Explore the vast range of titles available.

Traditional computer-aided diagnosis (CAD) processes include feature extraction, selection, and classification. Effective feature extraction in CAD is important in improving the classification’s performance. We introduce a machine-learning method and have designed an analysis procedure of benign and malignant breast tumour classification in ultrasound (US) images without a need for a priori tumour region-selection processing, thereby decreasing clinical diagnosis efforts while maintaining high classification performance. Our dataset constituted 677 US images (benign: 312, malignant: 365). Regarding two-dimensional US images, the oriented gradient descriptors’ histogram pyramid was extracted and utilised to obtain feature vectors. The correlation-based feature selection method was used to evaluate and select significant feature sets for further classification. Sequential minimal optimisation—combining local weight learning—was utilised for classification and performance enhancement. The image dataset’s classification performance showed an 81.64% sensitivity and 87.76% specificity for malignant images (area under the curve = 0.847). The positive and negative predictive values were 84.1 and 85.8%, respectively. Here, a new workflow, utilising machine learning to recognise malignant US images was proposed. Comparison of physician diagnoses and the automatic classifications made using machine learning yielded similar outcomes. This indicates the potential applicability of machine learning in clinical diagnoses.

Metaplastic breast carcinoma is a rare type of breast carcinoma, and there are limited data about the magnetic resonance imaging (MRI) findings of metaplastic carcinoma. This study evaluates the MRI characteristics and prognostic outcomes across metaplastic carcinoma subtypes. In this retrospective cohort study, a total of 29 patients with histologically confirmed metaplastic carcinoma from 2011 to 2019 were enrolled. Clinical, pathological, and follow-up data, focusing on disease-free (DFS) and overall survival (OS), are recorded. Breast MRI findings were analyzed and categorized based on BI-RADS 5th edition. Among the participants, 19 had squamous carcinoma, 8 had metaplastic carcinoma with mesenchymal differentiation, and 2 had unclassified subtypes. The most common findings were a solitary mass (75.8%), high T2 signal (51.7%), and heterogenous enhancement (65.5%) with a washout kinetic curve (86.2%). The apparent diffusion coefficient (ADC) values in the metaplastic carcinoma with mesenchymal differentiation group were significantly higher (mean 1.83 +/- 0.50 x 10-3 mm2/s) in comparison with the squamous carcinoma group (mean 1.12 +/- 0.21 x 10-3 mm2/s). The cut-off point of the ADC value was 1.53x10-3 mm2/s, with a sensitivity of 71.4% and a specificity of 100% (AUC = 0.937). The five-year DFS and OS rates were 63% and 79% across the board, 78% and 89.5% in the squamous group, and 50% and 53% in the mesenchymal differentiation group, respectively. Metaplastic breast carcinoma is a diverse and aggressive malignancy with variable prognosis. Our findings indicate that mesenchymal differentiation is characterized by higher ADC values and correlates with a worse prognosis.

Background Experience with application of a robotic surgery platform in the management of breast cancer is limited. The preliminary results of the robotic nipple-sparing mastectomy (R-NSM) and immediate breast reconstruction (IBR) with Gel implant procedure are reported. Methods The medical records of patients from a single institution who underwent an R-NSM and IBR with Gel implant procedure for breast cancer during the period March 2017 to February 2018 were assessed. Data on clinicopathologic characteristics, type of surgery, complications, and recurrence were analyzed to determine the effectiveness and oncologic safety of R-NSM. Patient-reported cosmetic outcome results were obtained. Results A total of 22 patients who received 23 R-NSM and IBR with Gel implant procedures were analyzed. The mean operation time for R-NSM was 118.8 ± 50.6 min, and 74.5 ± 26.6 min for Gel implant reconstruction. Docking time quickly dropped from 20 to 6–8 min, and the time needed to complete R-NSM was usually completed within 100 min after accumulation of case experience. Mean blood loss was 37 ± 38.2 mL, and the positive surgical margin rate was 0%. Three (13%) patients had transit nipple ischemia change, and no total nipple-areolar complex necrosis cases were observed. No local recurrence or mortality was found during a mean 6.9 ± 3.5 months of follow-up. All 22 patients were satisfied with the postoperative aesthetic outcome. Conclusion From our preliminary experience, R-NSM and IBR with Gel implant is a safe procedure, with good cosmetic results, and could be a promising new technique for breast cancer patients indicated for mastectomy.

Endoscopy-assisted breast surgery (EABS) performed through minimal axillary and/or periareolar incisions is a possible alternative to open surgery for certain patients with breast cancer. In this study, we report the early results of an EABS program in Taiwan. The medical records of patients who underwent EABS for breast cancer during the period May 2009 to December 2014 were collected from the Taiwan Endoscopic Breast Surgery Cooperative Group database. Data on clinicopathologic characteristics, type of surgery, method of breast reconstruction, complications and recurrence were analyzed to determine the effectiveness and oncologic safety of EABS in Taiwan. A total of 315 EABS procedures were performed in 292 patients with breast cancer, including 23 (7.8%) patients with bilateral disease. The number of breast cancer patients who underwent EABS increased initially from 2009 to 2012 and then stabilized during the period 2012-2014. The most commonly performed EABS was endoscopy-assisted total mastectomy (EATM) (85.4%) followed by endoscopy-assisted partial mastectomy (EAPM) (14.6%). Approximately 74% of the EATM procedures involved breast reconstruction, with the most common types of reconstruction being implant insertion and autologous pedicled TRAM flap surgery. During the six-year study period, there was an increasing trend in the performance of EABS for the management of breast cancer when total mastectomy was indicated. The positive surgical margin rate was 1.9%. Overall, the rate of complications associated with EABS was 15.2% and all were minor and wound-related. During a median follow-up of 26.8 (3.3-68.6) months, there were 3 (1%) cases of local recurrence, 1 (0.3%) case of distant metastasis and 1 (0.3%) death. The preliminary results from the EABS program in Taiwan show that EABS is a safe procedure and results in acceptable cosmetic outcome. These findings could help to promote this under-used surgical technique in the field of breast cancer.

BackgroundNew surgical innovations of nipple-sparing mastectomy (NSM), such as endoscopic NSM (E-NSM) or robotic NSM (R-NSM), were emerging. However, there was a lack of evidence comparing the effectiveness and safety in the management of breast cancer.MethodsA case–control comparison study was conducted for patients with breast cancer underwent E-NSM or R-NSM with immediate prosthesis breast reconstruction (IPBR) from July 2010 to February 2019 at a single institution to compare the clinical outcomes, learning curve, patient-reported cosmetic results, and medical cost.ResultsA total of 91 E-NSM and 40 R-NSM procedures were retrieved and analyzed. The surgical margin involvement rate in both R-NSM (2.5%) and E-NSM (4.4%) procedures were relatively low (P = 0.52). The R-NSM group was associated with higher satisfaction rates in terms of scar appearance, scar length, and surgical wound position compared with the E-NSM group. Compared with E-NSM, the R-NSM operation time took longer (241 ± 61 vs. 215 ± 70 min, P = 0.01), less blood loss (32 ± 29 vs. 79 ± 62 ml, P < 0.01), and higher medical cost (10,587 ± 554 vs. 6855 ± 936 U.S. dollars, P < 0.01). There was no statistically significant difference in nipple ischemia/necrosis or overall complication between R-NSM and E-NSM. In the learning curve analysis, it took the 27th procedure in E-NSM and 10th procedure in R-NSM to decrease operation time significantly.ConclusionsR-NSM was associated with higher wound-related satisfaction, lesser blood loss, and shorter learning curve compared with E-NSM, however, at the price of longer operation time and higher medical cost.

BackgroundThe preliminary results of an innovative surgical technique, which incorporated single-port three-dimensional (3D) videoscope and instruments for endoscopic nipple-sparing mastectomy (E-NSM), were reported.MethodsThe medical records of patients who underwent single-port 3D E-NSM for breast cancer from August 2018 to September 2020 were analyzed, and the preliminary outcome of this procedure as well as the patient-reported aesthetic results are described in this article.ResultsThe study enrolled 70 patients who received 80 procedures of single-port 3D E-NSM. The mean operation time was 158 ± 36 min, and the mean blood loss was 41 ± 26 ml. Three procedures (3.8 %) associated with delayed axillary wound-healing, eight cases of transient nipple ischemia (10 %), three cases of partial nipple ischemia/necrosis (3.7 %), and one case of total nipple-areolar complex (NAC) necrosis (1.3 %) were observed. No patient had margin involvement. Satisfaction rates of approximately 90 % were observed in terms of postoperative scar appearance, location, and length. Most of the patients (87.8 %) reported that they would choose the same operation again if given the chance to do so. The overall cost of a single-port 3D E-NSM was 7522 ± 470 U.S. dollars. According to cumulative sum (CUSUM) plot analysis, about 14 cases were needed for surgeons to familiarize themselves with single-port 3D E-NSM and immediate gel implant reconstruction and to decrease their operation time significantly in the initial learning phase.ConclusionSingle-port 3D E-NSM, a safe, efficient, lower-cost procedure, is associated with a good aesthetic result. It is a promising new technique for breast cancer patients indicated for mastectomy, but long-term oncologic safety follow-up evaluation still is needed.

In this study, an advanced semantic segmentation method and deep convolutional neural network was applied to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images, thereby facilitating image interpretation and diagnosis by providing radiologists an objective second opinion. A total of 684 images (380 benign and 308 malignant tumours) from 343 patients (190 benign and 153 malignant breast tumour patients) were analysed in this study. Six malignancy-related standardised BI-RADS features were selected after analysis. The DeepLab v3+ architecture and four decode networks were used, and their semantic segmentation performance was evaluated and compared. Subsequently, DeepLab v3+ with the ResNet-50 decoder showed the best performance in semantic segmentation, with a mean accuracy and mean intersection over union (IU) of 44.04% and 34.92%, respectively. The weighted IU was 84.36%. For the diagnostic performance, the area under the curve was 83.32%. This study aimed to automate identification of the malignant BI-RADS lexicon on breast ultrasound images to facilitate diagnosis and improve its quality. The evaluation showed that DeepLab v3+ with the ResNet-50 decoder was suitable for solving this problem, offering a better balance of performance and computational resource usage than a fully connected network and other decoders.

Hot flashes have been postulated to be linked to systemic inflammation. This study aimed to investigate the relationship between hot flashes, pro-inflammatory factors, and leukocytes in healthy, non-obese postmenopausal women. In this cross-sectional study, a total of 202 women aged 45-60 years were stratified into one of four groups according to their hot-flash status: never experienced hot flashes (Group N), mild hot flashes (Group m), moderate hot flashes (Group M), and severe hot flashes (Group S). Variables measured in this study included clinical parameters, hot flash experience, leukocytes, and fasting plasma levels of nine circulating cytokines/chemokines measured by using multiplex assays. Multiple linear regression analysis was used to evaluate the associations of hot flashes with these pro-inflammatory factors. The study was performed in a hospital medical center. The mean values of leukocyte number were not different between these four groups. The hot flash status had a positive tendency toward increased levels of circulating IL-6 (P-trend = 0.049), IL-8 (P-trend < 0.001), TNF-α (P-trend = 0.008), and MIP1β (P-trend = 0.04). Multivariate linear regression analysis revealed that hot-flash severity was significantly associated with IL-8 (P-trend < 0.001) and TNFα (P-trend = 0.007) among these nine cytokines/chemokines after adjustment for age, menopausal duration, BMI and FSH. Multivariate analysis further revealed that severe hot flashes were strongly associated with a higher IL-8 (% difference, 37.19%; 95% confidence interval, 14.98,63.69; P < 0.001) and TNFα (51.27%; 6.64,114.57; P < 0.05). The present study provides evidence that hot flashes are associated with circulating IL-8 and TNF-α in healthy postmenopausal women. It suggests that hot flashes might be related to low-grade systemic inflammation.

Background The aim of the current study was to report a single-institution experience using breast-conserving surgery after neoadjuvant chemotherapy (NACT), focusing on the association between microscopic resection margin status and locoregional recurrence (LRR). Methods Our institutional prospectively maintained database was reviewed to identify patients who were treated with NACT between January 2008 and April 2018. Results Among the main partial mastectomy specimens available for analysis ( n  = 161), 28 had margins < 1 mm, 21 had margin width of 1–2 mm and the remaining 112 had margins > 2 mm. LRR occurred in 16 patients (9.9%) and distant metastases were detected in 27 (16.8%) patients. There was no significant difference in the LRR between the > 2 mm margin group with a 60-month cumulative survival of 85.2% compared with 76.2% for the ≤2 mm group ( P =  0.335) in the Kaplan-Meier analysis. When we stratified patients by margin widths of ≥1 mm or <  1 mm, there was no LRR-free survival benefit observed for the ≥1 mm pathologic excision margin group in the univariate analysis (hazard ratio = 0.443; 95% confidence interval = 0.142–1.383; P =  0.161) with a 60-month cumulative LRR-free survival of 84.9% compared with 69.5% for the < 1 mm margin cohort ( P =  0.150). Conclusions In the absence of multiple scattered microscopic tumour foci, a negative margin of no ink on tumour maybe sufficient for stage I–III invasive breast cancer treated with NACT and breast-conserving surgery.

Women with unilateral breast cancer are at an increased risk for the development of contralateral breast cancers. We hypothesis that combined breast MRI would detect more contralateral synchronous breast cancer than conventional imaging alone, and resulted in less contralateral metachronous breast cancer during follow-up. We retrospectively collected two groups of breast cancer patients diagnosed from 2009 to 2013 for evaluating the effectiveness and value of adding pre-operative breast MRI to conventional breast images (mammography and sonography) for detection of contralateral synchronous breast cancer. The new metachronous contralateral breast cancer diagnosed during follow-up was prospectively evaluated and compared. Group A (n = 733) comprised patients who underwent conventional preoperative imaging and group B (n = 735) combined with MRI were enrolled and compared. Seventy (9.5%) of the group B patients were found to have contralateral lesions detected by breast MRI, and 65.7% of these lesions only visible with MRI. The positive predictive value of breast MRI detected contralateral lesions was 48.8%. With the addition of breast MRI to conventional imaging studies, more surgical excisions were performed in contralateral breasts (6% (44/735) versus 1.4% (10/733), P< 0.01), more synchronous contralateral breast cancer detected (2.9% (21/735) versus 1.1% (8/733), P = 0.02), and resulted in numerical less (2.2% (16/714) versus 3% (22/725), p = 0.3) metachronous contralateral breast cancer during a mean follow-up of 102 months. Our study provides useful estimates of the pre-operative breast MRI for the increased detection of contralateral synchronous breast cancer and less subsequent contralateral metachronous breast cancer.