Residual Learning

Zarvani, Maral; Saberi, Sara; Azmi, Reza; Shojaedini, Seyed Vahab

doi:10.4103/jmss.jmss_38_20

Cited by 6 publications

(4 citation statements)

References 33 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the main problems which arise in DL architectures is gradient vanishing. The research [ 102 ] focuses on the gradient vanishing problem and proposed a model residual of residual (ROR) U-Net model. The encoding path of the proposed model is similar to ResNet-U-Net, but three shortcut levels are introduced in the ResNet-U-Net model.…”

Section: LV Segmentation Using Dl Architecturesmentioning

confidence: 99%

“…Study Software [120] MATLAB 2019a [98] TensorFlow [92] Python/Keras [100] TensorFlow r1.12 and Keras 2.2.4. [86] Keras [77] MATLAB 2013a [99] Python with Keras-TensorFlow [78] TensorFlow/Ubuntu 18.04 [88] Pytorch/Ubuntu18.04 [101] Keras [102] Keras [80] MATLAB R2020 [89] Keras [106] TensorFlow [111] Keras [115] TensorFlow [107] MATLAB [108] MATLAB R 2016b [64] TensorFlow [105] TensorFlow [121] TensorFlow [116] MatConvNet, an open-source library in MATLAB [117] TensorFlow [118] Pytorch [113] TensorFlow [114] TensorFlow [122] Anaconda 5.0.1 (python 3.5), TensorFlow, and Tensorlayer environment [119] PyCharm Table 4: Te detail of datasets used for LV segmentation.…”

Section: Datasetmentioning

confidence: 99%

“…Study Dataset [63,68,69,81,95,96,102], Sunnybrook [57] TWINS-UK [61,66,77,95,97,103,104,120], ACDC [38,61,66,85,86,107,121], MICCAI [92,94,100,114] CAMUS [101,104] LVSC [97,101] STACOM [77] (UKBB) [81] Cardiac Atlas [113] CETUS [103] TOF [62] Own dataset (220 subjects) [75] Own dataset (5008 subjects and 93,500 images) [61] Own dataset [49] Own dataset 1100 subjects [49] Own dataset 1100 subjects [82] Own dataset (69 images) [83] Own dataset (500 patients) [84] Own dataset (250 patients) [91] Own dataset (596 subjects) [90] Own dataset (94 cases) [98] York + own dataset (17,683 images) [100] Own dataset (1080 + 290) + [99] Own dataset (5000 Pocus + 16000 cart base...…”

Section: Datasetmentioning

confidence: 99%

See 2 more Smart Citations

An Overview of Deep Learning Methods for Left Ventricle Segmentation

Shoaib

Chuah

Raza

et al. 2023

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Cardiac health diseases are one of the key causes of death around the globe. The number of heart patients has considerably increased during the pandemic. Therefore, it is crucial to assess and analyze the medical and cardiac images. Deep learning architectures, specifically convolutional neural networks have profoundly become the primary choice for the assessment of cardiac medical images. The left ventricle is a vital part of the cardiovascular system where the boundary and size perform a significant role in the evaluation of cardiac function. Due to automatic segmentation and good promising results, the left ventricle segmentation using deep learning has attracted a lot of attention. This article presents a critical review of deep learning methods used for the left ventricle segmentation from frequently used imaging modalities including magnetic resonance images, ultrasound, and computer tomography. This study also demonstrates the details of the network architecture, software, and hardware used for training along with publicly available cardiac image datasets and self-prepared dataset details incorporated. The summary of the evaluation matrices with results used by different researchers is also presented in this study. Finally, all this information is summarized and comprehended in order to assist the readers to understand the motivation and methodology of various deep learning models, as well as exploring potential solutions to future challenges in LV segmentation.

show abstract

Section: LV Segmentation Using Dl Architecturesmentioning

confidence: 99%

Section: Datasetmentioning

confidence: 99%

Section: Datasetmentioning

confidence: 99%

See 1 more Smart Citation

An Overview of Deep Learning Methods for Left Ventricle Segmentation

Shoaib

Chuah

Raza

et al. 2023

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The CNN cannot detect and interpret the overall piece simultaneously, repetitively examining the tiny pixel areas until the complete image is captured. Spatial adjustment levels and VGG19 have been utilized to retrieve functions, and ReLU stimulation was implemented as an accelerator because of its underlying minimal complexity and great computational speed [14][15][16]. The significant contribution of the current technique is that the image's fundamental, predictive characteristics remain, coupled with a substantial drop in dimensions.…”

Section: Literature Surveymentioning

confidence: 99%

An Efficient Multilevel Thresholding Scheme for Heart Image Segmentation Using a Hybrid Generalized Adversarial Network

Reddy

Kola

Jayaram³

et al. 2022

Journal of Sensors

View full text Add to dashboard Cite

Most people worldwide, irrespective of their age, are suffering from massive cardiac arrest. To detect heart attacks early, many researchers worked on the clinical datasets collected from different open-source datasets like PubMed and UCI repository. However, most of these datasets have collected nearly 13 to 147 raw attributes in textual format and implemented traditional data mining approaches. Traditional machine learning approaches just analyze the data extracted from the images, but the extraction mechanism is inefficient and it requires more number of resources. The authors of this research article proposed a system that is aimed at predicting heart attacks by integrating the techniques of computer vision and deep learning approaches on the heart images collected from the clinical labs, which are publicly available in the KAGGLE repository. The authors collected live images of the heart by scanning the images through IoT sensors. The primary focus is to enhance the quality and quantity of the heart images by passing through two popular components of GAN. GAN introduces noise in the images and tries to replicate the real-time scenarios. Subsequently, the available and newly created images are segmented by applying a multilevel threshold operation to find the region of interest. This step helps the system to predict the accurate attack rate by considering various factors. Earlier researchers have obtained sound accuracy by generating similar heart images and found the ROI parts of the 2D echo images. The proposed methodology has achieved an accuracy of 97.33% and a 90.97% true-positive rate. The reason for selecting the computed tomography (CT-SCAN) images is due to the gray scale images giving more reliable information at a low computational cost.

show abstract

A Multi-Element Identification System Based on Deep Learning for the Visual Field of Percutaneous Endoscopic Spine Surgery

Bu,

Lei,

Wang

et al. 2024

JOIO

View full text Add to dashboard Cite

Background Context:Lumbar disc herniation is a common degenerative lumbar disease with an increasing incidence.Percutaneous endoscopic lumbar discectomy can treat lumbar disc herniation safely and effectively with a minimally invasive procedure.However, it must be noted that the learning curve of this technology is steep,which means that initial learners are often not su ciently pro cient in endoscopic operations, which can easily lead to iatrogenic damage.At present, the application of computer deep learning technology to clinical diagnosis, treatment, and surgical navigation has achieved satisfactory results.Purpose:The objective of our team is to develop a multi-element identi cation system for the visual eld of endoscopic spine surgery using deep learning algorithms and to evaluate the feasibility of this system.Study Design: Retrospective study.Patient Sample:62 patients.Outcome Measure:To determine the effectiveness of the model, the precision, recall, speci city, and mean average precision were used.Method:We established an image database by collecting surgical videos of 62 patients diagnosed with lumbar disc herniation, which was labeled by two spinal surgeons.We selected 4,840 images of the visual eld of percutaneous endoscopic spine surgery (including various tissue structures and surgical instruments), divided into the training data, validation data, and test data according to 2:1:2,and trained the model based on Mask -RCNN.Result After 108 epochs of training, the precision, recall, speci city, and mean average precision of the ResNet101 model were 76.7% 75.9% 97.9% 67.9% respectively;the precision, recall, speci city, and mean average precision of the ResNet50 model were 77.2% 76.1% 97.9% 64.8% respectively.Compared to the two convolutional neural networks, ResNet101 was found to be the most stable backbone network, with the highest convergence effect. Conclusion:Our team have developed a multi-element identi cation system based on Mask R-CNN for percutaneous endoscopic spine surgery ,which identi es and tracks tissues (nerve, ligamentum avum, nucleus pulposus, etc.) and surgical instruments (endoscopic forceps, a high-speed diamond burr, etc.) in real time.It can help navigate intraoperative spinal endoscopic surgery safely in real-time.

show abstract

Residual Learning

Cited by 6 publications

References 33 publications

An Overview of Deep Learning Methods for Left Ventricle Segmentation

An Overview of Deep Learning Methods for Left Ventricle Segmentation

An Efficient Multilevel Thresholding Scheme for Heart Image Segmentation Using a Hybrid Generalized Adversarial Network

A Multi-Element Identification System Based on Deep Learning for the Visual Field of Percutaneous Endoscopic Spine Surgery

Contact Info

Product

Resources

About