Identification Of Lesions Research Articles

HHEPATO-Cy5, a Bimodal Tracer for Image-Guided Hepatobiliary Surgery.

Liver cancer is a leading cause of cancer deaths worldwide. Surgical resection of superficial hepatic lesions is increasingly guided by the disrupted bile excretion of the fluorescent dye indocyanine green (ICG). To extend this approach to deeper lesions, a dedicated bimodal tracer that facilitates both fluorescence guidance and radioguidance was developed. Methods: A tracer comprising a methylated cyanine-5 (Cy5) fluorescent dye and a mercaptoacetyltriserine chelate (hHEPATO-Cy5) was synthesized and characterized. Cellular uptake and excretion were evaluated in hepatocyte cultures (2-dimensional culture and invitro lesion model), using a fluorescent bile salt, MitoTracker dye, and methylated Cy5 as a control. After radiolabeling, the pharmacokinetics of 99mTc-hHEPATO-Cy5 were assessed in mice over 24 h (percentage injected dose and percentage injected dose per gram of tissue, SPECT/CT imaging and fluorescence imaging). The ability to provide real-time fluorescence guidance during robot-assisted hepatobiliary surgery was evaluated in a porcine model using ICG as a reference. Results: The unique molecular signature of hHEPATO-Cy5 promotes hepatobiliary excretion. In vitro studies on hepatocytes showed that where methylated Cy5 remained internalized, hHEPATO-Cy5 showed fast clearance (10 min) similar to that of fluorescent bile salt. In vivo use of 99mTc-hHEPATO-Cy5 in mice revealed liver accumulation and rapid biliary clearance. The effectiveness of bile clearance was best exemplified by the 2-orders-of-magnitude reduction in count rate for the gallbladder (P = 0.008) over time. During hepatobiliary surgery in a porcine model, hHEPATO-Cy5 enabled fluorescence-based lesion identification comparable to that of ICG. Conclusion: The bimodal 99mTc-hHEPATO-Cy5 provides an effective means to identify liver lesions. Uniquely, it helps overcome the shortcomings of fluorescence-only approaches by allowing for an extension to in-depth radioguidance.

Odontogenic Maxillary Sinusitis: A clinical case report

underdiagnosed due to its nonspecific clinical presentation, which overlaps with other types of rhinosinusitis. The etiopathogenesis involves a complex interplay of factors including iatrogenic causes, periodontal infections, and traumatic events, leading to a persistent inflammatory response in the maxillary sinus. This report details a clinical case involving a 19-year-old male patient presenting with exacerbated sinusitis symptoms linked to a carious upper right first molar. Clinical manifestations included blurred vision, facial pain, and nasal regurgitation of liquids. Radiographic analysis revealed a radiolucent area indicative of sinus involvement, confirming the diagnosis of OMS.Surgical intervention comprised the extraction of the infected molar and the debridement of the maxillary sinus, followed by the application of Bichat’s fat pad to repair the resulting oroantral communication. This technique demonstrated effective closure of the defect, promoting tissue healing and reducing postoperative complications. The postoperative regimen included antibiotics, anti-inflammatories, and antihistamines, which facilitated recovery. This case underscores the necessity of a multidisciplinary approach in the diagnosis and management of OMS, integrating dental and surgical expertise to optimize patient outcomes. Imaging plays a crucial role in the diagnostic process, enabling precise identification of odontogenic lesions and their extent. The successful use of Bichat’s fat pad highlights its utility in oral-maxillofacial surgery for managing oroantral fistulas. This report contributes to the growing body of evidence supporting the importance of tailored surgical and medical strategies in managing complex cases of odontogenic maxillary sinusitis.

Robotics In Gynecology- A Review

This review article focuses on the development of robotics-based operations in the medical field especially in gynecology. The goal of the surgical robot is to improve surgical skills and compensate for human limitations. The robot's performance in performing duties correctly and consistently has been the key to its success. Tubal anastomosis was the first gynecologic surgery performed with Robotic assistance in 2000 followed by first Robotic Hysterectomy in 2002. In 2003 Da Vinci surgical system was developed which was FDA approved for gynecological surgery in 2005. It has gained popularity fast and is already playing a big part in many of the places where it is available. It consists of a high-resolution three-dimensional (3D) vision system adjacent to the patient on a cart with robotic branches. It provides unique technical advancement, with tremor filtration, improved ergonomics and lower muscular load as compared to both laparoscopic and open surgeries. Autonomous camera and energy instrument control, wrist articulation with 7 degree freedom, telestration and dual- console capabilities, overcoming the limitations of conventional laparoscopy, such as counterintuitive hand movements, 2 dimensional visualization, limited degree of motion and tremor amplification. Compared to laparoscopy, robotic assistance has a lower conversion rate to open procedures. Endo wrist movement of an automated machine during myomectomy surgery can perform proper and better suturing than traditional laparoscopy. The automated program is a noticeable improvement over laparoscopic surgery and, if price issues are resolved, can gain popularity among gynecological surgeons around the globe. Not unique to robotic system, the integration of indigo cyanine green fluorescence with the Da Vinci robotic system allows identification of lesions, and assessment of perfusion of bowel and ureter during deep infiltrating endometriosis resection.

Deep learning-assisted multispectral imaging for early screening of skin diseases

IntroductionMelanocytic nevi (MN), warts, seborrheic keratoses (SK), and psoriasis are four common types of skin surface lesions that typically require dermatoscopic examination for definitive diagnosis in clinical dermatology settings. This process is labor-intensive and resource-consuming. Traditional methods for diagnosing skin lesions rely heavily on the subjective judgment of dermatologists, leading to issues in diagnostic accuracy and prolonged detection times. ObjectivesThis study aims to introduce a multispectral imaging (MSI)-based method for the early screening and detection of skin surface lesions. By capturing image data at multiple wavelengths, MSI can detect subtle spectral variations in tissues, significantly enhancing the differentiation of various skin conditions. MethodsThe proposed method utilizes a pixel-level mosaic imaging spectrometer to capture multispectral images of lesions, followed by reflectance calibration and standardization. Regions of interest were manually extracted, and the spectral data were subsequently exported for analysis. An improved one-dimensional convolutional neural network is then employed to train and classify the data. ResultsThe new method achieves an accuracy of 96.82 % on the test set, demonstrating its efficacy. ConclusionThis multispectral imaging approach provides a non-contact and non-invasive method for early screening, effectively addressing the subjective identification of lesions by dermatologists and the prolonged detection times associated with conventional methods. It offers enhanced diagnostic accuracy for a variety of skin lesions, suggesting new avenues for dermatological diagnostics.

New developments in the application of artificial intelligence to laryngology.

The purpose of this review is to summarize the existing literature on artificial intelligence technology utilization in laryngology, highlighting recent advances and current barriers to implementation. The volume of publications studying applications of artificial intelligence in laryngology has rapidly increased, demonstrating a strong interest in utilizing this technology. Vocal biomarkers for disease screening, deep learning analysis of videolaryngoscopy for lesion identification, and auto-segmentation of videofluoroscopy for detection of aspiration are a few of the new ways in which artificial intelligence is poised to transform clinical care in laryngology. Increasing collaboration is ongoing to establish guidelines and standards for the field to ensure generalizability. Artificial intelligence tools have the potential to greatly advance laryngology care by creating novel screening methods, improving how data-heavy diagnostics of laryngology are analyzed, and standardizing outcome measures. However, physician and patient trust in artificial intelligence must improve for the technology to be successfully implemented. Additionally, most existing studies lack large and diverse datasets, external validation, and consistent ground-truth references necessary to produce generalizable results. Collaborative, large-scale studies will fuel technological innovation and bring artificial intelligence to the forefront of patient care in laryngology.

Association between anesthesia assistance and precancerous lesions and early cancer detection during diagnostic esophagogastroduodenoscopy: a propensity score-matched retrospective study.

Esophagogastroduodenoscopy (EGD) is a fundamental procedure for early detection of upper gastrointestinal (UGI) cancer. However, limited research has been conducted on the impact of sedation during EGD on the identification of precancerous lesions and early cancer (EC). This retrospective study aims to evaluate whether sedation during EGD can improve the detection rates of precancerous lesions and EC. In this propensity score-matched retrospective study, we examined medical records from outpatients who underwent diagnostic EGD at a large tertiary center between January 2023 and December 2023. Data on endoscopic findings and histology biopsies were obtained from an endoscopy quality-control system. The primary objective was to compare the rates of detecting precancerous lesions and EC in patients who received sedation during EGD vs. those who did not receive sedation. Additionally, we aimed to identify factors influencing these detection rates using binary logistic regression analysis. Following propensity score matching, a total of 17,862 patients who underwent diagnostic EGD with or without propofol sedation were identified. The group that received sedation exhibited a higher detection rate of precancerous lesions and EC in comparison to the non-sedated group (1.04 vs. 0.75%; p = 0.039). Additionally, within the sedated group, there was an increased likelihood of identifying precancerous lesions and EC specifically at the gastric antrum (0.60 vs. 0.32%, p = 0.006). Binary logistic regression analysis demonstrated that independent risk factors influencing the detection rates included age, gender, observation time, and number of biopsies conducted during the procedure. Anesthesia assistance during EGD screening proved advantageous in detecting EC as well as precancerous lesions. It is crucial for endoscopists to consider these factors when performing EGD screening procedures.

Ectopic Cushing's Syndrome in Pediatric Age

Cushing's syndrome due to ectopic ACTH secretion is a rare clinical condition resulting from a dysregulated ACTH secretion by neuroendocrine tumors. The overall incidence of endogenous Cushing's syndrome is 0.7-2.4 per million people annually, with children accounting for only 10% of new cases each year. When the patient first presented clinically, she was a 17-year-old girl who displayed psychiatric symptoms. Blood tests showed diabetes mellitus and hypokalemia. She had hypertension and vertebral collapses. The hormone assay showed hypercortisolism, and because of this, she began taking metyrapone. The results of the 68Ga-PET/DOTATOC and 18FDG-PET scans were negative. The clinical course was intermittent. After one year, a 68Ga-PET/DOTATOC showed a nodule in the thymic lodge. Despite the thymectomy, the hypercortisolism persisted. A subsequent 68Ga-PET/DOTATOC repeated three months after surgery revealed an uptake corresponding to the thymic lodge. She underwent another surgery, which is finally being resolved. ACTH levels were monitored before, during, and post-surgery. The laboratory provided the ACTH results promptly, and thoracic surgeons waited for hormonal results before concluding the procedure. The adopted strategy permitted us to monitor the surgery outcome. The heterogeneity of ectopic Cushing's syndrome makes diagnosis difficult. 68Ga-PET/DOTATOC proves to be a tracer with good sensitivity and specificity for the identification of ACTH-secreting neuroendocrine lesions. The short half-life of ACTH is found to be a strategy to monitor the complete surgical resection of the neuroendocrine lesion.

Identification of adrenal lesions

Identification of adrenal lesions

Skin Lesion Prediction and Classification Using Innovative Modified Long Short-Term Memory-Based Hybrid Optimization Algorithm

Identification of pigmented skin lesions is necessary for the detection of severe diseases associated with the skin organ, notably malignancy. Accurate skin cancer diagnosis can be improved with the use of image detection approaches and computer classification skills. Therefore, this research work plans to perform skin lesion prediction and classification using a novel deep learning methodology. Initially, the data related to the skin lesion are gathered from the ISIC dataset. After collecting the images, the pre-processing is performed using hair removal and filtering hair removed images via median filtering. These pre-processed images undergo segmentation process accomplished using the U-Net method. Next, the features are extracted from these segmented images with the help of color features, and texture features by GLCM and RGB histogram features. These extracted features undergo the prediction phase that is accomplished using the MLSTM model, in which the parameter optimization is done by the nature inspired novel hybrid metaheuristic algorithm referred as SC-STBO algorithm with the consideration of accuracy maximization and RMSE minimization as the major fitness for the objective function. If the predicted output is returned as the presence of skin lesion, the same novel MLSTM model classifies the final skin lesion output into seven types, such as Vascular Lesions, Melanocytic Nevi, Melanoma, Dermatofibroma, Benign Keratosis-like Lesions, BCC, and Actinic Keratoses, respectively. Seven groups of skin diseases can be identified early thanks to the suggested effort, which can then be tested and properly handled by medical professionals. With an accuracy of 0.9931, the recommended methodology clearly outperforms traditional techniques. Similarly, the suggested methodology clearly beats the conventional methods, with a recall of 0.9825.

Evaluating the efficacy of few-shot learning for GPT-4Vision in neurodegenerative disease histopathology: A comparative analysis with convolutional neural network model.

Recent advances in artificial intelligence, particularly with large language models like GPT-4Vision (GPT-4V)-a derivative feature of ChatGPT-have expanded the potential for medical image interpretation. This study evaluates the accuracy of GPT-4V in image classification tasks of histopathological images and compares its performance with a traditional convolutional neural network (CNN). We utilised 1520 images, including haematoxylin and eosin staining and tau immunohistochemistry, from patients with various neurodegenerative diseases, such as Alzheimer's disease (AD), progressive supranuclear palsy (PSP) and corticobasal degeneration (CBD). We assessed GPT-4V's performance using multi-step prompts to determine how textual context influences image interpretation. We also employed few-shot learning to enhance improvements in GPT-4V's diagnostic performance in classifying three specific tau lesions-astrocytic plaques, neuritic plaques and tufted astrocytes-and compared the outcomes with the CNN model YOLOv8. GPT-4V accurately recognised staining techniques and tissue origin but struggled with specific lesion identification. The interpretation of images was notably influenced by the provided textual context, which sometimes led to diagnostic inaccuracies. For instance, when presented with images of the motor cortex, the diagnosis shifted inappropriately from AD to CBD or PSP. However, few-shot learning markedly improved GPT-4V's diagnostic capabilities, enhancing accuracy from 40% in zero-shot learning to 90% with 20-shot learning, matching the performance of YOLOv8, which required 100-shot learning to achieve the same accuracy. Although GPT-4V faces challenges in independently interpreting histopathological images, few-shot learning significantly improves its performance. This approach is especially promising for neuropathology, where acquiring extensive labelled datasets is often challenging.

Application of Tswin-F network based on multi-scale feature fusion in tomato leaf lesion recognition

Tomato leaf lesion identification can greatly help the detection and analysis of plant lesions. This study proposes Tswin-F network, a new network structure based on Transformer, to detect tomato leaf diseases. This Tswin-F network would obtain position information on images by implementing the bilateral local attention module and the self-supervised learning module. Specifically, the bilateral local attention mechanism focuses on the connection with certain continuous tokens, while the self-supervised learning module pays attention to the connection with random token positions. Then the information learned from the above two modules approaches will be combined to create the spatial connection between the final tokens. The combination of the above two modules can enhance the ability to communicate information between the windows of the input images and improve the accuracy of the models. In addition, a Feature Fuse Local Attention (FFLCA) structure is designed to solve the problem that attention distances would increase with the number of layers in the transformer network model. Furthermore, all the feature information is fused through the adaptive fusion strategy and is inputted into the classification network as the final global information of the model. Finally, an accuracy of 99.64% is obtained on 10 types of datasets, reaching the state-of-the-art level of CNN-based methods in terms of accuracy. The accuracy rate of identifying 13 types of tomato leaf lesions reaches 90.81% on average. Code is available at: https://github.com/fightpotato.

Brain Abscesses in Domestic Ruminants: Clinicopathological and Bacteriological Approaches.

Brain abscesses in ruminants often arise from primary infection foci, leading to an unfavorable prognosis for affected animals. This highlights the need for comprehensive studies on brain abscesses across different ruminant species. We retrospectively investigated medical records of epidemiological, clinical, neuroimaging, anatomopathological, and bacteriological findings in six ruminants (three goats, two cows, and one sheep) diagnosed with brain abscesses. All animals studied were female. Apathy (50%), compulsive walking (33%), decreased facial sensitivity (33%), head pressing (33%), seizures (33%), semicomatous mental status (33%), strabismus (33%), unilateral blindness (33%), and circling (33%) represented the most common neurologic signs. Leukocytosis and neutrophilia were the main findings in the hematological evaluation. Cerebrospinal fluid (CSF) analysis revealed predominant hyperproteinorrachia and pleocytosis. In three cases, computed tomography or magnetic resonance imaging were used, enabling the identification of typical abscess lesions, which were subsequently confirmed during postmortem examination. Microbiological culture of the abscess samples and/or CSF revealed bacterial coinfections in most cases. Advanced imaging examinations, combined with CSF analysis, can aid in diagnosis, although confirmation typically relies on postmortem evaluation and isolation of the causative agent. This study contributes to clinicopathological aspects, neuroimages, and bacteriological diagnosis of brain abscesses in domestic ruminants.

Recurrence of primary sclerosing cholangitis in the graft

Primary sclerosing cholangitis (PSC) is a disease characterized by inflammation, fibrosis and obliteration of both intra- and extrahepatic bile ducts, accompanied by cholestasis, with further outcome in biliary cirrhosis of the liver, cholangiocarcinoma. The pathogenesis of the disease is poorly understood, but, according to various sources, it involves genetic factors, innate and adaptive immunity mechanisms, the toxic effects of hydrophobic bile acids and, possibly, intestinal dysbiosis. The strong association with inflammatory bowel disease is associated with a significantly increased risk of colorectal cancer, which, along with cholangiocarcinoma, represents the most significant diagnostic challenge in the long-term management of PSC. The diagnosis of PSC is established based on the identification of typical cholangiographic lesions of the bile ducts and the exclusion of secondary causes of sclerosing cholangitis. Complex pathophysiology, heterogeneity of clinical features and the rare nature of the disease have led to the lack of effective therapy to date; there are no treatment algorithms, but a course of ursodeoxycholic acid in doses of 17–23 mg/kg/day can be prescribed for up to a year in order to monitor the dynamics of the decrease in levels serum alkaline phosphatase. A number of drugs are under investigation, including FXR (farnesoid X receptor) agonists with choleretic and antimicrobial properties. Clinically significant stenoses can be successfully treated with interventional endoscopy, but liver transplantation (LT) is currently the only curative treatment with a high survival rate. According to various literature data, 20–25% of patients develop disease relapse in the graft. Our case report of recurrent PSC in a patient 5 years after orthotopic LT provides an overview of management options from a practical, patient-centered perspective.

Using computational learning for non-melanoma skin cancer and actinic keratosis near-infrared hyperspectral signature classification

BackgroundThe early detection of Non-Melanoma Skin Cancer (NMSC) is essential to ensure patients receive the most effective treatment. Diagnostic screening tools for NMSC are crucial due to high confusion rates with other types of skin lesions, such as Actinic Keratosis. Nevertheless, current means of diagnosing and screening patients rely on either visual criteria, that are often conditioned by subjectivity and experience, or highly invasive, slow, and costly methods, such as histological diagnoses. From this, the objectives of the present study are to test if classification accuracies improve in the Near-Infrared region of the electromagnetic spectrum, as opposed to previous research in shorter wavelengths. MethodsThis study utilizes near-infrared hyperspectral imaging, within the range of 900.6 and 1454.8 nm. Images were captured for a total of 125 patients, including 66 patients with Basal Cell Carcinoma, 42 with cutaneous Squamous Cell Carcinoma, and 17 with Actinic Keratosis, to differentiate between healthy and unhealthy skin lesions. A combination of hybrid convolutional neural networks (for feature extraction) and support vector machine algorithms (as a final activation layer) was employed for analysis. In addition, we test whether transfer learning is feasible from networks trained on shorter wavelengths of the electromagnetic spectrum. ResultsThe implemented method achieved a general accuracy of over 80 %, with some tasks reaching over 90 %. F1 scores were also found to generally be over the optimal threshold of 0.8. The best results were obtained when detecting Actinic Keratosis, however differentiation between the two types of malignant lesions was often noted to be more difficult. These results demonstrate the potential of near-infrared hyperspectral imaging combined with advanced machine learning techniques in distinguishing NMSC from other skin lesions. Transfer learning was unsuccessful in improving the training of these algorithms. ConclusionsWe have shown that the Near-Infrared region of the electromagnetic spectrum is highly useful for the identification and study of non-melanoma type skin lesions. While the results are promising, further research is required to develop more robust algorithms that can minimize the impact of noise in these datasets before clinical application is feasible.

Oral Oncology: Two elective courses for advanced undergraduates - An Argentine teaching experience

The COVID-19 pandemic prompted significant adaptations in educational practices at Universidad Nacional de Córdoba, including the integration of e-learning and virtual education modalities. In response to an observed increase in advanced-stage oral cancer cases post-2020, we developed new educational strategies aimed at OC prevention and awareness. This study presents our experience with an innovative undergraduate program focusing on Oral Oncology and Oral Potentially Malignant Disorders. Two elective courses were integrated into the curriculum, featuring contributions from Oral Medicine and Pathology experts across several Latin American countries via virtual platforms. Each course provided comprehensive training, including clinical practice and telemedicine protocols for early lesion identification. A total of 107 students successfully completed the courses, highlighting the program's effectiveness in enhancing student engagement and competence in OC prevention. Recommendations from this initiative include reinforcing undergraduate curricula with OC-focused education and promoting international collaboration in higher education for comprehensive training. Future research should assess the long-term impact of such programs on early OC diagnosis and patient referral practices.

Pixel-level classification of pigmented skin cancer lesions using multispectral autofluorescence lifetime dermoscopy imaging.

There is no clinical tool available to primary care physicians or dermatologists that could provide objective identification of suspicious skin cancer lesions. Multispectral autofluorescence lifetime imaging (maFLIM) dermoscopy enables label-free biochemical and metabolic imaging of skin lesions. This study investigated the use of pixel-level maFLIM dermoscopy features for objective discrimination of malignant from visually similar benign pigmented skin lesions. Clinical maFLIM dermoscopy images were acquired from 60 pigmented skin lesions before undergoing a biopsy examination. Random forest and deep neural networks classification models were explored, as they do not require explicit feature selection. Feature pools with either spectral intensity or bi-exponential maFLIM features, and a combined feature pool, were independently evaluated with each classification model. A rigorous cross-validation strategy tailored for small-size datasets was adopted to estimate classification performance. Time-resolved bi-exponential autofluorescence features were found to be critical for accurate detection of malignant pigmented skin lesions. The deep neural network model produced the best lesion-level classification, with sensitivity and specificity of 76.84%±12.49% and 78.29%±5.50%, respectively, while the random forest classifier produced sensitivity and specificity of 74.73%±14.66% and 76.83%±9.58%, respectively. Results from this study indicate that machine-learning driven maFLIM dermoscopy has the potential to assist doctors with identifying patients in real need of biopsy examination, thus facilitating early detection while reducing the rate of unnecessary biopsies.

Managing the Intricacies of Coronary Revascularization: A Close Look at the Complete Versus Culprit-Only Approach and its Implications in Elderly Patients.

Coronary heart disease is the leading cause of mortality in the United States, and data indicates that 805,000 Americans will face a new or recurrent myocardial infarction (MI) attack every year. Frailty, a conceptual syndrome categorized by a functional decline that occurs with aging, has been linked to adverse health outcomes in cardiovascular disease and all cardiac-related procedures in general. It is therefore reasonable to deliberate that more conservative medical therapy or medical management should be considered in the frail population when managing acute coronary syndrome. This course of action has, in fact, been documented in clinical practice. However, the recent Functional Assessment in Elderly MI Patients with Multivessel Disease trial, in which all subjects were 75 years of age or above, indicated that the more invasive complete revascularization approach may be favorable over incomplete or culprit-only revascularization in patients with acute MI. In this review, we will discuss coronary heart disease and review guidelines and procedures for culprit lesion identification, including electrocardiogram procedures, coronary angiography, intravascular ultrasound, fractional flow reserve, and instantaneous fractional flow reserve. We then discuss the concept of complete vs culprit-only/incomplete coronary revascularization and staging. Following this, we will delve into recent trials discussing complete vs culprit-only revascularization, emphasizing the insights gleaned from this latest trial within this special frailty cohort which warrants special consideration.

Hyperechogenicity and histopathological features of focal liver lesions.

The identification and accurate diagnosis of focal liver lesions are important in modern medicine, where diagnostic radiology plays an essential role. This review aimed to examine the hyperechogenicity and histopathological features of focal liver lesions. Hyperechogenic liver lesions can be either benign or malignant. Evidence shows that hyperechogenicity is caused by factors such as fat deposition, sinusoidal dilation, peliotic changes, and pseudoglandular patterns. Fat deposition is a common cause of increased echogenicity in hepatocellular carcinoma (HCC). Meanwhile, sinusoidal dilation and peliotic changes are more frequently observed in larger HCC nodules. Pseudoglandular patterns, characterized by the reflection of ultrasound waves at the walls of numerous acini, are associated with hyperechogenicity in well-to-moderately differentiated HCCs. Moreover, this review comprehensively examined the histological features that may cause hyperechogenic internal echoes in not only HCCs but also localized liver lesions (metastases of adenocarcinoma and neuroendocrine neoplasm, intrahepatic cholangiocarcinoma, cavernous hemangioma, focal nodular hyperplasia, and angiomyolipoma). To make an accurate diagnosis and provide appropriate management, it is important to understand the histopathological basis for hyperechogenicity in focal liver lesions. By maximizing the accuracy of imaging studies and enhancing the radiology-pathology correlation, unnecessary biopsies can be avoided, thereby reducing potential complications and mortality. This review can help facilitate the effective management of patients with focal liver lesions, thereby resulting in timely and appropriate treatment decision-making.

Efficient multi-stage feedback attention for diverse lesion in cancer image segmentation

In the domain of Computer-Aided Diagnosis (CAD) systems, the accurate identification of cancer lesions is paramount, given the life-threatening nature of cancer and the complexities inherent in its manifestation. This task is particularly arduous due to the often vague boundaries of cancerous regions, compounded by the presence of noise and the heterogeneity in the appearance of lesions, making precise segmentation a critical yet challenging endeavor. This study introduces an innovative, an iterative feedback mechanism tailored for the nuanced detection of cancer lesions in a variety of medical imaging modalities, offering a refining phase to adjust detection results. The core of our approach is the elimination of the need for an initial segmentation mask, a common limitation in iterative-based segmentation methods. Instead, we utilize a novel system where the feedback for refining segmentation is derived directly from the encoder–decoder architecture of our neural network model. This shift allows for more dynamic and accurate lesion identification. To further enhance the accuracy of our CAD system, we employ a multi-scale feedback attention mechanism to guide and refine predicted mask subsequent iterations. In parallel, we introduce a sophisticated weighted feedback loss function. This function synergistically combines global and iteration-specific loss considerations, thereby refining parameter estimation and improving the overall precision of the segmentation. We conducted comprehensive experiments across three distinct categories of medical imaging: colonoscopy, ultrasonography, and dermoscopic images. The experimental results demonstrate that our method not only competes favorably with but also surpasses current state-of-the-art methods in various scenarios, including both standard and challenging out-of-domain tasks. This evidences the robustness and versatility of our approach in accurately identifying cancer lesions across a spectrum of medical imaging contexts. Our source code can be found at https://github.com/dewamsa/EfficientFeedbackNetwork.

18F-fluorodeoxyglucose positron emission tomography-computed tomography in the localization of the lesions in the osteogenic region of breast cancer bone metastases after therapy.

Accurate efficacy evaluation of bone metastases (BMs) from breast cancer (BC) is an intractable issue in clinical practice, for which solutions are urgently needed. This study aimed to investigate the utility of 18F-fluorodeoxyglucose positron emission tomography-computed tomography (18F-FDG PET/CT) in the response evaluation of bone metastasis of BC. In total, 22 patients diagnosed with BC and BM were enrolled. These patients underwent repeated 18F-FDG PET/CT evaluations. The patients and each BM site were divided into two groups based on their response to treatment: progressive disease (PD) and nonprogressive disease (non-PD). We analyzed and compared the changes in PET and CT images, as well as the serum concentration of carcinoembryonic antigen (CEA), carbohydrate antigen 153 (CA153), alkaline phosphatase (ALP), and calcium (Ca) over the same time frame. The immunohistochemistry (IHC) of primary lesions between groups and between the primary focus and BM with high 18F-FDG uptake were compared and analyzed. Maximum standard uptake value (SUVmax) after therapy [area under the curve (AUC): 0.932] and Δ-value of SUVmax (AUC: 0.811) on 18F-FDG PET imaging proved significantly valuable for the efficacy of therapy outcomes related to BM lesions (P<0.05). In terms of overall evaluation of BM, age and human epidermal growth factor receptor 2 (HER2) expression were significantly lower in the PD group than in the non-PD group (P<0.05). There were marked differences in CEA after therapy, the changes of CEA, and CA153 (∆-value) between the groups (P<0.05). The SUVmax and Ca concentration after therapy and ∆-value of SUVmax, along with the levels of CA153, CEA, and ALP, were valuable indicators for evaluating the efficacy of individual BMs (P<0.05). IHC of BM in the PD group showed differences compared to primary lesions, with antigen Ki-67 being downregulated in metastatic lesions and HER2 being downregulated in a portion of BMs (2 of 6). Meanwhile, the expression of estrogen receptor (ER) and progesterone receptor (PR) remained relatively unchanged. 18F-FDG PET/CT confers precise assessment of the posttreatment efficacy pertaining to BM in BC. This modality facilitates the identification of poor effect lesions following extant therapies and localization for pathological assessment and may substantially contribute to evaluating therapeutic efficacy, refining treatment strategies, and predicting the disease trajectory of patients with BC and BM.