检索结果-内蒙古大学图书馆

Cancer-Net BCa-S: Breast Cancer Grade Prediction using Volumetric Deep Radiomic Features from Synthetic Correlated Diffusion Imaging

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tai, Chi-En Amy Gunraj, Hayden Wong, Alexander Vision and Image Processing Lab University of Waterloo Canada

The prevalence of breast cancer continues to grow, affecting about 300,000 females in the United States in 2023. However, there are different levels of severity of breast cancer requiring different treatment strategies, and hence, grading breast cancer has become a vital component of breast cancer diagnosis and treatment planning. Specifically, the gold-standard Scarff-Bloom-Richardson (SBR) grade has been shown to consistently indicate a patient's response to chemotherapy. Unfortunately, the current method to determine the SBR grade requires removal of some cancer cells from the patient which can lead to stress and discomfort along with costly expenses. In this paper, we study the efficacy of deep learning for breast cancer grading based on synthetic correlated diffusion (CDIs) imaging, a new magnetic resonance imaging (MRI) modality and found that it achieves better performance on SBR grade prediction compared to those learnt using gold-standard imaging modalities. Hence, we introduce Cancer-Net BCa-S, a volumetric deep radiomics approach for predicting SBR grade based on volumetric CDIs data. Given the promising results, this proposed method to identify the severity of the cancer would allow for better treatment decisions without the need for a biopsy. Cancer-Net BCa-S has been made publicly available as part of a global open-source initiative for advancing machine learning for cancer care. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemotherapy

A Multi-Institutional Open-Source Benchmark Dataset for Breast Cancer Clinical Decision Support using Synthetic Correlated Diffusion Imaging Data

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tai, Chi-En Amy Gunraj, Hayden Wong, Alexander Vision and Image Processing Lab University of Waterloo Canada

Recently, a new form of magnetic resonance imaging (MRI) called synthetic correlated diffusion (CDIs) imaging was introduced and showed considerable promise for clinical decision support for cancers such as prostate cancer when compared to current gold-standard MRI techniques. However, the efficacy for CDIs for other forms of cancers such as breast cancer has not been as well-explored nor have CDIs data been previously made publicly available. Motivated to advance efforts in the development of computer-aided clinical decision support for breast cancer using CDIs, we introduce Cancer-Net BCa, a multi-institutional open-source benchmark dataset of volumetric CDIs imaging data of breast cancer patients. Cancer-Net BCa contains CDIs volumetric images from a pre-treatment cohort of 253 patients across ten institutions, along with detailed annotation metadata (the lesion type, genetic subtype, longest diameter on the MRI (MRLD), the Scarff-Bloom-Richardson (SBR) grade, and the post-treatment breast cancer pathologic complete response (pCR) to neoadjuvant chemotherapy). We further examine the demographic and tumour diversity of the Cancer-Net BCa dataset to gain deeper insights into potential biases. Cancer-Net BCa is publicly available as a part of a global open-source initiative dedicated to accelerating advancement in machine learning to aid clinicians in the fight against cancer. Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

How Much You Ate? Food Portion Estimation on Spoons

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sharma, Aaryam Czarnecki, Chris Chen, Yuhao Xi, Pengcheng Xu, Linlin Wong, Alexander Vision and Image Processing Lab University of Waterloo Canada National Research Council Canada

Monitoring dietary intake is a crucial aspect of promoting healthy living. In recent years, advances in computer vision technology have facilitated dietary intake monitoring through the use of images and depth cameras. However, the current state-of-the-art image-based food portion estimation algorithms assume that users take images of their meals one or two times, which can be inconvenient and fail to capture food items that are not visible from a top-down perspective, such as ingredients submerged in a stew. To address these limitations, we introduce an innovative solution that utilizes stationary user-facing cameras to track food items on utensils, not requiring any change of camera perspective after installation. The shallow depth of utensils provides a more favorable angle for capturing food items, and tracking them on the utensil’s surface offers a significantly more accurate estimation of dietary intake without the need for post-meal image capture. The system is reliable for estimation of nutritional content of liquid-solid heterogeneous mixtures such as soups and stews. Through a series of experiments, we demonstrate the exceptional potential of our method as a non-invasive, user-friendly, and highly accurate dietary intake monitoring tool. © 2024, CC BY.

关键词： Cameras

In The Wild Ellipse Parameter Estimation for Circular Dining Plates and Bowls

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Pathiranage, Akil Czarnecki, Chris Chen, Yuhao Xi, Pengcheng Xu, Linlin Wong, Alexander Vision and Image Processing Lab University of Waterloo Canada National Research Council Canada

Ellipse estimation is an important topic in food image processing because it can be leveraged to parameterize plates and bowls, which in turn can be used to estimate camera view angles and food portion sizes. Automatically detecting the elliptical rim of plates and bowls and estimating their ellipse parameters for data in-the-wild is challenging: diverse camera angles and plate shapes could have been used for capture, noisy background, multiple non-uniform plates and bowls in the image could be present. Recent advancements in foundational models offer promising capabilities for zero-shot semantic understanding and object segmentation. However, the output mask boundaries for plates and bowls generated by these models often lack consistency and precision compared to traditional ellipse fitting methods. In this paper, we combine ellipse fitting with semantic information extracted by zero-shot foundational models and propose WildEllipseFit, a method to detect and estimate the elliptical rim for plate and bowl. Evaluation on the proposed Yummly-ellipse dataset demonstrates its efficacy and zero-shot capability in real-world scenarios. © 2024, CC BY.

关键词： Parameter estimation

Memory-Efficient Continual Learning Object Segmentation for Long Videos

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Nazemi, Amir Shafiee, Mohammad Javad Gharaee, Zahra Fieguth, Paul Vision & Image Processing Lab Department of Systems Design Engineering University of Waterloo WaterlooON Canada

Recent state-of-the-art semi-supervised Video Object Segmentation (VOS) methods have shown significant improvements in target object segmentation accuracy when information from preceding frames is used in segmenting the current frame. In particular, such memory-based approaches can help a model to more effectively handle appearance changes (representation drift) or occlusions. Ideally, for maximum performance, Online VOS methods would need all or most of the preceding frames (or their extracted information) to be stored in memory and be used for online learning in later frames. Such a solution is not feasible for long videos, as the required memory size grows without bound, and such methods can fail when memory is limited and a target object experiences repeated representation drifts throughout a video. We propose two novel techniques to reduce the memory requirement of Online VOS methods while improving modeling accuracy and generalization on long videos. Motivated by the success of continual learning techniques in preserving previously-learned knowledge, here we propose Gated-Regularizer Continual Learning (GRCL), which improves the performance of any Online VOS subject to limited memory, and a Reconstruction-based Memory Selection Continual Learning (RMSCL), which empowers Online VOS methods to efficiently benefit from stored information in memory. We also analyze the performance of a hybrid combination of the two proposed methods. Experimental results show that the proposed methods are able to improve the performance of Online VOS models by more than 8%, with improved robustness on long-video datasets while maintaining comparable performance on short-video datasets such as DAVIS16, DAVIS17, and YouTube-VOS18. © 2023, CC BY-NC-SA.

关键词： image segmentation

NutritionVerse-Thin: An Optimized Strategy for Enabling Improved Rendering of 3D Thin Food Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tai, Chi-En Amy Li, Jason Kumar, Sriram Nair, Saeejith Chen, Yuhao Xi, Pengcheng Wong, Alexander Vision and Image Processing Lab University of Waterloo Canada National Research Council Canada

With the growth in capabilities of generative models, there has been growing interest in using photo-realistic renders of common 3D food items to improve downstream tasks such as food printing, nutrition prediction, or management of food wastage. Despite 3D modelling capabilities being more accessible than ever due to the success of NeRF based view-synthesis, such rendering methods still struggle to correctly capture thin food objects, often generating meshes with significant holes. In this study, we present an optimized strategy for enabling improved rendering of thin 3D food models, and demonstrate qualitative improvements in rendering quality. Our method generates the 3D model mesh via a proposed thin-object-optimized differentiable reconstruction method and tailors the strategy at both the data collection and training stages to better handle thin objects. While simple, we find that this technique can be employed for quick and highly consistent capturing of thin 3D objects. Copyright © 2023, The Authors. All rights reserved.

关键词： 3D modeling

NutritionVerse-3D: A 3D Food Model Dataset for Nutritional Intake Estimation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tai, Chi-En Amy Keller, Matthew Kerrigan, Mattie Chen, Yuhao Nair, Saeejith Xi, Pengcheng Wong, Alexander Vision and Image Processing Lab University of Waterloo Canada National Research Council Canada

77% of adults over 50 want to age in place today, presenting a major challenge to ensuring adequate nutritional intake. It has been reported that one in four older adults that are 65 years or older are malnourished and given the direct link between malnutrition and decreased quality of life, there have been numerous studies conducted on how to efficiently track nutritional intake of food. Recent advancements in machine learning and computer vision show promise of automated nutrition tracking methods of food, but require a large high-quality dataset in order to accurately identify the nutrients from the food on the plate. Unlike existing datasets, a collection of 3D models with nutritional information allow for view synthesis to create an infinite number of 2D images for any given viewpoint/camera angle along with the associated nutritional information. In this paper, we develop a methodology for collecting high-quality 3D models for food items with a particular focus on speed and consistency, and introduce NutritionVerse-3D, a large-scale high-quality high-resolution dataset of 105 3D food models, in conjunction with their associated weight, food name, and nutritional value. These models allow for large quantity food intake scenes, diverse and customizable scene layout, and an infinite number of camera settings and lighting conditions. NutritionVerse-3D is publicly available as a part of an open initiative to accelerate machine learning for nutrition sensing. Copyright © 2023, The Authors. All rights reserved.

关键词： Nutrition

The Influence of Input Variable Selection on Deep Learning-Based Sea Ice Parameter Inversion from Multi-Sensor Satellite Data

学校读者我要写书评

暂无评论

The Influence of Input Variable Selection on Deep Learning-B...

2023 MTS/IEEE U.S. Gulf Coast, OCEANS 2023

作者： Chen, Xinwei Patel, Muhammed Cantu, Fernando J. Pena Park, Jinman Turnes, Javier Noa Jiang, Mingzhe Xu, Linlin Scott, K. Andrea Clausi, David A. Huang, Weimin University of Waterloo Vision and Image Processing Lab Department of System Design Engineering Canada Memorial University of Newfoundland Faculty of Engineering and Applied Science St. John'sNLA1B 3X5 Canada

ISBN: (纸本)9798218142186

The automated mapping of Arctic sea ice using satellite data from various sources plays a critical role in maritime shipping and climate science research. Deep learning models, particularly convolutional neural networks (CNNs), have shown significant potential in generating more accurate and reliable automated sea ice maps from synthetic aperture radar (SAR) images. This study focuses on investigating the impact of integrating multi-source data on enhancing the performance of CNN-based sea ice mapping models. By employing a multitask U-Net architecture, the paper aims to estimate three essential sea ice parameters, namely sea ice concentration (SIC), stage of development (SOD), and floe size (FLOE), through different combinations of input data. The AI4Arctic Sea Ice Challenge dataset with multi-sensor satellite data is utilized for model training and evaluation. The experimental findings confirm the effectiveness of incorporating passive microwave data and spatial-temporal information in conjunction with SAR imagery, as well as feature redundancy removal, resulting in improved accuracy for sea ice parameter estimation. © 2023 The Marine Technology Society (MTS).

关键词： Sea ice

Efficient direct-block-address encoding for single-shot-based 3d reconstruction 58th

学校读者我要写书评

暂无评论

Efficient direct-block-address encoding for single-shot-base...

58th International Symposium on Digest of Technical Papers, ICDT 2021

作者： Farsangi, Sina Naiel, Mohamed A. Lamm, Mark Fieguth, Paul Vision and Image Processing Lab University of Waterloo WaterlooON Canada Christie Digital Systems Canada Inc KitchenerON Canada

We propose a new framework for single-shot 3D reconstruction based on two-dimensional tag embedding, where the Structured Light (SL) patterns are partitioned into a number of non-overlapping blocks that each represent a codeword for explicitly encoding the projector’s corresponding pixel address, resulting in an efficient computation for both constructing the SL images and for obtaining the projector-camera pixel correspondences. © 2021 SID.

关键词： Signal encoding