Using Sequential Decision Making to Improve Lung Cancer Screening Performance

Petousis, Panayiotis; Winter, Audrey; Speier, William; Aberle, Denise R.; Hsu, William; Bui, Alex A. T.

doi:10.1109/access.2019.2935763

Cited by 35 publications

(27 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lung cancer is cause by the uncontrolled increase of lung cells. [3]. Lung nodes are defects of the spherical and circular opaque lung tissue with a diameter of 30 mm.…”

Section: Introductionmentioning

confidence: 99%

An Early Prediction and Classification of Lung Nodule Diagnosis on CT Images Based on Hybrid Deep Learning Techniques

Gugulothu

Balaji

2022

Preprint

View full text Add to dashboard Cite

Detection of malignant lung nodules at an early stage may allow for clinical interventions that increase the survival rate of lung cancer patients. The use of hybrid deep learning techniques to detect nodules will improve the sensitivity of lung cancer screening and the interpretation speed of lung scans.Accurate detection of lung nodes is an important step in computed tomography (CT) imaging to detect lung cancer. However, it is very difficult to identify strong nodes due to the diversity of lung nodes and the complexity of the surrounding environment.Here, we proposed alung nodule detection and classification with CT images based on hybrid deep learning (LNDC-HDL) techniques. First, we introduce achaotic bird swarm optimization (CBSO) algorithm for lung nodule segmentation using statistical information. Second, we illustrate anImproved Fish Bee (IFB) algorithm for feature extraction and selection process. Third, we develop hybrid classifier i.e. hybrid differential evolution based neural network (HDE-NN) for tumor prediction and classification.Experimental results have shown that the use of computed tomography, which demonstrates the efficiency and importance of the HDE-NN specific structure for detecting lung nodes on CT scans, increases sensitivity and reduces the number of false positives. The proposed method shows that the benefits of HDE-NN node detection can be reaped by combining clinical practice.

show abstract

“…Lung cancer is cause by the uncontrolled increase of lung cells. [3]. Lung nodes are defects of the spherical and circular opaque lung tissue with a diameter of 30 mm.…”

Section: Introductionmentioning

confidence: 99%

An Early Prediction and Classification of Lung Nodule Diagnosis on CT Images Based on Hybrid Deep Learning Techniques

Gugulothu

Balaji

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…For |Z| finite the latent z t variables then might represent distinct progression "stages" or various classifications of a disease. Discrete separation like this is well established in both clinical guidelines and models for a range of cases including transplantation in patients with CF [8], the diagnosis of Alzheimer's disease [45], and cancer screening [47]. Accordingly we use the Attentive State-Space model of [3] to build an attention-based, customised state-space (CSS) representation of disease progression.…”

Section: Environmentsmentioning

confidence: 99%

The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation

Chan¹,

Bica²,

Hüyük³

et al. 2021

Preprint

View full text Add to dashboard Cite

Understanding decision-making in clinical environments is of paramount importance if we are to bring the strengths of machine learning to ultimately improve patient outcomes. Several factors including the availability of public data, the intrinsically offline nature of the problem, and the complexity of human decision making, has meant that the mainstream development of algorithms is often geared towards optimal performance in tasks that do not necessarily translate well into the medical regime; often overlooking more niche issues commonly associated with the area. We therefore present a new benchmarking suite designed specifically for medical sequential decision making: the Medkit-Learn(ing) Environment, a publicly available Python package providing simple and easy access to high-fidelity synthetic medical data. While providing a standardised way to compare algorithms in a realistic medical setting we employ a generating process that disentangles the policy and environment dynamics to allow for a range of customisations, thus enabling systematic evaluation of algorithms' robustness against specific challenges prevalent in healthcare.Preprint. Under review.

show abstract

“…Though the technique improves the accuracy, the huge amounts of data points were not considered. A Markov decision process was developed in [8] to concurrently optimize lung cancer recognition with higher specificity. However, the higher classification performance in detecting malignant pulmonary nodules was not obtained.…”

Section: Introductionmentioning

confidence: 99%

Target Projection Feature Matching Based Deep ANN with LSTM for Lung Cancer Prediction

Thaventhiran¹,

Sekar²

2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Prediction of lung cancer at early stages is essential for diagnosing and prescribing the correct treatment. With the continuous development of medical data in healthcare services, Lung cancer prediction is the most concerning area of interest. Therefore, early prediction of cancer helps in reducing the mortality rate of humans. The existing techniques are time-consuming and have very low accuracy. The proposed work introduces a novel technique called Target Projection Feature Matched Deep Artificial Neural Network with LSTM (TPFMDANN-LSTM) for accurate lung cancer prediction with minimum time consumption. The proposed deep learning model consists of multiple layers to learn the given input patient data. Different processes are carried out at each layer to predict lung cancer at an earlier stage. The input layer of the deep neural network receives the data and associated features and sends them to the hidden layer. The first hidden layer performs the feature selection process using Target Projection matching to identify the relevant features for accurate disease prediction with minimum time consumption. Hidden layer 2 performs the patient Data Classification based on Czekanowski's dice similarity coefficient with the selected relevant features from the previous layer to predict lung cancer. The factors considered for performance evaluation of the proposed technique with the existing state of the art approaches include prediction accuracy, false-positive rate and prediction time. Lunar 16 Lung Cancer dataset consisting of patient data is used for evaluation. The obtained results show that the proposed TPFMDANN-LSTM technique achieves higher prediction accuracy with minimum time consumption and less false positive rate than the state-of-the-art methods. The experimental results reveal that the TPFMDANN-LSTM technique performs better with a 6% improvement in prediction accuracy, 36% reduction of false positives, and 16% faster prediction time for lung cancer detection compared to existing works.

show abstract

Using Sequential Decision Making to Improve Lung Cancer Screening Performance

Cited by 35 publications

References 27 publications

An Early Prediction and Classification of Lung Nodule Diagnosis on CT Images Based on Hybrid Deep Learning Techniques

An Early Prediction and Classification of Lung Nodule Diagnosis on CT Images Based on Hybrid Deep Learning Techniques

The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation

Target Projection Feature Matching Based Deep ANN with LSTM for Lung Cancer Prediction

Contact Info

Product

Resources

About