Detection Of Lesions Research Articles

Periapical lesion detection in periapical radiographs using the latest convolutional neural network ConvNeXt and its integrated models

To overcome the limitation of a single classification model’s inability to simultaneously identify multiple lesion targets within periapical radiographs, This study proposes YoCNET (Yolov5 + ConvNeXt), a novel deep learning integrated model. YoCNET leverages the target detection capability of Yolov5 and the image classification capability of ConvNeXt to achieve automatic segmentation of individual teeth and concurrent detection of periapical lesions across multiple teeth. A dataset of 1,305 periapical radiographs was used to train and validate the ConvNeXt and ResNet34 models, with an 8:2 split for training and validation. Deciduous teeth were excluded from the dataset. Furthermore, 717 individual teeth images were extracted from 200 previously unused periapical radiographs for integrated model validation. Evaluation metrics included accuracy, precision, sensitivity, F1 score, AUC (Area Under Curve), and a confusion matrix.The YoCNET integrated model demonstrated values of 90.93%, 98.88%, 85.30%, 0.9159, and 0.9757 for accuracy, precision, sensitivity, F1 score, and AUC, respectively. These metrics were superior to those achieved by the YoRNET (Yolov5 + ResNet34) integrated model, which recorded 80.47%, 83.78%, 82.16%, 0.8296, and 0.8822. The integrated model achieved high accuracy and efficiency in automatic teeh segmentation by Yolov5 and in automatically detecting multiple periapical lesions by ConvNeXt. YoCNET exhibited superior overall data performance, making it a more suitable deep learning integrated model for clinical applications.

The impact of linked color imaging on adenoma detection rate in colonoscopy: a systematic review and meta-analysis.

Colorectal cancer prevention relies on surveillance colonoscopy, with the adenoma detection rate as a key factor in examination quality. Linked color imaging (LCI) enhances lesion contrast and improves the examination performance. This systematic review and meta-analysis aimed to evaluate the effect of LCI on adenoma detection rate in adults who underwent colonoscopy. We searched the Medline, PubMed, BIREME, LILACS, and Scientific Electronic Library Online databases for randomized controlled trials comparing the use of LCI versus white light (WL), published up to March 2023. The outcomes included lesion characteristics, number of adenomas per patient, and the additional polyp detection rate. Sixteen studies were included in the analysis, which showed that LCI was more accurate than WL in detecting adenomas, with an increased number of adenomas detected per patient. Although LCI performed well in terms of lesion size, morphology, and location, the subgroup analyses did not reveal any statistically significant differences between LCI and WL. The addition of LCI did not result in significant improvements in the detection of serrated lesions, and there were no differences in the withdrawal time between groups. LCI has been shown to be effective in detecting colonic lesions, improving the number of adenomas detected per patient and improving polyp detection rate without negatively affecting other quality criteria in colonoscopy.

Expanding generalized contrast-to-noise ratio into a clinically relevant measure of lesion detectability by considering size and spatial resolution.

Early image quality metrics were often designed with clinicians in mind, and ideal metrics would correlate with the subjective opinion of practitioners. Over time, adaptive beamformers and other post-processing methods have become more common, and these newer methods often violate assumptions of earlier image quality metrics, invalidating the meaning of those metrics. The result is that beamformers may "manipulate" metrics without producing more clinical information. In this work, Smith etal.'s signal-to-noise ratio (SNR) metric for lesion detectability is considered, and a more robust version, here called generalized SNR (gSNR), is proposed that uses generalized contrast-to-noise ratio (gCNR) as a core. It is analytically shown that for Rayleigh distributed data, gCNR is a function of Smith etal.'s (and therefore can be used as a substitution). More robust methods for estimating the resolution cell size are considered. Simulated lesions are included to verify the equations and demonstrate behavior, and it is shown to apply equally well to in vivo data. gSNR is shown to be equivalent to SNR for delay-and-sum (DAS) beamformed data, as intended. However, it is shown to be more robust against transformations and report lesion detectability more accurately for non-Rayleigh distributed data. In the simulation included, the SNR of DAS was , and minimum variance (MV) was , but the gSNR of DAS was , and MV was , which agrees with the subjective assessment of the image. Likewise, the transformation (which is clinically identical to DAS) had an incorrect SNR of and a correct gSNR of . Similar results are shown in vivo. Using gCNR as a component to estimate gSNR creates a robust measure of lesion detectability. Like SNR, gSNR can be compared with the Rose criterion and may better correlate with clinical assessments of image quality for modern beamformers.

A Quantitative Comparison Between Human and Artificial Intelligence in the Detection of Focal Cortical Dysplasia.

Artificial intelligence (AI) is thought to improve lesion detection. However, a lack of knowledge about human performance prevents a comparative evaluation of AI and an accurate assessment of its impact on clinical decision-making. The objective of this work is to quantitatively evaluate the ability of humans to detect focal cortical dysplasia (FCD), compare it to state-of-the-art AI, and determine how it may aid diagnostics. We prospectively recorded the performance of readers in detecting FCDs using single points and 3-dimensional bounding boxes. We acquired predictions of 3 AI models for the same dataset and compared these to readers. Finally, we analyzed pairwise combinations of readers and models. Twenty-eight readers, including 20 nonexpert and 5 expert physicians, reviewed 180 cases: 146 subjects with FCD (median age: 25, interquartile range: 18) and 34 healthy control subjects (median age: 43, interquartile range: 19). Nonexpert readers detected 47% (95% confidence interval [CI]: 46, 49) of FCDs, whereas experts detected 68% (95% CI: 65, 71). The 3 AI models detected 32%, 51%, and 72% of FCDs, respectively. The latter, however, also predicted more than 13 false-positive clusters per subject on average. Human performance was improved in the presence of a transmantle sign (P < 0.001) and cortical thickening (P < 0.001). In contrast, AI models were sensitive to abnormal gyration (P < 0.01) or gray-white matter blurring (P < 0.01). Compared with single experts, expert-expert pairs detected 13% (95% CI: 9, 18) more FCDs (P < 0.001). All AI models increased expert detection rates by up to 19% (95% CI: 15, 24) (P < 0.001). Nonexpert+AI pairs could still outperform single experts by up to 13% (95% CI: 10, 17). This study pioneers the comparative evaluation of humans and AI for FCD lesion detection. It shows that AI and human predictions differ, especially for certain MRI features of FCD, and, thus, how AI may complement the diagnostic workup.

Integrating standard epilepsy protocol, ASL-perfusion, MP2RAGE/EDGE and the MELD-FCD classifier in the detection of subtle epileptogenic lesions: a 3 Tesla MRI pilot study.

Malformations of cortical development (MCDs) in children with focal epilepsy pose significant diagnostic challenges, and a precise radiological diagnosis is crucial for surgical planning. New MRI sequences and the use of artificial intelligence (AI) algorithms are considered very promising in this regard, yet studies evaluating the relative contribution of each diagnostic technique are lacking. The study was conducted using a dedicated "EPI-MCD MR protocol" with a 3 Tesla MRI scanner in patients with focal epilepsy and previously negative MRI. MRI sequences evaluated included 3D FLAIR, 3D T1 MPRAGE, T2 Turbo Spin Echo (TSE), 3D T1 MP2RAGE, and Arterial Spin Labelling (ASL). Two paediatric neuroradiologists scored each sequence for localisation and extension of the lesion. The MELD-FCD AI classifier's performance in identifying pathological findings was also assessed. We only included patients where a diagnosis of MCD was subsequently confirmed on histology and/or sEEG. The 3D FLAIR sequence showed the highest yield in detecting epileptogenic lesions, with 3D T1 MPRAGE, T2 TSE, and 3D T1 MP2RAGE sequences showing moderate to low yield. ASL was the least useful. The MELD-FCD classifier achieved a 69.2% true positive rate. In one case, MELD identified a subtle area of cortical dysplasia overlooked by the neuroradiologists, changing the management of the patient. The 3D FLAIR sequence is the most effective in the MRI-based diagnosis of subtle epileptogenic lesions, outperforming other sequences in localisation and extension. This pilot study emphasizes the importance of careful assessment of the value of additional sequences.

Results of the cancer screening program in urban areas in Shaanxi province of China, 2019-2020

Objective: Analyze the cancer screening status of the cancer screening program in urban areas in Shaanxi province in 2019-2020. Methods: The early diagnosis and early treatment project for urban cancers carried out high-risk population screening for 5 types of high-incidence malignant tumors (breast cancer, lung cancer, upper gastrointestinal cancer, liver cancer, and colorectal cancer) in urban areas. Three prefecture-level cities in Shaanxi province with a population of over 1 million (Xi'an, Baoji, and Shangluo) were selected, and 4 communities with a relatively good working foundation were selected in each city. The general population aged 45-74 years was surveyed on the principles of informed consent and voluntariness, and high-risk groups identified through the questionnaire were further subjected to free endoscopy, ultrasound, CT, and other clinical screenings. The high-risk rates, screening compliance rates, and positive detection rates of the above 5 types of malignant tumors were analyzed. Results: A total of 19 632 people completed the survey effectively, with the proportion of male participants (40.0%) lower than that of females (60.0%). A total of 10 102 high-risk groups were identified, with an initial screening high-risk rate of 51.5%, and the high-risk rates for the 5 types of cancers were 24.1% for breast cancer, 28.6% for lung cancer, 9.1% for upper gastrointestinal cancer, 4.0% for liver cancer, and 20.0% for colorectal cancer. Among the 14 960 person-time initially assessed as high-risk, 5 129 person-time received clinical screening, with a screening compliance rate of 34.3%. The number of people receiving clinical screening and the screening compliance rates for the 5 types of cancers were 1 192 (41.9%) for breast cancer, 2 081 (37.1%) for lung cancer, 574 (32.0%) for upper gastrointestinal cancer, 404 (51.3%) for liver cancer, and 878 (22.3%) for colorectal cancer, with positive detection numbers and rates of 179 (15.0%) for breast, 289 (13.9%) for lung, 9 (1.6%) for upper gastrointestinal, 14 (3.5%) for suspected liver, and 67 (7.6%) for colorectal, respectively. Conclusion: The cancer screening status of the cancer screening program in urban areas in Shaanxi province is beneficial for the detection of precancerous lesions and early cancer patients, and improving the early diagnosis and treatment rate of patients, but the public participation rate is not high, and the project management model and technical plan need to be further improved.

Trends in high-risk human papillomavirus infection and cervical cytology of women in Karamay City, 2012-2021.

Background To describe the changes in cervical lesions prevalence and high-risk human papillomavirus (HR-HPV) infections from 2012 to 2021, which have never been reported before, to provide direction for the effective implementation of cervical cancer prevention measures. Methods This retrospective study included women aged >25years who received either organised or opportunistic cervical HR-HPV screening from January 2012 to December 2021 in Karamay Central Hospital, Karamay, China. The patients were split into four groups according to age 25-35, 36-45, 46-55 and >55years, respectively. The Joinpoint Regression Program was used to analyse the trends of HR-HPV infection and the detection of cervical lesions. Results Data from 85,429 women revealed a decline in HR-HPV infection rates across all age groups from 2012 to 2021. Although HR-HPV infection rates decreased, cervical lesion detection rates increased, although the proportion of cervical cancer in these lesions declined, likely due to enhanced awareness and HPV vaccination in Karamay. From 2012 to 2021, the prevalence of low-grade squamous intraepithelial lesions was 9.70%, and high-grade squamous intraepithelial lesions was 5.85%. HR-HPV infections were highest in the ≥55years age group, with HPV52 (20.96%) being the most prevalent type. Conclusions In the past 10years, the prevalence of HR-HPV infection has shown a decreasing trend, whereas the detection prevalence of cervical lesions has shown an upward trend among women in Karamay City. Importantly, particular emphasis should be placed on cervical cancer screening in women aged >55years.

LesionNet: an automated approach for skin lesion classification using SIFT features with customized convolutional neural network.

Accurate detection of skin lesions through computer-aided diagnosis has emerged as a critical advancement in dermatology, addressing the inefficiencies and errors inherent in manual visual analysis. Despite the promise of automated diagnostic approaches, challenges such as image size variability, hair artifacts, color inconsistencies, ruler markers, low contrast, lesion dimension differences, and gel bubbles must be overcome. Researchers have made significant strides in binary classification problems, particularly in distinguishing melanocytic lesions from normal skin conditions. Leveraging the "MNIST HAM10000" dataset from the International Skin Image Collaboration, this study integrates Scale-Invariant Feature Transform (SIFT) features with a custom convolutional neural network model called LesionNet. The experimental results reveal the model's robustness, achieving an impressive accuracy of 99.28%. This high accuracy underscores the effectiveness of combining feature extraction techniques with advanced neural network models in enhancing the precision of skin lesion detection.

Emerging strategies to investigate the biology of early cancer.

Early detection and intervention of cancer or precancerous lesions hold great promise to improve patient survival. However, the processes of cancer initiation and the normal-precancer-cancer progression within a non-cancerous tissue context remain poorly understood. This is, in part, due to the scarcity of early-stage clinical samples or suitable models to study early cancer. In this Review, we introduce clinical samples and model systems, such as autochthonous mice and organoid-derived or stem cell-derived models that allow longitudinal analysis of early cancer development. We also present the emerging techniques and computational tools that enhance our understanding of cancer initiation and early progression, including direct imaging, lineage tracing, single-cell and spatial multi-omics, and artificial intelligence models. Together, these models and techniques facilitate a more comprehensive understanding of the poorly characterized early malignant transformation cascade, holding great potential to unveil key drivers and early biomarkers for cancer development. Finally, we discuss how these new insights can potentially be translated into mechanism-based strategies for early cancer detection and prevention.

The Prevalence of Abnormal Cervical Cytology at Federal Teaching Hospital Gombe: A Cross-Sectional Study

Introduction: Cervical cancer continues to be a significant public health concern, ranking as the fourth most common cancer among women globally, with approximately 604,000 new cases and 342,000 deaths reported in 2020 (World Health Organization, 2020). The burden of cervical cancer disproportionately affects women in low- and middle-income countries (LMICs), where access to effective screening and treatment options is often limited. Early detection and treatment of cervical premalignant lesions are crucial in reducing the incidence and mortality associated with this preventable disease. The objectives of this study was to determine the prevalence of abnormal cervical cytology, the histological types and patient characteristics among patients attending the Gynaecology/postnatal clinic of Federal Teaching Hospital, Gombe State, Nigeria. Methods: A retrospective study of all cervical smears received and processed at the Pathology laboratory of Federal Teaching Hospital between January 2022 and December 2022. Results: The records of 596 smears of women between the ages of 20 and 65 years were retrieved and analyzed. Negative smears were predominant (62.6%) while 8.7% were inflammatory smears. Dyskaryotic smears were found in 155 smears (26.0%); this was made up atypical glandular cells of undetermined significance (AGCUS) in 1.8%, Atypical squamous cells of undetermined significance (ASCUS) in 10.23%, Low grade squamous intraepithelial lesion (LSIL) in 10.6% and High grade squamous intraepithelial lesion (HSIL) in 3.6%. Malignant cells were found in 0.5% of the smears while the remaining 2.1% were unsatisfactory. Conclusion: The relatively high frequency of dyskaryosis in this study lends credence to the need for us to widen our cervical screening coverage in order to achieve the highest possible coverage rate. This can be achieved through the use of public education by means of various media, women and religious organizations.

CT and MRI of pancreatic cystic lesions: tricks of the trade

PurposeTo describe CT and MRI findings of pancreatic cystic lesions.BackgroundThe growing use of ultrasound, CT and MRI has led to increasing incidental detection of pancreatic cystic lesions. These lesions range from benign entities (e.g., acute necrotic collection) to potentially malignant neoplasms (e.g., IPMN) and malignant neoplasms (e.g., ductal adenocarcinoma). CT and MRI can help to differentiate pancreatic cystic lesions.FindingsPancreatic cystic lesions neoplasms often have pathognomonic CT and MRI characteristics. It is important to consider size, number of cysts, septa, the relationship with the main pancreatic duct, internal nodules and wall enhancement. Guidelines from different societies have been developed to promote and standardize the management and follow-up of pancreatic cystic lesions.ConclusionCT and MRI play a crucial role in the detection and characterization of pancreatic cystic lesions.

Early experience with an artificial intelligence-based module for brain metastasis detection and segmentation.

- Accurate detection, segmentation, and volumetric analysis of brain lesions are essential in neuro-oncology. Artificial intelligence (AI)-based models have improved the efficiency of these processes. This study evaluated an AI-based module for detecting and segmenting brain metastases, comparing it with manual detection and segmentation. - MRIs from 51 patients treated with Gamma Knife radiosurgery for brain metastases were analyzed. Manual lesion identification and contouring on Leksell Gamma Plan at the time of treatment served as the gold standard. The same MRIs were processed through an AI-based module (Brainlab Smart Brush), and lesion detection and volumes were compared. Discrepancies were analyzed to identify possible sources of error. - Among 51 patients, 359 brain metastases were identified. The AI module achieved a sensitivity of 79.2% and a positive predictive value of 95.6%, compared to a 93.3% sensitivity for manual detection. However, for lesions > 0.1cc, the AI's sensitivity rose to 97.5%, surpassing manual detection at 93%. Volumetric agreement between AI and manual segmentations was high (Spearman's ρ = 0.997, p < 0.001). Most lesions missed by the AI (53.8%) were near anatomical structures that complicated detection. - The AI module demonstrated higher sensitivity than manual detection for metastases larger than 0.1cc, with robust volumetric accuracy. However, human expertise remains critical for detecting smaller lesions, especially near complex anatomical areas. AI offers significant potential to enhance neuro-oncology practice by improving the efficiency and accuracy of lesion management.

Automated lesion detection in cotton leaf visuals using deep learning

Cotton is one of the major cash crop in the agriculture led economies across the world. Cotton leaf diseases affects its yield globally. Determining cotton lesions on leaves is difficult when the area is big and the size of lesions is varied. Automated cotton lesion detection is quite useful; however, it is challenging due to fewer disease class, limited size datasets, class imbalance problems, and need of comprehensive evaluation metrics. We propose a novel deep learning based method that augments the data using generative adversarial networks (GANs) to reduce the class imbalance issue and an ensemble-based method that combines the feature vector obtained from the three deep learning architectures including VGG16, Inception V3, and ResNet50. The proposed method offers a more precise, efficient and scalable method for automated detection of diseases of cotton crops. We have implemented the proposed method on publicly available dataset with seven disease and one health classes and have achieved highest accuracy of 95% and F-1 score of 98%. The proposed method performs better than existing state of the art methods.

Image Quality and Lesion Detectability of Low-Concentration Iodine Contrast and Low Radiation Hepatic Multiphase CT Using a Deep-Learning-Based Contrast-Boosting Model in Chronic Liver Disease Patients.

This study investigated the image quality and detectability of double low-dose hepatic multiphase CT (DLDCT, which targeted about 30% reductions of both the radiation and iodine concentration) using a vendor-agnostic deep-learning-based contrast-boosting model (DL-CB) compared to those of standard-dose CT (SDCT) using hybrid iterative reconstruction. The CT images of 73 patients with chronic liver disease who underwent DLDCT between June 2023 and October 2023 and had SDCT were analyzed. Qualitative analysis of the overall image quality, artificial sensation, and liver contour sharpness on the arterial and portal phase, along with the hepatic artery clarity was conducted by two radiologists using a 5-point scale. For quantitative analysis, the image noise, signal-to-noise ratio, and contrast-to-noise ratio were measured. The lesion conspicuity was analyzed using generalized estimating equation analysis. Lesion detection was evaluated using the jackknife free-response receiver operating characteristic figures-of-merit. Compared with SDCT, a significantly lower effective dose (16.4 ± 7.2 mSv vs. 10.4 ± 6.0 mSv, 36.6% reduction) and iodine amount (350 mg iodine/mL vs. 270 mg iodine/mL, 22.9% reduction) were utilized in DLDCT. The mean overall arterial and portal phase image quality scores of DLDCT were significantly higher than SDCT (arterial phase, 4.77 ± 0.45 vs. 4.93 ± 0.24, AUCVGA 0.572 [95% CI, 0.507-0.638]; portal phase, 4.83 ± 0.38 vs. 4.92 ± 0.26, AUCVGA 0.535 [95% CI, 0.469-0.601]). Furthermore, DLDCT showed significantly superior quantitative results for the lesion contrast-to-noise ratio (7.55 ± 4.55 vs. 3.70 ± 2.64, p < 0.001) and lesion detectability (0.97 vs. 0.86, p = 0.003). In patients with chronic liver disease, DLDCT using DL-CB can provide acceptable image quality without impairing the detection and evaluation of hepatic focal lesions compared to SDCT.

Photon-counting computed tomography versus energy-integrating computed tomography for detection of small liver lesions: comparison using a virtual framework imaging.

Photon-counting computed tomography (PCCT) has the potential to provide superior image quality to energy-integrating CT (EICT). We objectively compare PCCT to EICT for liver lesion detection. Fifty anthropomorphic, computational phantoms with inserted liver lesions were generated. Contrast-enhanced scans of each phantom were simulated at the portal venous phase. The acquisitions were done using DukeSim, a validated CT simulation platform. Scans were simulated at two dose levels ( 1.5 to 6.0mGy) modeling PCCT (NAEOTOM Alpha, Siemens, Erlangen, Germany) and EICT (SOMATOM Flash, Siemens). Images were reconstructed with varying levels of kernel sharpness (soft, medium, sharp). To provide a quantitative estimate of image quality, the modulation transfer function (MTF), frequency at 50% of the MTF ( ), noise magnitude, contrast-to-noise ratio (CNR, per lesion), and detectability index ( , per lesion) were measured. Across all studied conditions, the best detection performance, measured by , was for PCCT images with the highest dose level and softest kernel. With soft kernel reconstruction, PCCT demonstrated improved lesion CNR and compared with EICT, with a mean increase in CNR of 35.0% ( ) and 21% ( ) and a mean increase in of 41.0% ( ) and 23.3% ( ) for the 1.5 and 6.0mGy acquisitions, respectively. The improvements were greatest for larger phantoms, low-contrast lesions, and low-dose scans. PCCT demonstrated objective improvement in liver lesion detection and image quality metrics compared with EICT. These advances may lead to earlier and more accurate liver lesion detection, thus improving patient care.

Assessment of Different Castration Resistance Definitions and Staging Modalities in Metastatic Castration-Resistant Prostate Cancer.

Background/Objectives: Progression to metastatic castration-resistant prostate cancer (mCRPC) is defined either biochemically, radiographically or both. Moreover, staging for mCRPC can be performed either conventionally or with molecular imaging such as prostate-specific membrane antigen computer tomography (PSMA-PET/CT). Methods: We relied on the Frankfurt Metastatic Cancer Database of the Prostate (FRAMCAP) database to compare progression-free (PFS) and overall survival (OS) outcomes regarding the cause of castration resistance and the staging modality used. Results: Overall, 35% progressed to mCRPC biochemically vs. 23% radiographically vs. 42% biochemically + radiographically. The PSA nadir in mHSPC (1.4 vs. 0.4 vs. 0.8 ng/mL) and PSA level at mCRPC progression (15 vs. 2 vs. 21 ng/mL, both p ≤ 0.01) were significantly higher for biochemical vs. radiographic vs. both progressed patients. In PFS and OS analyses, no significant differences were observed among all three compared groups. In the comparison of the staging used for progression to mCRPC, 67% received conventional vs. 33% PSMA-PET/CT, with higher metastatic burden in mHSPC and osseous lesions in mCRPC for conventionally staged patients (both p < 0.01). In PFS (15.3 vs. 10.1 months, hazard ratio [HR]: 0.75) and OS analyses (52.6 vs. 34.3 months, HR: 0.61, both p < 0.05), PSMA-PET/CT harbored better prognosis; however, this did not hold after multivariable adjustment. Similar results were observed for further analyses in second- and third-line mCRPC or patients with a PSA level of ≥2 ng/mL. Conclusions: The cause of progression to mCRPC seems not to influence cancer-control outcomes, despite important baseline tumor characteristic differences. The PSMA-PET/CT staging modality might be associated with better PFS and OS outcomes, possibly due to its more sensitive detection of progression or new metastatic lesions.

Comparative benefits of Ki and SUV images in lesion detection during PET/CT imaging

BackgroundClinical application of the tracer net influx rate (Ki) imaging in PET/CT remains limited, due to a lack of evidence demonstrating the superiority of Ki images in lesion detection, and guidelines on when to utilize Ki images. This study aims to compare the benefits of Ki and standardized uptake value (SUV) images in lesion detection during PET/CT imaging. By analyzing the performance of both techniques in identifying tumor lesions, the study seeks to provide guidance for the clinical application of Ki images.ResultsThis retrospective study included 134 patients with 244 pathologically confirmed lesions (200 malignant and 44 benign). Patients with a histopathological diagnosis received a weight-based 18F-FDG injection and underwent 60-min total-body PET/CT dynamic imaging. SUV images were reconstructed using data collected from the last 10 min of the scans. Ki images were generated using the Patlak methods with data from minutes 12–60. The background SUVmax, SUVmean, SUVSD, Kimax, Kimean, and KiSD values were recorded. The signal-to-noise ratios of the SUV (SUVSNR) and Ki (KiSNR) images were calculated. The lesion detection rate and sensitivity of the SUV and Ki images were evaluated. The lesion-detection rates were 97.7% (214/219) and 99.5% (218/219) for the SUV and Ki images, respectively (p = .22). Five false-negative lesions on the SUV images were true-positive on the Ki images (3 hepatic malignancies and 2 metastatic lymph nodes). The sensitivity (94.0% vs. 96.0%, p = .22), specificity (41.9% vs. 41.9%, p > .99), accuracy (84.4% vs. 86.1%, p = .61), positive predictive value (87.9% vs. 88.1%, p = .94), negative predictive value (60.0% vs. 69.2%, p = .47), and the area under the curve [0.68 (95% confidence interval, 0.61–0.73) vs. 0.69 (95% confidence interval, 0.62–0.74)] were similar in the SUV and Ki images (all p ≥ .10).ConclusionKi images exhibit benefits in lesion detection compared to SUV images, particularly in organs with high background such as liver. The enhanced contrast provided by Ki imaging is recommended to clinically improve detection rates in such cases.

Assessing the deep learning based image quality enhancements for the BGO based GE omni legend PET/CT

BackgroundThis study investigates the integration of Artificial Intelligence (AI) in compensating the lack of time-of-flight (TOF) of the GE Omni Legend PET/CT, which utilizes BGO scintillation crystals.MethodsThe current study evaluates the image quality of the GE Omni Legend PET/CT using a NEMA IQ phantom. It investigates the impact on imaging performance of various deep learning precision levels (low, medium, high) across different data acquisition durations. Quantitative analysis was performed using metrics such as contrast recovery coefficient (CRC), background variability (BV), and contrast to noise Ratio (CNR). Additionally, patient images reconstructed with various deep learning precision levels are presented to illustrate the impact on image quality.ResultsThe deep learning approach significantly reduced background variability, particularly for the smallest region of interest. We observed improvements in background variability of 11.8%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document}, 17.2%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document}, and 14.3%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} for low, medium, and high precision deep learning, respectively. The results also indicate a significant improvement in larger spheres when considering both background variability and contrast recovery coefficient. The high precision deep learning approach proved advantageous for short scans and exhibited potential in improving detectability of small lesions. The exemplary patient study shows that the noise was suppressed for all deep learning cases, but low precision deep learning also reduced the lesion contrast (about −30%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document}), while high precision deep learning increased the contrast (about 10%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document}).ConclusionThis study conducted a thorough evaluation of deep learning algorithms in the GE Omni Legend PET/CT scanner, demonstrating that these methods enhance image quality, with notable improvements in CRC and CNR, thereby optimizing lesion detectability and offering opportunities to reduce image acquisition time.

Optimizing Safety and Precision for Secondary Liposuctions: Integrating Intraoperative Ultrasound With VASER Technology.

Liposuction has gained significant popularity, leading to increased demand for secondary procedures due to complications such as scars and fibrosis that affect aesthetic outcomes. High-Definition Liposuction (HDL) has emerged as a preferred technique, but the presence of fibrosis from prior surgeries may limit its effectiveness. This study explores the application of ultrasound-assisted VASER (Vibration Amplification of Sound Energy at Resonance; VASER-Solta Medical, Bothell, WA) liposuction in secondary abdominal liposculpture to address these challenges. A prospective cohort study was conducted from May 2022 to May 2023, including patients undergoing secondary abdominal liposculpture with ultrasound-assisted VASER liposuction, at least 12 months post their initial procedure. Pre-operative ultrasound examinations were performed to identify and mark findings related to previous liposuction. Data on demographics, photographic results, and complications were collected and analyzed. Intraoperative ultrasound (I-US) significantly improved the detection of fibrotic lesions, leading to more precise, rapid, and atraumatic outcomes. The use of I-US optimized surgical procedures, reducing both costs and operation time. Clear communication with patients regarding potential limitations due to chronic damage was essential for setting realistic expectations. I-US has proven to be an invaluable tool in secondary liposculpture, enhancing surgical precision and outcomes. This methodology allows for better recognition of complications, promoting effective treatment strategies and ultimately improving patient satisfaction in the context of secondary abdominal liposculpture.

SWOT analysis of the application of artificial intelligence in radiologic technology and radiology

Artificial intelligence (AI) is bringing changes to radiology and radiologic technology, enabling the development of programs and algorithms that facilitate diagnosis and decisions. It is essential to understand how AI can improve patient outcomes, increase the efficiency of investigations and reduce costs. Machine and deep learning have proven to be extremely useful in the detection and characterization of lesions, improving routine imaging techniques and facilitating the work of radiologists by reducing workload and improving the quality of reporting. The practical application of artificial intelligence in radiology and radiologic technology has been slowed down by the lack of integrated solutions and well-structured data archives, as well as challenges such as non-transparency of decision-making systems and large amounts of quality data needed to train artificial intelligence models. There are concerns about the potential impact of AI on the work of radiologists and radiologic technologists, which may hinder the development and implementation of this technology. Textual data derived from image reports can provide valuable healthcare insights. Natural language processing (NLP), a subset of artificial intelligence, offers promising solutions for handling unstructured text in these reports, opening a new era in extracting information from medical images and related reports. Due to the challenges in training experts for the application of AI in healthcare, a multidisciplinary approach will have to be used and investments in collaboration and education will have to be made. There are outstanding issues of liability and regulation regarding data storage and privacy, particularly in the case of cloud storage. The concern of the workforce and their lack of education about artificial intelligence represents an obstacle to its adoption, but also offers an opportunity for the technological advancement of the profession.