Working principles for training neural networks with highly incomplete dataset: vanilla (upper panel) vs GapNet (lower panel) (Image by Y.-W. Chang.)
Training of neural network with incomplete medical datasets
Yu-Wei Chang
Neural network training and validation rely on the availability of large high-quality datasets. However, in many cases, only incomplete datasets are available, particularly in health care applications, where each patient typically undergoes different clinical procedures or can drop out of a study. Here, we introduce GapNet, an alternative deep-learning training approach that can use highly incomplete datasets without overfitting or introducing artefacts. Using two highly incomplete real-world medical datasets, we show that GapNet improves the identification of patients with underlying Alzheimer’s disease pathology and of patients at risk of hospitalization due to Covid-19. Compared to commonly used imputation methods, this improvement suggests that GapNet can become a general tool to handle incomplete medical datasets.
Spatio-temporal spectrum diagram of microscopy techniques and their applications. (Image by the Authors of the manuscript.)Roadmap on Deep Learning for Microscopy
Giovanni Volpe, Carolina Wählby, Lei Tian, Michael Hecht, Artur Yakimovich, Kristina Monakhova, Laura Waller, Ivo F. Sbalzarini, Christopher A. Metzler, Mingyang Xie, Kevin Zhang, Isaac C.D. Lenton, Halina Rubinsztein-Dunlop, Daniel Brunner, Bijie Bai, Aydogan Ozcan, Daniel Midtvedt, Hao Wang, Nataša Sladoje, Joakim Lindblad, Jason T. Smith, Marien Ochoa, Margarida Barroso, Xavier Intes, Tong Qiu, Li-Yu Yu, Sixian You, Yongtao Liu, Maxim A. Ziatdinov, Sergei V. Kalinin, Arlo Sheridan, Uri Manor, Elias Nehme, Ofri Goldenberg, Yoav Shechtman, Henrik K. Moberg, Christoph Langhammer, Barbora Špačková, Saga Helgadottir, Benjamin Midtvedt, Aykut Argun, Tobias Thalheim, Frank Cichos, Stefano Bo, Lars Hubatsch, Jesus Pineda, Carlo Manzo, Harshith Bachimanchi, Erik Selander, Antoni Homs-Corbera, Martin Fränzl, Kevin de Haan, Yair Rivenson, Zofia Korczak, Caroline Beck Adiels, Mite Mijalkov, Dániel Veréb, Yu-Wei Chang, Joana B. Pereira, Damian Matuszewski, Gustaf Kylberg, Ida-Maria Sintorn, Juan C. Caicedo, Beth A Cimini, Muyinatu A. Lediju Bell, Bruno M. Saraiva, Guillaume Jacquemet, Ricardo Henriques, Wei Ouyang, Trang Le, Estibaliz Gómez-de-Mariscal, Daniel Sage, Arrate Muñoz-Barrutia, Ebba Josefson Lindqvist, Johanna Bergman
arXiv: 2303.03793
Through digital imaging, microscopy has evolved from primarily being a means for visual observation of life at the micro- and nano-scale, to a quantitative tool with ever-increasing resolution and throughput. Artificial intelligence, deep neural networks, and machine learning are all niche terms describing computational methods that have gained a pivotal role in microscopy-based research over the past decade. This Roadmap is written collectively by prominent researchers and encompasses selected aspects of how machine learning is applied to microscopy image data, with the aim of gaining scientific knowledge by improved image quality, automated detection, segmentation, classification and tracking of objects, and efficient merging of information from multiple imaging modalities. We aim to give the reader an overview of the key developments and an understanding of possibilities and limitations of machine learning for microscopy. It will be of interest to a wide cross-disciplinary audience in the physical sciences and life sciences.
Deep-learning-detected tau deposition (color in orange) for Alzheimer’s Disease. (Image by Y.-W. Chang.)Deep-learning analysis in tau PET for Alzheimer’s continuum
Yu-Wei Chang, Giovanni Volpe, Joana B Pereira Submitted to SPIE-ETAI Date: 24 August 2022 Time: 16:40 (PDT)
Previous studies have suggested that Alzheimer’s disease (AD) is typically characterized by abnormal accumulation of tau proteins in neurofibrillary tangles. This is usually assessed by measuring tau levels in regions of interest (ROIs) defined based on previous post-mortem studies. However, it remains unclear where this approach is suitable for assessing tau accumulation in vivo across the different stages of individuals. This study employed a data-driven deep learning approach to detect tau deposition across different AD stages at the voxel level. Moreover, the classification performance of this approach on distinguishing different AD stages was compared with the one using conventional ROIs.
Working principles for training neural networks with highly incomplete dataset: vanilla (upper panel) vs GapNet (lower panel) (Image by Y.-W. Chang.)Neural network training with highly incomplete medical datasets
Yu-Wei Chang, Laura Natali, Oveis Jamialahmadi, Stefano Romeo, Joana B Pereira, Giovanni Volpe Submitted to SPIE-ETAI Date: 24 August 2022 Time: 08:00 (PDT)
Neural network training and validation rely on the availability of large high-quality datasets. However, in many cases, only incomplete datasets are available, particularly in health care applications, where each patient typically undergoes different clinical procedures or can drop out of a study. Here, we introduce GapNet, an alternative deep-learning training approach that can use highly incomplete datasets without overfitting or introducing artefacts. Using two highly incomplete real-world medical datasets, we show that GapNet improves the identification of patients with underlying Alzheimer’s disease pathology and of patients at risk of hospitalization due to Covid-19. Compared to commonly used imputation methods, this improvement suggests that GapNet can become a general tool to handle incomplete medical datasets.
The Soft Matter Lab participates to the SPIE Optics+Photonics conference in San Diego, CA, USA, 21-25 August 2022, with the presentations listed below.
Martin Selin: Scalable construction of quantum dot arrays using optical tweezers and deep learning (@SPIE)
22 August 2022 • 11:05 AM – 11:25 AM PDT | Conv. Ctr. Room 5A
Jesus Pineda: Revealing the spatiotemporal fingerprint of microscopic motion using geometric deep learning (@SPIE)
23 August 2022 • 11:05 AM – 11:25 AM PDT | Conv. Ctr. Room 5A
Anna Canal Garcia: Multilayer brain connectivity analysis in Alzheimer’s disease using functional MRI data (@SPIE)
24 August 2022 • 2:25 PM – 2:45 PM PDT | Conv. Ctr. Room 5A
Mite Mijalkov: A novel method for quantifying men and women-like features in brain structure and function (@SPIE)
24 August 2022 • 3:05 PM – 3:25 PM PDT | Conv. Ctr. Room 5A
Working principles for training neural networks with highly incomplete dataset: vanilla (upper panel) vs GapNet (lower panel) (Image by Yu-Wei Chang.)Neural Network Training with Highly Incomplete Datasets
Yu-Wei Chang, Laura Natali, Oveis Jamialahmadi, Stefano Romeo, Joana B. Pereira, Giovanni Volpe
Machine Learning: Science and Technology 3, 035001 (2022)
arXiV: 2107.00429
doi: 10.1088/2632-2153/ac7b69
Neural network training and validation rely on the availability of large high-quality datasets. However, in many cases only incomplete datasets are available, particularly in health care applications, where each patient typically undergoes different clinical procedures or can drop out of a study. Since the data to train the neural networks need to be complete, most studies discard the incomplete datapoints, which reduces the size of the training data, or impute the missing features, which can lead to artefacts. Alas, both approaches are inadequate when a large portion of the data is missing. Here, we introduce GapNet, an alternative deep-learning training approach that can use highly incomplete datasets. First, the dataset is split into subsets of samples containing all values for a certain cluster of features. Then, these subsets are used to train individual neural networks. Finally, this ensemble of neural networks is combined into a single neural network whose training is fine-tuned using all complete datapoints. Using two highly incomplete real-world medical datasets, we show that GapNet improves the identification of patients with underlying Alzheimer’s disease pathology and of patients at risk of hospitalization due to Covid-19. By distilling the information available in incomplete datasets without having to reduce their size or to impute missing values, GapNet will permit to extract valuable information from a wide range of datasets, benefiting diverse fields from medicine to engineering.
Brain nodes. (Image taken from the article.)Multiplex Connectome Changes across the Alzheimer’s Disease Spectrum Using Gray Matter and Amyloid Data
Mite Mijalkov, Giovanni Volpe, Joana B Pereira
Anna Canal-Garcia, Emiliano Gómez-Ruiz, Mite Mijalkov, Yu-Wei Chang, Giovanni Volpe, Joana B Pereira, Alzheimer’s Disease Neuroimaging Initiative
Cerebral Cortex, bhab429 (2022)
doi: 10.1093/cercor/bhab429
The organization of the Alzheimer’s disease (AD) connectome has been studied using graph theory using single neuroimaging modalities such as positron emission tomography (PET) or structural magnetic resonance imaging (MRI). Although these modalities measure distinct pathological processes that occur in different stages in AD, there is evidence that they are not independent from each other. Therefore, to capture their interaction, in this study we integrated amyloid PET and gray matter MRI data into a multiplex connectome and assessed the changes across different AD stages. We included 135 cognitively normal (CN) individuals without amyloid-β pathology (Aβ−) in addition to 67 CN, 179 patients with mild cognitive impairment (MCI) and 132 patients with AD dementia who all had Aβ pathology (Aβ+) from the Alzheimer’s Disease Neuroimaging Initiative. We found widespread changes in the overlapping connectivity strength and the overlapping connections across Aβ-positive groups. Moreover, there was a reorganization of the multiplex communities in MCI Aβ + patients and changes in multiplex brain hubs in both MCI Aβ + and AD Aβ + groups. These findings offer a new insight into the interplay between amyloid-β pathology and brain atrophy over the course of AD that moves beyond traditional graph theory analyses based on single brain networks.
Yu-Wei Chang is an engineer at the Digital Medicine Center at National Yang-Ming University in Taiwan, working on a machine learning approach for phenotyping psychiatric disorders.
He will visit us for 2 months from February 29, 2020, to April 30, 2020, and he will be working on deep learning for Alzheimer’s Disease as well as the development of BRAPH 2.0 (March-April 2020).
