Medical Image Identification System Using Convolutional Neural Networks for Digital Radiology-Based Disease Diagnosis
DOI:
https://doi.org/10.70062/jeci.v1i3.220Keywords:
Convolutional Neural Network, Diagnostic Accuracy, Medical Imaging, Pneumonia Detection, ResNet50 ModelAbstract
Medical imaging is one of the primary tools in disease diagnosis, but the manual process is often hindered by human factors such as fatigue, cognitive bias, and observational limitations. This study aims to explore the use of a pretrained Convolutional Neural Network (CNN) model, ResNet50, to improve diagnostic accuracy in medical imaging. ResNet50 was selected due to its efficient architecture, which addresses the vanishing gradient problem through the use of skip connections, making it ideal for complex medical image classification tasks. The dataset used includes medical images from various open-source datasets, including chest X-rays, brain MRIs, and retinal histopathology images, which were preprocessed using image normalization and augmentation techniques to enhance data quality. The model was trained with hyperparameters such as a learning rate of 0.001 and batch size of 32, over 50 epochs using the Adam optimizer. The results showed that the model achieved 95% accuracy, with 99% precision and 98% recall in detecting pneumonia from chest X-rays, and 95.44% accuracy in classifying brain tumors. While the model showed excellent performance, challenges such as varying data quality, limited computational resources, and potential overfitting remain. This study demonstrates the significant potential of AI in medical imaging to reduce human diagnostic errors, with promising prospects for wider implementation in clinics and hospitals. However, broader adoption requires integration with clinical workflows and training for healthcare professionals on the use of AI-based systems.
References
J. D. Rudie et al., "Brain MRI deep learning and Bayesian inference system augments radiology resident performance," J. Digit. Imaging, vol. 34, no. 4, pp. 1049–1058, 2021. Tersedia: https://doi.org/10.1007/s10278-021-00470-1.
M. A. Bruno, E. A. Walker, dan H. H. Abujudeh, "Understanding and confronting our mistakes: The epidemiology of error in radiology and strategies for error reduction," Radiographics, vol. 35, no. 6, pp. 1668–1676, 2015. Tersedia: https://doi.org/10.1148/rg.2015150023.
S. Sharma et al., "Using 'reader disagreement index' as a tool for monitoring impact on read quality due to reader fatigue in central reviewers," Progress Biomed. Opt. Imaging, vol. 12035, 2022, Art. no. 120350J. Tersedia: https://doi.org/10.1117/12.2613082.
A. Pinto et al., "Learning from diagnostic errors: A good way to improve education in radiology," Eur. J. Radiol., vol. 78, no. 3, pp. 372–376, 2011. Tersedia: https://doi.org/10.1016/j.ejrad.2010.12.028.
F. P. Busardò et al., "Errors and malpractice lawsuits in radiology: What the radiologist needs to know," Radiol. Med., vol. 120, no. 9, pp. 779–784, 2015. Tersedia: https://doi.org/10.1007/s11547-015-0561-x.
T. Taylor-Phillips dan C. Stinton, "Fatigue in radiology: A fertile area for future research," Br. J. Radiol., vol. 92, no. 1099, 2019, Art. no. 20190043. Tersedia: https://doi.org/10.1259/bjr.20190043.
G. Manjunatha et al., "AI-powered framework for X-ray and MRI image enhancement using Python: A novel approach to reducing noise, blur, and artifacts for superior diagnostic precision," dalam Proc. RAEEUCCI, 2025, pp. 542–547. Tersedia: https://doi.org/10.1109/RAEEUCCI63961.2025.11048227.
J. E. Cowen et al., "Human factors in diagnostic radiology: Practical challenges and cognitive biases," Eur. J. Radiol., vol. 190, 2025, Art. no. 112248. Tersedia: https://doi.org/10.1016/j.ejrad.2025.112248.
D. Kuzinkovas dan S. Clement, "The detection of COVID-19 in chest X-rays using ensemble CNN techniques," Information, vol. 14, no. 7, p. 370, 2023. Tersedia: https://doi.org/10.3390/info14070370.
S. Elhanashi et al., "AI-powered object detection in radiology: Current models, challenges, and future direction," J. Imaging, vol. 11, no. 5, p. 141, 2025. Tersedia: https://doi.org/10.3390/jimaging11050141.
M. Fathi et al., "Cultivating diagnostic clarity: The importance of reporting artificial intelligence confidence levels in radiologic diagnoses," Clin. Imaging, vol. 117, 2024, Art. no. 110356. Tersedia: https://doi.org/10.1016/j.clinimag.2024.110356.
R. Shrivastava et al., "AI in medical imaging: Enhancing diagnostic accuracy with deep convolutional networks," dalam Proc. ICCCIT, 2025, pp. 542–547. Tersedia: https://doi.org/10.1109/ICCCIT62592.2025.10927771.
A. Chepelev, S. Nicolaou, dan A. Sheikh, "AI for medical image processing: Improving quality, accessibility, and safety," dalam AI in Clinical Medicine: A Practical Guide for Healthcare Professionals, Wiley, 2023, pp. 350–364. Tersedia: https://doi.org/10.1002/9781119790686.ch34.
A. Taylor-Phillips et al., "Fatigue in radiology: A fertile area for future research," Digital Diagn., vol. 2, no. 2, pp. 211–222, 2021. Tersedia: https://doi.org/10.17816/DD71630.
A. K. Uchevatkin et al., "Shades of grey: How and why we make mistakes," Med. Visualization, vol. 24, no. 3, pp. 123–145, 2020. Tersedia: https://doi.org/10.24835/1607-0763-2020-3-123-145.
R. Rani dan S. Gupta, "Automated retinal disease classification using fine-tuned ResNet50: A deep learning approach for early diagnosis," Proc. 3rd Int. Conf. Intelligent Innov. Technol. Comput. Electrical Electronics, IITCEE 2025, pp. 109–153, 2025. Tersedia: https://doi.org/10.1109/IITCEE64140.2025.10915328.
G. Singh, K. Guleria, dan S. Sharma, "Advancing neuro-oncology with multiclass brain tumour classification using pre-trained ResNet50 model," 2024 Int. Conf. Control, Comput. Commun. Mater., ICCCCM 2024, pp. 385–390, 2024. Tersedia: https://doi.org/10.1109/ICCCCM61016.2024.11039938.
S. Cuenca-Dominguez et al., "Advancing healthcare: Early tuberculosis detection in chest X-rays through select convolutional neural networks," Lecture Notes in Networks and Systems, vol. 775, pp. 272–284, 2024. Tersedia: https://doi.org/10.1007/978-3-031-69228-4_18.
N. N. A. Zahrani dan R. Hedjar, "Comparison study of deep-learning architectures for classification of thoracic pathology," 2022 13th Int. Conf. Inf. Commun. Syst., ICICS 2022, pp. 192–198, 2022. Tersedia: https://doi.org/10.1109/ICICS55353.2022.9811150.
P. Kaushik dan S. Choudhary, "Enhanced breast cancer detection using ResNet50V2-based convolutional neural networks," Proc. 2024 4th Int. Conf. Soft Comput. Security Appl., ICSCSA 2024, pp. 374–379, 2024. Tersedia: https://doi.org/10.1109/ICSCSA64454.2024.00066.
M. Jayababu et al., "Classification of gastrointestinal disease images through residual learning algorithm and comparative analysis of deep learning architectures," Proc. 8th Int. Conf. Trends Electronics Informatics, ICOEI 2025, pp. 1388–1394, 2025. Tersedia: https://doi.org/10.1109/ICOEI65986.2025.11013720.
A. V. Ikechukwu dan S. Bhimshetty, "Optimizing ResNet50 and VGG19 networks for accurate COPD diagnosis through CXR analysis," Lecture Notes in Electrical Engineering, vol. 1300, pp. 307–320, 2025. Tersedia: https://doi.org/10.1007/978-981-96-0165-3_23.
S. Tirumala, N. Jamil, dan B. A. Sassani, "An investigation on ability of pre-trained convolutional neural networks trained on ImageNet to classify melanoma images without re-training," Commun. Comput. Inform. Sci., vol. 1198, pp. 539–548, 2020. Tersedia: https://doi.org/10.1007/978-981-15-5232-8_46.
B. Allen Jr., M. Chatfield, J. Burleson, dan W. T. Thorwarth, "Improving diagnosis in health care: Perspectives from the American College of Radiology," Diagnosis, vol. 4, no. 3, pp. 113–124, 2017. Tersedia: https://doi.org/10.1515/dx-2017-0020.
D. Ključevšek, V. Potočnik Tumpaj, dan A. Gazikalović, "The role of radiography in diagnosing, monitoring, and prognosing juvenile idiopathic arthritis," Pediatric Radiology, vol. 54, no. 4, pp. 481–489, 2024. Tersedia: https://doi.org/10.1007/s00247-023-05742-2.
Q. X. Tee, M. Nambiar, dan S. Stuckey, "Error and cognitive bias in diagnostic radiology," J. Med. Imaging Radiat. Oncol., vol. 66, no. 2, pp. 202–207, 2022. Tersedia: https://doi.org/10.1111/1754-9485.13320.
S. Waite et al., "Opportunity and opportunism in artificial intelligence-powered data extraction: A value-centered approach," Am. J. Roentgenol., vol. 223, no. 6, p. 31686, 2024. Tersedia: https://doi.org/10.2214/AJR.24.31686.
B. Morgan, J. A. Stephenson, dan Y. Griffin, "Minimising the impact of errors in the interpretation of CT images for surveillance and evaluation of therapy in cancer," Clin. Radiol., vol. 71, no. 11, pp. 1083–1094, 2016. Tersedia: https://doi.org/10.1016/j.crad.2016.07.001.
A. Pinto et al., "Errors in MDCT diagnosis of acute mesenteric ischemia," Abdom. Radiol., vol. 47, no. 5, pp. 1699–1713, 2022. Tersedia: https://doi.org/10.1007/s00261-020-02732-y.
M. Bordalo, "Errors in musculoskeletal radiology: What I have learned," Semin. Musculoskelet. Radiol., vol. 29, no. 5, pp. 807–812, 2025. Tersedia: https://doi.org/10.1055/s-0045-1802975.
A. J. Spies et al., "Case discussions of missed traumatic fractures on computed tomography scans," South African J. Radiol., vol. 26, no. 1, Art. no. a2516, 2022. Tersedia: https://doi.org/10.4102/sajr.v26i1.2516.
D. Stuhlman, "A method to optimize and automate the distribution of radiology studies," Lecture Notes in Networks and Systems, vol. 258, pp. 422–435, 2022. Tersedia: https://doi.org/10.1007/978-3-030-82099-2_38.
L. P. Busby, J. L. Courtier, dan C. M. Glastonbury, "Bias in radiology: The how and why of misses and misinterpretations," Radiographics, vol. 38, no. 1, pp. 236–247, 2018. Tersedia: https://doi.org/10.1148/rg.2018170107.
X. Wang et al., "Reducing errors in breast imaging: Insights from missed and near-missed cases," J. Breast Imaging, vol. 7, no. 3, pp. 363–377, 2025. Tersedia: https://doi.org/10.1093/jbi/wbaf005.
A. Pinto et al., "Errors in imaging patients in the emergency setting," Br. J. Radiol., vol. 89, no. 1061, Art. no. 20150914, 2016. Tersedia: https://doi.org/10.1259/bjr.20150914.
P. Kumari, "Transforming medical imaging with convolutional neural networks (CNNs): Advances in diagnosis and treatment," dalam Deep Learning in Medical Signal and Image Processing, pp. 195–230, 2025. Tersedia: https://doi.org/10.4018/979-8-3693-9816-6.ch009.
S. Tiwari et al., "A comprehensive review on the application of 3D convolutional neural networks in medical imaging," Eng. Proc., vol. 59, no. 1, p. 3, 2023. Tersedia: https://doi.org/10.3390/engproc2023059003.
E. Gürsoy dan Y. Kaya, "Brain-GCN-Net: Graph-convolutional neural network for brain tumor identification," Comput. Biol. Med., vol. 180, p. 108971, 2024. Tersedia: https://doi.org/10.1016/j.compbiomed.2024.108971.
O. Shobayo dan R. Saatchi, "Developments in deep learning artificial neural network techniques for medical image analysis and interpretation," Diagnostics, vol. 15, no. 9, p. 1072, 2025. Tersedia: https://doi.org/10.3390/diagnostics15091072.
L. Dai, M. Zhou, dan H. Liu, "Recent applications of convolutional neural networks in medical data analysis," dalam Federated Learning and AI for Healthcare 5.0, pp. 119–131, 2023. Tersedia: https://doi.org/10.4018/979-8-3693-1022-9.ch007.
D. Manolescu, N. Buckley, dan E. L. Secco, "Convolutional neural network applied to X-ray medical imagery for pneumonia identification," dalam Lecture Notes in Networks and Systems, vol. 967, pp. 183–197, 2024. Tersedia: https://doi.org/10.1007/978-981-97-2053-8_14.
M. A. Mahjoubi et al., "Improved multiclass brain tumor detection using convolutional neural networks and magnetic resonance imaging," Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 3, pp. 406–414, 2023. Tersedia: https://doi.org/10.14569/IJACSA.2023.0140346.
G. P. Pal dan R. Pal, "Exploring the potential of deep learning algorithms in medical image processing: A comprehensive analysis," dalam Lecture Notes in Networks and Systems, vol. 968, pp. 61–70, 2024. Tersedia: https://doi.org/10.1007/978-981-97-2079-8_5.
G. Kourounis et al., "Computer image analysis with artificial intelligence: A practical introduction to convolutional neural networks for medical professionals," Postgrad. Med. J., vol. 99, no. 1178, pp. 1287–1294, 2023. Tersedia: https://doi.org/10.1093/postmj/qgad095.
S. K. Mydhili et al., "CNN-based deep learning for pneumonia detection," dalam 12th IEEE Int. Conf. Adv. Comput., ICoAC 2023, 2023. Tersedia: https://doi.org/10.1109/ICoAC59537.2023.10249251.
M. Indikar, S. M. Dandgall, dan V. P. Baligar, "Brain tumor classification using convolutional neural network," dalam 2nd IEEE Int. Conf. Adv. Inf. Technol., ICAIT 2024, pp. 10690562, 2024. Tersedia: https://doi.org/10.1109/ICAIT61638.2024.10690562.
M. Shobayo, "AI in medical imaging and deep learning: Challenges and future directions," J. Med. Imaging and Comput. Vision, vol. 29, pp. 159–167, 2025. Tersedia: https://doi.org/10.1007/jmicv.2025.02937.
