Mammogram Images Thresholding for Breast Cancer Detection Using Different Thresholding Methods

The purpose of this study is to apply different thresholding in mammogram images, and then we will determine which technique is the best in thresholding (extraction) malignant and benign tumors from the rest breast tissues. The used technique is Otsu method, because it is one of the most effective methods for most real world views with regard to uniformity and shape measures. Also, we present all the thresholding methods that used the concept of between class variance. We found from the experimental results that all the used thresholding techniques work well in detection normal breast tissues. But in abnormal tissues (breast tumors), we found that only neighborhood valley emphasis method gave best detection of malignant tumors. Also, the results demonstrate that variance and intensity contrast technique is the best in extraction the micro calcifications which represent the first signs of breast cancer.

Ultrasound Alongside with Mammogram in Women with Physically Dense Breast

We report usefulness of ultrasound used as an adjunct diagnostic tool to mammogram in routine annual checkup for women breasts of certain ages and breast mass. The purpose of breast imaging is to detect areas of tissue distortion and breast cancers. A mammogram is the common diagnostic imaging modality used to find breast diseases but sometimes the mammogram might not give the doctor enough information especially in women with dense breasts. As a result, the patient may be asked to undergo ultrasound or magnetic resonance imaging as a better mean of judgment to the case. Because ultrasound is widely used, simple and safe to patients we were encouraged to emphasis on exploring its role adjunct to mammogram. A retrospective observation study was done at the diagnostic radiology department at King Abdulaziz University Hospital (KAUH) in the period from January 2012 to June 2012;we covered all women with dense breasts in mammography and ultrasound units. The study group was 40 patients. All patients were imaged with both mammography and ultrasound. The statistical measures of accuracy, sensitivity and specificity were calculated using the SPSS program. The results we obtained suggest that age and the physical density of breast potentially affect mammogram images of women with 41 years or smaller with sensitivity 66% and specificity 68%. Therefore, we recommend using ultrasound alongside the mammogram?in women with dense breast for better diagnosis of small cancers that were not identified on mammography or clinical breast examination alone.

融合自注意力的乳腺钼靶图像特征引导分割算法

为提高对乳腺癌钼靶图像中病灶区域的识别精度,本研究设计了一种面向乳腺肿块和钙化区域分割的特征引导注意网络。首先,该网络通过特征提取模块学习乳腺组织的语义特征;其次,利用融合自校正注意力的解码模块,增强对病灶区域边缘信息的关注度,提高边界的清晰度;最后,采用特征引导注意模块增强通道的依赖关系,进一步还原病灶区域边缘细节,提高分割精度。实验结果表明,本研究网络在扩充后的INBreast1数据库中肿块和钙化分割的平均骰子系数(mDice)分别达到了0.971和0.888,在DDSM数据库肿块分割的mDice达到了0.911,优于其他常规的分割模型,对乳腺癌的早期诊断和治疗具有重要意义。

基于Attention U-Net的乳腺X线图像微钙化检测模型的临床应用

目的:通过开发基于Attention U-Net的乳腺X线图像微钙化检测模型,实现微钙化的高效率检出,并探究不同性质钙化、不同乳腺密度对该深度学习模型微钙化检测性能的影响。方法:回顾性分析接受乳腺常规X线检查的347例患者的694幅图像。通过低年资医师独立阅片,高年资医师审核的方式,建立微钙化检出的参考标准。进行神经网络训练,建立深度学习模型。以钙化面积和数量分别计算,并采用精确率、召回率、F1分数、交并比等指标评估微钙化检测性能,分析不同性质钙化(良性vs恶性)、不同乳腺密度(a+b类vs c+d类)对深度学习模型微钙化检测性能的影响。结果:深度学习模型对微钙化检测的精确率为85.12%±18.39%(以钙化面积计算)和76.72%±19.85%(以钙化数量计算);召回率为78.18%±19.25%(以钙化面积计算)和85.12%±18.39%(以钙化数量计算);交并比为68.29%±21.39%(以钙化面积计算)和67.13%±23.84%(以钙化数量计算);F1分数为78.96%±17.70%(以钙化面积计算)和77.65%±9.37%(以钙化数量计算)。深度学习模型在不同钙化性质(良性vs恶性)中的精确率、召回率、交并比、F1分数之间差异均无统计学意义(P>0.05),在不同乳腺密度(a+b类vs c+d类)中对微钙化检测的精确率、召回率、交并比、F1分数之间差异无统计学意义(P>0.05)。结论:基于Attention U-Net的乳腺X线图像微钙化检测模型能够对乳腺微钙化进行有效的检测、有助于乳腺微钙化的定量研究,同时该模型稳定性强,钙化性质及乳腺密度对该模型的检测性能无影响。

超声造影联合乳腺钼靶X线对乳腺导管内乳头状瘤的诊断价值

目的:研究分析超声造影联合乳腺钼靶X线对乳腺导管内乳头状瘤(DIP)的诊断价值。方法:选取我院在2022年1月-2024年1月期间收治的60例疑似DIP患者采取超声造影、乳腺钼靶X线检查,对比分析检查结果。结果:60例疑似DIP患者经病理检查显示,将病理检查结果作为金标准,阳性检出56例,超声造影阳性检出46例,乳腺钼靶X线检出43例,阳性检出率分别为76.67%、71.67%,联合检查阳性检出55例,阳性检出率91.67%。敏感度、特异度和准确度对比,超声造影与乳腺钼靶X线比较无差异(P>0.05),联合检查敏感度和准确度则要高于超声造影、乳腺钼靶X线检查(P<0.05)。结论:在DIP的临床诊断中,采用超声造影、乳腺钼靶X线均有着良好优势,但是两者联合检测能够进一步提高诊断准确性。

Magnetic Resonance Imaging for Screening of Woman at High-Risk of Breast Cancer

MRI is an excellent option for detection of breast cancer for some selected groups, including those patients with a high probability to hit the disease. However, the high costs and low availability of the device have led to a decline in the application of imaging MRI. The aim of this study was to review usefulness of MRI as a new complementary way to detect breast cancer in routine annual checkup for women breasts of certain ages and breast mass. A cross-sectional Descriptive MRI study was performed on 105 asymptomatic women with a mean age of 49 years. The study group with at least one risk factor of breast cancer were presenting for routine annual screening or follow up at King Abdulaziz University Hospital in Jeddah. It has been found that, 48 patients had biopsy, they were recommended by magnetic resonance imaging and only 14 had positive results, while magnetic resonance imaging suggested 16 and mammography had 62 positive results. Magnetic resonance imaging is not recommended for the average-risk or the general population either;it had been advised for screening the high-risk women of breast cancer. Sensitivity of magnetic resonance imaging has been found to be much higher than of mammography but specificity was generally lower. We propose that it is reasonable to consider MRI as a complement to mammography in screening patients who were at high risk for breast cancer because Magnetic Resonance Imaging can detect small foci that are occult in mammography but we don’t advise to check with the general population.

Breast Density: Does It Vary among the Main Ethnic Groups in Malaysia?

Breast cancer is one of the common cancers among Malaysians and there are associated risk factors which include breast density. Therefore, this study was done to determine the association of breast cancer risks among ethnic groups in relation to breast density. Mammography was done on 300 women with equal numbers of Malays, Chinese and Indians with a mean age of 53.35 ± 7.4 years. Mammograms were evaluated using BI-RADS (Breast Imaging Reporting and Data System) protocol by two independent radiologists for breast density categorization. Chi-square analysis showed an association between breast density and age factor (p 0.05) whereas body mass index (BMI) was inversely associated with breast density (p > 0.05). There was significant difference in number of children and menopausal status (p 0.05). Results showed that 65% of Chinese subjects had denser breast density composition as to 50% in Malays and 35% in Indians. There was significant difference between breast density of three ethnic groups (p 0.05) with Chinese having 2.4 times denser breast (OR = 2.45, 95% CI: 1.466 - 3.948) followed by Malays (OR = 1.020, 95% CI: 0.681 - 1.689) and lowest in Indians (OR = 0.406, 95% CI: 0.247 - 0.668). Based on breast density, the Chinese are at a higher risk of developing breast cancer followed by Malays and lastly Indians.

Extracting and smoothing contours in mammograms using Fourier descriptors

Contour is an important pattern descriptor in image processing and particularly in region description, registration and length estimation. In many applications where contour is used, a good segmentation and an efficient smoothing method are needed. In X-ray images, such as mammograms, where object edge is not clearly discernible, estimating the object’s contour may yield substantial shift along the boundary due to noise or segmentation drawbacks. An appropriate smoothing is therefore required to reduce these effects. In this paper, an approach based on local adaptive threshold segmentation to extract contour and a new smoothing approach founded on Fourier descriptors are introduced. The experimental results of extraction obtained from a set of mammograms and compared with the breast regions delineated by radiologists yielded a percent overlap area of 98.7% ± 0.9% with false positive and negative rates of 0.36 ± 0.74 and 0.93 ± 0.44 respectively. The proposed method was tested on a set of images and improved the accuracy, leading to an average error of less than one pixel.

Awareness of Breast Cancer in Lower Socioeconomic Status Women Attending the Surgery Outpatient Department of a Tertiary Care Teaching Institution

Background: Worldwide breast cancer represents nearly a quarter (25%) of all cancers and is the most common female cancer. Objective: The present study was conducted to check the awareness of breast cancer warning signs & symptoms, available investigations and treatment options among women of a suburban area in Chennai, Tamilnadu (India). Materials and Methods: A cross-sectional, prospective study was conducted amongst women attending the surgery outpatient department of a tertiary care teaching institution in Chennai, Tamilnadu (India), using a semi-structured questionnaire. The questionnaires were administered during one to one interview by trained research assistants. Results: The study population showed poor awareness of warning signs like changes in position of nipple, pulling in of nipple, nipple rash, changes in size of nipple, puckering/dimpling of breast skin colour changes in breast skin, lump under armpit, changes in size and shape of breast. Conclusion: The observations indicated that the level of awareness and knowledge about the presentation and management of breast cancer is suboptimal among women in Thandalam (suburban Chennai).

基于改进YOLOv4模型的乳腺钼靶图像肿块检测

针对目前主流目标检测算法在乳腺钼靶图像的良恶性肿块目标检测中存在应用较少、检测准确率低和检测速度慢等问题,提出一种基于改进YOLOv4的乳腺钼靶图像肿块检测模型。该方法可以在一个框架中同时高效进行肿块的检测和分类。首先,引入了分流聚合双通道(JAnet)残差结构对模型的骨干网络进行改进;其次,引入深度可分离卷积来替换原YOLOv4模型中的标准卷积;最后,在后处理阶段提出了较大值求平均方法。以DDSM数据集作为训练集训练检测模型,并以INbreast数据集作为独立测试集。实验结果表明,提出的基于改进YOLOv4的乳腺钼靶图像肿块检测模型的Recall值、mAP值、FPS和AUC值相比原YOLOv4算法的分别提高了7.3%,6.45%,5.9 fps和13.02%。模型整体效果优于目前主流的目标检测模型的,体现出了良好的鲁棒性和有效性,可以在医师对乳腺癌临床诊断过程中发挥计算机辅助诊断作用。

基于乳腺X线的可疑钙化在乳腺癌分子分型诊断中的应用价值分析

目的探究基于乳腺X线的可疑钙化在乳腺癌分子分型诊断中的应用价值。方法选取2019年1月~2023年3月于本院就诊并行手术病理证实的乳腺癌患者100例。乳腺X线检查结果提示可疑钙化的62例患者为观察组,无可疑钙化38例患者为对照组。采用免疫组化法检测雌激素受体(ER)、孕激素受体(PR)、人类表皮生长因子受体-2(HER-2)以及Ki-67的表达情况,判断出乳腺癌的分子亚型,并分析可疑钙化与乳腺癌各分子亚型之间的关系。结果两组年龄、淋巴结转移情况差异均无统计学意义(P>0.05);病理类型、肿瘤直径以及分子分型差异比较均具有统计学意义(P<0.05)。不同的分子分型在单纯钙化中具有明显差异(P<0.05);在非单纯钙化中差异不显著(P>0.05)。钙化形态与乳腺癌分子分型相关(P<0.05)。Luminal A型、Luminal B型以及三阴型钙化形态多呈细小多形性;HER-2过表达型钙化形态多呈细小多形性、线样或线样分支状。结论乳腺癌分子分型与可疑钙化及钙化形态均具有一定的相关性。其中Luminal B型、HER-2过表达型的乳腺癌更容易表现出可疑钙化。基于乳腺X线的可疑钙化有利于乳腺癌分子分型的诊断,将二者相结合,可以更好地指导临床个体化治疗。

基于多示例学习的钼靶图像BI-RADS分类方法

目的:基于深度学习的乳腺X线图像分类模型对于所得出的决策无法给出诊断依据。本文旨在保证模型分类精度的同时,改善模型的可解释性。方法:基于多示例学习,提出一种弱监督病灶分类和定位方法,以应用于乳腺X线图像的乳腺影像报告和数据系统(BI-RADS)分级任务。为了解决传统多示例学习只能应用于二元分类任务的问题,本文利用了BI-RADS分类的有序性,引入了新的样本标签、训练方法和输出判断方法。结果:公开数据集INbreast上的实验结果表明,在使用相同的特征提取网络下,所提出的方法在分类准确性上相较传统方法提升了2.91%。模型在病灶检出上的准确率达到83.49%,真阳性率达到75.87%,具有一定的病灶定位能力。结论:在不借助病灶轮廓数据或是位置数据进行训练的情况下,所提出的深度学习模型可以展示出每一个可能存在的病变区域及其BI-RADS分类,具有较好的应用场景。

基于灰度共生矩阵的乳腺钼靶图像分析

目的应用灰度共生矩阵对乳腺钼靶图像进行纹理分析,自动分类识别乳腺肿块,实现乳腺肿瘤的辅助检测。资料与方法纳入60例乳腺钼靶图像,其中正常乳腺组织20例,良恶性乳腺肿块各20例。对图像进行预处理后,计算各感兴趣区基于灰度共生矩阵的纹理特征值,采用支持向量机和概率神经网络分别对肿块进行分类。结果三组各项纹理特征参数间差异有统计学意义(P<0.05);d=2时支持向量机的三组分类准确率为91.67%、86.73%、95.00%,SPREAD值取0.1时概率神经网络的三组分类准确率为79.22%、81.77%、81.13%。结论文中计算的纹理特征参数对乳腺肿块的良恶性判别有较显著的规律,支持向量机的分类准确率比概率神经网络的分类准确率高,该方法可成为乳腺肿瘤良恶性辅助诊断的有效方法之一。

数字化X线摄影在触诊阴性乳癌中的诊断价值

目的探讨数字化乳腺X线摄影对隐性乳癌的诊断价值。方法回顾性分析我院2004年2月-2006年12月门诊体检中遇到的32例未触及肿块乳癌。术前均行金属丝定位,并经病理证实。结果X线呈现单纯钙化16例,其中癌前病变3例,导管原位癌6例,浸润性导管癌7例;微结节或致密影伴钙化5例,其中癌前病变1例,导管原位癌2例,浸润性导管癌2例;呈现不对称性致密影5例,1例为小叶原位癌,4例为浸润性导管癌;微结节伴浅分叶或毛刺4例,其中1例为导管原位癌,3例为浸润性导管癌;结构紊乱2例,均为浸润性导管癌。结论数字化乳腺X线摄影对诊断未触及肿块的触诊阴性乳癌、提高患者生存率、降低病死率、以及开展保乳手术具有重大价值。

乳腺癌70例X线诊断与分析

目的 提高对乳腺癌X线征象的认识。方法 对 70例经手术病理证实的乳腺癌作回顾性X线分析。结果 肿块6 7例 (团块形 38例 ,结节形 2 2例 ,不规则形 7例 ) ,钙化 2 3例 ,乳头凹陷 12例 ,厚皮征 5例 ,cooper′s韧带“牛角征”4例 ,大导管相2例 ,乳后间隙不清 19例 ,腋下淋巴结 4 9例 ,引流血管增粗 3例。结论 钼靶X线摄影对诊断乳腺癌具有重要价值。

乳腺浸润性非特殊型癌钼靶X线表现与组织学分级之间的关系

目的探讨乳腺浸润性非特殊型癌钼靶X线表现与组织学分级之间的关系。方法回顾性研究2004年6月—2005年6月间100例经手术病理证实为乳腺浸润性非特殊型癌的影像学表现,以及影像学表现与肿瘤的组织学分级相关。结果20%的组织学分级为Ⅰ级的肿瘤及72%的组织学分级为Ⅲ级肿瘤X线表现肿块,68%的Ⅰ级肿瘤及8%的Ⅲ级肿瘤在钼靶X线表现边缘毛刺征,12%的Ⅰ级肿瘤及21%的Ⅲ级肿瘤X线表现边缘不清,8%的Ⅰ级肿瘤及23%的Ⅲ级肿瘤X线表现恶性细小钙化。结论乳腺Ⅰ级肿瘤的钼靶X线表现多具有典型的恶性肿块征象如边缘毛刺征,而Ⅲ级肿瘤往往边缘清楚。因此,Ⅲ级乳腺浸润性非特殊型癌可能与乳腺良性肿瘤的X线表现类似。

临床检查阴性的乳腺X线照片簇状钙化对乳腺癌诊断的意义

目的探讨乳腺X线片发现乳腺内簇状钙化在乳腺癌诊断的临床意义。方法对临床检查阴性,而乳腺X线摄片发现乳腺内簇状钙化共91例病人102个病灶,并进行手术活检。根据病理组织学结果,对其形态、数量及分布作进行回顾性分析及对照研究。结果91例病例发现102个乳腺内簇状钙化灶,其中43个恶性病变(42.15%),59个良性病变(57.42%)。结论根据乳腺内钙化的形态、数目、分布的X线特征,是有助于对乳腺癌早期诊断。

数字乳房X射线图像的肿块分割算法研究

为了使临床医生从数字乳房X射线图像中得到更多有用的肿块信息,通过研究增强后的数字乳房X射线图像,结合图像特点,提出利用区域生长方法对图像进行肿块分割的算法。此算法可以有效地分割出图像中的肿块区域,并很好地保持了肿块的边缘信息。

ER与PR在钼靶X线假阴性乳腺癌中的表达及临床意义

目的分析ER、PR在钼靶X线假阴性乳腺癌中表达的临床意义。方法将183例女性乳腺癌按照钼靶X线结果分成阳性和假阴性2组,采用免疫组化S-P法检测其ER、PR。结果钼靶X线假阴性组中,ER阳性比率低于阳性组(40%与67.57%,P=0.003);但2组患者PR阳性表达率差异无统计学意义(62.86%与57.43%,P=0.575)。结论与钼靶X线阳性患者相比,钼靶X线假阴性患者ER阳性表达率低,提示该组患者内分泌治疗效果及预后较差。

X线平片诊断乳腺癌常见漏诊和误诊分析

回顾分析X线平片诊断乳腺癌中常见漏诊和误诊的原因,及易被漏诊和误诊乳腺癌的X线特征,探讨减少X线平片诊断乳腺癌漏诊和误诊的方法和原则,提高早期乳腺癌的正确诊断率。