Influence of deep learning image reconstruction algorithm for reducing radiation dose and image noise compared to iterative reconstruction and filtered back projection for head and chest computed tomography examinations: a systematic review.

Background: The most recent advances in Computed Tomography (CT) image reconstruction technology are Deep learning image reconstruction (DLIR) algorithms. Due to drawbacks in Iterative reconstruction (IR) techniques such as negative image texture and nonlinear spatial resolutions, DLIRs are gradually replacing them. However, the potential use of DLIR in Head and Chest CT has to be examined further. Hence, the purpose of the study is to review the influence of DLIR on Radiation dose (RD), Image noise (IN), and outcomes of the studies compared with IR and FBP in Head and Chest CT examinations. Methods: We performed a detailed search in PubMed, Scopus, Web of Science, Cochrane Library, and Embase to find the articles reported using DLIR for Head and Chest CT examinations between 2017 to 2023. Data were retrieved from the short-listed studies using Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) guidelines. Results: Out of 196 articles searched, 15 articles were included. A total of 1292 sample size was included. 14 articles were rated as high and 1 article as moderate quality. All studies compared DLIR to IR techniques. 5 studies compared DLIR with IR and FBP. The review showed that DLIR improved IQ, and reduced RD and IN for CT Head and Chest examinations. Conclusions: DLIR algorithm have demonstrated a noted enhancement in IQ with reduced IN for CT Head and Chest examinations at lower dose compared with IR and FBP. DLIR showed potential for enhancing patient care by reducing radiation risks and increasing diagnostic accuracy.

Student Observations Reveal Gaps Between Chest Imaging Theory and Practice.

PURPOSE: To assess whether first-year radiography students observed differences between what they were taught in didactic and laboratory courses and how technologists perform chest imaging procedures during clinical experiences. METHODS: This study used a mixed-methods approach with a cross-sectional survey, consisting of 11 quantitative and 11 qualitative items, during the fall 2020 semester. The survey asked participants to evaluate survey statements based on their observations of radiographers' behaviors during chest imaging procedures in relation to the 11 American Registry of Radiologic Technologist clinical competency areas. Participants rated their evaluations based on the degree to which they agreed or disagreed with statements regarding radiographers' behaviors using a 5-point Likert scale, ranging from strongly disagree (1) to strongly agree (5). For each statement, a follow-up, open-ended question asked participants to provide reasons why they thought technologists did or did not exhibit certain behaviors. Data were analyzed quantitatively with differential statistics and qualitatively by thematically categorizing open-ended responses. RESULTS: A total of 19 first-year radiography students (N = 19) completed the survey. Most participants somewhat agreed or strongly agreed with 8 out of the 11 competency statements based on their observations of technologists when performing chest imaging procedures: room preparation (73.7%), patient identity verification (89.5%), examination order verification (79%), patient assessment (79%), equipment operation (52.6%), patient management (100%), technique selection (73.6%), and image evaluation (94.7%). Most participants somewhat disagreed, strongly disagreed, or were neutral with 3 out of the 11 categories: patient positioning, radiation safety, and image processing. Qualitatively, participants responded that technologists only provided lead shielding for pediatric patients, were not instructing patients to take 2 inspirations before making an exposure, and were cropping their images electronically before submitting them for diagnoses. DISCUSSION: Participants reported inconsistencies between what they were taught and what they saw technologists doing during chest imaging procedures related to patient positioning, radiation safety, and imaging processing. Participants' responses stated that these inconsistencies might be because of an increase in technologist responsibilities, patient volumes, and fear of not including relative anatomy on their images. CONCLUSION: Participants reported the most disagreement with radiation safety during chest imaging procedures. Although lead shielding for abdominal and pelvic procedures is no longer recommended, shielding patients during chest imaging procedures is still recommended. Radiography programs can educate students that inconsistency between task order does not mean there is a gap between theory and practice.

Evaluating GPT-V4 (GPT-4 with Vision) on Detection of Radiologic Findings on Chest Radiographs.

Background Generating radiologic findings from chest radiographs is pivotal in medical image analysis. The emergence of OpenAI's generative pretrained transformer, GPT-4 with vision (GPT-4V), has opened new perspectives on the potential for automated image-text pair generation. However, the application of GPT-4V to real-world chest radiography is yet to be thoroughly examined. Purpose To investigate the capability of GPT-4V to generate radiologic findings from real-world chest radiographs. Materials and Methods In this retrospective study, 100 chest radiographs with free-text radiology reports were annotated by a cohort of radiologists, two attending physicians and three residents, to establish a reference standard. Of 100 chest radiographs, 50 were randomly selected from the National Institutes of Health (NIH) chest radiographic data set, and 50 were randomly selected from the Medical Imaging and Data Resource Center (MIDRC). The performance of GPT-4V at detecting imaging findings from each chest radiograph was assessed in the zero-shot setting (where it operates without prior examples) and few-shot setting (where it operates with two examples). Its outcomes were compared with the reference standard with regards to clinical conditions and their corresponding codes in the International Statistical Classification of Diseases, Tenth Revision (ICD-10), including the anatomic location (hereafter, laterality). Results In the zero-shot setting, in the task of detecting ICD-10 codes alone, GPT-4V attained an average positive predictive value (PPV) of 12.3%, average true-positive rate (TPR) of 5.8%, and average F1 score of 7.3% on the NIH data set, and an average PPV of 25.0%, average TPR of 16.8%, and average F1 score of 18.2% on the MIDRC data set. When both the ICD-10 codes and their corresponding laterality were considered, GPT-4V produced an average PPV of 7.8%, average TPR of 3.5%, and average F1 score of 4.5% on the NIH data set, and an average PPV of 10.9%, average TPR of 4.9%, and average F1 score of 6.4% on the MIDRC data set. With few-shot learning, GPT-4V showed improved performance on both data sets. When contrasting zero-shot and few-shot learning, there were improved average TPRs and F1 scores in the few-shot setting, but there was not a substantial increase in the average PPV. Conclusion Although GPT-4V has shown promise in understanding natural images, it had limited effectiveness in interpreting real-world chest radiographs. © RSNA, 2024 Supplemental material is available for this article.

Quantitative analysis of lung lesions using unenhanced chest computed tomography images.

INTRODUCTION: Chest radiograph and computed tomography (CT) scans can accidentally reveal pulmonary nodules. Malignant and benign pulmonary nodules can be difficult to distinguish without specific imaging features, such as calcification, necrosis, and contrast enhancement. However, these lesions may exhibit different image texture characteristics which cannot be assessed visually. Thus, a computer-assisted quantitative method like histogram analysis (HA) of Hounsfield unit (HU) values can improve diagnostic accuracy, reducing the need for invasive biopsy. METHODS: In this exploratory control study, nonenhanced chest CT images of 20 patients with benign (10) and cancerous (10) lesion were selected retrospectively. The appearances of benign and malignant lesions were very similar in chest CT images, and only pathology report was used to discriminate them. Free hand region of interest (ROI) was inserted inside the lesion for all slices of each lesion. Mean, minimum, maximum, and standard deviations of HU values were recorded and used to make HA. RESULTS: HA showed that the most malignant lesions have a mean HU value between 30 and 50, a maximum HU less than 150, and a minimum HU between -30 and 20. Lesions outside these ranges were mostly benign. CONCLUSION: Quantitative CT analysis may differentiate malignant from benign lesions without specific malignancy patterns on unenhanced chest CT image.

Which is a real valuable screening tool for lung cancer and measure thoracic diseases, chest radiography or low-dose computed tomography?: A review on the current status of Japan and other countries.

Chest radiography (CR) has been used as a screening tool for lung cancer and the use of low-dose computed tomography (LDCT) is not recommended in Japan. We need to reconsider whether CR really contributes to the early detection of lung cancer. In addition, we have not well discussed about other major thoracic disease detection by CR and LDCT compared with lung cancer despite of its high frequency. We review the usefulness of CR and LDCT as veridical screening tools for lung cancer and other thoracic diseases. In the case of lung cancer, many studies showed that LDCT has capability of early detection and improving outcomes compared with CR. Recent large randomized trial also supports former results. In the case of chronic obstructive pulmonary disease (COPD), LDCT contributes to early detection and leads to the implementation of smoking cessation treatments. In the case of pulmonary infections, LDCT can reveal tiny inflammatory changes that are not observed on CR, though many of these cases improve spontaneously. Therefore, LDCT screening for pulmonary infections may be less useful. CR screening is more suitable for the detection of pulmonary infections. In the case of cardiovascular disease (CVD), CR may be a better screening tool for detecting cardiomegaly, whereas LDCT may be a more useful tool for detecting vascular changes. Therefore, the current status of thoracic disease screening is that LDCT may be a better screening tool for detecting lung cancer, COPD, and vascular changes. CR may be a suitable screening tool for pulmonary infections and cardiomegaly.

CNN application for automated determination of the patient's size to obtain the size-specific dose estimated in CT.

Introduction. The currently available dosimetry techniques in computed tomography can be inaccurate which overestimate the absorbed dose. Therefore, we aimed to provide an automated and fast methodology to more accurately calculate the SSDE usingDwobtained by using CNN from thorax and abdominal CT study images.Methods. The SSDE was determined from the 200 records files. For that purpose, patients' size was measured in two ways: (a) by developing an algorithm following the AAPM Report No. 204 methodology; and (b) using a CNN according to AAPM Report No. 220.Results. The patient's size measured by the in-house software in the region of thorax and abdomen was 27.63 ± 3.23 cm and 28.66 ± 3.37 cm, while CNN was 18.90 ± 2.6 cm and 21.77 ± 2.45 cm. The SSDE in thorax according to 204 and 220 reports were 17.26 ± 2.81 mGy and 23.70 ± 2.96 mGy for women and 17.08 ± 2.09 mGy and 23.47 ± 2.34 mGy for men. In abdomen was 18.54 ± 2.25 mGy and 23.40 ± 1.88 mGy in women and 18.37 ± 2.31 mGy and 23.84 ± 2.36 mGy in men.Conclusions. Implementing CNN-based automated methodologies can contribute to fast and accurate dose calculations, thereby improving patient-specific radiation safety in clinical practice.

Artificial intelligence in the healthcare sector: comparison of deep learning networks using chest X-ray images.

Purpose: Artificial intelligence has led to significant developments in the healthcare sector, as in other sectors and fields. In light of its significance, the present study delves into exploring deep learning, a branch of artificial intelligence. Methods: In the study, deep learning networks ResNet101, AlexNet, GoogLeNet, and Xception were considered, and it was aimed to determine the success of these networks in disease diagnosis. For this purpose, a dataset of 1,680 chest X-ray images was utilized, consisting of cases of COVID-19, viral pneumonia, and individuals without these diseases. These images were obtained by employing a rotation method to generate replicated data, wherein a split of 70 and 30% was adopted for training and validation, respectively. Results: The analysis findings revealed that the deep learning networks were successful in classifying COVID-19, Viral Pneumonia, and Normal (disease-free) images. Moreover, an examination of the success levels revealed that the ResNet101 deep learning network was more successful than the others with a 96.32% success rate. Conclusion: In the study, it was seen that deep learning can be used in disease diagnosis and can help experts in the relevant field, ultimately contributing to healthcare organizations and the practices of country managers.

Deep learning model for pleural effusion detection via active learning and pseudo-labeling: a multisite study.

BACKGROUND: The study aimed to develop and validate a deep learning-based Computer Aided Triage (CADt) algorithm for detecting pleural effusion in chest radiographs using an active learning (AL) framework. This is aimed at addressing the critical need for a clinical grade algorithm that can timely diagnose pleural effusion, which affects approximately 1.5 million people annually in the United States. METHODS: In this multisite study, 10,599 chest radiographs from 2006 to 2018 were retrospectively collected from an institution in Taiwan to train the deep learning algorithm. The AL framework utilized significantly reduced the need for expert annotations. For external validation, the algorithm was tested on a multisite dataset of 600 chest radiographs from 22 clinical sites in the United States and Taiwan, which were annotated by three U.S. board-certified radiologists. RESULTS: The CADt algorithm demonstrated high effectiveness in identifying pleural effusion, achieving a sensitivity of 0.95 (95% CI: [0.92, 0.97]) and a specificity of 0.97 (95% CI: [0.95, 0.99]). The area under the receiver operating characteristic curve (AUC) was 0.97 (95% DeLong's CI: [0.95, 0.99]). Subgroup analyses showed that the algorithm maintained robust performance across various demographics and clinical settings. CONCLUSION: This study presents a novel approach in developing clinical grade CADt solutions for the diagnosis of pleural effusion. The AL-based CADt algorithm not only achieved high accuracy in detecting pleural effusion but also significantly reduced the workload required for clinical experts in annotating medical data. This method enhances the feasibility of employing advanced technological solutions for prompt and accurate diagnosis in medical settings.

Target sign in COVID-19, radiological interpretation and diagnostic contribution of digital thoracic tomosynthesis.

INTRODUCTION: Our objectives are: To describe the radiological semiology, clinical-analytical features and prognosis related to the target sign (TS) in COVID-19. To determine whether digital thoracic tomosynthesis (DTT) improves the diagnostic ability of radiography. MATERIAL AND METHODS: Retrospective, descriptive, single-centre, case series study, accepted by our ethical committee. Radiological, clinical, analytical and follow-up characteristics of patients with COVID-19 and TS on radiography and DTT between November 2020 and January 2021 were analysed. RESULTS: Eleven TS were collected in 7 patients, median age 35 years, 57% male. All TS presented with a central nodule and a peripheral ring, and in at least 82%, the lung in between was of normal density. All TS were located in peripheral, basal regions and 91% in posterior regions. TS were multiple in 43%. Contiguous TS shared the peripheral ring. Other findings related to pneumonia were associated in 86% of patients. DTT detected 82% more TS than radiography. Only one patient underwent a CT angiography of the pulmonary arteries, positive for acute pulmonary thromboembolism. Seventy-one per cent presented with pleuritic pain. No distinctive laboratory findings or prognostic worsening were detected. CONCLUSIONS: TS in COVID-19 predominates in peripheral and declining regions and can be multiple. Pulmonary thromboembolism was detected in one case. It occurs in young people, frequently with pleuritic pain and does not worsen the prognosis. DTT detects more than 80 % of TS than radiography.

The role of chest X-ray in the diagnosis of neonatal respiratory distress syndrome: a systematic review concerning low-resource birth scenarios.

BACKGROUND: Access to diagnostic tools like chest radiography (CXR) is challenging in resource-limited areas. Despite reduced reliance on CXR due to the need for quick clinical decisions, its usage remains prevalent in the approach to neonatal respiratory distress syndrome (NRDS). OBJECTIVES: To assess CXR's role in diagnosing and grading NRDS severity compared to current clinical features and laboratory standards. METHODS: A review of studies with NRDS diagnostic criteria was conducted across six databases (MEDLINE, EMBASE, BVS, Scopus-Elsevier, Web of Science, Cochrane) up to 3 March 2023. Independent reviewers selected studies, with discrepancies resolved by a senior reviewer. Data were organised into descriptive tables to highlight the use of CXR and clinical indicators of NRDS. RESULTS: Out of 1,686 studies screened, 23 were selected, involving a total of 2,245 newborns. All selected studies used CXR to diagnose NRDS, and 21 (91%) applied it to assess disease severity. While seven reports (30%) indicated that CXR is irreplaceable by other diagnostic tools for NRDS diagnosis, 10 studies (43%) found that alternative methods surpassed CXR in several respects, such as severity assessment, monitoring progress, predicting the need for surfactant therapy, foreseeing Continuous Positive Airway Pressure failure, anticipating intubation requirements, and aiding in differential diagnosis. CONCLUSION: CXR remains an important diagnostic tool for NRDS. Despite its continued use in scientific reports, the findings suggest that the study's outcomes may not fully reflect the current global clinical practices, especially in low-resource settings where the early NRDS approach remains a challenge for neonatal survival.Trial registration: PROSPERO number CRD42022336480.

Main findings: Access to diagnostic tools like chest radiography is challenging in resource-limited areas, yet its usage persists in the management of neonatal respiratory distress syndrome despite a decreased dependency due to the imperative for swift clinical decisions.Added knowledge: Despite its continued significance in scientific literature, the usage of chest radiography as a diagnostic tool for neonatal respiratory distress syndrome may not entirely reflect current global clinical practices, particularly in low-resource settings where early management of neonatal respiratory distress syndrome poses a challenge for neonatal survival.Global health impact for policy and action: The results underscore the necessity of guidelines for the utilisation of chest radiography to minimise unnecessary ionising radiation exposure while ensuring timely access to critical clinical information for appropriate newborn care.

Size specific dose estimation in pediatric CT: preliminary study and conversion factors.

The objective of this paper is to compare the differences between volumetric CT dose index (CTDIVOL) and size-specific dose estimate (SSDEWED) based on water equivalent diameter (WED) in radiation dose measurement, and explore a new method for fast calculation of SSDEWED. The imaging data of 1238 cases of head, 1152 cases of chest and 976 cases of abdominopelvic were analyzed retrospectively, and they were divided into five age groups: ≤ 0.5, 0.5 ~ ≤ 1, 1 ~ ≤ 5, 5 ~ ≤ 10 and 10 ~ ≤ 15 years according to age. The area of interest (AR), CT value (CTR), lateral diameter (LAT) and anteroposterior diameter (AP) of the median cross-sectional image of the standard scanning range and the SSDEWED were manually calculated, and a t-test was used to compare the differences between CTDIVOL and SSDEWED in different age groups. Pearson analyzed the correlations between DE and age, DE and WED, f and age, and counted the means of conversion factors in each age group, and analyze the error ratios between SSDE calculated based on the mean age group conversion factors and actual measured SSDE. The CTDIVOL in head was (9.41 ± 1.42) mGy and the SSDEWED was (8.25 ± 0.70) mGy: the difference was statistically significant (t = 55.04, P < 0.001); the CTDIVOL of chest was (2.68 ± 0.91) mGy and the SSDEWED was (5.16 ± 1.16) mGy, with a statistically significant difference (t = -218.78, P < 0.001); the CTDIVOL of abdominopelvic was (3.09 ± 1.58) mGy and the SSDEWED was (5.89 ± 2.19) mGy: the difference was also statistically significant (t = -112.28, P < 0.001). The CTDIVOL was larger than the SSDEWED in the head except for the ≤ 0.5 year subgroup, and CTDIVOL was smaller than SSDEWED within each subgroup in chest and abdominopelvic. There were strong negative correlations between f and age (head: r = -0.81; chest: r = -0.89; abdominopelvic: r = -0.86; P < 0.001). The mean values of f at each examination region were 0.81 ~ 1.01 for head, 1.65 ~ 2.34 for chest and 1.71 ~ 2.35 for abdominopelvic region. The SSDEWED could be accurately estimated using the mean f of each age subgroup. SSDEWED can more accurately measure the radiation dose of children. For children of different ages and examination regions, the SSDEWED conversion factors based on age subgroup can be quickly adjusted and improve the accuracy of radiation dose estimation.

Multitask Adversarial Networks Based on Extensive Nonlinear Spiking Neuron Models.

Deep learning technology has been successfully used in Chest X-ray (CXR) images of COVID-19 patients. However, due to the characteristics of COVID-19 pneumonia and X-ray imaging, the deep learning methods still face many challenges, such as lower imaging quality, fewer training samples, complex radiological features and irregular shapes. To address these challenges, this study first introduces an extensive NSNP-like neuron model, and then proposes a multitask adversarial network architecture based on ENSNP-like neurons for chest X-ray images of COVID-19, called MAE-Net. The MAE-Net serves two tasks: (i) converting low-quality CXR images to high-quality images; (ii) classifying CXR images of COVID-19. The adversarial architecture of MAE-Net uses two generators and two discriminators, and two new loss functions have been introduced to guide the optimization of the network. The MAE-Net is tested on four benchmark COVID-19 CXR image datasets and compared them with eight deep learning models. The experimental results show that the proposed MAE-Net can enhance the conversion quality and the accuracy of image classification results.

Paciente varón de tres años con sibilancias y tos crónica / Three-Year-Old Male with Wheezing and Chronic Cough

Se presenta el caso de un niño de 3 años con diagnóstico de asma, rinitis alérgica, características craneofaciales dismórficas e infecciones respiratorias altas y bajas recurrentes, manejado como asma desde un inicio. Como parte del estudio de comorbilidades, se decide realizar una prueba del sudor que sale en rango intermedio y más tarde se encuentra una mutación, donde se obtiene un resultado positivo para una copia que se asocia a fibrosis quística. Se revisará el caso, así como el diagnóstico, clínica y tratamiento del síndrome metabólico relacionado con el regulador de conductancia transmembrana de fibrosis quística (CRMS).

We present the case of a 3-year-old boy with a diagnosis of asthma, allergic rhinitis, dysmorphic craniofacial characteristics and recurrent upper and lower respiratory infections, managed as asthma from the beginning. As part of the study of comorbidi-ties, it was decided to carry out a sweat test that came out in the intermediate range and later one mutation was found, where a positive result was obtained for a copy that is associated with cystic fibrosis. The case will be reviewed, as well as the diagnosis, symptoms and treatment of the metabolic syndrome related to the cystic fibrosis trans-membrane conductance regulator (CRMS).

X-ray interpretation in emergency department in the Kingdom of Saudi Arabia. Do we need the radiologist?

INTRODUCTION: Chest x-rays are widely used for diagnosing chest pathology worldwide. Pediatricians frequently interpret chest radiographs in the emergency department, guiding patient management. This study aims to assess the competency of non-radiologists in interpreting emergency chest x-rays and compare it with trainees of different levels to determine the necessity of radiologist input. METHODOLOGY: A cross-sectional online survey was conducted in Saudi Arabia from September to October 2023, involving 385 participants, including pediatricians and medical interns from various regions. Carefully selected questions addressed a range of x-ray abnormalities in pediatric emergencies, assessing fundamental understanding of x-ray interpretation, such as inspiratory vs. expiratory and AP or PA films. RESULTS: The study included 385 participants, primarily Saudi nationals in the eastern region, with an equal gender distribution and ages ranging from 20 to 29 years. Approximately 29.09% demonstrated fair knowledge, with 28% being Junior Pediatrics Residents, 18% Pediatric Consultants, and 15% Senior Pediatrics Residents. Fair knowledge was significantly associated with individuals aged 20-29 years, residents of the western region, and Junior Pediatrics Residents. Clinical knowledge varied among different groups, with 59% correctly identifying atypical pneumonia and 65% recognizing asymmetrical hyperinflation. However, rates for other conditions differed, with low identification of potential foreign body aspiration and film type. Accuracy in identifying tension pneumothorax and hyperlucency varied among clinicians. Pleural effusion films had a 65% identification rate for the diagnosis, but only 28% accurately described the X-ray and selected the correct answer for lung opacity. CONCLUSION: The study concluded that 29.9% of the participating physicians exhibited fair knowledge of common pediatric emergency radiological films. Junior pediatric residents showed the best knowledge, and Tetralogy of Fallot, asymmetrical hyperinflation, and pleural effusion had the highest recognition rates. In conclusion, there is still a need for radiologists in the pediatric emergency department to ensure optimal functioning.

Improving Computer-Aided Thoracic Disease Diagnosis through Comparative Analysis Using Chest X-ray Images Taken at Different Times.

Medical professionals in thoracic medicine routinely analyze chest X-ray images, often comparing pairs of images taken at different times to detect lesions or anomalies in patients. This research aims to design a computer-aided diagnosis system that enhances the efficiency of thoracic physicians in comparing and diagnosing X-ray images, ultimately reducing misjudgments. The proposed system encompasses four key components: segmentation, alignment, comparison, and classification of lung X-ray images. Utilizing a public NIH Chest X-ray14 dataset and a local dataset gathered by the Chiayi Christian Hospital in Taiwan, the efficacy of both the traditional methods and deep-learning methods were compared. Experimental results indicate that, in both the segmentation and alignment stages, the deep-learning method outperforms the traditional method, achieving higher average IoU, detection rates, and significantly reduced processing time. In the comparison stage, we designed nonlinear transfer functions to highlight the differences between pre- and post-images through heat maps. In the classification stage, single-input and dual-input network architectures were proposed. The inclusion of difference information in single-input networks enhances AUC by approximately 1%, and dual-input networks achieve a 1.2-1.4% AUC increase, underscoring the importance of difference images in lung disease identification and classification based on chest X-ray images. While the proposed system is still in its early stages and far from clinical application, the results demonstrate potential steps forward in the development of a comprehensive computer-aided diagnostic system for comparative analysis of chest X-ray images.

Vertebral heart size and vertebral left atrial size reference ranges in healthy Miniature Schnauzers.

OBJECTIVE: The inclusion of vertebral heart score (VHS) and, more recently, the inclusion of the vertebral left atrial size (VLAS) in radiographic evaluation have become important screening tools for identifying dogs with occult cardiac disease. Several recent papers have shown there are interbreed variations in the VHS reference range. Our hypothesis is that the Miniature Schnauzer would also have a higher reference range for its VHS. ANIMALS: The electronic medical records of IDEXX Telemedicine Consultants were searched for Miniature Schnauzers undergoing thoracic radiographs between March 1, 2022, and February 28, 2023. METHODS: Dogs were included if they had 3 view thoracic radiographs performed and no evidence of cardiopulmonary disease was detected. Dogs with incomplete radiographic studies or cardiac or extracardiac disease were excluded. The VHS and VLAS measurements were performed by 2 board-certified cardiologists independent of one another. RESULTS: A total of 1,000 radiographs were obtained of which 272 were included for the study. The overall range for the VHS in this cohort was 9.68 to 12.07 with a median of 10.9. For VLAS measurements, a range of 1.71 to 2.4 was documented with a median of 2.0. CLINICAL RELEVANCE: The VHS for Miniature Schnauzers without cardiac disease was confirmed to be higher than the canine reference range.

Hierarchical medical image report adversarial generation with hybrid discriminator.

BACKGROUND AND OBJECTIVES: Generating coherent reports from medical images is an important task for reducing doctors' workload. Unlike traditional image captioning tasks, the task of medical image report generation faces more challenges. Current models for generating reports from medical images often fail to characterize some abnormal findings, and some models generate reports with low quality. In this study, we propose a model to generate high-quality reports from medical images. METHODS: In this paper, we propose a model called Hybrid Discriminator Generative Adversarial Network (HDGAN), which combines Generative Adversarial Network (GAN) with Reinforcement Learning (RL). The HDGAN model consists of a generator, a one-sentence discriminator, and a one-word discriminator. Specifically, the RL reward signals are judged on the one-sentence discriminator and one-word discriminator separately. The one-sentence discriminator can better learn sentence-level structural information, while the one-word discriminator can learn word diversity information effectively. RESULTS: Our approach performs better on the IU-X-ray and COV-CTR datasets than the baseline models. For the ROUGE metric, our method outperforms the state-of-the-art model by 0.36 on the IU-X-ray, 0.06 on the MIMIC-CXR and 0.156 on the COV-CTR. CONCLUSIONS: The compositional framework we proposed can generate more accurate medical image reports at different levels.