Journal of Imaging最新文献

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.

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.

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.

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.

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.

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.

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.

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.