隨著醫學影像在疾病評估和症狀診斷中扮演著越來越關鍵的角色，眾多研究人員致力於探索高效且更快速的方法，以協助專業人員進行準確且迅速的診斷。然而，掃描設置、機器狀況以及影像重建技術等因素可能導致偽影並產生低品質影像，進而降低診斷效能。

針對低品質影像的分割問題，存在兩種截然不同的解決途徑。第一種方法是在分割之前應用去噪技術，以提升影像品質；而第二種方法則直接對那些可能難以或無法有效去噪的低品質影像進行分割。
在第一種途徑中，研究人員投入了大量精力提出各種偽影消除與去噪方法來去除噪聲。然而，多數現有的去噪方法均採用監督式框架，需依賴真實標註進行模型訓練。這些方法通常依賴模擬生成數據集，而該數據集可能與臨床情境有所不同，從而導致學習偏差。

為了解決這一挑戰，我們引入了一種無監督的偽影消減方法，成功地免除了對乾淨影像真實標註的需求。所提出的「零樣本」醫學影像偽影消減（ZSAR）框架利用深度學習的力量，且不依賴通用預訓練網絡或任何乾淨影像參考。此外，我們還探討了一種弱監督偽影消減方法——「單一樣本」醫學影像偽影消減（OSAR），該方法僅需對測試影像中的噪聲進行少量標註，但能顯著改善影像品質與測試時間。

一旦低品質醫學影像經過去噪處理後，便可進一步通過下游應用網絡實現多種目標，例如疾病分類或腫瘤分割。然而，傳統的監督式醫學影像分割同樣存在類似限制，因為許多現有方法需要大量針對目標的真實標註（例如醫學影像中的腫瘤標註）。為解決這一問題，本論文提出了一種弱監督腦腫瘤分割方法——多出口注意力類別激活映射（AME-CAM），該方法利用腫瘤影像與正常影像之間的特徵差異來達成分割目標。

針對第二種方法中帶有無法消除噪聲的低品質醫學影像分割任務，我們提出了一種多集群對比學習（MCC）框架，這是一種半監督方法，既能降低標註需求，又能保持高分割效能。該方法利用對比損失來強化前景特徵提取，並透過多集群對比損失來充分利用每批次中多個已標註的真實標記，同時搭配錨點幀選擇演算法以提升分割效能。MCC框架透過降低標註需求（特別是在建立新數據集時），提升了分割的實用性，並促進了低品質心臟超聲視頻的高效分割。

本論文探討了低品質醫學影像分割任務中的挑戰，並提出了新穎的弱監督去噪與分割方法來應對這些問題。所提出的解決方案不僅降低了對大量標註的依賴，也提升了實用性與準確性，為更高效的低品質醫學影像分割鋪平了道路。

As medical images increasingly play crucial roles in disease assessment and symptom diagnosis, numerous researchers are dedicated to discovering efficient and faster methods to assist professionals in accurate and rapid diagnosis. Unfortunately, factors such as scan settings, machine conditions, and image reconstruction techniques can lead to artifacts and result in low-quality images, degrading diagnostic performance.

Low-quality image segmentation presents two distinct solution paths. The first approach involves applying a denoising method before segmentation, aiming to improve the image quality prior to the segmentation process. The second path focuses on directly segmenting low-quality images that may be challenging or impossible to denoise effectively.

In the first solution path, researchers have dedicated efforts to propose artifact reduction and denoising methods to remove noise. However, most existing denoising approaches operate within a supervised framework, requiring ground-truth for model training. They usually rely on simulations to generate the dataset for these methods, which may be different from clinical situation and lead to biased learning.

To overcome this challenge, an unsupervised artifact reduction approach is introduced that successfully eliminates the need for a clean image ground-truth. The proposed ``Zero-Shot'' medical image Artifact Reduction (ZSAR) framework leverages the power of deep learning without using general pre-trained networks or any clean image reference. Additionally, we explore a weakly-supervised artifact reduction approach, ``One-Shot'' medical image Artifact Reduction (OSAR), which requires minor annotation of noise on the test image but significantly improves image quality and test time.

Once low-quality medical images are denoised, they can be further processed by a downstream application network for different objectives, such as disease classification or tumor segmentation. However, a similar limitation exists for conventional supervised medical image segmentation, as many existing approaches require a large amount of annotated ground-truth for the target, such as annotated tumors on medical images. To address this issue, this thesis proposes a weakly-supervised brain tumor segmentation approach, Attentive Multiple-Exit CAM (AME-CAM), which utilizes the feature differences between tumor and normal images to achieve the segmentation goal.

When it comes to the second solution path, segmentation task on low-quality medical images with indelible noise, we propose a Multi-Cluster Contrastive (MCC) learning framework, a semi-supervised approach that minimizes annotation requirements while maintaining high segmentation performance. Leveraging contrastive loss to enhance foreground feature extraction, our method incorporates multi-cluster contrastive loss to utilize multiple annotated ground-truths per batch and an anchor frame selection algorithm to improve segmentation performance. The MCC framework enhances segmentation practicality by reducing annotation requirements, particularly for developing new datasets, and facilitates efficient segmentation of low-quality echocardiogram videos.

In this thesis, we examine the challenges in the segmentation task on low-quality medical images and propose novel weakly-supervised denoising and segmentation approaches to tackle these issues. The proposed solutions reduce the need for extensive annotations, enhance practicality, and improve accuracy, paving the way for more efficient low-quality medical image segmentation.

[1] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-cam: Visual explanations from deep networks via gradient-based localiza- tion,” in Proceedings of the IEEE international conference on computer vision, pp. 618–626, 2017.
[2] H. Wang, Z. Wang, M. Du, F. Yang, Z. Zhang, S. Ding, P. Mardziel, and X. Hu, “Score-cam: Score-weighted visual explanations for convolutional neural net- works,” in Proceedings of the IEEE/CVF conference on computer vision and pat- tern recognition workshops, pp. 24–25, 2020.
[3] K. H. Lee, C. Park, J. Oh, and N. Kwak, “Lfi-cam: learning feature importance for better visual explanation,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1355–1363, 2021.
[4] P.-T. Jiang, C.-B. Zhang, Q. Hou, M.-M. Cheng, and Y. Wei, “Layercam: Ex- ploring hierarchical class activation maps for localization,” IEEE Transactions on Image Processing, vol. 30, pp. 5875–5888, 2021.
[5] Z. Qian, K. Li, M. Lai, E. I.-C. Chang, B. Wei, Y. Fan, and Y. Xu, “Trans- former based multiple instance learning for weakly supervised histopathology image segmentation,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, Septem- ber 18–22, 2022, Proceedings, Part II, pp. 160–170, Springer, 2022.
[6] S. Dodge and L. Karam, “Understanding how image quality affects deep neu- ral networks,” in 2016 eighth international conference on quality of multimedia experience (QoMEX), pp. 1–6, IEEE, 2016.
[7] S.-C. Wen, Y.-J. Chen, Z. Liu, W. Wen, X. Xu, Y. Shi, T.-Y. Ho, Q. Jia, M. Huang, and J. Zhuang, “Do noises bother human and neural networks in the same way? a medical image analysis perspective,” in 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1166–1170, IEEE, 2020.
[8] E. Manson, V. A. Ampoh, E. Fiagbedzi, J. Amuasi, J. Flether, and C. Schandorf, “Image noise in radiography and tomography: Causes, effects and reduction tech- niques,” Curr. Trends Clin. Med. Imaging, vol. 2, no. 5, p. 555620, 2019.
[9] R. Patil and S. Bhosale, “Medical image denoising techniques: a review,” In- ternational Journal on Engineering, Science and Technology (IJonEST), vol. 4, no. 1, pp. 21–33, 2022.
[10] Y.-J. Chen, Y.-J. Chang, S.-C. Wen, Y. Shi, X. Xu, T.-Y. Ho, Q. Jia, M. Huang, and J. Zhuang, “Zero-shot medical image artifact reduction,” in 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), pp. 862–866, IEEE, 2020.
[11] Y.-J. Chen, Y.-J. Chang, S.-C. Wen, X. Xu, M. Huang, H. Yuan, J. Zhuang, Y. Shi, and T.-Y. Ho, ““one-shot” reduction of additive artifacts in medical images,” in 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 836–841, IEEE, 2021.
[12] Y.-J. Chen, X. Hu, Y. Shi, and T.-Y. Ho, “Ame-cam: Attentive multiple-exit cam for weakly supervised segmentation on mri brain tumor,” in Medical Image Com- puting and Computer Assisted Intervention – MICCAI 2023, (Cham), pp. 173– 182, Springer Nature Switzerland, 2023.
[13] T. Wang, J. Xiong, X. Xu, M. Jiang, H. Yuan, M. Huang, J. Zhuang, and Y. Shi, “Msu-net: Multiscale statistical u-net for real-time 3d cardiac mri video segmen- tation,” in MICCAI, pp. 614–622, Springer, 2019.
[14] Z. Liu, X. Xu, T. Liu, Q. Liu, Y. Wang, Y. Shi, W. Wen, M. Huang, H. Yuan, and J. Zhuang, “Machine vision guided 3d medical image compression for efficient transmission and accurate segmentation in the clouds,” in CVPR, pp. 12687– 12696, 2019.
[15] X. Xu, T. Wang, Y. Shi, H. Yuan, Q. Jia, M. Huang, and J. Zhuang, “Whole heart and great vessel segmentation in congenital heart disease using deep neural networks and graph matching,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 477–485, Springer, 2019.
[16] X. Xu, Q. Lu, L. Yang, S. Hu, D. Chen, Y. Hu, and Y. Shi, “Quantization of fully convolutional networks for accurate biomedical image segmentation,” in CVPR, pp. 8300–8308, 2018.
[17] X. Xu, T. Wang, D. Zeng, Y. Shi, Q. Jia, H. Yuan, M. Huang, and J. Zhuang, “Ac- curate congenital heart disease model generation for 3d printing,” Proc. of IEEE International Workshop in Signal Processing Systems, Nanjing, China, 2019.
[18] Q. Yang, P. Yan, Y. Zhang, H. Yu, Y. Shi, X. Mou, M. K. Kalra, Y. Zhang, L. Sun, and G. Wang, “Low dose ct image denoising using a generative adversar- ial network with wasserstein distance and perceptual loss,” IEEE transactions on medical imaging, 2018.
[19] D. Jiang, W. Dou, L. Vosters, X. Xu, Y. Sun, and T. Tan, “Denoising of 3d mag- netic resonance images with multi-channel residual learning of convolutional neural network,” Japanese journal of radiology, vol. 36, no. 9, pp. 566–574, 2018.
[20] N. Yuan, J. Zhou, and J. Qi, “Low-dose ct image denoising without high-dose ref- erence images,” in IMF3DIRRNM, vol. 11072, p. 110721C, International Society for Optics and Photonics, 2019.
[21] X. Yi and P. Babyn, “Sharpness-aware low-dose ct denoising using conditional generative adversarial network,” Journal of digital imaging, vol. 31, no. 5, pp. 655–669, 2018.
[22] J. Veraart, D. S. Novikov, D. Christiaens, B. Ades-Aron, J. Sijbers, and E. Fiere- mans, “Denoising of diffusion mri using random matrix theory,” NeuroImage, vol. 142, pp. 394–406, 2016.
[23] E. Kang, H. J. Koo, D. H. Yang, J. B. Seo, and J. C. Ye, “Cycle consistent adver- sarial denoising network for multiphase coronary ct angiography,” arXiv preprint arXiv:1806.09748, 2018.
[24] M. Zaitsev, J. Maclaren, and M. Herbst, “Motion artifacts in mri: a complex problem with many partial solutions,” Journal of Magnetic Resonance Imaging, vol. 42, no. 4, pp. 887–901, 2015.
[25] K. Dabov, A. Foi, and K. Egiazarian, “Video denoising by sparse 3d transform- domain collaborative filtering,” in ESPC, pp. 145–149, IEEE, 2007.
[26] F. E. Boas and D. Fleischmann, “Ct artifacts: causes and reduction techniques,” Imaging Med, vol. 4, no. 2, pp. 229–240, 2012.
[27] K. Krupa and M. Bekiesin´ska-Figatowska, “Artifacts in magnetic resonance imaging,” Polish journal of radiology, vol. 80, p. 93, 2015.
[28] D. Ulyanov, A. Vedaldi, and V. Lempitsky, “Deep image prior,” in CVPR, pp. 9446–9454, 2018.
[29] H. Chen, Y. Zhang, M. K. Kalra, F. Lin, Y. Chen, P. Liao, J. Zhou, and G. Wang, “Low-dose ct with a residual encoder-decoder convolutional neural network,” IEEE transactions on medical imaging, vol. 36, no. 12, pp. 2524–2535, 2017.
[30] E. Kang, J. Min, and J. C. Ye, “A deep convolutional neural network using direc- tional wavelets for low-dose x-ray ct reconstruction,” Medical physics, vol. 44, no. 10, 2017.
[31] J. M. Wolterink, T. Leiner, M. A. Viergever, and I. Isˇgum, “Generative adversar- ial networks for noise reduction in low-dose ct,” IEEE transactions on medical imaging, vol. 36, no. 12, pp. 2536–2545, 2017.
[32] J. V. Manjo´n and P. Coupe, “Mri denoising using deep learning,” in International Workshop on Patch-based Techniques in Medical Imaging, pp. 12–19, Springer, 2018.
[33] L. Gjesteby, Q. Yang, Y. Xi, B. Claus, Y. Jin, B. De Man, and G. Wang, “Re- ducing metal streak artifacts in ct images via deep learning: Pilot results,” in The 14th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine, pp. 611–614, 2017.
[34] Y. Zhang and H. Yu, “Convolutional neural network based metal artifact reduc- tion in x-ray computed tomography,” IEEE transactions on medical imaging, vol. 37, no. 6, pp. 1370–1381, 2018.
[35] C. You, Y. Zhang, X. Zhang, G. Li, S. Ju, Z. Zhao, Z. Zhang, W. Cong, P. K. Saha, and G. Wang, “Ct super-resolution gan constrained by the identical, residual, and cycle learning ensemble (gan-circle),” arXiv preprint arXiv:1808.04256, 2018.
[36] F. Khader, G. Mu¨ller-Franzes, S. Tayebi Arasteh, T. Han, C. Haarburger, M. Schulze-Hagen, P. Schad, S. Engelhardt, B. Baeßler, S. Foersch, et al., “Denoising diffusion probabilistic models for 3d medical image generation,” Scien- tific Reports, vol. 13, no. 1, p. 7303, 2023.
[37] H. Jiang, M. Imran, L. Ma, T. Zhang, Y. Zhou, M. Liang, K. Gong, and W. Shao, “Fast-ddpm: Fast denoising diffusion probabilistic models for medical image-to- image generation,” arXiv preprint arXiv:2405.14802, 2024.
[38] M. Safari, X. Yang, A. Fatemi, and L. Archambault, “Mri motion artifact re- duction using a conditional diffusion probabilistic model (mar-cdpm),” Medical physics, vol. 51, no. 4, pp. 2598–2610, 2024.
[39] L. Pfaff, F. Wagner, N. Vysotskaya, M. Thies, N. Maul, S. Mei, T. Wuerfl, and A. Maier, “No-new-denoiser: A critical analysis of diffusion models for medical image denoising,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 568–578, Springer, 2024.
[40] A. Fahim, A. Salem, F. A. Torkey, and M. Ramadan, “An efficient enhanced k- means clustering algorithm,” Journal of Zhejiang University-Science A, vol. 7, no. 10, pp. 1626–1633, 2006.
[41] F. L. Goerner and G. D. Clarke, “Measuring signal-to-noise ratio in partially parallel imaging mri,” Medical physics, vol. 38, no. 9, pp. 5049–5057, 2011.
[42] P. Kellman and E. R. McVeigh, “Image reconstruction in snr units: a general method for snr measurement,” MRM, vol. 54, no. 6, pp. 1439–1447, 2005.
[43] N. Rajalakshmi, K. Narayanan, and P. Amudhavalli, “Wavelet based weighted median filter for image denoising of mri brain images,” IJEECS, vol. 10, no. 1, pp. 201–206, 2018.
[44] X. Glorot and Y. Bengio, “Understanding the difficulty of training deep feedfor- ward neural networks,” in ICAIS, pp. 249–256, 2010.
[45] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
[46] K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, “Image denoising with block- matching and 3d filtering,” in Image processing: algorithms and systems, neural networks, and machine learning, vol. 6064, pp. 354–365, SPIE, 2006.
[47] A. Buades, B. Coll, and J.-M. Morel, “A non-local algorithm for image denois- ing,” in 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), vol. 2, pp. 60–65, Ieee, 2005.
[48] J. Lehtinen, J. Munkberg, J. Hasselgren, S. Laine, T. Karras, M. Aittala, and T. Aila, “Noise2noise: Learning image restoration without clean data,” arXiv preprint arXiv:1803.04189, 2018.
[49] D. Wu, K. Gong, K. Kim, X. Li, and Q. Li, “Consensus neural network for medical imaging denoising with only noisy training samples,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 741–749, Springer, 2019.
[50] R. Qian, R. T. Tan, W. Yang, J. Su, and J. Liu, “Attentive generative adversarial network for raindrop removal from a single image,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2482–2491, 2018.
[51] J. Wolleb, F. Bieder, R. Sandku¨hler, and P. C. Cattin, “Diffusion models for med- ical anomaly detection,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, Septem- ber 18–22, 2022, Proceedings, Part VIII, pp. 35–45, Springer, 2022.
[52] L. Chan, M. S. Hosseini, and K. N. Plataniotis, “A comprehensive analysis of weakly-supervised semantic segmentation in different image domains,” Interna- tional Journal of Computer Vision, vol. 129, pp. 361–384, 2021.
[53] Y. Wang, J. Zhang, M. Kan, S. Shan, and X. Chen, “Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation,” in Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12275–12284, 2020.
[54] J. Xie, J. Xiang, J. Chen, X. Hou, X. Zhao, and L. Shen, “C2am: Contrastive learning of class-agnostic activation map for weakly supervised object localiza- tion and semantic segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 989–998, 2022.
[55] F. Yu, V. Koltun, and T. Funkhouser, “Dilated residual networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 472–480, 2017.
[56] S. Belharbi, A. Sarraf, M. Pedersoli, I. Ben Ayed, L. McCaffrey, and E. Granger, “F-cam: Full resolution class activation maps via guided parametric upscaling,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 3490–3499, 2022.
[57] A. Englebert, O. Cornu, and C. De Vleeschouwer, “Poly-cam: High resolu- tion class activation map for convolutional neural networks,” arXiv preprint arXiv:2204.13359, 2022.
[58] T. Tagaris, M. Sdraka, and A. Stafylopatis, “High-resolution class activation mapping,” in 2019 IEEE international conference on image processing (ICIP), pp. 4514–4518, IEEE, 2019.
[59] B. H. Menze, A. Jakab, S. Bauer, J. Kalpathy-Cramer, K. Farahani, J. Kirby, Y. Burren, N. Porz, J. Slotboom, R. Wiest, et al., “The multimodal brain tumor image segmentation benchmark (brats),” IEEE transactions on medical imaging, vol. 34, no. 10, pp. 1993–2024, 2014.
[60] S. Bakas, H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J. S. Kirby, J. B. Frey- mann, K. Farahani, and C. Davatzikos, “Advancing the cancer genome atlas glioma mri collections with expert segmentation labels and radiomic features,” Scientific data, vol. 4, no. 1, pp. 1–13, 2017.
[61] S. Bakas, M. Reyes, A. Jakab, S. Bauer, M. Rempfler, A. Crimi, R. T. Shinohara, C. Berger, S. M. Ha, M. Rozycki, et al., “Identifying the best machine learn- ing algorithms for brain tumor segmentation, progression assessment, and over- all survival prediction in the brats challenge,” arXiv preprint arXiv:1811.02629, 2018.
[62] B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, “Learning deep features for discriminative localization,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2921–2929, 2016.
[63] D. Omeiza, S. Speakman, C. Cintas, and K. Weldermariam, “Smooth grad- cam++: An enhanced inference level visualization technique for deep convo- lutional neural network models,” arXiv preprint arXiv:1908.01224, 2019.
[64] H. G. Ramaswamy et al., “Ablation-cam: Visual explanations for deep convolu- tional network via gradient-free localization,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 983–991, 2020.
[65] H.-G. Nguyen, A. Pica, J. Hrbacek, D. C. Weber, F. La Rosa, A. Schalenbourg, R. Sznitman, and M. B. Cuadra, “A novel segmentation framework for uveal melanoma in magnetic resonance imaging based on class activation maps,” in International Conference on Medical Imaging with Deep Learning, pp. 370–379, PMLR, 2019.
[66] H. Kang, H.-m. Park, Y. Ahn, A. Van Messem, and W. De Neve, “Towards a quantitative analysis of class activation mapping for deep learning-based computer-aided diagnosis,” in Medical Imaging 2021: Image Perception, Ob- server Performance, and Technology Assessment, vol. 11599, p. 115990M, Inter- national Society for Optics and Photonics, 2021.
[67] X. Zhang, Y. Wei, J. Feng, Y. Yang, and T. S. Huang, “Adversarial complemen- tary learning for weakly supervised object localization,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1325–1334, 2018.
[68] W. Tang, H. Kang, Y. Cao, P. Yu, H. Han, R. Zhang, and K. Chen, “M-seam-nam: Multi-instance self-supervised equivalent attention mechanism with neighbor- hood affinity module for double weakly supervised segmentation of covid-19,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 262–272, Springer, 2021.
[69] R. Li, Z. Mai, C. Trabelsi, Z. Zhang, J. Jang, and S. Sanner, “Transcam: Trans- former attention-based cam refinement for weakly supervised semantic segmen- tation,” arXiv preprint arXiv:2203.07239, 2022.
[70] P. Kra¨henbu¨hl and V. Koltun, “Efficient inference in fully connected crfs with gaussian edge potentials,” Advances in neural information processing systems, vol. 24, 2011.
[71] R. Dey and Y. Hong, “Asc-net: Adversarial-based selective network for unsu- pervised anomaly segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 236–247, Springer, 2021.
[72] P. Khosla, P. Teterwak, C. Wang, A. Sarna, Y. Tian, P. Isola, A. Maschinot, C. Liu, and D. Krishnan, “Supervised contrastive learning,” arXiv preprint arXiv:2004.11362, 2020.
[73] J. Chen and E. C. Frey, “Medical image segmentation via unsupervised convolu- tional neural network,” arXiv preprint arXiv:2001.10155, 2020.
[74] M. Futrega, A. Milesi, M. Marcinkiewicz, and P. Ribalta, “Optimized u-net for brain tumor segmentation,” arXiv preprint arXiv:2110.03352, 2021.
[75] J. A. Noble and D. Boukerroui, “Ultrasound image segmentation: a survey,” IEEE Transactions on medical imaging, vol. 25, no. 8, pp. 987–1010, 2006.
[76] G. Zamzmi, S. Rajaraman, L.-Y. Hsu, V. Sachdev, and S. Antani, “Real-time echocardiography image analysis and quantification of cardiac indices,” Medical image analysis, vol. 80, p. 102438, 2022.
[77] E. Evain, Y. Sun, K. Faraz, D. Garcia, E. Saloux, B. L. Gerber, M. De Craene, and O. Bernard, “Motion estimation by deep learning in 2d echocardiography: synthetic dataset and validation,” IEEE transactions on medical imaging, vol. 41, no. 8, pp. 1911–1924, 2022.
[78] C. Shen, H. Zhu, Y. Zhou, Y. Liu, S. Yi, L. Dong, W. Zhao, D. J. Brady, X. Cao, Z. Ma, et al., “Continuous 3d myocardial motion tracking via echocardiography,” IEEE Transactions on Medical Imaging, 2024.
[79] D. Ouyang, B. He, A. Ghorbani, N. Yuan, J. Ebinger, C. P. Langlotz, P. A. Hei- denreich, R. A. Harrington, D. H. Liang, E. A. Ashley, et al., “Video-based ai for beat-to-beat assessment of cardiac function,” Nature, vol. 580, no. 7802, pp. 252– 256, 2020.
[80] M. Li, D. Zeng, Q. Xie, R. Xu, Y. Wang, D. Ma, Y. Shi, X. Xu, M. Huang, and H. Fei, “A deep learning approach with temporal consistency for automatic myocardial segmentation of quantitative myocardial contrast echocardiography,” The International Journal of Cardiovascular Imaging, vol. 37, pp. 1967–1978, 2021.
[81] Y. Wang, Z. Xu, X. Wang, C. Shen, B. Cheng, H. Shen, and H. Xia, “End-to-end video instance segmentation with transformers,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 8741–8750, 2021.
[82] A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A. C. Berg, W.-Y. Lo, et al., “Segment anything,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4015–4026, 2023.
[83] Y. Li, K. Hong, X. Shi, W. Pang, Y. Xiao, P. Zhao, D. Xu, C. Song, X. Zhou, and Y. Zhou, “A deep learning based approach for automatic cardiac events identifi- cation,” Biomedical Signal Processing and Control, vol. 100, p. 107164, 2025.
[84] H. Wu, J. Liu, F. Xiao, Z. Wen, L. Cheng, and J. Qin, “Semi-supervised seg- mentation of echocardiography videos via noise-resilient spatiotemporal seman- tic calibration and fusion,” Medical Image Analysis, vol. 78, p. 102397, 2022.
[85] J. Yang, X. Ding, Z. Zheng, X. Xu, and X. Li, “Graphecho: Graph-driven unsupervised domain adaptation for echocardiogram video segmentation,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 11878–11887, 2023.
[86] N. Painchaud, N. Duchateau, O. Bernard, and P.-M. Jodoin, “Echocardiography segmentation with enforced temporal consistency,” IEEE Transactions on Medi- cal Imaging, vol. 41, no. 10, pp. 2867–2878, 2022.
[87] W. Xue, H. Cao, J. Ma, T. Bai, T. Wang, and D. Ni, “Improved segmentation of echocardiography with orientation-congruency of optical flow and motion- enhanced segmentation,” IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 12, pp. 6105–6115, 2022.
[88] H. Wei, J. Ma, Y. Zhou, W. Xue, and D. Ni, “Co-learning of appearance and shape for precise ejection fraction estimation from echocardiographic sequences,” Med- ical Image Analysis, vol. 84, p. 102686, 2023.
[89] H. Wei, H. Cao, Y. Cao, Y. Zhou, W. Xue, D. Ni, and S. Li, “Temporal- consistent segmentation of echocardiography with co-learning from appearance and shape,” in Medical Image Computing and Computer Assisted Intervention– MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part II 23, pp. 623–632, Springer, 2020.
[90] R. Gu, J. Zhang, G. Wang, W. Lei, T. Song, X. Zhang, K. Li, and S. Zhang, “Contrastive semi-supervised learning for domain adaptive segmentation across similar anatomical structures,” IEEE Transactions on Medical Imaging, vol. 42, no. 1, pp. 245–256, 2022.
[91] Y. Zhao, K. Liao, Y. Zheng, X. Zhou, and X. Guo, “Boundary attention with multi-task consistency constraints for semi-supervised 2d echocardiography seg- mentation,” Computers in Biology and Medicine, p. 108100, 2024.
[92] C.-J. Chao, Y. Gu, T. Xiang, L. Appari, J. Wu, J. M. Farina, R. Wraith, J. Jeong, R. Arsanjani, K. C. Garvan, et al., “Comparative eminence: Foundation versus domain-specific model for cardiac ultrasound segmentation,” medRxiv, pp. 2023– 09, 2023.
[93] N. J. B. Dias, G. T. Laureano, and R. M. Da Costa, “Keyframe selection for visual localization and mapping tasks: A systematic literature review,” Robotics, vol. 12, no. 3, p. 88, 2023.
[94] H. Wang and C. Schmid, “Action recognition with improved trajectories,” in Pro- ceedings of the IEEE international conference on computer vision, pp. 3551– 3558, 2013.
[95] S. Leclerc, E. Smistad, J. Pedrosa, A. Østvik, F. Cervenansky, F. Espinosa, T. Es- peland, E. A. R. Berg, P.-M. Jodoin, T. Grenier, et al., “Deep learning for segmen- tation using an open large-scale dataset in 2d echocardiography,” IEEE transac- tions on medical imaging, vol. 38, no. 9, pp. 2198–2210, 2019.
[96] Y. Ali, F. Janabi-Sharifi, and S. Beheshti, “Echocardiographic image segmen- tation using deep res-u network,” Biomedical Signal Processing and Control, vol. 64, p. 102248, 2021.
[97] M. J. Mortada, S. Tomassini, H. Anbar, M. Morettini, L. Burattini, and A. Sbrollini, “Segmentation of anatomical structures of the left heart from echocardiographic images using deep learning,” Diagnostics, vol. 13, no. 10, p. 1683, 2023.
[98] S. Ono, M. Komatsu, A. Sakai, H. Arima, M. Ochida, R. Aoyama, S. Yasutomi, K. Asada, S. Kaneko, T. Sasano, et al., “Automated endocardial border detec- tion and left ventricular functional assessment in echocardiography using deep learning,” Biomedicines, vol. 10, no. 5, p. 1082, 2022.
[99] G.-Q. Zhou, W.-B. Zhang, Z.-Q. Shi, Z.-R. Qi, K.-N. Wang, H. Song, J. Yao, and Y. Chen, “Dsanet: Dual-branch shape-aware network for echocardiography seg- mentation in apical views,” IEEE Journal of Biomedical and Health Informatics, 2023.
[100] H. Huang, Z. Ge, H. Wang, J. Wu, C. Hu, N. Li, X. Wu, and C. Pan, “Segmen- tation of echocardiography based on deep learning model,” Electronics, vol. 11, no. 11, p. 1714, 2022.
[101] M. Balasubramani, C.-W. Sung, M.-Y. Hsieh, E. P.-C. Huang, J.-S. Shieh, and M. F. Abbod, “Automated left ventricle segmentation in echocardiography using yolo: A deep learning approach for enhanced cardiac function assessment,” Electronics, vol. 13, no. 13, p. 2587, 2024.
[102] G. F. Cacao, D. Du, and N. Nair, “Unsupervised image segmentation on 2d echocardiogram,” Algorithms, vol. 17, no. 11, p. 515, 2024.
[103] Y. Chen, X. Zhang, C. M. Haggerty, and J. V. Stough, “Assessing the generaliz- ability of temporally coherent echocardiography video segmentation,” in Medical Imaging 2021: Image Processing, vol. 11596, pp. 463–469, SPIE, 2021.
[104] M. C. El Rai, M. Darweesh, and M. Al-Saad, “Semi-supervised segmentation of echocardiography videos using graph signal processing,” Electronics, vol. 11, no. 21, p. 3462, 2022.
[105] F. Maani, A. Ukaye, N. Saadi, N. Saeed, and M. Yaqub, “Simlvseg: Simpli- fying left ventricular segmentation in 2-d+ time echocardiograms with self-and weakly supervised learning,” Ultrasound in Medicine & Biology, vol. 50, no. 12, pp. 1945–1954, 2024.
[106] Y. Wan, D. Li, Z. Li, J. Bu, M. Tong, R. Luo, B. Yue, and S. Yu, “A semi- supervised four-chamber echocardiographic video segmentation algorithm based on multilevel edge perception and calibration fusion,” Ultrasound in Medicine & Biology, 2024.
[107] J. Lin, W. Xie, L. Kang, and H. Wu, “Dynamic-guided spatiotemporal attention for echocardiography video segmentation,” IEEE Transactions on Medical Imag- ing, 2024.
[108] D. Bhattacharya, K. Reuter, F. Behrendt, L. Maack, S. Grube, and A. Schlaefer, “Polypnextlstm: a lightweight and fast polyp video segmentation network using convnext and convlstm,” International journal of computer assisted radiology and surgery, vol. 19, no. 10, pp. 2111–2119, 2024.
[109] M. Li, W. Zhang, G. Yang, C. Wang, H. Zhang, H. Liu, W. Zheng, and S. Li, “Re- current aggregation learning for multi-view echocardiographic sequences seg- mentation,” in Medical Image Computing and Computer Assisted Intervention– MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13– 17, 2019, Proceedings, Part II 22, pp. 678–686, Springer, 2019.
[110] H. Reynaud, A. Vlontzos, B. Hou, A. Beqiri, P. Leeson, and B. Kainz, “Ul- trasound video transformers for cardiac ejection fraction estimation,” in Medi- cal Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part VI 24, pp. 495–505, Springer, 2021.
[111] S. Yang, X. Wang, Y. Li, Y. Fang, J. Fang, W. Liu, X. Zhao, and Y. Shan, “Tem- porally efficient vision transformer for video instance segmentation,” in Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2885–2895, 2022.
[112] Q. Liu, L. Yu, L. Luo, Q. Dou, and P. A. Heng, “Semi-supervised medical image classification with relation-driven self-ensembling model,” IEEE transactions on medical imaging, vol. 39, no. 11, pp. 3429–3440, 2020.
[113] G. Wang, X. Liu, C. Li, Z. Xu, J. Ruan, H. Zhu, T. Meng, K. Li, N. Huang, and S. Zhang, “A noise-robust framework for automatic segmentation of covid- 19 pneumonia lesions from ct images,” IEEE Transactions on Medical Imaging, vol. 39, no. 8, pp. 2653–2663, 2020.
[114] B. Li, Y. Wang, Y. Xu, and C. Wu, “Dsst: A dual student model guided student– teacher framework for semi-supervised medical image segmentation,” Biomedi- cal Signal Processing and Control, vol. 90, p. 105890, 2024.
[115] F. Rajiˇc, L. Ke, Y.-W. Tai, C.-K. Tang, M. Danelljan, and F. Yu, “Segment anything meets point tracking,” arXiv preprint arXiv:2307.01197, 2023.