Imaging Of Lesions Research Articles

Aphasia outcome: the role of diffusion tensor tractography in patients with acute ischemic stroke

BackgroundsRecovery for poststroke aphasia has a decelerating trajectory, with the greatest improvement is within weeks and the slope of change decreasing over time. Therefore, it is essential to predict the prognosis of aphasia at an early stage as it could provide useful data in specific plans for management strategies. The aim of this work was to assess the arcuate fasciculus in stroke patients with aphasia and its impact on predicting the outcome. A prospective study was performed including 25 patients with acute ischemic stroke and aphasia and 10 healthy control subjects with no history of neurologic or psychiatric disease. All patients underwent language assessment using an Arabic version of the Comprehensive Aphasia Test (Arabic CAT), with the resultant mean T-score aphasia quotient (AQ). Early assessment of stroke and delayed assessment at three months. All patients had diffusion-weighted magnetic resonance imaging (DWI-MRI) of the brain to localize the lesion and 3D diffusion tensor imaging (DTI) of the arcuate fasciculus (AF) within 30 days of stroke.ResultsPatients in whom the AF could not be reconstructed had a poor score in early and late AQ and a poor prognosis compared to those in whom the AF could be reconstructed. Preservation of the left AF on DTI could mean the potential recovery of aphasia after stroke.ConclusionThe prognosis of aphasia in patients whose left AF could be reconstructed was better than those whose left AF could not be reconstructed, irrespective of the AF's integrity. That is why, we can assume that evaluation of the DTI of the left AF at early stages of stroke can help in predicting outcome of aphasia.

Acquisition and reconstruction with motion suppression DWI enhance image quality in nasopharyngeal carcinoma patients: Non-echo-planar DWI comparison with single-shot echo-planar DWI

PurposeTo evaluate the impact of application acquisition and reconstruction with motion suppression (ARMS) technology on improving the image quality of diffusion-weighted Imaging (DWI) for nasopharyngeal carcinoma (NPC), compared to single-shot echo-planar imaging (SS-EPI). MethodsA total of 90 patients with NPC underwent MR examination, including ARMS DWI and SS-EPI DWI sequences. Both DWI sequences were acquired with b-values 0 and 800 s/mm2. Two radiologists evaluated the visibility of the lesion, geometric distortion, and overall image quality of the two DWI sequences. Signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), geometric distortion degree, and apparent diffusion coefficient (ADC) values of the nasopharyngeal lesions were assessed and compared for two sequences. The Wilcoxon signed-rank test was used to compare the quantitative and qualitative parameters of the two sequences. ResultsThe lesion visibility, geometric distortion, and overall image quality scores were significantly higher in ARMS DWI (all P<0.001). Four small-sized lesions were not visible and four lesions were partially visible in the SS-EPI DWI sequence. Lesion detection rate of ARMS DWI is 100 %, while that of SS-EPI is 95.56 %, P<0.043. The mismatch distance between the fusion images of ARMS DWI and T2WI was smaller than that of SS-EPI DWI and T2WI (all P<0.001). The SNR and CNR of ARMS DWI were lower than that of SS-EPI DWI (114.48 ± 37.89 vs. 202.61 ± 78.84, P<0.001 and 1.81 ± 1.84 vs. 3.29 ± 3.71, P<0.003) while the ADC value was higher (839.19 ± 138.44 × 10−6 mm2/s vs. 788.82 ± 110.96 × 10−6 mm2/s, P<0.002). ConclusionARMS DWI improves the image quality by reducing geometric distortion and magnetic susceptibility artifacts. ARMS DWI is superior to SS-EPI DWI for diagnosing small-sized nasopharyngeal lesions, although it has lower SNR and CNR.

Fundus-DANet: Dilated Convolution and Fusion Attention Mechanism for Multilabel Retinal Fundus Image Classification

The difficulty of classifying retinal fundus images with one or more illnesses present or missing is known as fundus multi-lesion classification. The challenges faced by current approaches include the inability to extract comparable morphological features from images of different lesions and the inability to resolve the issue of the same lesion, which presents significant feature variances due to grading disparities. This paper proposes a multi-disease recognition network model, Fundus-DANet, based on the dilated convolution. It has two sub-modules to address the aforementioned issues: the interclass learning module (ILM) and the dilated-convolution convolutional block attention module (DA-CBAM). The DA-CBAM uses a convolutional block attention module (CBAM) and dilated convolution to extract and merge multiscale information from images. The ILM uses the channel attention mechanism to map the features to lower dimensions, facilitating exploring latent relationships between various categories. The results demonstrate that this model outperforms previous models in classifying fundus multilocular lesions in the OIA-ODIR dataset with 93% accuracy.

Comorbidity and Disease Activity in Multiple Sclerosis

Multiple studies suggest that comorbidity worsens clinically relevant outcomes in multiple sclerosis (MS), including the severity of disability at diagnosis and rate of disability worsening after diagnosis. However, less is known regarding the association of comorbidity with measures of disease activity, such as relapse rate and magnetic resonance imaging lesion accrual, which are relevant to clinicians and clinical trialists. To evaluate the association of comorbidities with disease activity in clinical trials of disease-modifying therapies (DMTs) in populations with MS. A 2-stage meta-analytic approach was used in this cohort study of individual participant data from phase 3 clinical trials of MS DMTs that had 2 years of follow-up and were conducted from November 2001 to March 2018. Data were analyzed from February 2023 to June 2024. Comorbidity burden and individual comorbidities present at trial enrollment, including hypertension; hyperlipidemia; functional cardiovascular disease, ischemic heart, cerebrovascular, and peripheral vascular disease; diabetes; autoimmune thyroid and miscellaneous autoimmune conditions; migraine; lung and skin conditions; depression; anxiety; and other psychiatric disorders. The main outcome was evidence of disease activity (EDA) over 2 years of follow-up, defined as confirmed relapse activity, disability worsening, or any new lesions on magnetic resonance imaging. A total of 16 794 participants with MS were included from 17 clinical trials (67.2% female). Over the 2-year follow-up, 61.0% (95% CI, 56.2%-66.3%; I2 = 97.9%) of the pooled trials had EDA. After adjusting for multiple factors, the presence of 3 or more comorbidities was associated with an increased hazard of EDA (adjusted hazard ratio [AHR], 1.14; 95% CI, 1.02-1.28) compared with no comorbidity. Presence of 2 or more cardiometabolic conditions was also associated with an increased hazard of EDA (AHR, 1.21; 95% CI, 1.08-1.37) compared with no cardiometabolic comorbidity. Presence of 1 psychiatric disorder was associated with an increased hazard of EDA (AHR, 1.07; 95% CI, 1.02-1.14). In this study, a higher burden of comorbidity was associated with worse clinical outcomes in people with MS, although comorbidity could potentially be a partial mediator of other negative prognostic factors. Our findings suggest a substantial adverse association of the comorbidities investigated with MS disease activity and that prevention and management of comorbidities should be a pressing concern in clinical practice.

Preoperative cerebral angiography nearly doubles the rate of diffusion-weighted imaging lesion detection following minimally invasive surgery for intracerebral hemorrhage

BackgroundDiffusion-weighted imaging (DWI) lesions have been linked to poor outcomes after intracerebral hemorrhage (ICH). We aimed to assess the impact of cerebral digital subtraction angiography (DSA) on the presence of...

Comparative Effectiveness of Teledermatology Versus In-person Consultations: A Systematic Review of Diagnostic Information Elements

Context: Teledermatology is delivered through two primary methods: Live video conferencing, which enables real-time interaction between patients and doctors, and the store-and-forward technique, where images of skin lesions are sent over the internet for later examination. Objectives: This systematic review evaluates the concordance between in-person and telemedicine follow-up methods in dermatology. Methods: In February 2024, a comprehensive literature search was conducted across PubMed, Medline, ISI Web of Science, and the ACM Digital Library. Keywords such as "teledermatology," "telemedicine," and "mobile health" were used, following the PICOS criteria. Results: Initially, 716 articles were identified from the databases, along with four studies from the gray literature search. After removing duplicates, screening studies, and applying the inclusion and exclusion criteria, 21 studies were selected for the final review. These studies detailed follow-up procedures and assessed both direct and indirect costs and effectiveness. The consensus indicates that teledermatology reduces costs and satisfies both patients and healthcare professionals. Conclusions: Teledermatology has been shown to potentially increase the efficiency of follow-up care compared to traditional methods. However, further research is needed to develop standardized evaluation protocols and to more accurately measure and validate key variables. Publications suggest that teledermatology is cost-effective, reduces patient wait times, extends access to dermatological care in remote areas, and enhances satisfaction among patients, doctors, and nurses.

Classification of Human Monkeypox with by Fuzzy C-Means Algorithm Using Image Processing Methods and Haralick Texture Parameters

Aim: Human monkeypox can cause skin lesions in the form of blisters of different shapes on various parts of the body. Due to the fact that the skin lesions caused by human monkeypox have a very similar appearance to lesions caused by chickenpox and measles, the study includes images of chickenpox and measles as well as images of human monkeypox. The aim of this study is to distinguish human monkeypox virus skin lesion images from other viral diseases with similar images. Methods: For this study, the Monkeypox Skin Lesion Dataset, which consists of binary classification data for monkeypox and non-monkeypox (chickenpox, measles) skin lesions, is accessed from the Kaggle.com website. In total, 228 images are processed, with 101 images in the monkeypox group and 127 images in the non-monkeypox group. The images in the Monkeypox Skin Lesion Dataset are processed using image analysis methods and Haralick texture parameters are calculated to create 13 different features for each image. For the classification process in the statistical analysis part of the study, Fuzzy C-Means algorithm is used. Results: The images used in the study belong to individuals with varying skin tones and from different parts of the body, and the algorithm provides encouraging results in determining the type of skin lesions in the images. The overall classification accuracy rate is 61.8%, and the highest accuracy (76.2%) is achieved in the monkeypox class. Conclusion: This study demonstrates that images of viral diseases with similar skin lesions can be classified using various image processing techniques and different statistical methods.

Optimized clustering-based fusion for skin lesion image classification: Leveraging marine predators algorithm

This manuscript presents a comprehensive approach to enhance the accuracy of skin lesion image classification based on the HAM10000 and BCN20000 datasets. Building on prior feature fusion models, this research introduces an optimized cluster-based fusion approach to address limitations observed in our previous methods. The study proposes two novel feature fusion strategies, KFS-MPA (using K-means) and DFS-MPA (using DBSCAN), for skin lesion classification. These approaches leverage optimized clustering-based deep feature fusion and the marine predator algorithm (MPA). Ten fused feature sets are evaluated using three classifiers on both datasets, and their performance is compared in terms of dimensionality reduction and accuracy improvement. The results consistently demonstrate that the DFS-MPA approach outperforms KFS-MPA and other compared fusion methods, achieving notable dimensionality reduction and the highest accuracy levels. ROC-AUC curves further support the superiority of DFS-MPA, highlighting its exceptional discriminative capabilities. Five-fold cross-validation tests and a comparison with the previously proposed feature fusion method (FOWFS-AJS) are performed, confirming the effectiveness of DFS-MPA in enhancing classification performance. The statistical validation based on the Friedman test and Bonferroni-Dunn test also supports DFS-MPA as a promising approach for skin lesion classification among the evaluated feature fusion methods. These findings emphasize the significance of optimized cluster-based deep feature fusion in skin lesion classification and establish DFS-MPA as the preferred choice for feature fusion in this study.

Enhancing alzheimer’s diagnosis through optimized brain lesion classification in MRI with attention-driven grid feature fusion

This paper explores cognitive interface technology, aiming to tackle current challenges and shed light on the prospects of brain-computer interfaces (BCIs). It provides a comprehensive examination of their transformative impact on medical technology and patient well-being. Specifically, this study contributes to addressing challenges in classifying brain lesion images arising from the complex nature of lesions and limitations of traditional deep learning approaches. It introduces advanced feature fusion models that leverage deep learning algorithms, including the African vulture optimization (AVO) algorithm. These models integrate informative features from multiple pre-trained networks and employ innovative fusion techniques, including the attention-driven grid feature fusion (ADGFF) model. The ADGFF model incorporates an attention mechanism based on the optimized weights obtained using AVO. The objective is to improve the overall accuracy by providing fine-grained control over different regions of interest in the input image through a grid-based technique. This grid-based technique divides the image into vertical and horizontal grids, simplifying the exemplar feature generation process without compromising performance. Experimental results demonstrate that the proposed feature fusion strategies consistently outperform individual pre-trained models in terms of accuracy, sensitivity, specificity, and F1-score. The optimized feature fusion strategies, particularly the GRU-ADGFF model, further enhance classification performance, outperforming CNN and RNN classifiers. The learning progress analysis shows convergence, indicating the effectiveness of the feature fusion strategies in capturing lesion patterns. AUC-ROC curves highlight the superior discriminatory capabilities of the ADGFF-AVO strategy. Five-fold cross-validation is employed to assess the performance of the proposed models, demonstrating their accuracy, and few other accuracy-based measures. The GRU-ADGFF model optimized with AVO consistently achieves high accuracy, sensitivity, and AUC values, demonstrating its effectiveness and generalization capability. The GRU-ADGFF model also outperforms the majority voting ensemble technique in terms of accuracy and discriminative ability. Additionally, execution time analysis reveals good scalability and resource utilization of the proposed models. The Friedman rank test confirms significant differences in classifier performance, with the GRU-ADGFF model emerging as the top-performing method across different feature fusion strategies and optimization algorithms.

Impact of User's Background Knowledge and Polyp Characteristics in Colonoscopy with Computer-Aided Detection.

We investigated how interactions between humans and computer-aided detection (CADe) systems are influenced by the user's experience and polyp characteristics. We developed a CADe system using YOLOv4, trained on 16,996 polyp images from 1,914 patients and 1,800 synthesized sessile serrated lesion (SSL) images. The performance of polyp detection with CADe assistance was evaluated using a computerized test module. Eighteen participants were grouped by colonoscopy experience (nurses, fellows, and experts). The value added by CADe based on the histopathology and detection difficulty of polyps were analyzed. The area under the curve for CADe was 0.87 (95% confidence interval [CI], 0.83 to 0.91). CADe assistance increased overall polyp detection accuracy from 69.7% to 77.7% (odds ratio [OR], 1.88; 95% CI, 1.69 to 2.09). However, accuracy decreased when CADe inaccurately detected a polyp (OR, 0.72; 95% CI, 0.58 to 0.87). The impact of CADe assistance was most and least prominent in the nurses (OR, 1.97; 95% CI, 1.71 to 2.27) and the experts (OR, 1.42; 95% CI, 1.15 to 1.74), respectively. Participants demonstrated better sensitivity with CADe assistance, achieving 81.7% for adenomas and 92.4% for easy-to-detect polyps, surpassing the standalone CADe performance of 79.7% and 89.8%, respectively. For SSLs and difficult-to-detect polyps, participants' sensitivities with CADe assistance (66.5% and 71.5%, respectively) were below those of standalone CADe (81.1% and 74.4%). Compared to the other two groups (56.1% and 61.7%), the expert group showed sensitivity closest to that of standalone CADe in detecting SSLs (79.7% vs 81.1%, respectively). CADe assistance boosts polyp detection significantly, but its effectiveness depends on the user's experience, particularly for challenging lesions.

DAAM-Net: A dual-encoder U-Net network with adjacent auxiliary module for pituitary tumor and jaw cyst segmentation

In the diagnosis of various diseases, accurate segmentation of lesions in medical images is crucial. However, when faced with the challenges of blurred edges, noise, and low contrast in images of pituitary tumors and jaw cysts, existing methods do not perform well in solving these problems. To overcome these problems, we present a new approach based on U-Net architecture. Firstly, a more comprehensive semantic information capture is realized by superimposing two U-Net network structures. Following that, the method incorporates atrous spatial pyramid pooling (ASSP) technology to enable adjustable multi-scale feature extraction. Thirdly, an adjacent auxiliary module (AAM) is designed to smoothly fuse features from different levels, effectively suppressing noise interference and reducing feature ambiguity. By testing on the dataset provided by Quzhou People’s Hospital, the IoU, Dice, Specificity, and Mcc of the method were 77.46%, 87.18%, 99.64% and 86.97% on the pituitary tumor dataset, and 81.32%, 89.53%, 99.91% and 89.55% on the jaw cyst dataset, respectively. Compared with existing algorithms, our method exhibits superior segmentation performance and is expected to become a more reliable auxiliary tool in the diagnosis of medical diseases.

Magnetic resonance imaging features and stroke etiology of ischemic stroke in essential thrombocythemia

BackgroundVarious essential thrombocythemia (ET)-related stroke mechanisms have been proposed, including microcirculatory disturbance due to coagulopathy, vasculitis, and embolism due to thrombus formation in large vessels. However, the stroke mechanism in ET remains largely unexplored. The purpose of this study was to evaluate magnetic resonance image (MRI) features of ischemic stroke in ET and determine the potential stroke mechanism. MethodsWe retrospectively collected data from 21 acute ischemic stroke patients with ET who were admitted to two stroke centers between 2010 and 2023. ET was diagnosed according to the World Health Organization criteria. We evaluated MRI features including the diffusion-weighted image (DWI) lesion pattern, and the presence of hemorrhagic transformation and intracranial artery steno-occlusive lesion, as well as other etiological workup results. ResultsOf 21 patients, 20 exhibited multiple ischemic lesions on DWI, mainly within a single vascular territory. Cortical infarcts were observed in 19 patients. Hemorrhagic transformation occurred in 15 patients. Additionally, 15 patients had intracranial steno-occlusive arteries, which regressed to normal in 11 patients during follow-up. Out of all patients, only 2 had potential causes of stroke other than ET (1 with atrial fibrillation and 1 with intracranial atherosclerotic stenosis). The remaining 19 patients had ET as the only identified potential cause. ConclusionsMRI features, including DWI lesion pattern in ischemic stroke patients with ET, suggested embolic etiology despite the absence of major embolic sources. Intra-arterial thrombus appears to be part of the stroke mechanism related to ET and may contribute to ischemic stroke in ET.

Association between 99mTc-PSMA SPECT/CT imaging and prostate-specific antigen (PSA) and alkaline phosphatase (ALP) levels post-endocrine therapy in patients with prostate cancer and bone metastases

AimTo investigate the association between positive lesions detected by 99mTc-PSMA SPECT/CT and blood levels of prostate-specific antigen (PSA) and alkaline phosphatase (ALP) in patients with prostate cancer (PCa) and bone metastasis undergoing endocrine therapy. MethodsA retrospective analysis was performed on 43 patients diagnosed with PCa bone metastasis who underwent endocrine therapy. PSA, ALP, whole body bone imaging and 99mTc-PSMA SPECT/CT imaging were collected from all patients (Among them, 17 cases were re-examined 99mTc-PSMA SPECT/CT imaging). According to the results of the first 99mTc-PSMA SPECT/CT imaging for detecting bone metastasis, all cases were divided into two groups: positive group and negative group. The relationship between 99mTc-PSMA imaging and PSA and ALP was analyzed by ROC curve. Fisher exact probability method was used to examine the changes in imaging radioactivity uptake, PSA, and ALP levels in 17 patients after treatment, and P < 0.05 was statistically significant. ResultsAll 43 patients had different degrees of radioactive concentrations on whole-body bone imaging. The first 99mTc-PSMA SPECT/CT imaging showed positive bone metastases in 31 cases and negative bone metastases in 12 cases. ROC curve analysis of PSA and ALP, AUC were 0.778 and 0.770, respectively. When PSA > 1.13 ng/mL, 99mTc-PSMA SPECT/CT imaging diagnostic sensitivity was 93.55%, and specificity was 66.67%. When ALP was >86U/L, the diagnostic sensitivity of 99mTc-PSMA SPECT/CT imaging was 64.52%, and the specificity was 83.33%. In 17 cases, the PSA level decreased in 7 and increased in 10. There were 10 cases of increased ALP and 7 cases of decreased ALP levels. In the second 99mTc-PSMA imaging lesion, there were 9 cases with decreased or no uptake, and 8 cases with increased uptake or number of lesions. The changes in 99mTc-PSMA uptake by Fisher’s exact probability method were statistically significant (P < 0.05, P = 0.006, and P = 0.006, respectively), and ALP level was not statistically significant (P = 0.563). Conclusion99mTc-PSMA SPECT/CT imaging can detect PCa bone metastases, which are related to PSA levels. When PSA > 1.13 ng/mL, the sensitivity of diagnosis and detection of positive bone metastases is higher, and when ALP is >86U/L, 99mTc-PSMA imaging has higher specificity.

Classification Criteria for Axial Disease in Youth With Juvenile Spondyloarthritis.

The goal was to develop and validate classification criteria for axial juvenile spondyloarthritis (SpA; AxJSpA). This international initiative consisted of four phases: (1) item generation, (2) item reduction, (3) criteria development, and (4) validation of the AxJSpA criteria by an independent team of experts in an internationally representative validation cohort. These criteria are intended to be used on youth with a physician diagnosis of juvenile SpA and for whom axial disease is suspected. Item generation consisted of a systematic literature review and a free-listing exercise using input from international physicians, which collectively resulted in 108 items. After the item reduction exercise and expert panel input, 37 items remained for further consideration. The final AxJSpA criteria domains included the following: imaging of active inflammation, imaging of structural lesions, pain chronicity, pain pattern, pain location, stiffness, and genetics. The most heavily weighted domains were active inflammation and structural lesions on imaging. Imaging typical of sacroiliitis was deemed necessary, but not sufficient, to classify a youth with AxJSpA. The threshold for classification of AxJSpA was a score of ≥55 (out of 100). When tested in the validation data set, the final criteria had a specificity of 97.5% (95% confidence interval [CI] 91.4%-99.7%), sensitivity of 64.3% (95% CI 54.9%-73.1%), and area under the receiver operating characteristic curve of 0.81 (95% CI 0.76%-0.86%). The new AxJSpA classification criteria require an entry criterion and a physician diagnosis of juvenile SpA and include seven weighted domains. The AxJSpA classification criteria are validated and designed to identify participants for research studies.

Interobserver agreement on line-field confocal optical coherence tomography image markers in keratinocyte carcinomas and precursor lesions

Line-field confocal optical coherence tomography (LC-OCT) is a new technology for skin cancer diagnostics. However, the interobserver agreement (IOA) of known image markers of keratinocyte carcinomas (KC), including basal cell carcinoma (BCC) and squamous cell carcinoma (SCC), as well as precursors, SCC in situ (CIS) and actinic keratosis (AK), remains unexplored. This study determined IOA on the presence or absence of 10 key LC-OCT image markers of KC and precursors, among evaluators new to LC-OCT with different levels of dermatologic imaging experience. Secondly, the frequency and association between reported image markers and lesion types, was determined. Six evaluators blinded to histopathologic diagnoses, assessed 75 LC-OCT images of KC (21 SCC; 21 BCC), CIS (12), and AK (21). For each image, evaluators independently reported the presence or absence of 10 predefined key image markers of KCs and precursors described in an LC-OCT literature review. Evaluators were stratified by experience-level as experienced (3) or novices (3) based on previous OCT and reflectance confocal microscopy usage. IOA was tested for all groups, using Conger’s kappa coefficient (κ). The frequency of reported image marker and their association with lesion-types, were calculated as proportions and odds ratios (OR), respectively. Overall IOA was highest for the image markers lobules (κ = 0.68, 95% confidence interval (CI) 0.57;0.78) and clefting (κ = 0.63, CI 0.52;0.74), typically seen in BCC (94%;OR 143.2 and 158.7, respectively, p < 0.001), followed by severe dysplasia (κ = 0.42, CI 0.31;0.53), observed primarily in CIS (79%;OR 7.1, p < 0.001). The remaining seven image-markers had lower IOA (κ = 0.06–0.32) and were more evenly observed across lesion types. The lowest IOA was noted for a well-defined (κ = 0.07, CI 0;0.15) and interrupted dermal-epidermal junction (DEJ) (κ = 0.06, CI -0.002;0.13). IOA was higher for all image markers among experienced evaluators versus novices. This study shows varying IOA for 10 key image markers of KC and precursors in LC-OCT images among evaluators new to the technology. IOA was highest for the assessments of lobules, clefting, and severe dysplasia while lowest for the assessment of the DEJ integrity.

Evaluation of the prostate cancer and its metastases in the [ 68 Ga]Ga-PSMA PET/CT images: deep learning method vs. conventional PET/CT processing.

This study demonstrates the feasibility and benefits of using a deep learning-based approach for attenuation correction in [ 68 Ga]Ga-PSMA PET scans. A dataset of 700 prostate cancer patients (mean age: 67.6 ± 5.9 years, range: 45-85 years) who underwent [ 68 Ga]Ga-PSMA PET/computed tomography was collected. A deep learning model was trained to perform attenuation correction on these images. Quantitative accuracy was assessed using clinical data from 92 patients, comparing the deep learning-based attenuation correction (DLAC) to computed tomography-based PET attenuation correction (PET-CTAC) using mean error, mean absolute error, and root mean square error based on standard uptake value. Clinical evaluation was conducted by three specialists who performed a blinded assessment of lesion detectability and overall image quality in a subset of 50 subjects, comparing DLAC and PET-CTAC images. The DLAC model yielded mean error, mean absolute error, and root mean square error values of -0.007 ± 0.032, 0.08 ± 0.033, and 0.252 ± 125 standard uptake value, respectively. Regarding lesion detection and image quality, DLAC showed superior performance in 16 of the 50 cases, while in 56% of the cases, the images generated by DLAC and PET-CTAC were found to have closely comparable quality and lesion detectability. This study highlights significant improvements in image quality and lesion detection capabilities through the integration of DLAC in [ 68 Ga]Ga-PSMA PET imaging. This innovative approach not only addresses challenges such as bladder radioactivity but also represents a promising method to minimize patient radiation exposure by integrating low-dose computed tomography and DLAC, ultimately improving diagnostic accuracy and patient outcomes.

Efficient and real-time skin lesion image segmentation using spatial-frequency information and channel convolutional networks

Efficient and real-time skin lesion image segmentation using spatial-frequency information and channel convolutional networks

Deep learning approach for skin melanoma and benign classification using empirical wavelet decomposition.

Melanoma is a malignant skin cancer that causes high mortality. Early detection of melanoma can save patients' lives. The features of the skin lesion images can be extracted using computer techniques to differentiate early between melanoma and benign skin lesions. A new model of empirical wavelet decomposition (EWD) based on tan hyperbolic modulated filter banks (THMFBs) (EWD-THMFBs) was used to obtain the features of skin lesion images by MATLAB software. The EWD-THMFBs model was compared with the empirical short-time Fourier decomposition method based on THMFBs (ESTFD-THMFBs) and the empirical Fourier decomposition method based on THMFBs (EFD-THMFBs). The accuracy rates obtained for EWD-THMFBs, ESTFD-THMFBs, and EFD-THMFBs models were 100%, 98.89%, and 83.33%, respectively. The area under the curve (AUC) was 1, 0.97, and 0.91, respectively. The EWD-THMFBs model performed best in extracting features from skin lesion images. This model can be programmed on a mobile to detect skin lesions in rural areas by a nurse before consulting a dermatologist.

Fractional differentiation based image enhancement for automatic detection of malignant melanoma

Recent improvements in artificial intelligence and computer vision make it possible to automatically detect abnormalities in medical images. Skin lesions are one broad class of them. There are types of lesions that cause skin cancer, again with several types. Melanoma is one of the deadliest types of skin cancer. Its early diagnosis is at utmost importance. The treatments are greatly aided with artificial intelligence by the quick and precise diagnosis of these conditions. The identification and delineation of boundaries inside skin lesions have shown promise when using the basic image processing approaches for edge detection. Further enhancements regarding edge detections are possible. In this paper, the use of fractional differentiation for improved edge detection is explored on the application of skin lesion detection. A framework based on fractional differential filters for edge detection in skin lesion images is proposed that can improve automatic detection rate of malignant melanoma. The derived images are used to enhance the input images. Obtained images then undergo a classification process based on deep learning. A well-studied dataset of HAM10000 is used in the experiments. The system achieves 81.04% accuracy with EfficientNet model using the proposed fractional derivative based enhancements whereas accuracies are around 77.94% when using original images. In almost all the experiments, the enhanced images improved the accuracy. The results show that the proposed method improves the recognition performance.

Integrating Multi‐Scale Feature Boundary Module and Feature Fusion With CNN for Accurate Skin Cancer Segmentation and Classification

ABSTRACTThe skin, a crucial organ, plays a protective role in the human body, emphasizing the significance of early detection of skin diseases to prevent potential progression to skin cancer. The challenge lies in diagnosing these diseases at their early stages, where visual resemblance complicates differentiation, highlighting the need for an innovative automated method for precisely identifying skin lesions in biomedical images. This paper introduces a holistic methodology that combines DenseNet, multi‐scale feature boundary module (MFBM), and feature fusion and decoding engine (FFDE) to tackle challenges in existing deep‐learning image segmentation methods. Furthermore, a convolutional neural network model is designed for the classification of segmented images. The DenseNet encoder efficiently extracts features at four resolution levels, leveraging dense connectivity to capture intricate hierarchical features. The proposed MFBM plays a crucial role in extracting boundary information, employing parallel dilated convolutions with various dilation rates for effective multi‐scale information capture. To overcome potential disadvantages related to the conversion of features during segmentation, our approach ensures the preservation of context features. The proposed FFDE method adaptively fuses features from different levels, restoring skin lesion location information while preserving local details. The evaluation of the model is conducted on the HAM10000 dataset, which consists of 10 015 dermoscopy images, yielding promising results.