Breast histopathological image analysis using image processing techniques for diagnostic purposes: A methodological review

Rashmi, Richa; Prasad, Keerthana; Udupa, Chethana Babu K.

doi:10.1007/s10916-021-01786-9

Cited by 49 publications

(16 citation statements)

References 174 publications

(153 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analysis of breast cancer histopathological images by utilizing image processing methods developed for the medical field has received much attention as of late. Non-automatic examination of breast cancer histopathological images is susceptible to a host of problems including observer variability, human error and an extremely tedious procedure [46]. A solution that alleviates these obstacles is the use of CAD systems.…”

Section: Discussionmentioning

confidence: 99%

Classification of Breast Tumors Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods

Abbasniya

Sheikholeslamzadeh²,

Nasiri³

et al. 2022

Computers and Electrical Engineering

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Classification of Breast Tumors Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods

Abbasniya

Sheikholeslamzadeh²,

Nasiri³

et al. 2022

Computers and Electrical Engineering

View full text Add to dashboard Cite

“…Since mammograms do not enable to distinguish calcifications associated with benign from malignant pathologies, if any anomalies and suspect BMCs are observed on mammograms, histological analyses [53] will be performed to confirm or rule out the presence of cancerous cells (Figure 4). To this end, a fraction of suspect tissue has to be collected.…”

Section: Histological Analysis: the Utmost Assessment For Cancer Diag...mentioning

confidence: 99%

Multiscale approach to provide a better physicochemical description of women breast microcalcifications

Petay¹,

Cherfan²,

Bouderlique³

et al. 2022

Comptes Rendus. Chimie

View full text Add to dashboard Cite

Despite the incidence of breast cancer among women, mammography and anatomopathology investigations are still the gold standard method for preventive screening and diagnosis. Several criteria are used to diagnose precisely the severity of the pathology like the distribution and shape of breast microcalcifications (BMCs). However, the link between the different chemical phases of BMCs and the cancer stage remains unclear. As BMCs physicochemical speciation has the potential to help clinicians during their diagnosis, this study aims to propose a methodology using advanced spectroscopical analysis techniques to finely characterize BMCs and uncover the relationship between

show abstract

“…At MF 100×, the study of tissue structures and nuclear distribution assists in the identification of various cancer subtypes, and at MF 400×, numerous nuclear features, including mitotic count, prominent nuclei and hyperchromatic nuclei, are investigated. Therefore, each MF has a significant impact on the determination of BC (Rashmi et al , 2021). Although histopathology is critical, it can be time-consuming and prone to diagnostic errors (Wilson et al , 2018).…”

Section: Introductionmentioning

confidence: 99%

Binary classification of multi-magnification histopathological breast cancer images using late fusion and transfer learning

Nakach

Zerouaoui²,

Idri³

2023

DTA

View full text Add to dashboard Cite

PurposeHistopathology biopsy imaging is currently the gold standard for the diagnosis of breast cancer in clinical practice. Pathologists examine the images at various magnifications to identify the type of tumor because if only one magnification is taken into account, the decision may not be accurate. This study explores the performance of transfer learning and late fusion to construct multi-scale ensembles that fuse different magnification-specific deep learning models for the binary classification of breast tumor slides.Design/methodology/approachThree pretrained deep learning techniques (DenseNet 201, MobileNet v2 and Inception v3) were used to classify breast tumor images over the four magnification factors of the Breast Cancer Histopathological Image Classification dataset (40×, 100×, 200× and 400×). To fuse the predictions of the models trained on different magnification factors, different aggregators were used, including weighted voting and seven meta-classifiers trained on slide predictions using class labels and the probabilities assigned to each class. The best cluster of the outperforming models was chosen using the Scott–Knott statistical test, and the top models were ranked using the Borda count voting system.FindingsThis study recommends the use of transfer learning and late fusion for histopathological breast cancer image classification by constructing multi-magnification ensembles because they perform better than models trained on each magnification separately.Originality/valueThe best multi-scale ensembles outperformed state-of-the-art integrated models and achieved an accuracy mean value of 98.82 per cent, precision of 98.46 per cent, recall of 100 per cent and F1-score of 99.20 per cent.

show abstract

Breast histopathological image analysis using image processing techniques for diagnostic purposes: A methodological review

Cited by 49 publications

References 174 publications

Classification of Breast Tumors Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods

Classification of Breast Tumors Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods

Multiscale approach to provide a better physicochemical description of women breast microcalcifications

Binary classification of multi-magnification histopathological breast cancer images using late fusion and transfer learning

Contact Info

Product

Resources

About