检索结果-内蒙古大学图书馆

21st ieee International symposium on Biomedical Imaging (ISBI)

作者： Linares, Oscar Cuadros Belizario, Ivar Vargas Batah, Sabrina Setembre Hamann, Bernd Fabro, Alexandre Todorovic Azevedo-Marques, Paulo M. Traina, Agma J. M. Univ Campinas Unicamp Artificial Intelligence Lab Recod Ai Inst Comp BR-13083970 Campinas SP Brazil Univ Sao Paulo Inst Math & Comp Sci ICMC BR-13566590 Sao Carlos SP Brazil Univ Sao Paulo Fac Med BR-14049900 Ribeirao Preto SP Brazil Univ Calif Davis Dept Comp Sci Davis CA 95616 USA

ISBN: (纸本)9798350313345;9798350313338

Lung pleura is a reference structure for the identification of histological characteristics for the recognition of a pathological interstitial lung disease (ILD) pattern. When a pattern is found, it is important to know whether it is close to the pleura to determine its specific type and severity. This manual process is tedious and laborious for the pathologist. Automating this task is important for a complete computed-system-assisted ILD diagnostic process. We introduce "RadPleura" a framework for pleura classification of histopathological images using a radiomics-based approach. Our framework performs image pre-processing, region-of-interest segmentation, and extraction of a radiomic-signature suited for ILD classification. To evaluate a radiomic-signature, we classify it into pleura and non-pleura, using two classifiers, a Support Vector Machine (SVM) and Gradient-boosted Decision Tree (GBD). Our experiments are promising, producing F-scores of 92% (SVM) and 91% (GBD). We also created a dataset of lung histopathology images with respective ground truth for pleura classification. To the best of our knowledge, this study is the first published attempt to explore and develop a radiomic signature for pleura classification. The methods have been integrated into the RadPleura framework developed.

关键词： Interstitial lung disease Lung pleura Histopathology Radiomics Machine learning

来源：评论

学校读者我要写书评

暂无评论

A PIPELINE FOR HISTOPATHOLOGY ANALYSIS OF PROSTATE CANCER GUIDED BY MASS SPECTROMETRY IMAGING 21

A PIPELINE FOR HISTOPATHOLOGY ANALYSIS OF PROSTATE CANCER GU...

引用

21st ieee International symposium on Biomedical Imaging (ISBI)

作者： Luna, Jose Marcio Nakhoul, Hani Weimholt, Cody Kim, Eric H. Song, Sheng-Kwei Angel, Peggi M. Drake, Richard R. Ippolito, Joseph E. Washington Univ Sch Med Mallinckrodt Inst Radiol St Louis MO 63110 USA Washington Univ Sch Med Dept Pathol & Immunol St Louis MO USA Washington Univ Sch Med Dept Surg St Louis MO USA Med Univ South Carolina Dept Cell Mol Pharmacol & Expt Therapeut Charleston SC USA Washington Univ Sch Med Dept Biochem & Mol Biophys St Louis MO USA

ISBN: (纸本)9798350313345;9798350313338

Recent evidence shows that interactions between tumor cells, immune cells, and extracellular matrix (ECM) proteins in the stroma play an important role in prostate cancer (PCa) progression. However, to date these factors are not accounted for in clinical evaluation of PCa patients. Our team has developed methods based on matrix-assisted laser desorption/ionization (MALDI) imaging to identify sets of ECM glycan and collagen molecules associated with PCa. In this study, we leverage computational imaging methods and pathomic textural features to assess the potential of MALDI imaging to guide the identification of regions in PCa hematoxylin and eosin stain (H&E) images as tumor or nontumor. We provide preliminary evidence that MALDI imaging can elucidate tissue properties and guide pathomic textural analysis in H&E images, with potential applications in treatment guidance and prognostication of PCa.

关键词： Prostate Cancer image Analysis MALDI-TOF Mass Spectrometry H&E

来源：评论

学校读者我要写书评

暂无评论

APPQ-CNN: An Adaptive CNNs Inference Accelerator for Synergistically Exploiting Pruning and Quantization Based on FPGA

IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING

引用

ieee TRANSACTIONS ON SUSTAINABLE COMPUTING 2024年第6期9卷 874-888页

作者： Zhang, Xian Xiao, Guoqing Duan, Mingxing Chen, Yuedan Li, Kenli Huaihua Univ Sch Comp & Artificial Intelligence Huaihua 418000 Peoples R China Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Peoples R China Hunan Univ Shenzhen Inst Shenzhen 518063 Peoples R China

Convolutional neural networks (CNNs) are widely utilized in intelligent edge computing applications such as computational vision and image processing. However, as the number of layers of the CNN model increases, the number of parameters and computations gets larger, making it increasingly challenging to accelerate in edge computing applications. To effectively adapt to the tradeoff between the speed and accuracy of CNNs inference for smart applications. This paper proposes an FPGA-based adaptive CNNs inference accelerator synergistically utilizing filter pruning, fixed-point parameter quantization, and multi-computing unit parallelism called APPQ-CNN. First, the article devises a hybrid pruning algorithm based on the L1-norm and APoZ to measure the filter impact degree and a configurable parameter quantization fixed-point computing architecture instead of floating-point architecture. Then, design a cascade of the CNN pipelined kernel architecture and configurable multiple computation units. Finally, conduct extensive performance exploration and comparison experiments on various real and synthetic datasets. With negligible accuracy loss, the speed performance of our accelerator APPQ-CNN compares with current state-of-the-art FPGA-based accelerators PipeCNN and OctCNN by 2.15x and 1.91x, respectively. Furthermore, APPQ-CNN provides settable fixed-point quantization bit-width parameters, filter pruning rate, and multiple computation unit counts to cope with practical application performance requirements in edge computing.

关键词： Convolutional neural networks Convolution computational modeling Field programmable gate arrays Kernel Adaptation models Quantization (signal) fixed-point quantization FPGA inference accelerator pipeline pruning algorithm

来源：评论

学校读者我要写书评

暂无评论

Investigating the Usability of XAI in AI-based image Classification 12

Investigating the Usability of XAI in AI-based Image Classif...

引用

12th IFAC symposium on Biological and Medical Systems (BMS)

作者： Stodt, Jan Reich, Christoph Clarke, Nathan Furtwangen Univ D-78120 Furtwangen Germany Univ Plymouth Portland Sq Plymouth PL4 8AA Devon England

This paper investigates the usability of XAI (Explainable Artificial intelligence) in AI-based image classification, particularly for non-experts like medical professionals. XAI provides the user of AI systems with an explanation for a particular decision. But the usability of such explanations remains an open point of discussion. The investigation highlights that there is a need for integrating explainability in the design of the classification approach. This paper will present an approach to classify the parts of an object separately and then utilize a white box model (decision tree) for the final classification. This is enriched by additional information, achieving understandability of the classification. Copyright (C) 2024 The Authors. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)

关键词： AI-based image processing XAI Investigation Usability Non-AI Experts

来源：评论

学校读者我要写书评

暂无评论

image Test Libraries for the in-field test of ultra-low-power devices 26

Image Test Libraries for the in-field test of ultra-low-powe...

引用

26th ieee Latin American Test symposium, LATS 2025

作者： Porsia, Antonio Perlo, Giacomo Ruospo, Annachiara Sanchez, Ernesto Politecnico di Torino DAUIN Turin Italy

ISBN: (纸本)9781665477635

In recent years, research and technology advancements have driven exponential growth in the adoption of Artificial intelligence (AI)-based systems, even in safety-critical contexts such as autonomous driving and healthcare applications. The joint effort of academia and industry has yielded techniques and standards with the objective of ensuring the safe operation of AI-based technology. In the specific context of Convolutional Neural Networks (CNNs) running on GPUs, image Test Libraries (ITLs) have been proposed as an effective method for performing on-line functional testing of GPU multipliers. This is achieved by launching the inference of a set of test images containing a set of ATPG-generated functional test patterns. However, while the demand for computational power for DNN models is constantly increasing, another branch of Machine Learning (ML) research, namely TinyML, focuses on minimizing the computational requirements of DNN models in order to bring AI capabilities to edge devices, whose constraints on power usage, memory space and processing power do not allow for the deployment of conventional DNN models. This research work aims to adapt the ITL technique to CNNs running on ultra-low-power edge hardware, while also overcoming some limitations of GPU ITLs. Experimental results demonstrate that a single test image generated using the proposed method is capable of detecting 96.01% of stuck-at faults occurring in the 32-bit integer multiplier of a RISC-V-based ultra-low-power System-on-Chip executing a quantized CNN. © 2025 ieee.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Automated design of feature extraction for unsupervised image clustering using grammatical evolution.

Automated design of feature extraction for unsupervised imag...

引用

ieee symposium Series on computational intelligence (ieee SSCI)

作者： Gerber, Mia Pillay, Nelishia Univ Pretoria Dept Comp Sci Gauteng South Africa

ISBN: (纸本)9781665487689

When doing image processing it has been shown that the use of an appropriate feature extraction function can result in a significant boost in performance. Selecting or creating the correct feature extraction function is however non-trivial. This work uses grammatical evolution (GE) to evolve a feature extraction function for images. The goal is to evolve feature extraction functions that are able to improve the clustering results of three different unsupervised clustering algorithms: KMeans++, DBSCAN and Mean Shift. In order to test whether the feature extraction functions evolved by the GE are effective, the clustering algorithms are also used with no feature extraction and with randomly generated feature extraction functions. The results of experimentation show that using a GE to evolve a feature extraction function is more effective than using no feature extraction or randomly generated feature extraction, with the exception of K-Means++ when applied to the Oral lesion dataset where GE feature extraction performed equally as good as when no feature extraction is used. A possible reason for this might be that the grammar for the GE needs additional operators to generate color specific features. Future work includes applying transfer learning to the GE.

关键词： grammatical evolution image feature extraction unsupervised clustering

来源：评论

学校读者我要写书评

暂无评论

AN INTEGRATED VIRTUAL SURGICAL PLANNING SYSTEM FOR NASAL AIRWAY OBSTRUCTION 20

AN INTEGRATED VIRTUAL SURGICAL PLANNING SYSTEM FOR NASAL AIR...

引用

20th ieee International symposium on Biomedical Imaging (ISBI)

作者： Fillion-Robin, Jean-Christophe Bray, Aaron Vicory, Jared Clipp, Rachel B. Garcia, Guilherme J. M. Rhee, John S. Enquobahrie, Andinet Kitware Inc Med Comp Grp Carrboro NC 27510 USA Med Coll Wisconsin Dept Otolaryngol & Commun Sci Milwaukee WI USA Marquette Univ Dept Biomed Engn Milwaukee WI USA Med Coll Wisconsin Milwaukee WI USA

ISBN: (纸本)9781665473583

Nasal airway obstruction (NAO) is a condition where nasal passages are blocked, preventing normal airflow through the nose. NAO is one of the most common conditions treated by otolaryngologists using surgical procedures. However, surgical procedures have a high failure rate and surgery planning has the potential to improve surgical outcomes. However, current surgical planning systems are challenging to use, are not interactive, and don't consider physiological parameters. This paper reports the development of nSurgSim, an integrated virtual surgical planning application that incorporates model generation, computational fluid dynamics feedback, and patient-outcome analysis. We conducted a usability study with twenty-one board-certified ENT surgeons to evaluate the ease of use, perceived usefulness, and potential for clinical adoption. Overall, the study result shows nSurgSim will be a valuable tool in the ENT surgeon's arsenal for complex cases and a powerful tool for a general understanding of procedures and improvement in procedure outcomes.

关键词： Surgical Planning CFD segmentation image processing medical imaging

来源：评论

学校读者我要写书评

暂无评论

SSVT: Self-Supervised Vision Transformer For Eye Disease Diagnosis Based On Fundus images 21

SSVT: Self-Supervised Vision Transformer For Eye Disease Dia...

引用

21st ieee International symposium on Biomedical Imaging (ISBI)

作者： Wang, Jiaqi Kang, Mengtian Liu, Yong Zhang, Chi Liu, Ying Li, Shiming Qi, Yue Xu, Wenjun Tang, Chenyu Occhipinti, Edoardo Yusufu, Mayinuer Wang, Ningli Bai, Weiling Gao, Shuo Occhipinti, Luigi G. Beihang Univ Sch Instrumentat & Optoelect Engn Beijing Peoples R China Capital Med Univ Beijing Tongren Hosp Beijing Peoples R China Univ Melbourne Dept Surg Ophthalmol Melbourne Vic Australia Univ Cambridge Dept Engn Cambridge England Imperial Coll London Dept Comp UKRI Ctr Doctoral Training AI Healthcare London England

ISBN: (纸本)9798350313345;9798350313338

Machine learning-based fundus image diagnosis technologies trigger worldwide interest owing to their benefits such as reducing medical resource power and providing objective evaluation results. However, current methods are commonly based on supervised methods, bringing in a heavy workload to biomedical staff and hence suffering in expanding effective databases. To address this issue, in this article, we established a label-free method, named "SSVT", which can automatically analyze un-labeled fundus images and generate high evaluation accuracy of 97.0% of four main eye diseases based on six public datasets and two datasets collected by Beijing Tongren Hospital. The promising results showcased the effectiveness of the proposed unsupervised learning method, and the strong application potential in biomedical resource shortage regions to improve global eye health.

关键词： Eye Disease Diagnosis Fundus image processing Machine Learning Healthcare Self-supervised Learning

来源：评论

学校读者我要写书评

暂无评论

Symmetric Fine-Tuning for Improving Few-Shot Object Detection

Symmetric Fine-Tuning for Improving Few-Shot Object Detectio...

引用

2023 ieee symposium Series on computational intelligence, SSCI 2023

作者： Mpampis, Emmanouil Passalis, Nikolaos Tefas, Anastasios Aristotle University of Thessaloniki Computational Intelligence and Deep Learning Group AlIA Lab. Department of Informatics Thessaloniki Greece

ISBN: (纸本)9781665430654

Object detection plays a crucial role in automated image analysis by identifying and localizing objects within an image. One-stage Deep Learning (DL)-based object detectors have achieved impressive results, primarily due to large-scale datasets available for training them. However, these approaches rely heavily on abundant labeled data, posing challenges when only a few samples per class are available. To this end, few-shot object detection approaches have been proposed. Among them, fine-tuning the final detection head while keeping the feature extractor/backbone frozen is a commonly used approach for few-shot object detection. This approach effectively utilizes pre-existing knowledge encoded in the backbone, using a small number of samples to learn new object categories. However, in this paper, we argue that fine-tuning only the last layers may limit accuracy and lead to overfitting if the initial layers of the detection head are not adapted for the new task. The data processing inequality, which states that information lost in early network layers cannot be recovered in subsequent ones, supports this argument. To address this issue, we propose a symmetric fine-tuning method that involves both the first and last layers of the detection head, aiming to maintain a fixed trainable parameter budget while strategically selecting parameters for fine-tuning. Experimental results demonstrate the effectiveness and efficiency of this approach and open up several interesting future research directions. © 2023 ieee.

关键词： Few-shot Fine-Tuning Object detection Symmetric Fine-Tuning

来源：评论

学校读者我要写书评

暂无评论

A Low-Cost Passive Thermal IR Imaging System for Automated Hidden Object Detection Using AI 11

A Low-Cost Passive Thermal IR Imaging System for Automated H...

引用

11th International symposium on Telecommunication, IST 2024

作者： Amiri, Mohammad Javad Ghazanfari, Saman Sarmad, Mohammad Parsa Mirzaei Fakharzadeh, Mohammad Sharif University of Technology Electrical Engineering Department Tehran Iran

ISBN: (纸本)9798350356250

This paper presents a low-cost and AI-based automated solution for detecting hidden objects using thermal infrared imaging. We developed an affordable IR imaging setup and collected a comprehensive dataset of thermal images with different objects hidden under clothing. To overcome the challenges of low-resolution IR sensors, we implemented innovative signal processing techniques to enhance image quality, making it suitable for accurate object detection with AI. Meanwhile, a large dataset of over 1100 IR images with hidden objects was provided to train object detection algorithms, specifically YOLOv9 and RCNN. The average detection rate is close to 95%, which is higher than that of the similar work. Furthermore, we investigated the physics of thermal IR radiation, analyzing the temperature behavior of various concealed objects over time. © 2024 ieee.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：