no code implementations • 20 Sep 2022 • Thomas Buddenkotte, Lorena Escudero Sanchez, Mireia Crispin-Ortuzar, Ramona Woitek, Cathal McCague, James D. Brenton, Ozan Öktem, Evis Sala, Leonardo Rundo
On the contrary, we propose a scalable and intuitive framework to calibrate ensembles of deep learning models to produce uncertainty quantification measurements that approximate the classification probability.
no code implementations • 31 Oct 2021 • Michael Yeung, Leonardo Rundo, Evis Sala, Carola-Bibiane Schönlieb, Guang Yang
In recent years, there has been increasing interest to incorporate attention into deep learning architectures for biomedical image segmentation.
1 code implementation • 31 Oct 2021 • Michael Yeung, Leonardo Rundo, Yang Nan, Evis Sala, Carola-Bibiane Schönlieb, Guang Yang
However, it is well known that the DSC loss is poorly calibrated, resulting in overconfident predictions that cannot be usefully interpreted in biomedical and clinical practice.
no code implementations • 31 Oct 2021 • Michael Yeung, Guang Yang, Evis Sala, Carola-Bibiane Schönlieb, Leonardo Rundo
Manual segmentation is used as the gold-standard for evaluating neural networks on automated image segmentation tasks.
no code implementations • 4 Jun 2021 • Leonardo Rundo
Nowadays, the amount of heterogeneous biomedical data is increasing more and more thanks to novel sensing techniques and high-throughput technologies.
no code implementations • 16 May 2021 • Michael Yeung, Evis Sala, Carola-Bibiane Schönlieb, Leonardo Rundo
When evaluated on a combination of five public polyp datasets, our model similarly achieves state-of-the-art results with a mean DSC of 0. 878 and mean IoU of 0. 809, a 14% and 15% improvement over the previous state-of-the-art results of 0. 768 and 0. 702, respectively.
5 code implementations • 8 Feb 2021 • Michael Yeung, Evis Sala, Carola-Bibiane Schönlieb, Leonardo Rundo
We compare our loss function performance against six Dice or cross entropy-based loss functions, across 2D binary, 3D binary and 3D multiclass segmentation tasks, demonstrating that our proposed loss function is robust to class imbalance and consistently outperforms the other loss functions.
no code implementations • 24 Jul 2020 • Changhee Han, Leonardo Rundo, Kohei Murao, Tomoyuki Noguchi, Yuki Shimahara, Zoltan Adam Milacski, Saori Koshino, Evis Sala, Hideki Nakayama, Shinichi Satoh
Therefore, we propose unsupervised Medical Anomaly Detection Generative Adversarial Network (MADGAN), a novel two-step method using GAN-based multiple adjacent brain MRI slice reconstruction to detect brain anomalies at different stages on multi-sequence structural MRI: (Reconstruction) Wasserstein loss with Gradient Penalty + 100 L1 loss-trained on 3 healthy brain axial MRI slices to reconstruct the next 3 ones-reconstructs unseen healthy/abnormal scans; (Diagnosis) Average L2 loss per scan discriminates them, comparing the ground truth/reconstructed slices.
no code implementations • 15 May 2020 • Maureen van Eijnatten, Leonardo Rundo, K. Joost Batenburg, Felix Lucka, Emma Beddowes, Carlos Caldas, Ferdia A. Gallagher, Evis Sala, Carola-Bibiane Schönlieb, Ramona Woitek
This study showed the feasibility of deep learning based deformable registration of longitudinal abdominopelvic CT images via a novel incremental training strategy based on simulated deformations.
no code implementations • 12 Jan 2020 • Changhee Han, Leonardo Rundo, Kohei Murao, Takafumi Nemoto, Hideki Nakayama
Then, a questionnaire survey for physicians evaluates our pathology-aware Generative Adversarial Network (GAN)-based image augmentation projects in terms of Data Augmentation and physician training.
no code implementations • 14 Jun 2019 • Changhee Han, Leonardo Rundo, Kohei Murao, Zoltán Ádám Milacski, Kazuki Umemoto, Evis Sala, Hideki Nakayama, Shin'ichi Satoh
Unsupervised learning can discover various unseen diseases, relying on large-scale unannotated medical images of healthy subjects.
Generative Adversarial Network Unsupervised Anomaly Detection
no code implementations • 12 Jun 2019 • Changhee Han, Yoshiro Kitamura, Akira Kudo, Akimichi Ichinose, Leonardo Rundo, Yujiro Furukawa, Kazuki Umemoto, Yuanzhong Li, Hideki Nakayama
Accurate Computer-Assisted Diagnosis, relying on large-scale annotated pathological images, can alleviate the risk of overlooking the diagnosis.
no code implementations • 31 May 2019 • Changhee Han, Leonardo Rundo, Ryosuke Araki, Yudai Nagano, Yujiro Furukawa, Giancarlo Mauri, Hideki Nakayama, Hideaki Hayashi
In this context, Generative Adversarial Networks (GANs) can synthesize realistic/diverse additional training images to fill the data lack in the real image distribution; researchers have improved classification by augmenting data with noise-to-image (e. g., random noise samples to diverse pathological images) or image-to-image GANs (e. g., a benign image to a malignant one).
no code implementations • 17 Apr 2019 • Leonardo Rundo, Changhee Han, Yudai Nagano, Jin Zhang, Ryuichiro Hataya, Carmelo Militello, Andrea Tangherloni, Marco S. Nobile, Claudio Ferretti, Daniela Besozzi, Maria Carla Gilardi, Salvatore Vitabile, Giancarlo Mauri, Hideki Nakayama, Paolo Cazzaniga
The following mixed scheme is used for training/testing: (i) training on either each individual dataset or multiple prostate MRI datasets and (ii) testing on all three datasets with all possible training/testing combinations.
no code implementations • 29 Mar 2019 • Leonardo Rundo, Changhee Han, Jin Zhang, Ryuichiro Hataya, Yudai Nagano, Carmelo Militello, Claudio Ferretti, Marco S. Nobile, Andrea Tangherloni, Maria Carla Gilardi, Salvatore Vitabile, Hideki Nakayama, Giancarlo Mauri
Prostate cancer is the most common cancer among US men.
no code implementations • 29 Mar 2019 • Changhee Han, Leonardo Rundo, Ryosuke Araki, Yujiro Furukawa, Giancarlo Mauri, Hideki Nakayama, Hideaki Hayashi
Due to the lack of available annotated medical images, accurate computer-assisted diagnosis requires intensive Data Augmentation (DA) techniques, such as geometric/intensity transformations of original images; however, those transformed images intrinsically have a similar distribution to the original ones, leading to limited performance improvement.
no code implementations • 26 Feb 2019 • Changhee Han, Kohei Murao, Tomoyuki Noguchi, Yusuke Kawata, Fumiya Uchiyama, Leonardo Rundo, Hideki Nakayama, Shin'ichi Satoh
Accurate Computer-Assisted Diagnosis, associated with proper data wrangling, can alleviate the risk of overlooking the diagnosis in a clinical environment.