Malignant Masses Research Articles

Imaging phenotype evaluation from digital breast tomosynthesis data: A preliminary study

Background:Digital breast tomosynthesis (DBT) has been widely adopted as a supplemental imaging modality for diagnostic evaluation of breast cancer and confirmation studies. In this study, a deep learning-based method for characterizing breast tissue patterns in DBT data is presented. Methods:A set of 5388 2D image patches was produced from 230 right mediolateral oblique, 259 left mediolateral oblique, 18 right craniocaudal, and 15 left craniocaudal single-breast DBT studies, using slice-wise annotations of abnormalities and normal tissue. We implemented a patch classifier to predict samples according to two differing scenarios and train it using the patch dataset. First, tissue samples were classified into the following classes: malignant, benign, and normal breast tissue. Second, tissue samples were classified into the following classes: malignant mass, benign mass, benign architectural distortion, malignant architectural distortion, and normal breast tissue. We employed transfer learning and initialized the model base layers with existing pre-trained weights obtained from Globally-Aware Multiple Instance Classifier. Results:High class-wise recall values of 0.8906, 0.8541 and 0.7345 and specificities 0.9558, 0.9575 and 0.8830 were obtained for normal, benign, and malignant classification, respectively. More intricate classification yielded class-wise recall values of 0.8708, 0.8299, 0.9444 and 0.5723 and specificities 0.9406, 0.9833, 0.8943 and 0.9652 for benign mass, normal, malignant architectural distortion, and malignant mass, respectively. However, benign architectural distortion was confused with benign mass and malignant architectural distortion. Conclusions:Combining the proposed phenotype classifier with the commonly used malignant-benign-normal classification enables a more detailed assessment of digital breast tomosynthesis images.

An optimized siamese neural network with deep linear graph attention model for gynaecological abdominal pelvic masses classification.

An adnexal mass, also known as a pelvic mass, is a growth that develops in or near the uterus, ovaries, fallopian tubes, and supporting tissues. For women suspected of having ovarian cancer, timely and accurate detection of a malignant pelvic mass is crucial for effective triage, referral, and follow-up therapy. While various deep learning techniques have been proposed for identifying pelvic masses, current methods are often not accurate enough and can be computationally intensive. To address these issues, this manuscript introduces an optimized Siamese circle-inspired neural network with deep linear graph attention (SCINN-DLGN) model designed for pelvic mass classification. The SCINN-DLGN model is intended to classify pelvic masses into three categories: benign, malignant, and healthy. Initially, real-time MRI pelvic mass images undergo pre-processing using semantic-aware structure-preserving median morpho-filtering to enhance image quality. Following this, the region of interest (ROI) within the pelvic mass images is segmented using an EfficientNet-based U-Net framework, which reduces noise and improves the accuracy of segmentation. The segmented images are then analysed using the SCINN-DLGN model, which extracts geometric features from the ROI. These features are classified into benign, malignant, or healthy categories using a deep clustering algorithm integrated into the linear graph attention model. The proposed system is implemented on a Python platform, and its performance is evaluated using real-time MRI pelvic mass datasets. The SCINN-DLGN model achieves an impressive 99.9% accuracy and 99.8% recall, demonstrating superior efficiency compared to existing methods and highlighting its potential for further advancement in the field.

Improved diagnostic confidence using Super Resolution CEUS imaging in testicular lesions.

Ultrasound is the most used interdisciplinary non-ionizing imaging technique in clinical pathologies of the testis. The testis may be affected by a plethora of different disorders such as vasculopathies, trauma, infections and manifestations of primary and secondary malignant masses. Conventional ultrasound represents the basic imaging modality of choice to assess scrotal disorders. Contrast-enhanced ultrasound (CEUS) can provide further information to distinguish between benign and malignant testicular mass lesions. The recent introduction of Super Resolution CEUS Micro-Vascular Imaging (MVI SR) and Time of Arrival (TOA SR) parametric mapping compliments the information provided by conventional CEUS, since these two new post-processing techniques improve the visualization of microvascular structures with slow blood flow and provide high-resolution images of the peak contrast enhancement and temporal perfusion patterns. This paper gives a comprehensive overview of differential diagnoses of the testicular disorder and their corresponding sono-morphologic correlates based on representative cases of the Interdisciplinary Ultrasound Center of the University Hospital Munich.

The incremental value of Histogram Analysis in the differentiation between hyperdense cysts and solid renal masses on unenhanced CT images.

To investigate the utility of voxel histogram analysis (HA) for differentiating hyperdense renal cysts from small solid masses on unenhanced computed tomography (CT) scans. A retrospective analysis of 99 hyperdense cystic lesions and 28 solid malignant lesions was conducted using a radiological database (from 2015 to 2021) and a pathological database (from 2010 to 2020). The study investigated the distribution of voxel attenuation values using percentiles to establish reliable criteria for differentiation after drawing a region of interest (ROI) in the centre of the lesions. The standard of reference was a histopathological diagnosis for malignant masses and contrast-enhanced CT or magnetic resonance imaging (MRI) for cysts. HA provided higher diagnostic accuracy than the conventional mean attenuation value of 70 Hounsfield Units (HU). For the 75th and 90th percentiles ± 1 standard deviation, accuracies of 77.2% (95% confidence interval 68.9-84.2%) for the 75th and 68.5% (59.7-76.4%) for the 90th were found, versus 37.0% (28.6-46.0%) for the 70 HU threshold criterion. A Gaussian distribution of voxel attenuation values was observed in 88.9% of the lesions, suggesting that it is feasible to calculate these parameters from a single measurement. The study underscores the potential of HA as a valuable tool for characterizing hyperdense cysts on unenhanced CT by using the same ROI for measuring lesion attenuation. HA could offer additional value beyond the 70 HU criterion and possibly influence clinical decisions. Multi-institutional studies are necessary for external validation to confirm its generalizability and more extensive applicability.

Percutaneous Aspiration Injection and Re-aspiration as A Minimally Invasive Treatment for Spinal Cystic Echinococcosis: A Case Report.

Cystic echinococcosis is a parasitic disease with significant importance for public health in endemic regions. Spinal cystic echinococcosis, however, is a rare form that may lead to severe complications due to its localization. In this manuscript, we presented a 16-year-old male patient who admitted with abdominal and back edema for 2 months, evaluated with preliminary diagnoses of Pott's abscess and malignant mass, subsequently diagnosed with spinal cystic echinococcosis. It was concluded that cystic echinococcosis should be considered in differential diagnosis of large cystic masses and percutaneous aspiration, injection, reaspiration method might be a safe and effective treatment option particularly for cases of complicated spinal cystic echinococcosis.

8248 Glucocorticoid Induced Adrenal Crisis Masked By Metastatic Lung Carcinoma

Abstract Disclosure: N. Abrahimi: None. A. Abrahimi: None. Background: Chronic glucocorticoid use of three weeks or longer can cause hypothalamic-pituitary-adrenal axis inhibition by negative feedback, causing adrenal suppression. (1) Adrenal crisis is diagnosed by an acute clinical decompensation, persistent hypotension that resolves with high dose steroid administration. (2) Adrenal crisis is precipitated by several causes such as illness, dehydration, trauma, emotional distress and sometimes due to no identifiable cause. (2) Clinical Case: 64-year-old male past medical history of lung carcinoma metastatic to mediastinum who presented to the hospital with tachycardia. On presentation, patient was tachycardic, tachypneic, and hypotensive. Labs significant for WBC 22, Na+ 129, K+ 3.2, Cr 3.4. Patient received 2.5 L bolus of NS and was given one dose of azithromycin due to concern for sepsis. After fluid resuscitation, hypotension and tachycardia resolved. Presenting symptoms included ongoing nausea, decreased appetite and malaise for several weeks. Repeat labs post fluid resuscitation showed resolution of leukocytosis, improvement of AKI, and repletion of electrolytes. CT chest abdomen pelvis showed questionable pneumonia, however, consolidations were difficult to distinguish from known malignant masses. Clinical picture was not consistent with pneumonia and so additional antibiotics were held. Several hours later, blood pressure decreased, and patient began requiring vasopressors. Cefepime was started given concern for septic shock. Nearly 48 hours after initiation of broad-spectrum antibiotics hypotension persisted and patient remained on vasopressors. Given clinical decline, etiology of shock was reconsidered. Patient reported daily prednisone use over the last several months for COPD management. Given high clinical suspicion of adrenal crisis in setting of chronic steroid use and glucocorticoid withdrawal, patient was started on hydrocortisone 100 mg every 8 hours. Shortly after initiation of stress dosed steroids, the patient was successfully weaned off vasopressors with complete resolution of hypotension. Conclusion: Presentation and symptoms of adrenal insufficiency and crisis including nausea, anorexia, fatigue, malaise, hypotension and electrolyte abnormalities are nonspecific, can go unrecognized and be masked by other disease processes, such as metastatic cancer. (1) Adrenal crisis is life threatening and must be diagnosed and treated early to prevent mortality. (2) Therefore, adrenal crisis should always be on the differential in patients who present with shock.

Multiarm, non-randomised, single-centre feasibility study—investigation of the differential biology between benign and malignant renal masses using advanced magnetic resonance imaging techniques (IBM-Renal): protocol

IntroductionLocalised renal masses are an increasing burden on healthcare due to the rising number of cases. However, conventional imaging cannot reliably distinguish between benign and malignant renal masses, and renal...

Using the GoogLeNet deep-learning model to distinguish between benign and malignant breast masses based on conventional ultrasound: a systematic review and meta-analysis.

Breast cancer is one of the most common malignancies in women worldwide, and early and accurate diagnosis is crucial for improving treatment outcomes. Conventional ultrasound (CUS) is a widely used screening method for breast cancer; however, the subjective nature of interpreting the results can lead to diagnostic errors. The current study sought to estimate the effectiveness of using a GoogLeNet deep-learning convolutional neural network (CNN) model to identify benign and malignant breast masses based on CUS. A literature search was conducted of the Embase, PubMed, Web of Science, Wanfang, China National Knowledge Infrastructure (CNKI), and other databases to retrieve studies related to GoogLeNet deep-learning CUS-based models published before July 15, 2023. The diagnostic performance of the GoogLeNet models was evaluated using several metrics, including pooled sensitivity (PSEN), pooled specificity (PSPE), the positive likelihood ratio (PLR), the negative likelihood ratio (NLR), the diagnostic odds ratio (DOR), and the area under the curve (AUC). The quality of the included studies was evaluated using the Quality Assessment of Diagnostic Accuracy Studies Scale (QUADAS). The eligibility of the included literature were independently searched and assessed by two authors. All of the 12 studies that used pathological findings as the gold standard were included in the meta-analysis. The overall average estimation of sensitivity and specificity was 0.85 [95% confidence interval (CI): 0.80-0.89] and 0.86 (95% CI: 0.78-0.92), respectively. The PLR and NLR were 6.2 (95% CI: 3.9-9.9) and 0.17 (95% CI: 0.12-0.23), respectively. The DOR was 37.06 (95% CI: 20.78-66.10). The AUC was 0.92 (95% CI: 0.89-0.94). No obvious publication bias was detected. The GoogLeNet deep-learning model, which uses a CNN, achieved good diagnostic results in distinguishing between benign and malignant breast masses in CUS-based images.

Role of inter- and extra-lesion tissue, transfer learning, and fine-tuning in the robust classification of breast lesions

Accurate and unbiased classification of breast lesions is pivotal for early diagnosis and treatment, and a deep learning approach can effectively represent and utilize the digital content of images for more precise medical image analysis. Breast ultrasound imaging is useful for detecting and distinguishing benign masses from malignant masses. Based on the different ways in which benign and malignant tumors affect neighboring tissues, i.e., the pattern of growth and border irregularities, the penetration degree of the adjacent tissue, and tissue-level changes, we investigated the relationship between breast cancer imaging features and the roles of inter- and extra-lesional tissues and their impact on refining the performance of deep learning classification. The novelty of the proposed approach lies in considering the features extracted from the tissue inside the tumor (by performing an erosion operation) and from the lesion and surrounding tissue (by performing a dilation operation) for classification. This study uses these new features and three pre-trained deep neuronal networks to address the challenge of breast lesion classification in ultrasound images. To improve the classification accuracy and interpretability of the model, the proposed model leverages transfer learning to accelerate the training process. Three modern pre-trained CNN architectures (MobileNetV2, VGG16, and EfficientNetB7) are used for transfer learning and fine-tuning for optimization. There are concerns related to the neuronal networks producing erroneous outputs in the presence of noisy images, variations in input data, or adversarial attacks; thus, the proposed system uses the BUS-BRA database (two classes/benign and malignant) for training and testing and the unseen BUSI database (two classes/benign and malignant) for testing. Extensive experiments have recorded accuracy and AUC as performance parameters. The results indicate that the proposed system outperforms the existing breast cancer detection algorithms reported in the literature. AUC values of 1.00 are calculated for VGG16 and EfficientNet-B7 in the dilation cases. The proposed approach will facilitate this challenging and time-consuming classification task.

S2810 Colonic Deception: Two Cases of Ischemic Colitis Posing as Malignant Masses

S2810 Colonic Deception: Two Cases of Ischemic Colitis Posing as Malignant Masses

S3088 A Case of Atypical Endometriosis Presenting as a Malignant Appearing Colonic Mass

S3088 A Case of Atypical Endometriosis Presenting as a Malignant Appearing Colonic Mass

Trophoblastic disease and choriocarcinoma

Gestational trophoblastic disease (GTD) is a group of diseases associated with pregnancies that demonstrate abnormal development of trophoblastic cells. GTD includes hydatidiform moles (HM) that may continue to further develop into gestational trophoblastic neoplasms (GTN), such as choriocarcinoma (CC). Gestational CC is a malignant mass development that may arise from HM, from other (normal) pregnancies or from other gestational events (such as ectopic pregnancies). The aim of this review is to outline current understating of the genetics and epigenetics of GTD and gestational CC and the link between the two diseases.

18F-FDG PET/CT biomarkers as predictors of long term outcomes and survival rates in patients with high risk malignant pulmonary masses/nodules treated with stereotactic ablative radiotherapy.

Stereotactic ablative body radiotherapy (SABR) is a standard treatment option for patients with malignant pulmonary masses (including primary and metastatic lesions) who are unfit for surgery or who are medically operable but refuse surgery. Flourine-18 flurodeoxyglucose positron emission tomography (18F-FDG PET) volumetric metabolic parameters, i.e., metabolic tumour volume (MTV) and total lesion glycolysis (TLG) play an important role in assessing the biological characteristics of some tumours and its role as potential prognostic factors has also been introduced. The aim of this retrospective study is to assess the value of baseline metabolic volumetric parameters as prognostic imaging biomarkers in patients with pulmonary masses/nodules treated with SABR. 70 patients were included in this retrospective study (39 male and 31 female, age range 47-91years, mean 76years). Standardized uptake value (SUVmax), SUVmean, MTV and TLG for all the patients were calculated on baseline 18F-FDG PET/CT. Patient outcome was divided into 3 categories free of disease, stable disease and disease progression. There was no significant statistical difference in the SUVmax and SUVmean in all the three categories. Mean SUVmax ranges from 7.13 to 8.08 with its highest value in the stable disease and lowest value in the progressive disease categories. Similarly, the average SUVmean was 4.9 in the free of disease category and 4.68 in the progressive disease category. MTV and TLG were low in the free of disease and the highest in progressive disease. MTV increased from 2.25 cm3 in free of disease category to 3.23 cm3 and 7.29 cm3 in stable disease and progressive disease, respectively. TLG has increased from 11.7 in the disease-free survival category to 18.77 and 40.39 in the stable and progressive disease, respectively. Patients with low MTV had longer overall survival (OS) than patients with high MTV (37months versus 27months, p value = 0. 0018). In addition, OS was longer in patients with low TLG (36months versus 24months, p value = 0.016). TLG and MTV are more useful than SUVmax and SUVmean for predicting outcome, OS and progression-free survival (PFS) in patients receiving SABR. The TLG and MTV measurement on 18F-FDG PET imaging may be routinely recommended in baseline 18F-FDG PET/CT prior to SABR.

Diagnostic Value of Contrast-Enhanced Ultrasound in Benign and Malignant Adnexal Masses: A Meta-Analysis.

In the diagnosis of gynecological tumors, determining the benign or malignant nature of adnexal masses is a crucial and complex issue. Contrast-enhanced ultrasound (CEUS) is a relatively novel and increasingly used diagnostic method. Therefore, this study evaluated the diagnostic value of CEUS in differentiating benign and malignant adnexal masses through meta-analysis and systematic review. We systematically searched PubMed, Embase, Web of Science, and the Cochrane Library for studies published up to April 2024 regarding the use of CEUS in diagnosing benign and malignant adnexal masses. STATA 14.0 software was used for data analysis, pooling the sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio (DOR) of eligible studies. After initial screening, 305 studies were identified, 13 of which met the inclusion criteria and were analyzed in this meta-analysis. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and DOR of CEUS for the diagnosis of benign and malignant adnexal masses were 0.92 (95% confidence interval [CI]: 0.88-0.95), 0.88 (95% CI: 0.82-0.93), 8.00 (95% CI: 5.00-12.90), 0.09 (95% CI: 0.06-0.14), and 91.00 (95% CI: 45.00-185.00), respectively. The area under the summary receiver operating characteristic curve (AUC) was 0.95 (95% CI: 0.93-0.97). CEUS is a noninvasive, nonradiative imaging modality with high accuracy and reliability in the diagnosis of benign and malignant adnexal masses. To provide an effective adjunct tool in the clinic, future studies can further explore the specific application value of CEUS and its performance in different populations.

MRI quantitative T1 and T2 mapping of the renal cortex: Assessment of normal values and potential usefulness for renal masses at 3 T

PurposeThe purpose of this monocentric retrospective study consisted in exploring the potential improvement of the assessment of renal masses on MRI by using the T1 (T1m) and T2 (T2m) mapping relaxation times. Materials and MethodsWe recorded the renal cortex values of 125 patients with normal kidneys (reference group) and 75 patients with renal masses on a clinical 3 T MR unit using T1m and T2m sequences.For the quantitative evaluation, measurements were performed by delineating ROIs on T1m and T2m sequences in renal cortex of the reference group and in renal masses.Interobserver agreement for the qualitative analysis of image quality was assessed using quadratic Cohen’s weighted kappa statistics (k).Student’s paired t-test and non-parametric Kruskal-Wallis test were used to compare our datasets in terms of T1m and T2m values. ResultsFor the cohort of reference group, mean renal cortex T1m and T2m values were 1,529 ± 83 ms and 98 ± 7 ms, respectively. No statistically significant differences were found for T1m and T2m in the reference group regardless of age, gender or eGRF categories.For the group with renal masses, mean T1m and T2m values were 1,667 ± 87 ms and 105 ± 8 ms; 1,621 ± 96 ms and 117 ± 6 ms, and 1,530 ± 62 ms and 85 ± 4 ms for renal cell carcinomas, angiomyolipomas, and oncocytomas, respectively. For T1m values, there was no significant difference (p = 0.37) among the three types of renal masses. Among histological subtypes we have found: RCC versus angiomyolipoma (p = 0.25), RCC versus oncocytoma (p = 0.15), and oncocytoma versus angiomyolipoma (p = 0.47).However, we have found a statistically significant difference for the T2m value (p = 0.0005). Among histological subtypes, only T2m values were statistically significant for each combination: RCC versus angiomyolipoma (p = 0.012), RCC versus oncocytoma (p = 0.0002), and oncocytoma versus angiomyolipoma (p = 0.003). ConclusionAs this is the largest normal patient cohort, the T1m and T2m values recorded could be proposed as reference values and can play a role in the differential diagnosis between benign and malignant renal tumoral masses.

Comprehensive Evaluation of Pulmonary Masses Using Multi-detector CT: Correlating Morphological Features With CT-Guided Histopathological Findings for Enhanced Diagnostic Accuracy.

Lung masses pose a significant diagnostic challenge due to their diverse causes, from benign hamartomas to malignant bronchogenic carcinoma. Multi-detector CT (MDCT) is essential in evaluating these masses, offering detailed morphological insights to help differentiate between benign and malignant lesions. However, a definitive diagnosis often requires histopathological confirmation. CT-guided biopsy is crucial, providing a minimally invasive method to obtain tissue samples and thus guiding clinical management and treatment decisions. The primary objective of this study was to assess the diagnostic accuracy of MDCT in differentiating between benign and malignant lung mass lesions. The study focused on evaluating the characteristic features of lung masses on MDCT that aid in this differentiation, correlating imaging findings with histopathological results from CT-guided biopsies, and determining the overall diagnostic utility of MDCT in thoracic lesions. This hospital-based observational study was conducted over a period of 17 months. The study included 52 patients with thoracic lesions, identified through imaging techniques such as chest radiographs and CT scans. These patients underwent CT-guided biopsy, with tissue samples sent for histopathological examination. Inclusion criteria involved patients with clinically and radiographically diagnosed lung masses, while exclusion criteria included those who did not consent, had contraindications to contrast media, or had conditions such as severe respiratory distress or coagulopathy. The data were analyzed using descriptive statistics, with efficacy measures such as yield and failure rates of CT-guided biopsies and validation measures like sensitivity, specificity, positive predictive value, and negative predictive value for MDCT. The study included 52 patients (50% male, 50% female), aged 16-80, with the most common age group being 51-60 years. Lesions were mainly in the lung parenchyma (65.38%), followed by the mediastinum (15.38%), hilar region (11.54%), and pleura (7.69%). MDCT evaluation classified 84.44% of the lesions as malignant, characterized by irregular contours, inhomogeneous texture, and contrast enhancement, while 15.55% were benign. Histopathology confirmed 42 malignant lesions, with squamous cell carcinoma being the most prevalent. Benign lesions included abscesses, tuberculosis, and pneumonitis. The study achieved a 100% success rate for CT-guided biopsy, with one minor complication (pneumothorax). The diagnostic accuracy of MDCT was notable, with a sensitivity of 100% for detecting malignancies, a specificity of 77.78%, a positive predictive value of 87.50%, and a negative predictive value of 100%, emphasizing its effectiveness in thoracic lesion evaluation. MDCT is a highly effective tool in the evaluation of lung masses, providing critical information that aids in distinguishing between benign and malignant lesions. When combined with CT-guided biopsy, it offers a reliable method for obtaining diagnostic tissue samples, with a high degree of accuracy and a low complication rate. The study underscores the importance of integrating imaging and histopathological findings in the management of thoracic lesions, ultimately enhancing diagnostic precision and informing appropriate clinical interventions.

Breast Ultrasound Computer-Aided Diagnosis System Based on Mass Irregularity Features in Frequency Domain

Our study develops a computer-aided diagnosis (CAD) system for breast ultrasound by presenting an innovative frequency domain technique for extracting mass irregularity features, thereby significantly boosting tumor classification accuracy. The experimental data consists of 5252 ultrasound breast tumor images, including 2745 benign tumors and 2507 malignant tumors. A Support Vector Machine was employed to classify the tumor as either benign or malignant, and the effectiveness of the proposed features set in distinguishing malignant masses from benign ones was validated. For the constructed CAD system, the performance indices’ accuracy, sensitivity, specificity, PPV, and NPV were 92.91%, 89.94%, 91.38%, 90.29%, and 91.45%, respectively, and the area index in the ROC analysis (AUC) was 0.924, demonstrating our method’s superiority over traditional spatial gray level dependence (SGLD), the ratio of depth to width, the count of depressions, and orientation features. Therefore, the constructed CAD system with the proposed features will be able to provide a precise and quick distinction between benign and malignant breast tumors with minimal training time in clinical settings.

Endoscopic ultrasound (EUS) elastography-guided fine-needle aspiration cytology (FNAC) versus conventional EUS FNAC for solid pancreatic lesions: A pilot randomized trial.

Endoscopic ultrasound guided fine-needle aspiration (EUS FNA) is the first-line modality to diagnose suspected solid pancreatic malignant lesions. Elastography-guided FNA has been shown to improve the diagnostic yield of EUS FNA but prospective studies are limited. The aim of the study was to compare diagnostic accuracy, sensitivity and specificity of conventional and elastography-guided EUS FNA in patients with suspected malignant pancreatic solid masses. Patients with suspected malignant solid pancreatic lesions presenting to our institute from July 2021 to January 2023 were recruited and randomized to conventional and elastography-guided EUS FNA using a 22-G EUS FNA needle. Diagnostic accuracy, sensitivity, specificity and positive and negative predictive values were calculated. Total 48 patients were initially screened for inclusion in the study, of which six were excluded and 42 patients underwent randomization. Finally, 20 patients in each group underwent the assigned intervention and were analyzed further. Baseline patient characteristics were similar in conventional FNA and elastography-guided FNA group with median age 52 (range 29-74) years and 51.8 (range 31-72) years, respectively, males being 70% and 75%, respectively. Median size of the lesion was 34mm (range 14-48mm) and 37 (range 18 to 50mm), respectively, for both conventional and elastography arm. The average size of the lesion was 35.7mm. Overall, the diagnosis of adenocarcinoma was made in 65% of cases. In the remaining cases, diagnoses were inflammatory mass, Castleman's disease, solid pseudopapillary epithelial neoplasm (SPEN), diffuse large B-cell lymphoma (DLBCL), pancreatic gastrointestinal stromal tumor (GIST) and metastasis. Conventional EUS FNA had diagnostic accuracy, sensitivity, specificity and positive and negative predictive values of 90%, 87.5%, 100%, 100% and 62.92%, respectively, and elastography-guided EUS FNA had diagnostic accuracy, sensitivity, specificity and positive and negative predictive values of 85%, 100%, 100% and 54.59%, respectively. No severe adverse events were noted. There is no significant difference between conventional and elastography-guided EUS FNA in terms of diagnostic accuracy, sensitivity, specificity and positive and negative predictive values. Both techniques appear safe and effective for characterizing solid pancreatic masses and elastography did not score numerically over the conventional arm.

Gadoxetate disodium (Gd-EOB-DTPA) contrast-enhanced magnetic resonance imaging for differentiation between benign and malignant splenic lesions in dogs.

Malignant splenic lesions in dogs are common, with hemangiosarcoma diagnosed most frequently, and there have been no consistent clinicopathologic, gross, or imaging characteristics identified that differentiate malignant from benign splenic lesions. Histopathology is required for definitive diagnosis, and given the poor long-term prognosis of malignant splenic lesions, a noninvasive tool to aid in diagnosis would be valuable. This prospective cohort study utilized gadoxetate disodium, a liver-specific contrast agent (Gd-EOB-DPTA; Eovist), to identify the general lesion and pre- and postcontrast signal characteristics of benign and malignant splenic and hepatic lesions in dogs with naturally occurring disease. Twenty-five dogs were enrolled, Eovist-enhanced MRI was performed, and dogs were taken to surgery for splenectomy and other organ biopsy. All histopathology and MRI studies were evaluated by a single pathologist and a single radiologist, respectively. The associations between the tumor type and numerous variables defined on MRI were evaluated using Fisher's exact tests, and the significance was identified at a P-value of.05. Malignant splenic masses were identified in 11/25 (44%) dogs, and 5/11 malignancies represented hemangiosarcoma. The presence of abdominal effusion (P=.017) and the presence of hepatic nodules on MRI (P=.009) were associated with splenic malignancy. There were no benign T2 hyperintense and no malignant T2 hypointense lesions (P=.021). Utilization of the T2 W MRI sequence may aid in the identification of malignant splenic lesions, particularly when accompanied by abdominal effusion and hepatic lesions.

An optimal fast fractal method for breast masses diagnosis using machine learning

This article introduces a fast fractal method for classifying breast cancerous lesions in mammography. While fractal methods are valuable for extracting information, they often come with a high computational load and time consumption. This paper demonstrates that extracting optimal fractal information and focusing only on valuable information for classification not only improves computation speed and reduces process load but also enhances classification accuracy. To achieve this, we define an objective function based on accurate classification of benign and malignant masses to identify the best scale. Instead of extracting information from all nine scales, we extract and employ information solely from the best scale for classification. We validate the obtained scales using three classifiers: Support Vector Machine (SVM), Genetic Algorithm (GA), and Deep Learning (DL), which confirm the effectiveness of the proposed method. Comparative analysis with other studies reveals improved classification performance with the presented method.