segmentation

Utilizing Deep Learning-Based Fusion of Laser Point Cloud Data and Imagery for Digital Measurement in Steel Truss Member Applications

Multi-Modal Medical Image Matching Based on Multi-Task Learning and Semantic-Enhanced Cross-Modal Retrieval

Contact Info

Product

Resources

About