Classification of Breast Cancer in Mammograms with Deep Learning Adding a Fifth Class
Breast cancer is one of the diseases of most profound concern, with the most prevalence worldwide, where early detections and diagnoses play the leading role against this disease achieved through imaging techniques such as mammography. Radiologists tend to have a high false positive rate for mammogr...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/23/11398 |
| _version_ | 1827675086140735488 |
|---|---|
| author | Salvador Castro-Tapia Celina Lizeth Castañeda-Miranda Carlos Alberto Olvera-Olvera Héctor A. Guerrero-Osuna José Manuel Ortiz-Rodriguez Ma. del Rosario Martínez-Blanco Germán Díaz-Florez Jorge Domingo Mendiola-Santibañez Luis Octavio Solís-Sánchez |
| author_facet | Salvador Castro-Tapia Celina Lizeth Castañeda-Miranda Carlos Alberto Olvera-Olvera Héctor A. Guerrero-Osuna José Manuel Ortiz-Rodriguez Ma. del Rosario Martínez-Blanco Germán Díaz-Florez Jorge Domingo Mendiola-Santibañez Luis Octavio Solís-Sánchez |
| author_sort | Salvador Castro-Tapia |
| collection | DOAJ |
| description | Breast cancer is one of the diseases of most profound concern, with the most prevalence worldwide, where early detections and diagnoses play the leading role against this disease achieved through imaging techniques such as mammography. Radiologists tend to have a high false positive rate for mammography diagnoses and an accuracy of around 82%. Currently, deep learning (DL) techniques have shown promising results in the early detection of breast cancer by generating computer-aided diagnosis (CAD) systems implementing convolutional neural networks (CNNs). This work focuses on applying, evaluating, and comparing the architectures: AlexNet, GoogLeNet, Resnet50, and Vgg19 to classify breast lesions after using transfer learning with fine-tuning and training the CNN with regions extracted from the MIAS and INbreast databases. We analyzed 14 classifiers, involving 4 classes as several researches have done it before, corresponding to benign and malignant microcalcifications and masses, and as our main contribution, we also added a 5th class for the normal tissue of the mammary parenchyma increasing the correct detection; in order to evaluate the architectures with a statistical analysis based on the received operational characteristics (ROC), the area under the curve (AUC), F1 Score, accuracy, precision, sensitivity, and specificity. We generate the best results with the CNN GoogLeNet trained with five classes on a balanced database with an AUC of 99.29%, F1 Score of 91.92%, the accuracy of 91.92%, precision of 92.15%, sensitivity of 91.70%, and specificity of 97.66%, concluding that GoogLeNet is optimal as a classifier in a CAD system to deal with breast cancer. |
| first_indexed | 2024-03-10T04:57:13Z |
| format | Article |
| id | doaj.art-681be7432c424ef983dd5bb4607c5fa6 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:57:13Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-681be7432c424ef983dd5bb4607c5fa62023-11-23T02:07:32ZengMDPI AGApplied Sciences2076-34172021-12-0111231139810.3390/app112311398Classification of Breast Cancer in Mammograms with Deep Learning Adding a Fifth ClassSalvador Castro-Tapia0Celina Lizeth Castañeda-Miranda1Carlos Alberto Olvera-Olvera2Héctor A. Guerrero-Osuna3José Manuel Ortiz-Rodriguez4Ma. del Rosario Martínez-Blanco5Germán Díaz-Florez6Jorge Domingo Mendiola-Santibañez7Luis Octavio Solís-Sánchez8Laboratorio de Sistemas Inteligentes de Visión Artificial, Posgrado en Ingeniería y Tecnología Aplicada, Universidad Autónoma de Zacatecas, 801 Ramón López Velarde Avenue, Centro, Zacatecas 98000, MexicoLaboratorio de Sistemas Inteligentes de Visión Artificial, Posgrado en Ingeniería y Tecnología Aplicada, Universidad Autónoma de Zacatecas, 801 Ramón López Velarde Avenue, Centro, Zacatecas 98000, MexicoPosgrado en Ciencias de Ingeniería, Universidad Autónoma de Zacatecas, Km. 6 La Escondida, Zacatecas 98160, MexicoLaboratorio de Sistemas Inteligentes de Visión Artificial, Posgrado en Ingeniería y Tecnología Aplicada, Universidad Autónoma de Zacatecas, 801 Ramón López Velarde Avenue, Centro, Zacatecas 98000, MexicoLaboratorio de Sistemas Inteligentes de Visión Artificial, Posgrado en Ingeniería y Tecnología Aplicada, Universidad Autónoma de Zacatecas, 801 Ramón López Velarde Avenue, Centro, Zacatecas 98000, MexicoLaboratorio de Sistemas Inteligentes de Visión Artificial, Posgrado en Ingeniería y Tecnología Aplicada, Universidad Autónoma de Zacatecas, 801 Ramón López Velarde Avenue, Centro, Zacatecas 98000, MexicoLaboratorio de Sistemas Inteligentes de Visión Artificial, Posgrado en Ingeniería y Tecnología Aplicada, Universidad Autónoma de Zacatecas, 801 Ramón López Velarde Avenue, Centro, Zacatecas 98000, MexicoFacultad de Ingeniería UAQ, Cerro de las Campanas, Santiago de Querétaro 76010, MexicoLaboratorio de Sistemas Inteligentes de Visión Artificial, Posgrado en Ingeniería y Tecnología Aplicada, Universidad Autónoma de Zacatecas, 801 Ramón López Velarde Avenue, Centro, Zacatecas 98000, MexicoBreast cancer is one of the diseases of most profound concern, with the most prevalence worldwide, where early detections and diagnoses play the leading role against this disease achieved through imaging techniques such as mammography. Radiologists tend to have a high false positive rate for mammography diagnoses and an accuracy of around 82%. Currently, deep learning (DL) techniques have shown promising results in the early detection of breast cancer by generating computer-aided diagnosis (CAD) systems implementing convolutional neural networks (CNNs). This work focuses on applying, evaluating, and comparing the architectures: AlexNet, GoogLeNet, Resnet50, and Vgg19 to classify breast lesions after using transfer learning with fine-tuning and training the CNN with regions extracted from the MIAS and INbreast databases. We analyzed 14 classifiers, involving 4 classes as several researches have done it before, corresponding to benign and malignant microcalcifications and masses, and as our main contribution, we also added a 5th class for the normal tissue of the mammary parenchyma increasing the correct detection; in order to evaluate the architectures with a statistical analysis based on the received operational characteristics (ROC), the area under the curve (AUC), F1 Score, accuracy, precision, sensitivity, and specificity. We generate the best results with the CNN GoogLeNet trained with five classes on a balanced database with an AUC of 99.29%, F1 Score of 91.92%, the accuracy of 91.92%, precision of 92.15%, sensitivity of 91.70%, and specificity of 97.66%, concluding that GoogLeNet is optimal as a classifier in a CAD system to deal with breast cancer.https://www.mdpi.com/2076-3417/11/23/11398breast cancerearly detectiondeep learning (DL)convolutional neural networks (CNN)classificationmasses |
| spellingShingle | Salvador Castro-Tapia Celina Lizeth Castañeda-Miranda Carlos Alberto Olvera-Olvera Héctor A. Guerrero-Osuna José Manuel Ortiz-Rodriguez Ma. del Rosario Martínez-Blanco Germán Díaz-Florez Jorge Domingo Mendiola-Santibañez Luis Octavio Solís-Sánchez Classification of Breast Cancer in Mammograms with Deep Learning Adding a Fifth Class Applied Sciences breast cancer early detection deep learning (DL) convolutional neural networks (CNN) classification masses |
| title | Classification of Breast Cancer in Mammograms with Deep Learning Adding a Fifth Class |
| title_full | Classification of Breast Cancer in Mammograms with Deep Learning Adding a Fifth Class |
| title_fullStr | Classification of Breast Cancer in Mammograms with Deep Learning Adding a Fifth Class |
| title_full_unstemmed | Classification of Breast Cancer in Mammograms with Deep Learning Adding a Fifth Class |
| title_short | Classification of Breast Cancer in Mammograms with Deep Learning Adding a Fifth Class |
| title_sort | classification of breast cancer in mammograms with deep learning adding a fifth class |
| topic | breast cancer early detection deep learning (DL) convolutional neural networks (CNN) classification masses |
| url | https://www.mdpi.com/2076-3417/11/23/11398 |
| work_keys_str_mv | AT salvadorcastrotapia classificationofbreastcancerinmammogramswithdeeplearningaddingafifthclass AT celinalizethcastanedamiranda classificationofbreastcancerinmammogramswithdeeplearningaddingafifthclass AT carlosalbertoolveraolvera classificationofbreastcancerinmammogramswithdeeplearningaddingafifthclass AT hectoraguerreroosuna classificationofbreastcancerinmammogramswithdeeplearningaddingafifthclass AT josemanuelortizrodriguez classificationofbreastcancerinmammogramswithdeeplearningaddingafifthclass AT madelrosariomartinezblanco classificationofbreastcancerinmammogramswithdeeplearningaddingafifthclass AT germandiazflorez classificationofbreastcancerinmammogramswithdeeplearningaddingafifthclass AT jorgedomingomendiolasantibanez classificationofbreastcancerinmammogramswithdeeplearningaddingafifthclass AT luisoctaviosolissanchez classificationofbreastcancerinmammogramswithdeeplearningaddingafifthclass |