Computer-aided diagnosis for the classification of breast masses in automated whole breast ultrasound images

New automated whole breast ultrasound (ABUS) machines have recently been developed and the ultrasound (US) volume dataset of the whole breast can be acquired in a standard manner. The purpose of this study was to develop a novel computer-aided diagnosis system for classification of breast masses in ABUS images. One hundred forty-seven cases (76 benign and 71 malignant breast masses) were obtained by a commercially available ABUS system. Because the distance of neighboring slices in ABUS images is fixed and small, these continuous slices were used for reconstruction as three-dimensional (3-D) US images. The 3-D tumor contour was segmented using the level-set segmentation method. Then, the 3-D features, including the texture, shape and ellipsoid fitting were extracted based on the segmented 3-D tumor contour to classify benign and malignant tumors based on the logistic regression model. The Student’s t test, Mann-Whitney U test and receiver operating characteristic (ROC) curve analysis were used for statistical analysis. From the Az values of ROC curves, the shape features (0.9138) are better than the texture features (0.8603) and the ellipsoid fitting features (0.8496) for classification. The difference was significant between shape and ellipsoid fitting features (p = 0.0382). However, combination of ellipsoid fitting features and shape features can achieve a best performance with accuracy of 85.0% (125/147), sensitivity of 84.5% (60/71), specificity of 85.5% (65/76) and the area under the ROC curve Az of 0.9466. The results showed that ABUS images could be used for computer-aided feature extraction and classification of breast tumors. (E-mail: rfchang@csie.ntu.edu.tw)     

乳腺腺病与乳腺导管癌的MRI鉴别诊断及病理对照研究

目的探讨乳腺腺病与乳腺导管癌的动态增强磁共振成像(dynamic contrast enhanced magnetic resonance imaging,DCE-MRI)、扩散加权成像(diffusion weight imaging,DWI)鉴别诊断特征,及其与病理表现相关性。材料与方法回顾性收集分析经病理证实的105例乳腺腺病、78例乳腺导管癌患者的MRI资料。所有患者术前均行乳腺DWI、DCE-MRI扫描。分析两组患者的MRI表现特点及其与病理表现的相关性,采用χ~2检验比较两组的临床资料、病灶位置、大小、形态、时间-信号强度曲线(time-signal intensity curve,TIC)及强化方式等特征;采用单因素方差分析比较两组患者的表观扩散系数(apparent diffusion coefficient,ADC)值。结果 105例乳腺腺病呈肿块样强化(mass-like enhancement,MLE)50例,非肿块样强化(nonmass-like enhancement,NMLE)55例;78例乳腺导管癌中MLE52例,NMLE26例。腺病组MLE病变形态大多形态规则(37/50,74%)、边缘清晰(35/50,70%),两组MLE病变的强化方式、TIC类型的差异均有统计学意义(χ~2值分别为14.169和13.955,P均0.01);两组MLE病变的ADC值分别为(131.63±21.8)×10~(-3) mm~2/s、(104.21±18.54)×10~(-3) mm~2/s,两者的差异有明显统计学意义(F=52.167,P0.01);两组NMLE病变强化方式多样,其差异有统计学意义(χ~2值分别为4.478,P均0.05)。两组NMLE病变的ADC值分别为(136.23±14.8)×10~(-3) mm~2/s、(102.51±16.44)×10~(-3) mm~2/s,两者的差异有明显统计学意义(F=49.167,P0.01)。结论乳腺腺病的MRI表现具有一定的特征性,MLE病变多呈良性病变特点,NMLE病变形态与恶性病变相似,动态增强结合DWI有助于其与乳腺导管癌的鉴别诊断;乳腺腺病的间质纤维化可能是造成恶性征象出现的原因。     

Microvascular architecture of breast lesions: evaluation with contrast-enhanced ultrasonographic micro flow imaging.

OBJECTIVE: The purpose of this study was to evaluate the effectiveness of micro flow imaging (MFI) of the microvascular architecture with contrast-enhanced ultrasonography for classification of breast lesions as benign or malignant and the microvascular architectural patterns. METHODS: Contrast-enhanced ultrasonography and MFI were performed in 61 women with breast lesions. The microvascular morphologic and distribution features of the breast tumors were evaluated with MFI. Receiver operating characteristic curve analysis was used to evaluate the diagnostic value of MFI, and the microvascular architectural patterns were analyzed. RESULTS: Surgical pathologic analysis showed 29 benign and 32 malignant lesions. For MFI, the area under the receiver operating characteristic curve (A(z)) value for the overall features of the blood vessels for classification of breast lesions was 0.94. The accuracy, sensitivity, and specificity were 90.2% (55/61), 93.8% (30/32), and 86.2% (25/29), respectively. The A(z) value for the morphologic and distribution features of peripheral blood vessels was 0.91, which was significantly higher than the A(z) value for the morphologic and distribution features of interior vessels (P= .019). The microvascular architecture of the 61 lesions was categorized into 3 patterns: treelike, root hair-like, and crab claw-like. Benign lesions mainly displayed the treelike pattern (17 [58.6%]); malignant lesions tended to display the crab claw-like pattern (20 [62.5%]); and the root hair-like pattern was shown in both benign and malignant lesions (11 [37.9%] and 8 [25%], respectively). The microvascular architecture showed significant differences between benign and malignant lesions (P< .001). CONCLUSIONS: Micro flow imaging can clearly delineate the microvascular architecture of breast lesions and can aid in discrimination between benign and malignant breast lesions.     

乳腺癌新辅助化疗后钙化与临床病理特征及预后的关系分析

目的 分析乳腺癌新辅助化疗后钙化与临床病理特征及预后的关系,以期指导患者后续治疗.方法 选择2020年1月至2021年9月本院收治的160例乳腺癌患者作为研究对象,入院后均行新辅助化疗,根据新辅助化疗后钙化状态的改变分为钙化减少组、钙化增加组、无变化组,比较三组的临床病理特征、无病生存期(DFS)、总生存期(OS).结...     

2-D ultrasound strain images for breast cancer diagnosis using nonrigid subregion registration

Tissue elasticity of a lesion is a useful criterion for the diagnosis of breast ultrasound (US). Elastograms are created by comparing ultrasonic radio-frequency waveforms before and after a light-tissue compression. In this study, we evaluate the accuracy of continuous US strain image in the classification of benign from malignant breast tumors. A series of B-mode US images is applied and each case involves 60 continuous images obtained by using the steady artificial pressure of the US probe. In general, after compression by the US probe, a soft benign tumor will become flatter than a stiffened malignant tumor. We proposed a computer-aided diagnostic (CAD) system by utilizing the nonrigid image registration modality on the analysis of tumor deformation. Furthermore, we used some image preprocessing methods, which included the level set segmentation, to improve the performance. One-hundred pathology-proven cases, including 60 benign breast tumors and 40 malignant tumors, were used in the experiments to test the classification accuracy of the proposed method. Four characteristic values--normalized slope of metric value (NSM), normalized area difference (NAD), normalized standard deviation (NSD) and normalized center translation (NCT)--were computed for all cases. By using the support vector machine, the accuracy, sensitivity, specificity and positive and negative predictive values of the classification of continuous US strain images were satisfactory. The A(z) value of the support vector machine based on the four characteristic values used for the classification of solid breast tumors was 0.9358.     

正常女性乳腺的超声分型研究

目的 研究我国正常成年女性的乳腺实质结构和分型,并分析其与年龄的相关性.方法 将7532例体检健康的女性乳腺实质根据导管、间质及其他成份的不同进行超声分型,并对其与年龄的相关性进行分析.结果 本研究中正常乳腺实质可分为导管型、致密型、混合型及不均型.其中混合型占56.05%,致密型占26.61%,不均匀型占12.02%...     

Automatic breast parenchymal density classification integrated into a CADe system

Purpose  

Breast parenchymal density is an important risk factor for breast cancer. It is known that mammogram interpretation is more difficult where dense tissue is involved. Therefore, automated breast density classification may aid in breast lesion detection and analysis.     

Whole Breast Lesion Detection Using Naive Bayes Classifier for Portable Ultrasound

In recent years, portable PC-based ultrasound (US) imaging systems developed by some companies can provide an integrated computer environment for computer-aided diagnosis and detection applications. In this article, an automatic whole breast lesion detection system based on the naive Bayes classifier using the PC-based US system Terason t3000 (Terason Ultrasound, Burlington, MA, USA) with a hand-held probe is proposed. To easily retrieve the US images for any regions of the breast, a clock-based storing system is proposed to record the scanned US images. A computer-aided detection (CAD) system is also developed to save the physicians' time for a huge volume of scanned US images. The pixel classification of the US is based on the naive Bayes classifier for the proposed lesion detection system. The pixels of the US are classified into two types: lesions or normal tissues. The connected component labeling is applied to find the suspected lesions in the image. Consequently, the labeled two-dimensional suspected regions are separated into two clusters and further checked by two-phase lesion selection criteria for the determination of the real lesion, while reducing the false-positive rate. The free-response operative characteristics (FROC) curve is used to evaluate the detection performance of the proposed system. According to the experimental results of 31 cases with 33 lesions, the proposed system yields a 93.4% (31/33) sensitivity at 4.22 false positives (FPs) per hundred slices. Moreover, the speed for the proposed detection scheme achieves 12.3 frames per second (fps) with an Intel Dual-Core Quad 3 GHz processor and can be also effectively and efficiently used for other screening systems.     

乳腺黏液癌的声像图特点及病理学基础

目的探讨乳腺黏液癌的超声特征及病理学基础.方法对44例乳腺黏液癌的超声与病理特点进行回顾性分析.结果单纯型:本组28例,超声呈低或等回声,形态规则,边界清,内部回声均质,后方回声增强.病理黏液量多,部分边缘呈膨胀性生长.本组误诊率64%(18/28).混合型:本组16例,超声呈低或等回声,形态不规则,边界不清,内部回声不均质,后方回声不增强.病理黏液量少,边缘均呈浸润表现.误诊率19%(3/16).结论单纯型黏液癌类似良性疾病,了解其声像图特点对提高诊断率有一定帮助.     

基于迁移学习的乳腺肿瘤超声图像智能分类诊断

目的 探讨迁移学习方法对乳腺良恶性肿瘤超声图像分类的价值。方法 回顾性分析经病理证实的447例乳腺肿瘤的超声声像图,采用主成分分析法对原始图像进行分析提取;在Matlab 7.0软件中编程实现迁移学习,将量化的图像特征作为输入数据,利用迁移学习对乳腺良恶性肿瘤进行智能分类。结果 乳腺恶性肿瘤的边缘粗糙度、坚固度、邻域灰度差矩阵粗糙度、肿瘤后方与周围区域回声差异及水平方向高频分量和垂直方向低频分量的直方图能量均明显高于良性肿瘤（P均<0.05）。超声和迁移学习方法诊断乳腺恶性肿瘤的敏感度分别为96.21%（127/132）和96.04%（97/101）,特异度为66.35%（209/315）和98.49%（196/199）,准确率为75.17%（336/447）和97.67%（293/300）。结论 超声图像特征定量化可为识别良恶性乳腺肿瘤提供客观的量化参数;迁移学习可有效对乳腺良恶性肿瘤的声像图进行分类。     

Computer-Aided Diagnosis Based on Quantitative Elastographic Features with Supersonic Shear Wave Imaging

Supersonic shear wave imaging (SSI) has recently been explored as a technique to evaluate tissue elasticity modulus and has become a valuable tool for tumor characterization. The purpose of this study was to develop a novel computer-aided diagnosis (CAD) system that can acquire quantitative elastographic information from color SSI elastography images automatically and objectively for the purpose of classifying benign and malignant breast tumors. Conventional ultrasonography (US) and SSI elastography images of 125 breast tumors (81 benign, 44 malignant), in 93 consecutive patients (mean age: 40 y, age range: 16–75 y), were obtained. After reconstruction of tissue elasticity data and automatic segmentation of each breast tumor, 10 quantitative elastographic features of the tumor and peri-tumoral areas, respectively (elasticity modulus mean, maximum and standard deviation, hardness degree and elasticity ratio), were computed and evaluated. A support vector machine (SVM) classifier was used for optimum classification via combination of these features. The B-mode Breast Imaging Reporting and Data System (BI-RADS) was used to compare gray-scale US and SSI elastography with respect to diagnostic performance. Histopathologic examination was used as the reference standard. Student's t-test, the Mann-Whitney U-test, the point biserial correlation coefficient and receiver operating characteristic curve analysis were performed for statistical analysis. As a result, the accuracy, sensitivity, specificity, positive predictive value and negative predictive value of benign/malignant classification were 95.2% (119/125), 90.9% (40/44), 97.5% (79/81), 95.2% (40/42) and 95.2% (79/83) for the CAD scheme, respectively, and 79.2% (99/125), 90.9% (40/44), 72.8% (59/81), 64.5% (40/62) and 93.7% (59/63) for BI-RADS assessment, respectively. The area under the receiver operating characteristic curve (A_z value) for the proposed CAD system using the combination of elastographic features was significantly higher than the A_z value for visual assessment by the radiologists using BI-RADS (0.97 vs. 0.91). The results indicate that SSI elastography could be used for computer-aided feature extraction, and the proposed CAD method could improve the diagnostic accuracy of classification of breast tumors to avoid unnecessary biopsy. Furthermore, elastographic features of the peri-tumoral area have the potential to provide critical information in differential diagnosis.     

边界增强像素级多模态声像图融合方法评估良、恶性乳腺肿瘤

目的 观察以边界增强多模态乳腺声像图像素级特征融合方法评估良、恶性乳腺肿瘤性质的价值。方法 基于乳腺肿瘤B型声像图提取边界增强图像,于超声弹性复合声像图中提取纯弹性信息图像。对多模态乳腺肿瘤声像图进行像素级特征融合,形成边界特征增强的融合图像,再以卷积神经网络(CNN)进行分类;评估融合方法分类良、恶性乳腺肿瘤的性能,并与单模态方法、特征级融合方法、无边界增强像素级图像融合方法及其他CNN模型进行对比。结果 边界增强像素级特征融合方法有助于CNN提取乳腺肿瘤特征,分类良、恶性乳腺性能最佳,其分类准确率为85.71%,特异度为85.49%,敏感度为86.16%,模型稳定。结论 边界特征增强像素级多模态声像图融合方法可用于判断良、恶性乳腺肿瘤。     

剪切波弹性成像定性技术鉴别诊断乳腺良恶性病变

目的 探讨SWE定性技术在乳腺病灶良恶性鉴别诊断中的应用价值。方法 对236例患者共261个病灶行常规超声及SWE检查。以常规超声图像进行乳腺影像报告和数据系统（BI-RADS）分类,将SWE图像分为6种类型。以病理结果为金标准,绘制ROC曲线,评价SWE分型、BI-RADS分类及二者联合的诊断效能。结果 良性病灶100个,恶性病灶161个。以SWE分型3型为诊断界点,敏感度、特异度、准确率、阳性预测值、阴性预测值分别为85.71%（138/161）、93.00%（93/100）、88.51%（231/261）、95.17%（138/145）、80.17%（93/116）;以BI-RADS 4a类为诊断界点,敏感度、特异度、准确率、阳性预测值、阴性预测值分别为98.76%（159/161）、73.00%（73/100）、88.89%（232/261）、85.48%（159/186）、97.33%（73/75）;二者联合诊断的敏感度、特异度、准确率、阳性预测值、阴性预测值分别为99.38%（160/161）、70.00%（70/100）、88.12%（230/261）、84.21%（160/190）、98.59%（70/71）。SWE分型的特异度和阳性预测值均高于BI-RADS分类及联合诊断（P均<0.05）,BI-RADS分类及联合诊断的敏感度和阴性预测值均高于SWE分型（P均<0.05）,三者诊断准确率差异均无统计学意义（P均>0.05）。结论 SWE定性技术有助于乳腺良恶性病灶的鉴别诊断。     

肝泡球蚴病42例B超声像分析

来自甘肃漳县４２例肝泡球蚴患者由Ｂ超和酶联免疫吸附试验（ＥＬＩＳＡ）证实。根据泡球蚴Ｂ超显像特征可分为３种类型。２８例发生实体性非均质损害（６６．６７％；９例表现为强回声及液性暗区并存的“地图样”损害（２１．４３％）；５例仅有局限性钙化改变（１２％）。此外４２例中之２７例伴有不同程度的钙化。结合临床我们认为局限性结节状钙化损害（１０／４２）常提示是肝泡球蚴的早期病变。     

比较超声与乳腺钼靶摄影评估不同类型乳腺微小肿块

目的 比较超声（US）和钼靶X线乳腺摄影（MTM）评估不同类型乳腺微小肿块的价值。方法 选取562例经手术或穿刺确诊,并具有完整US、MTM以及病理结果的乳腺微小肿块患者,根据MTM图像将乳腺分为4种类型,比较US和MTM对不同类型乳腺微小肿块的检出率、敏感度、特异度及准确率,并分析US与MTM的诊断一致性。结果 在美国放射学院（ACR）a类乳腺,MTM对微小肿块的检出率以及诊断恶性微小肿块的敏感度、准确率均高于US（P均<0.05）,US和MTM的诊断一致性一般（Kappa=0.47）;在ACR b类和ACR c类乳腺,MTM和US对微小肿块的检出率以及诊断恶性微小肿块的敏感度、特异度以及准确率差异无统计学意义（P均>0.05）,两者的诊断一致性较好（Kappa=0.78、0.76）;在ACR d类乳腺,US对微小肿块的检出率以及诊断恶性微小肿块的敏感度、准确率均高于MTM（P<0.05）,两者的诊断一致性较差（Kappa=0.35）。结论 对于ACR a类乳腺发生的微小肿块,MTM优于US;对于ACR b类和ACR c类乳腺微小肿块,US和MTM无明显差异;对于ACR d类乳腺微小肿块,US优于MTM。     

Tissue harmonic imaging: utility in breast sonography.

OBJECTIVE: To determine the impact of tissue harmonic imaging on visualization of focal breast lesions and to compare gray scale contrast between focal breast lesions and fatty tissue of the breast between tissue harmonic imaging and fundamental frequency sonography. METHODS: A prospective study was performed on 219 female patients (254 lesions) undergoing sonographically guided fine-needle biopsy. The fundamental frequency and tissue harmonic images of all lesions were obtained on a scanner with a wideband 7.5-MHz linear probe. Twenty-three breast carcinomas, 6 suspect lesions, 9 fibroadenomas, 1 papilloma, 1 phyllodes tumor, 162 unspecified solid benign lesions, and 40 cysts were found. In 12 cases the fine-needle aspiration did not yield sufficient material. The gray scale intensity of the lesions and adjacent fatty tissue was measured with graphics software, and the gray scale contrast between lesions and adjacent fatty tissue was calculated. RESULTS: Tissue harmonic imaging improved the gray scale contrast between the fatty tissue and breast lesions in 230 lesions (90.6%; P < .001) compared with fundamental frequency images. The contrast improvement was bigger in breasts with predominantly fatty or mixed (fatty/glandular) composition than in predominantly glandular breasts. The overall conspicuity, lesion border definition, lesion content definition, and acoustic shadow conspicuity were improved or equal in the harmonic mode for all lesions.CONCLUSIONS: The tissue harmonic imaging technique used as an adjunct to conventional breast sonography may improve lesion detectability and characterization.     

Risk of malignancy in solid breast nodules according to their sonographic features.

OBJECTIVE: The purpose of this study was to assess the risk of malignancy for each type of sonographic feature in solid breast nodules. METHODS: The study included 304 patients from the Department of Gynecology and Obstetrics of the Federal University of Goiás who had solid breast nodules. A medical trainee, working under the supervision of a preceptor, obtained the sonographic images of the breast, and the features were recorded in a questionnaire. Each sonographic feature was analyzed and compared with the anatomic and pathologic findings after the lesion was excised. RESULTS: Of the 304 patients included in the study, 292 (96%) had a conclusive diagnosis. Among these women, 216 (74%) had benign tumors and 76 (26%) had malignant tumors. The odds ratio of malignancy in breast nodules, as calculated by multivariate analysis, was as follows: lesions without circumscribed margins, 17.02 (95% confidence interval, 5.28-54.90); lesions with heterogeneous echo texture, 7.70 (2.99-19.84); lesions with thickened Cooper ligaments, 15.61 (1.08-225.10); nodules whose anteroposterior dimension was larger than their width, 3.29 (1.09-9.96); those with an anterior echogenic rim, 2.59 (0.80-8.40); and those with posterior shadowing, 1.57 (0.62-4.01). Among the 133 cases that had all the sonographic features of a benign lesion, 3 nodules (2.3%) had a histologic diagnosis of malignant. CONCLUSIONS: Sonography is a diagnostic method that can help establish the differentiation between benign and malignant solid tumors. A lack of circumscribed margins, heterogeneous echo patterns, thickened Cooper ligaments, and an increased anteroposterior dimension can indicate a higher probability of malignancy in solid breast nodules.     

乳腺黏液癌MRI表现与免疫组化对照分析

目的探讨35例乳腺黏液癌MRI与免疫组化表现,提高对该病的认识和诊断水平。方法回顾我院经手术病理证实的35例乳腺黏液癌,分析对照MRI表现及免疫组化指标。结果单纯型22例,混合型13例。MRI上表现为肿块22例,非肿块6例,结节状7例;平扫T_1WI低信号24例,等信号9例,混杂高信号2例;T_2WI抑脂高信号15例,稍高混杂信号20例;动态增强早期呈典型环形强化11例;时间信号曲线呈流入型9例,流出型强化9例,平台型强化17例;全部病灶ER、PR、HER-2、Ki-67阳性率分别为91.43%(32/35),68.57%(24/35),28.57%(10/35),62.86%(22/35)。单纯型具有较高的ER、PR阳性率,混合型具有较高的Ki-67、HER-2阳性率;ER、PR与强化形态相关,HER-2与最大径及形状相关,Ki-67与TIC曲线及淋巴结转移相关(P0.05)。结论乳腺黏液癌的MRI表现与免疫组化表现具有一定特征及联系。     

基于自动乳腺容积扫描、乳腺X线摄影及MRI的BI-RADS分类鉴别乳腺良恶性肿块

目的比较基于自动乳腺容积扫描(ABVS)、乳腺X线摄影(MMG)及MRI的BI-RADS分类鉴别乳腺良恶性肿块的价值。方法回顾性分析94例乳腺肿块患者(104个病灶)的ABVS、MMG及MRI资料,根据第五版BI-RADS标准评估肿块并进行分类。以病理结果为标准,绘制ABVS、MMG、MRI的BI-RADS分类鉴别乳腺良恶性肿块的ROC曲线,比较3种方法的AUC、敏感度和特异度差异。结果104个乳腺肿块中,良性59个(56.73%),恶性45个(43.27%)。基于ABVS与基于MRI的BI-RADS分类鉴别乳腺良恶性肿块的AUC均为0.93,差异无统计学意义(Z=0.05,P=0.96),均高于MMG(0.82)(Z=2.74、3.32,P均<0.01)。3种方法诊断的最佳截断值均为BI-RADS 4a,ABVS的敏感度(91.11%)与MRI(88.89%)差异无统计学意义(χ²=0.12,P=0.73),且均高于MMG(71.11%)(χ²=5.87、4.44,P均<0.05);ABVS、MRI及MMG的特异度分别为86.44%、89.83%及83.05%,差异均无统计学意义(P均>0.05)。结论基于ABVS、MRI的BI-RADS分类鉴别乳腺良恶性肿块的效能相当,且均高于MMG。     

Deep weakly-supervised breast tumor segmentation in ultrasound images with explicit anatomical constraints

Breast tumor segmentation is an important step in the diagnostic procedure of physicians and computer-aided diagnosis systems. We propose a two-step deep learning framework for breast tumor segmentation in breast ultrasound (BUS) images which requires only a few manual labels. The first step is breast anatomy decomposition handled by a semi-supervised semantic segmentation technique. The input BUS image is decomposed into four breast anatomical structures, namely fat, mammary gland, muscle and thorax layers. Fat and mammary gland layers are used as constrained region to reduce the search space for breast tumor segmentation. The second step is breast tumor segmentation performed in a weakly-supervised learning scenario where only image-level labels are available. Breast tumors are first recognized by a classification network and then segmented by the proposed class activation mapping and deep level set (CAM-DLS) method. For breast anatomy decomposition, the proposed framework achieves Dice similarity coefficient (DSC) of 83.0 ± 11.8%, 84.3 ± 10.0%, 80.7 ± 15.4% and 91.0 ± 11.4% for fat, mammary gland, muscle and thorax layers, respectively. For breast tumor recognition, the proposed framework achieves sensitivity of 95.8%, precision of 92.4%, specificity of 93.9%, accuracy of 94.8% and F1-score of 0.941. For breast tumor segmentation, the proposed framework achieves DSC of 77.3% and intersection-over-union (IoU) of 66.0%. In conclusion, the proposed framework could efficiently perform breast tumor recognition and segmentation simultaneously in a weakly-supervised setting with anatomical constraints.