TOuNN: Topology optimization using neural networks

A Chandrasekhar, K Suresh - Structural and Multidisciplinary Optimization, 2021 - Springer
Neural networks, and more broadly, machine learning techniques, have been recently
exploited to accelerate topology optimization through data-driven training and image …

TONR: An exploration for a novel way combining neural network with topology optimization

Z Zhang, Y Li, W Zhou, X Chen, W Yao… - Computer Methods in …, 2021 - Elsevier
The rapid development of deep learning has opened a new door to the exploration of
topology optimization methods. The combination of deep learning and topology optimization …

High-level prior-based loss functions for medical image segmentation: A survey

R El Jurdi, C Petitjean, P Honeine, V Cheplygina… - Computer Vision and …, 2021 - Elsevier
Today, deep convolutional neural networks (CNNs) have demonstrated state of the art
performance for supervised medical image segmentation, across various imaging modalities …

Intra-and inter-slice contrastive learning for point supervised oct fluid segmentation

X He, L Fang, M Tan, X Chen - IEEE Transactions on Image …, 2022 - ieeexplore.ieee.org
OCT fluid segmentation is a crucial task for diagnosis and therapy in ophthalmology. The
current convolutional neural networks (CNNs) supervised by pixel-wise annotated masks …

Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision

H Kervadec, J Dolz, S Wang… - Medical imaging with …, 2020 - proceedings.mlr.press
We propose a novel weakly supervised learning segmentation based on several global
constraints derived from box annotations. Particularly, we leverage a classical tightness prior …

[HTML][HTML] CNN-based lung CT registration with multiple anatomical constraints

A Hering, S Häger, J Moltz, N Lessmann… - Medical Image …, 2021 - Elsevier
Deep-learning-based registration methods emerged as a fast alternative to conventional
registration methods. However, these methods often still cannot achieve the same …

An EfficientNet-based modified sigmoid transform for enhancing dermatological macro-images of melanoma and nevi skin lesions

V Venugopal, J Joseph, MV Das, MK Nath - Computer Methods and …, 2022 - Elsevier
Background and objective: During the initial stages, skin lesions may not have sufficient
intensity difference or contrast from the background region on dermatological macro-images …

Learning via Wasserstein-based high probability generalisation bounds

P Viallard, M Haddouche… - Advances in Neural …, 2024 - proceedings.neurips.cc
Minimising upper bounds on the population risk or the generalisation gap has been widely
used in structural risk minimisation (SRM)--this is in particular at the core of PAC-Bayesian …

Multi-material topology optimization using neural networks

A Chandrasekhar, K Suresh - Computer-Aided Design, 2021 - Elsevier
The focus of this paper is on multi-material topology optimization (MMTO), where the
objective is to not only compute the optimal topology, but also the distribution of two or more …

Deep interpretable classification and weakly-supervised segmentation of histology images via max-min uncertainty

S Belharbi, J Rony, J Dolz, IB Ayed… - … on Medical Imaging, 2021 - ieeexplore.ieee.org
Weakly-supervised learning (WSL) has recently triggered substantial interest as it mitigates
the lack of pixel-wise annotations. Given global image labels, WSL methods yield pixel-level …