Artificial intelligence; Biomedical image classification; Convolutional neural networks; Data augmentation; Entropy; Tumor detection; Anomaly detection; Automated detection; Biomedical images; Cancerous tumors; Convolutional neural network; Images classification; Lower complexity; Tumour detection; Control and Systems Engineering; Signal Processing; Computer Networks and Communications
Abstract :
[en] The automated detection of cancerous tumors has attracted interest during the last decade, due to the necessity of early and efficient diagnosis that will lead to the most effective possible treatment of the impending risk. Several machine learning and artificial intelligence methodologies have been employed aiming to provide trustworthy helping tools that will contribute efficiently to this attempt. In this article, we present a low-complexity convolutional neural network architecture for tumor classification enhanced by a robust image augmentation methodology. The effectiveness of the presented deep learning model has been investigated based on three datasets containing brain, kidney, and lung images, showing remarkable diagnostic efficiency with classification accuracies of 99.33%, 100%, and 99.7% for the three datasets, respectively. The impact of the augmentation preprocessing step has also been extensively examined using four evaluation measures. The proposed low-complexity scheme, in contrast to other models in the literature, renders our model quite robust to cases of overfitting that typically accompany small datasets frequently encountered in medical classification challenges. Finally, the model can be easily re-trained in case additional tumor images are included, as its simplistic architecture does not impose a significant computational burden.
Disciplines :
Computer science
Author, co-author :
Papageorgiou, Vasileios E. ; Aristotle University of Thessaloniki, Thessaloniki, Greece
DOGOULIS, Panteleimon Tsampikos ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal
Papageorgiou, Dimitrios-Panagiotis ; Aristotle University of Thessaloniki, Thessaloniki, Greece
External co-authors :
yes
Language :
English
Title :
A Convolutional Neural Network of Low Complexity for Tumor Anomaly Detection
Original title :
[en] A Convolutional Neural Network of Low Complexity for Tumor Anomaly Detection
Publication date :
15 September 2023
Event name :
ICICT 2023
Event place :
London, Gbr
Event date :
20-02-2023 => 23-02-2023
By request :
Yes
Audience :
International
Main work title :
Proceedings of 8th International Congress on Information and Communication Technology - ICICT 2023
Editor :
Yang, Xin-She
Publisher :
Springer Science and Business Media Deutschland GmbH
Saligkaras D, Papageorgiou VE (2022) On the detection of patterns in electricity prices across European countries: an unsupervised machine learning approach. AIMS Energy 10(6):1146– 1164
Saligkaras D, Papageorgiou VE (2022) Seeking the truth beyond the data. An unsupervised machine learning approach. III International Scientific Forum on Computer and Energy Sciences (WFCES-III 2022), AIP Conference Proceedings
De Angelis LM (2014) Brain tumors. New England J Med 344:114–123
Jassim MM (2022) Systematic review for lung cancer detection and lung nodule classification: taxonomy, challenges, and recommendation future works. J Intell Syst 31:944–964
Begum S et al (2021) Identification of biomarker on biological and gene expression data using fuzzy preference based rough set. J Intell Syst 30(1):130–141
Rasmussen R et al (2022) Artificial intelligence in kidney cancer. Am Soc Clin Oncol Educ Book 42:300–310
Hollingsworth JM et al (2006) Rising incidence of small renal masses: a need to reassess treatment effect. J Natl Cancer Inst 98:1331–1334
Papageorgiou VE, Tsaklidis G (2023) An improved epidemiological-unscented Kalman filter (hybrid SEIHCRDV-UKF) model for the prediction of COVID-19. Application on real-time data. Chaos, Solitons Fractals 166:112914
Vani N et al (2017) Brain tumor classification using support vector machine. Int Res J Eng Technol 4:1724–1729
Ramdlon RH et al. (2019) Brain tumor classification using MRI images with K-nearest neighbor method. In: 2019 International electronics symposium, pp 660–667
Manjunath S et al (2019) Brain tumor detection and classification using convolution neural network. Int J Recent Technol Eng 8:34–40
Seetha J, Raja SS (2018) Brain tumor classification using convolutional neural networks. Biomed Pharmacol J 11:1457–1461
Babu KR et al (2019) Comparative analysis of brain tumor detection using deep learning methods. Int J Sci Technol Res 8:250–254
Pathak K et al. (2019) Classification of brain tumor using convolutional neural network. In: Proceedings of the third international conference on electronics communication and aerospace technology, pp 128–132
Lang R et al. (2018) Brain tumor identification based on CNN-SVM Model. In: Proceedings of the 2nd international conference on biomedical engineering and bioinformatics, pp 31–35
Sert E et al. (2019) A new approach for brain tumor diagnosis system: Single image super resolution based maximum fuzzy entropy segmentation and convolutional neural network. Med Hypotheses 133
Özyurt F et al. (2019) Brain tumor detection on convolutional neural networks with neutrosophic expert maximum fuzzy sure entropy. Measurement 147
Kareem HF et al (2021) Evaluation of SVM performance in the detection of lung cancer in marked CT scan dataset. Indones J Electr Eng Comput Sci 21(3):1731–1738
Al-Huseiny MS, Sajit AS (2021) Transfer learning with GoogLeNet for detection of lung cancer. Indones J Electr Eng Comput Sci 22(2):1078–1086
Naqi SM et al (2019) A 3D nodule candidate detection method supported by hybrid features to reduce false positives in lung nodule detection. Mul Tools Appl 78(18):26287–26311
Abbas W et al. (2020) Lungs nodule cancer detection using statistical techniques. In: 2020 IEEE 23rd International multitopic conference (INMIC), pp 1–6
Roy K et al. (2019) A comparative study of lung cancer detection using supervised neural network. In: 2019 international conference on opto-electronics and applied optics (Optronix), pp 1–5
Mohite A (2021) Application of transfer learning technique for detection and classification of lung cancer using CT images. Int J Sci Res Manag. 9(11):621–634
Polat H, Mehr HD (2019) Classification of pulmonary CT images by using hybrid 3D-deep convolutional neural network architecture. Appl Sci (Switz) 9(5):940
Yang R et al (2020) Radiomics of small renal masses on multiphasic CT: accuracy of machine learning-based classification models for the differentiation of renal cell carcinoma and angiomyolipoma without visible fat. Eur Radiol 30:1254–1263
Cui EM et al (2019) Differentiation of renal angiomyolipoma without visible fat from renal cell carcinoma by machine learning based on whole-tumor computed tomography texture features. Acta Radiol 60:1543–1552
Feng Z et al (2018) Machine learning-based quantitative texture analysis of CT images of small renal masses: differentiation of angiomyolipoma without visible fat from renal cell carcinoma. Eur Radiol 28:1625–1633
Han S et al (2019) The classification of renal cancer in 3-phase CT images using a deep learning method. J Digit Imaging 32:638–643
Li Q et al (2020) Multiparametric MRI radiomic model for preoperative predicting WHO/ISUP nuclear grade of clear cell renal cell carcinoma. J Magn Reson Imaging 52:1557–1566
Papageorgiou V (2021) Brain tumor detection based on features extracted and classified using a low-complexity neural network. Traitement du signal 38(3):547–554
Papageorgiou VE et al (2022) Analysis of digitalized ECG signals based on artificial intelligence and spectral analysis methods specialized in ARVC. Int J Numer Methods Biomed Eng 38(11):e3644
Papageorgiou VE (2022) A study of primary school teachers’ tendencies regarding the usefulness of dramatization in the educational process. Int J Cogn Res Sci Eng Educ (IJCRSEE) 10(2)
Papageorgiou V, Tsaklidis G (2021) Modeling of premature mortality rates from chronic diseases in Europe, investigation of correlations, clustering and Granger causality. Commun Math Bio Neurosci 2021(67)
