Patents & Publications

2024

1. MICCAI-2024

   Unpaired Modality Translation for Pseudo Labeling of Histology Images

   Boschet Arthur, Collin Armand, Katoch Nishka, and Cohen-Adad Julien

   MICCAI Workshop on Deep Generative Models 2024

   Abs PDF

   The segmentation of histological images is critical for various biomedical applications, yet the lack of annotated data presents a significant challenge. We propose a microscopy pseudo labeling pipeline utilizing unsupervised image translation to address this issue. Our method generates pseudo labels by translating between labeled and unlabeled domains without requiring prior annotation in the target domain. We evaluate two pseudo labeling strategies across three image domains increasingly dissimilar from the labeled data, demonstrating their effectiveness. Notably, our method achieves a mean Dice score of 0.736 ± 0.005 on a SEM dataset using the tutoring path, which involves training a segmentation model on synthetic data created by translating the labeled dataset (TEM) to the target modality (SEM). This approach aims to accelerate the annotation process by providing high-quality pseudo labels as a starting point for manual refinement.

2. FR3121993B1

   Electronic Measuring and Recording Device for Evaluating Drained Body Fluid

   Morisse Gill, Mathelin Carole, Negre Aurelia, Rodriguez Louise, Hepiegne Raphael, Augustin-Latour Jehan, Abouchar Elie, Malcor Deydier De Pierrefeu Vincent, Boschet Arthur, Binvignat Jean-Francois, Baehr Aurore, Le Meur Gaultier, Goumbala Abdou Akim, Jollet May-Line, Ibnouhsein Issam, and Neuberger Karl

   Patent No: FR3121993B1 2024

   Abs

   Electronic measuring and recording device (1) for evaluating a bodily fluid collected in a collecting flask (3) connected by a tube (4) to a patient, with measuring means (12) making it possible to deduce a drainage volume and/or flow rate of the fluid, an optical analysis means (16) of a component of the fluid and a microcontroller (13) for receiving data supplied by the measuring means, the optical analysis means, and/or the microcontroller, making it possible to measure successive values, each with a confidence index greater than a given threshold, of the volume and/or of the flow rate of fluid. Figure for abstract: Fig. 2

2022

1. Insta-COVID-19

   Identifying COVID-19 Instagram behaviour patterns via a novel network analysis pipeline

   Boschet Arthur, Lee Vivian Chia-Jou, Shen Brenda, and Zhang William

   STEM Fellowship Journal 2022

   Abs PDF

   Instagram has become one of the most widely used social media platforms globally. The volume of information generated by Instagram users makes it an excellent data mine to study human behavior. Recently, researchers have turned to Twitter data to observe the flow of (mis)information surrounding the COVID-19 pandemic. However, there is little-to-no publication on coronavirus-related behaviours on Instagram. To address this knowledge gap, an extensive analysis of COVID-19-related big data from Instagram was conducted. Hashtags obtained from 5,300 global Instagram posts collected this year between January 5 and March 20 were processed using a novel, highly extensible Social Network Analysis pipeline. Eigenvector centrality and weight cluster indexing partitioned the hashtag data into clusters, three of which were studied to reflect public behaviour. It was concluded that contributions to the mental health cluster consisted mainly of Instagram Business Profiles, and that these were associated with positive sentiments. It was also found that a niche cluster containing conspiracy-related content was primarily created by genuine Instagram users, and was associated with very negative sentiments. Lastly, hashtags related to comedy and memes were classified by a supervised machine-learning approach to be bot-generated content. Some suggestions with promising directions for future investigations are provided. It is recommended that a large-scale behavioral analysis of bots and their effects on pandemic information be performed. Progress will be made through public health research focusing on the intersectionality of mental health and COVID-19, as well as the rise of conspiracy theorists amidst the infodemic.