Detection Of Lesions Research Articles

Comparison of adaptive imaging receiver coil and traditional coil for multiplexed sensitivity encoding diffusion-weighted imaging of the liver.

To compare the image quality and efficacy of the adaptive imaging receiver (AIR) coil (GE Healthcare) and the traditional coil for multiplexed sensitivity encoding diffusion-weighted imaging (MUSE-DWI) in the detection of focal liver lesions (FLLs). Two groups of MUSE-DWI were obtained. Image quality was qualitatively evaluated by 3 independent blinded radiologists on a 5-point scale, and quantitative parameters were calculated by measurements of the region of interest in the liver and FLLs. McNemar's test were used to compare the characteristics and detectability. Less image noise, sharper contours, milder susceptibility artefacts, and better liver lesion conspicuity were found by all radiologists in 60 livers with 140 FLLs with the AIR coil than with the traditional coil (reader average mean, 4.3-4.4 vs. 3.7-4.0, P < .001). The signal-to-noise ratio (SNR) of the liver was significantly higher with the AIR coil than with the traditional coil (right lobe: mean, 8.89 vs.7.76, P < .05; left lobe: mean, 7.14 vs.6.19, P < .001), and the SNR of FLLs (mean, 24.62 vs. 21.01, P < .001) and lesion-to-liver CNR (mean, 16.61 vs. 14.02, P < .001) exhibited significant differences between the AIR coil and the traditional coil. Besides, superior detection of FLLs was observed with the AIR coil compared to the traditional coil (95.7% [134/140] vs. 85.7% [120/140], P < .001). The AIR coil yields less noise, fewer distortions, better lesion detectability, higher SNR of the liver and FLLs, and improved lesion-to-liver CNR during liver MUSE-DWI. Thus, it is a feasible and effective scanning scheme in liver MRI. The AIR coil improves SNR and the quality of liver MR imaging compared with the traditional coil.

Ability of detection in different resolution endoscopy for upper gastrointestinal mucosal lesions

BackgroundMost endoscopists believe that higher resolution improves lesion detection rates. However, existing studies primarily compared the detection rates of white light endoscopy (WLE) and other imaging modalities. Our previous study demonstrated the advantages of magnifying endoscopy from general endoscopy for lesion detection, prompting further investigation into the variations in lesion detection rates across endoscopes with different resolutions.MethodsEndoscopic and corresponding pathological data from our medical unit over the past 5 years were analyzed. We excluded specific-purpose endoscopic procedures to ensure the natural randomization of the data. Baseline adjustment and risk factor analyses used multi-group propensity score matching and logistic regression.ResultsThe overall lesion detection rate was significantly higher with high-quality endoscopy (Q-endoscopy) compared to high-definition endoscopy (H-endoscopy) and high definition and quality endoscopy (HQ-endoscopy) (34.4% vs. 30.2% vs. 29.6%, P = 0.001). Similar results were observed for elevated lesions (25.7% vs. 21.0% vs. 22.9%, P = 0.001) and depressed lesions (6.6% vs. 6.2% vs. 3.6%, P < 0.001). HQ-endoscopy had a superior detection rate for superficial lesions compared to both H- and Q-endoscopies (3.0% vs. 2.8% vs. 1.8%, P = 0.041). However, there were no significant differences in neoplastic detection rate or missed neoplastic lesion rate among the three groups.ConclusionQ-endoscopy is superior in detecting non-superficial lesions, while HQ-endoscopy is better at detecting superficial lesions. However, there were no statistically significant differences in detecting or omitting neoplastic lesions among the three endoscopic examinations.

Enhancing boundary detection of radiofrequency ablation lesions through photoacoustic mapping

Atrial fibrillation (A-fib) is the most common type of heart arrhythmia, typically treated with radiofrequency catheter ablation to isolate the heart from abnormal electrical signals. Monitoring the formation of ablation-induced lesions is crucial for preventing recurrences and complications arising from excessive or insufficient ablation. Existing imaging modalities lack real-time feedback, and their intraoperative usage is in its early stages. A critical need exists for an imaging-based lesion indexing (LSI) method that directly reflects tissue necrosis formation. Previous studies have indicated that spectroscopic photoacoustic (sPA) imaging can differentiate ablated tissues from their non-ablated counterparts based on PA spectrum variation. In this paper, we introduce a method for detecting ablation lesion boundaries using sPA imaging. This approach utilizes ablation LSI, which quantifies the ratio between the signal from ablated tissue and the total tissue signal. We enhance boundary detection accuracy by adapting a regression model-based compensation. Additionally, the method was cross-validated with clinically used intraoperative monitoring parameters. The proposed method was validated with ex vivo porcine cardiac tissues with necrotic lesions created by different ablation durations. The PA-measured lesion size was compared with gross pathology. Statistical analysis demonstrates a strong correlation (R > 0.90) between the PA-detected lesion size and gross pathology. The PA-detected lesion size also exhibits a moderate to strong correlation (R > 0.75) with local impedance changes recorded during procedures. These results suggest that the introduced PA imaging-based LSI has great potential to be incorporated into the clinical workflow, guiding ablation procedures intraoperatively.

Value of hepatic artery digital subtraction angiography in the detection of small hepatocellular carcinoma lesions.

To compare the detection rates of hepatic artery digital subtraction angiography (HA-DSA) and magnetic resonance imaging (MRI) gadolinium diethylenetriaminepentaacetic acid (MRI-Gd-DTPA) and MRI gadolinium diethylenetriaminepentaacetic acid (MRI-Gd-EOB-DTPA) for small (diameter ≤2 cm) hepatocellular carcinoma (HCC) lesions. A prospective analysis of patients admitted to the Tumor Hospital of Guangxi Medical University between January 1, 2015, and December 30, 2016, was conducted. The detection rates of the three methods were analyzed. The diameter of small HCC lesions detected using HA-DSA and MRI-Gd-EOB-DTPA were evaluated. The diagnostic value of HCC Barcelona staging for HA-DSA was analyzed. For 107 small lesions detected in 57 patients, the detection rates of HA-DSA and MRI-Gd-DTPA were 86.0% (92/107) and 71.0% (76/107), respectively (p < .05). Of 77 small lesions detected in 42 patients using MRI-Gd-EOB-DTPA and HA-DSA, 67 were detected using HA-DSA, all of which had a rich blood supply, and 72 were detected using MRI-Gd-EOB-DTPA. The minimum diameter of lesions detected using MRI-Gd-EOB-DTPA was approximately 0.4 cm, whereas that of lesions detected using HA-DSA was approximately 0.5 cm. After HA-DSA, a change in the Barcelona staging occurred in 33.3% (62/186) of cases but not after MRI-Gd-DTPA; HA-DSA was significantly better than MRI-Gd-DTPA for staging (p = .03). HA-DSA and MRI-Gd-EOB-DTPA have high diagnostic values for the detection of small HCC lesions, which is helpful for accurate staging of HCC and provides the most valuable information for patient treatment and prognosis.

Penyuluhan Kesehatan tentang Kanker Serviks pada Wanita Usia Subur (WUS) di Desa Kertawinangun Kecamatan Kedawung Kabupaten Cirebon

Cervical cancer is a primary malignant tumor originating from squamous epithelial cells or cells originating from the vagina and urethra, usually occurring in the cervix or cervix which is located between the uterus and the sexual canal (vagina). According to WHO 2018, cervical cancer is the fourth leading cause of death in women throughout the world, estimated at 570,000, while new cases in 2018 or 6.6% of all cancers in women. Human papilloma virus or commonly called (HPV) is known to cause cervical cancer which can be transmitted through sexual intercourse, infection with several types of viruses, and personal hygiene. Symptoms of cervical cancer can be recognized by the presence of fluid from the birth canal, namely abnormal vaginal discharge, contact bleeding (bleeding during intercourse), and feeling pain during coitus / sexual intercourse as well as bleeding even after entering menopause. Early symptoms of pre-cancerous conditions are generally characterized by the discovery of abnormal cells. These abnormal cells develop into cervical cancer and then the following symptoms of cervical cancer appear; the appearance of pain and bleeding during sexual intercourse (contact bleeding), abnormal vaginal bleeding, such as bleeding outside the menstrual cycle, bleeding between regular menstrual periods, menstrual periods that are longer and more abundant than usual, bleeding after menopause, vaginal discharge excessive and abnormal, if the cancer has spread to the pelvis, the patient will suffer from complaints of pelvic pain, difficulty urinating, and enlarged kidneys. Cervical cancer can be prevented 100% by HPV vaccination, using condoms, avoiding tobacco consumption, and early detection and treatment of precancerous lesions.

A web-based mpox skin lesion detection system using state-of-the-art deep learning models considering racial diversity

The recent ‘Mpox’ outbreak, formerly known as ‘Monkeypox’, has been a significant public health concern and spread to over 110 countries globally. The challenge of clinically diagnosing mpox early on is due, in part, to its similarity to other types of rashes. Computer-aided screening tools have been proven valuable in cases where Polymerase Chain Reaction (PCR) based diagnosis is not immediately available. Deep learning methods excel at learning complex data representations, but their efficacy largely depends on adequate training data. To address this challenge, we present the “Mpox Skin Lesion Dataset Version 2.0 (MSLD v2.0)” as a follow-up to the previously released open-access dataset, one of the first to contain mpox lesion images. This dataset contains images of patients with mpox and five other non-mpox classes (chickenpox, measles, hand-foot-mouth disease, cowpox, and healthy). We benchmark the performance of several state-of-the-art deep learning models, including VGG16, ResNet50, DenseNet121, MobileNetV2, EfficientNetB3, InceptionV3, and Xception, to classify mpox and other infectious skin diseases. We leverage transfer learning implemented with pre-trained weights generated from the HAM10000 dataset, an extensive collection of pigmented skin lesion images. To reduce the impact of racial bias, we employ a color space data augmentation method to increase skin color variability during training and present a rigorous assessment of the technique’s effectiveness in skin lesion classification; we achieved the best overall accuracy of 83.59±2.11%. Finally, the developed models are incorporated within a prototype web application to analyze uploaded skin images by a user and determine whether a subject is a suspected mpox patient. We believe that the presented tool can be of significant impact in screening of mpox in case of a future outbreak.

Boundary-aware semantic clustering network for segmentation of prostate zones from T2-weighted MRI

Objective. Automatic segmentation of prostatic zones from MRI can improve clinical diagnosis of prostate cancer as lesions in the peripheral zone (PZ) and central gland (CG) exhibit different characteristics. Existing approaches are limited in their accuracy in localizing the edges of PZ and CG. The proposed boundary-aware semantic clustering network (BASC-Net) improves segmentation performance by learning features in the vicinity of the prostate zonal boundaries, instead of only focusing on manually segmented boundaries. Approach. BASC-Net consists of two major components: the semantic clustering attention (SCA) module and the boundary-aware contrastive (BAC) loss. The SCA module implements a self-attention mechanism that extracts feature bases representing essential features of the inner body and boundary subregions and constructs attention maps highlighting each subregion. SCA is the first self-attention algorithm that utilizes ground truth masks to supervise the feature basis construction process. The features extracted from the inner body and boundary subregions of the same zone were integrated by BAC loss, which promotes the similarity of features extracted in the two subregions of the same zone. The BAC loss further promotes the difference between features extracted from different zones. Main results. BASC-Net was evaluated on the NCI-ISBI 2013 Challenge and Prostate158 datasets. An inter-dataset evaluation was conducted to evaluate the generalizability of the proposed method. BASC-Net outperformed nine state-of-the-art methods in all three experimental settings, attaining Dice similarity coefficients of 79.9% and 88.6% for PZ and CG, respectively, in the NCI-ISBI dataset, 80.5% and 89.2% for PZ and CG, respectively, in Prostate158 dataset, and 73.2% and 87.4% for PZ and CG, respectively, in the inter-dataset evaluation. Significance. As prostate lesions in PZ and CG have different characteristics, the zonal boundaries segmented by BASC-Net will facilitate prostate lesion detection.

Can a fast T2-Dixon sequence surpass the time obstacle of whole-body MRI in the evaluation of skeletal metastases?

BackgroundWhole-body magnetic resonance imaging (WB-MRI) has shown its accuracy in the diagnosis of skeletal metastases in patients with known primary solid cancers. The standard protocol was a combination of T1 and short tau inversion recovery (STIR) sequences. Herein, this study was conducted to elucidate the role of the T2-Dixon sequence as a rapid alternative to the standard protocol with the assessment of its diagnostic accuracy and comparability to the established methodology.MethodsThis prospective study included 30 patients with primary solid malignancies who underwent WB-MRI. The sequences obtained were T1WI, STIR, and T2-Dixon (fat-only and water-only images). Skeletal metastases were evaluated in each sequence. Results were compared between the T1-STIR combination and T2-Dixon fat and water reconstructions.ResultsThe sensitivity of fat and water reconstructions from a single T2-Dixon in the detection of lytic skeletal metastases was marginally superior to a combination of T1WI and STIR sequences (0–7%). Detection of mixed lesions demonstrated equally high sensitivity in both protocols. Sclerotic metastases detection in WB-MRI showed low sensitivity in both protocols. However, specificity surpassed 95% for all lesion types in both protocols. Overall image quality was favored (in 87–90% of patients) in T2-Dixon images. The overall estimated acquisition timing using T2-Dixon appeared to be approximately half that of the standard T1-STIR combination.ConclusionsWB-MRI using T2-Dixon fat and water reconstructions showed similar accuracy to T1WI and STIR combination in the evaluation of skeletal metastases in patients with primary solid cancers with significantly shorter acquisition time.

YOLOv5s-BiPCNeXt, a Lightweight Model for Detecting Disease in Eggplant Leaves.

Ensuring the healthy growth of eggplants requires the precise detection of leaf diseases, which can significantly boost yield and economic income. Improving the efficiency of plant disease identification in natural scenes is currently a crucial issue. This study aims to provide an efficient detection method suitable for disease detection in natural scenes. A lightweight detection model, YOLOv5s-BiPCNeXt, is proposed. This model utilizes the MobileNeXt backbone to reduce network parameters and computational complexity and includes a lightweight C3-BiPC neck module. Additionally, a multi-scale cross-spatial attention mechanism (EMA) is integrated into the neck network, and the nearest neighbor interpolation algorithm is replaced with the content-aware feature recombination operator (CARAFE), enhancing the model's ability to perceive multidimensional information and extract multiscale disease features and improving the spatial resolution of the disease feature map. These improvements enhance the detection accuracy for eggplant leaves, effectively reducing missed and incorrect detections caused by complex backgrounds and improving the detection and localization of small lesions at the early stages of brown spot and powdery mildew diseases. Experimental results show that the YOLOv5s-BiPCNeXt model achieves an average precision (AP) of 94.9% for brown spot disease, 95.0% for powdery mildew, and 99.5% for healthy leaves. Deployed on a Jetson Orin Nano edge detection device, the model attains an average recognition speed of 26 FPS (Frame Per Second), meeting real-time requirements. Compared to other algorithms, YOLOv5s-BiPCNeXt demonstrates superior overall performance, accurately detecting plant diseases under natural conditions and offering valuable technical support for the prevention and treatment of eggplant leaf diseases.

Comparison of the Image Quality of Turbo Spin Echo and Echo-Planar Diffusion-Weighted Imaging of the Head and Neck Region.

Magnetic resonance imaging (MRI) of the head and neck region is notably challenging due to the complex anatomy and the critical need for high-resolution imaging to accurately diagnose various pathologies. The two prominent MRI techniques used in this context are turbo spin echo (TSE) and echo-planar diffusion-weighted imaging (EP-DWI). TSE is recognized for providing high-resolution anatomical images, whereas EP-DWI offers functional imaging that highlights the diffusion of water molecules, essential for detecting early pathological changes. This study aims to compare the image quality of TSE and EP-DWI in the head and neck region to assess their diagnostic efficacy and clinical utility. This retrospective study was conducted at Saveetha Medical College and Hospital over six months. A total of 100 patients (50 males and 50 females, aged 18-65 years) with various head and neck pathologies were included. Patients underwent both TSE and EP-DWI sequences using a Philips MULTIVA 1.5 T scanner. Image quality was assessed based on signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), artifact presence, and lesion detection. Two experienced radiologists independently reviewed the images, with inter-observer agreement calculated using Cohen's kappa coefficient. The mean SNR for TSE was significantly higher than EP-DWI (45.2 vs. 28.7, p<0.01), indicating superior image clarity and detail in TSE images. TSE demonstrated a higher mean CNR compared to EP-DWI (25.4 vs. 15.8, p<0.01), suggesting better differentiation between different tissue types and pathologies. Artifacts were more frequent in EP-DWI images (45% vs. 15%), with motion artifacts being the most common. TSE detected more lesions (120 vs. 95), with more precise delineation of lesions. The inter-observer agreement was excellent for both TSE and EP-DWI, with kappa values of 0.85 and 0.80, respectively. TSE MRI provides superior image quality compared to EP-DWI for evaluating the head and neck region. The enhanced SNR and CNR in TSE images result in clearer and more detailed visualizations of anatomical structures and pathological changes, with fewer artifacts. While EP-DWI is valuable for functional imaging, its role should be complementary to TSE. The study suggests that TSE should be the preferred modality for detailed anatomical assessment in the head and neck region. Further studies with larger sample sizes and advanced imaging techniques may provide additional insights into optimizing MRI protocols for head and neck imaging.

Clinical SWIR and CP-OCT imaging of interproximal lesions

BackgroundEnamel is highly transparent at short wavelength infrared imaging (SWIR) wavelengths allowing the detection of dental decay without the need for ionizing radiation. The purpose of this study was to use SWIR imaging methods including cross polarization optical coherence tomography (CP-OCT), occlusal transillumination (SWIR-OT), proximal transillumination (SWIR-PT), and occlusal reflectance (SWIR-R) to image interproximal lesions in vivo and compare the sensitivity with radiography.MethodsParticipants (n = 30) aged 18–80 each with a radiopositive interproximal lesion scheduled for restoration were enrolled in the study. Studies have shown that the opposing proximal surfaces across the contact will likely also have lesions. SWIR images were acquired of the adjoining teeth at each contact with an interproximal lesion scheduled for restoration. Lesion presence and depth were assessed on each side of the contact for radiography and each SWIR imaging method. Lesions on radiographs and in CP-OCT images were identified by a single examiner while lesions in SWIR images were identified by a contrast threshold via semi-automatic image segmentation.ResultsAll SWIR imaging methods had significantly higher sensitivity (P < 0.05) than radiographs for the detection of interproximal lesions on the teeth opposite those restored. CP-OCT and SWIR-R imaging methods had significantly higher sensitivity than the other methods. SWIR imaging methods showed significantly higher lesion contrast than radiography.ConclusionsSWIR imaging methods can be used to detect interproximal lesions on posterior teeth with higher diagnostic performance than radiographs. CP-OCT appears well suited as a potential gold standard for the detection of interproximal lesions and assessment of their severity in vivo.

Computer-Aided Diagnosis of Diabetic Retinopathy Lesions Based on Knowledge Distillation in Fundus Images

At present, the early diagnosis of diabetic retinopathy (DR), a possible complication of diabetes due to elevated glucose concentrations in the blood, is usually performed by specialists using a manual inspection of high-resolution fundus images based on lesion screening, leading to problems such as high work-intensity and accessibility only in specialized health centers. To support the diagnosis of DR, we propose a deep learning-based (DL) DR lesion classification method through a knowledge distillation (KD) strategy. First, we use the pre-trained DL architecture, Inception-v3, as a teacher model to distill the dataset. Then, a student model, also using the Inception-v3 model, is trained on the distilled dataset to match the performance of the teacher model. In addition, a new combination of Kullback–Leibler (KL) divergence and categorical cross-entropy (CCE) loss is used to measure the difference between the teacher and student models. This combined metric encourages the student model to mimic the predictions of the teacher model. Finally, the trained student model is evaluated on a validation dataset to assess its performance and compare it with both the teacher model and another competitive DL model. Experiments are conducted on the two datasets, corresponding to an imbalanced and a balanced dataset. Two baseline models (Inception-v3 and YOLOv8) are evaluated for reference, obtaining a maximum training accuracy of 66.75% and 90.90%, respectively, and a maximum validation accuracy of 35.94% and 81.52%, both for the imbalanced dataset. On the other hand, the proposed DR classification model achieves an average training accuracy of 99.01% and an average validation accuracy of 97.30%, overcoming the baseline models and other state-of-the-art works. Experimental results show that the proposed model achieves competitive results in DR lesion detection and classification tasks, assisting in the early diagnosis of diabetic retinopathy.

Classification of melanocytic lesions using direct illumination multispectral imaging

With rising melanoma incidence and mortality, early detection and surgical removal of primary lesions is essential. Multispectral imaging is a new, non-invasive technique that can facilitate skin cancer detection by measuring the reflectance spectra of biological tissues. Currently, incident illumination allows little light to be reflected from deeper skin layers due to high surface reflectance. A pilot study was conducted at the University Hospital Basel to evaluate, whether multispectral imaging with direct light coupling could extract more information from deeper skin layers for more accurate dignity classification of melanocytic lesions. 27 suspicious pigmented lesions from 23 patients were included (6 melanomas, 6 dysplastic nevi, 12 melanocytic nevi, 3 other). Lesions were imaged before excision using a prototype snapshot mosaic multispectral camera with incident and direct illumination with subsequent dignity classification by a pre-trained multispectral image analysis model. Using incident light, a sensitivity of 83.3% and a specificity of 58.8% were achieved compared to dignity as determined by histopathological examination. Direct light coupling resulted in a superior sensitivity of 100% and specificity of 82.4%. Convolutional neural network classification of corresponding red, green, and blue lesion images resulted in 16.7% lower sensitivity (83.3%, 5/6 malignant lesions detected) and 20.9% lower specificity (61.5%) compared to direct light coupling with multispectral image classification. Our results show that incorporating direct light multispectral imaging into the melanoma detection process could potentially increase the accuracy of dignity classification. This newly evaluated illumination method could improve multispectral applications in skin cancer detection. Further larger studies are needed to validate the camera prototype.

Superior lesion detection on 3D FSE T1WI with magnetization transfer and CHESS preparation pulses in children with focal epilepsy: Preliminary results.

In childhood drug-resistant focal epilepsy, the identification of a magnetic resonance imaging lesion significantly affects the management and prognosis, although it is often challenging. Herein we report the preliminary results of a modified MR sequence, in which both magnetization transfer and chemical shift selective preparation pulses are added to a 3D fast spin echo T1-weighted sequence to recognize focal cortical dysplasia. The scan time is short, and the images have expected uniform suppression of the background normal gray and white matter. We report four children with focal epilepsy, in whom the focal cortical and subcortical lesions are superiorly conspicuous on the aforementioned MR sequence compared to the high-resolution fluid-attenuated inversion recovery images obtained with typical epilepsy MR protocols.

Effect of deep learning reconstruction on the assessment of pancreatic cystic lesions using computed tomography.

This study aimed to compare the image quality and detection performance of pancreatic cystic lesions between computed tomography (CT) images reconstructed by deep learning reconstruction (DLR) and filtered back projection (FBP). This retrospective study included 54 patients (mean age: 67.7 ± 13.1) who underwent contrast-enhanced CT from May 2023 to August 2023. Among eligible patients, 30 and 24 were positive and negative for pancreatic cystic lesions, respectively. DLR and FBP were used to reconstruct portal venous phase images. Objective image quality analyses calculated quantitative image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) using regions of interest on the abdominal aorta, pancreatic lesion, and pancreatic parenchyma. Three blinded radiologists performed subjective image quality assessment and lesion detection tests. Lesion depiction, normal structure illustration, subjective image noise, and overall image quality were utilized as subjective image quality indicators. DLR significantly reduced quantitative image noise compared with FBP (p < 0.001). SNR and CNR were significantly improved in DLR compared with FBP (p < 0.001). Three radiologists rated significantly higher scores for DLR in all subjective image quality indicators (p ≤ 0.029). Performance of DLR and FBP were comparable in lesion detection, with no statistically significant differences in the area under the receiver operating characteristic curve, sensitivity, specificity and accuracy. DLR reduced image noise and improved image quality with a clearer depiction of pancreatic structures. These improvements may have a positive effect on evaluating pancreatic cystic lesions, which can contribute to appropriate management of these lesions.

Comparison of a handheld ultrasound device with cart-based ultrasound for the assessment of gout lesions in people with established gout

ObjectivesUse of handheld portable ultrasound is increasing and would improve access for people with rheumatic disease when conventional, cart-based ultrasound is unavailable. This study compared handheld and cart-based ultrasound for the assessment of gout lesions in people with gout. MethodsThe lower limbs of 21 participants with gout were independently scanned at six sites (1st and 2nd metatarsophalangeal joints, knee, patellar ligament, Achilles tendon, and peroneal tendons) using cart-based (LOGIQ P9) and handheld (Vscan Air™) ultrasound by two rheumatologists. One rheumatologist was randomized to scan the right or left leg first with the cart-based or handheld ultrasound. The other rheumatologist scanned the legs in the opposite order with the imaging devices reversed. Images were saved and blinded images scored for double contour, tophus, erosion and aggregates using OMERACT definitions by two rheumatologists experienced in gout ultrasound. ResultsOn handheld ultrasound, 90% of participants had at least one site with double contour, tophus and erosions, and 100% had at least one site with aggregates. There were similar findings using cart-based ultrasound. However, site-level inter-device analysis showed only fair-good agreement: kappa (percentage agreement) for double contour 0.22 (67%), tophus 0.46 (77%), erosion 0.63 (83%) and aggregates 0.37 (75%). There were more aggregates detected by cart-based ultrasound in joints and more tophi detected by handheld ultrasound in ligaments and tendons. ConclusionsHandheld ultrasound can detect gout lesions in people with established gout. However, concordance between cart-based and handheld ultrasound in detection of some gout lesions is low, particularly double contour and aggregates.

Self-normalization for a 1 mm3 resolution clinical PET system using deep learning

Objective. This work proposes, for the first time, an image-based end-to-end self-normalization framework for positron emission tomography (PET) using conditional generative adversarial networks (cGANs). Approach. We evaluated different approaches by exploring each of the following three methodologies. First, we used images that were either unnormalized or corrected for geometric factors, which encompass all time-invariant factors, as input data types. Second, we set the input tensor shape as either a single axial slice (2D) or three contiguous axial slices (2.5D). Third, we chose either Pix2Pix or polarized self-attention (PSA) Pix2Pix, which we developed for this work, as a deep learning network. The targets for all approaches were the axial slices of images normalized using the direct normalization method. We performed Monte Carlo simulations of ten voxelized phantoms with the SimSET simulation tool and produced 26,000 pairs of axial image slices for training and testing. Main results. The results showed that 2.5D PSA Pix2Pix trained with geometric-factors-corrected input images achieved the best performance among all the methods we tested. All approaches improved general image quality figures of merit peak signal to noise ratio (PSNR) and structural similarity index (SSIM) from ∼15 % to ∼55 %, and 2.5D PSA Pix2Pix showed the highest PSNR (28.074) and SSIM (0.921). Lesion detectability, measured with region of interest (ROI) PSNR, SSIM, normalized contrast recovery coefficient, and contrast-to-noise ratio, was generally improved for all approaches, and 2.5D PSA Pix2Pix trained with geometric-factors-corrected input images achieved the highest ROI PSNR (28.920) and SSIM (0.973). Significance. This study demonstrates the potential of an image-based end-to-end self-normalization framework using cGANs for improving PET image quality and lesion detectability without the need for separate normalization scans.

Comparison of the Accuracy of a Deep Learning Method for Lesion Detection in PET/CT and PET/MRI Images.

Develop a universal lesion recognition algorithm for PET/CT and PET/MRI, validate it, and explore factors affecting performance. The 2022 AutoPet Challenge's 1014 PET/CT dataset was used to train the lesion detection model based on 2D and 3D fractional-residual (F-Res) models. To extend this to PET/MRI, a network for converting MR images to synthetic CT (sCT) was developed, using 41 sets of whole-body MR and corresponding CT data. 38 patients' PET/CT and PET/MRI data were used to verify the universal lesion recognition algorithm. Image quality was assessed using signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Total lesion glycolysis (TLG), metabolic tumor volume (MTV), and lesion count were calculated from the resultant lesion masks. Experienced physicians reviewed and corrected the model's outputs, establishing the ground truth. The performance of the lesion detection deep-learning model on different PET images was assessed by detection accuracy, precision, recall, and dice coefficients. Data with a detection accuracy score (DAS) less than 1 was used for analysis of outliers. Compared to PET/CT, PET/MRI scans had a significantly longer delay time (135 ± 45min vs 61 ± 12min) and lower SNR (6.17 ± 1.11 vs 9.27 ± 2.77). However, CNR values were similar (7.37 ± 5.40 vs 5.86 ± 6.69). PET/MRI detected more lesions (with a mean difference of -3.184). TLG and MTV showed no significant differences between PET/CT and PET/MRI (TLG: 119.18 ± 203.15 vs 123.57 ± 151.58, p = 0.41; MTV: 36.58 ± 57.00 vs 39.16 ± 48.34, p = 0.33). A total of 12 PET/CT and 14 PET/MRI datasets were included in the analysis of outliers. Outlier analysis revealed PET/CT anomalies in intestines, ureters, and muscles, while PET/MRI anomalies were in intestines, testicles, and low tracer uptake regions, with false positives in ureters (PET/CT) and intestines/testicles (PET/MRI). The deep learning lesion detection model performs well with both PET/CT and PET/MRI. SNR, CNR and reconstruction parameters minimally impact recognition accuracy, but delay time post-injection is significant.

Improving Computer-aided Detection for Digital Breast Tomosynthesis by Incorporating Temporal Change.

Purpose To develop a deep learning algorithm that uses temporal information to improve the performance of a previously published framework of cancer lesion detection for digital breast tomosynthesis. Materials and Methods This retrospective study analyzed the current and the 1-year-prior Hologic digital breast tomosynthesis screening examinations from eight different institutions between 2016 and 2020. The dataset contained 973 cancer and 7123 noncancer cases. The front end of this algorithm was an existing deep learning framework that performed single-view lesion detection followed by ipsilateral view matching. For this study, PriorNet was implemented as a cascaded deep learning module that used the additional growth information to refine the final probability of malignancy. Data from seven of the eight sites were used for training and validation, while the eighth site was reserved for external testing. Model performance was evaluated using localization receiver operating characteristic curves. Results On the validation set, PriorNet showed an area under the receiver operating characteristic curve (AUC) of 0.931 (95% CI: 0.930, 0.931), which outperformed both baseline models using single-view detection (AUC, 0.892 [95% CI: 0.891, 0.892]; P < .001) and ipsilateral matching (AUC, 0.915 [95% CI: 0.914, 0.915]; P < .001). On the external test set, PriorNet achieved an AUC of 0.896 (95% CI: 0.885, 0.896), outperforming both baselines (AUC, 0.846 [95% CI: 0.846, 0.847]; P < .001 and AUC, 0.865 [95% CI: 0.865, 0.866]; P < .001, respectively). In the high sensitivity range of 0.9 to 1.0, the partial AUC of PriorNet was significantly higher (P < .001) relative to both baselines. Conclusion PriorNet using temporal information further improved the breast cancer detection performance of an existing digital breast tomosynthesis cancer detection framework. Keywords: Digital Breast Tomosynthesis, Computer-aided Detection, Breast Cancer, Deep Learning © RSNA, 2024 See also commentary by Lee in this issue.

Evaluation of prostate cancer detection using micro-ultrasound versus MRI through co-registration to whole-mount pathology

Micro-ultrasound has recently been introduced as a low-cost alternative to multi-parametric MRI for imaging prostate cancer. Early clinical studies have demonstrated promising results; however, robust validation via comparison with whole-mount pathology has yet to be achieved. Due to micro-ultrasound probe design and tissue deformation during scanning, it is difficult to accurately correlate micro-ultrasound imaging planes with ground truth whole-mount pathology slides. In this study, we developed a multi-step methodology to co-register micro-ultrasound and MRI to whole-mount pathology. The three-step process had a registration error of 3.90 ± 0.11 mm and consists of: (1) micro-ultrasound image reconstruction, (2) 3D landmark registration of micro-ultrasound to MRI, and (3) 2D capsule registration of MRI to whole-mount pathology. This process was then used in a preliminary reader study to compare the diagnostic accuracy of micro-ultrasound and MRI in 15 patients who underwent radical prostatectomy for prostate cancer. Micro-ultrasound was found to have equivalent performance to retrospective MRI review for index lesion detection (91.7% vs. 80%), while demonstrating an increased detection of tumor extent (52.5% vs. 36.7%) with similar false positive regions-of-interest (38.3% vs. 40.8%). Prospective MRI review had reduced detection of index lesions (73.3%) and tumor extent (18.9%) but improved false positive regions-of-interest (22.7%) relative to micro-ultrasound and retrospective MRI. Further evaluation is needed with a larger sample size.