Long bone fracture type classification for limited number of CT data with deep learning

Lee, Keon Myung; Lee, Sang Yeon; Han, Chan Sik; Choi, Seung Myung

doi:10.1145/3341105.3373900

Cited by 4 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this improvement came at the cost of an increase in training time from 1 h 23 min to 1 h 31 min. Similar results were observed when G-CNN SE(2) + DCT was trained using an augmentation dataset and compared with G-CNN SE (2), where the number of trainable parameters decreased by 870 due to the energy compaction capacity of the DCT, and the training time increased by 5 minutes. The accuracy in this scenario increased marginally, by 1.02%.…”

Section: Algorithmsupporting

confidence: 71%

“…Authors in [17] proposed a rotation-and translationinvariant deep learning framework using group theory and a special Euclidian motion group SE (2). They used SE(2) group convolution layers, which fit the classical CNNs framework and can handle rotated input samples without the need for data augmentation to encode the geometric structure given by SE(2) into CNNs.…”

Section: Related Workmentioning

confidence: 99%

“…Table(2). G-CNN reduces test error over CNN by 75%, G-CNN+DFT reduces test error over GCNN by 8%, CFNet+DCT reduces test error over GCNN+DFT by 13%, and GCNN+DCT reduces test error over CFNet+DCT by 6%.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Breast Cancer Classification Using Equivariance Transition in Group Convolutional Neural Networks

2023

View full text Add to dashboard Cite

In computer vision, rotation equivariance and translation invariance are properties of a representation that preserve the geometric structure of a transformed input. These properties are achieved in Convolutional Neural Networks (CNNs) through data augmentation. However, achieving these properties remains a challenge. This is because CNNs are not equivariance under rotation. In this study, a novel deep neural network architecture combining a group convolutional neural network (G-CNN) built with a special Euclidean (SE2) motion group and discrete cosine transform (DCT) is proposed. The former is based on the group theory and uses SE2 to guarantee equivariance in 2D images, whereas the latter is used to encode and parameterize the model space. To restore and preserve the equivariance property of the transformed and convoluted images, the DCT was used as a rotation-invariant module. These combined techniques are employed to improve breast cancer classification and data efficiency in the CNNs processing pipeline. The developed model is tested on the rotated MNIST datasets to assess its performance. Finally, the model is applied to mammography images and achieved a high computational performance and improved inference generation in breast cancer classification with an accuracy of 94.84%.

show abstract

Section: Algorithmsupporting

confidence: 71%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Breast Cancer Classification Using Equivariance Transition in Group Convolutional Neural Networks

2023

View full text Add to dashboard Cite

show abstract

Human Bone Assessment: A Deep Convolutional Neural Network Approach

Yadav

2022

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Flow-Mixup: Classifying Multi-labeled Medical Images with Corrupted Labels

Chen

Feng

et al. 2020

2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

View full text Add to dashboard Cite

In clinical practice, medical image interpretation often involves multi-labeled classification, since the affected parts of a patient tend to present multiple symptoms or comorbidities. Recently, deep learning based frameworks have attained expertlevel performance on medical image interpretation, which can be attributed partially to large amounts of accurate annotations. However, manually annotating massive amounts of medical images is impractical, while automatic annotation is fast but imprecise (possibly introducing corrupted labels). In this work, we propose a new regularization approach, called Flow-Mixup, for multi-labeled medical image classification with corrupted labels. Flow-Mixup guides the models to capture robust features for each abnormality, thus helping handle corrupted labels effectively and making it possible to apply automatic annotation. Specifically, Flow-Mixup decouples the extracted features by adding constraints to the hidden states of the models. Also, Flow-Mixup is more stable and effective comparing to other known regularization methods, as shown by theoretical and empirical analyses. Experiments on two electrocardiogram datasets and a chest X-ray dataset containing corrupted labels verify that Flow-Mixup is effective and insensitive to corrupted labels.

show abstract

Long bone fracture type classification for limited number of CT data with deep learning

Cited by 4 publications

References 12 publications

Breast Cancer Classification Using Equivariance Transition in Group Convolutional Neural Networks

Breast Cancer Classification Using Equivariance Transition in Group Convolutional Neural Networks

Human Bone Assessment: A Deep Convolutional Neural Network Approach

Flow-Mixup: Classifying Multi-labeled Medical Images with Corrupted Labels

Contact Info

Product

Resources

About