Computer-aided Diagnosis of Lung Cancer in Computed Tomography Scans: A Review

Paulraj, Tharcis; Chellliah, Kezi Selva Vijila

doi:10.2174/1573405613666170111155017

Cited by 8 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To meet this objective our models have been trained and tested not only against raw data, but also using simple histogram equalization using parameters matching ImageNet (Krizhevsky et al, 2017) and CLAHE as successfully employed in a number of studies into deep learning based lung pathology detection from medical images (Sarkar et al, 2020;Wajid et al, 2017). We were also interested in the effect of handcrafted feature extraction layers, often implemented as wavelet filters such as Gabor filters, which have been shown to improve the accuracy of deep learning classification networks (Han et al, 2014;Paulraj & Chellliah, 2018;Ye et al, 2007) in thoracic disease imaging applications.…”

Section: Pre-processing Pipelinesmentioning

confidence: 99%

“…Each of these models is then assessed against each other's test data partition with Histogram Equalization (OpenCV, n.d.) and Contrast Limited Adaptive Histogram Equalization (CLAHE) (Zuiderveld, 1994) image preprocessing techniques applied, these being the most commonly employed methods of reducing systematic image variance in brightness and contrast (Al-Ameen et al, 2015). Each test is repeated with the addition of a learning Gabor filter (Feichtinger & Strohmer, 2012) which has been shown by some studies to improve CNN accuracy in thoracic imaging applications (Han et al, 2014;Paulraj & Chellliah, 2018). From these tests we gain insights into the ability of each model to generalize to external datasets, along with an indication of the effects of image histogram pre-processing and application of a learning Gabor filter.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Systematic investigation into generalization of COVID-19 CT deep learning models with Gabor ensemble for lung involvement scoring

Horry¹,

Chakraborty²,

Pradhan³

et al. 2021

Preprint

View full text Add to dashboard Cite

The COVID-19 pandemic has inspired unprecedented data collection and computer vision modelling efforts worldwide, focusing on diagnosis and stratification of COVID-19 from medical images. Despite this large-scale research effort, these models have found limited practical application due in part to unproven generalization of these models beyond their source study. This study investigates the generalizability of key published models using the publicly available COVID-19 Computed Tomography data through cross dataset validation. We then assess the predictive ability of these models for COVID-19 severity using an independent new dataset that is stratified for COVID-19 lung involvement. Each inter-dataset study is performed using histogram equalization, and contrast limited adaptive histogram equalization with and without a learning Gabor filter. The study shows high variability in the generalization of models trained on these datasets due to varied sample image provenances and acquisition processes amongst other factors. We show that under certain conditions, an internally consistent dataset can generalize well to an external dataset despite structural differences between these datasets with f1 scores up to 86%. Our best performing model shows high predictive accuracy for lung involvement score for an independent dataset for which expertly labelled lung involvement stratification is available. Creating an ensemble of our best model for disease positive prediction with our best model for disease negative prediction using a min-max function resulted in a superior model for lung involvement prediction with average predictive accuracy of 75% for zero lung involvement and 96% for 75-100% lung involvement with almost linear relationship between these stratifications.

show abstract

Section: Pre-processing Pipelinesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Systematic investigation into generalization of COVID-19 CT deep learning models with Gabor ensemble for lung involvement scoring

Horry¹,

Chakraborty²,

Pradhan³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Effective lesion information reduces misdiagnoses and missed diagnoses caused by manual reading, and CAD systems have become important tools in lung cancer diagnosis and treatment. Doctors use CAD systems to accurately locate and segment lung nodules and analyse the pathological characteristics of lung nodule lesions ( 5 , 6 ). Since the segmentation results in lung nodule images directly affect pathological diagnoses, the accuracy of lung lesion segmentation algorithms is very important.…”

Section: Introductionmentioning

confidence: 99%

RAD-UNet: Research on an improved lung nodule semantic segmentation algorithm based on deep learning

Zuo

2023

Front. Oncol.

View full text Add to dashboard Cite

ObjectiveDue to the small proportion of target pixels in computed tomography (CT) images and the high similarity with the environment, convolutional neural network-based semantic segmentation models are difficult to develop by using deep learning. Extracting feature information often leads to under- or oversegmentation of lesions in CT images. In this paper, an improved convolutional neural network segmentation model known as RAD-UNet, which is based on the U-Net encoder-decoder architecture, is proposed and applied to lung nodular segmentation in CT images.MethodThe proposed RAD-UNet segmentation model includes several improved components: the U-Net encoder is replaced by a ResNet residual network module; an atrous spatial pyramid pooling module is added after the U-Net encoder; and the U-Net decoder is improved by introducing a cross-fusion feature module with channel and spatial attention.ResultsThe segmentation model was applied to the LIDC dataset and a CT dataset collected by the Affiliated Hospital of Anhui Medical University. The experimental results show that compared with the existing SegNet [14] and U-Net [15] methods, the proposed model demonstrates better lung lesion segmentation performance. On the above two datasets, the mIoU reached 87.76% and 88.13%, and the F1-score reached 93.56% and 93.72%, respectively. Conclusion: The experimental results show that the improved RAD-UNet segmentation method achieves more accurate pixel-level segmentation in CT images of lung tumours and identifies lung nodules better than the SegNet [14] and U-Net [15] models. The problems of under- and oversegmentation that occur during segmentation are solved, effectively improving the image segmentation performance.

show abstract

“…CT plays a vital role and more sensitive in the determination of tumor size. Computer Aided Diagnosis (CAD) has been used for the early prediction of lung cancer [5]. As far as CAD model is concerned, sensitivity, specificity, cost effectiveness and accuracy are achieved in the analysis of lung cancer [6].…”

Section: Introductionmentioning

confidence: 99%

Detection of Lung Tumor Using ASPP-Unet with Whale Optimization Algorithm

Alkhonaini¹,

Hassine²,

Obayya³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

The unstructured growth of abnormal cells in the lung tissue creates tumor. The early detection of lung tumor helps the patients avoiding the death rate and gives better treatment. Various medical image modalities can help the physicians in the diagnosis of disease. Many research works have been proposed for the early detection of lung tumor. High computation time and misidentification of tumor are the prevailing issues. In order to overcome these issues, this paper has proposed a hybrid classifier of Atrous Spatial Pyramid Pooling (ASPP)-Unet architecture with Whale Optimization Algorithm (ASPP-Unet -WOA). To get a fine tuning detection of tumor in the Computed Tomography (CT) of lung image, this model needs pre-processing using Gabor filter. Secondly, feature segmentation is done using Guaranteed Convergence Particle Swarm Optimization. Thirdly, feature selection is done using Binary Grasshopper Optimization Algorithm. This proposed (ASPP-Unet -WOA) is implemented in the dataset of National Cancer Institute (NCI) Lung Cancer Database Consortium. Various performance metric measures are evaluated and compared to the existing classifiers. The accuracy of Deep Convolutional Neural Network (DCNN) is 93.45%, Convolutional Neural Network (CNN) is 91.67%, UNet obtains 95.75% and ASPP-UNet-WOA obtains 98.68%. compared to the other techniques.

show abstract

Computer-aided Diagnosis of Lung Cancer in Computed Tomography Scans: A Review

Cited by 8 publications

References 0 publications

Systematic investigation into generalization of COVID-19 CT deep learning models with Gabor ensemble for lung involvement scoring

Systematic investigation into generalization of COVID-19 CT deep learning models with Gabor ensemble for lung involvement scoring

RAD-UNet: Research on an improved lung nodule semantic segmentation algorithm based on deep learning

Detection of Lung Tumor Using ASPP-Unet with Whale Optimization Algorithm

Contact Info

Product

Resources

About