Comparing YOLO and Detectron2 models for automatic extracting patients information from leprosy assessment form

• Anthony Militão UPE
• Hilson Gomes Vilar de Andrade UPE / IFPE
• Kayo H. Monteiro UPE
• Elisson da Silva Rocha UPE
• Patricia Takako Endo UPE

DOI: https://doi.org/10.5753/sbcas.2025.7140

Resumo

Leprosy, caused by Mycobacterium leprae, remains a global challenge, requiring strategies to achieve disease elimination by 2030. In Brazil, the Simplified Neurological Assessment (from Portuguese Avaliação Neurológica Simplificada, ANS) is mandatory for suspected cases; however, the form is still manually fulfilled, which limits the use of data. This study evaluates computer vision models (YOLOv8x, YOLO11x, Faster R-CNN) for detecting hand and foot sensitivity regions from ANS forms. All models were evaluated based on precision, recall, mean average precision (mAP) and confusion matrix. YOLO variants achieved over 94% precision and 84% recall across all classes. Automating ANS data extraction can facilitate the creation of structured datasets, enhancing disease monitoring and enabling the train of predictive models.

Referências

Brasil. Ministério da Saúde (2022). Protocolo clínico e diretrizes terapêuticas da hanseníase. [link].

Dahoklory, D. F., Haryanto, J., and Indarwati, R. (2023). The application of digital health as a nursing solution for leprosy patients during the covid-19 pandemic: A systematic review. JPMA. The Journal of the Pakistan Medical Association, 73(Suppl 2)(2):S170–S174. Department of Nursing, Airlangga University, Surabaya, Indonesia.

Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, pages 580–587.

Hao, Y., Pei, H., Lyu, Y., Yuan, Z., Rizzo, J.-R., Wang, Y., and Fang, Y. (2023). Understanding the impact of image quality and distance of objects to object detection performance. In 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 11436–11442.

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770–778.

Hsu, E., Malagaris, I., Kuo, Y., Sultana, R., and Roberts, K. (2021). Deep learning-based NLP data pipeline for EHR scanned document information extraction. CoRR, abs/2110.11864.

Ilemobayo, J., Durodola, O., Alade, O., Awotunde, O., Adewumi, T., Falana, O., Ogungbire, A., Osinuga, A., Ogunbiyi, D., Odezuligbo, I., Edu, O., and Ifeanyi, A. (2024). Hyperparameter tuning in machine learning: A comprehensive review. Journal of Engineering Research and Reports, 26:388–395.

Leite, S., Barros, A., Fonseca, M., Andrade, T., Foss, N., and Frade, M. (2010). Avaliação sensitiva de hansenianos pelos monofilamentos semmes-weinstein em serviço terciário de fisioterapia. Hansenologia Internationalis: hanseníase e outras doenças infecciosas, 35:9–16.

Leite-Moreira, A., Mendes, A., Pedrosa, A., Rocha-Sousa, A., Azevedo, A., Amaral-Gomes, A., Pinto, C., Figueira, H., Pereira, N. R., Mendes, P., and Pimenta, T. (2022). An nlp solution to foster the use of information in electronic health records for efficiency in decision-making in hospital care.

Li, Z., Liu, F., Yang, W., Peng, S., and Zhou, J. (2022). A survey of convolutional neural networks: Analysis, applications, and prospects. IEEE Transactions on Neural Networks and Learning Systems, 33(12):6999–7019.

Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Ministério da Saúde - Secretaria de Vigilância em Saúde (2021). Formulário para Avaliação Neurológica Simplificada e Classificação do Grau de Incapacidade Física em Hanseníase. Ministério da Saúde, Brasil.

Ministério da Saúde, Secretaria de Ciência, T. I. e. I. E. e. S. (2022). Protocolo clÍnico e diretrizes terapÊuticas da hansenÍase. [link]. Portaria SCTIE/MS Nº 67, de 7 de julho de 2022.

Mirzaei, B., Nezamabadi-Pour, H., Raoof, A., and Derakhshani, R. (2023). Small object detection and tracking: A comprehensive review. Sensors (Basel), 23(15):6887. Intelligent Data Processing Laboratory (IDPL), Department of Electrical Engineering, Shahid Bahonar University of Kerman, Kerman, Iran. Department of Earth Sciences, Utrecht University, Utrecht, Netherlands.

Nóbrega, M. d. M., Santana, E. M. F., Brito, K. K. G., Antas, E. M. V., Pacheco, F. C. d. S., Oliveira, S. H. d. S., and Soares, M. J. G. O. (2024). PercepÇÕes de profissionais sobre intervenÇÃo educativa acerca da avaliaÇÃo neurolÓgica simplificada da hansenÍase. Revista Baiana de Enfermagem, 38(.).

Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 779–788.

Sasakawa, Y. (2024). What’s needed to achieve zero leprosy. Bulletin of the World Health Organization, 102(8):554–554A. The Nippon Foundation, The Nippon Zaidan Building 1-2-2 Akasaka, Minato-ku Tokyo 107-8404, Japan.

WHO (2017). Guidelines for the Diagnosis, Treatment and Prevention of Leprosy. World Health Organization, Regional Office for South-East Asia, New Delhi, India. Licence: CC BY-NC-SA 3.0 IGO.

WHO (2021). Towards zero leprosy. global leprosy (hansen’s disease) strategy 2021–2030. Advocacy Brief.

WHO (2024). Global leprosy (hansen disease) update, 2023: Elimination of leprosy disease is possible – time to act! WHO Weekly Epidemiological Record, WER No 37, 2024, 99, 501–521.