Publications by authors named "J C Pesquet"
Article Synopsis
- Liver resection is effective for small hepatocellular carcinoma, but many patients face recurrence, making it important to identify those at a higher risk.
- A new deep learning algorithm using ResNet34 analyzed 680 whole slide images of liver specimens, achieving high accuracy (0.864 for patches, 0.823 for whole slides) in identifying risk indicators associated with HCC recurrence.
- Validated on an external dataset, the model showed promise in predicting recurrence by correlating pejorative architectural features with critical histological indicators like microvascular invasion, potentially paving the way for a comprehensive predictive tool for early post-resection recurrence.
Optical fibers aim to image in vivo biological processes. In this context, high spatial resolution and stability to fiber movements are key to enable decision-making processes (e.g.
View Article and Find Full Text PDFArticle Synopsis
- The study aimed to create a machine-learning model that can automatically identify bowel obstructions (BO) in abdominal CT scans, helping radiologists manage their heavy workloads and improve patient outcomes.
- The researchers used a dataset of 1,345 CT scans, with annotations from experienced radiologists, to train and test various neural network architectures for accurate binary classification of BO.
- The best-performing mixed convolutional network achieved high scores in sensitivity and accuracy, indicating its strong potential for automating the detection of bowel obstructions in clinical settings.
Background & Aims: The diagnosis of primary liver cancers (PLCs) can be challenging, especially on biopsies and for combined hepatocellular-cholangiocarcinoma (cHCC-CCA). We automatically classified PLCs on routine-stained biopsies using a weakly supervised learning method.
Method: We selected 166 PLC biopsies divided into training, internal and external validation sets: 90, 29 and 47 samples, respectively.
Joint Learning of Fully Connected Network Models in Lifting Based Image Coders.
IEEE Trans Image Process
December 2023
The optimization of prediction and update operators plays a prominent role in lifting-based image coding schemes. In this paper, we focus on learning the prediction and update models involved in a recent Fully Connected Neural Network (FCNN)-based lifting structure. While a straightforward approach consists in separately learning the different FCNN models by optimizing appropriate loss functions, jointly learning those models is a more challenging problem.
View Article and Find Full Text PDF