A Review On Lung Cancer Detection From CT Scan Images Using CNN
0 likes55 views
The document reviews various methodologies for detecting lung cancer from CT scan images, finding that convolutional neural networks along with image processing provide the most suitable approach. It discusses related work applying techniques like image enhancement, segmentation, and machine learning classification to identify cancerous nodules. Recent approaches using deep learning, specifically 3D convolutional neural networks, achieve high accuracy rates of 94-96% for cancer detection and classification.
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 12 | Dec 2020 www.irjet.net p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2352
A Review on Lung Cancer Detection from CT Scan Images using CNN
P L G Suraj Reddy1, Y Siva Kireeti Reddy2, Suraj Kumar B P3
1,2Department of Computer Science Engineering, Sir M Visvesvaraya Institute of Technology, Bangalore, India
3Assistant Professor in Dept. of Computer Science Engineering, Sir M Visvesvaraya Institute of Technology,
Bangalore, India
---------------------------------------------------------------------***----------------------------------------------------------------------
Abstract – One of the major causes of death in humans is
due to a disease called Lung Cancer. Cancer is a disease in
which cells in the body grow out of control and is one of the
most serious health issues. Lung cancer is theuncontrolledcell
growth in tissues of lungs. Early detection of the cancer helps
the physicians to act quickly which in turn which increase the
survival chances of the infected patients. Thisisareviewpaper
wherein different methodologies for the detection of Lung
Cancer from Computed Tomography (CT) scan images are
presented. It is observed that Convolution Neural Network
along with Image Processing is the most suitable approach to
detect the Lung Cancer from the CT scan image which is
provided as input.
Key Words: Lung Cancer, Convolution Neural Network,
Image Processing, Computed Tomography, Watershed
Segmentation.
1. Introduction
Cancer is one among the foremost serious health problems
within the world. Cancer disease is caused due to the out-of-
control growth of the cells in the body parts. Among the
different types of cancer, Lung Cancer is the mostdangerous
type of cancer. This is due to the fact that its one of the
leading causes of death in both men and women and also
according to World Health Organization, it was seen that
2.09 Million cases of Lung Cancer was found and a sum of
1.76 Million people died due to the Lung Cancer in a single
year of 2018. The cause for the large number of people
getting infected with lung cancer is the fact that there are
many ways present surrounding us and withtheuseofthese
or by coming in contact with these like Smoking and many
more, we will be quickly prone to be infected with Lung
Cancer. Also, the reason for high death ratesisbecauseofthe
late detection of the cancer. All these factors make it
necessary to devise a methodology usingcurrenttechnology
which can help to Detect the Lung Cancer from the scanned
images of the Lungs. Once the Lung cancer is detected, there
are various possible biological treatments available which
includes Thoracic Surgery, Chemotherapy, Radiotherapy.
Depending on the Cancer stage and other factors, the
physicians can choose the appropriate treatment for the
Lung Cancer. Hence, if the cancer is detected at the early
stage, the chances of survival of the patient increases.
A literature survey is made on the possible techniques and
methodologies which can be used to detect the Lung Cancer.
There are various techniques, methodology and technology
which can be used to accomplish the required objective.
2. Literature Review
Disha Sharma et al (2011),[1] gave an approach for early
detection of disease called lung cancer by processing lungs
CT images using Image Processing techniques. The authors
used bit-plane slicing, erosion and Weiner filter image
processing techniques. These techniques are used to extract
the lung regions from the Computed Tomography image.
Later the extracted lung regions were segmented using
Region growing Segmentation algorithm. Once the
segmentation was done Rule basedModel wasusedtodetect
the cancerous nodules. It was observed that the above
methodology gave an accuracy of 80%.
Anita Chaudhary et al (2012), [2] proposed a methodology
for the lung cancer detection on a CT image by using Image
processing. The pre-processing stage included image
enhancement where Gabor filter and Fast Fouriertransform
techniques were used and further for image segmentation
watershed algorithm was applied.Laterfeature extractionof
the segmented image wasdonetospecifythearea,perimeter
and eccentricity features which was used to detect and
classify the lung nodules.
Hamid Bagherieh etal(2013),[3]proposeda methodologyto
detect the lung nodules and also give the classification ofthe
same using Image Processing and Decision-Making
techniques. First and foremost, image pre-processing was
carried out on the CT scan images and the pre-processing
was done using the techniques called contrast enhancement
and linear filtering. Further, the filtered image was
segmented using Region growing Segmentation process.
Further the features like size, area and color were
considered and were given as input to the Fuzzy system
which employed fuzzy membership function to detect and
classify Lung Cancer.
Prashant Naresh et al (2014), [4] specified the approach to
detect the lung cancer using Image processing and Neural
Network Techniques. Initially the CT scanned image of lung
was filtered to remove Gaussian white noise and Otsu’s
threshold technique was used to do the segmentation of the
image. The structural featureswereextractedandwereused
which were given as input to themachineLearningclassifier.
The Support Vector Machine and Artificial Neural Network](https://image.slidesharecdn.com/areviewonlungcancerdetectionfromctscanimagesusingcnn-230805183655-86066d3c/85/A-Review-On-Lung-Cancer-Detection-From-CT-Scan-Images-Using-CNN-1-320.jpg)
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 12 | Dec 2020 www.irjet.net p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2353
techniques were used for the classifying the input CT
scanned image and it was found that SVM techniques gave a
higher accuracy of 95.12%.
Jennifer D Cruz et al (2015), [5] provided a framework to
detect the lung cancer from the Lung CT images usingneural
networks and Genetic Algorithm.Initiallythepre-processing
of image was done to enhance the quality of the image. Later
the Feature extraction and selection phase was carried out
on the enhanced image using the Genetic Algorithm. Then
the Back Propagation Neural Network techniquewasused to
classify the text image as cancerous or non-cancerous.
A Asuntha et al (2016), [6] proposed a method for
segmentation of MRI, CT and Ultrasound images. Correct
identification of neoplastic cell is completed bystudying the
required features extracted for the images. Ultrasound
images have been used to detect the validity of the system.
The feature selection by the use of Particle Swarm
Optimization (PSO),GeneticOptimizationandSVN algorithm
gave an accuracy of about 89.5% with reduction in false
positive.
Wafaa Alakwaa et al (2017), [7] designed a CAD system for
lung cancer classification of CT scans with unmarked
nodules. Thresholding was usedasinitial segment technique
which produced best Segmentation of the lungs. A U-Net
trained on LUNA16 data was used to detect nodule
representatives. The U-Net output were fed into 3D
Convolutional Neural Networks to finally classify CT image
as infected or not for lung cancer. The 3-D Convolution
Neural Network gave a test accuracy of 86.6%.
S Senthil et al (2018), [8] proposed an approach todetect the
lung cancer by using neural network with optimal features.
Initially the info pre-processing was applied on the input
images for the image enhancement. Then the enhanced
images were trained and tested by neural network. Initially,
Particle Swarm Optimization was applied to extract the
features of the input images and the input sample was
classified as cancerous or non-cancerous depending on the
Artificial Neural Network technique.Itwasobservedthat the
given technique gave an accuracy of 97.8%.
S Sasikala et al (2018), [9] presented a technique to classify
the tumors in lung as benign or malignant. The CT scan
image which is taken as input,ispre-processedusingmedian
filter technique. Then, back-propagationalgorithmwasused
to train the CNN to detect the lung tumors in CT image. To
train the model, lung image with different shape and size of
cancerous tissues were fed and the CNN based method was
able to detect the presence or absence of cancerous cells
with an accuracy of 96%.
K Mohanambal et al (2019),[10] proposed a methodology to
detect lung cancer using machine learning techniques. The
author processed the CT scan images to differentiate the
benign and the malignant nodule and its level of the growth
of the cancer cells by using machine learning. Theauthorhas
also implemented the method to detect the growth of the
cancerous cell in the initial stages. The approach to
differentiate the pulmonary modules into malignant and
benign nodules is to assist the radiologist and for the future
enhancement.
Rohit Y. Bhalerao et al (2019),[11] presented anapproachto
classify the input CT scan lung image as cancerous or non-
cancerous using CNN. Before training the images usingCNN,
the input images were converted to Gray scale and those in
turn were converted into binary format. Later the images
were trained using the CNN model to attain an overall
accuracy of 94%.
3. CONCLUSION
This paper presentsaLiteratureSurveyondifferentmethods,
approaches, techniques and technologies which can be used
to Detect Lung Cancer from Computed Tomography (CT)
scanned images and classify them as cancerous or non-
cancerous. Also depending on the inputdatasetwhichisused
to train the model, it was found that we can classify the
cancer as benign or malignant. As specified, there are several
techniques to detect the cancer but the most widely used
approach is to use Image Processing and Machine Learning
techniques. From the study of abovepapers,wecameupwith
the following conclusions. Early approaches used the
traditional Machine Learningtechniquesandhencegaveless
accurate results. With the invent of Deep learning and
specifically 3D Convolution Neural Networks, the
classification of image datasets has become easier and gave
good accurate results. With the use of traditional ML
techniques, the processing of the input image has to be taken
care by the programmer and hence the detection of Lung
Cancer wascomplex and difficult.Withtheuseof3DCNN,the
image classification involves less Image Processing.TheCNN
which is taken as a black boxperformsmostoftheprocessing
internally and hence reduces the external programming and
also give better and accurate results. Summarizing all the
papers, it was found that Detection of Lung cancer involves
mainly 3 phases. One is Image pre-processing, then
Segmentation using Watershed Algorithm and then
classifying the image as cancerous or non-cancerous using
CNN. It is found that the usage of CNN classifier to detect
cancer gave accuracies of 94%-96% [9][11].
REFERENCES
[1] Sharma, Disha, and Gagandeep Jindal. “Identifying
lung cancer using image processing techniques.” In
International Conference on computational
Techniques and Artificial intelligence (ICCTAI),
vol.17, pp. 872-880. 2011.
[2] Chaudhary, Anita, and Sonit Sukhraj Singh. "Lung
cancer detection on CT images by using image
processing." In 2012 International Conference on](https://image.slidesharecdn.com/areviewonlungcancerdetectionfromctscanimagesusingcnn-230805183655-86066d3c/85/A-Review-On-Lung-Cancer-Detection-From-CT-Scan-Images-Using-CNN-2-320.jpg)
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 12 | Dec 2020 www.irjet.net p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2354
Computing Sciences, pp. 142-146. IEEE, 2012.
[3] Bagherieh, Hamid, Atiyeh Hashemi, and Abdol Hamid
Pilevar. "Mass detection in lung CT images using
region growing segmentation and decision making
based on fuzzy systems." International Journal of
Image, Graphics and Signal Processing 6, no. 1
(November 2013):1.
[4] Naresh, Prashant, and Dr RajashreeShettar. "Early
detection of lung cancer using neural network
techniques." Prashant Naresh Int. Journal of
Engineering Research and Applications 4, no. 8
(2014): 78-83.
[5] D’Cruz, J., A. Jadhav, A. Dighe, V. Chavan, and J.
Chaudhari. "Detection of lung cancer using
backpropagation neural networks and genetic
algorithm." Comput Technol Appl 6, no. 5 (2016):
823-827.
[6] Asuntha, A., A. Brindha, S. Indirani, and Andy
Srinivasan. "Lung cancer detection using SVM
algorithm and optimization techniques." J. Chem.
Pharm. Sci (2016).
[7] Wafaa Alakwaa, Mohammad Nassef, Amr Badr.“Lung
Cancer Detection and Classification with 3D
Convolutional Neural Network (3D-CNN)”. (IJACSA)
International Journal of Advanced Computer Science
and Applications, Vol. 8, No. 8, 2017
[8] Senthil, S., and B. Ayshwarya. "Lungcancerprediction
using feed forwardback propagationneural networks
with optimal features." International Journal of
Applied Engineering Research 13, no. 1 (2018): 318-
325.
[9] Sasikala, S., M. Bharathi, and B. R. Sowmiya. "Lung
Cancer Detection and ClassificationUsing DeepCNN."
International Journal of Innovative Technology and
Exploring Engineering (IJITEE) ISSN: 2278-3075,
Volume-8 Issue-2S December, 2018
[10] K Mohanambal, Y Nirosha, E Oliviya Roshini, S
Punitha and M Shamini. “LungCancerDetectionusing
Machine Learning Techniques.”International Journal
of Advanced Research in Electrical, Electronics and
Instrumentation Engineering Vol 8, Issue 2, February
2019.
[11] Bhalerao, Rohit Y., Harsh P. Jani, Rachana K.Gaitonde,
and Vinit Raut. "A novel approach for detection of
Lung Cancer using Digital Image Processing and
Convolution Neural Networks." In 2019 5th
International Conference on Advanced Computing &
Communication Systems(ICACCS),pp.577-583.IEEE,
2019.](https://image.slidesharecdn.com/areviewonlungcancerdetectionfromctscanimagesusingcnn-230805183655-86066d3c/85/A-Review-On-Lung-Cancer-Detection-From-CT-Scan-Images-Using-CNN-3-320.jpg)
A Review On Lung Cancer Detection From CT Scan Images Using CNN
- 1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 07 Issue: 12 | Dec 2020 www.irjet.net p-ISSN: 2395-0072 © 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2352 A Review on Lung Cancer Detection from CT Scan Images using CNN P L G Suraj Reddy1, Y Siva Kireeti Reddy2, Suraj Kumar B P3 1,2Department of Computer Science Engineering, Sir M Visvesvaraya Institute of Technology, Bangalore, India 3Assistant Professor in Dept. of Computer Science Engineering, Sir M Visvesvaraya Institute of Technology, Bangalore, India ---------------------------------------------------------------------***---------------------------------------------------------------------- Abstract – One of the major causes of death in humans is due to a disease called Lung Cancer. Cancer is a disease in which cells in the body grow out of control and is one of the most serious health issues. Lung cancer is theuncontrolledcell growth in tissues of lungs. Early detection of the cancer helps the physicians to act quickly which in turn which increase the survival chances of the infected patients. Thisisareviewpaper wherein different methodologies for the detection of Lung Cancer from Computed Tomography (CT) scan images are presented. It is observed that Convolution Neural Network along with Image Processing is the most suitable approach to detect the Lung Cancer from the CT scan image which is provided as input. Key Words: Lung Cancer, Convolution Neural Network, Image Processing, Computed Tomography, Watershed Segmentation. 1. Introduction Cancer is one among the foremost serious health problems within the world. Cancer disease is caused due to the out-of- control growth of the cells in the body parts. Among the different types of cancer, Lung Cancer is the mostdangerous type of cancer. This is due to the fact that its one of the leading causes of death in both men and women and also according to World Health Organization, it was seen that 2.09 Million cases of Lung Cancer was found and a sum of 1.76 Million people died due to the Lung Cancer in a single year of 2018. The cause for the large number of people getting infected with lung cancer is the fact that there are many ways present surrounding us and withtheuseofthese or by coming in contact with these like Smoking and many more, we will be quickly prone to be infected with Lung Cancer. Also, the reason for high death ratesisbecauseofthe late detection of the cancer. All these factors make it necessary to devise a methodology usingcurrenttechnology which can help to Detect the Lung Cancer from the scanned images of the Lungs. Once the Lung cancer is detected, there are various possible biological treatments available which includes Thoracic Surgery, Chemotherapy, Radiotherapy. Depending on the Cancer stage and other factors, the physicians can choose the appropriate treatment for the Lung Cancer. Hence, if the cancer is detected at the early stage, the chances of survival of the patient increases. A literature survey is made on the possible techniques and methodologies which can be used to detect the Lung Cancer. There are various techniques, methodology and technology which can be used to accomplish the required objective. 2. Literature Review Disha Sharma et al (2011),[1] gave an approach for early detection of disease called lung cancer by processing lungs CT images using Image Processing techniques. The authors used bit-plane slicing, erosion and Weiner filter image processing techniques. These techniques are used to extract the lung regions from the Computed Tomography image. Later the extracted lung regions were segmented using Region growing Segmentation algorithm. Once the segmentation was done Rule basedModel wasusedtodetect the cancerous nodules. It was observed that the above methodology gave an accuracy of 80%. Anita Chaudhary et al (2012), [2] proposed a methodology for the lung cancer detection on a CT image by using Image processing. The pre-processing stage included image enhancement where Gabor filter and Fast Fouriertransform techniques were used and further for image segmentation watershed algorithm was applied.Laterfeature extractionof the segmented image wasdonetospecifythearea,perimeter and eccentricity features which was used to detect and classify the lung nodules. Hamid Bagherieh etal(2013),[3]proposeda methodologyto detect the lung nodules and also give the classification ofthe same using Image Processing and Decision-Making techniques. First and foremost, image pre-processing was carried out on the CT scan images and the pre-processing was done using the techniques called contrast enhancement and linear filtering. Further, the filtered image was segmented using Region growing Segmentation process. Further the features like size, area and color were considered and were given as input to the Fuzzy system which employed fuzzy membership function to detect and classify Lung Cancer. Prashant Naresh et al (2014), [4] specified the approach to detect the lung cancer using Image processing and Neural Network Techniques. Initially the CT scanned image of lung was filtered to remove Gaussian white noise and Otsu’s threshold technique was used to do the segmentation of the image. The structural featureswereextractedandwereused which were given as input to themachineLearningclassifier. The Support Vector Machine and Artificial Neural Network
- 2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 07 Issue: 12 | Dec 2020 www.irjet.net p-ISSN: 2395-0072 © 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2353 techniques were used for the classifying the input CT scanned image and it was found that SVM techniques gave a higher accuracy of 95.12%. Jennifer D Cruz et al (2015), [5] provided a framework to detect the lung cancer from the Lung CT images usingneural networks and Genetic Algorithm.Initiallythepre-processing of image was done to enhance the quality of the image. Later the Feature extraction and selection phase was carried out on the enhanced image using the Genetic Algorithm. Then the Back Propagation Neural Network techniquewasused to classify the text image as cancerous or non-cancerous. A Asuntha et al (2016), [6] proposed a method for segmentation of MRI, CT and Ultrasound images. Correct identification of neoplastic cell is completed bystudying the required features extracted for the images. Ultrasound images have been used to detect the validity of the system. The feature selection by the use of Particle Swarm Optimization (PSO),GeneticOptimizationandSVN algorithm gave an accuracy of about 89.5% with reduction in false positive. Wafaa Alakwaa et al (2017), [7] designed a CAD system for lung cancer classification of CT scans with unmarked nodules. Thresholding was usedasinitial segment technique which produced best Segmentation of the lungs. A U-Net trained on LUNA16 data was used to detect nodule representatives. The U-Net output were fed into 3D Convolutional Neural Networks to finally classify CT image as infected or not for lung cancer. The 3-D Convolution Neural Network gave a test accuracy of 86.6%. S Senthil et al (2018), [8] proposed an approach todetect the lung cancer by using neural network with optimal features. Initially the info pre-processing was applied on the input images for the image enhancement. Then the enhanced images were trained and tested by neural network. Initially, Particle Swarm Optimization was applied to extract the features of the input images and the input sample was classified as cancerous or non-cancerous depending on the Artificial Neural Network technique.Itwasobservedthat the given technique gave an accuracy of 97.8%. S Sasikala et al (2018), [9] presented a technique to classify the tumors in lung as benign or malignant. The CT scan image which is taken as input,ispre-processedusingmedian filter technique. Then, back-propagationalgorithmwasused to train the CNN to detect the lung tumors in CT image. To train the model, lung image with different shape and size of cancerous tissues were fed and the CNN based method was able to detect the presence or absence of cancerous cells with an accuracy of 96%. K Mohanambal et al (2019),[10] proposed a methodology to detect lung cancer using machine learning techniques. The author processed the CT scan images to differentiate the benign and the malignant nodule and its level of the growth of the cancer cells by using machine learning. Theauthorhas also implemented the method to detect the growth of the cancerous cell in the initial stages. The approach to differentiate the pulmonary modules into malignant and benign nodules is to assist the radiologist and for the future enhancement. Rohit Y. Bhalerao et al (2019),[11] presented anapproachto classify the input CT scan lung image as cancerous or non- cancerous using CNN. Before training the images usingCNN, the input images were converted to Gray scale and those in turn were converted into binary format. Later the images were trained using the CNN model to attain an overall accuracy of 94%. 3. CONCLUSION This paper presentsaLiteratureSurveyondifferentmethods, approaches, techniques and technologies which can be used to Detect Lung Cancer from Computed Tomography (CT) scanned images and classify them as cancerous or non- cancerous. Also depending on the inputdatasetwhichisused to train the model, it was found that we can classify the cancer as benign or malignant. As specified, there are several techniques to detect the cancer but the most widely used approach is to use Image Processing and Machine Learning techniques. From the study of abovepapers,wecameupwith the following conclusions. Early approaches used the traditional Machine Learningtechniquesandhencegaveless accurate results. With the invent of Deep learning and specifically 3D Convolution Neural Networks, the classification of image datasets has become easier and gave good accurate results. With the use of traditional ML techniques, the processing of the input image has to be taken care by the programmer and hence the detection of Lung Cancer wascomplex and difficult.Withtheuseof3DCNN,the image classification involves less Image Processing.TheCNN which is taken as a black boxperformsmostoftheprocessing internally and hence reduces the external programming and also give better and accurate results. Summarizing all the papers, it was found that Detection of Lung cancer involves mainly 3 phases. One is Image pre-processing, then Segmentation using Watershed Algorithm and then classifying the image as cancerous or non-cancerous using CNN. It is found that the usage of CNN classifier to detect cancer gave accuracies of 94%-96% [9][11]. REFERENCES [1] Sharma, Disha, and Gagandeep Jindal. “Identifying lung cancer using image processing techniques.” In International Conference on computational Techniques and Artificial intelligence (ICCTAI), vol.17, pp. 872-880. 2011. [2] Chaudhary, Anita, and Sonit Sukhraj Singh. "Lung cancer detection on CT images by using image processing." In 2012 International Conference on
- 3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 07 Issue: 12 | Dec 2020 www.irjet.net p-ISSN: 2395-0072 © 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2354 Computing Sciences, pp. 142-146. IEEE, 2012. [3] Bagherieh, Hamid, Atiyeh Hashemi, and Abdol Hamid Pilevar. "Mass detection in lung CT images using region growing segmentation and decision making based on fuzzy systems." International Journal of Image, Graphics and Signal Processing 6, no. 1 (November 2013):1. [4] Naresh, Prashant, and Dr RajashreeShettar. "Early detection of lung cancer using neural network techniques." Prashant Naresh Int. Journal of Engineering Research and Applications 4, no. 8 (2014): 78-83. [5] D’Cruz, J., A. Jadhav, A. Dighe, V. Chavan, and J. Chaudhari. "Detection of lung cancer using backpropagation neural networks and genetic algorithm." Comput Technol Appl 6, no. 5 (2016): 823-827. [6] Asuntha, A., A. Brindha, S. Indirani, and Andy Srinivasan. "Lung cancer detection using SVM algorithm and optimization techniques." J. Chem. Pharm. Sci (2016). [7] Wafaa Alakwaa, Mohammad Nassef, Amr Badr.“Lung Cancer Detection and Classification with 3D Convolutional Neural Network (3D-CNN)”. (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 8, No. 8, 2017 [8] Senthil, S., and B. Ayshwarya. "Lungcancerprediction using feed forwardback propagationneural networks with optimal features." International Journal of Applied Engineering Research 13, no. 1 (2018): 318- 325. [9] Sasikala, S., M. Bharathi, and B. R. Sowmiya. "Lung Cancer Detection and ClassificationUsing DeepCNN." International Journal of Innovative Technology and Exploring Engineering (IJITEE) ISSN: 2278-3075, Volume-8 Issue-2S December, 2018 [10] K Mohanambal, Y Nirosha, E Oliviya Roshini, S Punitha and M Shamini. “LungCancerDetectionusing Machine Learning Techniques.”International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering Vol 8, Issue 2, February 2019. [11] Bhalerao, Rohit Y., Harsh P. Jani, Rachana K.Gaitonde, and Vinit Raut. "A novel approach for detection of Lung Cancer using Digital Image Processing and Convolution Neural Networks." In 2019 5th International Conference on Advanced Computing & Communication Systems(ICACCS),pp.577-583.IEEE, 2019.