Araştırma Makalesi
BibTex RIS Kaynak Göster

ÖZNİTELİK ENTEGRASYONUNA DAYALI ESA MİMARİSİ KULLANILARAK ENDOSKOPİK GÖRÜNTÜLERİN SINIFLANDIRILMASI

Yıl 2024, , 121 - 132, 03.03.2024
https://doi.org/10.17780/ksujes.1362792

Öz

Derin öğrenme (DL) tekniklerindeki son gelişmeler, tıbbi görüntüler kullanılarak gastrointestinal (GI) hastalıkların sınıflandırılmasını otomatikleştirmek için umut verici bir potansiyel göstermektedir. Zamanında ve kesin teşhis, tedavi etkinliğini önemli ölçüde etkilemektedir. Bu araştırma, GI hastalıklarını tanımlamak için yeni bir DL tabanlı modeli tanıtmaktadır. Bu model, önceden eğitilmiş ağ mimarilerinin ara katmanlarından elde edilen öznitelikleri birleştirerek sınıflandırma işlemini gerçekleştirmektedir. Öznitelik entegrasyonuna dayalı evrişimsel sinir ağı (ESA) olarak adlandırılan bu modelde, endoskopik görüntüleri sınıflandırmak için önceden eğitilmiş ağ mimarilerinin yüksek ve düşük seviyeli öznitelikleri birleştirilerek nihai öznitelik haritası elde edilmektedir. Daha sonra bu öznitelik haritası sınıflandırma için kullanılmaktadır. Kvasirv2 veri seti kullanılarak yapılan deneysel analizler sonucunda, önerilen model ile başarılı bir performans elde edilmiştir. Özellikle, DenseNet201 modelinin ara katmanlarındaki özelliklerin birleştirilmesi, sırasıyla %94.25, %94.28, %94.24 ve %94.24 doğruluk, kesinlik, duyarlılık ve F1 puanı ile sonuçlanmıştır. Diğer ESA tabanlı önceden eğitilmiş modellerle ve son çalışmalarla yapılan karşılaştırmalı analizler, önerilen modelin üstünlüğünü ortaya koymuş ve doğruluğu %94.25'e yükseltmiştir. Bu, endoskopik görüntülerden GI hastalık tespitinde gelişmiş sınıflandırma doğruluğu için DenseNet201'in ara katmanlarındaki özelliklerden yararlanma potansiyelinin altını çizmektedir.

Kaynakça

  • Agrawa, T., Gupta, R., Sahu, S., & Wilson, C. E. (2017). SCL-UMD at the medico task-mediaeval 2017: Transfer learning based classification of medical images. CEUR Workshop Proceedings, 1984, 3–5.
  • Borgli, H., Thambawita, V., Smedsrud, P. H., Hicks, S., Jha, D., Eskeland, S. L., … de Lange, T. (2020). HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Scientific Data, 7(1), 1–14. https://doi.org/10.1038/s41597-020-00622-y
  • Du, W., Rao, N., Wang, Y., Hu, D., & Yong, J. (2020). Efficient Transfer Laerning Used in the Classification of Gastroscopic Images with Small Dataset. 2020 17th International Computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2020, 73–76. https://doi.org/10.1109/ICCWAMTIP51612.2020.9317450
  • Du, W., Rao, N., Yong, J., Wang, Y., Hu, D., Gan, T., … Zeng, B. (2022). Improving the Classification Performance of Esophageal Disease on Small Dataset by Semi-supervised Efficient Contrastive Learning. Journal of Medical Systems, 46(1). https://doi.org/10.1007/s10916-021-01782-z
  • Gunasekaran, H., Ramalakshmi, K., & Swaminathan, D. K. (2023). GIT-Net : An Ensemble Deep Learning-Based GI Tract Classification of Endoscopic Images. Bioengineering, 10(809).
  • Ha, Y., Du, Z., & Tian, J. (2022). Fine-grained interactive attention learning for semi-supervised white blood cell classification. Biomedical Signal Processing and Control, 75(September 2021), 103611. https://doi.org/10.1016/j.bspc.2022.103611
  • Haile, M. B., Salau, A. O., Enyew, B., Belay, A. J., & Jin, Z. (2022). Detection and classification of gastrointestinal disease using convolutional neural network and SVM Detection and classification of gastrointestinal disease using convolutional neural network and. Cogent Engineering, 9(1). https://doi.org/10.1080/23311916.2022.2084878
  • Iqbal, I., Walayat, K., Kakar, M. U., & Ma, J. (2022). Automated identification of human gastrointestinal tract abnormalities based on deep convolutional neural network with endoscopic images. Intelligent Systems with Applications, 16(November), 200149. https://doi.org/10.1016/j.iswa.2022.200149
  • Kahsaygebreslassie, A., Yaecobgirmaygezahegn, Hagos, M. T., Achimibenthal, & Pooja. (2019). Automated Gastrointestinal Disease Recognition for Endoscopic Images. Proceedings - 2019 International Conference on Computing, Communication, and Intelligent Systems, ICCCIS 2019, 2019-Janua, 312–316. https://doi.org/10.1109/ICCCIS48478.2019.8974458
  • Kaminski, M. F., Regula, J., Kraszewska, E., Polkowski, M., Wojciechowska, U., Didkowska, J., … Butruk, E. (2010). Quality indicators for colonoscopy and the risk of interval cancer. The New England Journal of Medicine, 362(19), 1795–1803. https://doi.org/10.1056/NEJMoa0907667
  • Khan, M. A., Sarfraz, M. S., Alhaisoni, M., Albesher, A. A., Wang, S., & Ashraf, I. (2020). StomachNet: Optimal deep learning features fusion for stomach abnormalities classification. IEEE Access, 8, 197969–197981. https://doi.org/10.1109/ACCESS.2020.3034217
  • Lin, T., Doll, P., Girshick, R., He, K., Hariharan, B., Belongie, S., & Ai, F. (2017). Feature Pyramid Networks for Object Detection.
  • Liu, Y., Gu, Z., & Cheung, W. K. (2017). HKBU at mediaeval 2017 medico: Medical multimedia task. CEUR Workshop Proceedings, 1984, 1–3.
  • Lonseko, Z. M., Adjei, P. E., Du, W., Luo, C., Hu, D., Zhu, L., … Rao, N. (2021). Gastrointestinal disease classification in endoscopic images using attention-guided convolutional neural networks. Applied Sciences (Switzerland), 11(23). https://doi.org/10.3390/app112311136
  • Majid, A., Khan, M. A., Yasmin, M., Rehman, A., Yousafzai, A., & Tariq, U. (2020). Classification of stomach infections: A paradigm of convolutional neural network along with classical features fusion and selection. Microscopy Research and Technique, 83(5), 562–576. https://doi.org/10.1002/jemt.23447
  • Mohapatra, S., Kumar Pati, G., Mishra, M., & Swarnkar, T. (2023). Gastrointestinal abnormality detection and classification using empirical wavelet transform and deep convolutional neural network from endoscopic images. Ain Shams Engineering Journal, 14(4), 101942. https://doi.org/10.1016/j.asej.2022.101942
  • Naz, J., Sharif, M., Yasmin, M., Raza, M., & Khan, M. A. (2021). Detection and Classification of Gastrointestinal Diseases using Machine Learning. Current Medical Imaging, 17(4), 479–490. https://doi.org/10.2174/1573405616666200928144626
  • Owais, M., Arsalan, M., Choi, J., Mahmood, T., & Park, K. R. (2019). Artificial intelligence-based classification of multiple gastrointestinal diseases using endoscopy videos for clinical diagnosis. Journal of Clinical Medicine, 8(7). https://doi.org/10.3390/jcm8070986
  • Pogorelov, K., Randel, K. R., Griwodz, C., Eskeland, S. L., De Lange, T., Johansen, D., … Halvorsen, P. (2017). Kvasir: A multi-class image dataset for computer aided gastrointestinal disease detection. Proceedings of the 8th ACM Multimedia Systems Conference, MMSys 2017, 164–169. https://doi.org/10.1145/3083187.3083212
  • Poudel, S., Kim, Y. J., Vo, D. M., & Lee, S. W. (2020). Colorectal Disease Classification Using Efficiently Scaled Dilation in Convolutional Neural Network. IEEE Access, 8, 99227–99238. https://doi.org/10.1109/ACCESS.2020.2996770
  • Pozdeev, A. A., Obukhova, N. A., & Motyko, A. A. (2019). Automatic Analysis of Endoscopic Images for Polyps Detection and Segmentation. In 2019 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus) (pp. 1216–1220). https://doi.org/10.1109/EIConRus.2019.8657018
  • Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. In N. Navab, J. Hornegger, W. M. Wells, & A. F. Frangi (Eds.), Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015 (pp. 234–241). Cham: Springer International Publishing.
  • Shahin, A. I., Guo, Y., Amin, K. M., & Sharawi, A. A. (2019). White blood cells identification system based on convolutional deep neural learning networks. Computer Methods and Programs in Biomedicine, 168, 69–80. https://doi.org/10.1016/j.cmpb.2017.11.015
  • Soffer, S., Klang, E., Shimon, O., Nachmias, N., Eliakim, R., Ben-Horin, S., … Barash, Y. (2020). Deep learning for wireless capsule endoscopy: a systematic review and meta-analysis. Gastrointestinal Endoscopy, 92(4), 831-839.e8. https://doi.org/10.1016/j.gie.2020.04.039
  • Su, Q., Wang, F., Chen, D., Chen, G., Li, C., & Wei, L. (2022). Deep convolutional neural networks with ensemble learning and transfer learning for automated detection of gastrointestinal diseases. Computers in Biology and Medicine, 150(July), 106054. https://doi.org/10.1016/j.compbiomed.2022.106054
  • Ucan, M., Kaya, B., & Kaya, M. (2022). Multi-Class Gastrointestinal Images Classification Using EfficientNet-B0 CNN Model. 2022 International Conference on Data Analytics for Business and Industry, ICDABI 2022, 146–150. https://doi.org/10.1109/ICDABI56818.2022.10041447
  • Xing, X., Yuan, Y., & Meng, M. Q. H. (2020). Zoom in Lesions for Better Diagnosis: Attention Guided Deformation Network for WCE Image Classification. IEEE Transactions on Medical Imaging, 39(12), 4047–4059. https://doi.org/10.1109/TMI.2020.3010102

CLASSIFICATION OF ENDOSCOPIC IMAGES USING CNN ARCHITECTURE BASED ON FEATURE INTEGRATION

Yıl 2024, , 121 - 132, 03.03.2024
https://doi.org/10.17780/ksujes.1362792

Öz

Recent developments in deep learning (DL) techniques show promising potential for automating the classification of gastrointestinal (GI) diseases using medical images. Timely and accurate diagnosis significantly impacts treatment effectiveness. This research introduces a new DL-based model for identifying GI diseases. This model performs classification by combining features extracted from intermediate layers of pretrained network architectures. In this model, named CNN based on feature integration, high and low-level features from pretrained network architectures are combined to obtain a final feature map for classifying endoscopic images. This feature map is then utilized for classification. Experimental analyses conducted using the Kvasirv2 dataset resulted in successful performance with the proposed model. Specifically, combining features from the intermediate layers of the DenseNet201 model resulted in accuracies, precision, recall, and F1 scores of 94.25%, 94.28%, 94.24%, and 94.24%, respectively. Comparative analyses against other CNN-based pretrained models and recent studies highlighted the superiority of the proposed model, elevating the accuracy to 94.25%. This underscores the potential of leveraging features from the intermediate layers of DenseNet201 for enhanced classification accuracy in detecting GI diseases from endoscopic images

Kaynakça

  • Agrawa, T., Gupta, R., Sahu, S., & Wilson, C. E. (2017). SCL-UMD at the medico task-mediaeval 2017: Transfer learning based classification of medical images. CEUR Workshop Proceedings, 1984, 3–5.
  • Borgli, H., Thambawita, V., Smedsrud, P. H., Hicks, S., Jha, D., Eskeland, S. L., … de Lange, T. (2020). HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Scientific Data, 7(1), 1–14. https://doi.org/10.1038/s41597-020-00622-y
  • Du, W., Rao, N., Wang, Y., Hu, D., & Yong, J. (2020). Efficient Transfer Laerning Used in the Classification of Gastroscopic Images with Small Dataset. 2020 17th International Computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2020, 73–76. https://doi.org/10.1109/ICCWAMTIP51612.2020.9317450
  • Du, W., Rao, N., Yong, J., Wang, Y., Hu, D., Gan, T., … Zeng, B. (2022). Improving the Classification Performance of Esophageal Disease on Small Dataset by Semi-supervised Efficient Contrastive Learning. Journal of Medical Systems, 46(1). https://doi.org/10.1007/s10916-021-01782-z
  • Gunasekaran, H., Ramalakshmi, K., & Swaminathan, D. K. (2023). GIT-Net : An Ensemble Deep Learning-Based GI Tract Classification of Endoscopic Images. Bioengineering, 10(809).
  • Ha, Y., Du, Z., & Tian, J. (2022). Fine-grained interactive attention learning for semi-supervised white blood cell classification. Biomedical Signal Processing and Control, 75(September 2021), 103611. https://doi.org/10.1016/j.bspc.2022.103611
  • Haile, M. B., Salau, A. O., Enyew, B., Belay, A. J., & Jin, Z. (2022). Detection and classification of gastrointestinal disease using convolutional neural network and SVM Detection and classification of gastrointestinal disease using convolutional neural network and. Cogent Engineering, 9(1). https://doi.org/10.1080/23311916.2022.2084878
  • Iqbal, I., Walayat, K., Kakar, M. U., & Ma, J. (2022). Automated identification of human gastrointestinal tract abnormalities based on deep convolutional neural network with endoscopic images. Intelligent Systems with Applications, 16(November), 200149. https://doi.org/10.1016/j.iswa.2022.200149
  • Kahsaygebreslassie, A., Yaecobgirmaygezahegn, Hagos, M. T., Achimibenthal, & Pooja. (2019). Automated Gastrointestinal Disease Recognition for Endoscopic Images. Proceedings - 2019 International Conference on Computing, Communication, and Intelligent Systems, ICCCIS 2019, 2019-Janua, 312–316. https://doi.org/10.1109/ICCCIS48478.2019.8974458
  • Kaminski, M. F., Regula, J., Kraszewska, E., Polkowski, M., Wojciechowska, U., Didkowska, J., … Butruk, E. (2010). Quality indicators for colonoscopy and the risk of interval cancer. The New England Journal of Medicine, 362(19), 1795–1803. https://doi.org/10.1056/NEJMoa0907667
  • Khan, M. A., Sarfraz, M. S., Alhaisoni, M., Albesher, A. A., Wang, S., & Ashraf, I. (2020). StomachNet: Optimal deep learning features fusion for stomach abnormalities classification. IEEE Access, 8, 197969–197981. https://doi.org/10.1109/ACCESS.2020.3034217
  • Lin, T., Doll, P., Girshick, R., He, K., Hariharan, B., Belongie, S., & Ai, F. (2017). Feature Pyramid Networks for Object Detection.
  • Liu, Y., Gu, Z., & Cheung, W. K. (2017). HKBU at mediaeval 2017 medico: Medical multimedia task. CEUR Workshop Proceedings, 1984, 1–3.
  • Lonseko, Z. M., Adjei, P. E., Du, W., Luo, C., Hu, D., Zhu, L., … Rao, N. (2021). Gastrointestinal disease classification in endoscopic images using attention-guided convolutional neural networks. Applied Sciences (Switzerland), 11(23). https://doi.org/10.3390/app112311136
  • Majid, A., Khan, M. A., Yasmin, M., Rehman, A., Yousafzai, A., & Tariq, U. (2020). Classification of stomach infections: A paradigm of convolutional neural network along with classical features fusion and selection. Microscopy Research and Technique, 83(5), 562–576. https://doi.org/10.1002/jemt.23447
  • Mohapatra, S., Kumar Pati, G., Mishra, M., & Swarnkar, T. (2023). Gastrointestinal abnormality detection and classification using empirical wavelet transform and deep convolutional neural network from endoscopic images. Ain Shams Engineering Journal, 14(4), 101942. https://doi.org/10.1016/j.asej.2022.101942
  • Naz, J., Sharif, M., Yasmin, M., Raza, M., & Khan, M. A. (2021). Detection and Classification of Gastrointestinal Diseases using Machine Learning. Current Medical Imaging, 17(4), 479–490. https://doi.org/10.2174/1573405616666200928144626
  • Owais, M., Arsalan, M., Choi, J., Mahmood, T., & Park, K. R. (2019). Artificial intelligence-based classification of multiple gastrointestinal diseases using endoscopy videos for clinical diagnosis. Journal of Clinical Medicine, 8(7). https://doi.org/10.3390/jcm8070986
  • Pogorelov, K., Randel, K. R., Griwodz, C., Eskeland, S. L., De Lange, T., Johansen, D., … Halvorsen, P. (2017). Kvasir: A multi-class image dataset for computer aided gastrointestinal disease detection. Proceedings of the 8th ACM Multimedia Systems Conference, MMSys 2017, 164–169. https://doi.org/10.1145/3083187.3083212
  • Poudel, S., Kim, Y. J., Vo, D. M., & Lee, S. W. (2020). Colorectal Disease Classification Using Efficiently Scaled Dilation in Convolutional Neural Network. IEEE Access, 8, 99227–99238. https://doi.org/10.1109/ACCESS.2020.2996770
  • Pozdeev, A. A., Obukhova, N. A., & Motyko, A. A. (2019). Automatic Analysis of Endoscopic Images for Polyps Detection and Segmentation. In 2019 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus) (pp. 1216–1220). https://doi.org/10.1109/EIConRus.2019.8657018
  • Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. In N. Navab, J. Hornegger, W. M. Wells, & A. F. Frangi (Eds.), Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015 (pp. 234–241). Cham: Springer International Publishing.
  • Shahin, A. I., Guo, Y., Amin, K. M., & Sharawi, A. A. (2019). White blood cells identification system based on convolutional deep neural learning networks. Computer Methods and Programs in Biomedicine, 168, 69–80. https://doi.org/10.1016/j.cmpb.2017.11.015
  • Soffer, S., Klang, E., Shimon, O., Nachmias, N., Eliakim, R., Ben-Horin, S., … Barash, Y. (2020). Deep learning for wireless capsule endoscopy: a systematic review and meta-analysis. Gastrointestinal Endoscopy, 92(4), 831-839.e8. https://doi.org/10.1016/j.gie.2020.04.039
  • Su, Q., Wang, F., Chen, D., Chen, G., Li, C., & Wei, L. (2022). Deep convolutional neural networks with ensemble learning and transfer learning for automated detection of gastrointestinal diseases. Computers in Biology and Medicine, 150(July), 106054. https://doi.org/10.1016/j.compbiomed.2022.106054
  • Ucan, M., Kaya, B., & Kaya, M. (2022). Multi-Class Gastrointestinal Images Classification Using EfficientNet-B0 CNN Model. 2022 International Conference on Data Analytics for Business and Industry, ICDABI 2022, 146–150. https://doi.org/10.1109/ICDABI56818.2022.10041447
  • Xing, X., Yuan, Y., & Meng, M. Q. H. (2020). Zoom in Lesions for Better Diagnosis: Attention Guided Deformation Network for WCE Image Classification. IEEE Transactions on Medical Imaging, 39(12), 4047–4059. https://doi.org/10.1109/TMI.2020.3010102
Toplam 27 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Derin Öğrenme
Bölüm Bilgisayar Mühendisliği
Yazarlar

Hüseyin Üzen 0000-0002-0998-2130

Hüseyin Fırat 0000-0002-1257-8518

Yayımlanma Tarihi 3 Mart 2024
Gönderilme Tarihi 19 Eylül 2023
Yayımlandığı Sayı Yıl 2024

Kaynak Göster

APA Üzen, H., & Fırat, H. (2024). ÖZNİTELİK ENTEGRASYONUNA DAYALI ESA MİMARİSİ KULLANILARAK ENDOSKOPİK GÖRÜNTÜLERİN SINIFLANDIRILMASI. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 27(1), 121-132. https://doi.org/10.17780/ksujes.1362792