Diagnostics of Multi-Order Lung Cancer Models: Comparison
View Latest Version
Please note this is a comparison between Version 2 by Lindsay Dong and Version 1 by umamaheswaran S.

The early detection and classification of lung cancer is crucial for improving a patient’s outcome. However, the traditional classification methods are based on single machine learning models. Hence, this is limited by the availability and quality of data at the centralized computing server. 

  • lung cancer classification
  • diagnostics
  • Machine learning models

1. Introduction

Lung cancer diagnosis and treatment utilizing computational approaches present multifaceted challenges at the intersection of medicine, data science, and technology. The etiology of lung cancers primarily involves somatic mutations arising from DNA resequencing events, induced by a myriad of factors, including environmental exposure and genetic predisposition. The detection of lung cancer at its early stages is hindered by the lack of distinct symptoms, often leading to delayed diagnosis and poor prognosis. Quantitative analysis by the World Health Organization (WHO) reveals a staggering global incidence of approximately 2.21 million reported cases of lung cancer annually, necessitating advanced research and innovative technological solutions to combat this prevalent and life-threatening disease. In the realm of computational methodologies, machine learning models have emerged as pivotal tools for addressing lung cancer challenges. These models are trained on diverse datasets, encompassing genomic profiles, radiological images (such as computed tomography scans), histopathological slides, and clinical records. Leveraging supervised and unsupervised learning paradigms, machine learning algorithms can discern complex patterns and features within these heterogeneous datasets, enabling early diagnosis, tumor subtyping, and survival prediction.
The successful amalgamation of computational methodologies with medical practices necessitates careful handling of medical terminologies and the implementation of standardized data representation schemas. Collaborative efforts among medical professionals, computational scientists, and domain experts are vital for constructing informative feature sets, minimizing data biases, and generating robust predictive models. State-of-the-art techniques like deep learning have exhibited exceptional capabilities in feature extraction and representation learning, empowering them to identify intricate biomarkers and genetic signatures, which were previously challenging to detect using traditional statistical methods. However, model interpretability remains a critical concern, as black-box models can hinder the medical community’s understanding of decisions made by these algorithms.
Translating computational results into clinical applications demands an adherence to rigorous validation and reproducibility standards. Cross-validation techniques, external validation cohorts, and robust statistical analyses are crucial to ensure model generalizability and clinical utility. Furthermore, establishing transparent reporting practices enhances the credibility and adoption of computational findings in the medical domain. Beyond diagnostic applications, computational approaches play a pivotal role in treatment monitoring and precision medicine. Predictive models can aid in drug sensitivity prediction, guiding oncologists to select personalized treatment regimens and optimize therapeutic interventions. Additionally, real-time monitoring systems can continuously assess treatment responses, enabling adaptive therapy and minimizing adverse effects.
Ethical considerations are imperative in the integration of technology into healthcare. Privacy preservation and secure data-sharing mechanisms are critical to safeguard patient data. Furthermore, continuous human oversight and the active involvement of medical professionals are essential to prevent overreliance on automated systems and ensure a patient-centered approach to care. The computational approaches, particularly machine learning models, hold tremendous promise in revolutionizing lung cancer diagnosis and treatment. By capitalizing on multidimensional data and leveraging cutting-edge algorithms, computational methodologies have the potential to usher in a new era of precision oncology, ultimately improving patient outcomes and transforming lung cancer management. However, a concerted effort among diverse stakeholders, rigorous validation, and ethical considerations are indispensable to unlock the full potential of computational technologies in combating lung cancer effectively.

2. Models

Lung cancer is widely concerning for technical researchers to provide solutions, as early detection and categorization is minimal. From the technological front, solutions have been initialized from X-ray image processing and have evolved over time to Artificial Intelligence (AI). Various studies and observations for combating lung cancer detection, classification, and diagnosis have been recorded and published in the last decade. In [1[1][2],2], a systematic approach of a deep learning model is proposed on multiple data types such as X-rays, computed tomography (CT), and magnetic image resonance (MRI) images. The study focuses on how deep learning approaches can be implemented for lung cancer diagnosis and evaluation. Further, the approach toward lung cancer is based on the medical prospects in categorizing it as small cell lung carcinoma (SCLC) or non-small cell lung carcinoma (NSCLC) [3], to provide a wider perspective on occurrence and decision-making challenges. The study [3] concludes with a remark that neural networking algorithms are a much more reliable source of evaluation among researchers.

2.1. Initial Models

Machine learning models play vital role in understanding the behavioral approach of classifying and detecting lung cancers, with [4,5][4][5] proposing various models and techniques for optimizing lung cancer classification and decision-making. The studies have further provided a reliable understanding of the purpose and need for upgrading technological approaches in solving challenging issues such as carcinoma classification on normalized datasets. An advanced machine learning-based approach for lung cancer [6] is proposed for customization of improved images ranges and data types. The studies have included computer-aided design engineering (CADE) models for analyzing and validating datasets [7[7][8],8], to assure a reliable decision-making support. The computer-aided image systems and techniques provide a scalable environment for multi-objective dataset consideration and changes as per the technological development. The lung cancer detection and prediction results and experience are shared and enhanced under a telemedicine ecosystem with an interdependency of electronic health records (EHR). The framework of Internet of Medical Things (IoMT) [9] has further provided an extended support for larger data sharing and decision-making. The terminology of Federated Learning (FL) provides greater prospects of shared information-based decision-making in a reliable manner. The federated models are reported by [10,11,12][10][11][12] in various medical data analysis and computations. The overall process of a Federated Learning model is to provide a distributed environment and a local- or client-based computation with reference to streamlining data operations. The architectural model and standard operation is proposed in [13]. The way forward for a Federated Learning model is to provide a threshold operation for customizing the information and data communication protocols via a remote server management tool.

2.2. Advanced Models

Deep learning (DL) models are used for the classification of lung cancer [14,15][14][15], with the classification based on the feature extraction of the lung cancer, while the techniques involved in the computation, such as the Histogram of Oriented Gradients (HoG), wavelet transformer-based features, and local binary patterns, are a few of the dominating approaches. Non-small cell-based lung cancer classification [16] is another prominent classification approach included in the domain of classifications followed by biomarkers [17]. The CT-based [18] classification under trivial approaches and the historiographic representations are included for reliable decision-making and support ecosystem development. This support system can be derived from contempory studies related to the classification process, as [19] with the extraction of patterns from the wave file and annotating them into depression and [20] with CT images classification-based on a fuzzy system. Positron emission tomography (PET) and CT images are further considered for processing in a single environment to improve decision-making support, as in [21]. Ref. [22] provides a detailed survey and different types of lung cancer with respect to the imaging. The survey further assures that the dependency is improved from one systems operation and dataset to an independent computing unit. Approaches such as machine learning [23] and classification [24] provide justifiable decision-making capabilities on the lung cancer computation. These approaches further customize and process the behavioral model of computations algorithms [25,26][25][26]. The basic image computation and processing approach was defined and maintained on summarizing computational techniques, and hence the interdependency on decision-making was an unavoidable situation. The approach of trivial processing under centralized servers was replaced by distributed servers, with Federated Learning leading the domain. The Federated Learning (FL) models are based on the policies and standards of operation [27], with other architecture such as [28,29,30][28][29][30] under a decentralized server’s configuration. The approach benefits the operations and customization possibilities of processing lung cancer [31,32,33][31][32][33].

References

  1. Wang, L. Deep learning techniques to diagnose lung cancer. Cancers 2022, 14, 5569.
  2. Riquelme, D.; Akhloufi, M.A. Deep learning for lung cancer nodules detection and classification in CT scans. Ai 2020, 1, 28–67.
  3. Shamas, S.; Panda, S.N.; Sharma, I. Review on lung nodule segmentation-based lung cancer classification using machine learning approaches. In Artificial Intelligence on Medical Data: Proceedings of International Symposium, ISCMM 2021, Sikkim, India, 11–12 November 2021; Springer Nature: Singapore, 2022; pp. 277–286.
  4. Joshua, E.S.N.; Chakkravarthy, M.; Bhattacharyya, D. An Extensive Review on Lung Cancer Detection Using Machine Learning Techniques: A Systematic Study. Rev. D’Intelligence Artif. 2020, 34.
  5. Raoof, S.S.; Jabbar, M.A.; Fathima, S.A. Lung Cancer prediction using machine learning: A comprehensive approach. In Proceedings of the 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), Bangalore, India, 5–7 March 2020; IEEE: Piscataway, NJ, USA, 2020; pp. 108–115.
  6. Kadir, T.; Gleeson, F. Lung cancer prediction using machine learning and advanced imaging techniques. Transl. Lung Cancer Res. 2018, 7, 304.
  7. Cong, L.; Feng, W.; Yao, Z.; Zhou, X.; Xiao, W. Deep learning model as a new trend in computer-aided diagnosis of tumor pathology for lung cancer. J. Cancer 2020, 11, 3615.
  8. Sathiyamoorthi, V.; Ilavarasi, A.K.; Murugeswari, K.; Ahmed, S.T.; Devi, B.A.; Kalipindi, M. A deep convolutional neural network based computer aided diagnosis system for the prediction of Alzheimer’s disease in MRI images. Measurement 2021, 171, 108838.
  9. Venkatesan, V.K.; Ramakrishna, M.T.; Izonin, I.; Tkachenko, R.; Havryliuk, M. Efficient Data Preprocessing with Ensemble Machine Learning Technique for the Early Detection of Chronic Kidney Disease. Appl. Sci. 2023, 13, 2885.
  10. Ramakrishna, M.T.; Venkatesan, V.K.; Izonin, I.; Havryliuk, M.; Bhat, C.R. Homogeneous Adaboost Ensemble Machine Learning Algorithms with Reduced Entropy on Balanced Data. Entropy 2023, 25, 245.
  11. Adnan, M.; Kalra, S.; Cresswell, J.C.; Taylor, G.W.; Tizhoosh, H.R. Federated learning and differential privacy for medical image analysis. Sci. Rep. 2022, 12, 1953.
  12. Chowdhury, A.; Kassem, H.; Padoy, N.; Umeton, R.; Karargyris, A. A review of medical federated learning: Applications in oncology and cancer research. In Proceedings of the International MICCAI Brainlesion Workshop, Virtual Event, 27 September 2021; Springer International Publishing: Cham, Switzerland, 2021; pp. 3–24.
  13. Antunes, R.S.; André da Costa, C.; Küderle, A.; Yari, I.A.; Eskofier, B. Federated learning for healthcare: Systematic review and architecture proposal. ACM Trans. Intell. Syst. Technol. 2022, 13, 1–23.
  14. Asuntha, A.; Srinivasan, A. Deep learning for lung Cancer detection and classification. Multimed. Tools Appl. 2020, 79, 7731–7762.
  15. Ibrahim, D.M.; Elshennawy, N.M.; Sarhan, A.M. Deep-chest: Multi-classification deep learning model for diagnosing COVID-19, pneumonia, and lung cancer chest diseases. Comput. Biol. Med. 2021, 132, 104348.
  16. Raghunath, K.M.K.; Kumar, V.V.; Venkatesan, M.; Singh, K.K.; Mahesh, T.R.; Singh, A. XGBoost Regression Classifier (XRC) Model for Cyber Attack Detection and Classification Using Inception V4. J. Web Eng. 2022, 21, 1295–1322.
  17. Saha, S.; Nassisi, M.; Wang, M.; Lindenberg, S.; Kanagasingam, Y.; Sadda, S.; Hu, Z.J. Automated detection and classification of early AMD biomarkers using deep learning. Sci. Rep. 2019, 9, 10990.
  18. Kuruvilla, J.; Gunavathi, K. Lung cancer classification using neural networks for CT images. Comput. Methods Programs Biomed. 2014, 113, 202–209.
  19. Ahmed, S.T.; Singh, D.K.; Basha, S.M.; Abouel Nasr, E.; Kamrani, A.K.; Aboudaif, M.K. Neural network based mental depression identification and sentiments classification technique from speech signals: A COVID-19 Focused Pandemic Study. Front. Public Health 2021, 9, 781827.
  20. Kuruvilla, J.; Gunavathi, K. Lung cancer classification using fuzzy logic for CT images. Int. J. Med. Eng. Inform. 2015, 7, 233–249.
  21. Hochhegger, B.; Alves, G.R.T.; Irion, K.L.; Fritscher, C.C.; Fritscher, L.G.; Concatto, N.H.; Marchiori, E. PET/CT imaging in lung cancer: Indications and findings. J. Bras. De Pneumol. 2015, 41, 264–274.
  22. Devarajan, D.; Alex, D.S.; Mahesh, T.R.; Kumar, V.V.; Aluvalu, R.; Maheswari, V.U.; Shitharth, S. Cervical cancer diagnosis using intelligent living behavior of artificial jellyfish optimized with artificial neural network. IEEE Access 2022, 10, 126957–126968.
  23. Dandıl, E. A computer-aided pipeline for automatic lung cancer classification on computed tomography scans. J. Healthc. Eng. 2018, 2018, 9409267.
  24. Nageswaran, S.; Arunkumar, G.; Bisht, A.K.; Mewada, S.; Kumar, J.N.V.R.; Jawarneh, M.; Asenso, E. Lung cancer classification and prediction using machine learning and image processing. BioMed Res. Int. 2022, 2022, 1755460.
  25. Nanglia, P.; Kumar, S.; Mahajan, A.N.; Singh, P.; Rathee, D. A hybrid algorithm for lung cancer classification using SVM and Neural Networks. ICT Express 2021, 7, 335–341.
  26. Kumar, B.N.; Mahesh, T.R.; Geetha, G.; Guluwadi, S. Redefining Retinal Lesion Segmentation: A Quantum Leap With DL-UNet Enhanced Auto Encoder-Decoder for Fundus Image Analysis. IEEE Access 2023, 11, 70853–70864.
  27. Fontana, R.S.; Sanderson, D.R.; Woolner, L.B.; Taylor, W.F.; Eugene Miller, W.; Muhm, J.R.; Bernatz, P.E.; Payne, W.S.; Pairolero, P.C.; Bergstralh, E.J. Screening for lung cancer. A critique of the Mayo Lung Project. Cancer 1991, 67, 1155–1164.
  28. Liu, L.; Fan, K.; Yang, M. Federated learning: A deep learning model based on resnet18 dual path for lung nodule detection. Multimed. Tools Appl. 2023, 82, 17437–17450.
  29. Subramanian, M.; Rajasekar, V.; Sathishkumar, V.E.; Shanmugavadivel, K.; Nandhini, P.S. Effectiveness of Decentralized Federated Learning Algorithms in Healthcare: A Case Study on Cancer Classification. Electronics 2022, 11, 4117.
  30. Dataset from Cancer Image Archives (CIA). Available online: https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=80970785 (accessed on 25 March 2023).
  31. Hassan, M.M.; Hassan, M.M.; Yasmin, F.; Khan, M.A.R.; Zaman, S.; Islam, K.K.; Bairagi, A.K. A comparative assessment of machine learning algorithms with the Least Absolute Shrinkage and Selection Operator for breast cancer detection and prediction. Decis. Anal. J. 2023, 7, 100245.
  32. Mukundan, A.; Feng, S.W.; Weng, Y.H.; Tsao, Y.M.; Artemkina, S.B.; Fedorov, V.E.; Lin, Y.-S.; Huang, Y.-C.; Wang, H.-C. Optical and material characteristics of MoS2/Cu2O sensor for detection of lung cancer cell types in hydroplegia. Int. J. Mol. Sci. 2022, 23, 4745.
  33. Tian, C.; Meng, X.; Zhang, Z.; Zhu, H.; An, H.; Li, W.; Yuan, S. Hyperspectral imaging: A new method for diagnosing benign and malignant lung cancer. In Proceedings of the Third International Conference on Optics and Image Processing (ICOIP 2023), Kuala Lumpur, Malaysia, 8–11 October 2023; SPIE: Bellingham, WA, USA, 2023; Volume 12747, pp. 474–480.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/)
Video Production Service
Feedback