Breast Tumor Detection and Diagnosis Using an Improved Faster R-CNN in DCE-MRI

AI-based breast cancer detection can improve the sensitivity and specificity of detection, especially for small lesions, which has clinical value in realizing early detection and treatment so as to reduce mortality. The two-stage detection network performs well; however, it adopts an imprecise ROI d...

Full description

Saved in:
Bibliographic Details
Main Authors: Haitian Gui, Han Jiao, Li Li, Xinhua Jiang, Tao Su, Zhiyong Pang
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Bioengineering
Subjects:
Online Access:https://www.mdpi.com/2306-5354/11/12/1217
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846105789511499776
author Haitian Gui
Han Jiao
Li Li
Xinhua Jiang
Tao Su
Zhiyong Pang
author_facet Haitian Gui
Han Jiao
Li Li
Xinhua Jiang
Tao Su
Zhiyong Pang
author_sort Haitian Gui
collection DOAJ
description AI-based breast cancer detection can improve the sensitivity and specificity of detection, especially for small lesions, which has clinical value in realizing early detection and treatment so as to reduce mortality. The two-stage detection network performs well; however, it adopts an imprecise ROI during classification, which can easily include surrounding tumor tissues. Additionally, fuzzy noise is a significant contributor to false positives. We adopted Faster RCNN as the architecture, introduced ROI aligning to minimize quantization errors and feature pyramid network (FPN) to extract different resolution features, added a bounding box quadratic regression feature map extraction network and three convolutional layers to reduce interference from tumor surrounding information, and extracted more accurate and deeper feature maps. Our approach outperformed Faster R-CNN, Mask R-CNN, and YOLOv9 in breast cancer detection across 485 internal cases. We achieved superior performance in mAP, sensitivity, and false positive rate ((0.752, 0.950, 0.133) vs. (0.711, 0.950, 0.200) vs. (0.718, 0.880, 0.120) vs. (0.658, 0.680, 405)), which represents a 38.5% reduction in false positives compared to manual detection. Additionally, in a public dataset of 220 cases, our model also demonstrated the best performance. It showed improved sensitivity and specificity, effectively assisting doctors in diagnosing cancer.
format Article
id doaj-art-bad0937d58c94130a3f12943ccb96cc9
institution Kabale University
issn 2306-5354
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Bioengineering
spelling doaj-art-bad0937d58c94130a3f12943ccb96cc92024-12-27T14:11:31ZengMDPI AGBioengineering2306-53542024-12-011112121710.3390/bioengineering11121217Breast Tumor Detection and Diagnosis Using an Improved Faster R-CNN in DCE-MRIHaitian Gui0Han Jiao1Li Li2Xinhua Jiang3Tao Su4Zhiyong Pang5School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen 518107, ChinaSchool of Electronics and Information Technology, Sun Yat-sen University, Guangzhou 510006, ChinaState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Department of Medical Imaging, Sun Yat-sen University Cancer Center (SYSUCC), Guangzhou 510060, ChinaState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Department of Medical Imaging, Sun Yat-sen University Cancer Center (SYSUCC), Guangzhou 510060, ChinaSchool of Electronics and Information Technology, Sun Yat-sen University, Guangzhou 510006, ChinaSchool of Electronics and Information Technology, Sun Yat-sen University, Guangzhou 510006, ChinaAI-based breast cancer detection can improve the sensitivity and specificity of detection, especially for small lesions, which has clinical value in realizing early detection and treatment so as to reduce mortality. The two-stage detection network performs well; however, it adopts an imprecise ROI during classification, which can easily include surrounding tumor tissues. Additionally, fuzzy noise is a significant contributor to false positives. We adopted Faster RCNN as the architecture, introduced ROI aligning to minimize quantization errors and feature pyramid network (FPN) to extract different resolution features, added a bounding box quadratic regression feature map extraction network and three convolutional layers to reduce interference from tumor surrounding information, and extracted more accurate and deeper feature maps. Our approach outperformed Faster R-CNN, Mask R-CNN, and YOLOv9 in breast cancer detection across 485 internal cases. We achieved superior performance in mAP, sensitivity, and false positive rate ((0.752, 0.950, 0.133) vs. (0.711, 0.950, 0.200) vs. (0.718, 0.880, 0.120) vs. (0.658, 0.680, 405)), which represents a 38.5% reduction in false positives compared to manual detection. Additionally, in a public dataset of 220 cases, our model also demonstrated the best performance. It showed improved sensitivity and specificity, effectively assisting doctors in diagnosing cancer.https://www.mdpi.com/2306-5354/11/12/1217breast cancer detectiondeep learningAI assistant
spellingShingle Haitian Gui
Han Jiao
Li Li
Xinhua Jiang
Tao Su
Zhiyong Pang
Breast Tumor Detection and Diagnosis Using an Improved Faster R-CNN in DCE-MRI
Bioengineering
breast cancer detection
deep learning
AI assistant
title Breast Tumor Detection and Diagnosis Using an Improved Faster R-CNN in DCE-MRI
title_full Breast Tumor Detection and Diagnosis Using an Improved Faster R-CNN in DCE-MRI
title_fullStr Breast Tumor Detection and Diagnosis Using an Improved Faster R-CNN in DCE-MRI
title_full_unstemmed Breast Tumor Detection and Diagnosis Using an Improved Faster R-CNN in DCE-MRI
title_short Breast Tumor Detection and Diagnosis Using an Improved Faster R-CNN in DCE-MRI
title_sort breast tumor detection and diagnosis using an improved faster r cnn in dce mri
topic breast cancer detection
deep learning
AI assistant
url https://www.mdpi.com/2306-5354/11/12/1217
work_keys_str_mv AT haitiangui breasttumordetectionanddiagnosisusinganimprovedfasterrcnnindcemri
AT hanjiao breasttumordetectionanddiagnosisusinganimprovedfasterrcnnindcemri
AT lili breasttumordetectionanddiagnosisusinganimprovedfasterrcnnindcemri
AT xinhuajiang breasttumordetectionanddiagnosisusinganimprovedfasterrcnnindcemri
AT taosu breasttumordetectionanddiagnosisusinganimprovedfasterrcnnindcemri
AT zhiyongpang breasttumordetectionanddiagnosisusinganimprovedfasterrcnnindcemri