Concentrated Thermomics for Early Diagnosis of Breast Cancer

Thermography has been employed broadly as a corresponding diagnostic instrument in breast cancer diagnosis. Among thermographic techniques, deep neural networks show an unequivocal potential to detect heterogeneous thermal patterns related to vasodilation in breast cancer cases. Such methods are used to extract high-dimensional thermal features, known as deep thermomics. In this study, we applied convex non-negative matrix factorization (convex NMF) to extract three predominant bases of thermal sequences. Then, the data were fed into a sparse autoencoder model, known as SPAER, to extract low-dimensional deep thermomics, which were then used to assist the clinical breast exam (CBE) in breast cancer screening. The application of convex NMF-SPAER, combining clinical and demographic covariates, yielded a result of 79.3% (73.5%, 86.9%); the highest result belonged to NMF-SPAER at 84.9% (79.3%, 88.7%). The proposed approach preserved thermal heterogeneity and led to early detection of breast cancer. It can be used as a noninvasive tool aiding CBE.

Download Full-text

Impact of Community-Based Clinical Breast Examinations in Botswana

JCO Global Oncology ◽

10.1200/go.20.00231 ◽

2021 ◽

pp. 17-26

Author(s):

Michael Dykstra ◽

Brighid Malone ◽

Onica Lekuntwane ◽

Jason Efstathiou ◽

Virginia Letsatsi ◽

...

Keyword(s):

Breast Cancer ◽

Cancer Diagnosis ◽

Screening Program ◽

Breast Cancer Mortality ◽

Clinical Breast Examination ◽

Breast Cancer Diagnosis ◽

Community Based ◽

Middle Income ◽

Clinical Breast ◽

Clinical Breast Examinations

PURPOSE We evaluated a clinical breast examination (CBE) screening program to determine the prevalence of breast abnormalities, number examined per cancer diagnosis, and clinical resources required for these diagnoses in a middle-income African setting. METHODS We performed a retrospective review of a CBE screening program (2015-2018) by Journey of Hope Botswana, a Botswana-based nongovernmental organization (NGO). Symptomatic and asymptomatic women were invited to attend. Screening events were held in communities throughout rural and periurban Botswana, with CBEs performed by volunteer nurses. Individuals who screened positive were referred to a private tertiary facility and were followed by the NGO. Data were obtained from NGO records. RESULTS Of 6,120 screened women (50 men excluded), 452 (7.4%) presented with a symptom and 357 (5.83%) were referred for further evaluation; 257 ultrasounds, 100 fine-needle aspirations (FNAs), 58 mammograms, and 31 biopsies were performed. In total, 6,031 were exonerated from cancer, 78 were lost to follow-up (67 for ≤ 50 years and 11 for > 50 years), and 11 were diagnosed with cancer (five for 41-50 years and six for > 50 years, 10 presented with symptoms). Overall breast cancer prevalence was calculated to be 18/10,000 (95% CI, 8 to 29/10,000). The number of women examined per breast cancer diagnosis was 237 (95% CI, 126 to 1910) for women of age 41-50 years and 196 (95% CI, 109 to 977) for women of age > 50 years. Median time to diagnosis for all women was 17.5 [1 to 32.5] days. CBE-detected tumors were not different than tumors presenting through standard care. CONCLUSION In a previously unscreened population, yield from community-based CBE screening was high, particularly among symptomatic women, and required modest diagnostic resources. This strategy has potential to reduce breast cancer mortality.

Download Full-text

Association of Previous Clinical Breast Examination With Reduced Delays and Earlier-Stage Breast Cancer Diagnosis Among Women in Peru

JAMA Oncology ◽

10.1001/jamaoncol.2017.1023 ◽

2017 ◽

Vol 3 (11) ◽

pp. 1563 ◽

Cited By ~ 15

Author(s):

Anya Romanoff ◽

Tara Hayes Constant ◽

Kay M. Johnson ◽

Manuel Cedano Guadiamos ◽

Ana María Burga Vega ◽

...

Keyword(s):

Breast Cancer ◽

Cancer Diagnosis ◽

Clinical Breast Examination ◽

Breast Cancer Diagnosis ◽

Breast Examination ◽

Clinical Breast

Download Full-text

META-HEURISTIC OPTIMIZATION ALGORITHMS BASED FEATURE SELECTION FOR CLINICAL BREAST CANCER DIAGNOSIS

Journal of the Egyptian Mathematical Society ◽

10.21608/jomes.2018.2673.1023 ◽

2018 ◽

Vol 26 (2) ◽

pp. 321-336

Author(s):

Ashraf Darwish ◽

Gehad Sayed ◽

Aboul Hassanien

Keyword(s):

Breast Cancer ◽

Feature Selection ◽

Cancer Diagnosis ◽

Optimization Algorithms ◽

Breast Cancer Diagnosis ◽

Heuristic Optimization ◽

Clinical Breast ◽

Selection For

Download Full-text

Conserved Self Pattern Recognition Algorithm with Novel Detection Strategy Applied to Breast Cancer Diagnosis

Journal of Artificial Evolution and Applications ◽

10.1155/2009/130498 ◽

2009 ◽

Vol 2009 ◽

pp. 1-12 ◽

Cited By ~ 2

Author(s):

Senhua Yu ◽

Dipankar Dasgupta

Keyword(s):

Breast Cancer ◽

Pattern Recognition ◽

Cancer Diagnosis ◽

Breast Cancer Diagnosis ◽

Recognition Algorithm ◽

Performance Measure ◽

Pattern Recognition Algorithm ◽

Cancer Data ◽

Detection Strategy ◽

Clinical Breast

This paper presents a novel approach based on an improved Conserved Self Pattern Recognition Algorithm to analyze cytological characteristics of breast fine-needle aspirates (FNAs) for clinical breast cancer diagnosis. A novel detection strategy by coupling domain knowledge and randomized methods is proposed to resolve conflicts on anomaly detection between two types of detectors investigated in our earlier work on Conserved Self Pattern Recognition Algorithm (CSPRA). The improved CSPRA is applied to detect the malignant cases using clinical breast cancer data collected by Dr. Wolberg (1990), and the results are evaluated for performance measure (detection rate and false alarm rate). Results show that our approach has promising performance on breast cancer diagnosis and great potential in the area of clinical diagnosis. Effects of parameters setting in the CSPRA are discussed, and the experimental results are compared with the previous works.

Download Full-text

SPAER: Sparse Deep Convolutional Autoencoder Model to Extract Low Dimensional Imaging Biomarkers for Early Detection of Breast Cancer Using Dynamic Thermography

Applied Sciences ◽

10.3390/app11073248 ◽

2021 ◽

Vol 11 (7) ◽

pp. 3248

Author(s):

Bardia Yousefi ◽

Hamed Akbari ◽

Michelle Hershman ◽

Satoru Kawakita ◽

Henrique C. Fernandes ◽

...

Keyword(s):

Breast Cancer ◽

Early Detection ◽

Matrix Factorization ◽

Low Rank ◽

Imaging Biomarkers ◽

Basis Matrix ◽

Convolutional Autoencoder ◽

Thermal Heterogeneity ◽

Low Dimensional ◽

Dynamic Thermography

Early diagnosis of breast cancer unequivocally improves the survival rate of patients and is crucial for disease treatment. With the current developments in infrared imaging, breast screening using dynamic thermography seems to be a great complementary method for clinical breast examination (CBE) prior to mammography. In this study, we propose a sparse deep convolutional autoencoder model named SPAER to extract low-dimensional deep thermomics to aid breast cancer diagnosis. The model receives multichannel, low-rank, approximated thermal bases as input images. SPAER provides a solution for high-dimensional deep learning features and selects the predominant basis matrix using matrix factorization techniques. The model has been evaluated using five state-of-the-art matrix factorization methods and 208 thermal breast cancer screening cases. The best accuracy was for non-negative matrix factorization (NMF)-SPAER + Clinical and NMF-SPAER for maintaining thermal heterogeneity, leading to finding symptomatic cases with accuracies of 78.2% (74.3–82.5%) and 77.7% (70.9–82.1%), respectively. SPAER showed significant robustness when tested for additive Gaussian noise cases (3–20% noise), evaluated by the signal-to-noise ratio (SNR). The results suggest high performance of SPAER for preserveing thermal heterogeneity, and it can be used as a noninvasive in vivo tool aiding CBE in the early detection of breast cancer.

Download Full-text