Detection-Guided Lumbar Spine Degeneration Classification Using Multi-Slice Encoded MRI

Samiul Karim Mazumder; Riyadul Islam; Siam Tahsin Bhuiyan; Rashedur Rahman; Sefatul Wasi; Ashraful Islam; Saadia Binte Alam

doi:10.1109/icmlc66258.2025.11280017

Conference Paper2025Cited by 2

Detection-Guided Lumbar Spine Degeneration Classification Using Multi-Slice Encoded MRI

Samiul Karim Mazumder, Riyadul Islam, Siam Tahsin Bhuiyan, Rashedur Rahman, Sefatul Wasi, Ashraful Islam, Saadia Binte Alam

2025 International Conference on Machine Learning and Cybernetics (ICMLC)

In: 2025 International Conference on Machine Learning and Cybernetics (ICMLC)

IEEE, pp. 75-80

DOI: 10.1109/icmlc66258.2025.11280017 URL

Abstract

Lumbar Spine Degeneration Classification (LSDC) poses significant diagnostic challenges as radiologists manually assess each MRI scan which is time-consuming, subjective, and prone to inter-observer variability. This highlights the need for an automated, objective, and efficient diagnostic solution to assist radiologists. Current deep learning-based approaches rely on single-slice MRI scans, which lack contextual spatial information. To address these challenges, we propose a Detection-Guided Classification Framework that integrates automated region detection with deep learning-based severity classification. Our approach introduces a novel RGB-based pre-processing technique that encodes multi-slice Sagittal T2-weighted MRI information into a single image. We first detect the degenerative regions to ensure that the classification models focus on the relevant areas. We then train multiple Convolutional Neural Network models to classify degeneration severity. Using the RSNA dataset, the YOLOv8 detection model achieves a mAP50 score of 0.9905. In the classification models, ResNet152 scores the highest accuracy of 92.74%, and EfficientNetB5 achieves the highest accuracy of 88.18% in the holdout test. Our result suggests that using the multi-slice encoded MRI dataset, the proposed detection-guided classification framework effectively localizes degenerative regions and achieves high classification accuracy by focusing on relevant areas rather than processing entire MRI slices.

Keywords

Convolutional neural networkFocus (optics)Sagittal planePattern recognition (psychology)Deep learningLumbar spineMagnetic resonance imagingLumbar

CCDS Authors

Samiul Karim Mazumder

Intern, CCDS

Riyadul Islam

Intern, CCDS

Bachelors

Daffodil International University

Siam Tahsin Bhuiyan

Intern, CCDS

Bachelors

Independent University, Bangladesh

Md. Rashedur Rahman, D. Eng.

Co-Director, MIRA & NEST Wings

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

Ashraful Islam, PhD

Center Director, CCDS
Director, HCI Wing

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh (IUB)

Research Interests

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

Saadia Binte Alam, PhD

Director, MIRA & WiSE Wings

Associate Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

References

1.Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. (2016). Deep Residual Learning for Image Recognition. , 770–778[10.1109/cvpr.2016.90]
2.Gao Huang, Zhuang Liu, Laurens Van Der Maaten, Kilian Q. Weinberger. (2017). Densely Connected Convolutional Networks. , 2261–2269[10.1109/cvpr.2017.243]
3.Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. , 4510–4520[10.1109/cvpr.2018.00474]
4.Theo Vos, Stephen S Lim, Cristiana Abbafati, Kaja M Abbas, Mohammad Abbasi, Mitra Abbasifard, Mohsen Abbasi-Kangevari, Hedayat Abbastabar, Foad Abd-Allah, Ahmed Abdelalim, Mohammad Abdollahi, Ibrahim Abdollahpour, Hassan Abolhassani, Victor Aboyans, Elissa M Abrams, Lucas Guimarães Abreu, Michael R M Abrigo, Laith Jamal Abu-Raddad, Abdelrahman I Abushouk, Alyssa Acebedo, Ilana N Ackerman, Maryam Adabi, Abdu A Adamu, Oladimeji M Adebayo, Victor Adekanmbi, Jaimie D Adelson, Olatunji O Adetokunboh, Davoud Adham, Mahdi Afshari, Ashkan Afshin, Emilie E Agardh, Gina Agarwal, Kareha M Agesa, Mohammad Aghaali, Seyed Mohammad Kazem Aghamir, Anurag Agrawal, Tauseef Ahmad, Alireza Ahmadi, Mehdi Ahmadi, Hamid Ahmadieh, Ehsan Ahmadpour, Temesgen Yihunie Akalu, Rufus Olusola Akinyemi, Tomi Akinyemiju, Blessing Akombi, Ziyad Al-Aly, Khurshid Alam, Noore Alam, Samiah Alam, Tahiya Alam, Turki M Alanzi, Samuel B Albertson, Jacqueline Elizabeth Alcalde-Rabanal, Niguse Meles Alema, Muhammad Ali, Saqib Ali, Gianfranco Alicandro, Mehran Alijanzadeh, Cyrus Alinia, Vahid Alipour, Syed Mohamed Aljunid, François Alla, Peter Allebeck, Amir Almasi-Hashiani, Jordi Alonso, Rajaa M Al-Raddadi, Khalid A Altirkawi, Nelson Alvis-Guzman, Nelson J Alvis-Zakzuk, Saeed Amini, Mostafa Amini-Rarani, Arya Aminorroaya, Fatemeh Amiri, Arianna Maever L Amit, Dickson A Amugsi, Gianna Gayle Herrera Amul, Deanna Anderlini, Catalina Liliana Andrei, Tudorel Andrei, Mina Anjomshoa, Fereshteh Ansari, Iman Ansari, Alireza Ansari-Moghaddam, Carl Abelardo T Antonio, Catherine M Antony, Ernoiz Antriyandarti, Davood Anvari, Razique Anwer, Jalal Arabloo, Morteza Arab-Zozani, Aleksandr Y Aravkin, Filippo Ariani, Johan Ärnlöv, Krishna K Aryal, Afsaneh Arzani, Mehran Asadi-Aliabadi, Ali A Asadi-Pooya, Babak Asghari, Charlie Ashbaugh, Desta Debalkie Atnafu. (2020). Global burden of 369 diseases and injuries in 204 countries and territories, 1990–2019: a systematic analysis for the Global Burden of Disease Study 2019. The Lancet, 396(10258), 1204–1222[10.1016/s0140-6736(20)30925-9]
5.Geert Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen A.W.M. van der Laak, Bram van Ginneken, Clara I. Sánchez. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60–88[10.1016/j.media.2017.07.005]
6.Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra. (2019). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. International Journal of Computer Vision, 128(2), 336–359[10.1007/s11263-019-01228-7]
7.Christian W. A. Pfirrmann, Alexander Metzdorf, Marco Zanetti, Juerg Hodler, Norbert Boos. (2001). Magnetic Resonance Classification of Lumbar Intervertebral Disc Degeneration. Spine, 26(17), 1873–1878[10.1097/00007632-200109010-00011]
8.Rejin Varghese, Sambath M.. (2024). YOLOv8: A Novel Object Detection Algorithm with Enhanced Performance and Robustness. , 1–6[10.1109/adics58448.2024.10533619]
9.GARY SCHNEIDERMAN, BONNIE FLANNIGAN, SCOTT KINGSTON, JAMES THOMAS, WILLIAM H. DILLIN, ROBERT G. WATKINS. (1987). Magnetic Resonance Imaging in the Diagnosis of Disc Degeneration. Spine, 12(3), 276–281[10.1097/00007632-198704000-00016]
10.Tyler J. Bradshaw, Zachary Huemann, Junjie Hu, Arman Rahmim. (2023). A Guide to Cross-Validation for Artificial Intelligence in Medical Imaging. Radiology Artificial Intelligence, 5(4), e220232[10.1148/ryai.220232]
11.Amir Jamaludin, Meelis Lootus, Timor Kadir, Andrew Zisserman, Jill Urban, Michele C. Battié, Jeremy Fairbank, Iain McCall. (2017). ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist. European Spine Journal, 26(5), 1374–1383[10.1007/s00586-017-4956-3]
12.Dean Chou, Dino Samartzis, Carlo Bellabarba, Alpesh Patel, Keith D. K. Luk, Jeannette M. Schenk Kisser, Andrea C. Skelly. (2011). Degenerative Magnetic Resonance Imaging Changes in Patients With Chronic Low Back Pain. Spine, 36(21 Suppl), S43–S53[10.1097/brs.0b013e31822ef700]
13.Merel Wassenaar, Rogier M. van Rijn, Maurits W. van Tulder, Arianne P. Verhagen, Danielle A. W. M. van der Windt, Bart W. Koes, Michiel R. de Boer, Abida Z. Ginai, Raymond W. J. G. Ostelo. (2011). Magnetic resonance imaging for diagnosing lumbar spinal pathology in adult patients with low back pain or sciatica: a diagnostic systematic review. European Spine Journal, 21(2), 220–227[10.1007/s00586-011-2019-8]
14.Atsuya Watanabe, Lorin M. Benneker, Chris Boesch, Tomoko Watanabe, Takayuki Obata, Suzanne E. Anderson. (2007). Classification of Intervertebral Disk Degeneration with Axial T2 Mapping. American Journal of Roentgenology, 189(4), 936–942[10.2214/ajr.07.2142]
15.Wafa Mbarki, Moez Bouchouicha, Sebastien Frizzi, Frederick Tshibasu, Leila Ben Farhat, Mounir Sayadi. (2020). Lumbar spine discs classification based on deep convolutional neural networks using axial view MRI. Interdisciplinary Neurosurgery, 22, 100837[10.1016/j.inat.2020.100837]
16.Wongthawat Liawrungrueang, Pyeoungkee Kim, Vit Kotheeranurak, Khanathip Jitpakdee, Peem Sarasombath. (2023). Automatic Detection, Classification, and Grading of Lumbar Intervertebral Disc Degeneration Using an Artificial Neural Network Model. Diagnostics, 13(4), 663[10.3390/diagnostics13040663]
17.MINNA TERTTI, HANNU PAAJANEN, MATTI LAATO, HEIKKI AHO, MARKKU KOMU, MARTTI KORMANO. (1991). Disc Degeneration in Magnetic Resonance Imaging. Spine, 16(6), 629–634[10.1097/00007632-199106000-00006]
18.R. Gunzburg, R. Parkinson, R. Moore, F. Cantraine, W. Hutton, B. Vernon-Roberts, R. Fraser. (1992). A Cadaveric Study Comparing Discography, Magnetic Resonance Imaging, Histology, and Mechanical Behavior of the Human Lumbar Disc. Spine, 17(4), 417–426[10.1097/00007632-199204000-00007]
19.Bahman Roudsari, Jeffrey G. Jarvik. (2010). Lumbar Spine MRI for Low Back Pain: Indications and Yield. American Journal of Roentgenology, 195(3), 550–559[10.2214/ajr.10.4367]
20.Nico Sollmann, Sebastian Mönch, Isabelle Riederer, Claus Zimmer, Thomas Baum, Jan S. Kirschke. (2020). Imaging of the degenerative spine using a sagittal T2-weighted DIXON turbo spin-echo sequence. European Journal of Radiology, 131, 109204[10.1016/j.ejrad.2020.109204]

Cited By

1.Sayeda Subha Ashrafi, Tushar Ahmed Shishir. (2026). Deep Learning-Based Automated Breast Cancer Detection from Histopathology Images: Benchmarking CNN and Transformer Architectures. , 1–6[10.1109/peccii70991.2026.11662018]
2.Rani Puspita, Thoyyibah T. (2025). Impact of Model Architecture and Optimizer on MRI-Based Detection of Alzheimer’s Disease: EfficientNetB1, EfficientNetB5, and NASNet-Large. , 596–601[10.1109/icsintesa68165.2025.11413624]

← All publications

Abstract

CCDS Authors

Samiul Karim Mazumder

Intern, CCDS

Riyadul Islam

Intern, CCDS

Bachelors

Daffodil International University

Siam Tahsin Bhuiyan

Intern, CCDS

Bachelors

Independent University, Bangladesh

Md. Rashedur Rahman, D. Eng.

Co-Director, MIRA & NEST Wings

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

Ashraful Islam, PhD

Center Director, CCDS
Director, HCI Wing

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh (IUB)

Research Interests

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

Saadia Binte Alam, PhD

Director, MIRA & WiSE Wings

Associate Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

References

1.Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. (2016). Deep Residual Learning for Image Recognition. , 770–778[10.1109/cvpr.2016.90]

2.Gao Huang, Zhuang Liu, Laurens Van Der Maaten, Kilian Q. Weinberger. (2017). Densely Connected Convolutional Networks. , 2261–2269[10.1109/cvpr.2017.243]

3.Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. , 4510–4520[10.1109/cvpr.2018.00474]

4.Theo Vos, Stephen S Lim, Cristiana Abbafati, Kaja M Abbas, Mohammad Abbasi, Mitra Abbasifard, Mohsen Abbasi-Kangevari, Hedayat Abbastabar, Foad Abd-Allah, Ahmed Abdelalim, Mohammad Abdollahi, Ibrahim Abdollahpour, Hassan Abolhassani, Victor Aboyans, Elissa M Abrams, Lucas Guimarães Abreu, Michael R M Abrigo, Laith Jamal Abu-Raddad, Abdelrahman I Abushouk, Alyssa Acebedo, Ilana N Ackerman, Maryam Adabi, Abdu A Adamu, Oladimeji M Adebayo, Victor Adekanmbi, Jaimie D Adelson, Olatunji O Adetokunboh, Davoud Adham, Mahdi Afshari, Ashkan Afshin, Emilie E Agardh, Gina Agarwal, Kareha M Agesa, Mohammad Aghaali, Seyed Mohammad Kazem Aghamir, Anurag Agrawal, Tauseef Ahmad, Alireza Ahmadi, Mehdi Ahmadi, Hamid Ahmadieh, Ehsan Ahmadpour, Temesgen Yihunie Akalu, Rufus Olusola Akinyemi, Tomi Akinyemiju, Blessing Akombi, Ziyad Al-Aly, Khurshid Alam, Noore Alam, Samiah Alam, Tahiya Alam, Turki M Alanzi, Samuel B Albertson, Jacqueline Elizabeth Alcalde-Rabanal, Niguse Meles Alema, Muhammad Ali, Saqib Ali, Gianfranco Alicandro, Mehran Alijanzadeh, Cyrus Alinia, Vahid Alipour, Syed Mohamed Aljunid, François Alla, Peter Allebeck, Amir Almasi-Hashiani, Jordi Alonso, Rajaa M Al-Raddadi, Khalid A Altirkawi, Nelson Alvis-Guzman, Nelson J Alvis-Zakzuk, Saeed Amini, Mostafa Amini-Rarani, Arya Aminorroaya, Fatemeh Amiri, Arianna Maever L Amit, Dickson A Amugsi, Gianna Gayle Herrera Amul, Deanna Anderlini, Catalina Liliana Andrei, Tudorel Andrei, Mina Anjomshoa, Fereshteh Ansari, Iman Ansari, Alireza Ansari-Moghaddam, Carl Abelardo T Antonio, Catherine M Antony, Ernoiz Antriyandarti, Davood Anvari, Razique Anwer, Jalal Arabloo, Morteza Arab-Zozani, Aleksandr Y Aravkin, Filippo Ariani, Johan Ärnlöv, Krishna K Aryal, Afsaneh Arzani, Mehran Asadi-Aliabadi, Ali A Asadi-Pooya, Babak Asghari, Charlie Ashbaugh, Desta Debalkie Atnafu. (2020). Global burden of 369 diseases and injuries in 204 countries and territories, 1990–2019: a systematic analysis for the Global Burden of Disease Study 2019. The Lancet, 396(10258), 1204–1222[10.1016/s0140-6736(20)30925-9]

5.Geert Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen A.W.M. van der Laak, Bram van Ginneken, Clara I. Sánchez. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60–88[10.1016/j.media.2017.07.005]

6.Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra. (2019). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. International Journal of Computer Vision, 128(2), 336–359[10.1007/s11263-019-01228-7]

7.Christian W. A. Pfirrmann, Alexander Metzdorf, Marco Zanetti, Juerg Hodler, Norbert Boos. (2001). Magnetic Resonance Classification of Lumbar Intervertebral Disc Degeneration. Spine, 26(17), 1873–1878[10.1097/00007632-200109010-00011]

8.Rejin Varghese, Sambath M.. (2024). YOLOv8: A Novel Object Detection Algorithm with Enhanced Performance and Robustness. , 1–6[10.1109/adics58448.2024.10533619]

9.GARY SCHNEIDERMAN, BONNIE FLANNIGAN, SCOTT KINGSTON, JAMES THOMAS, WILLIAM H. DILLIN, ROBERT G. WATKINS. (1987). Magnetic Resonance Imaging in the Diagnosis of Disc Degeneration. Spine, 12(3), 276–281[10.1097/00007632-198704000-00016]

10.Tyler J. Bradshaw, Zachary Huemann, Junjie Hu, Arman Rahmim. (2023). A Guide to Cross-Validation for Artificial Intelligence in Medical Imaging. Radiology Artificial Intelligence, 5(4), e220232[10.1148/ryai.220232]

11.Amir Jamaludin, Meelis Lootus, Timor Kadir, Andrew Zisserman, Jill Urban, Michele C. Battié, Jeremy Fairbank, Iain McCall. (2017). ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist. European Spine Journal, 26(5), 1374–1383[10.1007/s00586-017-4956-3]

12.Dean Chou, Dino Samartzis, Carlo Bellabarba, Alpesh Patel, Keith D. K. Luk, Jeannette M. Schenk Kisser, Andrea C. Skelly. (2011). Degenerative Magnetic Resonance Imaging Changes in Patients With Chronic Low Back Pain. Spine, 36(21 Suppl), S43–S53[10.1097/brs.0b013e31822ef700]

13.Merel Wassenaar, Rogier M. van Rijn, Maurits W. van Tulder, Arianne P. Verhagen, Danielle A. W. M. van der Windt, Bart W. Koes, Michiel R. de Boer, Abida Z. Ginai, Raymond W. J. G. Ostelo. (2011). Magnetic resonance imaging for diagnosing lumbar spinal pathology in adult patients with low back pain or sciatica: a diagnostic systematic review. European Spine Journal, 21(2), 220–227[10.1007/s00586-011-2019-8]

14.Atsuya Watanabe, Lorin M. Benneker, Chris Boesch, Tomoko Watanabe, Takayuki Obata, Suzanne E. Anderson. (2007). Classification of Intervertebral Disk Degeneration with Axial T2 Mapping. American Journal of Roentgenology, 189(4), 936–942[10.2214/ajr.07.2142]

15.Wafa Mbarki, Moez Bouchouicha, Sebastien Frizzi, Frederick Tshibasu, Leila Ben Farhat, Mounir Sayadi. (2020). Lumbar spine discs classification based on deep convolutional neural networks using axial view MRI. Interdisciplinary Neurosurgery, 22, 100837[10.1016/j.inat.2020.100837]

16.Wongthawat Liawrungrueang, Pyeoungkee Kim, Vit Kotheeranurak, Khanathip Jitpakdee, Peem Sarasombath. (2023). Automatic Detection, Classification, and Grading of Lumbar Intervertebral Disc Degeneration Using an Artificial Neural Network Model. Diagnostics, 13(4), 663[10.3390/diagnostics13040663]

17.MINNA TERTTI, HANNU PAAJANEN, MATTI LAATO, HEIKKI AHO, MARKKU KOMU, MARTTI KORMANO. (1991). Disc Degeneration in Magnetic Resonance Imaging. Spine, 16(6), 629–634[10.1097/00007632-199106000-00006]

18.R. Gunzburg, R. Parkinson, R. Moore, F. Cantraine, W. Hutton, B. Vernon-Roberts, R. Fraser. (1992). A Cadaveric Study Comparing Discography, Magnetic Resonance Imaging, Histology, and Mechanical Behavior of the Human Lumbar Disc. Spine, 17(4), 417–426[10.1097/00007632-199204000-00007]

19.Bahman Roudsari, Jeffrey G. Jarvik. (2010). Lumbar Spine MRI for Low Back Pain: Indications and Yield. American Journal of Roentgenology, 195(3), 550–559[10.2214/ajr.10.4367]

20.Nico Sollmann, Sebastian Mönch, Isabelle Riederer, Claus Zimmer, Thomas Baum, Jan S. Kirschke. (2020). Imaging of the degenerative spine using a sagittal T2-weighted DIXON turbo spin-echo sequence. European Journal of Radiology, 131, 109204[10.1016/j.ejrad.2020.109204]

Cited By

1.Sayeda Subha Ashrafi, Tushar Ahmed Shishir. (2026). Deep Learning-Based Automated Breast Cancer Detection from Histopathology Images: Benchmarking CNN and Transformer Architectures. , 1–6[10.1109/peccii70991.2026.11662018]

2.Rani Puspita, Thoyyibah T. (2025). Impact of Model Architecture and Optimizer on MRI-Based Detection of Alzheimer’s Disease: EfficientNetB1, EfficientNetB5, and NASNet-Large. , 596–601[10.1109/icsintesa68165.2025.11413624]