Automated Deep Learning Empowered Breast Cancer Diagnosis Using Biomedical Mammogram Images

Biomedical image processing is a hot research topic which helps to majorly assist the disease diagnostic process. At the same time, breast cancer becomes the deadliest disease among women and can be detected by the use of different imaging techniques. Digital mammograms can be used for the earlier identification and diagnostic of breast cancer to minimize the death rate. But the proper identification of breast cancer has mainly relied on the mammography findings and results to increased false positives. For resolving the issues of false positives of breast cancer diagnosis, this paper presents an automated deep learning based breast cancer diagnosis (ADL-BCD) model using digital mammograms. The goal of the ADL-BCD technique is to properly detect the existence of breast lesions using digital mammograms. The proposed model involves Gaussian filter based pre-processing and Tsallis entropy based image segmentation. In addition, Deep Convolutional Neural Network based Residual Network (ResNet 34) is applied for feature extraction purposes. Specifically, a hyper parameter tuning process using chimp optimization algorithm (COA) is applied to tune the parameters involved in ResNet 34 model. The wavelet neural network (WNN) is used for the classification of digital mammograms for the detection of breast cancer. The ADL-BCD method is evaluated using a benchmark dataset and the results are analyzed under several performance measures. The simulation outcome indicated that the ADL-BCD model outperforms the state of art methods in terms of different measures.     

Mammographic Images Enhancement and Denoising for Breast Cancer Detection Using Dyadic Wavelet Processing

Mammography is the most effective method for the early detection of breast diseases. However, the typical diagnostic signs such as microcalcifications and masses are difficult to detect because mammograms are low-contrast and noisy images. In this paper, a novel algorithm for image denoising and enhancement based on dyadic wavelet processing is proposed. The denoising phase is based on a local iterative noise variance estimation. Moreover, in the case of microcalcifications, we propose an adaptive tuning of enhancement degree at different wavelet scales, whereas in the case of mass detection, we developed a new segmentation method combining dyadic wavelet information with mathematical morphology. The innovative approach consists of using the same algorithmic core for processing images to detect both microcalcifications and masses. The proposed algorithm has been tested on a large number of clinical images, comparing the results with those obtained by several other algorithms proposed in the literature through both analytical indexes and the opinions of radiologists. Through preliminary tests, the method seems to meaningfully improve the diagnosis in the early breast cancer detection with respect to other approaches.     

具有分割健壮性的超声图像分类方法探索

在早期癌症的发病表现中,肿块和微小钙化点是重要的特征和诊断依据.然而,病变可疑区域与正常组织区域之间的差别很小,并且肿块的边界和内部结构在超声图像上形态不一,与周围组织的差别也很细微,很难用人眼检查到,这样使得早期确诊变得比较困难.本文采用一种基于模糊数学理论的乳腺超声图像增强算法,经过增强处理之后,原先由于图像的模糊而隐藏的信息能够清晰的观察到,这也后后面的肿瘤的分割与分类打好基础.     

基于差影技术的乳腺微钙化点检测方法

目的 协助医生进行诊断，避免医生因大量阅片引起疲劳而造成误诊，提高乳腺癌早期诊断的效率和准确率。方法 先对乳腺钼靶X线照片数字化；再对数字化的乳腺影像归一化；然后从中选取感兴趣区域；最后利用差影技术检测出微钙化点并标示于影像中。结果 对于16幅（其中13幅含有微钙化）经过病理解剖确诊的乳腺钼靶片进行实验，利用本文方法共检测出14幅钙化图像。结论 该方法检出率高，微钙化点定位准确，值得进一步研究。     

Forty-Sixth Annual Exhibition of the Institute of Physics and the Physical Society

Abstract

The frequency histogram of connected elements (FHCE) is a recently proposed algorithm that has successfully been applied in various medical image segmentation tasks. The FHCE is based on the idea that most pixels belong to the same class as their neighbouring pixels. However, the FHCE performance relies to a great extent on the optimal selection of a threshold parameter. Since evaluating segmentation results is a highly subjective process, a collection of threshold values must typically be examined. No algorithm has been proposed to automate the determination of the threshold parameter value of the FHCE. This study presents a method based on the fuzzy C-means clustering algorithm, designed to automatically generate optimal threshold values for the FHCE. This new approach was applied as a part of a structured sequence of image processing steps in order to facilitate segmentation of microcalcifications in digitized mammograms. A unique threshold value was generated for each mammogram, taking into account the different grey-level patterns based on different compositions of various breast tissues in it. The segmentation algorithm was tested on 100 mammograms (50 collected from the Mammographic Image Analysis Society and 50 normal mammograms onto which a number of simulated microcalcifications were generated). The algorithm was able to detect subtle microcalcifications with sensitivity ranging from 93 to 98%, False alarm ratio from 3 to 5% and false negatives variability from 2 to 3%.     

Clinical image quality criteria for full field digital mammography: a first practical application

In order to quantify the clinical quality of full-field digital mammography, a set of image quality parameters is developed. The set consisted of 12 image quality criteria and 8 physical characteristics of the image. The first set interrogates the visibility of anatomical structures and typical characteristics of a digital image, such as noise and saturation of dark and white areas. The second set of criteria evaluates contrast, sharpness and confidence with the representation of masses, microcalcifications and the image. The use of these criteria is reported in a retrospective study, in which the impact of dose on the radiological quality of digital mammograms is evaluated. Fifty patients acquired in a low-dose mode were retrieved and compared with 50 patients acquired in a dose mode that was set 41% higher. The dose affects, more than expected, contrast and sharpness of the image, whereas the visibility of the anatomical structures remains unchanged. With these parameters, quantification of the image quality is possible; however, because of subjectivity of the parameters, only intra-observer comparison and evaluation of the individual parameters rather than the overall results are advised. Together with physical tests of image quality, critical radiological evaluation of the quality should be included in the acceptance process of digital mammography.     

Automatic breast cancer detection based on optimized neural network using whale optimization algorithm

Breast cancer is the second deadliest type of cancer. Early detection of breast cancer can considerably improve the effectiveness of treatment. A significant early sign of breast cancer is the mass. However, separating the cancerous masses from the normal portions of the breast tissue is usually a challenge for radiologists. Recently, because of the availability of high‐accuracy computing, computer‐aided detection systems based on image processing have become capable of accurately diagnosing the various types of cancers. The main purpose of this study is to utilize a powerful image segmentation method for the diagnosis of cancerous regions through mammography, based on a new configuration of the multilayer perceptron (MLP) neural network. The most popular method for minimizing the errors in an MLP neural network is backpropagation. However, this method has certain drawbacks, such as a low convergence speed and becoming trapped at the local minimum. In this study, a new training algorithm based on the whale optimization algorithm is proposed for the MLP network. This algorithm is capable of solving various problems toward the current algorithms for the analyzed systems. The proposed method is validated on the Mammographic Image Analysis Society database, which contains 322 digitized mammography images, and the Digital Database for Screening Mammography, which contains approximately 2500 digitized mammography images. To assess the detection performance of the proposed system, the correct detection rate, percentage of identification with false acceptance, and percentage of identification with false rejection were evaluated and compared using various methods. The results indicate that the proposed method is highly efficient and yields significantly better accuracy compared with other methods.     

A quantitative method for evaluating the detectability of lesions in digital mammography

This study presents a quantitative method for evaluating the detectability of microcalcifications in digital mammography. Four hundred and twenty microcalcifications (with various morphology, size and contrast), simulated with a previously validated method, were used for the creation of image datasets. Lesions were inserted into 163 regions of interests of 59 selected raw digital mammograms with various anatomical backgrounds and acquired with a Siemens Novation DR. After processing, these composite images were scored by experienced radiologists, who located multiple simulated lesions and rated them under conditions of free-search. For statistical analysis, free-response receiver-operating characteristic curves are plotted; the use of jackknife free-response receiver-operating characteristic method has also been investigated. The main advantage of this methodology is that the exact number of inserted microcalcifications is well known and that the lesions are fully characterised in terms of pathology, size, morphology and peak contrast. A first application has been the evaluation of the effect of anatomical background on microcalcifications detection. Preliminary findings in this study indicate that this method may be a promising tool to evaluate factors that have an influence on the detectability of lesions, such as the clinical processing or the viewing conditions.     

Fusion of local and global features for classification of abnormality in mammograms

Mammography is the most widely used tool for the early detection of breast cancer. Computer-based algorithms can be developed to improve diagnostic information in mammograms and assist the radiologist to improve diagnostic accuracy. In this paper, we propose a novel computer aided technique to classify abnormalities in mammograms using fusion of local and global features. The objective of this work is to test the effectiveness of combined use of local and global features in detecting abnormalities in mammograms. Local features used in the system are Chebyshev moments and Haralick’s gray level co-occurrence matrix based texture features. Global features used are Laws texture energy measures, Gabor based texture energy measures and fractal dimension. All types of abnormalities namely clusters of microcalcifications, circumscribed masses, spiculated masses, architectural distortions and ill-defined masses are considered. A support vector machine classifier is designed to classify the samples into abnormal and normal classes. It is observed that combined use of local and global features has improved classification accuracy from 88.75% to 93.17%.     

Mammographic mass segmentation using multichannel and multiscale fully convolutional networks

Breast cancer is one of the leading causes of death among women worldwide. Mammographic mass segmentation is an important task in mammogram analysis. This process, however, poses a prominent challenge considering that masses can be obscured in images and appear with irregular shapes and low image contrast. In this study, a multichannel, multiscale fully convolutional network is proposed and evaluated for mass segmentation in mammograms. To reduce the impact of surrounding unrelated structures, preprocessed images with a salient mass appearance are obtained as the second input channel of the network. Furthermore, to jointly conduct fine boundary delineation and global mass localization, we incorporate more crucial context information by learning multiscale features from different resolution levels. The performance of our segmentation approach is compared with that of several traditional and deep-learning-based methods on the popular DDSM and INbreast datasets. The evaluation indices consist of the Dice similarity coefficient, area overlap measure, area undersegmentation measure, area oversegmentation measure, and Hausdorff distance. The mean values of the Dice similarity coefficient and Hausdorff distance of our proposed segmentation method are 0.915 ± 0.031 and 6.257 ± 3.380, respectively, on DDSM and 0.918 ± 0.038 and 2.572 ± 0.956, respectively, on INbreast, which are superior to those of the existing methods. The experimental results verify that our proposed multichannel, multiscale fully convolutional network can reliably segment masses in mammograms.     

Measurement of the radiation dose and assessment of the risk in mammography screening for early detection of cancer of the breast, in Israel

The mean glandular doses to samples of women attending for mammographic screening are measured routinely at screening centres in Israel. As at present, no detailed and systematic data have been collected regarding the average glandular dose in mammography screening procedures carried out in Israel for the last 20 y. Especially data are lacking related to the glandular dose (GD) involved in mammography with the new digital mammography systems. In this work, partial results of the measurements are presented to asses the radiation dose to the breast and to the glandular tissue within the Israeli national mammography programme updated to year 2009.     

Organisational aspects of mammography screening in digital settings: first experiences of Luxembourg

Luxembourg has been conducting a breast cancer screening programme since 1992, like a large number of other European countries, as early detection and treatment of breast cancer have been proven to reduce mortality. The majority of these screening programmes are based on analogue X-ray technology and have optimised their organisation of transporting, archiving and reading with respect to films. Last decade is marked by enormous developments in digital mammography. Different technologies such as flat panel-, computed radiography- and scanning systems became available. Digital mammography is expected to have a major impact on quality and organisation of breast cancer screening programmes. Screening programmes are now faced with a huge challenge of incorporating the digital technology, including implementation of electronic image exchange, conception of new electronic workflow, establishing adapted quality assurance programmes and training of radiologists and technical personnel. Initial experiences of the Luxembourg approach in organising digital mammography screening and its quality assurance are reported.     

Using simple mathematical functions to simulate pathological structures--input for digital mammography clinical trial

In this study a set of structures has been simulated to represent a range of clinically relevant breast cancer mammographic lesions including solid tumours and microcalcifications. All structures have been created using simple random-based mathematical functions and have been inserted into a subset of digital mammography images at appropriate contrast levels into various regions of the breast, including dense fibroglandular and adipose tissue. These structures and their appearance in these clinical images were evaluated in terms of how realistic they looked. They will be used as the input to a large-scale clinical trial designed to examine the effect of significant dose reduction in digital mammography by comparing the detectability of such structures in images acquired at full and quarter automatic exposure control (AEC) dose level and in images with simulated noise levels in between.     

Can the average glandular dose in routine digital mammography screening be reduced? A pilot study using revised image quality criteria

There is a need for tools that in a simple way can be used for the evaluation of image quality related to clinical requirements in mammography. The aim of this work was to adjust the present European image quality criteria to be relevant also for digital mammography images, and to use as simple and as few criteria as possible. A pilot evaluation of the new set of criteria was made with mammograms of 28 women from a General Electric Senographe 2000D full-field digital mammography system. One breast was exposed using the standard automatic exposure mode, the other using about half of that absorbed dose. Three experienced radiologists evaluated the images using visual grading analysis technique. The results indicate that the new quality criteria can be used for the evaluation of image quality related to clinical requirements in digital mammography in a simple way. The results also suggest that absorbed doses for the mammography system used may be substantially reduced.     

提高时域乳腺光学层析成像质量的方法

时域乳腺光学层析成像技术可以有效重建乳腺组织的光学参数,实现乳腺癌的早期检测.为了提高重建图像的性能,针对图像重建过程中吸收系数和约化散射系数的雅克比矩阵间的量级差异,提出了一种有效的雅克比矩阵标定方法;为了克服不适定性因素对重建图像质量的影响,引入了图像分割技术实现对雅克比矩阵有效降维.实验数据的相关验证表明,上述两种方法可有效提高重建图像的质量.     

Teaching syllabus for radiological aspects of breast cancer screening with digital mammography

The purpose of this study is to discuss the content of our new accreditation programme for radiologists' reading digital mammograms in a screening setting and to report our first experience with the new course. The course consisted of a theoretical part, given by the medical physicist, and a practical part given by the radiologist. The practical session is closely linked with the theoretical part and a reading session. The material is fully digital and can be presented on different platforms. In practice, the need for parallel soft-copy reading sessions on high-end workstations limits the number of participants. A high level of interactivity was noted between teacher and participant, with a thorough discussion of different digital mammography systems during a single teaching course. The main challenge for the teacher turned out to be the collection of representative material and the continuous updating of the material: new systems, processing techniques and artefacts need to be included regularly.     

A high-resolution voxel phantom of the breast for dose calculations in mammography

Though mammography is one of the most sensitive methods to detect breast cancer, the benefit of the mammography screening programmes is still not clearly proven. One of the reasons is the radiation dose delivered by the examinations. Simulations of the radiation transport based on realistic breast phantoms are a useful tool to estimate the dose for the risk relevant parenchymal tissue. Specimens of real breasts have been fixated using a specially designed process while being compressed as in mammography. They have been scanned using the high-resolution mode of a CT. A segmentation has been carried out by assigning the voxels to different tissues. The resulting voxel phantom allows the assessment of tissue doses by Monte-Carlo calculations and can be used to simulate the diagnostic outcome of different imaging procedures. Three different tissues were separated: skin, adipose and 'breast tissue'. This allows reasonable calculations of the average glandular doses in mammography.     

Breast cancer screening with tomosynthesis--initial experiences

Experiences gained so far using tomosynthesis for breast cancer screening will be reported. A short summary of results from preparatory studies will also be presented. The sensitivity and specificity of breast tomosynthesis (BT) will be compared with conventional two-dimensional digital mammography (DM) for breast cancer screening in a population-based study. Over 2000 women have been examined so far with BT and DM. The BT reading is significantly more time-consuming than the DM reading. Preparatory studies have shown that BT has a higher diagnostic precision and higher accuracy of size measurements and stage determination than DM. There is potential to use lower compression force with BT compared with DM, without decreasing the diagnostic accuracy. BT might play an important role in clinical as well as screening mammography. A large-scale population-based study to investigate BT as a screening modality is underway.     

Deep learning and optimization algorithms for automatic breast cancer detection

Breast cancer is caused by the abnormal and rapid growth of breast cells. An early diagnosis can ensure an easier and effective treatment. A mass in the breast is a significant early sign of breast cancer, even though differentiating the cancerous mass's tissue from normal tissue for diagnosis is a difficult task for radiologists. The development of computer-aided detection systems in recent years has led to nondestructive and efficient cancer diagnostic techniques. This paper proposes a comprehensive method to locate the cancerous region in the mammogram image. This method employs image noise reduction, optimal image segmentation based on the convolutional neural network, a grasshopper optimization algorithm, and optimized feature extraction and feature selection based on the grasshopper optimization algorithm, thereby improving precision and decreasing the computational cost. This method was applied to the Mammographic Image Analysis Society Digital Mammogram Database and Digital Database for Screening Mammography breast cancer databases and the simulation results were compared with 10 different state-of-the-art methods to analyze the proposed system's efficiency. Final results showed that the proposed method had 96% Sensitivity, 93% Specificity, 85% PPV, 97% NPV, 92% accuracy, and better efficiency than other traditional methods in terms of Sensitivity, Specificity, PPV, NPV, and Accuracy.     

Diagnosis of breast cancer by analysis of sialic acid concentrations in human saliva by surface-enhanced Raman spectroscopy of silver nanoparticles

Breast cancer is the most common type of malignant tumor among women and their second leading cause of cancer-related deaths.The most common method for screening and diagnosis is mammography.Nonetheless,two main problems have been identified.First,the dose of radiation received during the test prevents the method from the use on women who are ＜ 40 years old.Second,there can be mammogram failure owing to the lack of tumor contrast with the fibrous tissue.Therefore,there is a need for screening methods that will help to identify high-risk cases.We developed a biological marker test that can help to identify them.Increased levels of sialic acid (SA) in saliva are known to correlated with breast cancer.In this study,we evaluated the feasibility of Raman spectroscopy as a method for quantification of SA in saliva,using citrate-reduced silver nanoparticles (cit-Ag-NPs) as a surface-enhanced Raman spectroscopy (SERS) substrate.Quantification of SA was accomplished by measuring its intensity in saliva and comparing it with a calibration curve of SA standards.The mean SA concentration in saliva was found to be significantly higher among 100 breast cancer patients (18.3 ± 9.4 mg·dL-1;mean ± SD) than among 106 healthy controls (3.5 ± 1.0 mg·dL-1).The SERS test showed sensitivity of 94％ and specificity 98％ for detection of patients with breast cancer,assuming that SA concentration ＞ 7 mg·dL-1 is a cutoff for positive test results.Our findings prove the usefulness of this SERS technique as a simple,convenient,and highly sensitive method of quantitative analysis of SA in saliva.The simplicity of this nanotechnological test may help to substantially reduce the mortality among patients with breast cancer by providing women with a simple,noninvasive screening test that can be applied regardless of age or density of breast tissue.