Razali Noor Fadzilah, Isa Iza Sazanita, Sulaiman Siti Noraini, Abdul Karim Noor Khairiah, Osman Muhammad Khusairi, Che Soh Zainal Hisham
Centre for Electrical Engineering Studies, Universiti Teknologi MARA, Cawangan Pulau Pinang, Permatang Pauh Campus, Bukit Mertajam 13500, Pulau Pinang, Malaysia.
Integrative Pharmacogenomics Institute (iPROMISE), Universiti Teknologi MARA Cawangan Selangor, Puncak Alam Campus, Puncak Alam 42300, Selangor, Malaysia.
Bioengineering (Basel). 2023 Jan 23;10(2):153. doi: 10.3390/bioengineering10020153.
Mass detection in mammograms has a limited approach to the presence of a mass in overlapping denser fibroglandular breast regions. In addition, various breast density levels could decrease the learning system's ability to extract sufficient feature descriptors and may result in lower accuracy performance. Therefore, this study is proposing a textural-based image enhancement technique named Spatial-based Breast Density Enhancement for Mass Detection (SbBDEM) to boost textural features of the overlapped mass region based on the breast density level. This approach determines the optimal exposure threshold of the images' lower contrast limit and optimizes the parameters by selecting the best intensity factor guided by the best Blind/Reference-less Image Spatial Quality Evaluator (BRISQUE) scores separately for both dense and non-dense breast classes prior to training. Meanwhile, a modified You Only Look Once v3 (YOLOv3) architecture is employed for mass detection by specifically assigning an extra number of higher-valued anchor boxes to the shallower detection head using the enhanced image. The experimental results show that the use of SbBDEM prior to training mass detection promotes superior performance with an increase in mean Average Precision (mAP) of 17.24% improvement over the non-enhanced trained image for mass detection, mass segmentation of 94.41% accuracy, and 96% accuracy for benign and malignant mass classification. Enhancing the mammogram images based on breast density is proven to increase the overall system's performance and can aid in an improved clinical diagnosis process.
在乳腺钼靶片中进行肿块检测时，对于重叠的致密纤维腺体型乳腺区域中肿块的存在，检测方法有限。此外，不同的乳腺密度水平可能会降低学习系统提取足够特征描述符的能力，并可能导致较低的准确率表现。因此，本研究提出一种基于纹理的图像增强技术，称为用于肿块检测的基于空间的乳腺密度增强（SbBDEM），以根据乳腺密度水平增强重叠肿块区域的纹理特征。该方法确定图像较低对比度极限的最佳曝光阈值，并在训练前分别针对致密型和非致密型乳腺类别，通过选择由最佳盲/无参考图像空间质量评估器（BRISQUE）分数引导的最佳强度因子来优化参数。同时，采用改进的You Only Look Once v3（YOLOv3）架构进行肿块检测，具体做法是使用增强后的图像为较浅的检测头专门分配额外数量的高价值锚框。实验结果表明，在训练肿块检测之前使用SbBDEM可提升性能，与未增强训练的图像相比，平均精度均值（mAP）提高了17.24%，肿块分割准确率达到94.41%，良性和恶性肿块分类准确率达到96%。事实证明，基于乳腺密度增强乳腺钼靶图像可提高整个系统的性能，并有助于改善临床诊断过程。
