Arne Juette

A Review on Automatic Mammographic Density and Parenchymal Segmentation

Breast cancer is the most frequently diagnosed cancer in women. However, the exact cause(s) of breast cancer still remains unknown. Early detection, precise identification of women at risk, and application of appropriate disease prevention measures are by far the most effective way to tackle breast cancer. There are more than 70 common genetic susceptibility factors included in the current non-image-based risk prediction models (e.g., the Gail and the Tyrer-Cuzick models). Image-based risk factors, such as mammographic densities and parenchymal patterns, have been established as biomarkers but have not been fully incorporated in the risk prediction models used for risk stratification in screening and/or measuring responsiveness to preventive approaches. Within computer aided mammography, automatic mammographic tissue segmentation methods have been developed for estimation of breast tissue composition to facilitate mammographic risk assessment. This paper presents a comprehensive review of automatic mammographic tissue segmentation methodologies developed over the past two decades and the evidence for risk assessment/density classification using segmentation. The aim of this review is to analyse how engineering advances have progressed and the impact automatic mammographic tissue segmentation has in a clinical environment, as well as to understand the current research gaps with respect to the incorporation of image-based risk factors in non-image-based risk prediction models.

Breast image pre-processing for mammographic tissue segmentation

During mammographic image acquisition, a compression paddle is used to even the breast thickness in order to obtain optimal image quality. Clinical observation has indicated that some mammograms may exhibit abrupt intensity change and low visibility of tissue structures in the breast peripheral areas. Such appearance discrepancies can affect image interpretation and may not be desirable for computer aided mammography, leading to incorrect diagnosis and/or detection which can have a negative impact on sensitivity and specificity of screening mammography. This paper describes a novel mammographic image pre-processing method to improve image quality for analysis. An image selection process is incorporated to better target problematic images. The processed images show improved mammographic appearances not only in the breast periphery but also across the mammograms. Mammographic segmentation and risk/density classification were performed to facilitate a quantitative and qualitative evaluation. When using the processed images, the results indicated more anatomically correct segmentation in tissue specific areas, and subsequently better classification accuracies were achieved. Visual assessments were conducted in a clinical environment to determine the quality of the processed images and the resultant segmentation. The developed method has shown promising results. It is expected to be useful in early breast cancer detection, risk-stratified screening, and aiding radiologists in the process of decision making prior to surgery and/or treatment.

End-to-end breast ultrasound lesions recognition with a deep learning approach

Existing methods for automated breast ultrasound lesions detection and recognition tend to be based on multi-stage processing, such as preprocessing, filtering/denoising, segmentation and classification. The performance of these processes is dependent on the prior stages. To improve the current state of the art, we have proposed an end-to-end breast ultrasound lesions detection and recognition using a deep learning approach. We implemented a popular semantic segmentation framework, i.e. Fully Convolutional Network (FCN-AlexNet) for our experiment. To overcome data deficiency, we used a pre-trained model based on ImageNet and transfer learning. We validated our results on two datasets, which consist of a total of 113 malignant and 356 benign lesions. We assessed the performance of the model using the following split: 70% for training data, 10% for validation data, and 20% testing data. The results show that our proposed method performed better on benign lesions, with a Dice score of 0.6879, when compared to the malignant lesions with a Dice score of 0.5525. When considering the number of images with Dice score > 0.5, 79% of the benign lesions were successfully segmented and correctly recognised, while 65% of the malignant lesions were successfully segmented and correctly recognised. This paper provides the first end-to-end solution for breast ultrasound lesion recognition. The future challenges for the proposed approaches are to obtain additional datasets and customize the deep learning framework to improve the accuracy of this method.

Mammographic Segmentation and Density Classification: A Fractal Inspired Approach

Breast cancer is the most frequently diagnosed cancer in women. To date, the exact causes of breast cancer still remains unknown. The most effective way to tackle the disease is early detection through breast screening programmes. Breast density is a well established image based risk factor. An accurate dense breast tissue segmentation can play a vital role in precise identification of women at risk, and determining appropriate measures for disease prevention. Fractal techniques have been used in many biomedical image processing applications with varying degrees of success. This paper describes a fractal inspired approach to mammographic tissue segmentation. A multiresolution stack representation and 3D histogram features extended from 2D are proposed. Quantitative and qualitative evaluation was performed including mammographic tissue segmentation and density classification. Results showed that the developed methodology was able to differentiate between breast tissue variations. The achieved density classification accuracy for 360 digital mammograms is 78i¾?% based on the BI-RADS scheme. The developed fractal inspired approach in conjunction with the stack representation and 3D histogram features has demonstrated an ability to produce quality mammographic tissue segmentation. This in turn can be found useful in early breast cancer detection, risk-stratified screening, and aiding radiologists in the process of decision making prior to surgery and/or treatment.

A Revisit on Correlation between Tabár and Birads Based Risk Assessment Schemes with Full Field Digital Mammography

Mammographic risk assessment is used to determine the probability of a woman developing breast cancer and it plays an important role in the early detection and disease prevention within screening mammography. Tabar and Birads are two fundamentally different risk schemes, one is assessed based on mixtures of breast parenchyma and the other one is assessed based on the percentage of dense breast tissue. This paper presents findings on the correlation between these two mammographic risk assessment schemes; aspects with respect to reader experience and related inter reader variability were also investigated. As a follow up (revisit) investigation to a previously published paper, the new results have shown a strong correlation between Tabar and Birads with the highest Spearman’s correlation coefficient > 0.92 and κ = 0.86% (almost perfect agreement). The statistical results vary with readers’ mammographic reading experience, which also indicated subtle information such as that some mixture of breast parenchma (Tabar specific mammographic building blocks) may be more likely to cause inter reader variability.

A Novel Image Enhancement Methodology for Full Field Digital Mammography

During breast screening it is necessary and essential to compress the breast with a compression paddle, in order to obtain a clear mammographic image. The quality of the image has a direct correlation with the accuracy of mammogram reading, which in turn could affect radiologist’s interpretation. Clinical observation has indicated that breast compression may have a side effect on image quality during the image acquisition and can result in unexpected variations in texture and intensity appearances, between breast tissue near the skinline and the rest of the breast. Within computer aided mammography, such variations increase the difficulty in breast tissue modelling and can be detrimental to image analysis, leading to incorrect prompts which can have an impact on sensitivity and specificity of screening mammography. We present an automatic image enhancement approach, in which both Cranio Caudal and Medio-Lateral Oblique views are utilised. We estimate the relative breast thickness ratio at a given projection location in order to alter/correct an inconsistent intensity distribution as a means of improving mammographic image quality. Our dataset consists of 360 full field digital mammographic images was used in a quantitative and qualitative evaluation. Visual assessment indicated good and consistent intensity variation over the processed images, whilst texture information (breast parenchymal patterns) was preserved and/or enhanced. By improving the consistency of the intensity distribution on the mammographic images, the developed method has demonstrated a potential benefit in density based mammographic segmentation and risk assessment. This in turn can be found useful in computer aided mammography, and is beneficial in a clinical setting by aiding screening radiologists in the process of decision making.

Comparison of ultrasound localisation techniques for impalpable breast cancer

There are increasing numbers of impalpable breast cancers that require localisation prior to wide local excision. Wire localisation is the technique used in the majority of UK centres. Our centre changed to the relatively new technique of radio-isotope occult lesion localisation (ROLL) at the beginning of 2008 for ultrasound visible lesions.

Breast ultrasound lesions recognition:: end-to-end deep learning approaches

Abstract. Multistage processing of automated breast ultrasound lesions recognition is dependent on the performance of prior stages. To improve the current state of the art, we propose the use of end-to-end deep learning approaches using fully convolutional networks (FCNs), namely FCN-AlexNet, FCN-32s, FCN-16s, and FCN-8s for semantic segmentation of breast lesions. We use pretrained models based on ImageNet and transfer learning to overcome the issue of data deficiency. We evaluate our results on two datasets, which consist of a total of 113 malignant and 356 benign lesions. To assess the performance, we conduct fivefold cross validation using the following split: 70% for training data, 10% for validation data, and 20% testing data. The results showed that our proposed method performed better on benign lesions, with a top “mean Dice” score of 0.7626 with FCN-16s, when compared with the malignant lesions with a top mean Dice score of 0.5484 with FCN-8s. When considering the number of images with Dice score >0.5, 89.6% of the benign lesions were successfully segmented and correctly recognised, whereas 60.6% of the malignant lesions were successfully segmented and correctly recognized. We conclude the paper by addressing the future challenges of the work.

Novel multiresolution mammographic density segmentation using pseudo 3D features and adaptive cluster merging

Breast cancer is the most frequently diagnosed cancer in women. Early detection, precise identification of women at risk, and application of appropriate disease prevention measures are by far the most effective ways to overcome the disease. Successful mammographic density segmentation is a key aspect in deriving correct tissue composition, ensuring an accurate mammographic risk assessment. However, mammographic densities have not yet been fully incorporated with non-image based risk prediction models, (e.g. the Gail and the Tyrer-Cuzick model), because of unreliable segmentation consistency and accuracy. This paper presents a novel multiresolution mammographic density segmentation, a concept of stack representation is proposed, and 3D texture features were extracted by adapting techniques based on classic 2D first-order statistics. An unsupervised clustering technique was employed to achieve mammographic segmentation, in which two improvements were made; 1) consistent segmentation by incorporating an optimal centroids initialisation step, and 2) significantly reduced the number of missegmentation by using an adaptive cluster merging technique. A set of full field digital mammograms was used in the evaluation. Visual assessment indicated substantial improvement on segmented anatomical structures and tissue specific areas, especially in low mammographic density categories. The developed method demonstrated an ability to improve the quality of mammographic segmentation via clustering, and results indicated an improvement of 26% in segmented image with good quality when compared with the standard clustering approach. This in turn can be found useful in early breast cancer detection, risk-stratified screening, and aiding radiologists in the process of decision making prior to surgery and/or treatment.

Management of volvulus of an ileal conduit presenting with renal failure: Case report and literature review

A 49-year-old man presented with a short history of abdominal distension, pain, vomiting and anuria. He had undergone radical cystoprostatectomy and ileal conduit diversion 5 years previously for transitional cell carcinoma (TCC) of the bladder (G3pT1 + pTis). He had a parastomal hernia (Fig. 1a) that was managed conservatively as he refused further surgery. His blood picture on this presentation revealed creatinine of 1200 mol/l along with raised CRP and WCC. CT scan showed bilateral hydronephrosis with urinoma on the right psoas muscle secondary to fornicial rupture and stranding of peri-renal fat with gas within highly suggestive of peri-renal abscess. Ileal conduit appeared herniated through