Additional Imaging Research Articles

Heart failure with preserved ejection fraction.

Heart failure with preserved ejection fraction (HFpEF) accounts for nearly half of all heart failure cases and has a prevalence that is expected to rise with the growing ageing population. HFpEF is associated with significant morbidity and mortality. Specific HFpEF risk factors include age, diabetes, hypertension, obesity and atrial fibrillation. Haemodynamic contributions to HFpEF include changes in left ventricular structure, diastolic and systolic dysfunction, left atrial myopathy, pulmonary hypertension, right ventricular dysfunction, chronotropic incompetence, and vascular dysfunction. Inflammation, fibrosis, impaired nitric oxide signalling, sarcomere dysfunction, and mitochondrial and metabolic defects contribute to the cellular and molecular changes observed in HFpEF. HFpEF impacts multiple organ systems beyond the heart, including the skeletal muscle, peripheral vasculature, lungs, kidneys and brain. The diagnosis of HFpEF can bemade in individuals with signs and symptoms of heart failure with abnormality in natriuretic peptide levels or evidence of cardiopulmonary congestion, facilitated by the use of HFpEF risk scores and additional imaging and testing with the exclusion of HFpEF mimics. Management includes initiation of guideline-directed medical therapy and management of comorbidities. Given the significant impact of HFpEF on quality of life, future research efforts should include a particular focus on how patients can live better with this disease.

Combined Supine-Prone Myocardial Perfusion Imaging: Enhancing Diagnostic Accuracy.

The combined supine-prone imaging protocol for SPECT myocardial perfusion imaging offers significant advantages over supine imaging alone. By comparing supine and prone images, one can distinguish attenuation artifacts in the inferior and anterior walls from true perfusion defects, thus improving specificity and diagnostic accuracy. The recommended protocol is to perform prone imaging after supine stress imaging when perfusion defects are noted. The additional prone imaging time is 20%-40% less than the standard supine imaging time. Implementing prone imaging can optimize patient care and provide substantial benefits for nuclear cardiology labs, especially those without attenuation correction.

Implementing a rapid cord compression Magnetic Resonance Imaging protocol in the emergency department: Lessons learned.

(1) Evaluate efficacy of an abbreviated total spine protocol in triaging emergency department (ED) patients through retrospective evaluation. (2) Describe patient outcomes following implementation of a rapid cord compression protocol. (1) All contrast-enhanced total spine magnetic resonance imaging studies (MRIs) performed on ED patients (n = 75) between 10/1-12/31/2022 for evaluation of cord compression were included. Two readers with 6 and 5years of experience blindly reviewed the abbreviated protocol (comprised of sagittal T2w and axial T2w sequences) assessing presence of cord compression or severe spinal canal stenosis. Ground truth was consensus by a neuroradiology fellow and 2 attendings. (2) The implemented rapid protocol included sagittal T1w, sagittal T2w Dixon and axial T2w images. All ED patients (n = 85) who were imaged using the rapid protocol from 5/1-8/31/2023 were included. Patient outcomes and call-back rates were determined through chart review. (1) Sensitivity and specificity for severe spinal canal stenosis and/or cord compression was 1.0 and 0.92, respectively, for reader 1 and 0.78 and 0.85, respectively, for reader 2. Negative predictive value was 1.0 and 0.97 for readers 1 and 2, respectively. (2) The implemented rapid cord compression protocol resulted in 60% reduction in imaging time at 1.5T. The call-back rate for additional sequences was 7%. In patients who underwent surgery, no additional MRI images were acquired in 82% of cases (9/11). Implementing an abbreviated non-contrast total spine protocol in the ED results in a low call-back rate with acquired MRI images proving sufficient for both triage and treatment planning in most patients.

October 7th Mass Casualty Attack in Israel: Injury Profiles of Hospitalized Casualties.

On Saturday, October 7th, approximately 3000 Hamas-led terrorists infiltrated Israel's southern border and attacked civilians and soldiers. Terrorists murdered close to 1200 people, abducted hundreds, and injured thousands. This surprise attack involved an unprecedented number of casualties. This article describes the injuries and outcomes of the hospitalized casualties. Hospitalized trauma casualties with an injury date of October 7 to 8, 2023, and with ICD9 E-codes E979 and E990 through E999, were extracted from the Israel National Trauma Registry. Demographic, injury, and hospital resource-use data were analyzed. A total of 630 hospitalized casualties (277 civilians and 353 soldiers) suffered from gunshot wounds (90%), explosion-related wounds (19%), and multiple injury mechanisms (16%). The median age for civilians was 33 years (ages <1-88) and 21 years for soldiers. The most frequently injured body regions were lower (49%) and upper (42%) extremities, abdominal (28%), and thoracic (23%) injuries. Four hundred thirty-one (68%) patients underwent surgery, of which 240 within 12 hours. Over half of the severe and critical (Injury Severity Score 16+) casualties were discharged to a rehabilitation center. In-hospital mortality rate was 2.5%. Israel's hospitals faced many challenges following the mega mass casualty incident, including the absorption, diagnosis, treatment, and rehabilitation of a massive number of casualties. Hospitals needed to immediately repurpose to provide additional imaging equipment and operating rooms. Additionally, the huge demand for rehabilitation resources necessitated immediate reorganization and transformation of existing medical facilities to accommodate the many casualties requiring rehabilitation. The injury details and outcomes from this mega mass casualty incident provide important information for planning and preparedness at local, regional, and national levels.

Gossypiboma secondary to ovariohysterectomy in a dog

In veterinary medicine, intra-abdominal foreign bodies are a possible secondary complication of surgical procedures. Gossypiboma is defined as a forgotten textile material after surgery and is considered rare in veterinary medicine because most cases go unreported. The objective of this work is to report the diagnosis of an intra-abdominal gossypiboma in a dog, secondary to theovaryhysterectomy procedure. A 10-year-old Labrador dog had been sterilized about eight years ago. During the clinical analysis, a firm-looking increase in volume was found in the right mesogastric region, without the presence of pain on palpation. For further investigation, the patient was referred for additional imaging tests, such as x-ray and ultrasound. During inspection of the abdominal cavity, a firm circular mass was observed adhered to the omentum and jejunum, caudal to the right kidney. Resection of the mass was performed, and then the mass sample was sent for histopathological examination, which revealed an encapsulated foreign body, consistent with surgical gauze. Gossypiboma is one of the possible complications in surgical procedures in the abdominal cavity, but it is rarely reported in the veterinary literature.

Chronic Thromboembolic Pulmonary Hypertension

: While the majority of patients have complete resolution of their acute pulmonary embolism (PE) after an adequate course of anticoagulation, some patients remain symptomatic with evidence of chronic PE. Chronic Thromboembolic Pulmonary Hypertension (CTEPH) and Chronic Thromboembolic Pulmonary Disease (CTEPD) are terms that describe symptomatic patients with chronic thromboembolic occlusions of the pulmonary arteries with or without pulmonary hypertension, respectively. Here, we review the definitions, epidemiology, pathobiology, diagnosis and management of CTEPH. The chronic PE in CTEPH is essentially a scar in the pulmonary vasculature and is accompanied by a pulmonary arteriolar vasculopathy. Ventilation-perfusion scanning is the most sensitive screening test for CTEPH, and diagnosis must be confirmed by right heart catheterization (RHC). Treatment decisions require a multidisciplinary team and guidance from additional imaging, usually CT or pulmonary angiography. While pulmonary endarterectomy (PEA) to remove the chronic PE surgically is still the first-line treatment for appropriate candidates, there is an expanding role for balloon pulmonary angioplasty (BPA) and medical treatment, as well as multimodality treatment approaches that incorporate all of those options. New imaging modalities and treatment strategies hold the promise to improve our care and management of CTEPH patients in the future.

Detection of Contralateral Malignancies on Breast MRI.

Women with unilateral breast cancer are at increased risk for having simultaneous cancer of the contralateral breast. Overall, earlier detection of contralateral breast cancer prevents the burden of additional surgery or chemotherapy rounds and is associated with higher overall survival. However, MRI screening for the contralateral breast is seldom done following an initial unilateral breast cancer diagnosis. The purpose of this study is to retrospectively evaluate patients with known, biopsy-proven malignancy who went on to obtain a breast MRI and were later found to have cancer of the contralateral breast. Methods: This was a retrospective study that reviewed the charts of women aged over 18 years who were determined to have synchronous bilateral breast cancer from January 2017 to January 2022 at the University of Florida, Gainesville, FL. The study extracted data from this institution's cancer registry database, which provided information on patients with breast cancer diagnoses. The study conducted a review of mammography (MAM) and MRI imaging reports to ascertain the presence or absence of contralateral breast cancer identified by each respective imaging modality. Surgical pathology reports from the biopsy of the contralateral breast were reviewed to obtain information on the histological type of cancer and TNM (tumor, node, metastasis) staging. Of the 17 cases in which MAM missed contralateral cancer, follow-up MRI detected contralateral malignancy in 12 cases (70.59%) and subsequently changed management, resulting in additional imaging, biopsy, and eventual diagnosis and treatment of contralateral breast cancer. Examining the number of contralateral breast cancers detected by patients who had undergone MAM followed by MRI and those who had only undergone MAM, the study found that the detection rate of contralateral breast cancer from MAM was 45.45% (15/33). The tumor stages of the missed cancers were all T1 or Tis stage with one T1mi, and there was no nodal involvement. Conclusion: In addition to its utility in staging breast cancers, MRI also has the superior ability to detect otherwise undetected contralateral breast malignancy. This retrospective study found that MRI imaging led to a considerable increase in the detection of contralateral cancer. The study found that these undetected contralateral breast cancers by MAM were often of lower staging with no nodal involvement, highlighting the opportunity for MRI to assist in early cancer detection while the patient's prognosis is still good. Its high cost should be balanced with staging and occult malignancy detection utility in future practice.

Pain Experience and Image Quality with Curved versus Standard Compression for Breast Cancer Screening Mammography: A Randomized Controlled Trial.

Background A curve-shaped compression paddle could reduce the pain experienced by some women at breast cancer screening. Purpose To compare curved and standard compression systems in terms of pain experience and image quality in mammography screening. Materials and Methods In this randomized controlled trial conducted between October 2021 and February 2022, participants screened at three screening sites in the Netherlands were randomized to either a curved-paddle or sham-paddle group. The sham paddle was a standard paddle that was presented as a new paddle. At a standard screening examination, one additional image was acquired with a curved or sham paddle. Pain was measured on a numerical rating scale (range, 0-10). Participants provided a pain score after compression with the standard and test paddles, resulting in two scores per participant. Differences in pain scores were compared between groups using analysis of covariance, adjusting for pain score after standard-paddle compression. Two radiographers and two radiologists performed unblinded paired comparisons of curved-paddle vs standard-paddle images, using standard image quality criteria (radiographers evaluated 1246 image pairs using 12 criteria; radiologists evaluated 320 image pairs using six criteria). The one-sample Wilcoxon signed-rank test was used to determine if there was a significant preference for either paddle. Results In total, 2499 female participants (mean age, 61.6 years ± 7.1 [SD]) were studied; 1250 in the curved-paddle group and 1249 in the sham-paddle group. The mean pain score decreased by an additional 0.19 points in the curved-paddle group compared with the sham-paddle group (95% CI: 0.09, 0.28; P < .001). In terms of image quality, the observers showed no preference or a preference for the standard paddle. Decreased image contrast (range Bonferroni-corrected P values: P < .001 to P > .99) and visibility of structures were the main concerns for curved-paddle images. Conclusion The use of the curved paddle resulted in a minimal pain reduction during mammography breast compression but image quality was reduced. © RSNA, 2024 Supplemental material is available for this article.

Mammography and Breast Ultrasonography Services in Ghana, Availability, and Geographic Access.

Breast cancer is the leading type of cancer diagnosed and the second leading cause of cancer-related death in Ghana. Mammography and ultrasound have proven benefits in the early detection of breast cancer. This study evaluates mammography, breast ultrasound, and radiology work force availability throughout Ghana. A survey was administered to all hospitals in Ghana from November 2020 to October 2021. Mammography, breast ultrasound services, and the number of radiologists were assessed. For mammography, the number performed per month, cost incurred by the patient, where images were read, and how long it took to receive reports were also assessed. Health Facilities Regulatory Authority records on diagnostic centers were obtained to identify additional in-country breast imaging services. Three hundred and twenty-eight of 346 hospitals participated in the survey (95%). Only 21 hospitals reported on-site mammography. One hospital reported performing >100 mammographies per month. The average cost to the patient ranged from 100 to 500 Cedis ($17-87 US dollars [USD]), although three hospitals performed mammography at no cost. An additional 10 mammography machines were identified at diagnostic centers throughout the country, with 41.3% of the female population living within 1 hour of mammography services. There were 135 hospital-based breast ultrasound services identified with 69.5% of the female population living within 1 hour of these services. There were an additional 190 ultrasound machines at diagnostic centers. There were 96 in-country radiologists identified. Although there is limited availability and utilization of mammography in Ghana, there is more readily available ultrasonography. A focus on increasing breast cancer early diagnostic capabilities with breast ultrasound should be prioritized in addition to further expansion of the radiology workforce.

Load-dependent optical coherence tomography attenuation imaging: How tissue mechanics can influence optical scattering

Mechanical load imparted to tissue, for example via handheld imaging probes, leads to tissue deformation, altering the distribution of tissue microstructure and, consequently, attenuation of light and image formation in optical imaging. In mechanically heterogeneous tissue, the load can result in spatially varying deformation and, therefore, spatially varying changes in the attenuation of light, which may provide additional image contrast. To investigate this potential, an assessment of the spatially resolved impact of mechanical deformation of the tissue on optical imaging is critical; however, it is challenging to incorporate stress mapping into optical imaging without obscuring the detection of photons. To address this, we present the novel integration of stress imaging using optical palpation with attenuation imaging based on optical coherence tomography (OCT). The method was implemented using a compliant silicone sensor incorporated into a custom handheld OCT probe, providing two-dimensional stress imaging with concurrent attenuation imaging. Attenuation imaging with varying mechanical loads was demonstrated on 19 tissue regions acquired from eight freshly excised human breast specimens. The results demonstrated distinct characteristics for different breast tissue types: benign stroma showed relatively large increases in attenuation (e.g., ∼0.3 to 0.4 mm−1/kPa) over a low stress range (∼2 to 10 kPa), while cancerous tissue showed markedly small increases in attenuation (e.g., ∼0.005 to 0.02 mm−1/kPa) mainly over a medium to high stress range (∼10 to 90 kPa). The integration of stress imaging with attenuation imaging provided a pilot assessment of the spatially resolved impact of tissue mechanical heterogeneity on optical attenuation, providing novel image contrast by encoding variations in mechanical properties on optical attenuation in tissue.

Systematic Biopsy vs. Prostatectomy: Evaluating Correlations and Grading Discrepancies in Prostate Cancer.

Background Prostate Cancer (PCa) represents agrowing global health challenge. The main factor in predicting PCa prognosis is represented by the Gleason Score (GS)therefore, the accuracy of pathological features from preoperative biopsy is critical in the management of the patient. We aimed to investigate the correlation between prostate biopsy parameters and the prostatectomy specimen pathological features and to identify factors that lead to over- and under-grading tumors in biopsy samples. Materials and methods We performed a retrospective study that included 110 male patients with confirmed PCa, selected based on specific inclusion criteria. Biopsy and radical prostatectomy (RP) specimens were analyzed using standard histopathological techniques, and pathological features were assessed according to the latest guidelines. Statistical analysis was performed using IBM SPSS Statistics version 26.0.0 (IBM Corp., Armonk, NY). Results The study included 110 male patients with a median age of 67 years old, ranging from 48 to 79 years old. Correlations between biopsy parameters and RP outcomes were assessed and revealed several key findings. The tumoral length on biopsy was correlated with positive surgical margin (r=0.289, p<0.01) and with tumoral volume (r=0.526, p<0.001) on prostatectomy. Patients with higher grade groups (GG) on biopsy had an approximately four times higher chance of exhibiting extraprostatic extension. We demonstrated a significant correlation between Gleason Pattern 4 (%GP4) on biopsy and pT stage, with pT4 showing the highest %GP4, and a noticeable increase in %GP4 as the pT stage progressed from pT2b to pT4. The study found a significantly higher rate of undergrading at biopsy (30.90%) compared to overgrading (6.36%). Additionally, greater tumor length and higher tumor percentages in biopsies improved grading accuracy (p<0.001). Conclusion Our findings suggest that systemic biopsies play a key role in predicting pathological outcomes, especially through parameters that serve as key prognostic markers. However, due to the potential of the biopsy results to be under- or overgraded, urologists should take into consideration the advantages of using repeat biopsies or additional imaging techniques to achieve a more precise diagnosis and treatment strategy.

Demonstration of VCR: A Tabular Data Slicing Approach to Understanding Object Detection Model Performance

In this demonstration, we present VCR, an automated slice discovery method (SDM) for object detection models that helps practitioners identify and explain specific scenarios in which their models exhibit systematic errors. VCR leverages the capabilities of vision foundation models to generate segment-level visual concepts that serve as interpretable explanation primitives. By integrating these visual concepts with additional image metadata in a tabular format, VCR uses a scalable frequent itemset mining-based technique to identify common patterns associated with model performance. We will demonstrate VCR's capabilities through three usage scenarios. First, users can explore the automatically extracted visual concepts and their associated labels. Second, users can run slice finding on a large object detection dataset and visually inspect the results to discover systematic errors. Finally, users can iteratively refine their slicing results by providing feedback on the granularity of visual concepts and the quality of the generated labels. These scenarios will illustrate how VCR can aid practitioners in discovering non-trivial gaps in their models' performance, providing actionable insights for model improvement.

Large-scale calcium imaging reveals a systematic V4 map for encoding natural scenes

Biological visual systems have evolved to process natural scenes. A full understanding of visual cortical functions requires a comprehensive characterization of how neuronal populations in each visual area encode natural scenes. Here, we utilized widefield calcium imaging to record V4 cortical response to tens of thousands of natural images in male macaques. Using this large dataset, we developed a deep-learning digital twin of V4 that allowed us to map the natural image preferences of the neural population at 100-µm scale. This detailed map revealed a diverse set of functional domains in V4, each encoding distinct natural image features. We validated these model predictions using additional widefield imaging and single-cell resolution two-photon imaging. Feature attribution analysis revealed that these domains lie along a continuum from preferring spatially localized shape features to preferring spatially dispersed surface features. These results provide insights into the organizing principles that govern natural scene encoding in V4.

Parcel-Based Sugarcane Mapping Using Smoothed Sentinel-1 Time Series Data

The timely and accurate mapping of sugarcane cultivation is significant to ensure the sustainability of the sugarcane industry, including sugarcane production, rural society, sugar futures, and crop insurance. Synthetic aperture radar (SAR), due to its all-weather and all-time imaging capability, plays an important role in mapping sugarcane cultivation in cloudy areas. However, the inherent speckle noise of SAR data worsens the “salt and pepper” effect in the sugarcane map. Therefore, in previous studies, an additional land cover map or optical image was still required. This study proposes a new application paradigm of time series SAR data for sugarcane mapping to tackle this limitation. First, the locally estimated scatterplot smoothing (LOESS) smoothing technique was exploited to reconstruct time series SAR data and reduce SAR noise in the time domain. Second, temporal importance was evaluated using RF MDA ranking, and basic parcel units were obtained only based on multi-temporal SAR images with high importance values. Lastly, the parcel-based classification method, combining time series smoothing SAR data, RF classifier, and basic parcel units, was used to generate a sugarcane extent map without unreasonable sugarcane spots. The proposed paradigm was applied to map sugarcane cultivation in Suixi County, China. Results showed that the proposed paradigm was able to produce an accurate sugarcane cultivation map with an overall accuracy of 96.09% and a Kappa coefficient of 0.91. Compared with the pixel-based classification result with original time series SAR data, the new paradigm performed much better in reducing the “salt and pepper” spots and improving the completeness of the sugarcane plots. In particular, the unreasonable non-vegetation spots in the sugarcane map were eliminated. The results demonstrated the efficacy of the new paradigm for mapping sugarcane cultivation. Unlike traditional methods that rely on optical remote sensing data, the new paradigm offers a high level of practicality for mapping sugarcane in large regions. This is particularly beneficial in cloudy areas where optical remote sensing data is frequently unavailable.

Primary BAP1-absent atypical meningioma arising from median nerve within infraclavicular brachial plexus: illustrative case.

The authors present the only known case of a World Health Organization grade II ectopic meningioma occurring in the infraclavicular brachial plexus, causing pain within the axilla not associated with a primary malignant meningioma of the central nervous system. Peripheral nerve sheath tumors are rare entities, the majority of which are schwannomas or neurofibromas. Ectopic meningiomas only represent 1%-2% of all meningiomas. To date, there is one other published case specifically of a primary ectopic meningioma located in the brachial plexus. Following the dissection of the left axilla, a dominant rubbery tumor involving the median nerve was encountered. The tumor capsule contained areas of hemorrhage and a soft core with nerve fascicles coursing through, which were not compromised during internal tumor debulking. The tumor lacked a clear pseudocapsule that is characteristically seen in schwannomas. Histopathological studies confirmed an atypical epithelioid neoplasm with elevated numbers of mitotic figures and BAP1 gene deletion. Primary meningiomas arising outside the central nervous system are exceedingly rare. For this unusual higher-grade primary ectopic meningioma located in the distal brachial plexus, surgery with the goal of gross-total resection, adjuvant radiation, additional imaging, and genetics screening were recommended. Close follow-up is warranted. https://thejns.org/doi/10.3171/CASE24226.

The "Hypointense Focal Brain" on susceptibility-weighted imaging as a sign of venous congestion in cranial dural arteriovenous fistulas.

Cranial dural arteriovenous fistulas (dAVFs) are complex neurovascular malformations accounting for approximately 10%-15% of all intracranial arteriovenous malformations. The objective is to investigate the utility of susceptibility-weighted imaging (SWI) in identifying "hypointense focal brain" as an additional helpful sign of venous congestion in cranial dAVFs. A retrospective review of patients diagnosed with cranial dAVFs between January 2015 and June 2023 was conducted, and SWI was used to identify the "hypointense focal brain" sign within the venous drainage region of the dAVF. The "hypointense focal brain" on SWI was identified as a low-intensity signal within the venous drainage region, indicative of venous congestion. The presence of this imaging sign was assessed by two neuroradiologists and signal intensity measurements were performed to support the presence of the sign. The study included six patients with cranial dAVFs exhibiting cortical venous retrograde drainage and the "hypointense focal brain" on SWI. Follow-up imaging post-treatment revealed resolution or improvement of the hypointense signal, confirming its association with venous congestion. Signal intensity measurements further supported the presence of this imaging sign in pre-treatment scans. The study's findings demonstrate the presence of a reversible "hypointense focal brain" sign on SWI in patients with cranial dAVFs and CVR, which can be useful as an additional imaging sign for venous congestion.

Aversive memories can be weakened during human sleep via the reactivation of positive interfering memories

Recollecting painful or traumatic experiences can be deeply troubling. Sleep may offer an opportunity to reduce such suffering. We developed a procedure to weaken older aversive memories by reactivating newer positive memories during sleep. Participants viewed 48 nonsense words each paired with a unique aversive image, followed by an overnight sleep. In the next evening, participants learned associations between half of the words and additional positive images, creating interference. During the following non-rapid-eye-movement sleep, auditory memory cues were unobtrusively delivered. Upon waking, presenting cues associated with both aversive and positive images during sleep, as opposed to not presenting cues, weakened aversive memory recall while increasing positive memory intrusions. Substantiating these memory benefits, computational modeling revealed that cueing facilitated evidence accumulation toward positive affect judgments. Moreover, cue-elicited theta brain rhythms during sleep predominantly predicted the recall of positive memories. A noninvasive sleep intervention can thus modify aversive recollection and affective responses.

Using Machine Learning to Identify Diseases and Perform Sorting in Apple Fruit

Fruit diseases play a major role in global agriculture, leading to substantial crop losses and influencing food production and economic stability. In this age of Industry 4.0 the fruit sorting is an important part in the food processing wherein this work plays a vital role. In this study, a solution for the detection and classification of apple fruit diseases is proposed and experimentally validated. Deep learning models offer promise for automating disease identification using fruit images, but encounter obstacles such as therequirement for extensive training data, computational complexity, and the risk of overfitting. This study introduces an innovative convolutional neural network (CNN) architecture aimed at addressing these challenges by incorporating a reduced number of layers, thus alleviating computational burdens while maintaining performance. Additionally, augmentation techniques such as shift, shear, scaling, zoom, and flipping are employed to diversify the training set without additional image acquisition. Our CNN model is specifically trained to identify common apple crop diseases like Scab, Rot, and Blotch. Rigorous experimental evaluation demonstrates the effectiveness ofour model, achieving a remarkable classification accuracy of 95.37%. Significantly, our model demonstrates reduced storage requirements and faster execution times compared to existing deep CNN architectures, enabling deployment on handheld devices and resource-limited environments. While other CNN models may offer similar accuracy levels, our approach emphasizes efficiency and resource optimization, rendering it practical for real-world applications in agriculture. Furthermore, our CNN model exhibits resilience to environmental variations and imaging parameters, enhancing its applicability across diverse agricultural settings. By leveraging advanced machine learning techniques, the approach developed in this experimental work contributes to modernizing fruits and vegetables sorting operations in food processing, crop management practices thus promoting agricultural sustainability. The scalability and portability of our model make it suitable for deployment in both small-scale farms and large-scale agricultural operations.

Dutch multidisciplinary guideline on anterior knee pain: Patellofemoral pain and patellar tendinopathy.

The purpose of this study was to develop a multidisciplinary guideline for patellofemoral pain (PFP) and patellar tendinopathy (PT) to facilitate clinical decision-making in primary and secondary care. A multidisciplinary expert panel identified questions in clinical decision-making. Based on a systematic literature search, the strength of the scientific evidence was determined according to the Grading of Recommendations, Assessment, Development and Evaluations (GRADE) method and the weight assigned to the considerations by the expert panel together determined the strength of the recommendations. After confirming PFP or PT as a clinical diagnosis, patients should start with exercise therapy. Additional conservative treatments are indicated only when exercise therapy does not result in clinically relevant changes after six (PFP) or 12 (PT) weeks. Pain medications should be reserved for cases of severe pain. The additional value of imaging assessments for PT is limited. Open surgery is reserved for very specific cases of nonresponders to exercise therapy and those requiring additional conservative treatments. Although the certainty of evidence regarding exercise therapy for PFP and PT had to be downgraded ('very low GRADE' and 'low GRADE'), the expert panel advocates its use as the primary treatment strategy. The panel further formulated weaker recommendations regarding additional conservative treatments, pain medications, imaging assessments and open surgery ('very low GRADE' to 'low GRADE' assessment or absence of scientific evidence). This guideline recommends starting with exercise therapy for PFP and PT. The recommendations facilitate clinical decision-making, and thereby optimizing treatment and preventing unnecessary burdens, risks and costs to patients and society. Level V, clinical practice guideline.

Ultra-low dose hip CT-based automated measurement of volumetric bone mineral density at proximal femoral subregions.

Forty to fifty percent of women and 13%-22% of men experience an osteoporosis-related fragility fracture in their lifetimes. After the age of 50 years, the risk of hip fracture doubles in every 10 years. x-Ray based DXA is currently clinically used to diagnose osteoporosis and predict fracture risk. However, it provides only 2-D representation of bone and is associated with other technical limitations. Thus, alternative methods are needed. To develop and evaluate an ultra-low dose (ULD) hip CT-based automated method for assessment of volumetric bone mineral density (vBMD) at proximal femoral subregions. An automated method was developed to segment the proximal femur in ULD hip CT images and delineate femoral subregions. The computational pipeline consists of deep learning (DL)-based computation of femur likelihood map followed by shape model-based femur segmentation and finite element analysis-based warping of a reference subregion labeling onto individual femur shapes. Finally, vBMD is computed over each subregion in the target image using a calibration phantom scan. A total of 100 participants (50 females) were recruited from the Genetic Epidemiology of COPD (COPDGene) study, and ULD hip CT imaging, equivalent to 18 days of background radiation received by U.S. residents, was performed on each participant. Additional hip CT imaging using a clinical protocol was performed on 12 participants and repeat ULD hip CT was acquired on another five participants. ULD CT images from 80 participants were used to train the DL network; ULD CT images of the remaining 20 participants as well as clinical and repeat ULD CT images were used to evaluate the accuracy, generalizability, and reproducibility of segmentation of femoral subregions. Finally, clinical CT and repeat ULD CT images were used to evaluate accuracy and reproducibility of ULD CT-based automated measurements of femoral vBMD. Dice scores of accuracy (n=20), reproducibility (n=5), and generalizability (n=12) of ULD CT-based automated subregion segmentation were 0.990, 0.982, and 0.977, respectively, for the femoral head and 0.941, 0.970, and 0.960, respectively, for the femoral neck. ULD CT-based regional vBMD showed Pearson and concordance correlation coefficients of 0.994 and 0.977, respectively, and a root-mean-square coefficient of variation (RMSCV) (%) of 1.39% with the clinical CT-derived reference measure. After 3-digit approximation, each of Pearson and concordance correlation coefficients as well as intraclass correlation coefficient (ICC) between baseline and repeat scans were 0.996 with RMSCV of 0.72%. Results of ULD CT-based bone analysis on 100 participants (age (mean±SD) 73.6±6.6 years) show that males have significantly greater (p<0.01) vBMD at the femoral head and trochanteric regions than females, while females have moderately greater vBMD (p=0.05) at the medial half of the femoral neck than males. Deep learning, combined with shape model and finite element analysis, offers an accurate, reproducible, and generalizable algorithm for automated segmentation of the proximal femur and anatomic femoral subregions using ULD hip CT images. ULD CT-based regional measures of femoral vBMD are accurate and reproducible and demonstrate regional differences between males and females.