Light Deep Model for Pulmonary Nodule Detection from CT Scan Images for Mobile Devices

Masud, Mehedi; Muhammad, Ghulam; Hossain, M. Shamim; Alhumyani, Hesham; Alshamrani, Sultan S.; Cheikhrouhou, Omar; Ibrahim, Saleh

doi:10.1155/2020/8893494

Cited by 22 publications

(14 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonetheless, they have been put into comparison because the objective remains the same. As seen from the table, our method outperforms most of the other cancer identification methods in terms of the maximum classification accuracy; the only exceptions are the studies described in [ 19 , 28 , 29 , 31 , 34 ]. In the case of [ 19 , 29 ], apart from the accuracy values, only the recall values were presented, and both of them (94% and 93%) are lower than what our model has achieved (96.37%).…”

Section: Resultsmentioning

confidence: 85%

“…In the case of [ 19 , 29 ], apart from the accuracy values, only the recall values were presented, and both of them (94% and 93%) are lower than what our model has achieved (96.37%). Among the other studies, the authors of [ 28 ] worked with a set of colonoscopy images, and [ 31 , 34 ] worked based on CT scan images, so straightforward comparisons cannot be made. Only the studies cited in [ 51 , 52 , 53 ] work with the LC25000 dataset.…”

Section: Resultsmentioning

confidence: 99%

“…They achieved a 93.9% classification accuracy (maximum) using CNN-based classification algorithms [ 33 ]. Masud et al described a pulmonary nodule detection method based on CT scan images using a light CNN architecture [ 34 ]. Tested on the LIDC dataset, their model achieved a 97.9% classification accuracy while distinguishing among normal, benign, and malignant cases.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

A Machine Learning Approach to Diagnosing Lung and Colon Cancer Using a Deep Learning-Based Classification Framework

Masud

Sikder

Nahid

et al. 2021

Sensors

Self Cite

257

View full text Add to dashboard Cite

The field of Medicine and Healthcare has attained revolutionary advancements in the last forty years. Within this period, the actual reasons behind numerous diseases were unveiled, novel diagnostic methods were designed, and new medicines were developed. Even after all these achievements, diseases like cancer continue to haunt us since we are still vulnerable to them. Cancer is the second leading cause of death globally; about one in every six people die suffering from it. Among many types of cancers, the lung and colon variants are the most common and deadliest ones. Together, they account for more than 25% of all cancer cases. However, identifying the disease at an early stage significantly improves the chances of survival. Cancer diagnosis can be automated by using the potential of Artificial Intelligence (AI), which allows us to assess more cases in less time and cost. With the help of modern Deep Learning (DL) and Digital Image Processing (DIP) techniques, this paper inscribes a classification framework to differentiate among five types of lung and colon tissues (two benign and three malignant) by analyzing their histopathological images. The acquired results show that the proposed framework can identify cancer tissues with a maximum of 96.33% accuracy. Implementation of this model will help medical professionals to develop an automatic and reliable system capable of identifying various types of lung and colon cancers.

show abstract

Section: Resultsmentioning

confidence: 85%

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Machine Learning Approach to Diagnosing Lung and Colon Cancer Using a Deep Learning-Based Classification Framework

Masud

Sikder

Nahid

et al. 2021

Sensors

Self Cite

257

View full text Add to dashboard Cite

show abstract

“…The classification accuracy of their proposed model was 93.9%. For the detection of pulmonary nodules, M. Masud et al [23] proposed a light deep learning approach relying on CNN architecture with only four convolutional layers. Each convolutional layer is comprised of two successive convolutional blocks, a connecting convolutional block, non-linear activation functions after each block, and a pooling block.…”

Section: Related Workmentioning

confidence: 99%

Malignancy Detection in Lung and Colon Histopathology Images Using Transfer Learning With Class Selective Image Processing

et al. 2022

View full text Add to dashboard Cite

Cancer accounts for a huge mortality rate due to its aggressiveness, colossal potential of metastasis, and heterogeneity (causing resistance against chemotherapy). Lung and colon cancers are among the most prevalent types of cancer around the globe that can occur in both males and females. Early and accurate diagnosis of these cancers can substantially improve the quality of treatment as well as the survival rate of cancer patients. We propose a highly accurate and computationally efficient model for the swift and accurate diagnosis of lung and colon cancers as an alternative to current cancer detection methods. In this study, a large dataset of lung and colon histopathology images was employed for training and the validation process. The dataset is comprised of 25000 histopathology images of lung and colon tissues equally divided into 5 classes. A pretrained neural network (AlexNet) was tuned by modifying the four of its layers before training it on the dataset. Initial classification results were promising for all classes of images except for one class with an overall accuracy of 89%. To improve the overall accuracy and keep the model computationally efficient, instead of implementing image enhancement techniques on the entire dataset, the quality of images of the underperforming class was improved by applying a contrast enhancement technique which is fairly simple and efficient. The implementation of the proposed methodology has not only improved the overall accuracy from 89% to 98.4% but has also proved computationally efficient.

show abstract

“…They attained a 93.9% classification accuracy using CNN-based classification algorithms (9,10) . Masud et al presented a pulmonary nodule detection method based on CT scan images using a light CNN architecture (11) . Verified on the LIDC dataset, their model accomplished excellent classification accuracy while distinguishing among normal, benign, and malignant cases.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning based Mobilenet with Deep Belief Network for Lung Cancer Diagnosis in IOT and Cloud Enabled Environment

Jeya¹,

Valluru²,

Sherin³

2022

IJST

View full text Add to dashboard Cite

Background: The purpose of the present investigation is to unravel the complexity involved in Lung Cancer diagnosis by inculcating a new automated deep learning based MobileNet (DLMN) with deep belief network (DBN), called DLMN-DBN model in Internet of Things and cloud enabled environment. Methods: This paper presents an optimal DLMN-DBN model for lung cancer diagnosis where the parameters of DLMN-DBN model are optimized, and feature extraction and classification takes place by DLMN and DBN model respectively. The experimentation part takes place on four dimensions: 1) IoT devices enabled data acquisition for lung cancer diagnosis and the data are transmitted to the cloud server for diagnostic process, 2) the Guassian Filtering (GF) based preprocessing technique for noise removal, 3) feature extraction using DLMN model and 4) Optimal classification using DBN model. For experimental validation, an extensive experimentation analysis is performed to highlight the superior diagnostic outcome of the DLMN-DBN model. Findings:The experimental values stated that the DLMN-DBN model has resulted in superior results when compared with existing models with higher accuracy, sensitivity, and specificity of 95.55%, 93.94%, and 96.49% respectively. Novelty and applications: The new state of the art DLMN-DBN model and its robustness help general practitioners efficiently and effectively diagnose lung cancer conditions at the initial stage thereby reducing further complications and morbidity.

show abstract

Light Deep Model for Pulmonary Nodule Detection from CT Scan Images for Mobile Devices

Cited by 22 publications

References 42 publications

A Machine Learning Approach to Diagnosing Lung and Colon Cancer Using a Deep Learning-Based Classification Framework

A Machine Learning Approach to Diagnosing Lung and Colon Cancer Using a Deep Learning-Based Classification Framework

Malignancy Detection in Lung and Colon Histopathology Images Using Transfer Learning With Class Selective Image Processing

Deep Learning based Mobilenet with Deep Belief Network for Lung Cancer Diagnosis in IOT and Cloud Enabled Environment

Contact Info

Product

Resources

About