kaz29Вестник Казахстанско-Британского технического университетаHerald of the Kazakh-British Technical University1998-66882959-8109Казахстанско-Британский Технический Университет10.55452/1998-6688-2024-21-2-42-53kaz29-1253Research ArticleКОМПЬЮТЕРНЫЕ НАУКИCOMPUTER SCIENCEСРАВНИТЕЛЬНЫЙ АНАЛИЗ МОДЕЛЕЙ U-NET, U-NET++, TRANSUNET AND SWIN-UNET В ЗАДАЧЕ СЕГМЕНТАЦИИ РЕНТГЕН-СНИМКОВ ЛЕГКОГОCOMPARATIVE ANALYSIS OF U-NET, U-NET++, TRANSUNET AND SWIN-UNET FOR LUNG X-RAY SEGMENTATIONhttps://orcid.org/0000-0002-9356-3114НамД.NamD.

магистр техн. наук, PhD студент

050000, г. Алматы

Master of Tech. Sciences, PhD Student

050000, Almaty

d.nam@kbtu.kzhttps://orcid.org/0000-0002-8685-9355ПакА.PakA.

канд. техн. наук, профессор

050000, г. Алматы

Candidate of Tech. Sciences, Professor

050000, Almaty

a.pak@kbtu.kzКазахстанско-Британский технический университетКазахстанKazakh-British Technical UniversityKazakhstan2024300620242124253Copyright © Нам Д., Пак А., 20242024Нам Д., Пак А.Nam D., Pak A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.kbtu.edu.kz/jour/article/view/1253

Сегментация медицинских изображений является широко используемой задачей в обработке медицинских изображений. Использование сегментации в медицине позволяет получить местоположение и размер необходимой сущности. Существует несколько важных факторов при выборе модели. Во-первых, модель должна обеспечивать точное предсказание маски. Во-вторых, модель не должна требовать большого объема вычислительных ресурсов. Наконец, следует учесть распределение между ложноположительными и ложноотрицательными предсказаниями. Мы предоставляем сравнительный анализ четырех моделей глубокого обучения: базовой U-Net и ее расширений U-Net++, TranUNet и Swin-UNet для сегментации легких по рентгеновским снимкам на основе обучаемых параметров, DICE, IoU, расстояния Хаусдорфа, точности и полноты. Модели CNN с наименьшим количеством параметров показывают самые высокие показатели DICE и IoU по сравнению с моделями с большим количеством параметров на ограниченном по размеру наборе данных. Согласно результатам эксперимента, представленным в статье, U-Net имеет максимальные DICE, IoU и точность. Это делает модель наиболее подходящей для сегментации медицинских изображений. SwinU-Net – модель с минимальным расстоянием Хаусдорфа. U-Net++ имеет максимальную полноту.

Medical image segmentation is a widely used task in medical image processing. It allows us to receive the location and size of the required instance. Several critical factors should be considered. First, the model should provide an accurate prediction of the mask. Second, the model should not require a lot of computational resources. Finally, the distribution between the false positive and false negative predictions should be considered. We provide the comparative analysis between four deep learning models, base U-Net and its extension U-Net++, TranUNet, and Swin-UNet for lung X-ray segmentation based on trainable parameters, DICE, IoU, Hausdorff Distance, Precision and Recall. CNN models with the smallest number of parameters show the highest DICE and IoU scores than their descendants on the limited-size dataset. Based on the experiment results provided in the article U-Nethas maximum DICE, IoU, and precision. It makes the model the most appropriate for medical image segmentation. SwinU-Net is the model with minimum Hausdorff Distance. U-Net++ has the maximum Recall.

CNNсегментациятрансформерыобработка медицинских изображенийCNNsegmentationtransformersmedical image processingThis work was supported by the Ministry of Education and Sciences of the Republic of Kazakhstan under the following grant #AP14871214. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.ReferencesRonneberger O., Fischer P. and Brox T. (2015) U-Net: Convolutional networks for biomedical image segmentation, in Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent., pp. 234–241.Ronneberger O., Fischer P. and Brox T. (2015) U-Net: Convolutional networks for biomedical image segmentation, in Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent., pp. 234–241.Shaziya H., Shyamala K. and Zaheer R. (2018) Automatic Lung Segmentation on Thoracic CT Scans Using U-Net Convolutional Network, 2018 International Conference on Communication and Signal Processing (ICCSP), Chennai, India, pp. 0643–0647. https://doi.org/10.1109/ICCSP.2018.8524484.Shaziya H., Shyamala K. and Zaheer R. (2018) Automatic Lung Segmentation on Thoracic CT Scans Using U-Net Convolutional Network, 2018 International Conference on Communication and Signal Processing (ICCSP), Chennai, India, pp. 0643–0647. https://doi.org/10.1109/ICCSP.2018.8524484.Robin M., John J. and Ravikumar A. (2021) Breast Tumor Segmentation using U-NET, 2021 5th International Conference on Computing Methodologies and Communication (ICCMC), Erode, India, pp. 1164–1167. https:// doi.org/10.1109/ICCMC51019.2021.9418447.Robin M., John J. and Ravikumar A. (2021) Breast Tumor Segmentation using U-NET, 2021 5th International Conference on Computing Methodologies and Communication (ICCMC), Erode, India, pp. 1164–1167. https:// doi.org/10.1109/ICCMC51019.2021.9418447.Frid-Adar M., Ben-Cohen A., Amer R. and Greenspan H. (2018) Improving the segmentation of anatomical structures in chest radiographs using U-Net with an ImageNet pre-trained encoder, in Image Analysis for Moving Organ, Breast, and Thoracic Images. Cham, Switzerland: Springer, pp. 159–168.Frid-Adar M., Ben-Cohen A., Amer R. and Greenspan H. (2018) Improving the segmentation of anatomical structures in chest radiographs using U-Net with an ImageNet pre-trained encoder, in Image Analysis for Moving Organ, Breast, and Thoracic Images. Cham, Switzerland: Springer, pp. 159–168.He K., Zhang X., Ren S. and Sun J. (2016) Deep Residual Learning for Image Recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770–778. https://doi.org/10.1109/CVPR.2016.90.He K., Zhang X., Ren S. and Sun J. (2016) Deep Residual Learning for Image Recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770–778. https://doi.org/10.1109/CVPR.2016.90.Liang, Ming, and Xiaolin Hu (2015) Recurrent convolutional neural network for object recognition. Proceedings of the IEEE conference on computer vision and pattern recognition.Liang, Ming, and Xiaolin Hu (2015) Recurrent convolutional neural network for object recognition. Proceedings of the IEEE conference on computer vision and pattern recognition.Huang G., Liu Z., Van Der Maaten L. and Weinberger K.Q. (2017) Densely Connected Convolutional Networks, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 2261–2269. https://doi.org/10.1109/CVPR.2017.243.Huang G., Liu Z., Van Der Maaten L. and Weinberger K.Q. (2017) Densely Connected Convolutional Networks, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 2261–2269. https://doi.org/10.1109/CVPR.2017.243.Chen J., Lu Y., Yu Q., Luo X., Adeli E., Wang Y. ... and Zhou Y. (2021) Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306.Chen J., Lu Y., Yu Q., Luo X., Adeli E., Wang Y. ... and Zhou Y. (2021) Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306.Pan S., Liu X., Xie N. and Chong Y. (2023) EG-TransUNet: a transformer-based U-Net with enhanced and guided models for biomedical image segmentation. BMC bioinformatics, 24(1), 85.Pan S., Liu X., Xie N. and Chong Y. (2023) EG-TransUNet: a transformer-based U-Net with enhanced and guided models for biomedical image segmentation. BMC bioinformatics, 24(1), 85.Cao H., Wang Y., Chen J., Jiang D., Zhang X., Tian Q. and Wang M. (2023, February). Swin-unet: Unetlike pure transformer for medical image segmentation. In Computer Vision–ECCV 2022 Workshops: Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part III, pp. 205–218, Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-25066-8_9.Cao H., Wang Y., Chen J., Jiang D., Zhang X., Tian Q. and Wang M. (2023, February). Swin-unet: Unetlike pure transformer for medical image segmentation. In Computer Vision–ECCV 2022 Workshops: Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part III, pp. 205–218, Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-25066-8_9.Zhou Z., Rahman Siddiquee M.M., Tajbakhsh N. and Liang J. (2018) Unet++: A nested u-net architecture for medical image segmentation. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4, pp. 3–11, Springer International Publishing.Zhou Z., Rahman Siddiquee M.M., Tajbakhsh N. and Liang J. (2018) Unet++: A nested u-net architecture for medical image segmentation. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4, pp. 3–11, Springer International Publishing.Multi-Atlas Labeling Beyond the Cranial Vault – Workshop and Challenge. Synapse multi-organ computer tomography dataset. [Data set]. Synapse.org. https://repo-prod.prod.sagebase.org/repo/v1/doi/loca.te?id=syn3193805type=ENTITY. https://doi.org/10.7303/SYN3193805Multi-Atlas Labeling Beyond the Cranial Vault – Workshop and Challenge. Synapse multi-organ computer tomography dataset. [Data set]. Synapse.org. https://repo-prod.prod.sagebase.org/repo/v1/doi/loca.te?id=syn3193805type=ENTITY. https://doi.org/10.7303/SYN3193805Bernard O., Lalande A., Zotti C. et al. (2018) Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? IEEE Trans Med Imaging, vol.37, no.11, pp. 2514–2525. https://doi.org/10.1109/TMI.2018.2837502.Bernard O., Lalande A., Zotti C. et al. (2018) Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? IEEE Trans Med Imaging, vol.37, no.11, pp. 2514–2525. https://doi.org/10.1109/TMI.2018.2837502.Jaeger S., Karargyris A., Candemir S. et al. (2014) Automatic tuberculosis screening using chest radiographs. IEEE Trans Med Imaging, vol.33, no. 2, pp. 233–245. https://doi.org/10.1109/TMI.2013.2284099. PMID: 24108713Jaeger S., Karargyris A., Candemir S. et al. (2014) Automatic tuberculosis screening using chest radiographs. IEEE Trans Med Imaging, vol.33, no. 2, pp. 233–245. https://doi.org/10.1109/TMI.2013.2284099. PMID: 24108713Candemir S., Jaeger S., Palaniappan K., Musco JP, Singh RK, Xue Z., Karargyris A., Antani S., Thoma G. and McDonald CJ. (2014) Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE Trans Med Imaging, vol. 33, no. 2, pp. 577–590. https://doi.org/10.1109/ TMI.2013.2290491. PMID: 24239990Candemir S., Jaeger S., Palaniappan K., Musco JP, Singh RK, Xue Z., Karargyris A., Antani S., Thoma G. and McDonald CJ. (2014) Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE Trans Med Imaging, vol. 33, no. 2, pp. 577–590. https://doi.org/10.1109/ TMI.2013.2290491. PMID: 24239990Dong H., Yang G., Liu F., Mo Y. and Guo Y. (2017) Automatic brain tumor detection and segmentation using U-Net based fully convolutional networks. In Medical Image Understanding and Analysis: 21st Annual Conference, MIUA 2017, Edinburgh, UK, July 11–13, Proceedings 21, pp. 506–517, Springer International Publishing.Dong H., Yang G., Liu F., Mo Y. and Guo Y. (2017) Automatic brain tumor detection and segmentation using U-Net based fully convolutional networks. In Medical Image Understanding and Analysis: 21st Annual Conference, MIUA 2017, Edinburgh, UK, July 11–13, Proceedings 21, pp. 506–517, Springer International Publishing.Roja Ramani D. and Siva Ranjani S. (2019) U-Net based segmentation and multiple feature extraction of dermascopic images for efficient diagnosis of melanoma. In Computer Aided Intervention and Diagnostics in Clinical and Medical Images, pp. 81–101, Springer International Publishing. https://doi.org/10.1007/978-3-030-04061-1_9.Roja Ramani D. and Siva Ranjani S. (2019) U-Net based segmentation and multiple feature extraction of dermascopic images for efficient diagnosis of melanoma. In Computer Aided Intervention and Diagnostics in Clinical and Medical Images, pp. 81–101, Springer International Publishing. https://doi.org/10.1007/978-3-030-04061-1_9.Song L.I., Geoffrey K.F. and Kaijian H.E. (2020) Bottleneck feature supervised U-Net for pixel-wise liver and tumor segmentation. Expert Systems with Applications, no. 145, p. 113131. https://doi.org/10.1016/j.eswa.2019.113131.Song L.I., Geoffrey K.F. and Kaijian H.E. (2020) Bottleneck feature supervised U-Net for pixel-wise liver and tumor segmentation. Expert Systems with Applications, no. 145, p. 113131. https://doi.org/10.1016/j.eswa.2019.113131.Abderrahim N. Y. Q., Abderrahim S. and Rida A. (2020) Road Segmentation using U-Net architecture, 2020 IEEE International conference of Moroccan Geomatics (Morgeo), Casablanca, Morocco, pp. 1–4, https://doi.org/10.1109/Morgeo49228.2020.9121887.Abderrahim N. Y. Q., Abderrahim S. and Rida A. (2020) Road Segmentation using U-Net architecture, 2020 IEEE International conference of Moroccan Geomatics (Morgeo), Casablanca, Morocco, pp. 1–4, https://doi.org/10.1109/Morgeo49228.2020.9121887.Zhuang, J. (2018) LadderNet: Multi-path networks based on U-Net for medical image segmentation. arXiv preprint arXiv:1810.07810.Zhuang, J. (2018) LadderNet: Multi-path networks based on U-Net for medical image segmentation. arXiv preprint arXiv:1810.07810.Çiçek Ö., Abdulkadir A., Lienkamp S.S., Brox T. & Ronneberger O. (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2016: 19th International Conference, Athens, Greece, October 17–21, Proceedings, Part II 19, pp. 424–432. Springer International Publishing.Çiçek Ö., Abdulkadir A., Lienkamp S.S., Brox T. & Ronneberger O. (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2016: 19th International Conference, Athens, Greece, October 17–21, Proceedings, Part II 19, pp. 424–432. Springer International Publishing.Chen W., Liu B., Peng S., Sun J. & Qiao X. (2019) S3D-UNet: Separable 3D U-Net for Brain Tumor Segmentation. Lecture Notes in Computer Science, pp. 358–368. https://doi.org/10.1007/978-3-030-11726-9_32.Chen W., Liu B., Peng S., Sun J. & Qiao X. (2019) S3D-UNet: Separable 3D U-Net for Brain Tumor Segmentation. Lecture Notes in Computer Science, pp. 358–368. https://doi.org/10.1007/978-3-030-11726-9_32.Siddique N., Paheding S., Elkin C.P. and Devabhaktuni V. (2021) U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications, in IEEE Access, vol. 9, pp. 82031–82057. https://doi.org/10.1109/ACCESS.2021.3086020.Siddique N., Paheding S., Elkin C.P. and Devabhaktuni V. (2021) U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications, in IEEE Access, vol. 9, pp. 82031–82057. https://doi.org/10.1109/ACCESS.2021.3086020.Woo B. and Lee M. (2021) Comparison of tissue segmentation performance between 2D U-Net and 3D U-Net on brain MR Images, 2021 International Conference on Electronics, Information, and Communication (ICEIC), Jeju, Korea (South), pp. 1–4. https://doi.org/10.1109/ICEIC51217.2021.9369797.Woo B. and Lee M. (2021) Comparison of tissue segmentation performance between 2D U-Net and 3D U-Net on brain MR Images, 2021 International Conference on Electronics, Information, and Communication (ICEIC), Jeju, Korea (South), pp. 1–4. https://doi.org/10.1109/ICEIC51217.2021.9369797.Marcus D.S., Wang T.H., Parker J., Csernansky J.G., Morris J.G. and Buckner R.L. (2007) Open Access Series of Imaging Studies (OASIS): Crosssectional MRI data in young, middle aged, nondemented, and demented older adults, J. Cogn. Neurosci., vol. 19, pp. 1498–1507.Marcus D.S., Wang T.H., Parker J., Csernansky J.G., Morris J.G. and Buckner R.L. (2007) Open Access Series of Imaging Studies (OASIS): Crosssectional MRI data in young, middle aged, nondemented, and demented older adults, J. Cogn. Neurosci., vol. 19, pp. 1498–1507.Meine H., Chlebus G., Ghafoorian M., Endo I. and Schenk A. (2018) Comparison of u-net-based convolutional neural networks for liver segmentation in ct. arXiv preprint arXiv:1810.04017.Meine H., Chlebus G., Ghafoorian M., Endo I. and Schenk A. (2018) Comparison of u-net-based convolutional neural networks for liver segmentation in ct. arXiv preprint arXiv:1810.04017.Song G., Nie Y., Zhang J. and Chen G. (2020) Research on the fusion method of 2D and 3D UNet in pulmonary nodules segmentation task, 2020 International Conference on Computer Science and Management Technology (ICCSMT), Shanghai, China, pp. 44–47. https://doi.org/10.1109/ICCSMT51754.2020.00016.Song G., Nie Y., Zhang J. and Chen G. (2020) Research on the fusion method of 2D and 3D UNet in pulmonary nodules segmentation task, 2020 International Conference on Computer Science and Management Technology (ICCSMT), Shanghai, China, pp. 44–47. https://doi.org/10.1109/ICCSMT51754.2020.00016.Armato S.G. 3rd, McLennan G., Bidaut L. et al. (2011) The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A completed reference database of lung nodules on CT scans. Medical Physics, no.38, pp. 915–931. https://doi.org/10.1118/1.3528204Armato S.G. 3rd, McLennan G., Bidaut L. et al. (2011) The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A completed reference database of lung nodules on CT scans. Medical Physics, no.38, pp. 915–931. https://doi.org/10.1118/1.3528204Dosovitskiy A., Beyer L., Kolesnikov A., Weissenborn D., Zhai X., Unterthiner T. ... and Houlsby N. (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.Dosovitskiy A., Beyer L., Kolesnikov A., Weissenborn D., Zhai X., Unterthiner T. ... and Houlsby N. (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.Ying S., Wang B., Zhu H., Liu W. and Huang, F. (2022) Caries segmentation on tooth X-ray images with a deep network, Journal of Dentistry, no. 119, p. 104076. https://doi.org/10.1016/j.jdent.2022.104076.Ying S., Wang B., Zhu H., Liu W. and Huang, F. (2022) Caries segmentation on tooth X-ray images with a deep network, Journal of Dentistry, no. 119, p. 104076. https://doi.org/10.1016/j.jdent.2022.104076.Wang H., Xie S., Lin L., Iwamoto Y., Han X.H., Chen Y. W. and Tong R. (2022, May). Mixed transformer u-net for medical image segmentation. In ICASSP 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2390–2394 IEEE. https://doi.org/10.1109/ICASSP43922.2022.9746172.Wang H., Xie S., Lin L., Iwamoto Y., Han X.H., Chen Y. W. and Tong R. (2022, May). Mixed transformer u-net for medical image segmentation. In ICASSP 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2390–2394 IEEE. https://doi.org/10.1109/ICASSP43922.2022.9746172.Jia X., Bartlett J., Zhang T., Lu W., Qiu Z. and Duan J. (2022, September) U-net vs transformer: Is u-net outdated in medical image registration? In International Workshop on Machine Learning in Medical Imaging, pp. 151–160. Cham: Springer Nature Switzerland.Jia X., Bartlett J., Zhang T., Lu W., Qiu Z. and Duan J. (2022, September) U-net vs transformer: Is u-net outdated in medical image registration? In International Workshop on Machine Learning in Medical Imaging, pp. 151–160. Cham: Springer Nature Switzerland.Chen J., Frey E.C., He Y., Segars W.P., Li Y. & Du Y. (2022) Transmorph: Transformer for unsupervised medical image registration. Medical image analysis, no. 82, p. 102615. https://doi.org/10.1016/j.media.2022.102615.Chen J., Frey E.C., He Y., Segars W.P., Li Y. & Du Y. (2022) Transmorph: Transformer for unsupervised medical image registration. Medical image analysis, no. 82, p. 102615. https://doi.org/10.1016/j.media.2022.102615.He K., Gkioxari G., Dollár P. and Girshick R. (2017) Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pp. 2961–2969.He K., Gkioxari G., Dollár P. and Girshick R. (2017) Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pp. 2961–2969.Liu M., Dong J., Dong X., Yu H. and Qi L. (2018, September). Segmentation of lung nodule in CT images based on mask R-CNN. In 2018 9th International Conference on Awareness Science and Technology (iCAST), pp. 1–6, IEEE.Liu M., Dong J., Dong X., Yu H. and Qi L. (2018, September). Segmentation of lung nodule in CT images based on mask R-CNN. In 2018 9th International Conference on Awareness Science and Technology (iCAST), pp. 1–6, IEEE.Zhang Y., Chan S., Park V.Y., Chang, K.T., Mehta S., Kim M. J. ... and Su M. Y. (2022). Automatic detection and segmentation of breast cancer on MRI using mask R-CNN trained on non–fat-sat images and tested on fat-sat images. Academic Radiology, 29, pp. 135–144.Zhang Y., Chan S., Park V.Y., Chang, K.T., Mehta S., Kim M. J. ... and Su M. Y. (2022). Automatic detection and segmentation of breast cancer on MRI using mask R-CNN trained on non–fat-sat images and tested on fat-sat images. Academic Radiology, 29, pp. 135–144.Vuola A.O., Akram S.U. and Kannala J. (2019) Mask-RCNN and U-Net Ensembled for Nuclei Segmentation, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy, pp. 208–212. https://doi.org/10.1109/ISBI.2019.8759574.Vuola A.O., Akram S.U. and Kannala J. (2019) Mask-RCNN and U-Net Ensembled for Nuclei Segmentation, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy, pp. 208–212. https://doi.org/10.1109/ISBI.2019.8759574.

The authors declare that there are no conflicts of interest present.