Enhancement Curve Research Articles

The Added Role of Kaiser Score in Evaluating BIRADS 4 Breast Lesions in Breast MRI

Abstract Background Breast malignancy is one of the most common malignancies affecting women, representing 31% of overall tumors affecting the females around the world. The increase in breast cancer incidence is accompanied by an increase in the clinician and researchers concerns regarding the improvement of diagnostic and therapeutic tools. Dynamic contrast- enhanced magnetic resonance imaging (MRI) is one of the most sensitive breast imaging modalities, but it has a relatively low specificity. Breast MRI findings are evaluated using the standardized American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) lexicon, which uses multiple descriptors to characterize enhancing lesions. Kaiser score is a simple flowchart that includes five major diagnostic criteria (root sign, dynamic enhancement curve type, margins, internal enhancement pattern, and edema) and its diagnostic accuracy is high. Aim of the Work The study aims to evaluate the added role of Kaiser score in score in evaluating BIRADS 4 breast lesions in breast MRI. Patients and Methods This is a retrospective study included 22 female patients who were diagnosed with breast lesions categorized as BIRADS 4, using the Kaiser score, where the Kaiser score threshold for malignancy is ≤ 4. Results The study investigated the diagnostic performance of Kaiser score in BIRADS 4 breast lesions. Kaiser score demonstrated 93 % sensitivity and 71.43 % specificity and 86.36% accuracy in comparison to the histopathology which is the gold standard investigation. Conclusion Kaiser score is a simple classification model which follows an intuitive tree structure reflecting structured step by step diagnostic process for lesion differentiation, includes five major diagnostic criteria (root sign, dynamic enhancement curve type, margins, internal enhancement pattern, and oedema) and it can be reliable in predicting malignant breast lesions due to its high accuracy, which can decrease the percentage of unnecessary breast biopsies. This has a positive potential to impact healthcare costs, as well as patient concern.

A rare case of primary angiosarcoma of breast with histopathology correlation

Primary angiosarcoma of the breast is a rare malignancy accounting for 0.05% of cases, seen in young females, and has atypical radiological presentation. We present a case of a 54-year-old female with complaints of a lump in the right breast for 5 months associated with pain, on and off fever. On ultrasound examination, the patient was found to have a BIRADS-IVb lesion. On further investigation using MRI, the lesion was found to have diffusion restriction with low ADC values, heterogenous enhancement, and type III enhancement curves, suggesting a malignant etiology. On histopathology, the lesion turned out to be angiosarcoma of intermediate grade and is positive for IHC CD 34.

Unsupervised Illumination Adaptation for Low-Light Vision.

Insufficient lighting poses challenges to both human and machine visual analytics. While existing low-light enhancement methods prioritize human visual perception, they often neglect machine vision and high-level semantics. In this paper, we make pioneering efforts to build an illumination enhancement model for high-level vision. Drawing inspiration from camera response functions, our model could enhance images from the machine vision perspective despite being lightweight in architecture and simple in formulation. We also introduce two approaches that leverage knowledge from base enhancement curves and self-supervised pretext tasks to train for different downstream normal-to-low-light adaptation scenarios. Our proposed framework overcomes the limitations of existing algorithms without requiring access to labeled data in low-light conditions. It facilitates more effective illumination restoration and feature alignment, significantly improving the performance of downstream tasks in a plug-and-play manner. This research advances the field of low-light machine analytics and broadly applies to various high-level vision tasks, including classification, face detection, optical flow estimation, and video action recognition.

The potential role of breast MRI in evaluation of triple-negative breast cancer and fibroadenoma of less than 3 cm.

The majority of small-sized (<3 cm) triple-negative breast cancer (TNBC) exhibit smooth margins upon palpation and are often oval or rounded masses. Distinguishing these masses preoperatively from fibroadenomas (FAs) would be very meaningful for clinical practice. The aim of our study was to evaluate the magnetic resonance imaging (MRI) appearance of TNBC and differentiate it from FAs. In this retrospective single-center study, we included 37 patients with TNBCs and 36 patients with FAs who underwent breast MRI. We employed the χ2 test and t-test to compare the differences in morphological features, dynamic contrast-enhanced MRI (DCE-MRI) parameters, and apparent diffusion coefficient (ADC) values between the two groups. Additionally, we constructed non-parametric receiver operating characteristic (ROC) curves using ADC values, with pathological results serving as the gold standard. A total of 37 TNBC lesions and 39 FA lesions were included in the final analysis. TNBCs exhibited more frequent irregular shape, irregular margins, peritumoral edema, fast enhancement in the initial phase, rim enhancement, and time-signal intensity curve (TIC) type III compared to FAs (all P<0.05). Conversely, low-signal segregation in T2-weighted imaging (T2WI) and TIC type I were commonly found in FAs. The mean ADC value of TNBCs was significantly lower than that of FAs [(1.104±0.13)×10-3 vs. (1.613±0.16)×10-3 mm2/s, P<0.05]. The cutoff ADC for differentiating TNBCs from FAs was 1.239×10-3 mm2/s, yielding an area under the curve (AUC) of 0.997, a sensitivity of 94.6%, and a specificity of 100%. The morphological presentation of MRI, internal enhancement features of the mass, TIC curves, and ADC values provide valuable differential diagnostic information for TNBC and FA masses with a maximum diameter of less than 3 cm.

A Deep Learning-Based Framework for Highly Accelerated Prostate MR Dispersion Imaging.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) measures microvascular perfusion by capturing the temporal changes of an MRI contrast agent in a target tissue, and it provides valuable information for the diagnosis and prognosis of a wide range of tumors. Quantitative DCE-MRI analysis commonly relies on the nonlinear least square (NLLS) fitting of a pharmacokinetic (PK) model to concentration curves. However, the voxel-wise application of such nonlinear curve fitting is highly time-consuming. The arterial input function (AIF) needs to be utilized in quantitative DCE-MRI analysis. and in practice, a population-based arterial AIF is often used in PK modeling. The contribution of intravascular dispersion to the measured signal enhancement is assumed to be negligible. The MR dispersion imaging (MRDI) model was recently proposed to account for intravascular dispersion, enabling more accurate PK modeling. However, the complexity of the MRDI hinders its practical usability and makes quantitative PK modeling even more time-consuming. In this paper, we propose fast MR dispersion imaging (fMRDI) to effectively represent the intravascular dispersion and highly accelerated PK parameter estimation. We also propose a deep learning-based, two-stage framework to accelerate PK parameter estimation. We used a deep neural network (NN) to estimate PK parameters directly from enhancement curves. The estimation from NN was further refined using several steps of NLLS, which is significantly faster than performing NLLS from random initializations. A data synthesis module is proposed to generate synthetic training data for the NN. Two data-processing modules were introduced to improve the model's stability against noise and variations. Experiments on our in-house clinical prostate MRI dataset demonstrated that our method significantly reduces the processing time, produces a better distinction between normal and clinically significant prostate cancer (csPCa) lesions, and is more robust against noise than conventional DCE-MRI analysis methods.

Interactions between polymer molecules and hydrodynamic responses in multi-ion induced charge electroosmosis

Induced charge electroosmosis (ICEO) can assist lab-on-a-chip devices and macromolecular separation involving interface, multi-ion species, and solution properties. To supplement the mechanistic insights into the ICEO phenomenon in complex electrochemical scenarios, we numerically address electrokinetic ion transport–fluid flow coupling regulated by multi-ion species and polymer macromolecular rheology around a polarized cylinder. The physics of the ICEO are analysed from multiple perspectives, including the azimuthal velocity, flow type, energy distribution, interfacial ion transport, and electroelastic instability. The main findings are as follows: (1) Deviations under neutral pH conditions (multi-ion species) cause flow field asymmetry and alter the input energy distribution (PE) in the tight double layer. Polymers greatly modify the interfacial force features in ion-enriched regions, as identified by the first stress difference (N1). (2) The kinetic energy vs. viscosity ratio (β) represents the nonlinear enhancement curve Ek=0.011*exp(β/0.64)-0.0138 due to the weakened effective viscosity Rvis. In addition, shear thinning notably lifts the charge density and salt concentration at the cylinder surface, which boosts the PE. (3) Quadrupolar vortex modes impact the positive correlation between β and the ion current (Jtotal) at different pH levels, resulting in less ion current dependence for small β. A low enhancement efficiency occurs at 10-4 ≤ α (molecular anisotropy) ≤ 0.1, whereas a high efficiency exists at α > 0.1. Electroelastic instabilities are confirmed by the spatiotemporal evolution of the velocity fluctuation, with a broadband structural power-law decline in the power spectral density. These results allow microdevice mixing manipulation and disclose non-Newtonian barrier of electrokinetic dynamics.

Contrast-Enhanced Ultrasound in the Diagnosis of Solid Renal Lesions.

The availability of imaging methods has enabled increased detection of kidney lesions, which are a common clinical problem. It is estimated that more than half of patients over the age of 50 have at least one undetermined mass in the kidney. The appropriate characterization and diagnosis of lesions imaged in the kidney allows for proper therapeutic management. Previously, contrast-enhanced computed tomography (CT) and contrast-enhanced magnetic resonance imaging (MRI) have been used in their extended diagnosis. However, the limitations of these techniques, such as radiation exposure, renal toxicity, and allergies to contrast agents, must be considered. Contrast-enhanced ultrasound (CEUS) is increasingly being used as an examination to resolve interpretive doubts that arise with other diagnostic methods. Indeed, it can be considered both as a problem-solving technique for diagnosing and distinguishing lesions and as a technique used for observation in preservative treatment. Evaluation of the enhancement curve over time on CEUS examination can help to differentiate malignant renal cell carcinoma (RCC) subtypes that should be resected from benign lesions, such as oncocytoma or angiomyolipoma (AML), in which surgery can be avoided. It allows for distinguishing between benign and malignant tumors, renal and pseudotumors, and solid and cystic tumors. Therefore, with recent advances in ultrasound technology, CEUS has emerged as a fast, reliable, and cost-effective imaging tool in the preoperative evaluation and diagnosis of solid renal masses.

Contrast-enhanced ultrasound features as a potential biomarker for the prediction of breast cancer recurrence.

To investigate the associations between contrast-enhanced ultrasound imaging features and disease recurrence among patients with locally advanced breast cancer treated with neoadjuvant chemotherapy. In the study, pre- and post-neoadjuvant chemotherapy contrast-enhanced ultrasound images of 43 patients with breast cancer were retrospectively analysed. Post-acquisition image processing involved the placement of freehand-drawn regions of interest, followed by the generation of blood flow kinetics representing blood volume and velocity for these regions of interest. Qualitative and quantitative contrast-enhanced ultrasound parameters were compared to predict recurrence, and receiver operating characteristic analysis was used to evaluate predictive ability. Among the 43 patients, 10 (23%) exhibited disease recurrence (median [range]: 27 [4-68] months). Post-neoadjuvant chemotherapy peak enhancement, wash-in area under the curve, wash-out area under the curve, and wash-in and wash-out area under the curve (p=0.003, p=0.004, p=0.026, and p=0.014, respectively) differed between the no-recurrence and recurrence groups. The area under the receiver operating characteristic curve (0.88; 95% confidence interval: 0.75-1.00) for post-neoadjuvant chemotherapy peak enhancement was the highest among the contrast-enhanced ultrasound parameters, with a cut-off of 13.33 arbitrary units. Higher peak enhancement on post-neoadjuvant chemotherapy contrast-enhanced ultrasound images was associated with recurrence in women with locally advanced breast cancer and is a potential biomarker of tumor recurrence.

Dynamic Perviousness: A Novel Imaging Marker for Predicting Mechanical Thrombectomy Outcomes in Acute Ischemic Stroke.

The predictive value of thrombus standard perviousness (SP) in acute ischemic stroke (AIS) for the technical success rates of mechanical thrombectomy (MT) or functional outcomes is not yet conclusive. We investigated the relationship between dynamic perviousness (DP) and revascularization results using time-dependent enhancement curve types determined with computed tomography (CT). A retrospective analysis of 137 AIS patients was performed. DP was calculated as the thrombus attenuation increase (TAI) using three time points and categorized into four groups: (1) no enhancement (CNE); (2) late enhancement (CLE); (3) early enhancement with washout (CW); (4) early enhancement without washout (CNW). Associations with the technical success rate and functional outcomes were assessed. Late enhancement (CLE) had approximately two times higher odds for successful MT as compared to clots with other enhancement dynamics. The odds ratios (logistic regression model with CNW as the reference) for the TICI III scores were 4.04 (p = 0.067), 1.82 (p = 0.3), and 1.69 (p = 0.4) for CLE, CW, and CNE, respectively. The NIHSS scores at discharge and mRS scores at three months showed regression coefficients (linear regression model with CNW as reference) of -3.05 (p = 0.10), -1.17 (p = 0.51), and -1.24 (p = 0.47); and -1.30 (p = 0.097), -0.85 (p = 0.25), and -0.15 (p = 0.83) for CLE, CW, and CNE, respectively. Thrombi with late enhancement patterns showed a higher revascularization rate and better outcomes as compared to clots with early uptake or no washout.

Prediction of pCR with pretreatment MRI radiomics in triple negative breast cancer treated with neoadjuvant chemo-immunotherapy.

589 Background: Neoadjuvant chemo-immunotherapy (NACI) has become the new standard of care for stage II-III triple-negative breast cancers (TNBC). This approach is linked to high rates of pathological complete responses (pCR), yet factors influencing responses to this regimen remain poorly characterized. Our objective was to investigate whether pretreatment MRI perfusion-based radiomics could serve as a predictive tool for pCR to NACI in patients with TNBC. Methods: This prospective study enrolled women with early-stage TNBC undergoing NACI at two different centers from August 2021 to July 2023. Tumor segmentation and pharmacokinetic analyses of pretreatment multi-vendor dynamic-contrast-enhanced (DCE)-MRI were conducted using the standard perfusion Tofts model. Radiomics features were extracted from the Ktrans, Ve, and Slopemax maps. Unsupervised correlation analysis of reproducible features and least absolute shrinkage and selector operation were employed to construct a radiomics score. The performance of the radiomic score was evaluated using the area under the receiver operating characteristic curve (AUC). A multivariable logistic regression model was employed to establish a multimodal nomogram. Performance metrics included discrimination, calibration, and clinical usefulness, assessed on the external validation set. Results: The training set comprised 112 patients from center 1 (mean age, 52 years ± 11 [SD]), and the external validation set included 83 participants from center 2 (mean age, 49 years ± 11 [SD]). Overall, the pCR rate was 70% (137/195). In the validation set, the radiomic score achieved an AUC of 0.80 (95% CI: 0.70, 0.89) for predicting pCR. A nomogram incorporating the radiomics score, tumor grade, and Ki67 yielded an AUC of 0.86 (95% CI: 0.78, 0.94) and demonstrated superior predictive efficacy compared to the histological prediction model (AUC, 0.76 [95% CI: 0.66, 0.87]; P = .02) in the validation set. Calibration curves of the nomogram exhibited good concordance between predicted and observed pCR in both sets. The radiomic score correlated with tumor size, washout enhancement curve, androgen receptor (AR), and combined positive score (CPS) PD-L1 levels (all P &lt; 0.05). Conclusions: PretreatmentMRI-based radiomics is a reliable predictor of pCR to NACI and might help customizing treatment choice for early-stage TNBC patients.

The value of the malignant subregion-based texture analysis in predicting the Ki-67 status in breast cancer.

To evaluate the value of the malignant subregion-based texture analysis in predicting Ki-67 status in breast cancer. The dynamic contrast-enhanced magnetic resonance imaging data of 119 histopathologically confirmed breast cancer patients (81 patients with high Ki-67 expression status) from January 2018 to February 2023 in our hospital were retrospectively collected. According to the enhancement curve of each voxel within the tumor, three subregions were divided: washout subregion, plateau subregion, and persistent subregion. The washout subregion and the plateau subregion were merged as the malignant subregion. The texture features of the malignant subregion were extracted using Pyradiomics software for texture analysis. The differences in texture features were compared between the low and high Ki-67 expression cohorts and then the receiver operating characteristic (ROC) curve analysis to evaluate the predictive performance of texture features on Ki-67 expression. Finally, a support vector machine (SVM) classifier was constructed based on differential features to predict the expression level of Ki-67, the performance of the classifier was evaluated using ROC analysis and confirmed using 10-fold cross-validation. Through comparative analysis, 51 features exhibited significant differences between the low and high Ki-67 expression cohorts. Following feature reduction, 5 features were selected to build the SVM classifier, which achieved an area under the ROC curve (AUC) of 0.77 (0.68-0.87) for predicting the Ki-67 expression status. The accuracy, sensitivity, and specificity were 0.76, 0.80, and 0.68, respectively. The average AUC from the 10-fold cross-validation was 0.72 ± 0.14. The texture features of the malignant subregion in breast cancer were potential biomarkers for predicting Ki-67 expression level in breast cancer, which might be used to precisely diagnose and guide the treatment of breast cancer.

Development of the Split-Bolus Pulmonary Arteriovenous Separating Computed Tomography Angiography Protocol Based on Time Enhancement Curve for Lung Cancer Surgery.

We devised a split-bolus injection and imaging protocol for pulmonary artery and vein separation computed tomography (CT) angiography based on time enhancement curve characterization. Furthermore, we aimed to evaluate the contrast enhancement effect and success rate of blood vessel separation between the pulmonary artery and vein of this proposed protocol. In this study, 102 patients (45 patients with the standard protocol and 57 patients with the proposed protocol) who underwent pulmonary arteriovenous computed tomography angiography were included. The CT values of various vessels, CT value difference between the pulmonary trunk and left atrium, and coefficient of variation in pulmonary arteries and veins were obtained from images of the standard and proposed protocols. The CT values in the proposed protocol for the pulmonary trunk were significantly higher than those in the standard protocol (487.3 [415.5-546.9] HU vs. 293.0 [259.0-350.0] HU, P < 0.01). The CT value difference between the pulmonary trunk and left atrium in the proposed protocol was significantly higher than that in the conventional protocol (211.3 [158.0-265.7] HU vs. 32 [-30.0-55.0] HU, P < 0.01). The coefficient of variation in the proposed protocol was 0.08 (0.06-0.10) and 0.09 (0.08-0.11) in pulmonary arteries and 0.08 (0.06-0.09) and 0.09 (0.07-0.12) in pulmonary veins, respectively. The proposed protocol achieved separation between the pulmonary artery and vein in many patients, making it useful for the preoperative assessment of individual thoracic anatomy.

Follow-up results of BI-RADS 3 lesions on magnetic resonance imaging: a retrospective study

The categorization of Breast Imaging Reporting and Data System (BI-RADS) 3 lesions is not as clear in magnetic resonance imaging (MRI) as it is in mammography (MG). With the increasing number of MRI scans currently being conducted globally, incidentally detected lesions falling into the probably benign category are frequently being observed. In this study, our aim was to investigate the imaging characteristics and follow-up results of BI-RADS 3 lesions detected by MRI and to determine their malignancy rates. Breast MRI scans performed between January 2010 and January 2020 and classified as BI-RADS 3 lesions were retrospectively analyzed. The study included 216 lesions with known biopsy or surgical excision results or with at least one year of radiological follow-up. We assessed the patients' age, the presence of breast cancer, the follow-up interval, and the imaging findings at the beginning and during the follow-up. Lesions that remained stable, disappeared, or decreased in size and had a benign histopathological diagnosis were classified as benign. Lesions with the histopathological diagnosis of malignancy, identified by either biopsy or surgical excision, were classified as malignant. We determined the malignancy rate based on the histopathology and follow-up results. Considering the follow-up results of all cases, 8% of lesions were excised, 0.5% decreased in size, 1.4% became enlarged, 17.1% disappeared, and 73% remained stable. The malignancy rate was 2.8%. A significant relationship was found between lesion shape and malignancy, as progression to malignancy was more likely in round lesions than in other types. An irregular margin, heterogeneous enhancement, and kinetic curve (type 2) features were significant for lesion upgrade to malignancy. The malignancy rate in BI-RADS 3 lesions detected by MRI is low and falls within the accepted cancer rate for MG and sonography. Changes in size, morphology, and enhancement pattern should be considered in terms of malignancy development during follow-up. The follow-up intervals should be determined on a case-by-case basis.

Rethinking Zero-DCE for Low-Light Image Enhancement

Zero-Reference Deep Curve Estimation (Zero-DCE) is currently one of the most popular low-light image enhancement methods. Through extensive experimentation, we observe that: (i) the excellent performance of Zero-DCE depends on the training data with multiple exposure levels, (ii) it cannot effectively handle uneven light, extremely low light, or overexposed images in natural environments. Therefore, we propose an improved zero-reference dual-illumination deep curve estimation method for low-light image enhancement named Zero-DiDCE, which can enhance, suppress, or maintain light levels for images. The adaptive light enhancement curve was designed to handle images with different exposure levels. An iterator and amplitude controller are designed to control the curve enhancement intensity by calculating the gap between the input image and the optimal light level. Furthermore, instead of the DCE-Net in Zero-DCE only taking the input image as network input, our DiDCE-Net in Zero-DiDCE takes the input image and the inverted input image simultaneously as network input to ensure that the training set contains samples with multiple exposure levels. A piecewise non-reference loss function is designed to guide the training of DiDCE-Net from the perspective of information loss. Qualitative and quantitative experiments show that our method can handle images with different levels of exposure well and outperforms state-of-the-art methods. In addition, the proposed curve and iterator can be integrated into other methods to improve their enhancement effects. The code is available at https://github.com/Wenhui-Luo/Zero-DiDCE.

Learning Deep Scene Curve for Fast and Robust Underwater Image Enhancement

Learning Deep Scene Curve for Fast and Robust Underwater Image Enhancement

The value of dynamic contrast-enhanced MRI and diffusion-weighted sequence in the evaluation of endometrial lesions

Background/Aim: Endometrial abnormalities represent a diagnostic challenge due to overlapping imaging features with normal endometrium. Aim of this study was to assess accuracy of dynamic contrast-enhanced and diffusion-weighted magnetic resonance imaging (MRI) in evaluation of endometrial lesions in comparison with T2 and to assess local staging validity and degree of myometrial invasion in malignancy. Methods: Forty patients with abnormal vaginal bleeding or sonographic thickened endometrial were recruited. MRI examination of pelvis was per-formed using 1.5 T scanner with a pelvic array coil. Conventional T1-and T2, dynamic contrast-enhanced (DCE) sequences and diffusion-weighted image (DWI) were performed. Results: Mean age of patients was 53.2 years and 60 % of patients COM-plained of post-menopausal bleeding. Irregular margin, type III enhancement curve, a high signal in T2WI and DWI and low signal of apparent diffusion coefficient (ADC) were significantly associated with malignancy. The optimum ADC threshold value for distinguishing benign from malignant endometrial lesions was 0.905 × 10 -3 mm 2 /S, with 95.5 % sensitivity and 92.9 % specificity. DWI was most sensitive to malignant endometrial lesions, followed by DCE (89.6 %, 98.4 %) and T2 (86.7 %, 91.4 %). DWI and DCE staging correlated with FIGO staging (p = 0.0001 and p = 0.019, respectively). DWI had the best sensitivity for myometrial invasion (95.6 %), followed by DCE (91.9 %) and T2WI (90.1 %). All three sequences had 89.7 % specificity. Conclusion: DWI and DCE MRI were superior to conventional MRI at distinguishing malignant from benign endometrial lesions and can improve myometrial invasion depth evaluation and therapy planning when COM-bined with morphological T2WI. ADC cutoff at a high b value improved MRI diagnostic sensitivity and specificity.

Using the Kaiser Score as a clinical decision rule for breast lesion classification: Does computer-assisted curve type analysis improve diagnosis?

PurposeWe aimed to investigate the effect of using visual or automatic enhancement curve type assessment on the diagnostic performance of the Kaiser Score (KS), a clinical decision rule for breast MRI. MethodThis IRB-approved retrospective study analyzed consecutive conventional BI-RADS 0, 4 or 5 patients who underwent biopsy after 1.5T breast MRI according to EUSOBI recommendations between 2013 and 2015. The KS includes five criteria (spiculations; signal intensity (SI)-time curve type; margins of the lesion; internal enhancement; and presence of edema) resulting in scores from 1 (=lowest) to 11 (=highest risk of breast cancer). Enhancement curve types (Persistent, Plateau or Wash-out) were assessed by two radiologists independently visually and using a pixel-wise color-coded computed parametric map of curve types. KS diagnostic performance differences between readings were compared by ROC analysis. ResultsIn total 220 lesions (147 benign, 73 malignant) including mass (n = 148) and non-mass lesions (n = 72) were analyzed. KS reading performance in distinguishing benign from malignant lesions did not differ between visual analysis and parametric map (P = 0.119; visual: AUC 0.875, sensitivity 95 %, specificity 63 %; and map: AUC 0.901, sensitivity 97 %, specificity 65 %). Additionally, analyzing mass and non-mass lesions separately, showed no difference between parametric map based and visual curve type-based KS analysis as well (P = 0.130 and P = 0.787). ConclusionsThe performance of the Kaiser Score is largely independent of the curve type assessment methodology, confirming its robustness as a clinical decision rule for breast MRI in any type of breast lesion in clinical routine.

Comparing accuracy of machine learning approaches to identifying parathyroid adenomas: Lessons and new directions

PurposeThe purpose of this investigation is to understand the accuracy of machine learning techniques to detect biopsy-proven adenomas from similar appearing lymph nodes and factors that influence accuracy by comparing support vector machine (SVM) and bidirectional Long short-term memory (Bi-LSTM) analyses. This will provide greater insight into how these tools could integrate multidimensional data and aid the detection of parathyroid adenomas consistently and accurately. MethodsNinety-nine patients were identified; 93 4D-CTs of patients with pathology-proven parathyroid adenomas were reviewed; 94 parathyroid adenomas and 112 lymph nodes were analyzed. A 2D slice through the lesions in each phase was used to perform sequence classification with ResNet50 as the pre-trained network to construct the Bi-LSTM model, and the mean enhancement curves were used to form an SVM model. The model characteristics and accuracy were calculated for the training and validation data sets. ResultsOn the training data, the area under the curve (AUC) of the Bi-LSTM was 0.99, while the SVM was 0.95 and statistically significant on the DeLong test. The overall accuracy of the Bi-LSTM on the validation data set was 92 %, while the SVM was 88 %. The accuracy for parathyroid adenomas specifically was 93 % for the Bi-LSTM and 83 % for the SVM model. ConclusionEnhancement characteristics are a distinguishing feature that accurately identifies parathyroid adenomas alone. The Bi-LSTM performs statistically better in identifying parathyroid adenomas than the SVM analysis when using both morphologic and enhancement information to distinguish between parathyroid adenomas and lymph nodes. Summary statementThe Bi-LSTM more accurately identifies parathyroid adenomas than the SVM analysis, which uses both morphologic and enhancement information to distinguish between parathyroid adenomas and lymph nodes, performs statistically better.

Multi-phasic magnetic resonance imaging of hemodynamic interchanges in hepatocarcinogenesis

BackgroundLiver cirrhosis and hepatocellular cancer deem a substantial global health burden and are the end result of a variety of chronic liver diseases. Guidelines have been introduced to secure standardized approaches in the diagnosis and management of hepatocellular carcinoma (HCC). Established guidelines agree upon the distinctive dynamic enhancement findings of HCC, characterized by arterial phase wash-in and venous or delayed phase washout. The indeterminate focal hepatic lesions constitute a diagnostic dilemma. The aim of the study was quantification of hepatic vascular parameters using dynamic contrast-enhanced (DCE)-MRI to study liver hemodynamic disturbances that can differentiate between focal hepatic lesions during hepatocellular carcinogenesis.ResultsThe study was conducted on 95 patients with comparing perfusion abnormalities across different liver cirrhosis pathologies, and the comparison revealed the correlation of hemodynamics with hepatocarcinogenesis and grades of cirrhosis. Relative enhancement curves were graphed to illustrate the different enhancement patterns across the spectrum of hepatonodular lesions of cirrhosis and among types of de novo and recurrent HCC. Statistical significance was highest between dysplastic nodules (DNs) and HCCs (maximal relative enhancement (MRE) 0.88, wash-in ratio (WIR) 0.84, washout ratio (WOR) 0.78, time to peak (TTP) 0.74, area under curve (AUC 0.73, T0 0.70), compared to those between cirrhotic liver and DNs (MRE 0.74, To 0.62). Least significances were between de novo and recurrent HCCs (TTP 0.66, r AUC 0.66, MRE 0.63). Performances between non-cirrhotic and cirrhotic liver [WOR 0.81, time to peak (TTP) 0.80, r AUC 0.63] surpassed those among different grades of cirrhosis (the highest was between non-tumoral and tumoral cirrhosis: TTP 0.74, MRE 0.68, WIR 0.65, WOR 0.65).ConclusionsDynamic contrast-enhanced magnetic resonance imaging hemodynamic metrics promise potential usefulness as non-invasive biomarkers in assessment of liver cirrhosis, characterization of cirrhotic nodules, and evaluation of multistep hepatocarcinogenesis.

Pseudoangiomatous stromal hyperplasia of the breast: multimodality imaging findings

Background/Aim: Pseudoangiomatous stromal hyperplasia (PASH) is a rare benign mesenchymal proliferative breast lesion. The literature contains little information on the radiological results of this uncommon tumor. In this study, we aim to define the radiologic findings of PASH through our institutional experience.&#x0D; Materials and Methods: Patients with PASH of the breast reported in the surgical database of our institution from 2020 to 2023 were retrospectively reviewed. PASH was detected in 11 female patients among the patients who underwent a total of 2172 breast tru-cut biopsies. Nine patients whose imaging studies could be recalled from the picture archiving systems (PACS) were included in the study. BI-RADS, 5th edition, was used to analyze and classify radiologic findings.&#x0D; Results: The median age of cases was 41 (range 22–53). Our single-center incidence was found to be 0.5%. Considering the sonographic findings, all of the lesions had an oval shape. On mammography, they were defined as focal asymmetry or circumscribed masses. An MRI was available in three cases. All three cases were hypointense on T1-weighted sequences and hyperintense on T2-weighted sequences. They displayed type 1 or type 2 enhancement curves in the dynamic contrast-enhanced images. No diffusion restriction was detected.&#x0D; Conclusion: In this study, tumor-forming PASH were generally circumscribed oval hypoechoic solid masses with minimal vascularity and no posterior acoustic features on ultrasound. On mammography, calcification, architectural distortion, or spiculation were not present in any of the cases. MRI findings were t2 hyperintensity, type 1–2 enhancement kinetics, and no diffusion restriction. In all imaging modalities, the imaging characteristics point to a benign lesion.