Performance In Breast Cancer Research Articles

A multi-task framework for breast cancer segmentation and classification in ultrasound imaging

Background:Ultrasound (US) is a medical imaging modality that plays a crucial role in the early detection of breast cancer. The emergence of numerous deep learning systems has offered promising avenues for the segmentation and classification of breast cancer tumors in US images. However, challenges such as the absence of data standardization, the exclusion of non-tumor images during training, and the narrow view of single-task methodologies have hindered the practical applicability of these systems, often resulting in biased outcomes. This study aims to explore the potential of multi-task systems in enhancing the detection of breast cancer lesions. Methods:To address these limitations, our research introduces an end-to-end multi-task framework designed to leverage the inherent correlations between breast cancer lesion classification and segmentation tasks. Additionally, a comprehensive analysis of a widely utilized public breast cancer ultrasound dataset named BUSI was carried out, identifying its irregularities and devising an algorithm tailored for detecting duplicated images in it. Results:Experiments are conducted utilizing the curated dataset to minimize potential biases in outcomes. Our multi-task framework exhibits superior performance in breast cancer respecting single-task approaches, achieving improvements close to 15% in segmentation and classification. Moreover, a comparative analysis against the state-of-the-art reveals statistically significant enhancements across both tasks. Conclusion:The experimental findings underscore the efficacy of multi-task techniques, showcasing better generalization capabilities when considering all image types: benign, malignant, and non-tumor images. Consequently, our methodology represents an advance towards more general architectures with real clinical applications in the breast cancer field.

Epithelial cell-related prognostic risk model in breast cancer based on single-cell and bulk RNA sequencing

ObjectiveThis study aims to construct an epithelial cell-related prognostic risk model for breast cancer (BRCA) and explore its significance. MethodsGSE42568, GSE10780, GSE245601, and TCGA-BRCA datasets were sourced from public databases. Epithelial cell-related differentially expressed genes were identified using single-cell data analysis. Venn diagrams determined the intersecting genes between epithelial cell-related and BRCA-related genes. Batch Kaplan-Meier (K-M) survival analysis identified core intersecting genes for BRCA overall survival. Consensus clustering, enrichment, LASSO, and COX regression analyses were performed on the core intersecting genes, and then a prognostic risk model was constructed. The diagnostic and prognostic effectiveness of the risk model was subsequently evaluated and immune infiltration analysis was conducted. Finally, qRT-PCR was used to verify the expression of genes in the risk model. ResultsThere were 374 intersecting genes between epithelial cell-related and BRCA-related genes, among which 51 core intersecting genes were associated with BRCA prognosis. Consensus clustering categorized TCGA-BRCA into C1 and C2, with shared regulation of the estrogen signaling pathway. Three genes (DIRC3, SLC6A2, TUBA3D) were independent predictors of BRCA prognosis, forming the basis for a risk model. Except for exhibiting satisfactory diagnostic efficacy, the risk score elevation correlated with poor prognosis, elevated matrix, immune, and ESTIMATE scores, and negative correlation with microsatellite instability. The in vitro results confirmed the differential expression levels of DIRC3, SLC6A2, and TUBA3D. ConclusionThe prognostic risk model associated with epithelial cells demonstrates effective diagnostic performance in BRCA, serving as an independent prognostic factor for BRCA patients. Additionally, it exhibits a correlation with immune scores.

Abstract PO5-14-08: External Reproducibility of PD-L1 IHC 22C3 pharmDx on Breast Cancer Specimens at CPS ≥ 1 and CPS ≥ 10 Cutoffs

Abstract Background: PD-L1 IHC 22C3 pharmDx is an approved companion diagnostic for pembrolizumab treatment in triple-negative breast cancer (TNBC). Clinical evidence for pembrolizumab approval in TNBC was demonstrated by KEYNOTE-355 (NCT02819518), which investigated the clinical validity of PD-L1 IHC 22C3 pharmDx in identifying patients with PD-L1 expressing Combined Positive Score (CPS) ≥ 10 in previously untreated locally recurrent unresectable or metastatic TNBC.1 The role of immune checkpoint inhibitors for breast cancer as a whole is not as well defined as it is for TNBC. In this study, we show evidence of the reproducibility of PD-L1 IHC 22C3 pharmDx in PD-L1 expression determination in breast cancer specimens at the CPS ≥ 1 and CPS ≥ 10 cutoffs documenting robust assay performance in breast cancer. Methods: A blinded, randomized study was conducted at three external sites using formalin-fixed, paraffin-embedded breast cancer specimens. Reproducibility of PD-L1 IHC 22C3 pharmDx was assessed at the inter-site, intra-site/inter-day, inter-observer, and intra-observer endpoints at the CPS ≥ 1 and CPS ≥ 10 cutoffs. To assess inter-site and intra-site reproducibility, five replicate sets of pre-qualified unstained specimens were stained and evaluated at each of the three external sites. To assess inter-observer and intra-observer reproducibility, one set of pre-stained specimens was evaluated three times by each of three external pathologists. Negative percent agreement (NPA), positive percent agreement (PPA), and overall percent agreement (OA), based on comparisons to consensus diagnostic outcome, were computed with corresponding two-sided 95% percentile bootstrap confidence intervals. Acceptance criteria required at least 85.0% for the lower-bound (LB) of the two-sided 95% confidence interval (CI) on NPA, PPA, and OA for all endpoints. Results: All but one endpoint in the external reproducibility study met pre-determined acceptance criteria. Both the inter- and intra-site reproducibility endpoints had 95% CI LB values of 98.8% for NPA, 95.9% for PPA, and 97.9% OA at the CPS ≥ 1 cutoff. At the CPS ≥ 10 cutoff, the inter-site reproducibility endpoint had 95% CI LB values of 88.0% for NPA, 87.1% for PPA, and 89.5% OA, and the intra-site reproducibility endpoint had 95% CI LB values of 96.7% for NPA, 92.2% for PPA, and 95.6% OA. The inter-observer reproducibility endpoint had 95% CI LB values of 95.3% for NPA, 92.3% for PPA, and 94.7% OA at the CPS ≥ 1 cutoff. At the CPS ≥ 10 cutoff, the inter-observer reproducibility endpoint had 95% CI LB values of 84.9% for NPA, 86.8% for PPA, and 87.3% OA. The intra-observer reproducibility endpoint had 95% CI LB values of 97.0% for NPA, 95.0% for PPA, and 96.6% OA at the CPS ≥ 1 cutoff. At the CPS ≥ 10 cutoff, the intra-observer reproducibility endpoint had 95% CI LB values of 92.2% for NPA, 89.2% for PPA, and 91.7% OA. Conclusions: Acceptance criteria were met for all endpoints in the breast cancer external reproducibility study of PD-L1 IHC 22C3 pharmDx at the CPS ≥ 1 and CPS ≥ 10 cutoffs, except for inter-observer at the CPS ≥ 10 cutoff, which had a 95% CI LB value of 84.9% for NPA.

Transcriptional intra-tumour heterogeneity predicted by deep learning in routine breast histopathology slides provides independent prognostic information

BackgroundIntra-tumour heterogeneity (ITH) causes diagnostic challenges and increases the risk for disease recurrence. Quantification of ITH is challenging and has not been demonstrated in large studies. It has previously been shown that deep learning can enable spatially resolved prediction of molecular phenotypes from digital histopathology whole slide images (WSIs). Here we propose a novel method (Deep-ITH) to predict and measure ITH, and we evaluate its prognostic performance in breast cancer. MethodsDeep convolutional neural networks were used to spatially predict gene-expression (PAM50 set) from WSIs. For each predicted transcript, 12 measures of heterogeneity were extracted in the training data set (N = 931). A prognostic score to dichotomise patients into Deep-ITH low- and high-risk groups was established using an elastic-net regularised Cox proportional hazards model (recurrence-free survival). Prognostic performance was evaluated in two independent data sets: SöS-BC-1 (N = 1358) and SCAN-B-Lund (N = 1262). ResultsWe observed an increase in risk of recurrence in the high-risk group with hazard ratio (HR) 2.11 (95%CI:1.22–3.60; p = 0.007) using nested cross-validation. Subgroup analyses confirmed the prognostic performance in oestrogen receptor (ER)-positive, human epidermal growth factor receptor 2 (HER2)-negative, grade 3, and large tumour subgroups. The prognostic value was confirmed in the independent SöS-BC-1 cohort (HR=1.84; 95%CI:1.03–3.3; p = 3.99 ×10−2). In the other external cohort, significant HR was observed in the subgroup of histological grade 2 patients, as well as in the subgroup of patients with small tumours (<20 mm). ConclusionWe developed a novel method for an automated, scalable, and cost-efficient measure of ITH from WSIs that provides independent prognostic value for breast cancer. SignificanceTranscriptional ITH predicted by deep learning models enables prediction of patient survival from routine histopathology WSIs in breast cancer.

Discovering Breast Cancer Biomarkers Candidates through mRNA Expression Analysis Based on The Cancer Genome Atlas Database.

Background: Research on the discovery of tumor biomarkers based on big data analysis is actively being conducted. This study aimed to secure foundational data for identifying new biomarkers of breast cancer via breast cancer datasets in The Cancer Genome Atlas (TCGA). Methods: The mRNA profiles of 526 breast cancer and 60 adjacent non-cancerous breast tissues collected from TCGA datasets were analyzed via MultiExperiment Viewer and GraphPad Prism. Diagnostic performance was analyzed by identifying the pathological grades of the selected differentially expressed (DE) mRNAs and the expression patterns of molecular subtypes. Results: Via DE mRNA profile analysis, we selected 14 mRNAs with downregulated expression (HADH, CPN2, ADAM33, TDRD10, SNF1LK2, HBA2, KCNIP2, EPB42, PYGM, CEP68, ING3, EMCN, SYF2, and DTWD1) and six mRNAs with upregulated expression (ZNF8, TOMM40, EVPL, EPN3, AP1M2, and SPINT2) in breast cancer tissues compared to that in non-cancerous tissues (p < 0.001). Conclusions: In total, 20 DE mRNAs had an area under cover of 0.9 or higher, demonstrating excellent diagnostic performance in breast cancer. Therefore, the results of this study will provide foundational data for planning preliminary studies to identify new tumor biomarkers.

Histopathological image recognition of breast cancer based on three-channel reconstructed color slice feature fusion

Although computer-aided diagnosis (CAD) have shown excellent performance in Breast cancer (BC) histopathological image, it commonly requires a high-level network, and the recognition efficiency is frequently unsatisfied due to the complex structure of histopathological image. In this study, a ten-layers convolutional neural network (CNN) model called “ColorDeep” is used to extract color features corresponding to the different tissue parts in cell, pure color image slices obtained by a three-channel separation and reconstruction method are used as model input. Two models are tested on the BreaKHis dataset show that images under four magnifications achieved the recognition accuracy of 96.89%–99.67% at the image level, which is better than many state-of-the-art methods. The characteristics contained by the B channel have the largest effect on BC recognition, and compared to other research results, the proposed model improves the recognition speed on a single image by about 0.1s. More importantly, instead of using large histopathological images to input into the model for BC diagnosis, and instead of segmenting the nuclei, only the reconstructed B-channel features containing the nuclei region in the stained BC image need to be input into the model to enable accurate diagnosis of BC.

Circadian PERformance in breast cancer: a germline and somatic genetic study of PER3VNTR polymorphisms and gene co-expression

Polymorphisms in the PER3 gene have been associated with several human disease phenotypes, including sleep disorders and cancer. In particular, the long allele of a variable number of tandem repeat (VNTR) polymorphism has been previously linked to an increased risk of breast cancer. Here we carried out a combined germline and somatic genetic analysis of the role of the PER3VNRT polymorphism in breast cancer. The combined data from 8284 individuals showed a non-significant trend towards increased breast cancer risk in the 5-repeat allele homozygous carriers (OR = 1.17, 95% CI: 0.97–1.42). We observed allelic imbalance at the PER3 locus in matched blood and tumor DNA samples, showing a significant retention of the long variant (risk) allele in tumor samples, and a preferential loss of the short repetition allele (p = 0.0005). Gene co-expression analysis in healthy and tumoral breast tissue samples uncovered significant associations between PER3 expression levels with those from genes which belong to several cancer-associated pathways. Finally, relapse-free survival (RFS) analysis showed that low expression levels of PER3 were linked to a significant lower RSF in luminal A (p = 3 × 10−12) but not in the rest of breast cancer subtypes.

Identification of MicroRNAs as Diagnostic Biomarkers for Breast Cancer Based on the Cancer Genome Atlas.

Breast cancer is the most common cancer among women worldwide. MicroRNAs (miRNAs or miRs) play an important role in tumorigenesis, and thus, they have been identified as potential targets for translational research with diagnostic, prognostic, and therapeutic markers. This study aimed to identify differentially expressed (DE) miRNAs in breast cancer using the Cancer Genome Atlas. The miRNA profiles of 755 breast cancer tissues and 86 adjacent non-cancerous breast tissues were analyzed using Multi Experiment Viewer; miRNA–mRNA network analyses and constructed KEGG pathways with the predicted target genes were performed. The clinical relevance of miRNAs was investigated using area under the receiver operating characteristic curve (AUC) analysis, sensitivity, and specificity. The analysis identified 28 DE miRNAs in breast cancer tissues, including nine upregulated and 19 downregulated miRNAs, compared to non-cancerous breast tissues (p < 0.001). The AUC for each DE miRNA, miR-10b, miR-21, miR-96, miR-99a, miR-100, miR-125b-1, miR-125b-2, miR-139, miR-141, miR-145, miR-182, miR-183, miR-195, miR-200a, miR-337, miR-429, and let-7c, exceeded 0.9, indicating excellent diagnostic performance in breast cancer. Moreover, 1381 potential target genes were predicted using the prediction database tool, miRNet. These genes are related to PD-L1 expression and PD-1 checkpoint in cancer, MAPK signaling, apoptosis, and TNF pathways; hence, they regulate the development, progression, and immune escape of cancer. Thus, these 28 miRNAs can serve as prospective biomarkers for the diagnosis of breast cancer. Taken together, these results provide insight into the pathogenic mechanisms and potential therapies for breast cancer.

Automatic detection of squamous cell carcinoma metastasis in esophageal lymph nodes using semantic segmentation.

Esophageal squamous cell carcinoma (ESCC) is more prevalent than esophageal adenocarcinoma in Asia, especially in China, where more than half of ESCC cases occur worldwide. Many studies have reported that the automatic detection of lymph node metastasis using semantic segmentation shows good performance in breast cancer and other adenocarcinomas. However, the detection of squamous cell carcinoma metastasis in hematoxylin‐eosin (H&E)‐stained slides has never been reported. We collected a training set of 110 esophageal lymph node slides with metastasis and 132 lymph node slides without metastasis. An iPad‐based annotation system was used to draw the contours of the cancer metastasis region. A DeepLab v3 model was trained to achieve the best fit with the training data. The learned model could estimate the probability of metastasis. To evaluate the effectiveness of the detection model of learned metastasis, we used another large cohort of clinical H&E‐stained esophageal lymph node slides containing 795 esophageal lymph nodes from 154 esophageal cancer patients. The basic authenticity label for each slide was confirmed by experienced pathologists. After filtering isolated noise in the prediction, we obtained an accuracy of 94%. Furthermore, we applied the learned model to throat and lung lymph node squamous cell carcinoma metastases and achieved the following promising results: an accuracy of 96.7% in throat cancer and an accuracy of 90% in lung cancer. In this work, we organized an annotated dataset of H&E‐stained esophageal lymph node and trained a deep neural network to detect lymph node metastasis in H&E‐stained slides of squamous cell carcinoma automatically. Moreover, it is possible to use this model to detect lymph nodes metastasis in squamous cell carcinoma from other organs. This study directly demonstrates the potential for determining the localization of squamous cell carcinoma metastases in lymph node and assisting in pathological diagnosis.

A lymph node metastasis‐related protein‐coding genes combining with long noncoding RNA signature for breast cancer survival prediction

Integrating protein-coding gene (PCG) with long noncoding RNA (lncRNA) expression profiles, our aim is to identify a multidimensional transcriptome model that can predict individual prognosis of patients with breast cancer (BRCA). After diverse bioinformatics and statistical analyses, we obtained gene expression profiles of 1,016 BRCA samples from Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) database, and constructed a prognostic signature, which is composed of four PCGs (TFCP2, LRRC75B, PROSER2, and STOML1) and one lncRNA (AL355592.1). In the training set, the multidimensional transcriptome signature could part patients withBRCA into two groups with different survival, defined as high- and low-risk group by Kaplan-Meier (KM) analysis (p < 0.001). In the other five validation datasets, the PCG-lncRNA signature showed a similar predictive performance in BRCA by KM (p < 0.05). The prognostic independence for the PCG-lncRNA model was verified by the multivariable Cox regression analysis. Because Chi-squared test showed the signature was associated with lymph node metastasis status, stratification analysis found that it could further subdivide lymph node metastasis status more precisely in BRCA. The function analysis suggested that the genes from the signature were associated with immunity-related pathways. In summary, we constructed a PCG-lncRNA signature, which could accurately predict survival in patients with BRCA.

Comparison of different functional prediction scores using a gene-based permutation model for identifying cancer driver genes

BackgroundIdentifying cancer driver genes (CDG) is a crucial step in cancer genomic toward the advancement of precision medicine. However, driver gene discovery is a very challenging task because we are not only dealing with huge amount of data; but we are also faced with the complexity of the disease including the heterogeneity of background somatic mutation rate in each cancer patient. It is generally accepted that CDG harbor variants conferring growth advantage in the malignant cell and they are positively selected, which are critical to cancer development; whereas, non-driver genes harbor random mutations with no functional consequence on cancer. Based on this fact, function prediction based approaches for identifying CDG have been proposed to interrogate the distribution of functional predictions among mutations in cancer genomes (eLS 1–16, 2016). Assuming most of the observed mutations are passenger mutations and given the quantitative predictions for the functional impact of the mutations, genes enriched of functional or deleterious mutations are more likely to be drivers. The promises of these methods have been continually refined and can therefore be applied to increase accuracy in detecting new candidate CDGs. However, current function prediction based approaches only focus on coding mutations and lack a systematic way to pick the best mutation deleteriousness prediction algorithms for usage.ResultsIn this study, we propose a new function prediction based approach to discover CDGs through a gene-based permutation approach. Our method not only covers both coding and non-coding regions of the genes; but it also accounts for the heterogeneous mutational context in cohort of cancer patients. The permutation model was implemented independently using seven popular deleteriousness prediction scores covering splicing regions (SPIDEX), coding regions (MetaLR, and VEST3) and pan-genome (CADD, DANN, Fathmm-MKL coding and Fathmm-MKL noncoding). We applied this new approach to somatic single nucleotide variants (SNVs) from whole-genome sequences of 119 breast and 24 lung cancer patients and compared the seven deleteriousness prediction scores for their performance in this study.ConclusionThe new function prediction based approach not only predicted known cancer genes listed in the Cancer Gene Census (CGC), but also new candidate CDGs that are worth further investigation. The results showed the advantage of utilizing pan-genome deleteriousness prediction scores in function prediction based methods. Although VEST3 score, a deleteriousness prediction score for missense mutations, has the best performance in breast cancer, it was topped by CADD and Fathmm-MKL coding, two pan-genome deleteriousness prediction scores, in lung cancer.

The Relationship between Knowledge, Attitude, and Performance in Breast Cancer with Nutritional Behaviors and Drug Use

Breast cancer is the most common cancer in women, and tobacco and alcohol usage as well as inappropriate diet are some risk factors for developing this cancer. On the other hand, breast self-examination is a simple, effective, and cheap method for screening and early detection of breast cancer that is accessible for most of women. The aim of this study was to assess the correlation between knowledge, attitude, and performance in the case of breast cancer, with nutritional behaviors and tobacco use. In this descriptive-analytical study, studied population was all women over 15 years old, who were referred to health and treatment center of Buin-Zahra in 2018. The sample size was 250 cases according to a pilot study. Sampling method was random simple sampling, and data were collected using interview method. Data collection tool included two questionnaires (questionnaire of knowledge, attitude, and performance in the case of breast cancer, and questionnaire of life style in the case of tobacco use and diet). Collected data entered SPSS 25 software and Pearson’s correlation test, T-test, and ANOVA were used for data analysis. Most of the studied cases were in 26-30 years old age group (32.8%). 54.8% had diploma, 88% were married, and 90.8% were house-wives. It was indicated that 7% of cases had monthly self-examination and 82.8% had no mammography experience. There was a positive correlation between knowledge and performance about breast cancer, and nutritional status. There were also a significant correlation between age and performance (p-value: 0.044), education level and knowledge (p-value: 0.003), and attitude (p-value: 0.029), marriage status and performance (p-value: 0.002), and occupational type and performance (p-value: 0.001). It is shown that there is a significant correlation between education level, knowledge and attitude. So, it is recommended that educational effective programs should be used in the health and treatment centers to increase the level of knowledge and attitude of women about breast cancer, and to alter life style pattern in the case of tobacco use (as an environmental factor), and to alter nutritional pattern.

The Relationship between Knowledge, Attitude, and Performance in Breast Cancer with Nutritional Behaviors and Drug Use

Breast cancer is the most common cancer in women, and tobacco and alcohol usage as well as inappropriate diet are some risk factors for developing this cancer. On the other hand, breast self-examination is a simple, effective, and cheap method for screening and early detection of breast cancer that is accessible for most of women. The aim of this study was to assess the correlation between knowledge, attitude, and performance in the case of breast cancer, with nutritional behaviors and tobacco use. In this descriptive-analytical study, studied population was all women over 15 years old, who were referred to health and treatment center of Buin-Zahra in 2018. The sample size was 250 cases according to a pilot study. Sampling method was random simple sampling, and data were collected using interview method. Data collection tool included two questionnaires (questionnaire of knowledge, attitude, and performance in the case of breast cancer, and questionnaire of life style in the case of tobacco use and diet). Collected data entered SPSS 25 software and Pearson’s correlation test, T-test, and ANOVA were used for data analysis. Most of the studied cases were in 26-30 years old age group (32.8%). 54.8% had diploma, 88% were married, and 90.8% were house-wives. It was indicated that 7% of cases had monthly self-examination and 82.8% had no mammography experience. There was a positive correlation between knowledge and performance about breast cancer, and nutritional status. There were also a significant correlation between age and performance (p-value: 0.044), education level and knowledge (p-value: 0.003), and attitude (p-value: 0.029), marriage status and performance (p-value: 0.002), and occupational type and performance (p-value: 0.001). It is shown that there is a significant correlation between education level, knowledge and attitude. So, it is recommended that educational effective programs should be used in the health and treatment centers to increase the level of knowledge and attitude of women about breast cancer, and to alter life style pattern in the case of tobacco use (as an environmental factor), and to alter nutritional pattern.

Antibody-drug conjugates: Principles and clinical results in breast cancer treatment

Antibody-drug conjugates (ADCs) are consisted of the combination of highly specific monoclonal antibodies (mAbs) with conventional cytotoxic agents to particular cancer types. The use of mAbs that are specific to tumor cell-surface proteins allows highly selective accumulation of cytotoxic agents as ADCs at the tumor tissue, that is not achievable with conventional cytotoxic agents alone. Designing of effective ADCs for cancer treatment requires identification of an appropriate target, a mAb against the target, potent cytotoxic agents and conjugation of the mAb to cytotoxic agents. Until now, three ADCs including Gemtuzumab ozogamicin, Brentuximab and trastuzumab emtansine have received an FDA approval so far. These three ADCs have shown improved efficacy and safety data compared with standard chemotherapy for the treatment of patients of acute myeloid leukemia, advanced lymphoma and breast cancer, respectively. Moreover, several promising ADCs are now in the latter-phase of clinical testing. Thus, with special focusing on these new anti-cancer drugs, this review briefly describes the principles of ADCs including their structure and mechanism of action, and summarizes their clinical performance in breast cancer. Citation: Nguyen Phuong Loan, Duong Hong Quan, 2017. Antibody-drug conjugates: Principles and clinical results in breast cancer treatment. Tap chi Sinh hoc, 39(4): 489-493. DOI: 10.15625/0866-7160/v39n4.9327.*Corresponding author: quanvspt@gmail.comReceived 15 March 2017, accepted 12 December 2017

A comparison of methods for three-class mammograms classification.

Mammography is considered the gold standard for early breast cancer detection but it is very difficult to interpret mammograms for many reason. Computer aided diagnosis (CAD) is an important development that may help to improve the performance in breast cancer detection. We present a CAD system based on feature extraction techniques for detecting abnormal patterns in digital mammograms. Computed features based on gray-level co-occurrence matrices (GLCM) are used to evaluate the effectiveness of textural information possessed by mass regions. A total of 20 texture features are extracted from each mammogram. The ability of feature set in differentiating normal, benign and malign tissue is investigated using a Support Vector Machine (SVM) classifier, Naive Bayes classifier and K-Nearest Neighbor (k-NN) classifier. The efficiency of classification is provided using cross-validation technique. Support Vector Machine was originally designed for binary classification. We constructed a three-class SVM classifier by combining two binary classifiers and then compared his performance with classifiers intended for multi-class classification. To evaluate the classification performance, confusion matrix and Receiver Operating Characteristic (ROC) analysis were performed. Obtained results indicate that SVM classification results are better than the k-NN and Naive Bayes classification results, with accuracy ratio of 65% according to 51.6% and 38.1%, respectively.The unbalanced classification that occurs in all three classification tests is reason for unsatisfactory accuracy. Obtained experimental results indicate that the proposed three-class SVM classifier is more suitable for practical use than the other two methods.

The Relationship of Fatigue and Meaning in Life in Breast Cancer Survivors

To determine relationships among (a) cancer-related fatigue and meaning in life, (b) overall symptom distress and meaning in life, (c) fatigue and performance, and (d) overall symptom distress and performance in breast cancer survivors. Cross-sectional and correlational. Community-based setting in eastern Pennsylvania. 34 women who had completed their last treatment for breast cancer within the prior 16 months. Data were collected using the Piper Fatigue Scale (PFS), Life Attitude Profile-Revised (LAP-R), Memorial Symptom Assessment Scale-Short Form (MSAS-SF), and Medical Outcomes Study-Short Form 36 (SF-36). Fatigue and meaning in life. One moderate negative correlation was found between the PFS sensory subscale and the choice or responsibleness dimension of the LAP-R. Significant moderate to strong negative correlations were found between the MSAS-SF total score and two subscale scores and the existential transcendence dimension of the LAP-R. Significant moderate to strong negative correlations were found between four subscales of the SF-36 representing performance and the MSAS-SF total score. Meaning in life may influence fatigue and overall symptoms in breast cancer survivors. Assessment of meaning in life may be important in the management of fatigue and overall symptoms in women after treatment for breast cancer.

Leitlinien zur sozialmedizinischen Beurteilung der Leistungsfähigkeit bei Mammakarzinom

The following guidelines were developed for the medical assessment services of the German Pension Insurance Federal Institution. Starting from day-to-day practice, criteria and attributes to guide decisions for a systemisation of the sociomedical assessment of performance in breast cancer were compiled. The guidelines aim at standardising the sociomedical assessment of performance and help to make the decision-making process more transparent, e. g., for the assessment of applications for decreased earning capacity benefits. The guidelines summarise typical manifestations of breast cancer and describe the necessary medical information for the sociomedical assessment of performance. Relevant assessment criteria for the medical history, clinical examination, and for diagnostic tests are illustrated. The assessment of the individual's capacity is outlined, taking occupational factors into account. Following the determination of dysfunctions, the remaining abilities and disabilities, respectively, are deduced and compared with occupational demands. Finally, inferences are drawn regarding the occupational capacity of the individual.

Neurocognitive performance in breast cancer following exposure to adjuvant systemic therapy

Neurocognitive performance in breast cancer following exposure to adjuvant systemic therapy

Improving breast cancer diagnosis with computer-aided diagnosis

The purpose of this study was to test whether computer-aided diagnosis (CAD) can improve radiologists' performance in breast cancer diagnosis. The computer classification scheme used in this study estimates the likelihood of malignancy for clustered microcalcifications based on eight computer-extracted features obtained from standard-view mammograms. One hundred four histologically verified cases of microcalcifications (46 malignant, 58 benign) in a near-consecutive biopsy series were used in this study. Observer performance was measured on 10 radiologists who read the original standard- and magnification-view mammograms. The computer aid provided a percentage estimate of the likelihood of malignancy. Comparison was made between computer-aided performance and unaided (routine clinical) performance by using receiver operating characteristic (ROC) analysis and by comparing biopsy recommendations. The average ROC curve area (Az) increased from 0.61 without aid to 0.75 with the computer aid (P < .0001). On average, with the computer aid, each observer recommended 6.4 additional biopsies for cases with malignant lesions (P = .0006) and 6.0 fewer biopsies for cases with benign lesions (P = .003). This improvement corresponded to increases in sensitivity (from 73.5% to 87.4%), specificity (from 31.6% to 41.9%), and hypothetical positive biopsy yield (from 46% to 55%). CAD can be used to improve radiologists' performance in breast cancer diagnosis.