Automatic detection of injuries in mammograms using image analysis techniques

Fiallos, Carlos B.; Pérez, María Jesús Verdú; Conci, Aura; Andaluz, Víctor H.

doi:10.1109/iwssip.2015.7314222

Cited by 6 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The AUC of CNN was 0.87, which was higher than the mean AUC of the radiologists (0.84), though the difference was not significant. On the other hand, [74], [26] circumvented the use of deep learning by adopting the use of wavelet decomposition. Although our research is focused on CNN models, their work is, however, worth mentioning and may interest others.…”

Section: ) Calcificationmentioning

confidence: 99%

A State-of-the-Art Survey on Deep Learning Methods for Detection of Architectural Distortion From Digital Mammography

Oyelade

Ezugwu

2020

IEEE Access

View full text Add to dashboard Cite

Breast cancer is a type of cancer that has risen to be the second cause of death among women. Classification of breast tissues into normal, benign, or malignant depends on the presence of abnormalities like microcalcifications, masses, architectural distortions, and asymmetries. Architectural distortion (AD) is subtle in detection with no association with masses but shows the abnormal arrangement of tissue strands, often in a radial, spiculation, or random pattern. It is widely rated as the third symptom of breast cancer which is the most commonly missed abnormality. Most computational approaches characterizing abnormalities in breast images often concentrate on the detection of microcalcification and masses with architectural distortions appearing as a secondary finding. The subtle nature and a minimal occurrence of architectural distortions may seem to complicate computational approaches for its detection. As a result, little research interest has been recorded in this area. It is widely reported that some cases of recent breast cancer are wrongly diagnosed due to the omission in detecting the presence of architectural distortion at the early stage of the disease. However, we discovered that most computational solutions to early detection of breast cancer are focused mainly on detecting other abnormalities such as masses and microcalcification, which are some evidence of the advanced stage of the disease. To emphasise the little efforts channeled towards detection of AD compared to other abnormalities, this article aims to detail the review of such studies in the last decade. To the best of our knowledge, this study presents the first review which focuses on the detection of architectural distortion (AD) from mammographic images. Furthermore, this article presents a comprehensive review of approaches, advances, and challenges on the computational methods for detecting AD, with the sole aim of advancing the use of deep learning models in detecting AD. Moreover, a comparative study of performance analyses of articles surveyed in this article is investigated. Our findings revealed that about 70% of the existing literature adopted Gabor Filters, while just less than 10% leveraged on the state-ofthe-art performances recorded in computer vision and deep learning, in building outstanding computational models for the detection of AD. The current study also discovered that using a deep learning approach, such as the convolution neural network (CNN) method, can yield a significant increase in performance for the task of detection of architectural distortions. This assertion is based on literature results obtained using the CNN, which generates an accuracy of 99.4% compared to the use of Gabor filters method, which accounts for 95% accuracy.

show abstract

Section: ) Calcificationmentioning

confidence: 99%

A State-of-the-Art Survey on Deep Learning Methods for Detection of Architectural Distortion From Digital Mammography

Oyelade

Ezugwu

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…detection in mammography based on the general preprocessing steps: removal of noise, partitioning image, extraction of the area of interest (ROI) and other features that illusrate the possible mismatches between the ROI of both left and right breasts. [17] The author found that till now in cancer detection of breast region, first and second order GLCM features were mostly used, according to their best knowledge there is no evidence of using of third order features of GLCM. [18] The author reviews the diagnosis methods and breast image enhancement approaches for detection of breast cancer in early stage.…”

Section: Related Workmentioning

confidence: 99%

Content Based Image Retrieval System for Mammogram Images Using BI_RADS Standard and SVM.

Kaur¹

2018

IJRASET

View full text Add to dashboard Cite

The mammogram images are exposed to region of interest algorithm for extraction of infected area. The region of interest algorithm is fine-tuned using the combination of red, green and blue color matrices thresholds. The threshold limits are discussed in later section of the paper. The features including spot size, shape, brightness, contrast, density and Zernike moments are used to generate a vector set that is used to retrieve the images from the data base. The data base used for CBIR system for mammograms is MIAS data base consisting of different class of mammogram images. The data base contains images in PGM format and is converted to jpeg format using the matlab function class. The database images are categorized into different class as per the database instruction. Equal no. of images from each class are used to train a support vector machine classifier. Rests of the images are used to test the algorithm.

show abstract

“…Para extração de atributos de textura, foram avaliadas as medidas de entropia, energia, média e desvio padrão de componentes das transformadas wavelet coiflets 5 e ranklet. Transformadas wavelet descrevem de forma precisa atributos locais de sinais da imagem [Fiallos et al 2015]. A decomposição de wavelets resultam na sub-banda de aproximação, que representa uma aproximaçãoà imagem original, e em três sub-bandas que apresentam detalhes da imagem nas direções vertical (V ), horizontal (H) e diagonal (D) [Lahmiri 2016].…”

Section: Método Propostounclassified

Avaliação de Atributos de Textura de Núcleos Neoplásicos para a Classificação de Imagens Histológicas de Linfoma

Tosta¹,

Faria²,

Neves³

et al. 2017

Anais Do Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS)

View full text Add to dashboard Cite

Pela utilização de técnicas de processamento digital de imagens, é possível desenvolver sistemas de auxílio a diagnósticos para que a análise de amostras histológicas torne-se mais objetiva. Assim, este trabalho propõe um algoritmo para a classificação de imagens histológicas de linfoma folicular e leucemia linfóide crõnica. Para identificação de núcleos neoplásicos, o canal R do modelo de cores RGB foi extráıdo, seguido pelas aplicações de equalização do histograma, filtro Gaussiano, fuzzy 3-partition entropy com o método de evolução diferencial, valley-emphasis e operações morfológicas. Atributos de textura obtidos pelas transformadas ranklet e wavelet foram avaliados pela classificação de máquinas de vetores suporte. A segmentação de núcleos neoplásicos das lesões proporcionou uma taxa média de acurácia de 80,49%

show abstract

Automatic detection of injuries in mammograms using image analysis techniques

Cited by 6 publications

References 10 publications

A State-of-the-Art Survey on Deep Learning Methods for Detection of Architectural Distortion From Digital Mammography

A State-of-the-Art Survey on Deep Learning Methods for Detection of Architectural Distortion From Digital Mammography

Content Based Image Retrieval System for Mammogram Images Using BI_RADS Standard and SVM.

Avaliação de Atributos de Textura de Núcleos Neoplásicos para a Classificação de Imagens Histológicas de Linfoma

Contact Info

Product

Resources

About