.png)
Multi Domain Feature Fusion and Boosting Based Learning for Robust Gallbladder Ultrasound Image Classification
Abstract
Accurate identification of gallbladder conditions is critically important in the medical sector, as early detection of diseases such as gallstones, cholecystitis, carcinoma, and polyps can substantially improve treatment outcomes, reduce complications, and guide timely surgical or therapeutic interventions. Existing literature on gallbladder disease classification still presents notable gaps. Most prior works rely solely on single-domain feature extraction either deep CNN-based spatial descriptors or handcrafted statistical/texture features without exploiting the complementary strengths of multi-domain feature fusion. This study addresses these gaps by proposing a hybrid framework that combines advanced preprocessing, multi-domain feature fusion, feature selection, and ensemble classification. The preprocessing pipeline applies Non-Local Means (NLM) denoising, Contrast Limited Adaptive Histogram Equalization (CLAHE), frequency-domain low-pass filtering, and Gabor filtering to enhance image quality and highlight diagnostically relevant structures. Features are extracted by fusing deep spatial descriptors from a pretrained Inception V3 network with handcrafted statistical and texture-based features, including Gray Level Dependency Matrix (GLDM) measures. Dimensionality reduction is performed using ANOVA k-best selection to retain the most discriminative attributes. The refined features are classified using LightGBM, XGBoost, Histogram Gradient Boosting, and AdaBoost, enabling a comprehensive performance comparison. Experiments conducted on the balanced UIdataGB dataset (10,692 annotated images across nine diagnostic categories) demonstrate that LightGBM, XGBoost, and Histogram Gradient Boosting achieve near-perfect performance, with accuracies exceeding 98.6% and AUC values of 0.98 across all classes, while AdaBoost shows markedly lower discriminative capability.The results suggest that gradient boosting approaches are a promising option for multi-class gallbladder disease detection, particularly when combined with multi-domain feature fusion and appropriate preprocessing and feature selection techniques.
Keywords
Full Text:
PDFReferences
M. Byra et al., “Transfer learning with deep convolutional neural network for liver steatosis assessment in ultrasound images,” Int. J. Comput. Assist. Radiol. Surg., vol. 13, no. 12, pp. 1895–1903, Dec. 2018, doi: 10.1007/s11548-018-1843-2.
S. Y. Rhyou and J. C. Yoo, “Cascaded deep learning neural network for automated liver steatosis diagnosis using ultrasound images,” Sensors, vol. 21, no. 16, Aug. 2021, doi: 10.3390/s21165304.
S. Mahmud et al., “Automated grading of prenatal hydronephrosis severity from segmented kidney ultrasounds using deep learning,” Expert Syst. Appl., vol. 255, Dec. 2024, doi: 10.1016/j.eswa.2024.124594.
M. Tounsi, D. Y. Abdulhussain, A. T. Azar, A. Al-Khayyat, and I. K. Ibraheem, “Deep Learning Model-based Decision Support System for Kidney Cancer on Renal Images,” Engineering, Technology and Applied Science Research, vol. 14, no. 5, pp. 17177–17187, Oct. 2024, doi: 10.48084/etasr.8335.
G. A. Pradipta, R. Wardoyo, A. Musdholifah, and I. N. H. Sanjaya, “Improving classifiaction performance of fetal umbilical cord using combination of SMOTE method and multiclassifier voting in imbalanced data and small dataset,” International Journal of Intelligent Engineering and Systems, vol. 13, no. 5, pp. 441–454, Oct. 2020, doi: 10.22266/ijies2020.1031.39.
G. A. Pradipta, R. Wardoyo, A. Musdholifah, and I. N. H. Sanjaya, “Machine learning model for umbilical cord classification using combination coiling index and texture feature based on 2-D Doppler ultrasound images,” Health Informatics J., vol. 28, no. 1, Mar. 2022, doi: 10.1177/14604582221084211.
P. D. W. Ayu, G. A. Pradipta, R. R. Huizen, E. S. W. Kadek, and I. G. E. Artana, “Combining CNN Feature Extractors and Oversampling Safe Level SMOTE to Enhance Amniotic Fluid Ultrasound Image Classification,” International Journal of Intelligent Engineering and Systems, vol. 17, no. 1, pp. 251–262, 2024, doi: 10.22266/ijies2024.0229.24.
P. D. W. Ayu, S. Hartati, A. Musdholifah, and D. S. Nurdiati, “Amniotic fluid segmentation based on pixel classification using local window information and distance angle pixel,” in Applied Soft Computing, Elsevier Ltd, Aug. 2021. doi: 10.1016/j.asoc.2021.107196.
Himanshi Arora and N. Neetu Mittal Amity University Uttar Pradesh, “Image Enhancement Techniques for Gastric Diseases Detection using Ultrasound Images,” in Third International Conference on Electronics Communication and Aerospace Technology [ICECA 2019], IEEE, 2019, pp. 251–256.
J. Glory Precious and Shirley Selvan, “Detection of Abnormalities in Ultrasound Images Using Texture and Shape Features,” in IEEE International Conference on Current Trends toward Converging Technologies, IEEE, 2018, pp. 1–6.
R. Buettner, M. Bilo, N. Bay, and T. Zubac, “A Systematic Literature Review of Medical Image Analysis Using Deep Learning,” in IEEE Symposium on Industrial Electronics & Applications (ISIEA), 2020.
U. R. Acharya et al., “A Novel Algorithm for Breast Lesion Detection Using Textons and Local Configuration Pattern Features with Ultrasound Imagery,” IEEE Access, vol. 7, pp. 22829–22842, 2019, doi: 10.1109/ACCESS.2019.2898121.
Y. Wang, X. Ge, H. Ma, S. Qi, G. Zhang, and Y. Yao, “Deep Learning in Medical Ultrasound Image Analysis: A Review,” IEEE Access, vol. 9, pp. 54310–54324, 2021, doi: 10.1109/ACCESS.2021.3071301.
H. Yang, X. Sun, Y. Sun, L. Cui, and B. Li, “Ultrasound Image-Based Diagnosis of Cirrhosis with an End-to-End Deep Learning model,” in Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020, Institute of Electrical and Electronics Engineers Inc., Dec. 2020, pp. 1193–1196. doi: 10.1109/BIBM49941.2020.9313579.
Y. Mao, W. Lu, Y. Li, and Y. Wang, “Enhancing Ultrasound Imaging with Synthetic Aperture Data: A Deep Learning Approach for Superior Resolution and Contrast,” in Proceedings - International Symposium on Biomedical Imaging, IEEE Computer Society, 2024. doi: 10.1109/ISBI56570.2024.10635178.
J. M. Urman et al., “Pilot multi-omic analysis of human bile from benign and malignant biliary strictures: A machine-learning approach,” Cancers (Basel)., vol. 12, no. 6, pp. 1–30, Jun. 2020, doi: 10.3390/cancers12061644.
C. Yao, S. Wu, Z. Liu, and P. Li, “A deep learning model for predicting chemical composition of gallstones with big data in medical Internet of Things,” Future Generation Computer Systems, vol. 94, pp. 140–147, May 2019, doi: 10.1016/j.future.2018.11.011.
Y. Chang, Q. Wu, L. Chi, H. Huo, and Q. Li, “Adoption of combined detection technology of tumor markers via deep learning algorithm in diagnosis and prognosis of gallbladder carcinoma,” Journal of Supercomputing, vol. 78, no. 3, pp. 3955–3975, Feb. 2022, doi: 10.1007/s11227-021-03843-z.
W. Zhou et al., “Ensembled deep learning model outperforms human experts in diagnosing biliary atresia from sonographic gallbladder images,” Nat. Commun., vol. 12, no. 1, Dec. 2021, doi: 10.1038/s41467-021-21466-z.
A. M. Obaid, A. Turki, H. Bellaaj, and M. Ksontini, “Detection of Biliary Artesia using Sonographic Gallbladder Images with the help of Deep Learning approaches,” in 2022 8th International Conference on Control, Decision and Information Technologies, CoDIT 2022, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 705–711. doi: 10.1109/CoDIT55151.2022.9804084.
Y. Cao, J. Lian, B. Shi, and X. Yang, “A gallbladder segmentation method of a CFC-MSPCNN in ultrasound image,” in Proceedings of 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 312–319. doi: 10.1109/ICIBA56860.2023.10165027.
S. Basu, M. Gupta, C. Madan, P. Gupta, and C. Arora, “FocusMAE: Gallbladder Cancer Detection from Ultrasound Videos with Focused Masked Autoencoders,” in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2024, pp. 11715–11725. doi: 10.1109/CVPR52733.2024.01113.
S. Dadjouy and H. Sajedi, “Gallbladder Cancer Detection in Ultrasound Images based on YOLO and Faster R-CNN,” in 2024 10th International Conference on Artificial Intelligence and Robotics, QICAR 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 227–231. doi: 10.1109/QICAR61538.2024.10496645.
T. Kim, Y. H. Choi, J. H. Choi, S. H. Lee, S. Lee, and I. S. Lee, “Gallbladder polyp classification in ultrasound images using an ensemble convolutional neural network model,” J. Clin. Med., vol. 10, no. 16, Aug. 2021, doi: 10.3390/jcm10163585.
S. Basu, M. Gupta, P. Rana, P. Gupta, and C. Arora, “Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, 2022, pp. 20854–20864. doi: 10.1109/CVPR52688.2022.02022.
A. Turki, A. M. Obaid, H. Bellaaj, M. Ksantini, and A. AlTaee, “UIdataGB: Multi-Class ultrasound images dataset for gallbladder disease detection,” Data Brief, vol. 54, Jun. 2024, doi: 10.1016/j.dib.2024.110426.
A. M. Obaid, A. Turki, H. Bellaaj, M. Ksantini, A. AlTaee, and A. Alaerjan, “Detection of Gallbladder Disease Types Using Deep Learning: An Informative Medical Method,” Diagnostics, vol. 13, no. 10, May 2023, doi: 10.3390/diagnostics13101744.
DOI: https://doi.org/10.47738/jads.v7i3.1268
Refbacks
- There are currently no refbacks.
Journal of Applied Data Sciences
| ISSN | : | 2723-6471 (Online) |
| Publisher | : | Bright Publisher |
| Website | : | http://bright-journal.org/JADS |
| : | taqwa@amikompurwokerto.ac.id (principal contact) | |
| support@bright-journal.org (technical issues) |
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0