An Intelligent method of analysis of Magnetic Resonance Images (MRI), X-Ray and CT Images for Abnormality Identification.
Keywords:
outcomes, diagnostic, X-ray, MRI, comprehensive, integrationAbstract
The efficient and accurate interpretation of biomedical imaging data, including Computed Tomography (CT), X-ray, and Magnetic Resonance Imaging (MRI), is crucial for the diagnosis, treatment planning, and management of various diseases. This study aims to develop and validate advanced computational models for the automated analysis of CT, X-ray, and MRI images to improve diagnostic accuracy and efficiency. By employing machine learning and deep learning techniques, our models are trained and tested on a comprehensive dataset of biomedical images to identify and classify pathological features across different conditions.
In this work, we focus on the evaluation metrics of True Positive (TP), True Negative (TN), False Positive (FP), and False Negative (FN) rates, alongside derived statistical measures such as Sensitivity (Recall rate), Specificity, Precision, SNR and PSNR and the F1 score to assess the performance of our models. Sensitivity measures the model's ability to correctly identify positive cases, while Specificity assesses its ability to exclude negative cases accurately. Precision evaluates the proportion of true positive results in all positive predictions, and the F1 score provides a harmonic mean of Precision and Sensitivity, offering a balance between them for a comprehensive performance metric.
Our findings demonstrate that the integration of proposed methodology significantly enhances the model's capability to accurately distinguish between pathological and non-pathological cases across CT, X-ray, and MRI modalities. The models exhibit high Sensitivity and Specificity, indicating reliable identification of disease presence and absence. Furthermore, the Precision and F1 scores highlight the models' accuracy and balanced performance in diagnostic predictions. The implications of this study are profound, offering a pathway towards the development of automated diagnostic tools that can support radiologists and healthcare practitioners in making more accurate, efficient, and consistent diagnostic decisions. By leveraging the quantitative analysis of TP, TN, FP, and FN rates, along with key performance metrics such as Sensitivity, Specificity, Precision, and F1 score, our research contributes to the ongoing efforts in improving patient outcomes through enhanced diagnostic imaging analysis.
Downloads
References
P. Brocken, B. A. Kiers, M. G. Looijen-Salamon et al., “Timeliness of lung cancer diagnosis and treatment in a rapid outpatient diagnostic program with combined 18FDG-PET and contrast enhanced CT scanning,” Lung Cancer, vol. 75, no. 3, pp. 336–341, 2012.
P. Vivekanandan, “An efficient SVM based tumor classification with symmetry non-negative matrix factorization using gene expression data,” in In 2013 International conference on information communication and embedded systems (Icices), pp. 761–768, IEEE, USA, February 2013.
J. D’Cruz, A. Jadhav, A. Dighe, V. Chavan, and J. Chaudhari, “Detection of lung cancer using backpropagation neural networks and genetic algorithm,” Computing Technologies and Applications, vol. 6, pp. 823–827, 2016.
J. Shen, J. Wu, M. Xu, D. Gan, B. An, and F. Liu, “A hybrid method to predict postoperative survival of lung cancer using improved SMOTE and adaptive SVM,” Computational and Mathematical Methods in Medicine, vol. 2021, Article ID 2213194, 15 pages, 2021.
S. Mandal and I. Banerjee, “Cancer classification using neural network,” International Journal, vol. 172, pp. 18–49, 2015.
D. M. Abdullah, A. M. Abdulazeez, and A. B. Sallow, “Lung cancer prediction and classification based on correlation selection method using machine learning techniques,” Qubahan Academic Journal, vol. 1, no. 2, pp. 141–149, 2021.
F. Taher, N. Prakash, A. Shaffie, A. Soliman, and A. El-Baz, “An overview of lung cancer classification algorithms and their performances,” IAENG International Journal of Computer Science, vol. 48, no. 4, 2021.
Jaweed and F. Siddiqui, “Implementation of machine learning in lung cancer prediction and prognosis: a review,” in Cyber Intelligence and Information Retrieval, pp. 225–231,India, 2022.
V. N. Jenipher and S. Radhika, “SVM kernel methods with data normalization for lung cancer survivability prediction application,” in In 2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), pp. 1294–1299, IEEE, Canada, February 2021.
V. A. Binson, M. Subramoniam, Y. Sunny, and L. Mathew, “Prediction of pulmonary diseases with electronic nose using SVM and XGBoost,” IEEE Sensors Journal, vol. 21, no. 18, pp. 20886–20895, 2021.
B. R. Manju, V. Athira, and A. Rajendran, “Efficient multi-level lung cancer prediction model using support vector machine classifier,” in In IOP Conference Series: Materials Science and Engineering, vol. 1012, India, 2021no. 1, Article ID 012034IOP Publishing.
P. Nanglia, S. Kumar, A. N. Mahajan, P. Singh, and D. Rathee, “A hybrid algorithm for lung cancer classification using SVM and neural networks,” ICT Express, vol. 7, no. 3, pp. 335–341, 2021.
G. Yin, Y. Song, X. Li et al., “Prediction of mediastinal lymph node metastasis based on 18F-FDG PET/CT imaging using support vector machine in non-small cell lung cancer,” European Radiology, vol. 31, no. 6, pp. 3983–3992, 2021.
Y. Xie, W.-Y. Meng, R.-Z. Li et al., “Early lung cancer diagnostic biomarker discovery by machine learning methods,” Translational Oncology, vol. 14, no. 1, article 100907, 2021.
M. Yakar, D. Etiz, M. Metintas, G. Ak, and O. Celik, “Prediction of radiation pneumonitis with machine learning in stage III lung cancer: a pilot study,” Technology in Cancer Research & Treatment, vol. 20, p. 153303382110163, 2021.
N. Maleki, Y. Zeinali, and S. T. A. Niaki, “A k-NN method for lung cancer prognosis with the use of a genetic algorithm for feature selection,” Expert Systems with Applications, vol. 164, article 113981, 2021.
S. Vijh, R. Sarma, and S. Kumar, “Lung tumor segmentation using marker-controlled watershed and support vector machine,” International Journal of E-Health and Medical Communications (IJEHMC), vol. 12, no. 2, pp. 51–64, 2021.
S. S. Ashwini, M. Z. Kurian, and M. Nagaraja, “Lung cancer detection and prediction using customized selective segmentation technique with SVM classifier,” in Emerging Research in Computing, Information, Communication and Applications, pp. 37–44, Springer, Singapore, 2022.
H. A. Miller, X. Yin, S. A. Smith et al., “Evaluation of disease staging and chemotherapeutic response in non-small cell lung cancer from patient tumor-derived metabolomic data,” Lung Cancer, vol. 156, pp. 20–30, 2021.
X. Fang, M. Netzer, C. Baumgartner, C. Bai, and X. Wang, “Genetic network and gene set enrichment analysis to identify biomarkers related to cigarette smoking and lung cancer,” Cancer Treatment Reviews, vol. 39, no. 1, pp. 77–88, 2013.
N. L. Guo and Y. W. Wan, “Pathway-based identification of a smoking associated 6-gene signature predictive of lung cancer risk and survival,” Artificial Intelligence in Medicine, vol. 55, no. 2, pp. 97–105, 2012.
V. Krishnaiah, G. Narsimha, and N. S. Chandra, “Diagnosis of lung cancer prediction system using data mining classification techniques,” International Journal of Computer Science and Information Technologies, vol. 4, no. 1, pp. 39–45, 2013.
C. Anil Kumar et al, “Lung Cancer Prediction from Text Datasets Using Machine Learning ” , Hindawi BioMed Research International Volume 2022, Article ID 6254177, 10 pages https://doi.org/10.1155/2022/6254177
K. Polat and S. Güneş, “Principles component analysis, fuzzy weighting pre-processing and artificial immune recognition system based diagnostic system for diagnosis of lung cancer,” Expert Systems with Applications, vol. 34, no. 1, pp. 214–221, 2008.
Y. Qian, Y. Zhang, X. Ma, H. Yu, and L. Peng, “EARS: emotion-aware recommender system based on hybrid information fusion,” Information Fusion, vol. 46, pp. 141–146, 2019.
Y. Shin and J. Ghosh, “Ridge polynomial networks,” IEEE Transactions on Neural Networks, vol. 6, no. 3, pp. 610–622, 1995.
F. Taher and R. Sammouda, “Lung cancer detection by using artificial neural network and fuzzy clustering methods,” in In 2011 IEEE GCC conference and exhibition (GCC), pp. 295–298, IEEE, United Arab Emirates, February 2011.
Q. N. Tran, “A novel method for finding non-small cell lung cancer diagnosis biomarkers,” BMC Medical Genomics, vol. 6, Supplement 1, p. S11, 2013.
T. Kaur and N. Gupta, “Classification of lung diseases using particle swarm optimization,” International Journal of Advanced Research in Electronics and Communication Engineering, vol. 4, no. 9, pp. 2440–2446, 2015.
S. Xiao, H. Yu, Y. Wu, Z. Peng, and Y. Zhang, “Self-evolving trading strategy integrating internet of things and big data,” IEEE Internet of Things Journal, vol. 5, no. 4, pp. 2518–2525, 2018.
Y. Zhang, R. Gravina, H. Lu, M. Villari, and G. Fortino, “PEA: parallel electrocardiogram-based authentication for smart healthcare systems,” Journal of Network and Computer Applications,vol. 117, pp. 10–16, 2018.
Y. Zhang, Z. Tu, and Q. Wang, “TempoRec: temporal-topic based recommender for social network services,” Mobile Networks and Applications, vol. 22, no. 6, pp. 1182–1191, 2017.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
