Search

Lupus mastitis is a presentation of lupus panniculitis that involves subcutaneous fat in patients with systemic lupus erythematosus (SLE). Moreover, lupus mastitis is a rare condition that typically presents as a palpable breast mass. Here, we report the case of a 29-year-old woman with a prior diagnosis of SLE who presented with palpable lumps in both breasts. Imaging studies were performed, and mammography revealed extensive and bizarre calcifications, mainly in the retromammary area. US revealed large irregular calcifications with posterior shadowing, and breast MRI images exhibited diffuse irregular persistent rim enhancement in the retromammary area. An US-guided biopsy was performed to differentiate the condition from breast cancer and confirmed the diagnosis of fat necrosis, consistent with the pathological characteristics of lupus mastitis. Herein, we present a case of lupus mastitis, an unusual clinical manifestation of SLE, and discuss the clinical, pathological, and imaging findings supporting the diagnosis and the differential diagnosis.

Abstract The surgical range of breast cancer that shows pathologic complete response (pCR) without change in microcalcifications after neoadjuvant chemotherapy (NAC) is controversial. This study examined whole breast specimens to evaluate the necessity of mastectomy in those cases. The viability of cancer cells around the residual microcalcification was assessed using prospectively collected breast samples to confirm the presence or absence of cancer cells. A total of 144 patients with breast cancer and diffuse microcalcifications were classified into the reduced mass with no change in residual microcalcification (RESMIN, n = 49) and non-RESMIN (n = 95) groups. Five specimens were prospectively evaluated to assess the presence of viable cancer cells around the microcalcification. Tumor responses to NAC were significantly better with high pCR rates in the RESMIN group (p = 0.005 and p = 0.002). The incidence of human epidermal growth factor receptor 2-positive and triple-negative breast cancers was significantly high in the RESMIN group (p = 0.007). Although five (10.2%) patients had locoregional recurrence in the RESMIN group, no local recurrence in the breast was reported. Although pCR was highly estimated, residual cancers, including ductal carcinoma in situ, remained in 80% cases. Therefore, given the weak scientific evidence available currently, complete removal of residual microcalcifications should be considered for oncologic safety.

Purpose We compared the radiation dose and image quality between the 2nd generation and the 3rd generation dual-source single-energy (DSSE) and dual-source dual-energy (DSDE) CT of the abdomen. Materials and Methods We included patients undergoing follow-up abdominal CT after partial or radical nephrectomy in the first 10 months of 2019 (2nd generation DS CT) and the first 10 months of 2020 (3rd generation DS CT). We divided the 320 patients into 4 groups (A, 2nd generation DSSE CT; B, 2nd generation DSDE CT; C, 3rd generation DSSE CT; and D, 3rd generation DSDE CT) (n = 80 each) matched by sex and body mass index. Radiation dose and image quality (objective and subjective qualities) were compared between the groups. Results The mean size-specific dose estimation of 3rd generation DSDE CT group was significantly lower than that of the 2nd generation DSSE CT (42.5%, p = 0.013) and 2nd generation DSDE CT (46.9%, p = 0.015) groups. Interobserver agreement was excellent for the overall image quality (intraclass correlation coefficient [ICC]: 0.8867) and image artifacts (ICC: 0.9423). Conclusion Our results showed a considerable reduction in the radiation dose while maintaining high image quality with 3rd generation DSDE CT as compared to the 2nd generation DSDE CT and 2nd generation DSSE CT.

The kidney is a rare site of ectopic adrenal adenoma. To the best of our knowledge, some cases of ectopic adrenal adenoma have been found in the kidney, but few of these cases explain the CT and MRI findings of the lesion. We reported a case of ectopic adrenal adenoma in the left renal sinus. A 47-year-old male patient underwent abdominal CT for routine health check-ups, which revealed a 1.2 cm enhancing mass in the left renal sinus. The MRI showed a signal drop of the mass in T1 weighted in- and opposed-phase, which indicates fat components. The mass was confirmed as an ectopic adrenal adenoma after surgery.

Hyperechoic lesions of the breast encompass a wide range of conditions that are occasionally encountered during breast ultrasonography. Although typical hyperechoic lesions with a distinct fat component on imaging are well known, some hyperechoic lesions are diagnosed as unexpected pathology, making the radiology-pathology correlation difficult. Therefore, understanding the pathology of these lesions and how it correlates with imaging findings can help radiologists accurately diagnose and properly manage a range of related conditions. This article presents a pictorial review of unexpected hyperechoic benign and malignant breast lesions, with a focus on the pathological conditions that give rise to the hyperechoic pattern.

Bladder cancer (BC) is the most common urinary malignancy; however accurate diagnosis and prediction of recurrence after therapies remain elusive. This study aimed to develop a biosignature of immunotherapy-based responses using gene expression data. Publicly available BC datasets were collected, and machine learning (ML) approaches were applied to identify a novel biosignature to differentiate patient subgroups. Immune phenotyping of BC in the IMvigor210 dataset included three subtypes: inflamed, excluded, and desert immune. Immune phenotypes were analyzed with gene expressions using traditional but powerful classification methods such as random forests, Deep Neural Networks (DNN), Support Vector Machines (SVM) together with boosting and feature selection methods. Specifically, DNN yielded the highest area under the curve (AUC) with precision and recall (PR) curves and receiver operating characteristic (ROC) curves for each phenotype ($0.711 \pm 0.092$ and $0.86 \pm 0.039$, respectively) resulting in the identification of gene expression features useful for immune phenotype classification. Our results suggest significant potential to further develop and utilize machine learning algorithms for analysis of BC and its precaution. In conclusion, the findings from this study present a novel gene expression assay that can accurately discriminate BC patients from controls. Upon further validation in independent cohorts, this gene signature could be developed into a predictive test that can support clinical evaluation and patient care.

Abstract Conventional deep learning (DL) algorithm requires full supervision of annotating the region of interest (ROI) that is laborious and often biased. We aimed to develop a weakly-supervised DL algorithm that diagnosis breast cancer at ultrasound without image annotation. Weakly-supervised DL algorithms were implemented with three networks (VGG16, ResNet34, and GoogLeNet) and trained using 1000 unannotated US images (500 benign and 500 malignant masses). Two sets of 200 images (100 benign and 100 malignant masses) were used for internal and external validation sets. For comparison with fully-supervised algorithms, ROI annotation was performed manually and automatically. Diagnostic performances were calculated as the area under the receiver operating characteristic curve (AUC). Using the class activation map, we determined how accurately the weakly-supervised DL algorithms localized the breast masses. For internal validation sets, the weakly-supervised DL algorithms achieved excellent diagnostic performances, with AUC values of 0.92–0.96, which were not statistically different (all Ps > 0.05) from those of fully-supervised DL algorithms with either manual or automated ROI annotation (AUC, 0.92–0.96). For external validation sets, the weakly-supervised DL algorithms achieved AUC values of 0.86–0.90, which were not statistically different (Ps > 0.05) or higher (P = 0.04, VGG16 with automated ROI annotation) from those of fully-supervised DL algorithms (AUC, 0.84–0.92). In internal and external validation sets, weakly-supervised algorithms could localize 100% of malignant masses, except for ResNet34 (98%). The weakly-supervised DL algorithms developed in the present study were feasible for US diagnosis of breast cancer with well-performing localization and differential diagnosis.

Syringomatous adenoma of the nipples, first reported in 1983, is an extremely rare benign tumor extending to the subareolar area and, pathologically, has a shape similar to that of sweat gland tumors. Radiologically, infiltrating patterns and calcifications can cause misdiagnosis of malignant tumors. The authors report a case of syringomatous adenoma that shows only calcifications of the nipple in a screening mammography.

Abstract Peritumoral edema (PE) of breast cancer at T2-weighted MR images is considered a poor prognostic sign and may represent the microenvironment surrounding the tumor; however, its histopathological mechanism remains unclear. The purpose of the study was to identify and describe detailed histopathological characteristics associated with PE at preoperative breast MRI in breast cancer patients. This retrospective study included breast cancer patients who had undergone preoperative MRI and surgery between January 2011 and December 2012. Two radiologists determined the presence of PE in consensus based on the signal intensity surrounding the tumor at T2-weighted images. The following detailed histopathological characteristics were reviewed by two breast pathologists using four-tiered grades; lymphovascular invasion, vessel ectasia, stromal fibrosis, growth pattern, and tumor budding. Tumor necrosis and tumor infiltrating lymphocytes were assessed using a percent scale. Baseline clinicopathological characteristics, including age and histologic grade, were collected. The associations between detailed histopathologic characteristics and PE were examined using multivariable logistic regression with odds ratio (OR) calculation. A total of 136 women (median age, 49 ± 9 years) were assessed; among them 34 (25.0%) had PE. After adjustment of baseline clinicopathological characteristics that were significantly associated with PE (age, T stage, N stage, histologic grade, and subtype, all Ps

PURPOSENeck ultrasonography (US), computed tomography (CT), and 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) are all known to be useful imaging modalities for detecting supraclavicular lymph node (SCN) metastasis in breast cancer. The authors compared the diagnostic values of neck US, CT, and PET/CT in the detection of SCN metastasis in breast cancer.METHODSSCN metastases identified in neck US, CT, or PET/CT during follow-up visits of patients with breast cancer were pathologically confirmed with the use of US-guided fine-needle aspiration cytology. The clinicopathological factors of the patients were analyzed, and the statistical parameters including sensitivity, specificity, positive and negative predictive values, false-positive and false-negative rates, and accuracy of neck US, CT, and PET/CT were compared.RESULTSAmong 32 cases of suspicious SCNs, 24 were pathologically confirmed as metastasis of breast cancer. The sensitivity of US + CT was 91.7%, which was the same as that of PET/CT, while the sensitivity rates of US alone and CT alone were 87.5% and 83.3%, respectively. Accuracy was 99.8% in PET/CT alone and 98.1% in US + CT. The false-negative rate was 0.1% in US + PET/CT, while it was 0.2% in PET/CT and US + CT, 0.3% in US alone and 0.4% in CT alone.CONCLUSIONPET/CT can be the first choice for detecting SCN metastases in breast cancer. However, if PET/CT is unavailable for any reason, US + CT could be a good second option to avoid false-negative results.

Although breast ultrasonography is the mainstay modality for differentiating between benign and malignant breast masses, it has intrinsic problems with false positives and substantial interobserver variability. Artificial intelligence (AI), particularly with deep learning models, is expected to improve workflow efficiency and serve as a second opinion. AI is highly useful for performing three main clinical tasks in breast ultrasonography: detection (localization/segmentation), differential diagnosis (classification), and prognostication (prediction). This article provides a current overview of AI applications in breast ultrasonography, with a discussion of methodological considerations in the development of AI models and an up-to-date literature review of potential clinical applications.

Purpose: This study evaluated the efficiency of preoperative ultrasound (US)-guided tattooing of the axillary lymph nodes with activated charcoal and the correlation between sonographically suspicious nodes and final histologic results by node-to-node analysis. The concordance rate between the tattooed nodes and sentinel nodes was also determined. Methods : : US-guided tattooing of sonographically suspicious axillary nodes was performed preoperatively by an injection of activated charcoal. The identification of black pigment and the concordance between the sentinel and tattooed nodes was evaluated. Results : : Regarding node-to-node analysis, the false-negative rate of US-fine needle aspiration (FNA) was 43.3%. The sensitivity and negative predictive values were 56.7% and 81.7%, respectively. The specificity and positive predictive values were 100%. The accuracy of US-FNA was 85.2%. In the final pathology, 45/125 patients (36.0%) had positive nodes, including two micrometastases. The false-negative rate of sentinel lymph node biopsy (SLNB) was 4.0%, but there were no skip metastases. The sensitivity and specificity of SLNB were 95.6% and 100%, respectively. The negative predictive value was 97.6%, and the positive predictive value was 100%. The accuracy of SLNB was 98.4%. In 117 of 125 patients (93.6%), there was concordance between the charcoal tattooed axillary lymph nodes and SLNs. Conclusion : : SLNB, in conjunction with US-guided tattooing of sonographically suspicious axillary lymph nodes, is a useful procedure to reduce the false-negative rate of SLNB and improve the accuracy of an intraoperative evaluation of axillary nodes in breast cancer patients. This paper proposes the concept of targeted axillary node biopsy with preoperative US-guided tattooing for the most accurate axillary staging in patients with breast cancer.

Background This study evaluated the usefulness of judgment of central lymph node (LN) metastasis by surgeon’s palpation in papillary thyroid cancer. Methods This study included 127 patients who underwent thyroidectomy and central compartment node dissection between October 2014 and February 2015. The criterion for suspicious LNs was hardness. Results Of the 20.5% (28/127) of suspicious for metastatic LNs according to surgeon determination, 92.8% (26/28) were confirmed to be metastatic in the final pathological examinations. Metastatic LNs were found in 38 (38.3%) of 99 patients without suspicious LNs, 29 of whom (76.3%) had micrometastases. The sensitivity, specificity, and positive and negative predictive values for the determination of LN metastasis by a surgeon were 40.6%, 96.8%, 92.9%, and 61.6%, respectively. Conclusion Determination of central LN metastasis by a surgeon’s palpation may be useful to evaluate LNs owing to the high specificity and positive predictive values, especially in macrometastasis or high-risk LN disease.

Abstract Background Preoperative breast magnetic resonance imaging (MRI) provides more information than mammography and ultrasonography for determining the surgical plan for patients with breast cancer. This study aimed to determine whether breast MRI is more useful for patients with ductal carcinoma in situ (DCIS) lesions than for those with invasive ductal carcinoma (IDC). Methods A total of 1113 patients with breast cancer underwent mammography, ultrasonography, and additional breast MRI before surgery. The patients were divided into 2 groups: DCIS (n = 199) and IDC (n = 914), and their clinicopathological characteristics and oncological outcomes were compared. Breast surgery was classified as follows: conventional breast-conserving surgery (Group 1), partial mastectomy with volume displacement (Group 2), partial mastectomy with volume replacement (Group 3), and total mastectomy with or without reconstruction (Group 4). The initial surgical plan (based on routine mammography and ultrasonography) and final surgical plan (after additional breast MRI) were compared between the 2 groups. The change in surgical plan was defined as group shifting between the initial and final surgical plans. Results Changes (both increasing and decreasing) in surgical plans were more common in the DCIS group than in the IDC group (P

Despite various success in computer vision with facial images (e.g., face detection, recognition, and generation), facial expression recognition is still a challenging problem yet to be solved. This is because of simple but fundamental bottlenecks: 1) no global agreement on different facial expressions, 2) significant dataset biases that prevent cross-dataset analysis for a large-scale study, and 3) high class imbalance in in-the-wild datasets that causes inconsistency in predicting expressions in images using a machine learning algorithm. To tackle these issues, we propose a novel Deep Learning approach via adaptive cross-dataset scheme. We combine multiple in-the-wild datasets to secure sufficient training samples while minimizing dataset bias using ideas of reversal gradients to retain generality. For this, we introduce a flexible objective function that can control for skewed label distributions in the dataset. Incorporating these ideas, together with the ResNet pipeline as a backbone, we carried extensive experiments to validate our ideas using three independent in-the-wild facial expression datasets, which first confirmed bias from different datasets and yielded improved performance on facial expression recognition using the multi-site dataset.

In the medical field, it is delicate to anticipate good performance in using deep learning due to the lack of large-scale training data and class imbalance. In particular, ultrasound, which is a key breast cancer diagnosis method, is delicate to diagnose accurately as the quality and interpretation of images can vary depending on the operator’s experience and proficiency. Therefore, computer-aided diagnosis technology can facilitate diagnosis by visualizing abnormal information such as tumors and masses in ultrasound images. In this study, we implemented deep learning-based anomaly detection methods for breast ultrasound images and validated their effectiveness in detecting abnormal regions. Herein, we specifically compared the sliced-Wasserstein autoencoder with two representative unsupervised learning models autoencoder and variational autoencoder. The anomalous region detection performance is estimated with the normal region labels. Our experimental results showed that the sliced-Wasserstein autoencoder model outperformed the anomaly detection performance of others. However, anomaly detection using the reconstruction-based approach may not be effective because of the occurrence of numerous false-positive values. In the following studies, reducing these false positives becomes an important challenge.

Abstract Background We report on our experience of ultrasound (US)-guided dual-localization for axillary nodes before and after neoadjuvant chemotherapy (NAC) with clip and activated charcoal to guide axillary surgery in breast cancer patients. Methods Between November 2017 and May 2018, a dual-localization procedure was performed under US guidance for the most suspicious axillary nodes noted at initial staging (before NAC, with clip) and restaging (after NAC, with activated charcoal) in 28 cytologically proven node-positive breast cancer patients. Patients underwent axillary sampling or dissection, which involved removing not only the sentinel nodes (SNs), but also clipped nodes (CNs) and tattooed nodes (TNs). Success (or failure) rates of biopsies of SNs, CNs, and TNs and inter-nodal concordance rates were determined. Sensitivities for the individual and combined biopsies were calculated. Results SN biopsy failed in four patients (14%), whereas the CN biopsy failed in one patient (4%). All TNs were identified in the surgical field. Concordance rates were 79% for CNs–TNs, 63% for CNs–SNs, and 58% for TNs–SNs. Sensitivity for SN, CN, and TN biopsy was 73%, 67%, and 67%, respectively. Sensitivity was 80% for any combination of biopsies (SN plus CN, SN plus TN, SN plus CN plus TN). Conclusions US-guided dual-localization of axillary nodes before and after NAC with clip and activated charcoal was a feasible approach that might facilitate more reliable nodal staging with less-invasive strategies in node-positive breast cancer patients.

Purpose Absorbable retaining thread (ART) needle localization utilizes a guiding needle with a thread; this technique was invented to reduce patient discomfort and wire migration. We investigated the feasibility of ultrasound (US)-guided ART needle localization for nonpalpable breast lesions. Methods ART needle localization was performed for 26 nonpalpable breast lesions in 26 patients who were scheduled to undergo surgical excision the day after localization. Seventeen breast lesions were initially diagnosed as invasive ductal carcinoma, six as ductal carcinomas in situ, and one as fibrocystic change. The other two cases without an initial pathologic diagnosis had suspicious US features, and excision was planned concomitantly with contralateral breast cancer surgery. The primary outcome was the technical success rate of ART needle localization confirmed by US immediately after the procedure, and the secondary outcomes were the percentage of clear margins on pathology and the complication rate of ART needle localization. Results The technical success rate of ART needle localization was 96.2% (25 of 26 patients), and the ART was located 1 cm away from the mass in one patient (3.8%). The lesions were successfully removed with clear margins in all 26 patients. No significant complications related to ART needle localization were observed. Conclusion ART needle localization can be an alternative to wire needle localization for nonpalpable breast lesions.

Secretory carcinoma of the breast is an extremely rare, clinically and histologically distinct variant of invasive ductal carcinoma, with an indolent growth pattern and a more favorable prognosis than that of typical ductal carcinoma. Few studies have described its imaging features. Herein, we report on a secretory breast carcinoma with findings from various imaging modalities, especially including the MRI findings, which appears a well-defined complex cystic mass. Awareness of its imaging features using various modalities will be helpful for the differential diagnosis.

Summary: Background: axillary lymph nodes dissection (ALND) has been a standard treatment in breast cancer with positive sentinel LNs. However, various short- and long-term postoperative morbidities have been reported after conventional ALND. To define the concept of targeted axillary sampling (AS) and to assess its oncological feasibility for breast cancer. We compared the oncological outcomes in the axillary area between conventional ALND and targeted AS with or without radiotherapy. Methods: One hundred and twenty-nine female patients with cT1-2N1 breast cancer underwent breast and axillary surgery. We defined the concept of targeted AS in clinical and pathological terms, and the oncological outcomes were compared between ALND and AS, and between AS with and without radiotherapy. Results: There were no significant differences in oncological outcomes in the axilla between conventional ALND and AS, or between AS with radiotherapy and AS alone. Conclusions: The 5-year oncological outcomes of targeted AS were not inferior to those of conventional ALND, regardless of whether radiotherapy was added. Keywords: Breast, Carcinoma, Lymph node, Dissection, Sampling

Abstract Background Although the role of axillary imaging has been redirected for predicting high nodal burden rather than predicting nodal metastases since ACOSOG Z1011 trial, it remains unclear whether and how axillary lymph node (ALN) characteristics predicts high nodal burden. Our study was aimed to evaluate the predictive value of imaging characteristics of ALNs at ultrasound and magnetic resonance imaging (MRI) for prediction of high nodal burden (≥3 metastatic ALNs) in clinically node-negative breast cancer patients. Methods Clinicopathological and imaging characteristics were evaluated in patients with ultrasound (n = 312) and MRI (n = 256). Imaging characteristics include number of suspicious ALNs and cortical morphologic changes (grade 1, cortical thickness

Purpose: To evaluate the association of volumetric breast density with clinicopathological factors in breast cancer patients. Materials and Methods: A total of 205 Korean patients with breast cancer who underwent mammography for initial staging between January 2015 and June 2016 were enrolled. Volumetric breast density was measured using a fully automated commercial method (Volpara®). in the contralateral breast. The association of volumetric breast density with clinical and histopathological factors was evaluated using t-test and analysis of variance as appropriate. Results: Mean volumetric breast density in all patients was 13.5% (range, 4.1– 34.9%). The mean volumetric breast density in patients with symptom-detected cancers was significantly higher than that in those with screening-detected cancers (14.9% vs. 11.8%, p = 0.002). Mean volumetric breast density tended to decrease with age (20–39 years: 19.0%, 40–59 years: 14.3%, 60–80 years: 7.7%). The mean volumetric breast density in postmenopausal women was significantly lower than that in premenopausal women (9.8% vs. 17.6%, p < 0.001). Other histopathological factors including histologic grade or hormone receptor status were not associated with volumetric breast density. Conclusion: Our results suggest that volumetric breast density is associated with the method of detection, age, and menopausal status.

Recently, the amount of attention paid towards convolutional neural networks (CNN) in medical image analysis has rapidly increased since they can analyze and classify images faster and more accurately than human abilities. As a result, CNNs are becoming more popular and play a role as a supplementary assistant for healthcare professionals. Using the CNN on portable medical devices can enable a handy and accurate disease diagnosis. Unfortunately, however, the CNNs require high-performance computing resources as they involve a significant amount of computation to process big data. Thus, they are limited to being used on portable medical devices with limited computing resources. This paper discusses the network quantization techniques that reduce the size of CNN models and enable fast CNN inference with an energy-efficient CNN accelerator integrated into recent mobile processors. With extensive experiments, we show that the quantization technique reduces inference time by 97% on the mobile system integrating a CNN acceleration engine.

Purpose To retrospectively evaluate the performance of 3D computer-aided detection (CAD) for digital breast tomosynthesis (DBT) in the detection of calcifications in comparison with 2D CAD for digital mammography (DM). Materials and Methods Between 2012 and 2013, both 3D CAD and 2D CAD systems were retrospectively applied to the calcification data set including 69 calcifications (31 malignant calcifications and 38 benign calcifications) and the normal data set including 20 bilateral normal mammograms. Each data set consisted of paired DBT and DM images. Sensitivities for the detection of malignant calcifications were calculated from the calcification data set. False-positive mark rates were calculated from the normal data set. They were compared between the two systems. Results Sensitivities of 3D CAD [100% (31/31) at levels 2, 1, and 0] were same as those of the 2D CAD system [100% (31/31) at levels 2 and 1] (p = 1.0, respectively). The mean value of false-positive marks per view with 3D CAD was higher than that with 2D CAD at level 2 (0.52 marks ± 0.91 vs. 0.07 marks ± 0.26, p = 0.009). Conclusion 3D CAD for DBT showed equivalent sensitivity, albeit with a higher false-positive mark rate, than 2D CAD for DM in the detection of calcifications.

In addition to the development of beta amyloid plaques and neurofibrillary tangles, Alzheimer's disease (AD) involves the loss of connecting structures including degeneration of myelinated axons and synaptic connections. However, the extent to which white matter tracts change longitudinally, particularly in the asymptomatic, preclinical stage of AD, remains poorly characterized. In this study we used a novel graph wavelet algorithm to determine the extent to which microstructural brain changes evolve in concert with the development of AD neuropathology as observed using CSF biomarkers. A total of 118 participants with at least two diffusion tensor imaging (DTI) scans and one lumbar puncture for CSF were selected from two observational and longitudinally followed cohorts. CSF was assayed for pathology specific to AD (Aβ42 and phosphorylated-tau), neurodegeneration (total-tau), axonal degeneration (neurofilament light chain protein; NFL), and synaptic degeneration (neurogranin). Tractography was performed on DTI scans to obtain structural connectivity networks with 160 nodes where the nodes correspond to specific brain regions of interest (ROIs) and their connections were defined by DTI metrics (i.e., fractional anisotropy (FA) and mean diffusivity (MD)). For the analysis, we adopted a multi-resolution graph wavelet technique called Wavelet Connectivity Signature (WaCS) which derives higher order representations from DTI metrics at each brain connection. Our statistical analysis showed interactions between the CSF measures and the MRI time interval, such that elevated CSF biomarkers and longer time were associated with greater longitudinal changes in white matter microstructure (decreasing FA and increasing MD). Specifically, we detected a total of 17 fiber tracts whose WaCS representations showed an association between longitudinal decline in white matter microstructure and both CSF p-tau and neurogranin. While development of neurofibrillary tangles and synaptic degeneration are cortical phenomena, the results show that they are also associated with degeneration of underlying white matter tracts, a process which may eventually play a role in the development of cognitive decline and dementia. Keywords: DTI tractography, CSF biomarker, Longitudinal brain connectivity, Alzheimer's disease pathology, Multi-resolution analysis

Weakly labeled data are inevitable in various research areas in artificial intelligence (AI) where one has a modicum of knowledge about the complete dataset. One of the reasons for weakly labeled data in AI is insufficient accurately labeled data. Strict privacy control or accidental loss may also cause missing-data problems. However, supervised machine learning (ML) requires accurately labeled data in order to successfully solve a problem. Data labeling is difficult and time-consuming as it requires manual work, perfect results, and sometimes human experts to be involved (e.g., medical labeled data). In contrast, unlabeled data are inexpensive and easily available. Due to there not being enough labeled training data, researchers sometimes only obtain one or few data points per category or label. Training a supervised ML model from the small set of labeled data is a challenging task. The objective of this research is to recover missing labels from the dataset using state-of-the-art ML techniques using a semisupervised ML approach. In this work, a novel convolutional neural network-based framework is trained with a few instances of a class to perform metric learning. The dataset is then converted into a graph signal, which is recovered using a recover algorithm (RA) in graph Fourier transform. The proposed approach was evaluated on a Fashion dataset for accuracy and precision and performed significantly better than graph neural networks and other state-of-the-art methods.

A multigene expression assay corresponds to the likelihood of breast cancer recurrence after the initial diagnosis and can be used to guide the decision for additional chemotherapy. However, only few studies have investigated the associations between the imaging features of breast cancer and the results of multigene expression assays. Our study was to identify the relationship between imaging features on ultrasound (US) and the recurrence score (RS) on a 21-gene expression assay in patients with oestrogen receptor (ER)-positive, HER2-negative breast cancer. 267 patients with ER-positive, HER-negative invasive breast cancer who underwent examinations using US and Oncotype DX assay were included. US images were independently reviewed by dedicated breast radiologists who were blind to the RS. Tumour roundness was measured using a laboratory-developed software program. The pathological data were reviewed, including immunohistochemistry results. Univariate analysis was performed to assess the associations between the RS and each variable. Multiple logistic regression analysis was used to identify independent predictors of high RS. Of 267 patients, 147 (55%) had low, 96 (36%) intermediate, and 24 (9%) had high RS. According to the univariate analysis, parallel orientation, presence of calcification in the mass, and tumour roundness were positively associated with high RS. Multiple logistic regression analysis showed that parallel orientation (OR = 5.53) and tumour roundness (OR = 1.70 per 10 increase) were associated with high RS. Parallel orientation and tumour roundness are independent variables that may predict high RS in patients with ER-positive, HER2-negative breast cancer.

There has been a major need to better understand the biological characteristics of triple-negative breast cancers. Compared with estrogen receptor (ER)-positive cancers, several magnetic resonance (MR) imaging findings have been reported as characteristic findings. However, information regarding their location has not been described. Our study was to compare the location of triple-negative breast cancers with that of ER-positive breast cancers using magnetic resonance (MR) imaging. The locations of 1102 primary breast cancers (256 triple-negative and 846 ER-positive) in 1090 women (mean, 52.1 years) were reviewed using three-dimensional (3D) coordinates. The x-axis measurement was recorded as the transverse distance from the posterior nipple line; y-axis measurement as the anteroposterior distance from the chest wall; z-axis measurement as the superoinferior distance from the posterior nipple line. The association between breast cancer subtype and tumor location was evaluated using multiple linear regression analysis. Triple-negative breast cancers were significantly closer to the chest wall than ER-positive breast cancers in absolute (1.8 cm vs. 2.3 cm, P < .0001) and normalized (0.21 vs. 0.25, P < .0001) y-axis distances. The x- and z-axes distances were not significantly different between triple-negative and ER-positive breast cancers. Multiple linear regression analysis revealed that age, mammographic density, axillary nodal status, and triple-negative subtype were significantly associated with absolute and normalized distances from the chest wall (all P < .05). Our results show that triple-negative breast cancers have a tendency toward a posterior or prepectoral location compared with ER-positive breast cancers.