A Review of Breast Cancer Detection in Medical Images
01 Dec 2018-pp 1-4
TL;DR: This paper introduces some commonly used medical imaging methods for diagnosis of breast cancer, and based on them some recently proposed approaches for breast cancer detection with computer vision and machine learning techniques are investigated.
Abstract: Breast cancer is a malignant tumor that occurs in the glandular epithelium of the breast. It is considered to be one of the most common cancers affecting women in the world. However, there is not an effective way to cure breast cancer yet, the key to reducing the risk of death is the early detection and diagnosis of breast cancer. Accurate diagnosis of breast cancer normally requires analysis of medical images of different modalities. There is a great need of automated system that could analyze these images accurately and rapidly. In this paper, we introduce some commonly used medical imaging methods for diagnosis of breast cancer, and based on them we investigate some recently proposed approaches for breast cancer detection with computer vision and machine learning techniques. Finally, we compare and analyze the detection performance of different methods on histological images and mammograph images respectively.
Citations
More filters
TL;DR: The comparative analysis of machine learning, deep learning and data mining techniques being used for the prediction of breast cancer is presented to find out the most appropriate method that will support the large dataset with good accuracy of prediction.
Abstract: Breast cancer is type of tumor that occurs in the tissues of the breast. It is most common type of cancer found in women around the world and it is among the leading causes of deaths in women. This article presents the comparative analysis of machine learning, deep learning and data mining techniques being used for the prediction of breast cancer. Many researchers have put their efforts on breast cancer diagnoses and prognoses, every technique has different accuracy rate and it varies for different situations, tools and datasets being used. Our main focus is to comparatively analyze different existing Machine Learning and Data Mining techniques in order to find out the most appropriate method that will support the large dataset with good accuracy of prediction. The main purpose of this review is to highlight all the previous studies of machine learning algorithms that are being used for breast cancer prediction and this article provides the all necessary information to the beginners who want to analyze the machine learning algorithms to gain the base of deep learning.
72 citations
Cites background from "A Review of Breast Cancer Detection..."
...Breast cancer is originated through malignant tumors, when the growth of the cell got out of control [3]....
[...]
TL;DR: A complete CAD system for mass detection and diagnosis, which consists of four steps where the preprocessing where the image is enhanced and the noise removed, and the support vector machine (SVM) is used to classify the abnormalities as malignant or benign.
Abstract: Mammography is currently the most powerful technique for early detection of breast cancer. To assist radiologists to better interpret mammogram images, computer-aided detection and diagnosis (CAD) systems have been proposed. This paper proposes a complete CAD system for mass detection and diagnosis, which consists of four steps. The first step consists of the preprocessing where the image is enhanced and the noise removed. In the second step, the abnormalities are segmented using the proposed HRAK algorithm. In the third step, the false positives are reduced using texture and shape features and the bagged trees classifier. Finally, the support vector machine (SVM) is used to classify the abnormalities as malignant or benign. The proposed CAD system is verified with both the MIAS and CBIS-DDSM databases. The experimental results proved to be successful. The accuracy detection rate achieves 93,15% for sensitivity and 0,467 FPPI for MIAS and 90,85% for sensitivity and 0,65 FPPI for CBIS-DDSM. The accuracy classification rate achieves 94,2% and the AUC 0,95 for MIAS and 90,44% and 0,9 for CBIS-DDSM.
30 citations
TL;DR: The aim of this review article is to help to choose the appropriate breast cancer prediction techniques specifically in the Big data environment to produce effective and efficient result, because “Early detection is the key to prevention-in case of any cancer”.
Abstract: In recent years, big data in health care is commonly used for the prediction of diseases. The most common cancer is breast cancer infections of metropolitan Indian women as well as in women worldwide with a broadly factor occurrence among nations and regions. According to WHO, among 14% of all cancer tumours in women breast cancer is well-known cancer in women in India also. Few researches have been done on breast cancer prediction on Big data. Big data is now triggering a revolution in healthcare, resulting in better and more optimized outcomes. Rapid technological advancements have increased data generation; EHR (Electronic Health Record) systems produce a massive amount of patient-level data. In the healthcare industry, applications of big data will help to improve outcomes. However, the traditional prediction models have less efficiency in terms of accuracy and error rate. This review article is about the comparative assessment of complex data mining, machine learning, deep learning models used for identifying breast cancer because accuracy rate of any particular algorithm depends on various factors such as implementation framework, datasets(small or large),types of dataset used(attribute based or image based)etc. Aim of this review article is to help to choose the appropriate breast cancer prediction techniques specifically in the Big data environment to produce effective and efficient result, Because “Early detection is the key to prevention-in case of any cancer”.
12 citations
7 citations
TL;DR: In this paper , a systematic literature review on the deep learning-based methods for breast cancer detection is presented, which can guide practitioners and researchers in understanding the challenges and new trends in the field.
Abstract: Breast cancer is one of the precarious conditions that affect women, and a substantive cure has not yet been discovered for it. With the advent of Artificial intelligence (AI), recently, deep learning techniques have been used effectively in breast cancer detection, facilitating early diagnosis and therefore increasing the chances of patients’ survival. Compared to classical machine learning techniques, deep learning requires less human intervention for similar feature extraction. This study presents a systematic literature review on the deep learning-based methods for breast cancer detection that can guide practitioners and researchers in understanding the challenges and new trends in the field. Particularly, different deep learning-based methods for breast cancer detection are investigated, focusing on the genomics and histopathological imaging data. The study specifically adopts the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA), which offer a detailed analysis and synthesis of the published articles. Several studies were searched and gathered, and after the eligibility screening and quality evaluation, 98 articles were identified. The results of the review indicated that the Convolutional Neural Network (CNN) is the most accurate and extensively used model for breast cancer detection, and the accuracy metrics are the most popular method used for performance evaluation. Moreover, datasets utilized for breast cancer detection and the evaluation metrics are also studied. Finally, the challenges and future research direction in breast cancer detection based on deep learning models are also investigated to help researchers and practitioners acquire in-depth knowledge of and insight into the area.
6 citations
References
More filters
Radboud University Nijmegen1, Eindhoven University of Technology2, Utrecht University3, Beth Israel Deaconess Medical Center4, Massachusetts Institute of Technology5, Harvard University6, The Chinese University of Hong Kong7, Munich Business School8, Middle East Technical University9, University of Toronto10, University of Warwick11, Coventry Health Care12, Qatar University13, HTW Berlin - University of Applied Sciences14, Tampere University of Technology15, University of Tampere16, Technische Universität München17, Osaka University18, University of South Florida19, National Academy of Sciences of Belarus20, University of Castilla–La Mancha21, Pontifical Catholic University of Peru22, Pierre-and-Marie-Curie University23
TL;DR: In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints.
Abstract: Importance Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. Objective Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin–stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists’ diagnoses in a diagnostic setting. Design, Setting, and Participants Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC). Exposures Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation. Main Outcomes and Measures The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor. Results The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884];P Conclusions and Relevance In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints. Whether this approach has clinical utility will require evaluation in a clinical setting.
2,116 citations
"A Review of Breast Cancer Detection..." refers methods in this paper
...3) Camelyon16: Camelyon16 [5] dataset contains 399 whole-slide images from 399 patients in the Netherlands: Radboud University Medical Center (RUMC) and University Medical Center Utrecht (UMCU)....
[...]
01 Jan 2007
1,101 citations
"A Review of Breast Cancer Detection..." refers background in this paper
...2) DDSM: DDSM [7] is a digital mammograph images database for breast cancer diagnosis....
[...]
...There are 410 mammograms of 115 cases which are divided into six possible classes same as DDSM. 116 images of it contain benign or malignant masses, and the rest does not contain any masses....
[...]
TL;DR: A new mammographic database built with full-field digital mammograms, which presents a wide variability of cases, and is made publicly available together with precise annotations is presented and can be a reference for future works centered or related to breast cancer imaging.
724 citations
"A Review of Breast Cancer Detection..." refers background in this paper
...3) INbreast: INbreast [10] is a database that contains high quality full-field digital (FFD) mammograms....
[...]
TL;DR: An experimental study on learning from crowds that handles data aggregation directly as part of the learning process of the convolutional neural network (CNN) via additional crowdsourcing layer (AggNet), which gives valuable insights into the functionality of deep CNN learning from crowd annotations and proves the necessity of data aggregation integration.
Abstract: The lack of publicly available ground-truth data has been identified as the major challenge for transferring recent developments in deep learning to the biomedical imaging domain. Though crowdsourcing has enabled annotation of large scale databases for real world images, its application for biomedical purposes requires a deeper understanding and hence, more precise definition of the actual annotation task. The fact that expert tasks are being outsourced to non-expert users may lead to noisy annotations introducing disagreement between users. Despite being a valuable resource for learning annotation models from crowdsourcing, conventional machine-learning methods may have difficulties dealing with noisy annotations during training. In this manuscript, we present a new concept for learning from crowds that handle data aggregation directly as part of the learning process of the convolutional neural network (CNN) via additional crowdsourcing layer (AggNet). Besides, we present an experimental study on learning from crowds designed to answer the following questions. 1) Can deep CNN be trained with data collected from crowdsourcing? 2) How to adapt the CNN to train on multiple types of annotation datasets (ground truth and crowd-based)? 3) How does the choice of annotation and aggregation affect the accuracy? Our experimental setup involved Annot8, a self-implemented web-platform based on Crowdflower API realizing image annotation tasks for a publicly available biomedical image database. Our results give valuable insights into the functionality of deep CNN learning from crowd annotations and prove the necessity of data aggregation integration.
512 citations
"A Review of Breast Cancer Detection..." refers methods in this paper
...Method dataset Precision (%) Recall (%) F2 score (%) AUC AggNet [4] AMIDA13 44....
[...]
...[4] proposed multi-scale CNN AggNet to learn feature from crowd annotation....
[...]
TL;DR: A learning-based framework for robust and automatic nucleus segmentation with shape preservation is proposed that is applicable to different staining histopathology images and general enough to perform well across multiple scenarios.
Abstract: Computer-aided image analysis of histopathology specimens could potentially provide support for early detection and improved characterization of diseases such as brain tumor, pancreatic neuroendocrine tumor (NET), and breast cancer. Automated nucleus segmentation is a prerequisite for various quantitative analyses including automatic morphological feature computation. However, it remains to be a challenging problem due to the complex nature of histopathology images. In this paper, we propose a learning-based framework for robust and automatic nucleus segmentation with shape preservation. Given a nucleus image, it begins with a deep convolutional neural network (CNN) model to generate a probability map, on which an iterative region merging approach is performed for shape initializations. Next, a novel segmentation algorithm is exploited to separate individual nuclei combining a robust selection-based sparse shape model and a local repulsive deformable model. One of the significant benefits of the proposed framework is that it is applicable to different staining histopathology images. Due to the feature learning characteristic of the deep CNN and the high level shape prior modeling, the proposed method is general enough to perform well across multiple scenarios. We have tested the proposed algorithm on three large-scale pathology image datasets using a range of different tissue and stain preparations, and the comparative experiments with recent state of the arts demonstrate the superior performance of the proposed approach.
311 citations
"A Review of Breast Cancer Detection..." refers methods in this paper
...[17] proposed a novel nucleus segmentation method with deep convolutional neural network and selection-based sparse shape model....
[...]