Breast Cancer Mass Detection in DCE–MRI Using Deep-Learning Features Followed by Discrimination of Infiltrative vs. In Situ Carcinoma through a Machine-Learning Approach
Breast cancer is the leading cause of cancer deaths worldwide in women. This aggressive tumor can be categorized into two main groups—in situ and infiltrative, with the latter being the most common malignant lesions. The current use of magnetic resonance imaging (MRI) was shown to provide the highes...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/17/6109 |
| id |
doaj-cb9fdf0e2a5b496ba3023a6b144fe0f0 |
|---|---|
| record_format |
Article |
| spelling |
doaj-cb9fdf0e2a5b496ba3023a6b144fe0f02020-11-25T03:18:30ZengMDPI AGApplied Sciences2076-34172020-09-01106109610910.3390/app10176109Breast Cancer Mass Detection in DCE–MRI Using Deep-Learning Features Followed by Discrimination of Infiltrative vs. In Situ Carcinoma through a Machine-Learning ApproachLuana Conte0Benedetta Tafuri1Maurizio Portaluri2Alessandro Galiano3Eleonora Maggiulli4Giorgio De Nunzio5Laboratory of Biomedical Physics and Environment, Department of Mathematics and Physics “E. De Giorgi”, University of Salento, 73100 Lecce, ItalyLaboratory of Biomedical Physics and Environment, Department of Mathematics and Physics “E. De Giorgi”, University of Salento, 73100 Lecce, ItalyOperative Unit of Radiotherapy, ASL (Local Health Authority), Brindisi, and ‘Di Summa-Perrino’ Hospital, 72100 Brindisi, ItalyOperative Unit of Radiodiagnostics, ASL (Local Health Authority), Brindisi, and ‘Di Summa-Perrino’ Hospital, 72100 Brindisi, ItalyOperative Unit of Medical Physics, ASL (Local Health Authority), Brindisi, and ‘Di Summa-Perrino’ Hospital, 72100 Brindisi, ItalyLaboratory of Biomedical Physics and Environment, Department of Mathematics and Physics “E. De Giorgi”, University of Salento, 73100 Lecce, ItalyBreast cancer is the leading cause of cancer deaths worldwide in women. This aggressive tumor can be categorized into two main groups—in situ and infiltrative, with the latter being the most common malignant lesions. The current use of magnetic resonance imaging (MRI) was shown to provide the highest sensitivity in the detection and discrimination between benign vs. malignant lesions, when interpreted by expert radiologists. In this article, we present the prototype of a computer-aided detection/diagnosis (CAD) system that could provide valuable assistance to radiologists for discrimination between in situ and infiltrating tumors. The system consists of two main processing levels—(1) localization of possibly tumoral regions of interest (ROIs) through an iterative procedure based on intensity values (ROI Hunter), followed by a deep-feature extraction and classification method for false-positive rejection; and (2) characterization of the selected ROIs and discrimination between in situ and invasive tumor, consisting of Radiomics feature extraction and classification through a machine-learning algorithm. The CAD system was developed and evaluated using a DCE–MRI image database, containing at least one confirmed mass per image, as diagnosed by an expert radiologist. When evaluating the accuracy of the ROI Hunter procedure with respect to the radiologist-drawn boundaries, sensitivity to mass detection was found to be 75%. The AUC of the ROC curve for discrimination between in situ and infiltrative tumors was 0.70.https://www.mdpi.com/2076-3417/10/17/6109breast cancerRadiomicsmachine learningdeep learningsegmentationin situ breast cancer |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Luana Conte Benedetta Tafuri Maurizio Portaluri Alessandro Galiano Eleonora Maggiulli Giorgio De Nunzio |
| spellingShingle |
Luana Conte Benedetta Tafuri Maurizio Portaluri Alessandro Galiano Eleonora Maggiulli Giorgio De Nunzio Breast Cancer Mass Detection in DCE–MRI Using Deep-Learning Features Followed by Discrimination of Infiltrative vs. In Situ Carcinoma through a Machine-Learning Approach Applied Sciences breast cancer Radiomics machine learning deep learning segmentation in situ breast cancer |
| author_facet |
Luana Conte Benedetta Tafuri Maurizio Portaluri Alessandro Galiano Eleonora Maggiulli Giorgio De Nunzio |
| author_sort |
Luana Conte |
| title |
Breast Cancer Mass Detection in DCE–MRI Using Deep-Learning Features Followed by Discrimination of Infiltrative vs. In Situ Carcinoma through a Machine-Learning Approach |
| title_short |
Breast Cancer Mass Detection in DCE–MRI Using Deep-Learning Features Followed by Discrimination of Infiltrative vs. In Situ Carcinoma through a Machine-Learning Approach |
| title_full |
Breast Cancer Mass Detection in DCE–MRI Using Deep-Learning Features Followed by Discrimination of Infiltrative vs. In Situ Carcinoma through a Machine-Learning Approach |
| title_fullStr |
Breast Cancer Mass Detection in DCE–MRI Using Deep-Learning Features Followed by Discrimination of Infiltrative vs. In Situ Carcinoma through a Machine-Learning Approach |
| title_full_unstemmed |
Breast Cancer Mass Detection in DCE–MRI Using Deep-Learning Features Followed by Discrimination of Infiltrative vs. In Situ Carcinoma through a Machine-Learning Approach |
| title_sort |
breast cancer mass detection in dce–mri using deep-learning features followed by discrimination of infiltrative vs. in situ carcinoma through a machine-learning approach |
| publisher |
MDPI AG |
| series |
Applied Sciences |
| issn |
2076-3417 |
| publishDate |
2020-09-01 |
| description |
Breast cancer is the leading cause of cancer deaths worldwide in women. This aggressive tumor can be categorized into two main groups—in situ and infiltrative, with the latter being the most common malignant lesions. The current use of magnetic resonance imaging (MRI) was shown to provide the highest sensitivity in the detection and discrimination between benign vs. malignant lesions, when interpreted by expert radiologists. In this article, we present the prototype of a computer-aided detection/diagnosis (CAD) system that could provide valuable assistance to radiologists for discrimination between in situ and infiltrating tumors. The system consists of two main processing levels—(1) localization of possibly tumoral regions of interest (ROIs) through an iterative procedure based on intensity values (ROI Hunter), followed by a deep-feature extraction and classification method for false-positive rejection; and (2) characterization of the selected ROIs and discrimination between in situ and invasive tumor, consisting of Radiomics feature extraction and classification through a machine-learning algorithm. The CAD system was developed and evaluated using a DCE–MRI image database, containing at least one confirmed mass per image, as diagnosed by an expert radiologist. When evaluating the accuracy of the ROI Hunter procedure with respect to the radiologist-drawn boundaries, sensitivity to mass detection was found to be 75%. The AUC of the ROC curve for discrimination between in situ and infiltrative tumors was 0.70. |
| topic |
breast cancer Radiomics machine learning deep learning segmentation in situ breast cancer |
| url |
https://www.mdpi.com/2076-3417/10/17/6109 |
| work_keys_str_mv |
AT luanaconte breastcancermassdetectionindcemriusingdeeplearningfeaturesfollowedbydiscriminationofinfiltrativevsinsitucarcinomathroughamachinelearningapproach AT benedettatafuri breastcancermassdetectionindcemriusingdeeplearningfeaturesfollowedbydiscriminationofinfiltrativevsinsitucarcinomathroughamachinelearningapproach AT maurizioportaluri breastcancermassdetectionindcemriusingdeeplearningfeaturesfollowedbydiscriminationofinfiltrativevsinsitucarcinomathroughamachinelearningapproach AT alessandrogaliano breastcancermassdetectionindcemriusingdeeplearningfeaturesfollowedbydiscriminationofinfiltrativevsinsitucarcinomathroughamachinelearningapproach AT eleonoramaggiulli breastcancermassdetectionindcemriusingdeeplearningfeaturesfollowedbydiscriminationofinfiltrativevsinsitucarcinomathroughamachinelearningapproach AT giorgiodenunzio breastcancermassdetectionindcemriusingdeeplearningfeaturesfollowedbydiscriminationofinfiltrativevsinsitucarcinomathroughamachinelearningapproach |
| _version_ |
1724626398633525248 |