Enhancing Multi-Label Chest X-Ray Classification Using an Improved Ranking Loss
Abstract
1. Introduction
- The focal ZLPR (FZLPR) loss function is proposed by modifying the ZLPR loss function and incorporates a temperature parameter to effectively handle hard examples during training.
- Our experimental results demonstrate that the FZLPR loss function is effective in classifying thoracic diseases in CXR images. It outperforms the BCE loss and focal loss in terms of average AUC.
- By utilizing test-time augmentations, our model trained with the FZLPR loss achieves an average AUC of 80.96%, which is comparable to that of state-of-the-art methods.
2. Literature Review
2.1. Multi-Label Classification for CXR Images
2.2. Loss Functions for Class Imbalance
3. Materials and Methods
3.1. Focal ZLPR Loss
- When the positive instance is correctly classified with high probability i.e., the label score , the weighting by causes its contribution to the loss function to become zero. This means the model does not focus on such instances, as their gradient is zero.
- When the positive instance is correctly classified but with low probability i.e., the label score , the weighting by ensures that its contribution is included in the loss function and its gradient flows during training.
- When the positive instance is incorrectly classified i.e., the label score , , the weighting by significantly increases its contribution to the loss function, ensuring that the model focuses on such instances and allowing a substantial gradient flow during training.
3.2. Transfer Learning
4. Experimental Results
4.1. Chest X-Ray Dataset and Evaluation Metric
4.2. Training Methodology and Implementation Details
4.3. Results and Discussion
4.4. Ablation Study
4.5. Comparison with Existing Methods
4.6. Qualitative Results
5. Conclusions and Future Works
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Li, J.; Jiang, P.; An, Q.; Wang, G.G.; Kong, H.F. Medical image identification methods: A review. Comput. Biol. Med. 2024, 169, 107777. [Google Scholar] [CrossRef]
- Wang, J.; Wang, S.; Zhang, Y. Deep learning on medical image analysis. CAAI Trans. Intell. Technol. 2025, 10, 1–35. [Google Scholar] [CrossRef]
- Zhang, S.; Metaxas, D. On the challenges and perspectives of foundation models for medical image analysis. Med. Image Anal. 2024, 91, 102996. [Google Scholar] [CrossRef] [PubMed]
- Wang, X.; Peng, Y.; Lu, L.; Lu, Z.; Bagheri, M.; Summers, R.M. Chest X-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 2097–2106. [Google Scholar]
- Katona, T.; Tóth, G.; Petró, M.; Harangi, B. Advanced Multi-Label Image Classification Techniques Using Ensemble Methods. Mach. Learn. Knowl. Extr. 2024, 6, 1281–1297. [Google Scholar] [CrossRef]
- Nguyen-Mau, T.H.; Huynh, T.L.; Le, T.D.; Nguyen, H.D.; Tran, M.T. Advanced augmentation and ensemble approaches for classifying long-tailed multi-label chest x-rays. In Proceedings of the IEEE International Conference on Computer Vision, Paris, France, 2–6 October 2023; pp. 2729–2738. [Google Scholar]
- Johnson, A.E.; Pollard, T.J.; Berkowitz, S.J.; Greenbaum, N.R.; Lungren, M.P.; Deng, C.Y.; Mark, R.G.; Horng, S. MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 2019, 6, 317. [Google Scholar] [CrossRef] [PubMed]
- CXR-LT: Multi-Label Long-Tailed Classification on Chest X-Rays. Available online: https://physionet.org/content/cxr-lt-iccv-workshop-cvamd/1.0.0/ (accessed on 1 March 2025).
- Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M.; et al. Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 2015, 115, 211–252. [Google Scholar] [CrossRef]
- Ridnik, T.; Ben-Baruch, E.; Noy, A.; Zelnik-Manor, L. ImageNet-21K Pretraining for the Masses. In Proceedings of the Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1), Virtual Conference, 6–14 December 2021. [Google Scholar]
- Lin, T.Y.; Goyal, P.; Girshick, R.; He, K.; Dollár, P. Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 2980–2988. [Google Scholar]
- Chai, J.C.L.; Ng, T.S.; Low, C.Y.; Park, J.; Teoh, A.B.J. Recognizability embedding enhancement for very low-resolution face recognition and quality estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada, 18–22 June 2023; pp. 9957–9967. [Google Scholar]
- Liu, G.H.; Li, Z.Y.; Yang, J.Y.; Zhang, D. Exploiting sublimated deep features for image retrieval. Pattern Recognit. 2024, 147, 110076. [Google Scholar] [CrossRef]
- Revaud, J.; De Souza, C.; Humenberger, M.; Weinzaepfel, P. R2d2: Reliable and repeatable detector and descriptor. In Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada, 8–14 December 2019; pp. 12414–12424. [Google Scholar]
- Shen, D.; Wu, G.; Suk, H.I. Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 2017, 19, 221–248. [Google Scholar] [CrossRef] [PubMed]
- Shoeibi, A.; Khodatars, M.; Jafari, M.; Ghassemi, N.; Sadeghi, D.; Moridian, P.; Khadem, A.; Alizadehsani, R.; Hussain, S.; Zare, A.; et al. Automated detection and forecasting of COVID-19 using deep learning techniques: A review. Neurocomputing 2024, 577, 127317. [Google Scholar] [CrossRef]
- Kumar, R.; Kumbharkar, P.; Vanam, S.; Sharma, S. Medical images classification using deep learning: A survey. Multimed. Tools Appl. 2024, 83, 19683–19728. [Google Scholar] [CrossRef]
- Irvin, J.; Rajpurkar, P.; Ko, M.; Yu, Y.; Ciurea-Ilcus, S.; Chute, C.; Marklund, H.; Haghgoo, B.; Ball, R.; Shpanskaya, K.; et al. Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA, 27 January–1 February 2019; Volume 33, pp. 590–597. [Google Scholar]
- Nawaz, M.; Nazir, T.; Baili, J.; Khan, M.A.; Kim, Y.J.; Cha, J.H. CXray-EffDet: Chest disease detection and classification from X-ray images using the EfficientDet model. Diagnostics 2023, 13, 248. [Google Scholar] [CrossRef] [PubMed]
- Guan, Q.; Huang, Y. Multi-label Chest X-ray Image Classification via Category-wise Residual Attention Learning. Pattern Recognit. Lett. 2020, 130, 259–266. [Google Scholar] [CrossRef]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep Residual Learning for Image Recognition. In Proceedings of the Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 26 June–1 July 2016; pp. 770–778. [Google Scholar]
- Huang, G.; Liu, Z.; Weinberger, K.Q. Densely Connected Convolutional Networks. In Proceedings of the Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017; pp. 4700–4708. [Google Scholar]
- Tan, M.; Le, Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In Proceedings of the International Conference on Machine Learning, PMLR, Long Beach, CA, USA, 9–15 June 2019; pp. 6105–6114. [Google Scholar]
- Howard, A.; Sandler, M.; Chu, G.; Chen, L.C.; Chen, B.; Tan, M.; Wang, W.; Zhu, Y.; Pang, R.; Vasudevan, V.; et al. Searching for mobilenetv3. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea, 27 October–2 November 2019; pp. 1314–1324. [Google Scholar]
- Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going Deeper with Convolutions. In Proceedings of the Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7–12 June 2015; pp. 1–9. [Google Scholar]
- Chollet, F. Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 1251–1258. [Google Scholar]
- Su, J.; Zhu, M.; Murtadha, A.; Pan, S.; Wen, B.; Liu, Y. Zlpr: A novel loss for multi-label classification. arXiv 2022, arXiv:2208.02955. [Google Scholar]
- Kufel, J.; Bielówka, M.; Rojek, M.; Mitręga, A.; Lewandowski, P.; Cebula, M.; Krawczyk, D.; Bielówka, M.; Kondoł, D.; Bargieł-Łączek, K.; et al. Multi-label classification of chest X-ray abnormalities using transfer learning techniques. J. Pers. Med. 2023, 13, 1426. [Google Scholar] [CrossRef] [PubMed]
- Ge, Z.; Mahapatra, D.; Chang, X.; Chen, Z.; Chi, L.; Lu, H. Improving multi-label chest X-ray disease diagnosis by exploiting disease and health labels dependencies. Multimed. Tools Appl. 2020, 79, 14889–14902. [Google Scholar] [CrossRef]
- Baltruschat, I.M.; Nickisch, H.; Grass, M.; Knopp, T.; Saalbach, A. Comparison of deep learning approaches for multi-label chest X-ray classification. Sci. Rep. 2019, 9, 6381. [Google Scholar] [CrossRef] [PubMed]
- Katona, T.; Tóth, G.; Petró, M.; Harangi, B. Developing New Fully Connected Layers for Convolutional Neural Networks with Hyperparameter Optimization for Improved Multi-Label Image Classification. Mathematics 2024, 12, 806. [Google Scholar] [CrossRef]
- Han, Y.; Chen, C.; Tewfik, A.; Glicksberg, B.; Ding, Y.; Peng, Y.; Wang, Z. Knowledge-augmented contrastive learning for abnormality classification and localization in chest X-rays with radiomics using a feedback loop. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA, 4–8 January 2022; pp. 2465–2474. [Google Scholar]
- Guendel, S.; Grbic, S.; Georgescu, B.; Liu, S.; Maier, A.; Comaniciu, D. Learning to recognize abnormalities in chest X-rays with location-aware dense networks. In Proceedings of the 23rd Iberoamerican Congress on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications (CIARP), Madrid, Spain, 19–22 November 2019; pp. 757–765. [Google Scholar]
- Huang, C.; Li, Y.; Loy, C.C.; Tang, X. Learning deep representation for imbalanced classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 26 June–1 July 2016; pp. 5375–5384. [Google Scholar]
- Cui, Y.; Jia, M.; Lin, T.Y.; Song, Y.; Belongie, S. Class-balanced loss based on effective number of samples. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 9268–9277. [Google Scholar]
- Ridnik, T.; Ben-Baruch, E.; Zamir, N.; Noy, A.; Friedman, I.; Protter, M.; Zelnik-Manor, L. Asymmetric loss for multi-label classification. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Virtual Conference, 11–17 October 2021; pp. 82–91. [Google Scholar]
- Bénédict, G.; Koops, H.V.; Odijk, D.; de Rijke, M. sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification. arXiv 2022, arXiv:2108.10566. [Google Scholar]
- Huang, Y.; Qi, J.; Wang, X.; Lin, Z. Asymmetric polynomial loss for multi-label classification. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 4–10 June 2023; pp. 1–5. [Google Scholar]
- Park, W.; Park, I.; Kim, S.; Ryu, J. Robust asymmetric loss for multi-label long-tailed learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Paris, France, 2–6 October 2023; pp. 2711–2720. [Google Scholar]
- Timmermann, C.; Jung, S.; Kim, M.; Lee, W. LM-CLIP: Adapting Positive Asymmetric Loss for Long-Tailed Multi-Label Classification. IEEE Access 2025, 13, 71053–71065. [Google Scholar] [CrossRef]
- Li, Y.; Song, Y.; Luo, J. Improving pairwise ranking for multi-label image classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 3617–3625. [Google Scholar]
- Kim, G.; Im, S.; Oh, H.S. Hierarchy-aware Biased Bound Margin Loss Function for Hierarchical Text Classification. In Proceedings of the Findings of the Association for Computational Linguistics ACL 2024, Bangkok, Thailand, 11–16 August 2024; pp. 7672–7682. [Google Scholar]
- Lin, D.; Peng, T.; Chen, R.; Xie, X.; Qin, X.; Cui, Z. Distributionally Robust Loss for Long-Tailed Multi-label Image Classification. In Proceedings of the European Conference on Computer Vision, Milan, Italy, 29 September–4 October 2024; pp. 417–433. [Google Scholar]
- Kim, D.; Heo, B.; Han, D. DenseNets reloaded: Paradigm shift beyond ResNets and ViTs. In Proceedings of the European Conference on Computer Vision, Milan, Italy, 29 September–4 October 2024; pp. 395–415. [Google Scholar]
- Loshchilov, I.; Hutter, F. Decoupled Weight Decay Regularization. In Proceedings of the International Conference on Learning Representations ICLR, New Orleans, LA, USA, 6–9 May 2019. [Google Scholar]
- Loshchilov, I.; Hutter, R. SGDR: Stochastic Gradient Descent with Warm Restarts. In Proceedings of the International Conference on Learning Representations ICLR, Toulon, France, 24–26 April 2017. [Google Scholar]
- Abadi, M.; Agarwal, A.; Barham, P.; Brevdo, E.; Chen, Z.; Citro, C.; Corrado, G.S.; Davis, A.; Dean, J.; Devin, M.; et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Available online: https://www.tensorflow.org/ (accessed on 20 July 2024).
- Lin, T.Y.; Maire, M.; Belongie, S.; Hays, J.; Perona, P.; Ramanan, D.; Dollár, P.; Zitnick, C.L. Microsoft coco: Common objects in context. In Proceedings of the European Conference on Computer Vision (ECCV), Zurich, Switzerland, 6–12 September 2014; pp. 740–755. [Google Scholar]
- Yang, P.; Sun, X.; Li, W.; Ma, S.; Wu, W.; Wang, H. SGM: Sequence Generation Model for Multi-label Classification. In Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe, NM, USA, 20–26 August 2018; pp. 3915–3926. [Google Scholar]
Loss Function | Validation Set |
---|---|
BCE | 0.8082 |
Focal Loss | 0.8312 |
ZLPR | 0.8238 |
FZLPR () | 0.8344 |
Disease Label | BCE | Focal Loss | ZLPR | FZLPR () |
---|---|---|---|---|
Atelectasis | 0.7716 | 0.7770 | 0.7733 | 0.7729 |
Cardiomegaly | 0.8742 | 0.8834 | 0.8761 | 0.8787 |
Effusion | 0.8270 | 0.8273 | 0.8250 | 0.8266 |
Infiltration | 0.6831 | 0.6765 | 0.6686 | 0.6655 |
Mass | 0.8241 | 0.8246 | 0.8177 | 0.8247 |
Nodule | 0.7697 | 0.7723 | 0.7619 | 0.7582 |
Pneumonia | 0.7042 | 0.7290 | 0.7118 | 0.7158 |
Pneumothorax | 0.8628 | 0.8599 | 0.8593 | 0.8639 |
Consolidation | 0.7458 | 0.7437 | 0.7442 | 0.7447 |
Edema | 0.8414 | 0.8456 | 0.8374 | 0.8403 |
Emphysema | 0.9072 | 0.9112 | 0.9057 | 0.9077 |
Fibrosis | 0.8004 | 0.8083 | 0.8018 | 0.8058 |
Pleural Thickening | 0.7707 | 0.7723 | 0.7666 | 0.7670 |
Hernia | 0.7276 | 0.7740 | 0.7406 | 0.8911 |
Average | 0.7936 | 0.8004 | 0.7921 | 0.8045 |
Disease Label | Test Image | Test Image + HF | Test Image + HF + Z |
---|---|---|---|
Atelectasis | 0.7729 | 0.7754 | 0.7785 |
Cardiomegaly | 0.8787 | 0.8818 | 0.8857 |
Effusion | 0.8266 | 0.8287 | 0.8289 |
Infiltration | 0.6655 | 0.6688 | 0.6848 |
Mass | 0.8247 | 0.8301 | 0.8313 |
Nodule | 0.7582 | 0.7622 | 0.7687 |
Pneumonia | 0.7158 | 0.7160 | 0.7174 |
Pneumothorax | 0.8639 | 0.8677 | 0.8670 |
Consolidation | 0.7447 | 0.7462 | 0.7472 |
Edema | 0.8403 | 0.8428 | 0.8436 |
Emphysema | 0.9077 | 0.9096 | 0.9066 |
Fibrosis | 0.8058 | 0.8101 | 0.8125 |
Pleural Thickening | 0.7670 | 0.7671 | 0.7670 |
Hernia | 0.8911 | 0.8909 | 0.8952 |
Average | 0.8045 | 0.8070 | 0.8096 |
Disease Label | ||||||
---|---|---|---|---|---|---|
Atelectasis | 0.7743 | 0.7729 | 0.7741 | 0.7745 | 0.7728 | 0.7733 |
Cardiomegaly | 0.8748 | 0.8787 | 0.8747 | 0.8708 | 0.8761 | 0.8761 |
Effusion | 0.8250 | 0.8266 | 0.8236 | 0.8265 | 0.8261 | 0.8250 |
Infiltration | 0.6716 | 0.6655 | 0.6624 | 0.6649 | 0.6731 | 0.6686 |
Mass | 0.8169 | 0.8247 | 0.8189 | 0.8182 | 0.8143 | 0.8177 |
Nodule | 0.7540 | 0.7582 | 0.7521 | 0.7546 | 0.7585 | 0.7619 |
Pneumonia | 0.7159 | 0.7158 | 0.7172 | 0.7143 | 0.7146 | 0.7118 |
Pneumothorax | 0.8599 | 0.8639 | 0.8606 | 0.8660 | 0.8601 | 0.8593 |
Consolidation | 0.7360 | 0.7447 | 0.7415 | 0.7446 | 0.7464 | 0.7442 |
Edema | 0.8371 | 0.8403 | 0.8366 | 0.8400 | 0.8364 | 0.8374 |
Emphysema | 0.9065 | 0.9077 | 0.9080 | 0.9074 | 0.9049 | 0.9057 |
Fibrosis | 0.7950 | 0.8058 | 0.8051 | 0.8020 | 0.8042 | 0.8018 |
Pleural Thickening | 0.7567 | 0.7670 | 0.7683 | 0.7642 | 0.7764 | 0.7666 |
Hernia | 0.8848 | 0.8911 | 0.8543 | 0.8246 | 0.7533 | 0.7406 |
Average | 0.8006 | 0.8045 | 0.7998 | 0.7980 | 0.7941 | 0.7921 |
Disease Label | Wang et al. [4] | Gundel et al. [33] | Guan et al. [20] | Baltruschat et al. [30] 1 | Kufel et al. [28] 2 | Kotana et al. [5] 3 | Proposed with TTA | Approach |
---|---|---|---|---|---|---|---|---|
Atelectasis | 0.7003 | 0.7670 | 0.7810 | 0.7630 | 0.8170 | 0.8323 | 0.7785 | −0.0538 |
Cardiomegaly | 0.8100 | 0.8830 | 0.8830 | 0.8750 | 0.9110 | 0.9014 | 0.8857 | −0.0253 |
Effusion | 0.7585 | 0.8280 | 0.8310 | 0.8220 | 0.8790 | 0.8915 | 0.8289 | −0.0626 |
Infiltration | 0.6614 | 0.7090 | 0.6970 | 0.6940 | 0.7160 | 0.6489 | 0.6848 | −0.0312 |
Mass | 0.6933 | 0.8210 | 0.8300 | 0.8200 | 0.8530 | 0.8676 | 0.8313 | −0.0363 |
Nodule | 0.6687 | 0.7580 | 0.7640 | 0.7470 | 0.7710 | 0.7773 | 0.7687 | −0.0086 |
Pneumonia | 0.6580 | 0.7310 | 0.7250 | 0.7140 | 0.7690 | 0.7465 | 0.7174 | −0.0516 |
Pneumothorax | 0.7993 | 0.8460 | 0.8660 | 0.8400 | 0.8980 | 0.8651 | 0.8670 | −0.0310 |
Consolidation | 0.7032 | 0.7450 | 0.7580 | 0.7490 | 0.8150 | 0.8123 | 0.7472 | −0.0678 |
Edema | 0.8052 | 0.8350 | 0.8530 | 0.8460 | 0.9080 | 0.9040 | 0.8436 | −0.0644 |
Emphysema | 0.8330 | 0.8950 | 0.9110 | 0.8950 | 0.9350 | 0.8918 | 0.9066 | −0.0284 |
Fibrosis | 0.7859 | 0.8180 | 0.8260 | 0.8160 | 0.8240 | 0.8076 | 0.8125 | −0.0135 |
Pleural Thickening | 0.6835 | 0.7610 | 0.7800 | 0.7630 | 0.8120 | 0.8208 | 0.7670 | −0.0538 |
Hernia | 0.8717 | 0.8960 | 0.9180 | 0.9370 | 0.8900 | 0.8628 | 0.8952 | −0.0418 |
Average | 0.7451 | 0.8066 | 0.8159 | 0.8058 | 0.8427 | 0.8307 | 0.8096 | −0.0331 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Hanif, M.S.; Bilal, M.; Alsaggaf, A.H.; Al-Saggaf, U.M. Enhancing Multi-Label Chest X-Ray Classification Using an Improved Ranking Loss. Bioengineering 2025, 12, 593. https://doi.org/10.3390/bioengineering12060593
Hanif MS, Bilal M, Alsaggaf AH, Al-Saggaf UM. Enhancing Multi-Label Chest X-Ray Classification Using an Improved Ranking Loss. Bioengineering. 2025; 12(6):593. https://doi.org/10.3390/bioengineering12060593
Chicago/Turabian StyleHanif, Muhammad Shehzad, Muhammad Bilal, Abdullah H. Alsaggaf, and Ubaid M. Al-Saggaf. 2025. "Enhancing Multi-Label Chest X-Ray Classification Using an Improved Ranking Loss" Bioengineering 12, no. 6: 593. https://doi.org/10.3390/bioengineering12060593
APA StyleHanif, M. S., Bilal, M., Alsaggaf, A. H., & Al-Saggaf, U. M. (2025). Enhancing Multi-Label Chest X-Ray Classification Using an Improved Ranking Loss. Bioengineering, 12(6), 593. https://doi.org/10.3390/bioengineering12060593