Pub Date : 2024-08-05DOI: 10.3390/jimaging10080188
Entesar Z Dalah, Maryam K Alkaabi, Hashim M Al-Awadhi, Nisha A Antony
Screening mammography is considered to be the most effective means for the early detection of breast cancer. However, epidemiological studies suggest that longitudinal exposure to screening mammography may raise breast cancer radiation-induced risk, which begs the need for optimization and internal auditing. The present work aims to establish a comprehensive well-structured Diagnostic Reference Level (DRL) system that can be confidently used to highlight healthcare centers in need of urgent action, as well as cases exceeding the dose notification level. Screening mammographies from a total of 2048 women who underwent screening mammography at seven different healthcare centers were collected and retrospectively analyzed. The typical DRL for each healthcare center was established and defined as per (A) bilateral image view (left craniocaudal (LCC), right craniocaudal (RCC), left mediolateral oblique (LMLO), and right mediolateral oblique (RMLO)) and (B) structured compressed breast thickness (CBT) criteria. Following this, the local DRL value was established per the bilateral image views for each CBT group. Screening mammography data from a total of 8877 images were used to build this comprehensive DRL system (LCC: 2163, RCC: 2206, LMLO: 2288, and RMLO: 2220). CBTs were classified into eight groups of <20 mm, 20-29 mm, 30-39 mm, 40-49 mm, 50-59 mm, 60-69 mm, 70-79 mm, 80-89 mm, and 90-110 mm. Using the Kruskal-Wallis test, significant dose differences were observed between all seven healthcare centers offering screening mammography. The local DRL values defined per bilateral image views for the CBT group 60-69 mm were (1.24 LCC, 1.23 RCC, 1.34 LMLO, and 1.32 RMLO) mGy. The local DRL defined per bilateral image view for a specific CBT highlighted at least one healthcare center in need of optimization. Such comprehensive DRL system is efficient, easy to use, and very clinically effective.
乳腺 X 射线筛查被认为是早期发现乳腺癌的最有效手段。然而,流行病学研究表明,纵向暴露于乳腺 X 线照相筛查可能会增加乳腺癌辐射诱发风险,因此需要进行优化和内部审核。本研究旨在建立一个结构合理的综合诊断参考水平(DRL)系统,该系统可用于突出显示需要采取紧急行动的医疗保健中心以及超过剂量通知水平的病例。研究人员收集并回顾分析了在七家不同医疗中心接受乳腺 X 射线筛查的 2048 名妇女的乳腺 X 射线筛查照片。根据 (A) 双侧图像视图(左侧颅尾(LCC)、右侧颅尾(RCC)、左侧内外侧斜视(LMLO)和右侧内外侧斜视(RMLO))和 (B) 结构化压缩乳房厚度(CBT)标准,确定并定义了每个医疗中心的典型 DRL。然后,根据每个 CBT 组的双侧图像视图确定局部 DRL 值。该综合 DRL 系统共使用了 8877 张筛查乳腺 X 射线图像的数据(LCC:2163 张;RCC:2206 张;LMLO:2288 张;RMLO:2220 张)。CBT 被分为以下八组
{"title":"Screening Mammography Diagnostic Reference Level System According to Compressed Breast Thickness: Dubai Health.","authors":"Entesar Z Dalah, Maryam K Alkaabi, Hashim M Al-Awadhi, Nisha A Antony","doi":"10.3390/jimaging10080188","DOIUrl":"10.3390/jimaging10080188","url":null,"abstract":"<p><p>Screening mammography is considered to be the most effective means for the early detection of breast cancer. However, epidemiological studies suggest that longitudinal exposure to screening mammography may raise breast cancer radiation-induced risk, which begs the need for optimization and internal auditing. The present work aims to establish a comprehensive well-structured Diagnostic Reference Level (DRL) system that can be confidently used to highlight healthcare centers in need of urgent action, as well as cases exceeding the dose notification level. Screening mammographies from a total of 2048 women who underwent screening mammography at seven different healthcare centers were collected and retrospectively analyzed. The typical DRL for each healthcare center was established and defined as per (A) bilateral image view (left craniocaudal (LCC), right craniocaudal (RCC), left mediolateral oblique (LMLO), and right mediolateral oblique (RMLO)) and (B) structured compressed breast thickness (CBT) criteria. Following this, the local DRL value was established per the bilateral image views for each CBT group. Screening mammography data from a total of 8877 images were used to build this comprehensive DRL system (LCC: 2163, RCC: 2206, LMLO: 2288, and RMLO: 2220). CBTs were classified into eight groups of <20 mm, 20-29 mm, 30-39 mm, 40-49 mm, 50-59 mm, 60-69 mm, 70-79 mm, 80-89 mm, and 90-110 mm. Using the Kruskal-Wallis test, significant dose differences were observed between all seven healthcare centers offering screening mammography. The local DRL values defined per bilateral image views for the CBT group 60-69 mm were (1.24 LCC, 1.23 RCC, 1.34 LMLO, and 1.32 RMLO) mGy. The local DRL defined per bilateral image view for a specific CBT highlighted at least one healthcare center in need of optimization. Such comprehensive DRL system is efficient, easy to use, and very clinically effective.</p>","PeriodicalId":37035,"journal":{"name":"Journal of Imaging","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11355625/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142082083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study focuses on semantic segmentation in crop Opuntia spp. orthomosaics; this is a significant challenge due to the inherent variability in the captured images. Manual measurement of Opuntia spp. vegetation areas can be slow and inefficient, highlighting the need for more advanced and accurate methods. For this reason, we propose to use deep learning techniques to provide a more precise and efficient measurement of the vegetation area. Our research focuses on the unique difficulties posed by segmenting high-resolution images exceeding 2000 pixels, a common problem in generating orthomosaics for agricultural monitoring. The research was carried out on a Opuntia spp. cultivation located in the agricultural region of Tulancingo, Hidalgo, Mexico. The images used in this study were obtained by drones and processed using advanced semantic segmentation architectures, including DeepLabV3+, UNet, and UNet Style Xception. The results offer a comparative analysis of the performance of these architectures in the semantic segmentation of Opuntia spp., thus contributing to the development and improvement of crop analysis techniques based on deep learning. This work sets a precedent for future research applying deep learning techniques in agriculture.
{"title":"Semantic Segmentation in Large-Size Orthomosaics to Detect the Vegetation Area in <i>Opuntia</i> spp. Crop.","authors":"Arturo Duarte-Rangel, César Camacho-Bello, Eduardo Cornejo-Velazquez, Mireya Clavel-Maqueda","doi":"10.3390/jimaging10080187","DOIUrl":"10.3390/jimaging10080187","url":null,"abstract":"<p><p>This study focuses on semantic segmentation in crop <i>Opuntia</i> spp. orthomosaics; this is a significant challenge due to the inherent variability in the captured images. Manual measurement of <i>Opuntia</i> spp. vegetation areas can be slow and inefficient, highlighting the need for more advanced and accurate methods. For this reason, we propose to use deep learning techniques to provide a more precise and efficient measurement of the vegetation area. Our research focuses on the unique difficulties posed by segmenting high-resolution images exceeding 2000 pixels, a common problem in generating orthomosaics for agricultural monitoring. The research was carried out on a <i>Opuntia</i> spp. cultivation located in the agricultural region of Tulancingo, Hidalgo, Mexico. The images used in this study were obtained by drones and processed using advanced semantic segmentation architectures, including DeepLabV3+, UNet, and UNet Style Xception. The results offer a comparative analysis of the performance of these architectures in the semantic segmentation of <i>Opuntia</i> spp., thus contributing to the development and improvement of crop analysis techniques based on deep learning. This work sets a precedent for future research applying deep learning techniques in agriculture.</p>","PeriodicalId":37035,"journal":{"name":"Journal of Imaging","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11355387/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142082084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-31DOI: 10.3390/jimaging10080185
Ivan Galyaev, Alexey Mashtakov
An extended four-dimensional version of the traditional Petitot-Citti-Sarti model on contour completion in the visual cortex is examined. The neural configuration space is considered as the group of similarity transformations, denoted as M=SIM(2). The left-invariant subbundle of the tangent bundle models possible directions for establishing neural communication. The sub-Riemannian distance is proportional to the energy expended in interneuron activation between two excited border neurons. According to the model, the damaged image contours are restored via sub-Riemannian geodesics in the space M of positions, orientations and thicknesses (scales). We study the geodesic problem in M using geometric control theory techniques. We prove the existence of a minimal geodesic between arbitrary specified boundary conditions. We apply the Pontryagin maximum principle and derive the geodesic equations. In the special cases, we find explicit solutions. In the general case, we provide a qualitative analysis. Finally, we support our model with a simulation of the association field.
本文研究了传统的 Petitot-Citti-Sarti 模型在视觉皮层中轮廓完成的扩展四维版本。神经配置空间被视为相似性变换组,表示为 M=SIM(2)。切线束的左不变子束模拟了建立神经通信的可能方向。子黎曼距离与两个兴奋边界神经元之间的神经元间激活所消耗的能量成正比。根据该模型,受损的图像轮廓是通过位置、方向和厚度(尺度)空间 M 中的亚黎曼大地线恢复的。我们利用几何控制理论技术研究了 M 空间中的大地线问题。我们证明了在任意指定的边界条件之间存在一条最小的大地线。我们应用庞特里亚金最大原则,推导出大地方程。在特殊情况下,我们找到了显式解。在一般情况下,我们提供了定性分析。最后,我们通过模拟关联场来支持我们的模型。
{"title":"A Cortical-Inspired Contour Completion Model Based on Contour Orientation and Thickness.","authors":"Ivan Galyaev, Alexey Mashtakov","doi":"10.3390/jimaging10080185","DOIUrl":"10.3390/jimaging10080185","url":null,"abstract":"<p><p>An extended four-dimensional version of the traditional Petitot-Citti-Sarti model on contour completion in the visual cortex is examined. The neural configuration space is considered as the group of similarity transformations, denoted as M=SIM(2). The left-invariant subbundle of the tangent bundle models possible directions for establishing neural communication. The sub-Riemannian distance is proportional to the energy expended in interneuron activation between two excited border neurons. According to the model, the damaged image contours are restored via sub-Riemannian geodesics in the space <i>M</i> of positions, orientations and thicknesses (scales). We study the geodesic problem in <i>M</i> using geometric control theory techniques. We prove the existence of a minimal geodesic between arbitrary specified boundary conditions. We apply the Pontryagin maximum principle and derive the geodesic equations. In the special cases, we find explicit solutions. In the general case, we provide a qualitative analysis. Finally, we support our model with a simulation of the association field.</p>","PeriodicalId":37035,"journal":{"name":"Journal of Imaging","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11355450/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142082029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-31DOI: 10.3390/jimaging10080186
Chengran Li, Ajit Narayanan, Akbar Ghobakhlou
In the field of 2-D image processing and computer vision, accurately detecting and segmenting objects in scenarios where they overlap or are obscured remains a challenge. This difficulty is worse in the analysis of shoeprints used in forensic investigations because they are embedded in noisy environments such as the ground and can be indistinct. Traditional convolutional neural networks (CNNs), despite their success in various image analysis tasks, struggle with accurately delineating overlapping objects due to the complexity of segmenting intertwined textures and boundaries against a background of noise. This study introduces and employs the YOLO (You Only Look Once) model enhanced by edge detection and image segmentation techniques to improve the detection of overlapping shoeprints. By focusing on the critical boundary information between shoeprint textures and the ground, our method demonstrates improvements in sensitivity and precision, achieving confidence levels above 85% for minimally overlapped images and maintaining above 70% for extensively overlapped instances. Heatmaps of convolution layers were generated to show how the network converges towards successful detection using these enhancements. This research may provide a potential methodology for addressing the broader challenge of detecting multiple overlapping objects against noisy backgrounds.
{"title":"Overlapping Shoeprint Detection by Edge Detection and Deep Learning.","authors":"Chengran Li, Ajit Narayanan, Akbar Ghobakhlou","doi":"10.3390/jimaging10080186","DOIUrl":"10.3390/jimaging10080186","url":null,"abstract":"<p><p>In the field of 2-D image processing and computer vision, accurately detecting and segmenting objects in scenarios where they overlap or are obscured remains a challenge. This difficulty is worse in the analysis of shoeprints used in forensic investigations because they are embedded in noisy environments such as the ground and can be indistinct. Traditional convolutional neural networks (CNNs), despite their success in various image analysis tasks, struggle with accurately delineating overlapping objects due to the complexity of segmenting intertwined textures and boundaries against a background of noise. This study introduces and employs the YOLO (You Only Look Once) model enhanced by edge detection and image segmentation techniques to improve the detection of overlapping shoeprints. By focusing on the critical boundary information between shoeprint textures and the ground, our method demonstrates improvements in sensitivity and precision, achieving confidence levels above 85% for minimally overlapped images and maintaining above 70% for extensively overlapped instances. Heatmaps of convolution layers were generated to show how the network converges towards successful detection using these enhancements. This research may provide a potential methodology for addressing the broader challenge of detecting multiple overlapping objects against noisy backgrounds.</p>","PeriodicalId":37035,"journal":{"name":"Journal of Imaging","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11355314/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142082081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-30DOI: 10.3390/jimaging10080183
Shohag Barman, Fahmid Al Farid, Jaohar Raihan, Niaz Ashraf Khan, Md Ferdous Bin Hafiz, Aditi Bhattacharya, Zaeed Mahmud, Sadia Afrin Ridita, Md Tanjil Sarker, Hezerul Abdul Karim, Sarina Mansor
Agriculture plays a vital role in Bangladesh's economy. It is essential to ensure the proper growth and health of crops for the development of the agricultural sector. In the context of Bangladesh, crop diseases pose a significant threat to agricultural output and, consequently, food security. This necessitates the timely and precise identification of such diseases to ensure the sustainability of food production. This study focuses on building a hybrid deep learning model for the identification of three specific diseases affecting three major crops: late blight in potatoes, brown spot in rice, and common rust in corn. The proposed model leverages EfficientNetB0's feature extraction capabilities, known for achieving rapid high learning rates, coupled with the classification proficiency of SVMs, a well-established machine learning algorithm. This unified approach streamlines data processing and feature extraction, potentially improving model generalizability across diverse crops and diseases. It also aims to address the challenges of computational efficiency and accuracy that are often encountered in precision agriculture applications. The proposed hybrid model achieved 97.29% accuracy. A comparative analysis with other models, CNN, VGG16, ResNet50, Xception, Mobilenet V2, Autoencoders, Inception v3, and EfficientNetB0 each achieving an accuracy of 86.57%, 83.29%, 68.79%, 94.07%, 90.71%, 87.90%, 94.14%, and 96.14% respectively, demonstrated the superior performance of our proposed model.
{"title":"Optimized Crop Disease Identification in Bangladesh: A Deep Learning and SVM Hybrid Model for Rice, Potato, and Corn.","authors":"Shohag Barman, Fahmid Al Farid, Jaohar Raihan, Niaz Ashraf Khan, Md Ferdous Bin Hafiz, Aditi Bhattacharya, Zaeed Mahmud, Sadia Afrin Ridita, Md Tanjil Sarker, Hezerul Abdul Karim, Sarina Mansor","doi":"10.3390/jimaging10080183","DOIUrl":"10.3390/jimaging10080183","url":null,"abstract":"<p><p>Agriculture plays a vital role in Bangladesh's economy. It is essential to ensure the proper growth and health of crops for the development of the agricultural sector. In the context of Bangladesh, crop diseases pose a significant threat to agricultural output and, consequently, food security. This necessitates the timely and precise identification of such diseases to ensure the sustainability of food production. This study focuses on building a hybrid deep learning model for the identification of three specific diseases affecting three major crops: late blight in potatoes, brown spot in rice, and common rust in corn. The proposed model leverages EfficientNetB0's feature extraction capabilities, known for achieving rapid high learning rates, coupled with the classification proficiency of SVMs, a well-established machine learning algorithm. This unified approach streamlines data processing and feature extraction, potentially improving model generalizability across diverse crops and diseases. It also aims to address the challenges of computational efficiency and accuracy that are often encountered in precision agriculture applications. The proposed hybrid model achieved 97.29% accuracy. A comparative analysis with other models, CNN, VGG16, ResNet50, Xception, Mobilenet V2, Autoencoders, Inception v3, and EfficientNetB0 each achieving an accuracy of 86.57%, 83.29%, 68.79%, 94.07%, 90.71%, 87.90%, 94.14%, and 96.14% respectively, demonstrated the superior performance of our proposed model.</p>","PeriodicalId":37035,"journal":{"name":"Journal of Imaging","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11355783/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142082080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In radiation therapy, patient setup is important for improving treatment accuracy. The six-axis couch semi-automatically adjusts the patient's position; however, adjusting the patient to twist is difficult. In this study, we developed and evaluated a virtual reality setup training tool for medical students to understand and improve their patient setup skills for radiation therapy. First, we set up a simulated patient in a virtual space to reproduce the radiation treatment room. A gyro sensor was attached to the patient phantom in real space, and the twist of the phantom was linked to the patient in the virtual space. Training was conducted for 24 students, and their operation records were analyzed and evaluated. The training's efficacy was also evaluated through questionnaires provided at the end of the training. The total time required for patient setup tests before and after training decreased significantly from 331.9 s to 146.2 s. As a result of the questionnaire regarding the usability of training to the trainee, most were highly evaluated. We found that training significantly improved students' understanding of the patient setup. With the proposed system, trainees can experience a simulated setup that can aid in deepening their understanding of radiation therapy treatments.
{"title":"The Usefulness of a Virtual Environment-Based Patient Setup Training System for Radiation Therapy.","authors":"Toshioh Fujibuchi, Kosuke Kaneko, Hiroyuki Arakawa, Yoshihiro Okada","doi":"10.3390/jimaging10080184","DOIUrl":"10.3390/jimaging10080184","url":null,"abstract":"<p><p>In radiation therapy, patient setup is important for improving treatment accuracy. The six-axis couch semi-automatically adjusts the patient's position; however, adjusting the patient to twist is difficult. In this study, we developed and evaluated a virtual reality setup training tool for medical students to understand and improve their patient setup skills for radiation therapy. First, we set up a simulated patient in a virtual space to reproduce the radiation treatment room. A gyro sensor was attached to the patient phantom in real space, and the twist of the phantom was linked to the patient in the virtual space. Training was conducted for 24 students, and their operation records were analyzed and evaluated. The training's efficacy was also evaluated through questionnaires provided at the end of the training. The total time required for patient setup tests before and after training decreased significantly from 331.9 s to 146.2 s. As a result of the questionnaire regarding the usability of training to the trainee, most were highly evaluated. We found that training significantly improved students' understanding of the patient setup. With the proposed system, trainees can experience a simulated setup that can aid in deepening their understanding of radiation therapy treatments.</p>","PeriodicalId":37035,"journal":{"name":"Journal of Imaging","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11355315/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142082087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-29DOI: 10.3390/jimaging10080181
Stefan Baar, Masahiro Kuragano, Naoki Nishishita, Kiyotaka Tokuraku, Shinya Watanabe
When analyzing microscopic time-lapse observations, frame alignment is an essential task to visually understand the morphological and translation dynamics of cells and tissue. While in traditional single-sample microscopy, the region of interest (RoI) is fixed, multi-sample microscopy often uses a single microscope that scans multiple samples over a long period of time by laterally relocating the sample stage. Hence, the relocation of the optics induces a statistical RoI offset and can introduce jitter as well as drift, which results in a misaligned RoI for each sample's time-lapse observation (stage drift). We introduce a robust approach to automatically align all frames within a time-lapse observation and compensate for frame drift. In this study, we present a sub-pixel precise alignment approach based on recurrent all-pairs field transforms (RAFT); a deep network architecture for optical flow. We show that the RAFT model pre-trained on the Sintel dataset performed with near perfect precision for registration tasks on a set of ten contextually unrelated time-lapse observations containing 250 frames each. Our approach is robust for elastically undistorted and translation displaced (x,y) microscopic time-lapse observations and was tested on multiple samples with varying cell density, obtained using different devices. The approach only performed well for registration and not for tracking of the individual image components like cells and contaminants. We provide an open-source command-line application that corrects for stage drift and jitter.
在分析显微延时观察结果时,帧对准是直观了解细胞和组织形态及翻译动态的一项基本任务。在传统的单样品显微镜中,感兴趣区(RoI)是固定的,而多样品显微镜通常使用一台显微镜,通过横向移动样品台来长时间扫描多个样品。因此,光学器件的移动会引起统计上的 RoI 偏移,并可能引入抖动和漂移,从而导致每个样本的延时观测出现 RoI 错位(平台漂移)。我们引入了一种稳健的方法来自动对齐延时观测中的所有帧,并补偿帧漂移。在这项研究中,我们提出了一种基于递归全对场变换(RAFT)的亚像素精确对齐方法;RAFT 是一种用于光流的深度网络架构。我们的研究表明,在 Sintel 数据集上预先训练的 RAFT 模型在一组包含 250 个帧的 10 个上下文无关的延时观测数据的配准任务中表现出近乎完美的精度。我们的方法对于无弹性失真和平移位移(x,y)的显微延时观察结果具有鲁棒性,并在使用不同设备获得的具有不同细胞密度的多个样本上进行了测试。该方法仅在配准方面表现出色,而在跟踪细胞和污染物等单个图像组件方面却不尽如人意。我们提供了一个开源的命令行应用程序,可以校正平台漂移和抖动。
{"title":"Fiduciary-Free Frame Alignment for Robust Time-Lapse Drift Correction Estimation in Multi-Sample Cell Microscopy.","authors":"Stefan Baar, Masahiro Kuragano, Naoki Nishishita, Kiyotaka Tokuraku, Shinya Watanabe","doi":"10.3390/jimaging10080181","DOIUrl":"10.3390/jimaging10080181","url":null,"abstract":"<p><p>When analyzing microscopic time-lapse observations, frame alignment is an essential task to visually understand the morphological and translation dynamics of cells and tissue. While in traditional single-sample microscopy, the region of interest (RoI) is fixed, multi-sample microscopy often uses a single microscope that scans multiple samples over a long period of time by laterally relocating the sample stage. Hence, the relocation of the optics induces a statistical RoI offset and can introduce jitter as well as drift, which results in a misaligned RoI for each sample's time-lapse observation (stage drift). We introduce a robust approach to automatically align all frames within a time-lapse observation and compensate for frame drift. In this study, we present a sub-pixel precise alignment approach based on recurrent all-pairs field transforms (RAFT); a deep network architecture for optical flow. We show that the RAFT model pre-trained on the Sintel dataset performed with near perfect precision for registration tasks on a set of ten contextually unrelated time-lapse observations containing 250 frames each. Our approach is robust for elastically undistorted and translation displaced (x,y) microscopic time-lapse observations and was tested on multiple samples with varying cell density, obtained using different devices. The approach only performed well for registration and not for tracking of the individual image components like cells and contaminants. We provide an open-source command-line application that corrects for stage drift and jitter.</p>","PeriodicalId":37035,"journal":{"name":"Journal of Imaging","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11355451/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142082074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-29DOI: 10.3390/jimaging10080182
Marco Conti, Francesca Morciano, Silvia Amodeo, Elisabetta Gori, Giovanna Romanucci, Paolo Belli, Oscar Tommasini, Francesca Fornasa, Rossella Rella
Breast cancer is a complex disease that includes entities with different characteristics, behaviors, and responses to treatment. Breast cancers are categorized into subgroups based on histological type and grade, and these subgroups affect clinical presentation and oncological outcomes. The subgroup of "special types" encompasses all those breast cancers with insufficient features to belong to the subgroup "invasive ductal carcinoma not otherwise specified". These cancers account for around 25% of all cases, some of them having a relatively good prognosis despite high histological grade. The purpose of this paper is to review and illustrate the radiological appearance of each special type, highlighting insights and pitfalls to guide breast radiologists in their routine work.
{"title":"Special Types of Breast Cancer: Clinical Behavior and Radiological Appearance.","authors":"Marco Conti, Francesca Morciano, Silvia Amodeo, Elisabetta Gori, Giovanna Romanucci, Paolo Belli, Oscar Tommasini, Francesca Fornasa, Rossella Rella","doi":"10.3390/jimaging10080182","DOIUrl":"10.3390/jimaging10080182","url":null,"abstract":"<p><p>Breast cancer is a complex disease that includes entities with different characteristics, behaviors, and responses to treatment. Breast cancers are categorized into subgroups based on histological type and grade, and these subgroups affect clinical presentation and oncological outcomes. The subgroup of \"special types\" encompasses all those breast cancers with insufficient features to belong to the subgroup \"invasive ductal carcinoma not otherwise specified\". These cancers account for around 25% of all cases, some of them having a relatively good prognosis despite high histological grade. The purpose of this paper is to review and illustrate the radiological appearance of each special type, highlighting insights and pitfalls to guide breast radiologists in their routine work.</p>","PeriodicalId":37035,"journal":{"name":"Journal of Imaging","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11355320/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142082086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-24DOI: 10.3390/jimaging10080180
Birthe Göbel, Alexander Reiterer, Knut Möller
Image-based 3D reconstruction enables laparoscopic applications as image-guided navigation and (autonomous) robot-assisted interventions, which require a high accuracy. The review’s purpose is to present the accuracy of different techniques to label the most promising. A systematic literature search with PubMed and google scholar from 2015 to 2023 was applied by following the framework of “Review articles: purpose, process, and structure”. Articles were considered when presenting a quantitative evaluation (root mean squared error and mean absolute error) of the reconstruction error (Euclidean distance between real and reconstructed surface). The search provides 995 articles, which were reduced to 48 articles after applying exclusion criteria. From these, a reconstruction error data set could be generated for the techniques of stereo vision, Shape-from-Motion, Simultaneous Localization and Mapping, deep-learning, and structured light. The reconstruction error varies from below one millimeter to higher than ten millimeters—with deep-learning and Simultaneous Localization and Mapping delivering the best results under intraoperative conditions. The high variance emerges from different experimental conditions. In conclusion, submillimeter accuracy is challenging, but promising image-based 3D reconstruction techniques could be identified. For future research, we recommend computing the reconstruction error for comparison purposes and use ex/in vivo organs as reference objects for realistic experiments.
{"title":"Image-Based 3D Reconstruction in Laparoscopy: A Review Focusing on the Quantitative Evaluation by Applying the Reconstruction Error","authors":"Birthe Göbel, Alexander Reiterer, Knut Möller","doi":"10.3390/jimaging10080180","DOIUrl":"https://doi.org/10.3390/jimaging10080180","url":null,"abstract":"Image-based 3D reconstruction enables laparoscopic applications as image-guided navigation and (autonomous) robot-assisted interventions, which require a high accuracy. The review’s purpose is to present the accuracy of different techniques to label the most promising. A systematic literature search with PubMed and google scholar from 2015 to 2023 was applied by following the framework of “Review articles: purpose, process, and structure”. Articles were considered when presenting a quantitative evaluation (root mean squared error and mean absolute error) of the reconstruction error (Euclidean distance between real and reconstructed surface). The search provides 995 articles, which were reduced to 48 articles after applying exclusion criteria. From these, a reconstruction error data set could be generated for the techniques of stereo vision, Shape-from-Motion, Simultaneous Localization and Mapping, deep-learning, and structured light. The reconstruction error varies from below one millimeter to higher than ten millimeters—with deep-learning and Simultaneous Localization and Mapping delivering the best results under intraoperative conditions. The high variance emerges from different experimental conditions. In conclusion, submillimeter accuracy is challenging, but promising image-based 3D reconstruction techniques could be identified. For future research, we recommend computing the reconstruction error for comparison purposes and use ex/in vivo organs as reference objects for realistic experiments.","PeriodicalId":37035,"journal":{"name":"Journal of Imaging","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141807286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-24DOI: 10.3390/jimaging10080179
Rhys G. Evans, Ester Devlieghere, Robrecht Keijzer, J. Dirckx, S. Van der Jeught
In 3D optical metrology, single-shot deep learning-based structured light profilometry (SS-DL-SLP) has gained attention because of its measurement speed, simplicity of optical setup, and robustness to noise and motion artefacts. However, gathering a sufficiently large training dataset for these techniques remains challenging because of practical limitations. This paper presents a comprehensive DL-SLP dataset of over 10,000 physical data couples. The dataset was constructed by 3D-printing a calibration target featuring randomly varying surface profiles and storing the height profiles and the corresponding deformed fringe patterns. Our dataset aims to serve as a benchmark for evaluating and comparing different models and network architectures in DL-SLP. We performed an analysis of several established neural networks, demonstrating high accuracy in obtaining full-field height information from previously unseen fringe patterns. In addition, the network was validated on unique objects to test the overall robustness of the trained model. To facilitate further research and promote reproducibility, all code and the dataset are made publicly available. This dataset will enable researchers to explore, develop, and benchmark novel DL-based approaches for SS-DL-SLP.
{"title":"Deep Learning for Single-Shot Structured Light Profilometry: A Comprehensive Dataset and Performance Analysis","authors":"Rhys G. Evans, Ester Devlieghere, Robrecht Keijzer, J. Dirckx, S. Van der Jeught","doi":"10.3390/jimaging10080179","DOIUrl":"https://doi.org/10.3390/jimaging10080179","url":null,"abstract":"In 3D optical metrology, single-shot deep learning-based structured light profilometry (SS-DL-SLP) has gained attention because of its measurement speed, simplicity of optical setup, and robustness to noise and motion artefacts. However, gathering a sufficiently large training dataset for these techniques remains challenging because of practical limitations. This paper presents a comprehensive DL-SLP dataset of over 10,000 physical data couples. The dataset was constructed by 3D-printing a calibration target featuring randomly varying surface profiles and storing the height profiles and the corresponding deformed fringe patterns. Our dataset aims to serve as a benchmark for evaluating and comparing different models and network architectures in DL-SLP. We performed an analysis of several established neural networks, demonstrating high accuracy in obtaining full-field height information from previously unseen fringe patterns. In addition, the network was validated on unique objects to test the overall robustness of the trained model. To facilitate further research and promote reproducibility, all code and the dataset are made publicly available. This dataset will enable researchers to explore, develop, and benchmark novel DL-based approaches for SS-DL-SLP.","PeriodicalId":37035,"journal":{"name":"Journal of Imaging","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141806417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}