ERV-Net: An efficient 3D residual neural network for brain tumor segmentation

Zhou, Xinyu; Li, Xuanya; Hu, Kai; Zhang, Yuan; Chen, Zhineng; Gao, Xieping

doi:10.1016/j.eswa.2021.114566

Cited by 105 publications

(40 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of artificial intelligence and deep learning is a matter of discussion in recent years. It could help not only in the detection process and the classification into benign and malignant types, but also during the follow-up of the patient, and could be of value in terms of RTH and tumour and healthy tissue delineation [ 80 , 81 , 82 , 83 , 84 , 85 ]. Very high accuracy was reported for many of those systems that could improve the diagnostic process in the future and that have the potential to find tumour regions with the most aggressive tissues [ 85 ].…”

Section: Discussionmentioning

confidence: 99%

Polish Multi-Institutional Study of Children with Ependymoma—Clinical Practice Outcomes in the Light of Prospective Trials

et al. 2021

View full text Add to dashboard Cite

We performed a multi-institutional analysis of 74 children with ependymoma to evaluate to what extent the clinical outcome of prospective trials could be reproduced in routine practice. The evaluation of factors that correlated with outcome was performed with a log rank test and a Cox proportional-hazard model. Survival was estimated with the Kaplan–Meier method. The majority of patients had brain tumours (89%). All had surgery as primary treatment, with adjuvant radiotherapy (RTH) and chemotherapy (CTH) applied in 78% and 57%, respectively. Median follow-up was 80 months and 18 patients died. Five- and 10-year overall survival (OS) was 83% and 73%. Progression was observed in 32 patients, with local recurrence in 28 cases. The presence of metastases was a negative prognostic factor for OS. Five- and 10-year progression-free survival (PFS) was 55% and 40%, respectively. The best outcome in patients with non-disseminated brain tumours was observed when surgery was followed by RTH (+/−CTH afterwards; p = 0.0001). Children under 3 years old who received RTH in primary therapy had better PFS (p = 0.010). The best outcome of children with ependymoma is observed in patients who received radical surgery followed by RTH, and irradiation should not be omitted in younger patients. The role of CTH remains debatable.

show abstract

Section: Discussionmentioning

confidence: 99%

Polish Multi-Institutional Study of Children with Ependymoma—Clinical Practice Outcomes in the Light of Prospective Trials

et al. 2021

View full text Add to dashboard Cite

show abstract

“…ShuffleNetV2 represents the advanced progress of ShuffleNetV1 to achieve improved performance of recent mobile vision applications [43]. For instance, 3D ShuffleNetV2 is utilized for accurate brain tumor segmentation [44]. ShuffleNetV2 enhanced group convolution by the channel split for back propagation.…”

Section: Shufflenetsmentioning

confidence: 99%

Lightweight Transfer Learning Models for Ultrasound-Guided Classification of COVID-19 Patients

Karar¹,

Reyad²,

Abdelnaby³

et al. 2021

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Lightweight deep convolutional neural networks (CNNs) present a good solution to achieve fast and accurate image-guided diagnostic procedures of COVID-19 patients. Recently, advantages of portable Ultrasound (US) imaging such as simplicity and safe procedures have attracted many radiologists for scanning suspected COVID-19 cases. In this paper, a new framework of lightweight deep learning classifiers, namely COVID-LWNet is proposed to identify COVID-19 and pneumonia abnormalities in US images. Compared to traditional deep learning models, lightweight CNNs showed significant performance of real-time vision applications by using mobile devices with limited hardware resources. Four main lightweight deep learning models, namely MobileNets, ShuffleNets, MENet and MnasNet have been proposed to identify the health status of lungs using US images. Public image dataset (POCUS) was used to validate our proposed COVID-LWNet framework successfully. Three classes of infectious COVID-19, bacterial pneumonia, and the healthy lung were investigated in this study. The results showed that the performance of our proposed MnasNet classifier achieved the best accuracy score and shortest training time of 99.0% and 647.0 s, respectively. This paper demonstrates the feasibility of using our proposed COVID-LWNet framework as a new mobilebased radiological tool for clinical diagnosis of COVID-19 and other lung diseases.

show abstract

“…Neural modelling is very popular method in the biological and medical community [52]. It can be used in many diagnostic aspects [53][54][55][56][57][58][59][60][61][62][63]…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Neural Modelling as a Precise Method in the Assessment of the Chronological Age of Children and Adolescents Using Tooth and Bone Parameters

Zaborowicz

Biedziak

et al. 2022

Sensors

View full text Add to dashboard Cite

Dental age is one of the most reliable methods for determining a patient’s age. The timing of teething, the period of tooth replacement, or the degree of tooth attrition is an important diagnostic factor in the assessment of an individual’s developmental age. It is used in orthodontics, pediatric dentistry, endocrinology, forensic medicine, and pathomorphology, but also in scenarios regarding international adoptions and illegal immigrants. The methods used to date are time-consuming and not very precise. For this reason, artificial intelligence methods are increasingly used to estimate the age of a patient. The present work is a continuation of the work of Zaborowicz et al. In the presented research, a set of 21 original indicators was used to create deep neural network models. The aim of this study was to verify the ability to generate a more accurate deep neural network model compared to models produced previously. The quality parameters of the produced models were as follows. The MAE error of the produced models, depending on the learning set used, was between 2.34 and 4.61 months, while the RMSE error was between 5.58 and 7.49 months. The correlation coefficient R2 ranged from 0.92 to 0.96.

show abstract

ERV-Net: An efficient 3D residual neural network for brain tumor segmentation

Cited by 105 publications

References 42 publications

Polish Multi-Institutional Study of Children with Ependymoma—Clinical Practice Outcomes in the Light of Prospective Trials

Polish Multi-Institutional Study of Children with Ependymoma—Clinical Practice Outcomes in the Light of Prospective Trials

Lightweight Transfer Learning Models for Ultrasound-Guided Classification of COVID-19 Patients

Deep Learning Neural Modelling as a Precise Method in the Assessment of the Chronological Age of Children and Adolescents Using Tooth and Bone Parameters

Contact Info

Product

Resources

About