Medical image analysis based on deep learning approach

Puttagunta, Murali Krishna; Ravi, S.

doi:10.1007/s11042-021-10707-4

Cited by 125 publications

(46 citation statements)

References 171 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Aside from moral concerns, the need for systemic, close evaluation of the effect of electronic systems on well-being markers and proportions of changes in mental and physical condition, responses, and outcomes is a notable test in this new aspect of therapeutic consideration. 26 In an assortment of prescription courses, artificial intelligence may be used. Four models are given here: 18,27…”

Section: Physical Branchmentioning

confidence: 99%

“…To inspire engine-evoked potential reactions reported for individual muscles, Robot-helped picture directed transcranial magnetic stimulation (Ri-TMS) was used to recreate useful engine maps of the critical engine cortex. 26 For a neurosurgical resident, it is increasingly becoming difficult to learn" about a patient in the OT. The need for functional neurosurgical recreation is of great significance.…”

Section: Ai In Neurosciencesmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence in healthcare

Shah¹,

Soni²,

Patel³

2021

IJPP

View full text Add to dashboard Cite

Artificial Intelligence (AI) is described as a field of science and engineering that is concerned with the artificial appreciation of what is generally referred to as prudent behavior and the formation of fascinations that demonstrate such conduct. AI is an expansive concept that encloses a series of advances (a considerable lot of which have been being worked on for quite a few years) that are expected to use human-like insight to handle the problems. Right now in combination with enhanced AI developments like extreme or significantly more engaged, we are experiencing a renewed enthusiasm for AI, energized by a tremendous increase in computing capacity and a significantly greater increase in knowledge. AI, along with machine learning, can be used in computer vision. More advantages in the field of engineering as well as in medicine can be accomplished based on these future scenarios worldwide. Healthcare is seen as the next domain that is said to be altered by the use of the concept of artificial intelligence. The AI process is used for critical diseases such as cancer, neurology, cardiology and diabetes. The review includes the ongoing flow status of medical services for AI applications. A few progressive explorations of AI applications in medicinal services that provide a perspective on future where human interactions are gradually brought together by social insurance conveyance. Likewise, this review will discuss how AI and machine learning can save the life of someone. It is also a guide for healthcare professionals to see how, when, and where AI can be more efficient and have the desired outcomes.

show abstract

Section: Physical Branchmentioning

confidence: 99%

Section: Ai In Neurosciencesmentioning

confidence: 99%

Artificial intelligence in healthcare

Shah¹,

Soni²,

Patel³

2021

IJPP

View full text Add to dashboard Cite

show abstract

“…In ( Deepika et al, 2021 ), a fuzzy neural network has been used to compress medical images and read them quickly. The deep neural network has been used to classify and quickly read medical images ( Puttagunta and Ravi, 2021 ). In the mentioned paper, a convolutional neural network (2D) has been used, which has a high speed, but unfortunately, it does not have good accuracy and has some errors.…”

Section: Introductionmentioning

confidence: 99%

Medical Image Interpolation Using Recurrent Type-2 Fuzzy Neural Network

Tavoosi

Zhang

Mohammadzadeh

et al. 2021

Front. Neuroinform.

View full text Add to dashboard Cite

Image interpolation is an essential process for image processing and computer graphics in wide applications to medical imaging. For image interpolation used in medical diagnosis, the two-dimensional (2D) to three-dimensional (3D) transformation can significantly reduce human error, leading to better decisions. This research proposes the type-2 fuzzy neural networks method which is a hybrid of the fuzzy logic and neural networks as well as recurrent type-2 fuzzy neural networks (RT2FNNs) for advancing a novel 2D to 3D strategy. The ability of the proposed methods in the approximation of the function for image interpolation is investigated. The results report that both proposed methods are reliable for medical diagnosis. However, the RT2FNN model outperforms the type-2 fuzzy neural networks model. The average squares error for the recurrent network and the typical network reported 0.016 and 0.025, respectively. On the other hand, the number of fuzzy rules for the recurrent network and the typical network reported 16 and 22, respectively.

show abstract

“…Examples include astronomical imaging [45], autonomous driving [46], fluorescence microscopy [47], X-ray [48], magnetic resonance (MR) [49], computed tomography (CT) [50], and histological imaging [51]. While access to an arbitrarily large amount of data could be used to form all possible combinations of signals of interest and artifact signals during training, a common problem is the limited availability of data, particularly in medical imaging tasks [52]. It is caused by high time and material costs for recording examples and intensified by data privacy restrictions that create further hurdles for the data collection [52].…”

Section: Introductionmentioning

confidence: 99%

“…While access to an arbitrarily large amount of data could be used to form all possible combinations of signals of interest and artifact signals during training, a common problem is the limited availability of data, particularly in medical imaging tasks [52]. It is caused by high time and material costs for recording examples and intensified by data privacy restrictions that create further hurdles for the data collection [52]. Additionally, the annotation of images can be a time-consuming task requiring experts' review [52].…”

Section: Introductionmentioning

confidence: 99%

A Data-Centric Augmentation Approach for Disturbed Sensor Image Segmentation

2021

View full text Add to dashboard Cite

Deep learning methods have become increasingly popular for optical sensor image analysis. They are adaptable to specific tasks and simultaneously demonstrate a high degree of generalization capability. However, applying deep neural networks to problems with low availability of labeled training data can lead to a model being incapable of generalizing to possible scenarios that may occur in test data, especially with the occurrence of dominant imaging artifacts. We propose a data-centric augmentation approach based on generative adversarial networks that overlays the existing labeled data with synthetic artifacts that are generated from data not present in the training set. This augmentation leads to a more robust generalization capability in semantic segmentation. Our method does not need any additional labeling and does not lead to additional memory or time consumption during inference. Further, we find it to be more effective than comparable approaches that are based on procedurally generated disturbances and the direct use of real disturbances. Building upon the improved segmentation results, we observe that our approach leads to improvements of 22% in the F1-score for an evaluated detection problem, which promises significant robustness towards future disturbances. In the context of sensor-based data analysis, the compensation of image artifacts is a challenge. When the structures of interest are not clearly visible in an image, algorithms that can cope with artifacts are crucial for obtaining the desired information. Thereby, the high variation of artifacts, the combination of different types of artifacts, and their similarity to signals of interest are specific issues that have to be considered in the analysis. Despite the high generalization capability of deep learning-based approaches, their recent success was driven by the availability of large amounts of labeled data. Therefore, the provision of comprehensive labeled image data with different characteristics of image artifacts is of importance. At the same time, applying deep neural networks to problems with low availability of labeled data remains a challenge. This work presents a data-centric augmentation approach based on generative adversarial networks that augments the existing labeled data with synthetic artifacts generated from data not present in the training set. In our experiments, this augmentation leads to a more robust generalization in segmentation. Our method does not need additional labeling and does not lead to additional memory or time consumption during inference. Further, we find it to be more effective than comparable augmentations based on procedurally generated artifacts and the direct use of real artifacts. Building upon the improved segmentation results, we observe that our approach leads to improvements of 22% in the F1-score for an evaluated detection problem. Having achieved these results with an example sensor, we expect increased robustness against artifacts in future applications.

show abstract

Medical image analysis based on deep learning approach

Cited by 125 publications

References 171 publications

Artificial intelligence in healthcare

Artificial intelligence in healthcare

Medical Image Interpolation Using Recurrent Type-2 Fuzzy Neural Network

A Data-Centric Augmentation Approach for Disturbed Sensor Image Segmentation

Contact Info

Product

Resources

About