Going beyond a First Reader: A Machine Learning Methodology for Optimizing Cost and Performance in Breast Ultrasound Diagnosis

Machine learning and new insights for breast cancer diagnosis

Breast cancer (BC) is the most prominent form of cancer among females all over the world. The current methods of BC detection include X-ray mammography, ultrasound, computed tomography, magnetic resonance imaging, positron emission tomography and breast thermographic techniques. More recently, machine learning (ML) tools have been increasingly employed in diagnostic medicine for its high efficiency in detection and intervention. The subsequent imaging features and mathematical analyses can then be used to generate ML models, which stratify, differentiate and detect benign and malignant breast lesions. Given its marked advantages, radiomics is a frequently used tool in recent research and clinics. Artificial neural networks and deep learning (DL) are novel forms of ML that evaluate data using computer simulation of the human brain. DL directly processes unstructured information, such as images, sounds and language, and performs precise clinical image stratification, medical record analyses and tumour diagnosis. Herein, this review thoroughly summarizes prior investigations on the application of medical images for the detection and intervention of BC using radiomics, namely DL and ML. The aim was to provide guidance to scientists regarding the use of artificial intelligence and ML in research and the clinic.

Robot-Guided Ultrasonography in Surgical Interventions

INTRODUCTION

The introduction of robotic-guided procedures in surgical techniques has brought an increase in the accuracy and control of resections. Surgery has evolved as a technique since the development of laparoscopy, which has added to the visualisation of the peritoneal cavity from a different perspective. Multi-armed robot associated with real-time intraoperative imaging devices brings important manoeuvrability and dexterity improvements in certain surgical fields.

MATERIALS AND METHODS

The present study is designed to synthesise the development of imaging techniques with a focus on ultrasonography in robotic surgery in the last ten years regarding abdominal surgical interventions.

RESULTS

All studies involved abdominal surgery. Out of the seven studies, two were performed in clinical trials. The other five studies were performed on organs or simulators and attempted to develop a hybrid surgical technique using ultrasonography and robotic surgery. Most studies aim to surgically identify both blood vessels and nerve structures through this combined technique (surgery and imaging).

CONCLUSIONS

Ultrasonography is often used in minimally invasive surgical techniques. This adds to the visualisation of blood vessels, the correct identification of tumour margins, and the location of surgical instruments in the tissue. The development of ultrasound technology from 2D to 3D and 4D has brought improvements in minimally invasive and robotic surgical techniques, and it should be further studied to bring surgery to a higher level.

Ethics of Artificial Intelligence in Breast Imaging

There is great interest in the development of artificial intelligence (AI) applications for medical imaging in general and specifically in breast imaging. Because of the scale of application and the potential for harm, there has been a parallel interest in assuring that these new technologies are scrutinized and applied in ethical ways. The four principles of autonomy, beneficence, non-maleficence, and justice are widely accepted as a framework for bioethical analysis. We incorporate a fifth principle of explicability (adapted from Floridi and Cowls) because of the unique considerations of AI. We review definitions of each of these principles and provide examples of their practical application to breast imaging.

A non-invasive method for prediction of neurodegenerative diseases using gait signal features

The steady degeneration of neurons is the hallmark of neurodegenerative illnesses, which are, by definition, incurable. Corticobasal Syndrome (CS), Huntington's Disease (HD), Dementia, Amyotrophic Lateral Sclerosis (ALS), Progressive supranuclear palsy (PSP) and Parkinson's Disease (PD) are some of the common neurodegenerative diseases which has impacted millions of people, predominantly among the older population. Various computational techniques, including but not limited to machine learning, are emerging as discrimination and detection of neuro-related diseases. This research proposed a machine learning-based framework to correctly detect PD, HD, and ALS from the gait signals of subjects both in binary and multi-class detection environment. The detection approach proposed here combines the classification power of Naïve Bayes and Logistic Regression jointly in a modern UltraBoost ensemble framework. The proposed method is unique in its ability to detect neuro diseases with a small number of gait features. The proposed approach ascertains most essential gait features through three state-of-the-art feature selection schemes, infinite feature selection, infinite latent feature selection and Sigmis feature selection. It has been observed that the gait signal features of the subjects are identified through Infinite Feature Selection manifests better detection results than the features obtained through Infinite Latent Feature and Sigmis feature selection while detecting Parkinson's and Huntington's Disease in a multi-class environment. So far as the binary detection environment is concern, the Amyotrophic lateral sclerosis is detected with 99.1% detection accuracy using 18 Sigmis gait features, with 99.1% sensitivity and 98.9% specificity, respectively. Similarly, Huntington's disease was detected with 94.2% detection accuracy, 94.2% sensitivity, and 94.5% specificity using 5 Sigmis gait features. Finally, Parkinson's disease was detected with 98.4% sensitivity, specificity, and detection accuracy.

Deep learning applied to breast imaging classification and segmentation with human expert intervention

PURPOSE

Automatic classification and segmentation of tumors in breast ultrasound images enables better diagnosis and planning treatment strategies for breast cancer patients.

METHODS

We collected 953 breast ultrasound images from two open-source datasets and classified them with help of an expert radiologist according to BI-RADS criteria. The data was split into normal, benign and malignant classes. We then used machine learning to develop classification and segmentation algorithms.

RESULTS

We found 3.92% of the images across the open-source datasets had erroneous classifications. Post-radiologist intervention, three algorithms were developed based on the classification categories. Classification algorithms distinguished images with healthy breast tissue from those with abnormal tissue with 96% accuracy, and distinguished benign from malignant images with 85% accuracy. Both algorithms generated robust F1 and AUROC metrics. Finally, the masses within images were segmented with an 80.31% DICE score.

CONCLUSIONS

Our work illustrates the potential of deep learning algorithms to improve the accuracy of breast ultrasound assessments and to facilitate automated assessments.

Application of Convolution Neural Network Algorithm Based on Multicenter ABUS Images in Breast Lesion Detection

Objective

This study aimed to evaluate a convolution neural network algorithm for breast lesion detection with multi-center ABUS image data developed based on ABUS image and Yolo v5.

Methods

A total of 741 cases with 2,538 volume data of ABUS examinations were analyzed, which were recruited from 7 hospitals between October 2016 and December 2020. A total of 452 volume data of 413 cases were used as internal validation data, and 2,086 volume data from 328 cases were used as external validation data. There were 1,178 breast lesions in 413 patients (161 malignant and 1,017 benign) and 1,936 lesions in 328 patients (57 malignant and 1,879 benign). The efficiency and accuracy of the algorithm were analyzed in detecting lesions with different allowable false positive values and lesion sizes, and the differences were compared and analyzed, which included the various indicators in internal validation and external validation data.

Results

The study found that the algorithm had high sensitivity for all categories of lesions, even when using internal or external validation data. The overall detection rate of the algorithm was as high as 78.1 and 71.2% in the internal and external validation sets, respectively. The algorithm could detect more lesions with increasing nodule size (87.4% in ≥10 mm lesions but less than 50% in <10 mm). The detection rate of BI-RADS 4/5 lesions was higher than that of BI-RADS 3 or 2 (96.5% vs 79.7% vs 74.7% internal, 95.8% vs 74.7% vs 88.4% external). Furthermore, the detection performance was better for malignant nodules than benign (98.1% vs 74.9% internal, 98.2% vs 70.4% external).

Conclusions

This algorithm showed good detection efficiency in the internal and external validation sets, especially for category 4/5 lesions and malignant lesions. However, there are still some deficiencies in detecting category 2 and 3 lesions and lesions smaller than 10 mm.

Machine-Learning-Based Disease Diagnosis: A Comprehensive Review

Globally, there is a substantial unmet need to diagnose various diseases effectively. The complexity of the different disease mechanisms and underlying symptoms of the patient population presents massive challenges in developing the early diagnosis tool and effective treatment. Machine learning (ML), an area of artificial intelligence (AI), enables researchers, physicians, and patients to solve some of these issues. Based on relevant research, this review explains how machine learning (ML) is being used to help in the early identification of numerous diseases. Initially, a bibliometric analysis of the publication is carried out using data from the Scopus and Web of Science (WOS) databases. The bibliometric study of 1216 publications was undertaken to determine the most prolific authors, nations, organizations, and most cited articles. The review then summarizes the most recent trends and approaches in machine-learning-based disease diagnosis (MLBDD), considering the following factors: algorithm, disease types, data type, application, and evaluation metrics. Finally, in this paper, we highlight key results and provides insight into future trends and opportunities in the MLBDD area.

Differential diagnosis between small breast phyllodes tumors and fibroadenomas using artificial intelligence and ultrasound data

Background

It is challenging to differentiate between phyllodes tumors (PTs) and fibroadenomas (FAs). Artificial intelligence (AI) can provide quantitative information regarding the morphology and textural features of lesions. This study attempted to use AI to evaluate the ultrasonic images of PTs and FAs and to explore the diagnostic performance of AI features in the differential diagnosis of PTs and FAs.

Methods

A total of 40 PTs and 290 FAs <5 cm in maximum diameter found in female patients were retrospectively analyzed. All tumors were segmented by doctors, and the features of the lesions were collated, including circularity, height-to-width ratio, margin spicules, margin coarseness (MC), margin indistinctness, margin lobulation (ML), internal calcification, angle between the long axis of the lesion and skin, energy, grey entropy, and grey mean. The differences between PTs and FAs were analyzed, and the diagnostic performance of AI features in the differential diagnosis of PTs and FAs was evaluated.

Results

Statistically significant differences (P<0.05) were found in the height-to-width ratio, ML, energy, and grey entropy between the PTs and FAs. Receiver operating characteristic (ROC) curve analysis of single features showed that the area under the curve [(AUC) 0.759] of grey entropy was the largest among the four features with statistically significant differences, and the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 0.925, 0.459, 0.978, and 0.190, respectively. When considering the combinations of the features, the combination of height-to-width ratio, margin indistinctness, ML, energy, grey entropy, and internal calcification was the most optimal of the combinations of features with an AUC of 0.868, and a sensitivity, specificity, PPV, and NPV of 0.734, 0.900, 0.982, and 0.316, respectively.

Conclusions

Quantitative analysis of AI can identify subtle differences in the morphology and textural features between small PTs and FAs. Comprehensive consideration of multiple features is important for the differential diagnosis of PTs and FAs.

Application of ultrasound artificial intelligence in the differential diagnosis between benign and malignant breast lesions of BI-RADS 4A

Background

The classification of Breast Imaging Reporting and Data System 4A (BI-RADS 4A) lesions is mostly based on the personal experience of doctors and lacks specific and clear classification standards. The development of artificial intelligence (AI) provides a new method for BI-RADS categorisation. We analysed the ultrasonic morphological and texture characteristics of BI-RADS 4A benign and malignant lesions using AI, and these ultrasonic characteristics of BI-RADS 4A benign and malignant lesions were compared to examine the value of AI in the differential diagnosis of BI-RADS 4A benign and malignant lesions.

Methods

A total of 206 lesions of BI-RADS 4A examined using ultrasonography were analysed retrospectively, including 174 benign lesions and 32 malignant lesions. All of the lesions were contoured manually, and the ultrasonic morphological and texture features of the lesions, such as circularity, height-to-width ratio, margin spicules, margin coarseness, margin indistinctness, margin lobulation, energy, entropy, grey mean, internal calcification and angle between the long axis of the lesion and skin, were calculated using grey level gradient co-occurrence matrix analysis. Differences between benign and malignant lesions of BI-RADS 4A were analysed.

Results

Significant differences in margin lobulation, entropy, internal calcification and ALS were noted between the benign group and malignant group (P = 0.013, 0.045, 0.045, and 0.002, respectively). The malignant group had more margin lobulations and lower entropy compared with the benign group, and the benign group had more internal calcifications and a greater angle between the long axis of the lesion and skin compared with the malignant group. No significant differences in circularity, height-to-width ratio, margin spicules, margin coarseness, margin indistinctness, energy, and grey mean were noted between benign and malignant lesions.

Conclusions

Compared with the naked eye, AI can reveal more subtle differences between benign and malignant BI-RADS 4A lesions. These results remind us carefully observation of the margin and the internal echo is of great significance. With the help of morphological and texture information provided by AI, doctors can make a more accurate judgment on such atypical benign and malignant lesions.

Color Doppler Ultrasound Improves Machine Learning Diagnosis of Breast Cancer

Color Doppler is used in the clinic for visually assessing the vascularity of breast masses on ultrasound, to aid in determining the likelihood of malignancy. In this study, quantitative color Doppler radiomics features were algorithmically extracted from breast sonograms for machine learning, producing a diagnostic model for breast cancer with higher performance than models based on grayscale and clinical category from the Breast Imaging Reporting and Data System for ultrasound (BI-RADS_US). Ultrasound images of 159 solid masses were analyzed. Algorithms extracted nine grayscale features and two color Doppler features. These features, along with patient age and BI-RADS_US category, were used to train an AdaBoost ensemble classifier. Though training on computer-extracted grayscale features and color Doppler features each significantly increased performance over that of models trained on clinical features, as measured by the area under the receiver operating characteristic (ROC) curve, training on both color Doppler and grayscale further increased the ROC area, from 0.925 ± 0.022 to 0.958 ± 0.013. Pruning low-confidence cases at 20% improved this to 0.986 ± 0.007 with 100% sensitivity, whereas 64% of the cases had to be pruned to reach this performance without color Doppler. Fewer borderline diagnoses and higher ROC performance were both achieved for diagnostic models of breast cancer on ultrasound by machine learning on color Doppler features.

Reviewing ensemble classification methods in breast cancer

CONTEXT

Ensemble methods consist of combining more than one single technique to solve the same task. This approach was designed to overcome the weaknesses of single techniques and consolidate their strengths. Ensemble methods are now widely used to carry out prediction tasks (e.g. classification and regression) in several fields, including that of bioinformatics. Researchers have particularly begun to employ ensemble techniques to improve research into breast cancer, as this is the most frequent type of cancer and accounts for most of the deaths among women.

OBJECTIVE AND METHOD

The goal of this study is to analyse the state of the art in ensemble classification methods when applied to breast cancer as regards 9 aspects: publication venues, medical tasks tackled, empirical and research types adopted, types of ensembles proposed, single techniques used to construct the ensembles, validation framework adopted to evaluate the proposed ensembles, tools used to build the ensembles, and optimization methods used for the single techniques. This paper was undertaken as a systematic mapping study.

RESULTS

A total of 193 papers that were published from the year 2000 onwards, were selected from four online databases: IEEE Xplore, ACM digital library, Scopus and PubMed. This study found that of the six medical tasks that exist, the diagnosis medical task was that most frequently researched, and that the experiment-based empirical type and evaluation-based research type were the most dominant approaches adopted in the selected studies. The homogeneous type was that most widely used to perform the classification task. With regard to single techniques, this mapping study found that decision trees, support vector machines and artificial neural networks were those most frequently adopted to build ensemble classifiers. In the case of the evaluation framework, the Wisconsin Breast Cancer dataset was the most frequently used by researchers to perform their experiments, while the most noticeable validation method was k-fold cross-validation. Several tools are available to perform experiments related to ensemble classification methods, such as Weka and R Software. Few researchers took into account the optimisation of the single technique of which their proposed ensemble was composed, while the grid search method was that most frequently adopted to tune the parameter settings of a single classifier.

CONCLUSION

This paper reports an in-depth study of the application of ensemble methods as regards breast cancer. Our results show that there are several gaps and issues and we, therefore, provide researchers in the field of breast cancer research with recommendations. Moreover, after analysing the papers found in this systematic mapping study, we discovered that the majority report positive results concerning the accuracy of ensemble classifiers when compared to the single classifiers. In order to aggregate the evidence reported in literature, it will, therefore, be necessary to perform a systematic literature review and meta-analysis in which an in-depth analysis could be conducted so as to confirm the superiority of ensemble classifiers over the classical techniques.

Breast-lesions characterization using Quantitative Ultrasound features of peritumoral tissue

The presented studies evaluate for the first time the efficiency of tumour classification based on the quantitative analysis of ultrasound data originating from the tissue surrounding the tumour. 116 patients took part in the study after qualifying for biopsy due to suspicious breast changes. The RF signals collected from the tumour and tumour-surroundings were processed to determine quantitative measures consisting of Nakagami distribution shape parameter, entropy, and texture parameters. The utility of parameters for the classification of benign and malignant lesions was assessed in relation to the results of histopathology. The best multi-parametric classifier reached an AUC of 0.92 and of 0.83 for outer and intra-tumour data, respectively. A classifier composed of two types of parameters, parameters based on signals scattered in the tumour and in the surrounding tissue, allowed the classification of breast changes with sensitivity of 93%, specificity of 88%, and AUC of 0.94. Among the 4095 multi-parameter classifiers tested, only in eight cases the result of classification based on data from the surrounding tumour tissue was worse than when using tumour data. The presented results indicate the high usefulness of QUS analysis of echoes from the tissue surrounding the tumour in the classification of breast lesions.

Artificial Intelligence (AI) for the early detection of breast cancer: a scoping review to assess AI's potential in breast screening practice

INTRODUCTION

Various factors are driving interest in the application of artificial intelligence (AI) for breast cancer (BC) detection, but it is unclear whether the evidence warrants large-scale use in population-based screening.

AREAS COVERED

We performed a scoping review, a structured evidence synthesis describing a broad research field, to summarize knowledge on AI evaluated for BC detection and to assess AI's readiness for adoption in BC screening. Studies were predominantly small retrospective studies based on highly selected image datasets that contained a high proportion of cancers (median BC proportion in datasets 26.5%), and used heterogeneous techniques to develop AI models; the range of estimated AUC (area under ROC curve) for AI models was 69.2-97.8% (median AUC 88.2%). We identified various methodologic limitations including use of non-representative imaging data for model training, limited validation in external datasets, potential bias in training data, and few comparative data for AI versus radiologists' interpretation of mammography screening.

EXPERT OPINION

Although contemporary AI models have reported generally good accuracy for BC detection, methodological concerns, and evidence gaps exist that limit translation into clinical BC screening settings. These should be addressed in parallel to advancing AI techniques to render AI transferable to large-scale population-based screening.

Using Machine Learning to Assess Physician Competence: A Systematic Review

PURPOSE

To identify the different machine learning (ML) techniques that have been applied to automate physician competence assessment and evaluate how these techniques can be used to assess different competence domains in several medical specialties.

METHOD

In May 2017, MEDLINE, EMBASE, PsycINFO, Web of Science, ACM Digital Library, IEEE Xplore Digital Library, PROSPERO, and Cochrane Database of Systematic Reviews were searched for articles published from inception to April 30, 2017. Studies were included if they applied at least one ML technique to assess medical students', residents', fellows', or attending physicians' competence. Information on sample size, participants, study setting and design, medical specialty, ML techniques, competence domains, outcomes, and methodological quality was extracted. MERSQI was used to evaluate quality, and a qualitative narrative synthesis of the medical specialties, ML techniques, and competence domains was conducted.

RESULTS

Of 4,953 initial articles, 69 met inclusion criteria. General surgery (24; 34.8%) and radiology (15; 21.7%) were the most studied specialties; natural language processing (24; 34.8%), support vector machine (15; 21.7%), and hidden Markov models (14; 20.3%) were the ML techniques most often applied; and patient care (63; 91.3%) and medical knowledge (45; 65.2%) were the most assessed competence domains.

CONCLUSIONS

A growing number of studies have attempted to apply ML techniques to physician competence assessment. Although many studies have investigated the feasibility of certain techniques, more validation research is needed. The use of ML techniques may have the potential to integrate and analyze pragmatic information that could be used in real-time assessments and interventions.

Machine learning to improve breast cancer diagnosis by multimodal ultrasound

Despite major advances in breast cancer imaging there is compelling need to reduce unnecessary biopsies by improving characterization of breast lesions. This study demonstrates the use of machine learning to enhance breast cancer diagnosis with multimodal ultrasound. Surgically proven solid breast lesions were studied using quantitative features extracted from grayscale and Doppler ultrasound images. Statistically different features from the logistic regression classifier were used train and test lesion differentiation by leave-one-out cross-validation. The area under the ROC curve (AUC) of the grayscale morphologic features was 0.85 (sensitivity = 87, specificity = 69). The diagnostic performance improved (AUC = 0.89, sensitivity = 79, specificity = 89) when Doppler features were added to the analysis. Reliability of the individual training cycles of leave-one-out cross-validation was tested by measuring dispersion from the mean model. Significant dispersion from the mean, representing weak learning, was observed in 11.3% of cases. Pruning the high-dispersion cases improved the diagnostic performance markedly (AUC 0.96, sensitivity = 92, specificity = 95). These results demonstrate the effectiveness of dispersion to identify weakly learned cases. In conclusion, machine learning with multimodal ultrasound including grayscale and Doppler can achieve high performance for breast cancer diagnosis, comparable to that of human observers. Identifying weakly learned cases can markedly enhance diagnosis.

Machine learning techniques for breast cancer computer aided diagnosis using different image modalities: A systematic review

BACKGROUND AND OBJECTIVE

The high incidence of breast cancer in women has increased significantly in the recent years. Physician experience of diagnosing and detecting breast cancer can be assisted by using some computerized features extraction and classification algorithms. This paper presents the conduction and results of a systematic review (SR) that aims to investigate the state of the art regarding the computer aided diagnosis/detection (CAD) systems for breast cancer.

METHODS

The SR was conducted using a comprehensive selection of scientific databases as reference sources, allowing access to diverse publications in the field. The scientific databases used are Springer Link (SL), Science Direct (SD), IEEE Xplore Digital Library, and PubMed. Inclusion and exclusion criteria were defined and applied to each retrieved work to select those of interest. From 320 studies retrieved, 154 studies were included. However, the scope of this research is limited to scientific and academic works and excludes commercial interests.

RESULTS

This survey provides a general analysis of the current status of CAD systems according to the used image modalities and the machine learning based classifiers. Potential research studies have been discussed to create a more objective and efficient CAD systems.

Ultrasound Imaging Technologies for Breast Cancer Detection and Management: A Review

Ultrasound imaging is a commonly used modality for breast cancer detection and diagnosis. In this review, we summarize ultrasound imaging technologies and their clinical applications for the management of breast cancer patients. The technologies include ultrasound elastography, contrast-enhanced ultrasound, 3-D ultrasound, automatic breast ultrasound and computer-aided detection of breast ultrasound. We summarize the study results seen in the literature and discuss their future directions. We also provide a review of ultrasound-guided, breast biopsy and the fusion of ultrasound with other imaging modalities, especially magnetic resonance imaging (MRI). For comparison, we also discuss the diagnostic performance of mammography, MRI, positron emission tomography and computed tomography for breast cancer diagnosis at the end of this review. New ultrasound imaging techniques, ultrasound-guided biopsy and the fusion of ultrasound with other modalities provide important tools for the management of breast patients.

The Role of Affordable, Point-of-Care Technologies for Cancer Care in Low- and Middle-Income Countries: A Review and Commentary

As the burden of non-communicable diseases such as cancer continues to rise in low- and middle-income countries (LMICs), it is essential to identify and invest in promising solutions for cancer control and treatment. Point-of-care technologies (POCTs) have played critical roles in curbing infectious disease epidemics in both high- and low-income settings, and their successes can serve as a model for transforming cancer care in LMICs, where access to traditional clinical resources is often limited. The versatility, cost-effectiveness, and simplicity of POCTs warrant attention for their potential to revolutionize cancer detection, diagnosis, and treatment. This paper reviews the landscape of affordable POCTs for cancer care in LMICs with a focus on imaging tools, in vitro diagnostics, and treatment technologies and aspires to encourage innovation and further investment in this space.

Sonoelastomics for Breast Tumor Classification: A Radiomics Approach with Clustering-Based Feature Selection on Sonoelastography

A radiomics approach to sonoelastography, called "sonoelastomics," is proposed for classification of benign and malignant breast tumors. From sonoelastograms of breast tumors, a high-throughput 364-dimensional feature set was calculated consisting of shape features, intensity statistics, gray-level co-occurrence matrix texture features and contourlet texture features, which quantified the shape, hardness and hardness heterogeneity of a tumor. The high-throughput features were then selected for feature reduction using hierarchical clustering and three-feature selection metrics. For a data set containing 42 malignant and 75 benign tumors from 117 patients, seven selected sonoelastomic features achieved an area under the receiver operating characteristic curve of 0.917, an accuracy of 88.0%, a sensitivity of 85.7% and a specificity of 89.3% in a validation set via the leave-one-out cross-validation, revealing superiority over the principal component analysis, deep polynomial networks and manually selected features. The sonoelastomic features are valuable in breast tumor differentiation.