no code implementations • 8 May 2024 • Takumi Okuo, Kazuya Nishimura, Hiroaki Ito, Kazuhiro Terada, Akihiko Yoshizawa, Ryoma Bise
The PD-L1 rate, the number of PD-L1 positive tumor cells over the total number of all tumor cells, is an important metric for immunotherapy.
no code implementations • 20 Mar 2024 • Kaito Shiku, Hiromitsu Shirai, Takeshi Ishihara, Ryoma Bise
Second, we propose a pairwise detection method, which uses the information of detection results at the previous frame for detecting cells at the current frame.
1 code implementation • 20 Mar 2024 • Kaito Shiku, Shinnosuke Matsuo, Daiki Suehiro, Ryoma Bise
Existing MIL methods are unsuitable for LML due to aggregating confidences, which may lead to inconsistency between the bag-level label and the label obtained by counting the number of instances for each class.
no code implementations • ICCV 2023 • Takanori Asanomi, Shinnosuke Matsuo, Daiki Suehiro, Ryoma Bise
In this paper, we propose a bag-level data augmentation method for LLP called MixBag, based on the key observation from our preliminary experiments; that the instance-level classification accuracy improves as the number of labeled bags increases even though the total number of instances is fixed.
1 code implementation • 9 Jul 2023 • Kazuya Nishimura, Ami Katanaya, Shinichiro Chuma, Ryoma Bise
First, we generate an image pair not containing mitosis events by frame-order flipping.
no code implementations • 26 Apr 2023 • Xiaoqing Liu, Kengo Araki, Shota Harada, Akihiko Yoshizawa, Kazuhiro Terada, Mariyo Kurata, Naoki Nakajima, Hiroyuki Abe, Tetsuo Ushiku, Ryoma Bise
The domain shift in pathological segmentation is an important problem, where a network trained by a source domain (collected at a specific hospital) does not work well in the target domain (from different hospitals) due to the different image features.
no code implementations • 26 Apr 2023 • Xiaoqing Liu, Kenji Ono, Ryoma Bise
The development of medical image segmentation using deep learning can significantly support doctors' diagnoses.
1 code implementation • 9 Mar 2023 • Hyeonwoo Cho, Kazuya Nishimura, Kazuhide Watanabe, Ryoma Bise
In particular, cells are cultured under different conditions depending on the purpose of the research.
no code implementations • 2 Mar 2023 • Shota Harada, Ryoma Bise, Kengo Araki, Akihiko Yoshizawa, Kazuhiro Terada, Mariyo Kurata, Naoki Nakajima, Hiroyuki Abe, Tetsuo Ushiku, Seiichi Uchida
Semi-supervised domain adaptation is a technique to build a classifier for a target domain by modifying a classifier in another (source) domain using many unlabeled samples and a small number of labeled samples from the target domain.
1 code implementation • 17 Feb 2023 • Shinnosuke Matsuo, Ryoma Bise, Seiichi Uchida, Daiki Suehiro
This paper proposes a novel and efficient method for Learning from Label Proportions (LLP), whose goal is to train a classifier only by using the class label proportions of instance sets, called bags.
no code implementations • 5 Aug 2022 • Takeaki Kadota, Hideaki Hayashi, Ryoma Bise, Kiyohito Tanaka, Seiichi Uchida
This paper proposes a deep Bayesian active-learning-to-rank, which trains a Bayesian convolutional neural network while automatically selecting appropriate pairs for relative annotation.
no code implementations • 6 Nov 2021 • Shota Harada, Ryoma Bise, Hideaki Hayashi, Kiyohito Tanaka, Seiichi Uchida
Ulcerative colitis (UC) classification, which is an important task for endoscopic diagnosis, involves two main difficulties.
no code implementations • 19 Aug 2021 • Kengo Araki, Mariyo Rokutan-Kurata, Kazuhiro Terada, Akihiko Yoshizawa, Ryoma Bise
Pathological diagnosis is used for examining cancer in detail, and its automation is in demand.
1 code implementation • 20 Jul 2021 • Kazuma Fujii, Daiki Suehiro, Kazuya Nishimura, Ryoma Bise
Our proposed method takes a pseudo labeling approach for cell detection from imperfect annotated data.
2 code implementations • 19 Jul 2021 • Hyeonwoo Cho, Kazuya Nishimura, Kazuhide Watanabe, Ryoma Bise
We propose an unsupervised domain adaptation method for cell detection using the pseudo-cell-position heatmap, where a cell centroid becomes a peak with a Gaussian distribution in the map.
1 code implementation • 19 Jul 2021 • Kazuya Nishimura, Hyeonwoo Cho, Ryoma Bise
This annotation is a time-consuming and labor-intensive task.
1 code implementation • ECCV 2020 • Kazuya Nishimura, Junya Hayashida, Chenyang Wang, Dai Fei Elmer Ker, Ryoma Bise
We propose a weakly-supervised cell tracking method that can train a convolutional neural network (CNN) by using only the annotation of "cell detection" (i. e., the coordinates of cell positions) without association information, in which cell positions can be easily obtained by nuclear staining.
no code implementations • ECCV 2020 • Hiroki Tokunaga, Brian Kenji Iwana, Yuki Teramoto, Akihiko Yoshizawa, Ryoma Bise
We propose a weakly-supervised cell tracking method that can train a convolutional neural network (CNN) by using only the annotation of "cell detection" (i. e., the coordinates of cell positions) without association information, in which cell positions can be easily obtained by nuclear staining.
3 code implementations • 27 Apr 2020 • Kazuya Nishimura, Ryoma Bise
In this paper, we propose a novel mitosis detection method that can detect multiple mitosis events in a candidate sequence and mitigate the human annotation gap via estimating a spatiotemporal likelihood map by 3DCNN.
3 code implementations • CVPR 2020 • Junya Hayashida, Kazuya Nishimura, Ryoma Bise
Conventional cell tracking methods detect multiple cells in each frame (detection) and then associate the detection results in successive time-frames (association).
1 code implementation • 29 Nov 2019 • Kazuya Nishimura, Dai Fei Elmer Ker, Ryoma Bise
In addition, we demonstrated that our method can perform without any annotation by using fluorescence images that cell nuclear were stained as training data.
Cell Segmentation Cultural Vocal Bursts Intensity Prediction +2
no code implementations • CVPR 2019 • Hiroki Tokunaga, Yuki Teramoto, Akihiko Yoshizawa, Ryoma Bise
A key assumption is that the importance of the magnifications depends on the characteristics of the input image, such as cancer subtypes.
no code implementations • 22 Sep 2017 • Qiuyu Chen, Ryoma Bise, Lin Gu, Yinqiang Zheng, Imari Sato, Jenq-Neng Hwang, Nobuaki Imanishi, Sadakazu Aiso
We propose a fully automatic system to reconstruct and visualize 3D blood vessels in Augmented Reality (AR) system from stereo X-ray images with bones and body fat.
no code implementations • CVPR 2017 • Mihoko Shimano, Hiroki Okawa, Yuta Asano, Ryoma Bise, Ko Nishino, Imari Sato
We derive an analytical spectral appearance model of wet surfaces that expresses the characteristic spectral sharpening due to multiple scattering and absorption in the surface.