scholarly journals A Lightweight Convolutional Neural Network Architecture Applied for Bone Metastasis Classification in Nuclear Medicine: A Case Study on Prostate Cancer Patients

Healthcare ◽  
2020 ◽  
Vol 8 (4) ◽  
pp. 493
Author(s):  
Charis Ntakolia ◽  
Dimitrios E. Diamantis ◽  
Nikolaos Papandrianos ◽  
Serafeim Moustakidis ◽  
Elpiniki I. Papageorgiou
Keyword(s):  
Neural Network ◽  
Prostate Cancer ◽  
Bone Metastasis ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Cancer Metastasis ◽  
State Of The Art ◽  
Metastatic Cancer ◽  
Whole Body ◽  
Free Parameters

Bone metastasis is among the most frequent in diseases to patients suffering from metastatic cancer, such as breast or prostate cancer. A popular diagnostic method is bone scintigraphy where the whole body of the patient is scanned. However, hot spots that are presented in the scanned image can be misleading, making the accurate and reliable diagnosis of bone metastasis a challenge. Artificial intelligence can play a crucial role as a decision support tool to alleviate the burden of generating manual annotations on images and therefore prevent oversights by medical experts. So far, several state-of-the-art convolutional neural networks (CNN) have been employed to address bone metastasis diagnosis as a binary or multiclass classification problem achieving adequate accuracy (higher than 90%). However, due to their increased complexity (number of layers and free parameters), these networks are severely dependent on the number of available training images that are typically limited within the medical domain. Our study was dedicated to the use of a new deep learning architecture that overcomes the computational burden by using a convolutional neural network with a significantly lower number of floating-point operations (FLOPs) and free parameters. The proposed lightweight look-behind fully convolutional neural network was implemented and compared with several well-known powerful CNNs, such as ResNet50, VGG16, Inception V3, Xception, and MobileNet on an imaging dataset of moderate size (778 images from male subjects with prostate cancer). The results prove the superiority of the proposed methodology over the current state-of-the-art on identifying bone metastasis. The proposed methodology demonstrates a unique potential to revolutionize image-based diagnostics enabling new possibilities for enhanced cancer metastasis monitoring and treatment.

scholarly journals ThriftyNets: Convolutional Neural Networks with Tiny Parameter Budget

IoT ◽  
2021 ◽  
Vol 2 (2) ◽  
pp. 222-235
Author(s):  
Guillaume Coiffier ◽  
Ghouthi Boukli Hacene ◽  
Vincent Gripon
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Spatial Resolution ◽  
Network Architecture ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Feature Maps ◽  
Neural Network Architecture

Deep Neural Networks are state-of-the-art in a large number of challenges in machine learning. However, to reach the best performance they require a huge pool of parameters. Indeed, typical deep convolutional architectures present an increasing number of feature maps as we go deeper in the network, whereas spatial resolution of inputs is decreased through downsampling operations. This means that most of the parameters lay in the final layers, while a large portion of the computations are performed by a small fraction of the total parameters in the first layers. In an effort to use every parameter of a network at its maximum, we propose a new convolutional neural network architecture, called ThriftyNet. In ThriftyNet, only one convolutional layer is defined and used recursively, leading to a maximal parameter factorization. In complement, normalization, non-linearities, downsamplings and shortcut ensure sufficient expressivity of the model. ThriftyNet achieves competitive performance on a tiny parameters budget, exceeding 91% accuracy on CIFAR-10 with less than 40 k parameters in total, 74.3% on CIFAR-100 with less than 600 k parameters, and 67.1% On ImageNet ILSVRC 2012 with no more than 4.15 M parameters. However, the proposed method typically requires more computations than existing counterparts.

scholarly journals Evolutionary Convolutional Neural Network: a case study

2021 ◽  
Author(s):  
Amanda Lucas Pereira ◽  
Manoela Kohler ◽  
Marco Aurélio C. Pacheco
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
State Of The Art ◽  
Building Blocks ◽  
Research Field ◽  
Search Problem ◽  
Original Network ◽  
Selection Of

Most of the state-of-the-art Convolutional Neural Network (CNN) architectures are manually crafted by experts, usually with background knowledge from extent working experience in this research field. Therefore, this manner of designing CNNs is highly limited and many approaches have been developed to try to make this procedure more automatic. This paper presents a case study in tackling the architecture search problem by using a Genetic Algorithm (GA) to optimize an existing CNN Architecture. The proposed methodology uses VGG-16 convolutional blocks as its building blocks and each individual from the GA corresponds to a possible model built from these blocks with varying filter sizes, keeping fixed the original network architecture connections. The selection of the fittest individuals are done according to their weighted F1-Score when training from scratch on the available data. To evaluate the best individual found from the proposed methodology, the performance is compared to a VGG-16 model trained from scratch on the same data.

scholarly journals Bone Metastasis Detection in the Chest and Pelvis from a Whole-Body Bone Scan Using Deep Learning and a Small Dataset

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1201
Author(s):  
Da-Chuan Cheng ◽  
Chia-Chuan Liu ◽  
Te-Chun Hsieh ◽  
Kuo-Yang Yen ◽  
Chia-Hung Kao
Keyword(s):  
Neural Network ◽  
Prostate Cancer ◽  
Bone Metastasis ◽  
Bone Scan ◽  
Diagnostic System ◽  
Whole Body ◽  
Satisfactory Performance ◽  
Body Bone ◽  
Early Diagnostic ◽  
Small Dataset

The aim of this study was to establish an early diagnostic system for the identification of the bone metastasis of prostate cancer in whole-body bone scan images by using a deep convolutional neural network (D-CNN). The developed system exhibited satisfactory performance for a small dataset containing 205 cases, 100 of which were of bone metastasis. The sensitivity and precision for bone metastasis detection and classification in the chest were 0.82 ± 0.08 and 0.70 ± 0.11, respectively. The sensitivity and specificity for bone metastasis classification in the pelvis were 0.87 ± 0.12 and 0.81 ± 0.11, respectively. We propose the use of hard example mining for increasing the sensitivity and precision of the chest D-CNN. The developed system has the potential to provide a prediagnostic report for physicians’ final decisions.

scholarly journals Efficient Bone Metastasis Diagnosis in Bone Scintigraphy Using a Fast Convolutional Neural Network Architecture

Diagnostics ◽  
2020 ◽  
Vol 10 (8) ◽  
pp. 532 ◽  
Author(s):  
Nikolaos Papandrianos ◽  
Elpiniki Papageorgiou ◽  
Athanasios Anagnostis ◽  
Konstantinos Papageorgiou
Keyword(s):  
Prostate Cancer ◽  
Neural Networks ◽  
Bone Metastasis ◽  
Bone Scintigraphy ◽  
Network Architecture ◽  
High Sensitivity ◽  
Degenerative Changes ◽  
Whole Body ◽  
Imaging Method ◽  
Medicine Physician

(1) Background: Bone metastasis is among diseases that frequently appear in breast, lung and prostate cancer; the most popular imaging method of screening in metastasis is bone scintigraphy and presents very high sensitivity (95%). In the context of image recognition, this work investigates convolutional neural networks (CNNs), which are an efficient type of deep neural networks, to sort out the diagnosis problem of bone metastasis on prostate cancer patients; (2) Methods: As a deep learning model, CNN is able to extract the feature of an image and use this feature to classify images. It is widely applied in medical image classification. This study is devoted to developing a robust CNN model that efficiently and fast classifies bone scintigraphy images of patients suffering from prostate cancer, by determining whether or not they develop metastasis of prostate cancer. The retrospective study included 778 sequential male patients who underwent whole-body bone scans. A nuclear medicine physician classified all the cases into three categories: (a) benign, (b) malignant and (c) degenerative, which were used as gold standard; (3) Results: An efficient and fast CNN architecture was built, based on CNN exploration performance, using whole body scintigraphy images for bone metastasis diagnosis, achieving a high prediction accuracy. The results showed that the method is sufficiently precise when it comes to differentiate a bone metastasis case from other either degenerative changes or normal tissue cases (overall classification accuracy = 91.61% ± 2.46%). The accuracy of prostate patient cases identification regarding normal, malignant and degenerative changes was 91.3%, 94.7% and 88.6%, respectively. To strengthen the outcomes of this study the authors further compared the best performing CNN method to other popular CNN architectures for medical imaging, like ResNet50, VGG16, GoogleNet and MobileNet, as clearly reported in the literature; and (4) Conclusions: The remarkable outcome of this study is the ability of the method for an easier and more precise interpretation of whole-body images, with effects on the diagnosis accuracy and decision making on the treatment to be applied.

Non-Blind Image Deconvolution Based on “Ringing” Removal Using Convolutional Neural Network

2020 ◽  
Vol 2020 (10) ◽  
pp. 181-1-181-7
Author(s):  
Takahiro Kudo ◽  
Takanori Fujisawa ◽  
Takuro Yamaguchi ◽  
Masaaki Ikehara
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Blind Deconvolution ◽  
Training Dataset ◽  
Image Deconvolution ◽  
Classic Problem ◽  
Key Points ◽  
Blind Image

Image deconvolution has been an important issue recently. It has two kinds of approaches: non-blind and blind. Non-blind deconvolution is a classic problem of image deblurring, which assumes that the PSF is known and does not change universally in space. Recently, Convolutional Neural Network (CNN) has been used for non-blind deconvolution. Though CNNs can deal with complex changes for unknown images, some CNN-based conventional methods can only handle small PSFs and does not consider the use of large PSFs in the real world. In this paper we propose a non-blind deconvolution framework based on a CNN that can remove large scale ringing in a deblurred image. Our method has three key points. The first is that our network architecture is able to preserve both large and small features in the image. The second is that the training dataset is created to preserve the details. The third is that we extend the images to minimize the effects of large ringing on the image borders. In our experiments, we used three kinds of large PSFs and were able to observe high-precision results from our method both quantitatively and qualitatively.

scholarly journals SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

2021 ◽  
Vol 40 (3) ◽  
pp. 1-13
Author(s):  
Lumin Yang ◽  
Jiajie Zhuang ◽  
Hongbo Fu ◽  
Xiangzhi Wei ◽  
Kun Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Large Scale ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Structure Information ◽  
Graph Neural Networks ◽  
Node Labels ◽  
Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

Sign in / Sign up

Export Citation Format

Share Document