Machine Learning: A Tool to Shape the Future of Medicine

Hazapi, Orsalia; Lаgopati, Nefeli; Pezoulas, Vasileios C.; Papayiannis, Georgios I.; Fotiadis, Dimitrios I.; Skaltsas, Dimitrios; Vergetis, Vangelis; Tsirigos, Aristotelis; Stratis, Ioannis G.; Yannacopoulos, A. N.; Gorgoulis, Vassilis G.

doi:10.1007/978-981-16-9158-4_12

Cited by 2 publications

(3 citation statements)

References 117 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three techniques for image segmentation can also be categorized: statistical, variational, and geometric. Statistical techniques simulate the image data and represent the region-processing as mappings from the original images [5]. Geometric approaches use representations of item shapes to categorize the details of an image.…”

Section: ░ 2 Review Of Literaturementioning

confidence: 99%

“…The national institute of health (NIH) defines lung cancer as "Cancer that forms in tissues of the lung, usually in the cells lining air passages, two main types are small cell lung cancer and non-small cell lung cancer". The cells' appearance below a microscope is used to diagnose various types [5]. More people develop lung cancer than every form of cancer.…”

Section: ░ 1 Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction and Classification of CT images for Early Detection of Lung Cancer Using Various Segmentation Models

Nair

Devi

Bhasi

2022

IJEER

View full text Add to dashboard Cite

One of the most serious and deadly diseases in the world is lung cancer. On the other hand, prompt diagnosis, as well as care, could save lives. Probably the most capable imaging method in the medical world, computed tomography (CT) scans are challenging for clinicians to analyze as well as detect cancer. In recent years, there has been an increase in the use of image analysis techniques for the detection of CT scan images matching cancer tissues. Using a Computer-aided detection (CAD) system employing CT scans to aid inside the early lung cancer diagnosis as well as to differentiate among benign/malignant tumors is thus interesting to address. The primary objective of this study would be to assess several computer-aided approaches, analyze the right methodology already in use, and afterward propose a new approach that integrates enhancements to the best system currently in use. This research improves the performance of the existing retrieval system by combining various image feature extraction processes and modifying the internal layer section of the classifier. The segmentation method proposed here to identify cancer is Improved Random Walker segmentation along with Random Forest (RF) classifier and K-Nearest Neighbors (KNN) classifier. Here, the research is accomplished on the Lung Image database consortium (LIDC) datasets which is a collection of CT images and is utilized as the input images to verify the effectiveness of the suggested strategy. The accuracy of the proposed method for the detection of lung cancer with the aid of the RF classifier is 99.6 % as well as the KNN classifier is 96.4% accordingly.

show abstract

Section: ░ 2 Review Of Literaturementioning

confidence: 99%

Section: ░ 1 Introductionmentioning

confidence: 99%

Prediction and Classification of CT images for Early Detection of Lung Cancer Using Various Segmentation Models

Nair

Devi

Bhasi

2022

IJEER

View full text Add to dashboard Cite

show abstract

“…Algorithms for predicting RNA 3D structure from nucleotide sequence [ 6 ] are dominated by four approaches: (i) template based methods such as FARFAR2 [ 7 , 8 ] and 3dRNA2 [ 9 , 10 ], which decompose known structures into 1- to 3-mer fragments and combinatorially reassemble them to find the structures with lowest molecular interaction energies [ 11 ], (ii) coarse grained force field methods that minimise interaction energy by stochastically displacing groups of atoms like SimRNA and RNA-BRiQ [ 12 , 13 ], (iii) comparative modelling methods that are based on the availability of homologous structures, and (iv) machine learning approaches [ 14 , 15 ] that combine sequence and chemical probing information to generate candidate structures. Despite the steady increase in affordable computing power and the use of more accurate energy functions [ 11 , 16 ], the de novo structure prediction of larger RNAs (>80nt) still remains challenging [ 7 ].…”

Section: Introductionmentioning

confidence: 99%

De novo prediction of RNA 3D structures with deep generative models

Ramakers,

Blum,

König

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

We present a Deep Learning approach to predict 3D folding structures of RNAs from their nucleic acid sequence. Our approach combines an autoregressive Deep Generative Model, Monte Carlo Tree Search, and a score model to find and rank the most likely folding structures for a given RNA sequence. We show that RNA de novo structure prediction by deep learning is possible at atom resolution, despite the low number of experimentally measured structures that can be used for training. We confirm the predictive power of our approach by achieving competitive results in a retrospective evaluation of the RNA-Puzzles prediction challenges, without using structural contact information from multiple sequence alignments or additional data from chemical probing experiments. Blind predictions for recent RNA-Puzzle challenges under the name “Dfold” further support the competitive performance of our approach.

show abstract

Machine Learning: A Tool to Shape the Future of Medicine

Cited by 2 publications

References 117 publications

Prediction and Classification of CT images for Early Detection of Lung Cancer Using Various Segmentation Models

Prediction and Classification of CT images for Early Detection of Lung Cancer Using Various Segmentation Models

De novo prediction of RNA 3D structures with deep generative models

Contact Info

Product

Resources

About