Deep learning based enhanced tumor segmentation approach for MR brain images

Mittal, Mamta; Goyal, Lalit Mohan; Kaur, Sumit; Kaur, Iqbaldeep; Verma, Amit; Hemanth, D. Jude

doi:10.1016/j.asoc.2019.02.036

Cited by 212 publications

(91 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The sinusoidal regressive model [34] utilized Gaia Data Archive, giving parameters such as x-, y-, z-coordinates, angular velocity, classified spiral arm and the inclination with respect to time. The research has been concluded with the following.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Ml Driven Prediction of Collision of Milky Way & Andromeda

Mittal¹,

Anusurya²,

Kumar³

et al. 2019

IJRTE

View full text Add to dashboard Cite

The 3D position of Sun with respect to the galactic center of Milky Way can be used to understand its evolution. After Milky Way collides with Andromeda(M31), the same will hold true. Ensuing sections deal with the implementation of Regressive Analysis to predict the location of Sun in the galactic center after Galactic collision. This model utilizes results of previous studies of black hole mergers to predict the resultant mass of Sagittarius A* and M31’s black hole, which had been found to be (1.49±0.16) × 108 M☉. This mass has been used to calculate the centrifugal force that Sun might experience during and after the galactic collision. The current position, inclination, and velocity of Sun (derived from aforementioned predictions) have been used to predict its distance and inclination after the collision which has been predicted as 63,362.83 ly and 32.75o , from the new galactic center and its plane (97.48% and 96.32% accurate) respectively.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Ml Driven Prediction of Collision of Milky Way & Andromeda

Mittal¹,

Anusurya²,

Kumar³

et al. 2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…Connections from the encoder are feeding the decoder block at several stages and this leads to intense learning. Considering the promising results of U‐Net for biomedical images (Mittal et al, ; Ronneberger et al, ), road extraction (Zhang, Liu, & Wang, ) and building extraction (Xu, Wu, Xie, & Chen, ) from aerial images, we considered the adaptation of this approach for analysis of features resulting from archaeo‐geophysical images.…”

Section: Image Analysis By Means Of Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Deep learning based automated analysis of archaeo‐geophysical images

Küçükdemirci

Sarris

2020

Archaeological Prospection

View full text Add to dashboard Cite

Thanks to recent advances in deep learning (DL) and the increasing availability of large labeled/annotated datasets and trained network models, there has been impressive progress in the automated analysis of images from different scientific domains such as medicine, microbiology, astronomy and remote sensing. The automated analysis of archaeo-geophysical data is also considered important due to the large spatial extent of areas covered by landscape surveys using multi-sensor arrays driven by motorized carts and subsequently the large volume of collected data. In this work, a convolutional neural network (CNN) is built by Python 3.6 programming language using the Deep Learning Library of Keras with Tensorflow backends, a library that implements the building blocks for CNN. The network is trained from scratch adopting U-Net architecture to accomplish an automatic analysis of the archaeo-geophysical features with emphasis on ground-penetrating radar (GPR) anomalies. K E Y W O R D S archaeo-geophysics, convolutional neural networks (CNNs), deep learning, feature extraction, GPR (ground-penetrating radar), U-Net

show abstract

“…The neural network itself is not an algorithm, rather, it sets a framework for many different machine learning algorithms to work together and process complex data inputs [8]. The past research revealed that various soft computing techniques have been effectively used to solve a wide variety of real-world problems like disease diagnosis [13][14], query optimization [15][16][17], feature selection [18][19], task scheduling [20][21], sentiment analysis [22][23],stock analysis [24] and crop prediction [25][26]which are difficult or time consuming to solve otherwise. Research related to the diagnosis of different human disorders like diabetes, cancer and cardio-problems using soft computing techniques has been witnessed.…”

Section: Soft Computing Techniquesmentioning

confidence: 99%