no code implementations • 19 Dec 2023 • Fahim Ahmed Zaman, Mathews Jacob, Amanda Chang, Kan Liu, Milan Sonka, Xiaodong Wu
Diffusion models have shown impressive performance for image generation, often times outperforming other generative models.
2 code implementations • 29 Nov 2023 • Yaopeng Peng, Milan Sonka, Danny Z. Chen
We evaluate our method on several public medical image segmentation datasets for skin lesion segmentation and polyp segmentation, and the experimental results demonstrate the segmentation accuracy of our new method over state-of-the-art methods, while preserving memory and computational efficiency.
1 code implementation • 28 Nov 2023 • Yaopeng Peng, Hongxiao Wang, Milan Sonka, Danny Z. Chen
The PH module is lightweight and capable of integrating topological features into any CNN or Transformer architectures in an end-to-end fashion.
no code implementations • 25 Oct 2023 • Fahim Ahmed Zaman, Xiaodong Wu, Weiyu Xu, Milan Sonka, Raghuraman Mudumbai
We describe a method for verifying the output of a deep neural network for medical image segmentation that is robust to several classes of random as well as worst-case perturbations i. e. adversarial attacks.
1 code implementation • 14 May 2023 • Dixian Zhu, Bokun Wang, Zhi Chen, Yaxing Wang, Milan Sonka, Xiaodong Wu, Tianbao Yang
This paper considers a novel application of deep AUC maximization (DAM) for multi-instance learning (MIL), in which a single class label is assigned to a bag of instances (e. g., multiple 2D slices of a CT scan for a patient).
no code implementations • 11 Mar 2021 • Kyungmoo Lee, Alexis K. Warren, Michael D. Abramoff, Andreas Wahle, S. Scott Whitmore, Ian C. Han, John H. Fingert, Todd E. Scheetz, Robert F. Mullins, Milan Sonka, Elliott H. Sohn
New Method: Eighty macular SDOCT volumes from 80 patients were obtained using the Zeiss Cirrus machine.
4 code implementations • ICCV 2021 • Zhuoning Yuan, Yan Yan, Milan Sonka, Tianbao Yang
Our studies demonstrate that the proposed DAM method improves the performance of optimizing cross-entropy loss by a large margin, and also achieves better performance than optimizing the existing AUC square loss on these medical image classification tasks.
Ranked #2 on Multi-Label Classification on CheXpert
no code implementations • 10 Sep 2020 • Shakib Yazdani, Shervin Minaee, Rahele Kafieh, Narges Saeedizadeh, Milan Sonka
We also provide a visualization of the attention maps of the model for several test images, and show that our model is attending to the infected regions as intended.
1 code implementation • 24 Jul 2020 • Narges Saeedizadeh, Shervin Minaee, Rahele Kafieh, Shakib Yazdani, Milan Sonka
Through experimental results on a relatively large-scale CT segmentation dataset of around 900 images, we show that adding this new regularization term leads to 2\% gain on overall segmentation performance compared to the U-Net model.
no code implementations • 21 Jun 2020 • Zhihui Guo, Honghai Zhang, Zhi Chen, Ellen van der Plas, Laurie Gutmann, Daniel Thedens, Peggy Nopoulos, Milan Sonka
Automated segmentation of individual calf muscle compartments from 3D magnetic resonance (MR) images is essential for developing quantitative biomarkers for muscular disease progression and its prediction.
1 code implementation • 20 Apr 2020 • Shervin Minaee, Rahele Kafieh, Milan Sonka, Shakib Yazdani, Ghazaleh Jamalipour Soufi
In this work, we propose a model based on sentence Transformer to detect the main topics of Tweets in recent months.
no code implementations • 25 Mar 2019 • Zhihui Guo, Junjie Bai, Yi Lu, Xin Wang, Kunlin Cao, Qi Song, Milan Sonka, Youbing Yin
The proposed method generates well-positioned centerlines, exhibiting lower number of missing branches and is more robust in the presence of minor imperfections of the object segmentation mask.
no code implementations • 10 Mar 2019 • Satyananda Kashyap, Ipek Oguz, Honghai Zhang, Milan Sonka
We present a fully automated learning-based approach for segmenting knee cartilage in the presence of osteoarthritis (OA).
no code implementations • 10 Mar 2019 • Satyananda Kashyap, Honghai Zhang, Karan Rao, Milan Sonka
4D LOGISMOS validation on 108 MRIs from baseline and 12 month follow-up scans of 54 patients showed a significant reduction in segmentation errors (\emph{p}$<$0. 01) compared to 3D.
no code implementations • 10 Mar 2019 • Satyananda Kashyap, Honghai Zhang, Milan Sonka
State-of-the-art automated segmentation algorithms are not 100\% accurate especially when segmenting difficult to interpret datasets like those with severe osteoarthritis (OA).
no code implementations • 25 Jan 2018 • Zhihui Guo, Ling Zhang, Le Lu, Mohammadhadi Bagheri, Ronald M. Summers, Milan Sonka, Jianhua Yao
The cost for each node of the graph is determined by the UNet probability maps.
no code implementations • CVPR 2017 • Hossam Isack, Olga Veksler, Ipek Oguz, Milan Sonka, Yuri Boykov
We propose an effective optimization algorithm for a general hierarchical segmentation model with geometric interactions between segments.
no code implementations • CVPR 2016 • Hossam Isack, Olga Veksler, Milan Sonka, Yuri Boykov
In contrast to star-convexity, the tightness of our normal constraint can be changed giving better control over allowed shapes.
no code implementations • 11 Dec 2013 • Raheleh Kafieh, Hossein Rabbani, Fedra Hajizadeh, Michael D. Abramoff, Milan Sonka
This study was conducted to determine the thickness map of eleven retinal layers in normal subjects by spectral domain optical coherence tomography (SD-OCT) and evaluate their association with sex and age.