Conference Paper2025

Preprocessing Matters: Benchmarking Image Enhancement Techniques for Pelvic Fracture Detection

Siam Tahsin Bhuiyan, Rubaya Khatun, Samiul Karim Mazumder, Fatin Israq, Sefatul Wasi, Rashedur Rahman, Ashraful Islam, Saadia Binte Alam

2025 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE)

IEEE, pp. 379-384

  • Good Health and Well-being — Relevance: 93%
DOI: 10.1109/wiecon-ece69386.2025.11525920URL

Abstract

Pelvic fractures are often first assessed via radiograph. Yet low contrast and subtle fracture lines in radiographs contribute to missed diagnoses in up to 22% of trauma cases, while 51% of the patients remain underdiagnosed. In this study, we investigate the effects of five image preprocessing techniques, Histogram Equalization (HE), Gamma Correction, Contrast-Limited Adaptive HE (CLAHE), Image Complement, and Balance-Contrast Enhancement Technique (BCET), on the binary classification (normal vs fractured) performance of a ResNet50 convolutional neural network using the PXR150 dataset. Each preprocessing method was applied independently to create five enhanced datasets alongside the original set. Both the original and the five preprocessed datasets were trained and tested on the ResNet50 model using a 5-fold cross-validation technique. Performance metrics, including accuracy, specificity, recall, and AUROC, were computed and averaged across folds. Compared to the original baseline accuracy of 77.33% and AUROC of 0.7790, CLAHE and Gamma Correction achieved the highest accuracy of 80.67% and AUROC of 0.8140 and 0.8160. BCET also improved performance (accuracy 80.00%, AUROC of 0.8090). These findings demonstrate that localized and nonlinear contrast enhancements improve CNN-based pelvic fracture detection, underscoring the importance of tailored preprocessing in medical imaging workflows.

Keywords

  • gamma correction
  • CLAHE
  • ResNet50
  • image preprocessing
  • histogram equalization
  • low-contrast medical images
  • Binary classification

CCDS Authors

Siam Tahsin Bhuiyan
Siam Tahsin Bhuiyan

Siam Tahsin Bhuiyan

  • Intern, CCDS

Bachelors

Independent University, Bangladesh

Published at

Scientific Reports

Md. Rashedur Rahman, D. Eng.
Md. Rashedur Rahman, D. Eng.

Md. Rashedur Rahman, D. Eng.

  • Co-Director, MIRA & NEST Wings

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

Published at

CHI, HCII, Scientific Reports, Cognitive Computation, Neural Computing and Applications

Ashraful Islam, PhD
Ashraful Islam

Ashraful Islam, PhD

  • Center Director, CCDS
  • Director, HCI Wing

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh (IUB)

Published at

CHI, UIST, UbiComp, IJCNN, ICIP, HCII, ICDMW, BLP, IEEE Internet of Things Journal, JMIR, JMIR Human Factors, JMIR Formative Research, IEEE Access, Smart Agricultural Technology, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Human-Computer Interaction, AI for Social Good, AI for Public Health, AI for Impact

Saadia Binte Alam, PhD
Saadia Binte Alam, PhD

Saadia Binte Alam, PhD

  • Director, MIRA & WiSE Wings

Associate Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

Published at

HCII, Scientific Reports, Cognitive Computation, Neural Computing and Applications

References

  1. 1.Tzu-Tsung Wong. (2015). Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recognition, 48(9), 2839–2846[10.1016/j.patcog.2015.03.009]
  2. 2.Oliver Hauschild, Peter C. Strohm, Ulf Culemann, Tim Pohlemann, Norbert P. Suedkamp, Wolfgang Koestler, Hagen Schmal. (2008). Mortality in Patients With Pelvic Fractures: Results From the German Pelvic Injury Register. The Journal of Trauma: Injury, Infection, and Critical Care, 64(2), 449–455[10.1097/ta.0b013e31815982b1]
  3. 3.Bhawna Goyal, Ayush Dogra, Sunil Agrawal, B.S. Sohi. (2018). Noise Issues Prevailing in Various Types of Medical Images. Biomedical & Pharmacology Journal, 11(3), 1227–1237[10.13005/bpj/1484]
  4. 4.Wan Azani Mustafa, Mohamed Mydin M. Abdul Kader. (2018). A Review of Histogram Equalization Techniques in Image Enhancement Application. Journal of Physics Conference Series, 1019, 012026[10.1088/1742-6596/1019/1/012026]
  5. 5.Chi-Tung Cheng, Yirui Wang, Huan-Wu Chen, Po-Meng Hsiao, Chun-Nan Yeh, Chi-Hsun Hsieh, Shun Miao, Jing Xiao, Chien-Hung Liao, Le Lu. (2021). A scalable physician-level deep learning algorithm detects universal trauma on pelvic radiographs. Nature Communications, 12(1), 1066[10.1038/s41467-021-21311-3]
  6. 6.Agata Giełczyk, Anna Marciniak, Martyna Tarczewska, Zbigniew Lutowski. (2022). Pre-processing methods in chest X-ray image classification. PLoS ONE, 17(4), e0265949[10.1371/journal.pone.0265949]
  7. 7.Mayank Tiwari, Bhupendra Gupta. (2016). Brightness preserving contrast enhancement of medical images using adaptive gamma correction and homomorphic filtering. , 1–4[10.1109/sceecs.2016.7509287]
  8. 8.Myoung Jun Kim, Jae Gil Lee, Seung Hwan Lee. (2018). Factors predicting the need for hemorrhage control intervention in patients with blunt pelvic trauma: a retrospective study. BMC Surgery, 18(1), 101[10.1186/s12893-018-0438-8]
  9. 9.Rashedur Rahman, Naomi Yagi, Keigo Hayashi, Akihiro Maruo, Hirotsugu Muratsu, Syoji Kobashi. (2024). Enhancing fracture diagnosis in pelvic X-rays by deep convolutional neural network with synthesized images from 3D-CT. Scientific Reports, 14(1), 8004[10.1038/s41598-024-58810-4]
  10. 10.Jung Min Lee, Jun Young Park, Young Jae Kim, Kwang Gi Kim. (2024). Deep-learning-based pelvic automatic segmentation in pelvic fractures. Scientific Reports, 14(1), 12258[10.1038/s41598-024-63093-w]
  11. 11.Jiwon Han, Byungmin Choi, Jae Young Kim, Yeonjoon Lee. (2025). BO-CLAHE enhancing neonatal chest X-ray image quality for improved lesion classification. Scientific Reports, 15(1), 4931[10.1038/s41598-025-88451-0]
  12. 12.Amal Kamil Obaid, Andrew Barleben, Diana Porral, Stephanie Lush, Marianne Cinat. (2006). Utility of Plain Film Pelvic Radiographs in Blunt Trauma Patients in the Emergency Department. The American Surgeon, 72(10), 951–954[10.1177/000313480607201025]
  13. 13.Dominik Weishaupt, Ana M. Grozaj, Jürgen K. Willmann, Justus E. Roos, Paul R. Hilfiker, Borut Marincek. (2002). Traumatic injuries: imaging of abdominal and pelvic injuries. European Radiology, 12(6), 1295–1311[10.1007/s00330-002-1462-7]
  14. 14.Ma Guadalupe Sanchez, V. Vidal, G. Verdu, P. Mayo, F. Rodenas. (2012). Medical image restoration with different types of noise. , 2012, 4382–4385[10.1109/embc.2012.6346937]
  15. 15.Yuntong Ma, Jacob C. Mandell, Tatiana Rocha, Maria ADuran Mendicuti, Michael J. Weaver, Bharti Khurana. (2022). Diagnostic accuracy of pelvic radiographs for the detection of traumatic pelvic fractures in the elderly. Emergency Radiology, 29(6), 1009–1018[10.1007/s10140-022-02090-w]
  16. 16.Avinash M. Pawar, Nitin Sherje. (2023). Deep Learning for Medical Image Analysis: Challenges and Opportunities. International Journal Of Recent Advances in Engineering & Technology, 12(1), 16–23[10.65521/intjournalrecadvengtech.v12i1.118]
  17. 17.Hakan Dalkıç. (2025). A Contrast Enhancement Approach for Improving Analysis in X-Ray Container Scan Images. Preprints.org[10.20944/preprints202504.0601.v1]
← All publications