Wavelet based thermogram analysis for breast cancer detection

Health care is informed first and foremost by scientific and medical understanding of how to treat and prevent disease. Economics can, however, provide useful insights to inform policy in the design and implementation of the systems to provide health care, as well as in the process of prioritizing interventions to make the best use of scarce resources. Treating a single cancer patient may require the coordination of many inputs and may cost tens or even hundreds of thousands of dollars in high-income countries (HICs). Ongoing population cancer screening and early detection also require considerable coordination, including treatment for cases detected, and costs. Finally, although knowledge of cancer prevention is inadequate, prevention can be a costly endeavor—as demonstrated by the large sums spent on behavior change promotion (such as smoking cessation) or on vaccines to prevent cancer, such as against human papilloma virus to prevent cervical cancer and hepatitis B virus to prevent liver cancer—and economics can be informative.The second section of this chapter reviews how the availability of resources for cancer care varies by economic status, using the World Bank’s categories of low-income countries (LICs), middle-income countries (MICs) (comprising lower-middle-income countries and upper-middle-income countries), and HICs. At the same time, economy is not destiny. Countries at the same level of economic development differ because other factors intervene. Urbanization affects the patterns of cancer and the ability to access care. Local champions, governmental political leadership, and international partnerships can all loosen the constraints of local economic resources. Conversely, some countries are underachievers in cancer care despite their income level, perhaps because of leadership failures.The third section reviews the cost-effectiveness of interventions for cancer care, where care is here defined to include prevention. The cost-effectiveness of interventions has been well studied in HICs, but much less so in low- and middle-income countries (LMICs). This section summarizes the literature on the economics of cancer care in LMICs; the section also draws on the literature from HICs, particularly for cancer treatment, in areas where reliable studies for LMICs are particularly scarce. It may be possible to make inferences for one country using results from another country; the validity of these inferences rises with the extent of the similarities in the two countries. Where possible, we separate out the findings for high-income economies in Asia, since they are likely to be more relevant for LMICs in this region than the results from North America or Western Europe.We use the resource grouping suggested by Anderson and others (see chapter 3) for the Breast Health Global Initiative and apply this to other cancers. In this framework, facility resource environments fall into four categories of resource availability: Basic Limited Enhanced Maximal These categories are correlated with the World Bank income groupings. LICs have a preponderance of Basic facilities, rural areas in MICs have more facilities with Limited capabilities, urban areas in MICs have more facilities with Enhanced capabilities, and much of the population in HICs has access to facilities with Maximal capabilities. The implications for the availability of resources specific to cancer care are described. This section requires some interpolation on the authors’ part because of the paucity of previous work in the area and is subject to further validation by experts.The fourth and final section contains conclusions, consisting of summary recommendations of packages of cancer care appropriate for each of the four resource environments, as well as priority areas where further research is required. The appropriateness of a package is defined by feasibility (those resources can be expected to exist or could exist with reasonable investments) and by likely cost-effectiveness (within the limits of available data). Although there are internationally validated resource-specific care guidelines for breast cancer (the Breast Health Global Initiative), no such guidelines are available as yet for other cancers. The packages presented here have been validated in consultation with the chapter authors of this volume (chapters 3 through 8), but need to be further refined by expert consultation.

Effects of radiotherapy and of differences in the extent of surgery for early breast cancer on local recurrence and 15-year survival: an overview of the randomised trials

Breast cancer is the most common form of cancer in women. Its aggressive nature has made it one of the chief factors of high female mortality. Therefore, this has motivated research to achieve early diagnosis since it is the best strategy for patient survival. Currently, mammography is the gold standard for detecting breast cancer. However, it is expensive, unsuitable for dense breasts, and an invasive process that exposes the patient to radiation. Infrared thermography is gaining popularity as a screening modality for the early detection of breast cancer. It is a noninvasive and cost-effective modality that allows health practitioners to observe the temperature profile of the breast region for signs of cancerous tumors. Deep learning has emerged as a powerful computational tool for the early detection of breast cancer in radiology. As such, this study presents a review that shows existing work on deep learning-based Computer-aided Diagnosis (CADx) systems for breast cancer detection. In the same context, it reflects on classification utilizing breast thermograms. It first provides an overview of infrared thermography, details on available breast thermogram datasets, and then segmentation techniques applied to these thermograms. We also provide a brief overview of deep neural networks. Finally, it reviews works adopting Deep Neural Networks (DNNs) for breast thermogram classification.

Targeting Early Stage DCIS Breast Cancer Directly in the Ducts with Intraductal Chemotherapy

A time for creative collaboration

Breast cancer is a disease associated with aging. In the US, the median age of breast cancer diagnosis and death is 61 years and 68 years, respectively. The number of older adults in the US is rising, and the number of individuals age 65 and older is expected to double by the year 2030. This demographic shift will lead to an increase in the number of individuals diagnosed with breast cancer. It is estimated that from 2010 to 2030 there will be a 57% growth in the number of new cases of breast cancer in patients age 65 and older.1 A challenge in caring for older adults with breast cancer is that they have been historically underrepresented in clinical trials that set the standard for breast cancer care.2 However, a growing body of evidence-based literature can be utilized to inform and optimize the care of the older adults with breast cancer. This presentation will focus on the treatment of early stage breast cancer in older adults, including the risks and benefits of local and systemic therapies, as well as survivorship issues. Recently reported phase III studies have led to advances in the treatment of older adults with breast cancer. A phase III randomized study evaluated the role of radiation therapy following lumpectomy in patients age 70 and older with stage I hormone receptor (HR) positive breast cancer who received treatment with tamoxifen. Receipt of radiation therapy was associated with a decrease in the risk of locoregional recurrence; however, there was no difference in overall survival. The study results underscore the importance of competing comorbidity as a cause of death in older adults with early stage breast cancer.3 The role of axillary lymph node dissection was evaluated in a randomized study of women over age 60 with node-negative, HR positive breast cancer who received treatment with tamoxifen. Patients were randomized to breast surgery and axillary dissection, or breast surgery alone. There was no difference between disease-free and overall survival in the 2 study arms.4 A phase III randomized study evaluated the efficacy of standard adjuvant IV chemotherapy (doxorubicin and cyclophosphamide [AC] or cyclophosphamide, methotrexate, and 5-fluorouracil [CMF]) versus oral chemotherapy (capecitabine) in patients age 65 and older with stage I-III breast cancer. Those patients who received standard chemotherapy showed improvement in progression-free and overall survival compared with patients who received capecitabine. This study demonstrates that IV polychemotherapy regimens remain the standard of care for older adults who are prescribed adjuvant chemotherapy.5 These phase III studies advance our understanding in the care of older adults with breast cancer. Furthermore, they demonstrate the feasibility and importance of accruing older adults to phase III trials, which will improve our evidence-based care of this growing population.

Additional age-related issues should be considered when managing breast cancer in young women.1 Among them, the potential consequences of anticancer treatments on ovarian function and fertility potential are of particular concern and need to be addressed as early as possible after diagnosis.2,3 Therefore, current guidelines strongly voice the need to provide proper oncofertility counseling with all patients of reproductive age with newly diagnosed cancer irrespective of its stage.2,3 This is a crucial step to discuss with all young women their disease and prognosis, the required treatments including their potential gonadotoxicity, the need for contraception during and after active systemic therapies, their future desire of conception, likelihood of pregnancy, its safety and outcomes as well as the available strategies to avoid the negative impact of the proposed treatment on ovarian function and fertility.

ABSTRACTEarly diagnosis of breast cancer is essential for improving patient survival rates and reducing treatment costs. Despite breast thermogram images having high quality, doctors in developing countries often struggle with early diagnosis due to difficulties in interpreting subtle details. Implementing a Computer‐Aided Diagnosis (CAD) system can assist doctors in accurately analyzing these details. This article presents an innovative approach to breast cancer diagnosis using thermal images. The proposed method enhances the quality and clarity of relevant features while preserving sharp and curved edges through U‐Net‐based segmentation for automatic selection of the ROI, advanced hybrid image enhancement techniques, and a machine learning classifier. Subjective analysis compares the processed images with five conventional enhancement techniques, demonstrating the efficiency of the proposed method. The quantitative analysis further validates the effectiveness of the proposed method against five conventional methods using four quality measures. The proposed method achieves superior performance with PSNR of 15.27 for normal and 14.31 for malignant images, AMBE of 6.594 for normal and 7.46 for malignant images, SSIM of 0.829 for normal and 0.80 for malignant images, and DSSIM of 0.084 for normal and 0.14 for malignant images. The classification phase evaluates four classifiers using 13 features from three categories. The Random Forest (RF) classifier with Discrete Wavelet Transform (DWT) based features initially outperformed other classifier features but had limited performance, with accuracy, sensitivity and specificity of 81.8%, 88.8%, and 91%, respectively. To improve this, three categories of features were normalized and converted into two principal components using Principal Component Analysis (PCA) to train the RF classifier, which then showed superior performance with 97.7% accuracy, 96.5% sensitivity, and 98.2% specificity. The dataset utilized in this article is obtained from the Indira Gandhi Centre for Atomic Research (IGCAR), Kalpakkam, India. The entire proposed model is implemented in a Jupyter notebook.

Up to 25 per cent of patients presenting with "early" breast cancer subsequently develop distant metastases indicating that this group must have occult disseminated disease when initially evaluated. Routine pre-operative haematological and radiological investigation is recommended in order to identify these patients and alter their management accordingly. The aim of this study was to examine the outcome of a pre-operative metastatic screening programme in patients presenting with early breast cancer. Eighty-two patients underwent surgery for stage I-II breast cancer over a 5 yr period from 1990-1995. Before surgery all patients underwent screening tests for metastatic disease. These included a full blood count, liver function tests, chest x-ray, skeletal survey and abdominal ultrasound. Of the 82 patients, metastatic screening significantly altered management in only 1 patient who was found to have asymptomatic lymphangitis carcinomatosa on chest x-ray. The results of this study suggest that the number of patients restaged by screening for metastatic breast cancer may be small and questions the necessity for its routine use in the management of early primary breast cancer.

e21707 Background: There is growing evidence in oncology that skeletal muscle (SM) loss, known as sarcopenia, can be identified from routine computed tomography (CT) imaging and used to predict increased chemotherapy toxicity, mortality, and other adverse clinical outcomes (Shachar-EJC, 2016, Shachar-CCR, 2016). The contributions of age-related and cancer-related loses in SM at diagnosis remains poorly understood. This study compares CT-derived measures of SM at the time of diagnosis in patients with early BC (EBC) versus metastatic BC (MBC) patients to investigate the impact of metastatic cancer on SM. Methods: Body composition measures were compared between patients with EBC receiving adjuvant chemotherapy and MBC initiating first line palliative chemotherapy. Measures were derived from analysis CT scans of L3 lumbar segments using radiological software (ABACS). Measures include: skeletal muscle area (SMA), density (SMD), index (SMI = SMA/height ^2), and integrated density (SMID = SMI x SMD). Sarcopenia was defined as SMI < 41(Martin-JCO, 2013). Lean body mass (LBM) was calculated (kg) = [(L3 Muscle measured by CT (cm2) × 0.3) + 6.06]) (Prado-CCR, 2009). Body surface area (BSA) was calculated using the Mosteller formula. T-tests (continuous) and Chi-squared tests (categorical) compared variables between groups; multivariable linear regression models controlled for age and body mass index (BMI). Results: MBC patients (n = 40) were older than EBC (n = 151) (56 vs 49 years, p < 0.001). Mean BMI and BSA were similar in both groups (29.0 vs 28.8, p = 0.84; 1.87 vs 1.86 m2, p = 0.55). After adjusting for age and BMI, SMI (41.3 vs 44.7 cm2/m2, p = 0.009), SMD (29.8 vs 36.4 Hounsfield Units, p < 0.0001), SMG (1250 vs 1612, p < 0.0001), and LBM (39.3 vs 41.9 kg, p = 0.024) were significantly lower in the MBC group. The MBC group included significantly more sarcopenic patients (58% vs 31%, p = 0.0016). Conclusions: Although BMI and BSA were similar in EBC and MBC patients, SM measures showed significant differences. MBCs had lower LBM, SMI, and SMD. More advanced BC was associated with higher proportions of sarcopenia. Further research is needed to explore interventions in sarcopenic patients in order improve outcomes in women with both EBC and MBC.

Rationale: while large efforts have been done to characterize early breast cancer, little is known about the genomic landscape of metastatic breast cancer. In the present study, we performed whole exome sequencing of 800 metastatic breast cancers, in order to identify new candidate targets and better stratify patients eligible for innovative therapies. Patients and Methods: Patients were selected to present a metastatic breast cancer and to have received a biopsy in the context of precision medicine trials (SAFIR01, SAFIR02, PERMED, MOSCATO, SHIVA). Samples with >30% cancer cells, and normal DNA, were sequenced using Hiseq and Novaseq. Drivers were identified using MutSigCV. Actionability of somatic genetic alterations was determined based on OncoKB. Decomposition of mutational signatures was performed using deconstructSigs. Prognostic value was assessed using a cox model. TCGA database was used as comparator to identify gene alterations enriched in metastatic samples. Results: results presented in the current abstract are based on the first 629 patients analyzed.Sequencing was performed in 387 patients with HR+/Her2- breast cancer, 186 triple negative breast cancers, and 32 Her2-overexpressing breast cancers. only 9 patients received a pretreatment with a CDK4 inhibitor. 24 driver genes were significantly mutated. In patients with HR+/Her2- breast cancer, 11 genes were found more frequently mutated in the metastatic setting as compared to early stage breast cancer. This includes TP53 (29%), KMT2C (13%), NCOR1 (8%), NF1 (7%), RB1 (4%), C16orf3 (2%), FRG1 (6%), ESR1 (21%), RIC8A (4%), AKT1 (7%), PLSCR5 (2%). In addition, in the whole population, KRAS was found mutated in 3% of samples (G12A/C/R/V) while its frequency of mutation in early breast cancer is <1%. No gene alteration was found enriched in metastatic Her2+++ and TNBC. Copy number alterations were compared between metastatic and early breast cancer. 18 amplicons were found more frequently in HR+/Her2- metastatic breast cancers as compared to eBC. Among the genes enriched in metastatic samples, mutations in RB1 or NF1 were associated with a poor outcome ( median OS 9 and 13 months respectively, p=0.0038 and 0.01 respectively). 73% of patients presenting HR+/Her2- mBC had an actionable alteration, as compared to 55% of patients presenting HR+/Her2- eBC (p<0.01). Patients with HR+/Her2- mBC presented an enrichment of gene alterations in the MAPK/ERK pathway (37% vs 22%) and in the HRD pathway (22% vs 10%). When the analysis focuses on mTNBC; the proportion of patient presenting an actionable alteration was comparable to the eTNBC. 11 (6%) and 16 (9%) patients presented a somatic mutation or homozygous gene deletion on BRCA1 and PTEN respectively. We further assessed the mutational signatures in order to better understand which mutational processes could drive cancer progression. Metastatic HR+/Her2- mBC presented an increase in APOBEC, S3 (HRD), S10 (POLE-associated signature), S17 signatures as compared to early HR+/Her2- BC. Conclusion: the present study, based on 629 patients, identifies 11 driver gene alterations and four mutational processes enriched in HR+/Her2- metastatic breast cancers. Final results on 800 patients will be presented. Citation Format: Andre F, Filleron T, Ng C, Bertucci F, Letourneau C, Jacquet A, Piscuoglio S, Jimenez M, Bachelot T. Genomic characterisation of metastatic breast cancer [abstract]. In: Proceedings of the 2018 San Antonio Breast Cancer Symposium; 2018 Dec 4-8; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2019;79(4 Suppl):Abstract nr GS1-08.

Safety of adjuvant CDK4/6 inhibitors during the COVID-19 pandemic.

The Adjuvant Advantage

Breast density and background parenchymal enhancement (BPE) are suggested to be related to the risk of breast cancer. The first step to quantitative analysis of breast density and BPE is segmenting the breast from body. Nowadays, convolutional neural networks (CNNs) are widely used in image segmentation and work well in semantic segmentation, however, CNNs have been rarely used in breast region segmentation. In this paper, the CNN was employed to segment the breast region in transverse fat-suppressed breast dynamic contrast enhanced magnetic resonance imaging (DCE-MRI). Image normalization was initially performed. Subsequently, the dataset was divided into three sets randomly: train set validation set and test set. The 2-D U-Net was trained by train set and the optimum model was chosen by validation set. Finally, segmentation results of test set obtained by U-Net were adjusted in the postprocessing. In this step, two largest volumes were computed to determine whether the smaller volume is the scar after mastectomy. With the limitation of small dataset, 5-fold cross-validation and data augmentation were used in this study. Final results on the test set were evaluated by volume-based and boundary-based metrics with manual segmentation results. By using this method, the mean dice similarity coefficient (DSC), dice difference coefficient (DDC), and root-mean-square distance reached 97.44%, 5.11%, and 1.25 pixels, respectively.

ATAC trial update