CAD System Design for Pituitary Tumor Classification based on Transfer
Learning Technique

Sagrika      Gargya; Shruti      Jain

Abstract

Background: A brain tumor is an asymmetrical expansion by cells inevitably emulating amid them. Image processing is a vibrant research area where the handing out of the image in the medical field is an exceedingly tricky field. In this paper, an expert algorithm is suggested for the detection of pituitary brain tumors from MR images.

Methods: The preprocessing techniques (smoothing, edge detection, filtering) and segmentation techniques (watershed) are applied to the online data set. The transfer learning technique is used as a classifier whose performance is measured in terms of classification accuracy. Resnet 50, Inception V3VGG16, and VGG19 models are used as classification algorithms. The proposed model is validated using different machine learning techniques considering hybrid features.

Results: 96% accuracy was obtained employing the Inception V3 model & 95% accuracy was attained using hybrid GLDS and GLCM features employing Support Vector Machine algorithm while 93% was attained using Probabilistic Neural Network and k Nearest Neighbor techniques.

Conclusion: Computer-aided systems gave much faster and more accurate results than image processing techniques.1.0% accuracy improvement was observed while using Inception V3 over GLDS + GLCM + SVM and 2.1% accuracy improvement using GLDS + GLCM + SVM over GLDS + GLCM + kNN.

[1]
Chesnokova V, Zhou C, Ben-Shlomo A, et al. Growth hormone is a cellular senescence target in pituitary and nonpituitary cells. Proc Natl Acad Sci  2013; 110(35): E3331-9.
 [http://dx.doi.org/10.1073/pnas.1310589110] [PMID: 23940366]

[2]
Heaney AP, Fernando M, Melmed S. Functional role of estrogen in pituitary tumor pathogenesis. J Clin Invest  2002; 109(2): 277-83.
 [http://dx.doi.org/10.1172/JCI0214264] [PMID: 11805140]

[3]
Herman V, Fagin J, Gonsky R, Kovacs K, Melmed S. Clonal origin of pituitary adenomas. J Clin Endocrinol Metab  1990; 71(6): 1427-33.
 [http://dx.doi.org/10.1210/jcem-71-6-1427] [PMID: 1977759]

[4]
Pituitary Gland and Pituitary Tumors.  Available from: https://www.aans.org/en/Patients/Neurosurgical-Conditions-and-Treatments/Pituitary-Gland-and-Pituitary-Tumors

[5]
Pituitary Adenomas.  Available from: https://my.clevelandclinic.org/health/diseases/15328-pituitary-adenomas

[6]
What Are Pituitary Gland Tumors?.  Available from: https://www.webmd.com/cancer/brain-cancer/pituitary-gland-tumors

[7]
Rohini Paul Joseph C. Brain tumor mri image segmentation and detection in image processing. IJRET  2014; 3(13): 1-5.

[8]
Lakshmi YV. MRI brain image segmentation based on thresholding. Int J Adv Comput Res  2013; 3(1): 97-101.

[9]
Mehmood M, Rizwan M, Gregus ml M, Abbas S. Machine learning assisted cervical cancer detection. Front Public Health  2021; 9: 788376.
 [http://dx.doi.org/10.3389/fpubh.2021.788376] [PMID: 35004588]

[10]
Cancer. 2022. Available from: https://www.who.int/news-room/factsheets/detail/cancer (accessed on 30 June, 2022) 

[11]
National Cancer Institute (NCI).  Available from: https://www.nih.gov/about-nih/what-we-do/nih-almanac/national-cancer-institute-nci#dcb

[12]
Glioblastoma (GBM).  Available from: https://www.abta.org/tumor_types/glioblastoma-gbm/

[13]
CBTRUS Factsheets.  Available from: https://cbtrus.org/cbtrus-published-factsheets/

[14]
Javed AR, Fahad LG, Farhan AA, et al. Automated cognitive health assessment in smart homes using machine learning. Sustain Cities Soc  2021; 65: 102572. a
 [http://dx.doi.org/10.1016/j.scs.2020.102572]

[15]
Vijan A, Dubey P, Jain S. Comparative analysis of various image fusion techniques for brain magnetic resonance images. Procedia Comput Sci  2020; 167: 413-22.
 [http://dx.doi.org/10.1016/j.procs.2020.03.250]

[16]
Pal B, Jain S. Novel discrete component wavelet transform for detection of cerebrovascular diseases. Sadhana  2022; 47(4): 237.
 [http://dx.doi.org/10.1007/s12046-022-02016-9]

[17]
Bhardwaj C, Jain S, Sood M. Transfer learning based robust automatic detection system for diabetic retinopathy grading. Neural Comput Appl  2021; 33(20): 13999-4019.
 [http://dx.doi.org/10.1007/s00521-021-06042-2]

[18]
Bhardwaj C, Jain S, Sood M. Deep learning–based diabetic retinopathy severity grading system employing quadrant ensemble model. J Digit Imaging  2021; 34(2): 440-57.
 [http://dx.doi.org/10.1007/s10278-021-00418-5] [PMID: 33686525]

[19]
Kenhub.  Available from: https://www.kenhub.com/

[20]
Pituitary (Hypophysis) - Endocrine.  Available from: https://step1.medbullets.com/endocrine/109002/pituitary-hypophysis

[21]
Goceri E, Songul C. Biomedical information technology: Image based computer aided diagnosis systems. The 7th International Conference on Advanced Technologies. Antalya. 2018.

[22]
Javed AR, Sarwar MU, Khan HU, Al-Otaibi YD, Alnumay WS, et al. Pp-spa: Privacy preserved smartphone-based personal assistant to improve routine life functioning of cognitive impaired individuals. Neural Process Lett  2021; 1-18.
 [http://dx.doi.org/10.1007/s11063-020-10414-5]

[23]
Dogra J, Jain S, Sood M. Novel seed selection techniques for MR brain image segmentation using graph cut. Comput Methods Biomech Biomed Eng Imaging Vis  2020; 8(4): 389-99.
 [http://dx.doi.org/10.1080/21681163.2019.1697966]

[24]
Mohiyuddin A, Basharat A, Ghani U, et al. Breast tumor detection and classification in mammogram images using modified yolov5 network. Comput Math Methods Med  2022; 2022: 1-16.
 [http://dx.doi.org/10.1155/2022/1359019] [PMID: 35027940]

[25]
Rehman A, Razzak I, Xu G. Federated learning for privacy preservation of healthcare data from smartphone-based side-channel attacks. IEEE J Biomed Health Inform  2022; 27(2): 684-90.
 [http://dx.doi.org/10.1109/JBHI.2022.3171852]

[26]
Goceri N, Goceri E. A neural network based kidney segmentation from MR images. IEEE 14th International Conference on Machine Learning and Applications (ICMLA). Miami, FL, USA. 2015.09-11 Dec; 
 [http://dx.doi.org/10.1109/ICMLA.2015.229]

[27]
Dura E, Domingo J, Göçeri E, Martí-Bonmatí L. A method for liver segmentation in perfusion MR images using probabilistic atlases and viscous reconstruction. Pattern Anal Appl  2018; 21(4): 1083-95.
 [http://dx.doi.org/10.1007/s10044-017-0666-z]

[28]
Göçeri̇ E, Ünlü MZ, Di̇cle O. A comparative performance evaluation of various approaches for liver segmentation from SPIR images. Turk J Electr Eng Comput Sci  2015; 23(3): 741-68.
 [http://dx.doi.org/10.3906/elk-1304-36]

[29]
Göçeri E. Convolutional neural network based desktop applications to classify dermatological diseases. IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS).  Genova, Italy. 2020; pp. 138-43.
 [http://dx.doi.org/10.1109/IPAS50080.2020.9334956]

[30]
Harangi B. Skin lesion classification with ensembles of deep convolutional neural networks. J Biomed Inform  2018; 86: 25-32.
 [http://dx.doi.org/10.1016/j.jbi.2018.08.006] [PMID: 30103029]

[31]
Kumar DM, Satyanarayana D, Prasad MNG. MRI brain tumor detection using optimal possibilistic fuzzy C-means clustering algorithm and adaptive k-nearest neighbor classifier. J Ambient Intell Humaniz Comput  2021; 12(2): 2867-80.
 [http://dx.doi.org/10.1007/s12652-020-02444-7]

[32]
Sathies Kumar T, Arun C, Ezhumalai P. An approach for brain tumor detection using optimal feature selection and optimized deep belief network. Biomed Signal Process Control  2022; 73: 103440.
 [http://dx.doi.org/10.1016/j.bspc.2021.103440]

[33]
Vipin Y. Image processing techniques for brain tumor detection: A review. IJETTCS  2015; 4(2)

[34]
Rajesh C. Brain tumor extraction from MRI images Using MAT Lab. IJECSCSE  2(1)

[35]
Dubey RB, Hanmandlu M. Evaluation of three methods for MRI brain tumor segmentation. Eighth International Conference on Information Technology: New Generations.  Las Vegas, NV, USA. 2011; p. 11-13 April; 92.

[36]
Al-Badarnech Amer, Najadat Hassan, Alraziqi Ali M. A classifier to detect tumor disease in MRI brain images. IEEE Comput Soc  2012; 142

[37]
Dina AA. Automated brain tumor detection and identification using image processing and probabilistic neural network techniques. Int J Image Proc Visual Commun 2012.

[38]
Brain-Tumor-Classification-DataSet.  Available from: https://github.com/sartajbhuvaji/brain-tumor-classification-dataset

[39]
Brain Tumor Classification (MRI).  Available from: https://www.kaggle.com/sartajbhuvaji/brain-tumor-classification-mri

[40]
Goceri E. Fully automated and adaptive intensity normalization using statistical features for brain MR images. Celal Bayar Üniversitesi Fen Bilimleri Dergisi  2018; 14(1): 125-34.
 [http://dx.doi.org/10.18466/cbayarfbe.384729]

[41]
Dogra J, Jain S, Sood M. Gradient‐based kernel selection technique for tumour detection and extraction of medical images using graph cut. IET Image Process  2020; 14(1): 84-93.
 [http://dx.doi.org/10.1049/iet-ipr.2018.6615]

[42]
Amin J, Sharif M, Raza M, Saba T, Sial R, Shad SA. Brain tumor detection: A long short-term memory (LSTM)-based learning model. Neural Comput Appl  2020; 32(20): 15965-73.
 [http://dx.doi.org/10.1007/s00521-019-04650-7]

[43]
Bhardwaj C, Jain S, Sood M. A computational framework for diabetic retinopathy severity grading categorization using ophthalmic image processing. PhD Thesis,Jaypee University of Information Technology, Himachal Pradesh, India 2021.

[44]
Goceri E. Medical image data augmentation: Techniques, comparisons and interpretations. Artif Intell Rev  2023; 1-45.
 [http://dx.doi.org/10.1007/s10462-023-10453-z] [PMID: 37362888]

[45]
Goceri E. Comparison of the impacts of dermoscopy image augmentation methods on skin cancer classification and a new augmentation method with wavelet packets. Int J Imaging SysTechnol  2023; 33(5)
 [http://dx.doi.org/10.1002/ima.22890]

[46]
Goceri E. Evaluation of denoising techniques to remove speckle and Gaussian noise from dermoscopy images. Comput Biol Med  2023; 152: 106474.
 [http://dx.doi.org/10.1016/j.compbiomed.2022.106474] [PMID: 36563540]

[47]
Qian Y, Qiu Y, Li CC, et al. A novel diagnostic method for pituitary adenoma based on magnetic resonance imaging using a convolutional neural network. Pituitary  2020; 23(3): 246-52.
 [http://dx.doi.org/10.1007/s11102-020-01032-4] [PMID: 32062801]

[48]
Li H, Zhao Q, Zhang Y, et al. Image-driven classification of functioning and nonfunctioning pituitary adenoma by deep convolutional neural networks. Comput Struct Biotechnol J  2021; 19: 3077-86.
 [http://dx.doi.org/10.1016/j.csbj.2021.05.023] [PMID: 34136106]

Cite As

Current Medical Imaging

CAD System Design for Pituitary Tumor Classification based on Transfer Learning Technique

Abstract