Advances in Deep Learning Techniques for Medical Image Analysis

Niyaz, Usma; Sambyal, Abhishek Singh; Devanand,

doi:10.1109/pdgc.2018.8745790

Cited by 25 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through learning extracted features, the network parameters can be updated iteratively to realize the identification and classification on test set. Neural network based on deep learning has been applied to medical image analyzation, classification [9,10] and lesion detection after 2013 [11][12][13][14] . Cruz-Roa et al [15] use three-layer convolutional neural network (CNN) to diagnose invasive ductal carcinoma of breast cancer; the result shows that the accuracy can be improved 6% comparing with hand-crafted feature extraction.…”

Section: Introductionmentioning

confidence: 99%

Identification of Colon Cancer Using Multi-Scale Feature Fusion Convolutional Neural Network Based on Shearlet Transform

et al. 2020

View full text Add to dashboard Cite

Colon cancer identification is of great significance in medical diagnosis. Real-time, objective and accurate inspection results will facilitate medical professionals to explore symptomatic treatment promptly. However, the existing methods depend on hand-crafted features which require extensive professional expertise and long inspection period. Therefore, we propose a multi-scale feature fusion convolutional neural network (MFF-CNN) based on shearlet transform to identify histopathological image of colon cancer. The characteristic of the framework is the shearlet coefficients of histopathological image in multiple decomposition scales were extracted as supplementary feature which were also fed to the network with the original pathological image. After feature learning and feature fusion, the MFF-CNN based on shearlet transform can achieve the identification accuracy of 96% and average F-1 score of 0.9594 for colorectal adenocarcinoma epithelium (TUM) and normal colon mucosa (NORM). The false negative rate and false positive rate can be reduced to 5.5% and 2.5%, respectively. The superior performance of the network opens a new perspectives for real-time, objective and accurate diagnosis of cancer.

show abstract

Section: Introductionmentioning

confidence: 99%

Identification of Colon Cancer Using Multi-Scale Feature Fusion Convolutional Neural Network Based on Shearlet Transform

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Training a deep model by using a small datasets may cause over fitting [11] [19]. Preventing Over-fitting can be achieved by exploiting a large amount of unlabeled data with a small amount of labeled data [20] [21]. Training the model using labeled and unlabeled data this encourages the network to have a similar distribution [22] [23].…”

Section: Related Workmentioning

confidence: 99%

“…Generative adversarial network has shown great promise for medical image diagnostics [28]. To be more specific, in brain segmentation [25] [21]. Fig.…”

Section: B Generative Adversarial Networkmentioning

confidence: 99%

Multi-Model Medical Image Segmentation Using Multi-Stage Generative Adversarial Network

Khaled¹,

Han²

2021

Preprint

View full text Add to dashboard Cite

Image segmentation is a new challenge prob- lem in medical application. The use of medical imaging has become an integral part of research, as it allows us to see inside the human body without surgical intervention. Many researcher have studied brain segmentation. One stage method is used to segment the brain tissues. In this paper, we proposed the multi-stage generative ad- versarial network to solve the problem of information loss in the one-stage. We utilize the coarse-to-fine to improve brain segmentation using multi-stage generative adversar- ial networks (GAN). In the first stage, our model generated a coarse outline for (i) background and (ii) brain tissues. Then, in the second stage, the model generated outline for (i) white matter (WM), (ii) gray matter (GM) and (iii) cerebrospinal fluid (CSF). A good result can be achieved by fusing the coarse outline and refine outline. We conclude that our model is more efficient and accu- rate in practice for both infant and adult brain segmenta- tion. Moreover, we observe that multi-stage model is faster than prior models. To be more specific, the main goal of multi-stage model is to see the performance of the model in a few shot learning case where a few labeled data are available. For medical image, this proposed model can work in a wide range of image segmentation where the convolution neural networks and one-stage methods have failed.

show abstract

“…Moreover, CapsNet is able to preserve hierarchical spatial relationships, and in theory it could be as effective as any CNN but using fewer samples for training [ 14 ]. Niyaz et al [ 15 ] reviewed several deep learning methods for the prediction of different types of cancer. In that time the authors did not find evidence of the application of CapsNet in cancer diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Melanoma Recognition by Fusing Convolutional Blocks and Dynamic Routing between Capsules

Pérez

Ventura

2021

Cancers

View full text Add to dashboard Cite

Skin cancer is one of the most common types of cancers in the world, with melanoma being the most lethal form. Automatic melanoma diagnosis from skin images has recently gained attention within the machine learning community, due to the complexity involved. In the past few years, convolutional neural network models have been commonly used to approach this issue. This type of model, however, presents disadvantages that sometimes hamper its application in real-world situations, e.g., the construction of transformation-invariant models and their inability to consider spatial hierarchies between entities within an image. Recently, Dynamic Routing between Capsules architecture (CapsNet) has been proposed to overcome such limitations. This work is aimed at proposing a new architecture which combines convolutional blocks with a customized CapsNet architecture, allowing for the extraction of richer abstract features. This architecture uses high-quality 299×299×3 skin lesion images, and a hyper-tuning of the main parameters is performed in order to ensure effective learning under limited training data. An extensive experimental study on eleven image datasets was conducted where the proposal significantly outperformed several state-of-the-art models. Finally, predictions made by the model were validated through the application of two modern model-agnostic interpretation tools.

show abstract

Advances in Deep Learning Techniques for Medical Image Analysis

Cited by 25 publications

References 19 publications

Identification of Colon Cancer Using Multi-Scale Feature Fusion Convolutional Neural Network Based on Shearlet Transform

Identification of Colon Cancer Using Multi-Scale Feature Fusion Convolutional Neural Network Based on Shearlet Transform

Multi-Model Medical Image Segmentation Using Multi-Stage Generative Adversarial Network

Melanoma Recognition by Fusing Convolutional Blocks and Dynamic Routing between Capsules

Contact Info

Product

Resources

About