Detecting breast cancer, especially identifying microcalcifications in mammograms, is challenging due to the need for high sensitivity and efficient processing. This study presents a novel algorithm, Sigmoidal Slope Analysis and Aspect Ratio Evaluation (SAAR), designed for real-time application on edge devices. By employing a multi-step adaptive process with sigmoidal functions, SAAR enhances intensity contrast and prioritizes regions of interest, enabling fast, accurate detection of microcalcifications.
Objective
This study aims to develop and validate an efficient, edge-device-compatible method for detecting microcalcifications in mammographic images. The goal is to provide a tool that enhances diagnostic efficiency through real-time processing, thereby supporting early breast cancer detection in both clinical and remote settings.
Methods
The SAAR algorithm utilizes an adaptive slope detection technique based on the sigmoid function, dynamically adjusting to local intensity features. This approach allows for greater adaptability to image variations. The algorithm prioritizes regions of interest through a multi-step adaptive process, enhancing intensity differences to focus on potential microcalcifications.
Results
Testing on established mammography databases, such as MIAS, demonstrates the algorithm's effectiveness, with improved sensitivity compared to conventional methods. Designed for edge devices, the algorithm leverages their real-time processing capabilities, offering lower latency and enhanced privacy.
Conclusions
The integration of SAAR with edge devices represents a promising advancement in breast cancer detection. The adaptive nature of SAAR, coupled with the real-time processing capabilities of edge devices, provides a robust solution for enhancing microcalcification detection efficiency and sensitivity in mammography.
MuduliDDashRMajhiB. Automated breast cancer detection in digital mammograms: a moth flame optimization based ELM approach. Biomed Signal Process Control2020; 59: 101912.
2.
ShenLHeMShenN, et al.Optimal breast tumor diagnosis using discrete wavelet transform and deep belief network based on improved sunflower optimization method. Biomed Signal Process Control2020; 60: 101953.
3.
CastiPMencattiniASalmeriM, et al.Contour-independent detection and classification of mammographic lesions. Biomed Signal Process Control2016; 25: 165–177.
4.
MilosevicMJankovicDPeulicA. Segmentation for the enhancement of microcalcifications in digital mammograms. Technol Health Care2014; 22: 701–715.
5.
ZhaoHHuaJGengX, et al.A shortcut weighted fusion pyramid network for microcalcification detection in breast mammograms. Technol Health Care2023; 31: 841–853.
6.
WangHFengJWangH. Grouped fuzzy SVM with EM-based partition of sample space for clustered microcalcification detection. Technol Health Care2017; 25: 325–336.
7.
De SantoMMolinaraMTortorellaF, et al.Automatic classification of clustered microcalcifications by a multipleexpert system. Pattern Recognit2003; 36: 1467–1477.
8.
RehmanKULiJPeiY, et al.Computer vision-based microcalcification detection in digital mammograms using fully connected depthwise separable convolutional neural network. Sensors2021; 21: 4854.
9.
LeeSParkSJJeonJM, et al.Noise removal in medical mammography images using fast non-local means denoising algorithm for early breast cancer detection: a phantom study. Optik (Stuttg)2019; 180: 569–575.
10.
NasserMYusofUK. Deep learning based methods for breast cancer diagnosis: a systematic review and future direction. Diagnostics (Basel)2023; 13: 161.
11.
ShiWCaoJZhangQ, et al.Edge computing: vision and challenges. IEEE Internet Things J2016; 3: 637–646.
12.
YoshidaHDoiKNishikawaR, et al.Application of the wavelet transform to automated detection of clustered microcalcifications in digital mammograms. Acad Rep Tokyo Inst Polytech1994; 16: 24–37.
13.
YoshidaHNishikawaRMaryellenG, et al.Computer-aided diagnosis in mammography: Detection of clustered microcalcifications based on multiscale edge representation. Computer Assisted Radiology1996; 1091: 390–395.
14.
BoccignoneaGChianeseAPicarielloA. Computer aided detection of microcalcifications in digital mammograms. Comput Biol Med2000; 30: 267–286.
15.
ZhangXHommaNGotoS, et al.A hybrid image filtering method for computer-aided detection of microcalcification clusters in mammograms. J Med Eng2013; 2013: 615254.
16.
LahmiriS. A wavelet-wavelet based processing approach for microcalcifications detection in mammograms. J Adv Inf Technol2012; 3: 162–167.
17.
Subash Chandra BoseJShankar KumarKRKarnanM. Detection of microcalcification in mammograms using soft computing techniques. Eur J Sci Res2012; 86: 103–122.
18.
WangZXinJZhangQ, et al.Breast microcalcifications detection based on fusing features with DTCWT. J X-Ray Sci Technol2020; 28: 197–218.
19.
WoodsKDossCBowyerK, et al.Comparative evaluation of pattern recognition techniques for detection of microcalcifications in mammography. Int J Pattern Recognit Artif Intell1994; 7: 1417–1436.
20.
El-NaqaIYangYWernickMN, et al.A support vector machine approach for detection of microcalcifications. IEEE Trans Med Imaging2002; 21: 1552–1563.
21.
RízzíMD’AloiaMCastagnoloB. A supervised method for microcalcification cluster diagnosis. Integr Comput Aided Eng2013; 20: 157–167.
22.
VermaBZakosJ. A computer-aided diagnosis system for digital mammograms based on fuzzy-neural and feature extraction techniques. IEEE Trans Inf Technol Biomed2001; 5: 46–54.
23.
ChengHLuiYMFeiimanisRI. A novel approach to microcalcification detection using fuzzy logic techniques. IEEE Trans Med Imaging1998; 17: 442–450.
24.
NagelRHNishikawaRMPapaioannouJ, et al.Analysis of methods for reducing false positives in automated detection of clustered microcalcifications in mammograms. Med Phys1998; 25: 1502–1506.
25.
PapadopoulosaAFotiadisDILikasA. An automatic microcalcification detection system based on a hybrid neural network classifier. Artif Intell Med2002; 25: 149–167.
26.
WangJNishikawaRMYangY. Global detection approach for clustered microcalcifications in mammograms using a deep learning network. J Med Imaging2017; 4: 024501.
27.
WangJYangY. A context-sensitive deep learning approach for microcalcification detection in mammograms. Pattern Recognit2018; 78: 12–22.
28.
ValvanoGSantiniGMartiniN, et al.Convolutional neural networks for the segmentation of microcalcification in mammography imaging. J Healthc Eng2019; 9360941: 1–9.
29.
CaiHHuangQRongW, et al.Breast microcalcification diagnosis using deep convolutional neural network from digital mammograms. Comput Math Methods Med2019; 2717454: 1–10.
30.
WangJYangXCaiH, et al.Discrimination of breast cancer with microcalcifications on mammography by deep learning. Sci Rep2016; 6: 27327.
31.
KimJKParkHW. Statistical textural features for detection of microcalcifications in digitized mammograms. IEEE Trans Med Imaging1999; 18: 231–238.
32.
PesapaneFTrentinCFerrariF, et al.Deep learning performance for detection and classification of microcalcifications on mammography. Eur Radiol Exp2023; 7: 69.
33.
MakeevAGlickSJ. Task-based assessment of digital mammography microcalcification detection with deep learning denoising algorithms using in silico and physical phantom studies. J Med Imaging2023; 10: 053502.
34.
DomaMKPadmanandamKTambvekarS, et al.Artificial intelligence-based breast cancer detection using WPSO. Int J Oper Res Inf Syst2022; 13: 1–16.
35.
SchonenbergerCHejdukPCiritsisA, et al.Classification of mammographic breast microcalcifications using a deep convolutional neural network: a BI-RADS-based approach. Invest Radiol2021; 56: 224–231.
36.
LiuHChenYZhangY, et al.A deep learning model integrating mammography and clinical factors facilitates the malignancy prediction of BI-RADS 4 microcalcifications in breast cancer screening. Eur Radiol2021; 31: 5902–5912.
37.
StelzerPDStedingORaudnerMW, et al.Combined texture analysis and machine learning in suspicious calcifications detected by mammography: potential to avoid unnecessary stereotactical biopsies. Eur J Radiol2020; 132: 109309.
38.
MansourSMokhtarOEl GalilMASMA, et al.Artificial intelligence reading digital mammogram: enhancing detection and differentiation of suspicious microcalcifications. Br J Radiol2025; 98: 246–253.
39.
AphinivesCAphinivesPNawapanS. Artificial intelligence development for detecting microcalcification within mammography. J Med Assoc Thail2021; 104: 1.
40.
YuSNLiKYHuangYK. Detection of microcalcifications in digital mammograms using wavelet filter and markov random field model. Comput Med Imaging Graph2006; 30: 163–173.
41.
MarroccoCMolinaraMD’EliaC, et al.A computer-aided detection system for clustered microcalcifications. Artif Intell Med2010; 50: 23–32.
42.
QuellecGLamardMCozicM, et al.Multiple-Instance learning for anomaly detection in digital mammography. IEEE Trans Med Imaging2016; 35: 1604–1614.
43.
XuXGuoQLiZ, et al.Uncertainty ordinal multi-instance learning for breast cancer diagnosis. Healthcare2022; 10: 2300.
44.
HuTZhangLXieL, et al.A multi-instance networks with multiple views for classification of mammograms. Neurocomputing2021; 443: 320–328.
45.
ElmoufidiA. Deep multiple instance learning for automatic breast cancer assessment using digital mammography. IEEE Trans Instrum Meas2022; 71: 4503813.
46.
LiCZhangWZhuHH, et al.Fast vibration characteristics analysis of an underwater shield tunnel using the accelerometer network enhanced by edge computing. Measurement ( Mahwah N J)2019; 141: 52.
47.
RayPPDashDDeD. Edge computing for internet of things: a survey, e-healthcare case study and future direction. J Netw Comput Appl2019; 140: 1.
48.
SatyanarayananMSimoensPXiaoY, et al.Edge analytics in the internet of things. IEEE Pervasive Comput2017; 16: 24–31.
49.
DinhHTLeeCNiyatoD, et al.A survey of mobile cloud computing: architecture, applications, and approaches. Wirel Commun Mob Comput2013; 13: 1587–1611.
50.
MaoYYouCZhangJ, et al.A survey on Mobile edge computing: the communication perspective. IEEE Commun Surv Tutorials2017; 19: 2322–2358.
51.
LvZChenDLouR, et al.Intelligent edge computing based on machine learning for smart city. Future Gener Comput Syst2021; 115: 90.
52.
ElhanashiADiniPSaponaraS, et al.Integration of deep learning into the IoT: a survey of techniques and challenges for real-world applications. Electronics (Basel)2023; 12: 4925.
53.
RostamiATarvirdizadehBAlipourK, et al. Real-time stress detection from raw noisy PPG signals using LSTM model leveraging TinyML. Arab J Sci Eng2024; 50: 6959–6981.
54.
SucklingJParkerJDanceD, et al.The mammographic images analysis society digital mammogram database. Exerpta Medica1994; 1069: 375–378.
55.
MilosevicMJankovicDPeulicA. Comparative analysis of breast cancer detection in mammograms and thermograms. Biomed. Eng. / Biomed. Tech2015; 60: 49–56.
56.
MilosevicMJankovicDPeulicA. Thermography based breast cancer detection using texture features and Minimum variance quantization. EXCLI J2014; 13: 1204–1215.
57.
EllinasJNMandadelisTTzortzisA, et al.Image de-noising using wavelets. T.E.I. Piraeus Appl Res Rev2004; 9: 97–109.
58.
RangarajanRVenkataramananRShahS. Image Denoising Using Wavelets. Technical report. College of Engineering, University of Michigan2002.
59.
CannyJ. A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell1986; 8: 679–698.
60.
ZhouPYeWWangQ. An improved canny algorithm for edge detection. J Comput Inf Syst2011; 7: 1516–1523.
61.
ChenYLiLLiW, et al.AI Computing Systems: An Application Driven Perspective. Amsterdam, Netherlands: Elsevier, 2023, ISBN 978-0-323-95399-3.
62.
ChanussotJLambertP. Adaptive filtering and change detection in hyperspectral imagery. J Remote Sens2022; 25: 123–145.
