Abstract

Convolutional Neural Networks (CNNs) have become essential tools in automated medical diagnostics, delivering strong performance across a wide range of medical imaging types. In this study, we introduce a 17-layer CNN—made up of 15 convolutional layers and 2 fully connected layers—designed to detect and classify brain tumors, COVID-19, pneumonia, and breast cancer from multimodal images, including MRI scans, chest X-rays, and histopathological slides. The model is first trained on balanced datasets to develop stable and generalizable feature representations, and then fine-tuned on realworld, imbalanced data using a weighted random sampling technique to account for class distribution differences. Cross-validation results show high accuracy across all tasks: 99.97% for brain tumor detection, 99.96% for COVID-19, 98.06% for pneumonia, and 94.87% for breast histopathology. To boost generalization and reduce overfitting, the architecture incorporates batch normalization, transfer learning, and strategic data resampling. Diagnostic performance is further validated using ROC curves, precision–recall metrics, and confusion matrices. By effectively addressing common challenges like class imbalance and domain variability, this work demonstrates the real-world potential of deep learning models to enhance clinical decision-making and support precision medicine.

References

• Ahmed H Abdel-Gawad, Lobna A Said, and Ahmed G Radwan. Optimized edge detection technique for brain tumor detection in mr images. IEEE Access, 8:136243–136259, 2020.
• Nyoman Abiwinanda, Muhammad Hanif, S Tafwida Hesaputra, Astri Handayani, and Tati Rajab Mengko. Brain tumor classification using convolutional neural network. In World Congress on Medical Physics and Biomedical Engineering 2018: June 3-8, 2018, Prague, Czech Republic (Vol. 1), pages 183–189. Springer, 2019.
• Parnian Afshar, Arash Mohammadi, and Konstantinos N Plataniotis. Brain tumor type classification via capsule networks. In 2018 25th IEEE international conference on image processing (ICIP), pages 3129–3133. IEEE, 2018.
• Hayat O Alasasfeh, Taqwa Alomari, and MS Ibbini. Deep learning approach for covid-19 detection based on x-ray images. In 2021 18th International Multi-Conference on Systems, Signals & Devices (SSD), pages 1–6. IEEE, 2021.
• Javeria Amin, Muhammad Sharif, Mussarat Yasmin, and Steven Lawrence Fernandes. Big data analysis for brain tumor detection: Deep convolutional neural networks. Future Generation Computer Systems, 87:290–297, 2018.
• Jun Cheng. Brain tumor dataset. figshare. Dataset, 1512427(5), 2017.
• Sreeparna Das, Ishan Ayus, and Deepak Gupta. A comprehensive review of covid-19 detection with machine learning and deep learning techniques. Health and Technology, pages 1–14, 2023.
• Mohammad Havaei, Axel Davy, David Warde-Farley, Antoine Biard, Aaron Courville, Yoshua Bengio, Chris Pal, Pierre-Marc Jodoin, and Hugo Larochelle. Brain tumor segmentation with deep neural networks. Medical image analysis, 35:18–31, 2017.
• Shrutika Santosh Hunnur, Akshata Raut, and Swati Kulkarni. Implementation of image processing for detection of brain tumors. In 2017 International Conference on Computing Methodologies and Communication (ICCMC), pages 717–722. IEEE, 2017.
• Yohan Jun, Taejoon Eo, Taeseong Kim, Hyungseob Shin, Dosik Hwang, So Hi Bae, Yae Won Park, Ho-Joon Lee, ByoungWook Choi, and Sung Soo Ahn. Deep-learned 3d blackblood imaging using automatic labelling technique and 3d convolutional neural networks for detecting metastatic brain tumors. Scientific reports, 8(1):9450, 2018.
• Naresh Khuriwal and Nidhi Mishra. Breast cancer detection from histopathological images using deep learning. In 2018 3rd international conference and workshops on recent advances and innovations in engineering (ICRAIE), pages 1–4. IEEE, 2018.
• Gulshan Kumar, Puneet Kumar, and Deepika Kumar. Brain tumor detection using convolutional neural network. In 2021 IEEE International Conference on Mobile Networks and Wireless Communications (ICMNWC), pages 1–6. IEEE, 2021.
• Tingting Liu, Zhi Yuan, LiWu, and Benjamin Badami. An optimal brain tumor detection by convolutional neural network and enhanced sparrow search algorithm. Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, 235(4):459–469, 2021.
• Shraddha S More, Mansi Ashok Mange, Mitheel Sandip Sankhe, and Shwethali Santosh Sahu. Convolutional neural network based brain tumor detection. In 2021 5th International conference on intelligent computing and control systems (ICICCS), pages 1532–1538. IEEE, 2021.
• Ayush Pant, Akshat Jain, Kiran C Nayak, Daksh Gandhi, and BG Prasad. Pneumonia detection: An efficient approach using deep learning. In 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT), pages 1–6. IEEE, 2020.
• J Seetha and S Selvakumar Raja. Brain tumor classification using convolutional neural networks. Biomedical & Pharmacology Journal, 11(3):1457, 2018.
• Ghada A Shadeed, Abdullah A Jabber, and Nahedh H Alwash. I. covid-19 detection using deep learning models. In 2021 1st Babylon international conference on information technology and science (BICITS), pages 194–198. IEEE, 2021.
• Komal Sharma, Akwinder Kaur, and Shruti Gujral. Brain tumor detection based on machine learning algorithms. International Journal of Computer Applications, 103(1), 2014.
• Swapnil Singh. Pneumonia detection using deep learning. In 2021 4th Biennial International Conference on Nascent Technologies in Engineering (ICNTE), pages 1–6. IEEE, 2021.
• Fabio Alexandre Spanhol, Luiz S Oliveira, Caroline Petitjean, and Laurent Heutte. Breast cancer histopathological image classification using convolutional neural networks. In 2016 international joint conference on neural networks (IJCNN), pages 2560–2567. IEEE, 2016.