Development of a multi-fusion convolutional neural network (MF-CNN) for enhanced gastrointestinal disease diagnosis in endoscopy image analysis

• Main Authors: Hossain, Tanzim, Shamrat, F.M. Javed Mehedi, Zhou, Xujuan, Mahmud, Imran, Mazumder, Md. Sakib Ali, Sharmin, Sharmin, Gururajan, Raj
• Format: Article
• Published: PeerJ 2024
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://eprints.um.edu.my/45299/; https://doi.org/10.7717/peerj-cs.1950
• Institution: Universiti Malaya

Gastrointestinal (GI) diseases are prevalent medical conditions that require accurate and timely diagnosis for effective treatment. To address this, we developed the MultiFusion Convolutional Neural Network (MF-CNN), a deep learning framework that strategically integrates and adapts elements from six deep learning models, enhancing feature extraction and classi fi cation of GI diseases from endoscopic images. The MF-CNN architecture leverages truncated and partially frozen layers from existing models, augmented with novel components such as Auxiliary Fusing Layers (AuxFL), Fusion Residual Block (FuRB), and Alpha Dropouts ( alpha DO) to improve precision and robustness. This design facilitates the precise identi fi cation of conditions such as ulcerative colitis, polyps, esophagitis, and healthy colons. Our methodology involved preprocessing endoscopic images sourced from open databases, including KVASIR and ETIS-Larib Polyp DB, using adaptive histogram equalization (AHE) to enhance their quality. The MF-CNN framework supports detailed feature mapping for improved interpretability of the model ` s internal workings. An ablation study was conducted to validate the contribution of each component, demonstrating that the integration of AuxFL, alpha DO, and FuRB played a crucial part in reducing over fi tting and ef fi ciency saturation and enhancing overall model performance. The MF-CNN demonstrated outstanding performance in terms of ef fi cacy, achieving an accuracy rate of 99.25%. It also excelled in other key performance metrics with a precision of 99.27%, a recall of 99.25%, and an F1 -score of 99.25%. These metrics con fi rmed the model ` s pro fi ciency in accurate classi fi cation and its capability to minimize false positives and negatives across all tested GI disease categories. Furthermore, the AUC values were exceptional, averaging 1.00 for both test and validation sets, indicating perfect discriminative ability. The fi ndings of the P -R curve analysis and confusion matrix further con fi rmed the robust classi fi cation performance of the MF-CNN. This research introduces a technique for medical imaging that can potentially transform diagnostics in gastrointestinal healthcare facilities worldwide.