Predicting Underestimation of Invasive Cancer in Patients with Core-Needle-Biopsy-Diagnosed Ductal Carcinoma In Situ Using Deep Learning Algorithms
The prediction of an occult invasive component in ductal carcinoma in situ (DCIS) before surgery is of clinical importance because the treatment strategies are different between pure DCIS without invasive component and upgraded DCIS. We demonstrated the potential of using deep learning models for di...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Tomography |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2379-139X/9/1/1 |
| _version_ | 1797895042175598592 |
|---|---|
| author | Luu-Ngoc Do Hyo-Jae Lee Chaeyeong Im Jae Hyeok Park Hyo Soon Lim Ilwoo Park |
| author_facet | Luu-Ngoc Do Hyo-Jae Lee Chaeyeong Im Jae Hyeok Park Hyo Soon Lim Ilwoo Park |
| author_sort | Luu-Ngoc Do |
| collection | DOAJ |
| description | The prediction of an occult invasive component in ductal carcinoma in situ (DCIS) before surgery is of clinical importance because the treatment strategies are different between pure DCIS without invasive component and upgraded DCIS. We demonstrated the potential of using deep learning models for differentiating between upgraded versus pure DCIS in DCIS diagnosed by core-needle biopsy. Preoperative axial dynamic contrast-enhanced magnetic resonance imaging (MRI) data from 352 lesions were used to train, validate, and test three different types of deep learning models. The highest performance was achieved by Recurrent Residual Convolutional Neural Network using Regions of Interest (ROIs) with an accuracy of 75.0% and area under the receiver operating characteristic curve (AUC) of 0.796. Our results suggest that the deep learning approach may provide an assisting tool to predict the histologic upgrade of DCIS and provide personalized treatment strategies to patients with underestimated invasive disease. |
| first_indexed | 2024-04-10T07:20:08Z |
| format | Article |
| id | doaj.art-e4d27b03fcde46fca6414a8dbeb8468d |
| institution | Directory Open Access Journal |
| issn | 2379-1381 2379-139X |
| language | English |
| last_indexed | 2024-04-10T07:20:08Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Tomography |
| spelling | doaj.art-e4d27b03fcde46fca6414a8dbeb8468d2023-02-24T15:54:29ZengMDPI AGTomography2379-13812379-139X2022-12-019111110.3390/tomography9010001Predicting Underestimation of Invasive Cancer in Patients with Core-Needle-Biopsy-Diagnosed Ductal Carcinoma In Situ Using Deep Learning AlgorithmsLuu-Ngoc Do0Hyo-Jae Lee1Chaeyeong Im2Jae Hyeok Park3Hyo Soon Lim4Ilwoo Park5Department of Radiology, Chonnam National University, 42 Jebong-ro, Dong-gu, Gwangju 61469, Republic of KoreaDepartment of Radiology, Chonnam National University Hospital, 42 Jebong-ro, Dong-gu, Gwangju 61469, Republic of KoreaDepartment of Medicine, Chonnam National University, Gwangju 61469, Republic of KoreaDepartment of Medicine, Chonnam National University, Gwangju 61469, Republic of KoreaDepartment of Radiology, Chonnam National University, 42 Jebong-ro, Dong-gu, Gwangju 61469, Republic of KoreaDepartment of Radiology, Chonnam National University, 42 Jebong-ro, Dong-gu, Gwangju 61469, Republic of KoreaThe prediction of an occult invasive component in ductal carcinoma in situ (DCIS) before surgery is of clinical importance because the treatment strategies are different between pure DCIS without invasive component and upgraded DCIS. We demonstrated the potential of using deep learning models for differentiating between upgraded versus pure DCIS in DCIS diagnosed by core-needle biopsy. Preoperative axial dynamic contrast-enhanced magnetic resonance imaging (MRI) data from 352 lesions were used to train, validate, and test three different types of deep learning models. The highest performance was achieved by Recurrent Residual Convolutional Neural Network using Regions of Interest (ROIs) with an accuracy of 75.0% and area under the receiver operating characteristic curve (AUC) of 0.796. Our results suggest that the deep learning approach may provide an assisting tool to predict the histologic upgrade of DCIS and provide personalized treatment strategies to patients with underestimated invasive disease.https://www.mdpi.com/2379-139X/9/1/1ductal carcinoma in situunderestimation of invasive cancerdeep learningmagnetic resonance imagingmachine learning |
| spellingShingle | Luu-Ngoc Do Hyo-Jae Lee Chaeyeong Im Jae Hyeok Park Hyo Soon Lim Ilwoo Park Predicting Underestimation of Invasive Cancer in Patients with Core-Needle-Biopsy-Diagnosed Ductal Carcinoma In Situ Using Deep Learning Algorithms Tomography ductal carcinoma in situ underestimation of invasive cancer deep learning magnetic resonance imaging machine learning |
| title | Predicting Underestimation of Invasive Cancer in Patients with Core-Needle-Biopsy-Diagnosed Ductal Carcinoma In Situ Using Deep Learning Algorithms |
| title_full | Predicting Underestimation of Invasive Cancer in Patients with Core-Needle-Biopsy-Diagnosed Ductal Carcinoma In Situ Using Deep Learning Algorithms |
| title_fullStr | Predicting Underestimation of Invasive Cancer in Patients with Core-Needle-Biopsy-Diagnosed Ductal Carcinoma In Situ Using Deep Learning Algorithms |
| title_full_unstemmed | Predicting Underestimation of Invasive Cancer in Patients with Core-Needle-Biopsy-Diagnosed Ductal Carcinoma In Situ Using Deep Learning Algorithms |
| title_short | Predicting Underestimation of Invasive Cancer in Patients with Core-Needle-Biopsy-Diagnosed Ductal Carcinoma In Situ Using Deep Learning Algorithms |
| title_sort | predicting underestimation of invasive cancer in patients with core needle biopsy diagnosed ductal carcinoma in situ using deep learning algorithms |
| topic | ductal carcinoma in situ underestimation of invasive cancer deep learning magnetic resonance imaging machine learning |
| url | https://www.mdpi.com/2379-139X/9/1/1 |
| work_keys_str_mv | AT luungocdo predictingunderestimationofinvasivecancerinpatientswithcoreneedlebiopsydiagnosedductalcarcinomainsituusingdeeplearningalgorithms AT hyojaelee predictingunderestimationofinvasivecancerinpatientswithcoreneedlebiopsydiagnosedductalcarcinomainsituusingdeeplearningalgorithms AT chaeyeongim predictingunderestimationofinvasivecancerinpatientswithcoreneedlebiopsydiagnosedductalcarcinomainsituusingdeeplearningalgorithms AT jaehyeokpark predictingunderestimationofinvasivecancerinpatientswithcoreneedlebiopsydiagnosedductalcarcinomainsituusingdeeplearningalgorithms AT hyosoonlim predictingunderestimationofinvasivecancerinpatientswithcoreneedlebiopsydiagnosedductalcarcinomainsituusingdeeplearningalgorithms AT ilwoopark predictingunderestimationofinvasivecancerinpatientswithcoreneedlebiopsydiagnosedductalcarcinomainsituusingdeeplearningalgorithms |