Proposed Framework for Detection of Breast Tumors

Computer vision is one of the significant trends in computer science.It plays as a vital role in many applications,especially in the medical field.Early detection and segmentation of different tumors is a big challenge in the medical world.The proposed framework uses ultrasound images from Kaggle,applying five diverse models to denoise the images,using the best possible noise-free image as input to the U-Net model for segmentation of the tumor,and then using the Convolution Neural Network(CNN)model to classify whether the tumor is benign,malignant,or normal.The main challenge faced by the framework in the segmentation is the speckle noise.It’s is a multiplicative and negative issue in breast ultrasound imaging,because of this noise,the image resolution and contrast become reduced,which affects the diagnostic value of this imaging modality.As result,speckle noise reduction is very vital for the segmentation process.The framework uses five models such as Generative Adversarial Denoising Network(DGAN-Net),Denoising U-Shaped Net(D-U-NET),Batch Renormalization U-Net(Br-UNET),Generative Adversarial Network(GAN),and Nonlocal Neutrosophic ofWiener Filtering(NLNWF)for reducing the speckle noise from the breast ultrasound images then choose the best image according to peak signal to noise ratio(PSNR)for each level of speckle-noise.The five used methods have been compared with classical filters such as Bilateral,Frost,Kuan,and Lee and they proved their efficiency according to PSNR in different levels of noise.The five diverse models are achieved PSNR results for speckle noise at level(0.1,0.25,0.5,0.75),(33.354,29.415,27.218,24.115),(31.424,28.353,27.246,24.244),(32.243,28.42,27.744,24.893),(31.234,28.212,26.983,23.234)and(33.013,29.491,28.556,25.011)forDGAN,Br-U-NET,D-U-NET,GANand NLNWF respectively.According to the value of PSNR and level of speckle noise,the best image passed for segmentation using U-Net and classification usingCNNto detect tumor type.The experiments proved the quality ofU-Net and CNN in segmentation and classification respectively,since they achieved 95.11 and 95.13 in segmentation and 95.55 and 95.67 in classification as dice score and accuracy respectively.

Pre-Trained Deep Neural Network-Based Computer-Aided Breast Tumor Diagnosis Using ROI Structures

Deep neural network(DNN)based computer-aided breast tumor diagnosis(CABTD)method plays a vital role in the early detection and diagnosis of breast tumors.However,a Brightness mode(B-mode)ultrasound image derives training feature samples that make closer isolation toward the infection part.Hence,it is expensive due to a metaheuristic search of features occupying the global region of interest(ROI)structures of input images.Thus,it may lead to the high computational complexity of the pre-trained DNN-based CABTD method.This paper proposes a novel ensemble pretrained DNN-based CABTD method using global-and local-ROI-structures of B-mode ultrasound images.It conveys the additional consideration of a local-ROI-structures for further enhan-cing the pretrained DNN-based CABTD method’s breast tumor diagnostic performance without degrading its visual quality.The features are extracted at various depths(18,50,and 101)from the global and local ROI structures and feed to support vector machine for better classification.From the experimental results,it has been observed that the combined local and global ROI structure of small depth residual network ResNet18(0.8 in%)has produced significant improve-ment in pixel ratio as compared to ResNet50(0.5 in%)and ResNet101(0.3 in%),respectively.Subsequently,the pretrained DNN-based CABTD methods have been tested by influencing local and global ROI structures to diagnose two specific breast tumors(Benign and Malignant)and improve the diagnostic accuracy(86%)compared to Dense Net,Alex Net,VGG Net,and Google Net.Moreover,it reduces the computational complexity due to the small depth residual network ResNet18,respectively.

Dermatofibrosarcoma Protuberans—An Atypical Breast Tumor

A 49-year-old woman was referred to the Department of Plastic and Breast Surgery under suspicion of breast cancer after a mammogram revealed a self-discovered tumor in the lower part of her left breast. Clinical examination, mammography, and histopathological examination revealed that the original tumor in the left breast was benign, and an incidental malignant tumor, a dermatofibrosarcoma protuberans (DFSP), was found in the contralateral breast. DFSP is a rare and highly malignant entity that is often silent and difficult to diagnose, making a biopsy essential. Surgical treatment must be aggressive due to the high risk of recurrence, which constitutes a technical challenge. The patient underwent surgery using an oncoplastic approach with a volume-reducing technique to achieve the best possible therapeutic and aesthetic results. Therapeutic breast reduction was performed on the right breast and the tumor was removed within the resected tissue. A contralateral symmetrizing mammoplasty was also performed simultaneously. The patient was discharged without major complications, and no recurrence of the tumor was seen during the 30-month follow-up period. The surgical approach included alternative solutions in addition to conventional lumpectomy or mastectomy. A multidisciplinary, open-minded, and creative approach resulted in a satisfying outcome for this patient.

Ipsilateral breast tumor recurrence in early stage breast cancer patients treated with breast conserving surgery and adjuvant radiation therapy: Concordance of biomarkers and tumor location from primary tumor to in-breast tumor recurrence

BACKGROUND Patients with an in-breast tumor recurrence(IBTR)after breast-conserving therapy have a high risk of distant metastasis and disease-related mortality.Classifying clinical parameters that increase risk for recurrence after IBTR remains a challenge.AIM To describe primary and recurrent tumor characteristics in patients who experience an IBTR and understand the relationship between these characteristics and disease outcomes.METHODS Patients with stage 0-II breast cancer treated with lumpectomy and adjuvant radiation were identified from institutional databases of patients treated from 2003-2017 at our institution.Overall survival(OS),disease-free survival,and local recurrence-free survival(LRFS)were estimated using the Kaplan Meier method.We identified patients who experienced an isolated IBTR.Concordance of hormone receptor status and location of tumor from primary to recurrence was evaluated.The effect of clinical and treatment parameters on disease outcomes was also evaluated.RESULTS We identified 2164 patients who met the eligibility criteria.The median follow-up for all patients was 3.73[interquartile range(IQR)2.27-6.07]years.Five-year OS was 97.7%(95%CI:96.8%-98.6%)with 28 deaths;5-year LRFS was 98.0%(97.2-98.8)with 31 IBTRs.We identified 37 patients with isolated IBTR,19(51.4%)as ductal carcinoma in situ and 18(48.6%)as invasive disease,of whom 83.3%had an in situ component.Median time from initial diagnosis to IBTR was 1.97(IQR:1.03-3.5)years.Radiotherapy information was available for 30 of 37 patients.Median whole-breast dose was 40.5 Gy and 23 patients received a boost to the tumor bed.Twenty-five of thirty-two(78.1%)patients had concordant hormone receptor status,HER-2 receptor status,and estrogen receptor(ER)(P=0.006)and progesterone receptor(PR)(P=0.001)status from primary to IBTR were significantly associated.There were no observed changes in HER-2 status from primary to IBTR.The concordance between quadrant of primary to IBTR was 10/19[(62.2%),P=0.008].Tumor size greater than 1.5 cm(HR=0.44,95%CI:0.22-0.90,P=0.02)and use of endocrine therapy upfront(HR=0.36,95%CI:0.18-0.73,P=0.004)decreased the risk of IBTR.CONCLUSION Among patients with early stage breast cancer who had breast conserving surgery treated with adjuvant RT,ER/PR status and quadrant were highly concordant from primary to IBTR.Tumor size greater than 1.5 cm and use of adjuvant endocrine therapy were significantly associated with decreased risk of IBTR.

GubenyiliuⅡ inhibits breast tumor growth and metastasis associated with decreased heparanase expression and Akt phosphorylation

OBJECTIVE GubenyiliuⅡ(GYⅡ),a traditional Chinese medicine(TCM)formula used in our hospital,has shown beneficial effects in cancer patients.In this study,we investigated the molecular mechanisms underlying the beneficial effects of GYⅡon murine breast cancer models.METHODS Inhibition of tumor growth and metastasis was evaluated by assessment of tumor weight and analysis of bioluminescent signal after a homograft inoculation.Viability of cultured breast cancer cells was determined using MTT assay andreal-time cell analysis(RTCA).Cell migratory ability was evaluated by Transwell?assay and wound healing assay.Subsequently,the potential anti-tumor and anti-metastatic mechanism was investigated by Western blotting and Immunohistochemistry.RESULTS GYⅡshowed significant inhibitory effects on tumor growth and metastasis in the murine breast cancer model.And GYⅡsuppressed theproliferation of 4T1 and MCF-7 cells in a dose-dependent manner.A better inhibitory effect on 4T1 cells proliferation and migration was found in sub-fractions(SF)of GYⅡ.Moreover,heparanase expression and degree of angiogenesis were reduced in tumor tissues.Western blotting analysis showed decreased expression of heparanase and growth factors in the cells treated with GYⅡand its sub-fractions(SF2 and SF3),there by a reduction in phosphorylation of ERK and AKT.CONCLUSION GYⅡexerts anti-tumor growth and anti-metastatic effects on murine breast cancer model.Sub-fractions 2 and 3 exhibits higher potency of the anti-tumor activity that is,at least partly,associated with decreased heparanase and growth factor sexpression,which subsequently sup-pressed activation of ERK and AKT pathways.

Suspension state promotes extravasation of breast tumor cells by increasing integrin β1 expression

Mechanical microenvironment can strongly affect the metastatic efficiency of circulating tumor cells.However,the effect of suspension state on their extravasation and the mechanisms involved are still unclear.To explore the influence of suspension state on extravasation(including adhesion,spreading and transendothelial migration)of breast tumor cells and its relevant molecular mechanism,MDA-MB-231 cells were cultured on poly(2-hydroxyethyl methacrylate)coated 6-well plates to minic the suspension state.Suspension state promoted adhesion,spreading and transendothelial migration of MDA-MB-231 cells to EAhy926 endothelial cells(ECs)monolayer under both the static condition and 0.5 dyne/cm^(2) flow shear stress(FSS).The number of cells adhered to ECs monolayer reached 2.15(static condition,3 d)and 1.67(FSS,3 d)times,and the number of migration reached 10.60 times,respectively,as compared to that in adhesion state.Moreover,MDA-MB-231 cells knockdown of integrin β1 provoked poor adhesion and transendothelial migration,as compared with MDA-MB-231 cells.But it made no difference in cell spreading.Our results implied the increasing expression of integrin β1 induced by suspension culture promoted the adhesion and transendothelial migration of MDA-MB-231 cells,but had no significant influence on their spreading.

Expression of p53 and CD44 in Canine Breast Tumor

The p53 and CD44 expression of 10 cases in canine breast tumor were examined utilizing immunohistochemical assay with rabbit anti-mouse polyclonal antibodies against p53 or CD44, respectively. The p53 expression was significantly higher in malignant than in benign breast tumor. The expression of CD44 was not significantly different in malignant breast cancer and benign breast tumor. This suggests that p53 can be used as an indicator for animal prognosis.

Advances in the Diagnosis of Breast Tumor by Using Imaging Technology

Breast tumor is the most common tumor in the world. The most important method to reduce the mortality due to breast tumor is diagnosed and found as early as possible. Imaging technology is one of the most important means to help doctors diagnose tumor early. This paper first simply introduces the common imaging technology. Then the mechanism and application of the ultrasonic elastic imaging technology in the diagnosis of breast tumor are summarized and discussed detailly. The methods for image treatment are introduced also. At last the development trend is analyzed. It is shown that the ultrasonic imaging technology is the most convenient and the cheapest relative to other imaging technologies such as nuclear magnetic imaging (NMI) and computer tomography (CT). Especially the ultrasonic elastic imaging technology can provide not only imaging information but also mechanism parameters, which helps to improve the accuracy of diagnosis obviously. Therefore, the ultrasonic elastic imaging technology is worthy of being studied further. More effective image analysis method is required.

A Gaussian Multivariate Hidden Markov Model for Breast Tumor Diagnosis

The stage of a tumor is sometimes hard to predict, especially early in its development. The size and complexity of its observations are the major problems that lead to false diagnoses. Even experienced doctors can make a mistake in causing terrible consequences for the patient. We propose a mathematical tool for the diagnosis of breast cancer. The aim is to help specialists in making a decision on the likelihood of a patient’s condition knowing the series of observations available. This may increase the patient’s chances of recovery. With a multivariate observational hidden Markov model, we describe the evolution of the disease by taking the geometric properties of the tumor as observable variables. The latent variable corresponds to the type of tumor: malignant or benign. The analysis of the covariance matrix makes it possible to delineate the zones of occurrence for each group belonging to a type of tumors. It is therefore possible to summarize the properties that characterize each of the tumor categories using the parameters of the model. These parameters highlight the differences between the types of tumors.

ACETYLATOR PHENOTYPE AND ITS RELATIONSHIP TO BREAST TUMOR

The patterns of acetylator phenotypes has been determined in 102 women with breast tumors, including 25 with benign breast disease and 77 with breast cancer, and compared to that in 59 healthy controls. There was significant increase (16.2%) of rapid acetylators in 77 patients with breast cancer, P<0.05. As a result of the effect of therapy on the rate of acetylation, it was found that in 39 patients with breast cancer the level of acetylation was decreased after mastectomy. The difference of percentage acetylation between preoperation and post-operation was statistically significant, P<0.05. A similar change in 8 patients with breast cancer could be observed after chemotherapy, P<0.01. The results obtained in the present study indicated that there was a significant association between rapid phcnotype and breast cancer of women. The mastectomy or inhibition of tumor growth may bring about a decrease in the level of acetylation.

Application of T2~*-weighted first-pass perfusion imaging in the diagnosis of breast tumors

Objective:To study the diagnostic value of T2*-weighted first-pass perfusion imaging in breast tumors.Methods: We analyzed the magnetic resonance imaging(MRI)information along with the pathological and immunohistochemistry re- sults.Magnetic resonance imaging was performed in 28 patients with breast tumor.The time to signal intensity curves were generated according to the T2*-weighted first-pass perfusion imaging.The curve’s maximal signal intensity drop rate and maximal signal intensity decrease time were analyzed and compared with the pathological diagnoses after surgery.Results: Malignant breast lesions showed higher maximal signal intensity drop rate(44.69%±17.07 vs.17.22%±7.49,P<0.001) than benign lesions,but there was no significant difference of maximal signal decrease time between those two lesions(23.94 s±4.92 vs.20.02 s±6.83,P>0.05).Conclusion:The T2*-weighted first-pass perfusion imaging has enough sensitivity and specificity in breast tumor diagnosis.

Clinical utility of proton magnetic resonance spectroscopy in the diagnosis of breast tumors

Proton magnetic resonance spectroscopy (1H MRS) can provide specific biochemical information within breast lesions and the elevated composite choline concentration as a useful diagnostic tool has been used to distinguish malignant from benign breast lesions, early evaluate response to therapy and predict prognosis. However, several obstacles including poor spatial resolution, low signal-to-noise ratio (SNR), long acquisition time and the difficulty of "extra" lipid suppression may have a negative impact on the routine application of in vivo 1H MRS for human breast cancer. At present, optimization H MRS methodology for breast studies has been performed.

Study of Correlation Coefficient for Breast Tumor Detection in Microwave Tomography

In microwave tomography, it is necessary to increase the amount of diverse observation data for accurate image reconstruction of the dielectric properties of the imaging area. The multi-polarization method has been proposed as a suitable technique for the acquisition of a variety of observation data. While the effectiveness of employing multi-polarization to reconstruct images has been confirmed, the physical considerations related to image reconstruction have not been investigated. In this paper, a compact-sized imaging sensor using multi-polarization for breast cancer detection is presented. An analysis of the correlation coefficient of the received data of adjacent antennas was performed to interpret the imaging results. Numerical simulation results demonstrated that multi-polarization can reconstruct images better compared to single polarizations owing to its low correlation coefficient and condition number.

Protective antitumor immunity induced by tumor cell lysates conjugated with diphtheria toxin and adjuvant epitope in mouse breast tumor models

Cancer cell vaccine-based immunotherapy has received increasing interest in many clinical trials involving patients with breast cancer. Combining with appropriate adjuvants can enhance the weak immunogenic properties of tumor cell lysates (TCL). In this study, diphtheria toxin (DT) and two tandem repeats of mycobacterial heat shock protein 70 (mHSP70) fragment 407-426 (M2) were conjugated to TCL with glutaraldehyde, and the constructed cancer cell vaccine was named DT-TCL-M2. Subcutaneous injection of DT-TCL-M2in mice effectively elicited tumor-specific polyclonal immune responses, including humoral and cellular immune responses. High levels of antibodies against TCL were detected in the serum of immunized mice with ELISA and verified with Western blot analyses. The splenocytes from immunized mice showed potent cytotoxicity on Ehrlich ascites carcinoma cells. Moreover, the protective antitumor immunity induced by DT-TCL-M2 inhibited tumor growth in a mouse breast tumor model. DT-TCL-M2 also attenuated tumor-induced angiogenesis and slowed tumor growth in a mouse intradermal tumor model. These findings demonstrate that TCL conjugated with appropriate adjuvants induced effective antitumor immunity in vivo. Improvements in potency could further make cancer cell vaccines a useful and safe method for preventing cancer recurrence after resection.

Significance of ipsilateral breast tumor recurrence after breast conserving treatment: role of surgical removal

Objective： To analyze the pattern over time （dynamics） of further recurrence and death after ipsilateral breast tumor recurrence （IBTR） in breast cancer patients undergoing breast conserving treatment （BCT）. Methods： A total of 338 evaluable patients experiencing IBTR were extracted from a database of 3,293 patients undergoing BCT. The hazard rates for recurrence and mortality throughout 10 years of follow-up after IBTR were assessed and were compared to the analogous estimates associated to the primary treatment. Results： In a time frame with the time origin at the surgical treatment for IBTR, the hazard rate for further recurrence displays a bimodal pattern （peaks at the second and at the sixth year）. Patients receiving mastectomy for IBTR reveal recurrence and mortality dynamics similar to that of node positive （N＋） patients receiving mastectomy as primary surgery, apart from the first two-three years, when IBTR patients do worse. If the patients with time to IBTR longer than 2.5 years are considered, differences disappear. Conclusions： The recurrence and mortality dynamics following IBTR surgical removal is similar to the corresponding dynamics following primary tumor removal. In particular, patients with time to IBTR in excess of 2.5 years behave like N＋ patients following primary tumor removal. Findings may be suitably explained by assuming that the surgical manoeuvre required by IBTR treatment is able to activate a sudden growing phase for tumor foci most of which, as suggested by the systemic model of breast cancer, would have reached the clinical level according to their own dynamics.

Value of ultrasound elastography in detecting small breast tumors

Background Detecting small breast tumors is difficult for conventional ultrasound. The goal of this study was to assess the value of ultrasound elastography in characterizing small breast tumors and to compare its sensitivity, specificity and accuracy with conventional ultrasound. Methods A total of 308 breast tumors less than 2 cm in size from 283 in-hospital patients examined with both conventional ultrasound and ultrasound elastography were retrospectively analyzed. The results were compared to surgical pathology. Results There were 104 malignant and 204 benign lesions. The sensitivities of sonography and sonoelastography were similar （P 〈0.05）, and the sensitivity of the two modalities combined improved remarkably to 97.1%. The mean elastic score of malignant and benign tumors less than 2 cm were 3.76±1.01 and 1.73±0.99, respectively （P 〈0.05）, and the mean elastic score of the false-negative lesions on conventional ultrasound was 3.61±1.14. Conclusions Ultrasound elastography in combination with conventional ultrasound can improve the sensitivity for detecting small breast tumors. It is also valuable in detecting small malignant tumors which are difficult to diagnose with conventional ultrasound. Ultrasound elastography can be a useful adjunct to conventional ultrasound in diagnosing small breast tumors.

Structurally defined tandem-responsive nanoassemblies composed of dipeptide-based photosensitive derivatives and hypoxia-activated camptothecin prodrugs against primary and metastatic breast tumors

Substantial progress in the use of chemo-photodynamic nano-drug delivery systems(nanoDDS) for the treatment of the malignant breast cancer has been achieved. The inability to customize precise nanostructures, however, has limited the therapeutic efficacy of the prepared nano-DDS to date. Here,we report a structurally defined tandem-responsive chemo-photosensitive co-nanoassembly to eliminate primary breast tumor and prevent lung metastasis. This both-in-one co-nanoassembly is prepared by assembling a biocompatible photosensitive derivative(pheophorbide-diphenylalanine peptide, PPADA) with a hypoxia-activated camptothecin(CPT) prodrug [(4-nitrophenyl) formate camptothecin, NCPT]. According to computational simulations, the co-assembly nanostructure is not the classical core-shell type, but consists of many small microphase regions. Upon exposure to a 660 nm laser,PPA-DA induce high levels of ROS production to effectively achieve the apoptosis of normoxic cancer cells. Subsequently, the hypoxia-activated N-CPT and CPT spatially penetrate deep into the hypoxic region of the tumor and suppress hypoxia-induced tumor metastasis. Benefiting from the rational design of the chemo-photodynamic both-in-one nano-DDS, these nanomedicines exhibit a promising potential in the inhibition of difficult-to-treat breast tumor metastasis in patients with breast cancer.

Layer-Wise Pre-Training Low-Rank NMF Model for Mammogram-Based Breast Tumor Classification

Image-based breast tumor classification is an active and challenging problem.In this paper,a robust breast tumor classification framework is presented based on deep feature representation learning and exploiting available information in existing samples.Feature representation learning of mammograms is fulfilled by a modified nonnegative matrix factorization model called LPML-LRNMF,which is motivated by hierarchical learning and layer-wise pre-training(LP)strategy in deep learning.Low-rank(LR)constraint is integrated into the feature representation learning model by considering the intrinsic characteristics of mammograms.Moreover,the proposed LPML-LRNMF model is optimized via alternating direction method of multipliers and the corresponding convergence is analyzed.For completing classification,an inverse projection sparse representation model is introduced to exploit information embedded in existing samples,especially in test ones.Experiments on the public dataset and actual clinical dataset show that the classification accuracy,specificity and sensitivity achieve the clinical acceptance level.

Lesion Segmentation and Identification of Breast Tumor on Dynamic Contrast-Enhanced Magnetic Resonance Imaging

Dynamic contrast-enhanced magnetic resonance imaging(DCE-MRI) can show subtle lesion morphology, improve the display of lesion definitions, and objectively reflect the blood supply of breast tumors; it can also reflect different strengthening patterns of normal tissues and lesion areas after medical tracer injection. DCE-MRI has become an important basis for the clinical diagnosis of breast cancer. To DCE-MRI data acquired from several hospitals across multiple provinces, a series of in-silico computational methods were applied for lesion segmentation and identification of breast tumor in this paper. The image segmentation methods include Otsu segmentation of subtraction images, signal-interference-ratio segmentation method and an improved variational level set method,each has its own application scope. After that, the distribution of benign and malignant in lesion region is identified based on three-time-point theory. From the experiment, the analysis of DCE-MRI data of breast tumor can show the distribution of benign and malignant in lesion region, provide a great help for clinicians to diagnose breast cancer more expediently and lay a basis for medical diagnosis and treatment planning.

COMBINED EFFECTS OF METRONOMIC ZOLEDRONATE WITH CORIOLUS VERSICOLOR IN A METASTATIC BREAST TUMOR MOUSE MODEL

Incidence of breast cancer is high in women worldwide and mortality usually results from tumor metastasis.Adjuvant chemotherapeutic,such as zoledronate(ZOL),has been used in metastatic breast cancer mainly for skeletal protection.Our previous studies demonstrated that Coriolus versicolor(CV)aqueous extract exhibited anti-tumor