Breast Area Research Articles

Prediction of breast cancer based on RF, SVM and PCA

Breast cancer is often called the pink killer. The most recent statistics from the 2018 International Agency for Research on Cancer (IARC) survey show that the incidence rate of breast cancer is 24.2%, placing it first among women’s cancers globally, with 52.9% of cases occurring in developing nations. When cells in the breast start to grow abnormally, it can lead to the formation of tumours. These tumours can be detected through X-ray imaging or felt as lumps in the breast area, so early detection and treatment are the key to reducing the mortality rate of breast cancer. In this paper, machine learning techniques are employed to construct a breast cancer prediction model using the breast cancer dataset. Different algorithms were utilized in this paper, e.g., 3 machine learning algorithms - Support Vector Machines (SVM), Random Forest (RF), and Principal Component Analysis (PCA) - were utilized to build models for this task. The resulting models achieved impressive performance metrics, with accuracy rates of 94%, 97%, and 96% respectively. The author also finds that some features in the data are insignificant for prediction, and discarding them can lead to faster training time. However, more data is needed to achieve better performance in actual scenarios. These models can help doctors diagnose breast cancer more quickly and accurately.

Abstract PR009: Effect of testosterone therapy on quantitative breast lobular atrophy in transmasculine individuals

Abstract Background. Most transmasculine (TM) individuals pursue gender-affirming testosterone therapy (TT). The health outcomes associated with long-term TT use remains unclear. We previously reported that TT is associated with breast lobular atrophy (i.e., shrinking) when assessed by pathologists. Breast lobules are the main sites whereby cancer develops, and there are ongoing research to clarify the association between lobular atrophy and breast cancer risk. As such, TT may influence breast cancer risk in TM individuals. This study investigated the quantitative relationship between length of TT use and lobular atrophy. Materials and Methods. Breast surgical specimens were obtained from 417 TM subjects who had gender affirming chest-contouring surgery. Clinical data were retrieved from medical records. Each subject had one to six H&E slides that were reviewed by pathologists and digitized at 20× (n=1073 whole slide images (WSIs)). We applied our deep-learning computational pathology method that detects and quantifies acini and breast lobules to the WSIs. For each WSI, our method extracted total tissue area (mm2), fat area (mm2), number of breast lobules, area (mm2) and span (mm) of each lobule, and the number of acini in each lobule. Multiple WSIs for each subject were combined to compute four measures of lobular atrophy—1) median lobule size (mm2), 2) median acini counts per lobule, 3) number of lobules per mm2 of tissue area, and 4) % lobular area. We evaluated the relationship between quantitative measures of lobular atrophy for every six months of TT use with linear regression models, adjusting for age, year of surgery, race/ethnicity, BMI, chest binding, whether the subject removed their ovaries, and TT dose. Patients who did not use TT prior to surgery were assigned as zero months of TT. In order to improve the interpretability of the beta coefficient, we back transformed the natural log beta coefficients. Results. The size of breast lobules in TM individuals shrank by 3.9 % for every six months of TT use (adjusted p<0.001). The results of the other three measures were similar: the median number of acini in each breast lobule decreased by 5.5%, the number of lobules per mm2 of breast tissue decreased by 4.9%, and the % of lobular area in the breast was reduced by 10.0%, for every six months that a patient received TT (all adjusted p≤0.001). Conclusions. This is the first study to investigate the quantitative relationship between duration of TT and lobular atrophy. For every six months of TT, the breast lobules of TM subjects decreased in size and numbers at an approximate rate of 5%, after accounting for potential confounders. This work will support the understanding of breast cancer risk in the TM population, and contributes to reducing healthcare disparities in the transgender community. Citation Format: Gabrielle M. Baker, Yaileen D. Guzman-Arocho, Vanessa C. Bret-Mounet, Mitko Veta, Suzanne C. Wetstein, Brittany M. Charlton, Sarah S. Jackson, Gerburg M. Wulf, Yujing Jan Heng. Effect of testosterone therapy on quantitative breast lobular atrophy in transmasculine individuals [abstract]. In: Proceedings of the 16th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2023 Sep 29-Oct 2;Orlando, FL. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2023;32(12 Suppl):Abstract nr PR009.

Abstract B106: Assessing racial disparities in the receipt of quality care in the most prevalent cancers in American Indians

Abstract INTRODUCTION Previous SEER-Medicare analyses reported lower receipt of guideline concordant care for American Indian (AI) compared with White (WH) patients across several cancers. While large scale assessments are informative, there is a need to assess cancer outcomes and develop interventions at a level closer to communities. To address this gap, we assessed measures of quality care in AI and WH breast, prostate, and colorectal cancer patients. METHODS We assembled novel cohorts of AI and WH patients from the North Carolina (NC) cancer registry, the state with the largest AI population east of the Mississippi River. Eligible patients were diagnosed with breast, prostate, and colorectal cancers who linked to public and private insurance claims with continuous enrollment (2003-2019). Measures were assessed within 1 year of diagnosis unless stated otherwise. Breast cancer measures included receipt of: (1) HER2 testing within 3 months of diagnosis [NQF #1878]; (2) Tamoxifen/Aromatase Inhibitors for Stage I-III ER/PR+ [NQF #220]; (3) radiation among stage I-III breast conserving surgery or mastectomy patients [NQF #0219]. Stage II-III colorectal cancer measures included receipt of: (1) carcinoembryonic antigen (CEA) testing; (2) surveillance colonoscopy; and (3) computed tomography (CT) among resected patients [NCCN 2.2023 COL-8]. We assessed receipt of prostate-specific antigen (PSA) testing in the first 15 months after prostate cancer diagnosis to monitor disease recurrence. Poisson regression adjusting for sex, urbanicity, insurance type, and age at diagnosis was used to estimate risk ratios (RR) and 95% confidence intervals (CI) comparing the receipt of care between AI and WH patients. RESULTS The sample sizes of AI patients differed across measures, ranging from 104 colorectal to 554 prostate cancer patients. Evidence of disparity was mixed for the breast cancer measures. AI breast cancer patients less frequently received HER2 testing within 3 months of diagnosis (AI=61% vs WH=71%), although adjustment attenuated this association (RR=0.90; CI: 0.81-1.01). Among stage I-III breast cancer patients, AIs more frequently received radiation within 1 year of surgery (AI=75% vs WH=71%) compared with WH patients (RR=1.11; CI: 1.01-1.21). Across colorectal cancer measures, AI patients performed as well or better than WH patients. Notably, AI patients more frequently received CEA testing (AI=71% vs WH=59%), a difference that persisted after adjustment (RR=1.17; CI: 1.03-1.32). AI prostate cancer patients received PSAs less often in the 15 months following diagnosis (AI=82% vs WH=88%) than WH patients (RR=0.96; CI: 0.93-1.00). CONCLUSIONS The magnitude and direction of AI/WH disparities in receipt of quality cancer care differed across measures. Racial misclassification is a challenge in AI health outcomes research, which may misrepresent the experience of AIs. Nevertheless, our findings provide insight into specific areas of breast, prostate, and colorectal cancer care where local tailored interventions can be focused to improve care equity. Citation Format: Bradford E. Jackson, Marc E. Emerson, Lisa P. Spees, Chris D. Baggett, Hayley N. Morris, Ana I. Salas, Angelo Moore, Yadurshini Raveendran, Clare Meernik, Tomi Akinyemiju, Rachel Denlinger-Apte, Ronny A. Bell, Stephanie B. Wheeler. Assessing racial disparities in the receipt of quality care in the most prevalent cancers in American Indians [abstract]. In: Proceedings of the 16th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2023 Sep 29-Oct 2;Orlando, FL. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2023;32(12 Suppl):Abstract nr B106.

Analisis Perbandingan Pengukuran Jarak Algoritma K-Nearest Neighbor Dengan Menggunakan Data Breast Cancer Dan Data Heart Disease


 
 
 
 Breast Cancer is a cancerous condition that appears in the breast area. This type of cancer is often experienced by women with a characteristic feature of Breast Cancer, namely the appearance of unusual lumps in the breast area. Heart or Heart Disease is a type of Non-Communicable Disease (PTM): which results in a fairly high mortality rate. Heart Disease is caused by several risk factors including smoking, an unhealthy lifestyle, high cholesterol, hypertension, and diabetes.
 Based on these facts, an appropriate algorithm is needed to classify Breast Caner and Heart Disease as an effort to prevent an increase in mortality rates due to Breast Cancer and Heart Disease. And the algorithm that will be used is the K-Nearest Neighbor algorithm with 3 distance measurement methods, namely Euclidean distance, Manhattan distance, and Minkowsky distance .
 
 
 
 
 From the stages that have been carried out, the final results of the Euclidean distance method obtained an Accuracy value of 80.88% Breast Cancer data at K = 11, and 78.69% heart Disease data at K = 11. The Manhattan distance method obtained an Accuracy value of 89.71% of Breast Cancer data on K=11, and 78.69% of Heart Disease data on K=20.The Minkowsky distance method obtained an Accuracy value of 98.53% of Breast Cancer data on K=11, and 79.41% of Heart Disease data on K=11. This shows that the Minkowsky distance method works more optimally than the Euclidean distance and Manhattan distance methods.

Latissimus dorsi flap in breast reconstruction following radical mastectomy and prophylactic subcutaneous mastectomy in the same patient: Case report

One of the most common surgical treatment options for breast cancer is radical mastectomy, which affects the quality of life of patients in remission and their psychological state. One of the solutions to this problem is the use of skin and muscle flaps from other anatomical areas, in particular the back, for plastic reconstruction of the breast after radical mastectomy. The study aimed to present the practical implementation of reconstruction of both breasts in the remote period of radical mastectomy in a patient in remission of breast cancer using a skin and muscle flap of the broadest back muscle in combination with an implant. The patient, who met the criteria for participation in the study, had previously undergone a radical mastectomy of the right breast for direct indications along with radiotherapy. Delayed breast reconstruction within the study was performed 6 years after the planned right-sided mastectomy. The first surgical intervention included marking the back and breast area, excision and harvesting of the flap, preparation of the implantation site and its placement with the implant. Three months after the operation, she underwent a prophylactic mastectomy of the left breast based on molecular genetic testing with immediate reconstruction using the second flap of the broadest back muscle. The surgery was performed using a perimammary approach. Due to the available dissection, various anatomical configurations of the flap, and low-variability vascular anatomy, the latissimus dorsi flap is an adequate choice of material for the reconstruction of radical postmastectomy interventions. The final result of bilateral use of the flap for breast reconstruction after mastectomy is in favour of restoration of the anatomical tissue defect and a satisfactory aesthetic option, without complications in the form of seromas, haematomas, or pain. The result has a positive impact on the quality of life of a patient in remission of breast cancer

Neurofibroma of breast- A rare case report

Neurofibroma are benign tumour of peripheral nerve sheath that are mostly sporadic. Solitary neurofibromas of breast are uncommon. In this study, a case of 21-year-old female was referred with complaint of hyper pigmented lump in left breast since birth with recent increase in size for 5 months. Ultrasonography revealed a well-defined hypoechoic Space occupying lesion in subcutaneous plane at 11’o clock position of left breast along with a large ill-defined hypoechoic area with normal vascularity noted extending from 11’o clock to 2’o clock areas in left breast. Microscopically, the underlying stroma showed proliferating spindle cells with interspersed collagen bundles. Spindle cells show bland serpentine (wavy dark) nuclei and scant cytoplasm.

Differences in mutational signature of diffuse large B-cell lymphomas according to the primary organ.

Comprehensive molecular subtyping of diffuse large B-cell lymphoma (DLBCL) through genetic profiling has broadened our understanding of DLBCL biology. In this study, we investigated whether DLBCL, not otherwise specified (NOS) shows differences in mutational patterns depending on the primary organ. Panel-based next-generation sequencing was performed on 345 DLBCL from various primary organs, and patterns of mutations according to primary organs were analyzed. DLBCL showed a characteristic mutational signature in several primary organs. Among them, the mutational pattern of DLBCL in the breast and ileocecal area was particularly different from that of other DLBCL NOS. In breast DLBCL, MYD88L265P (57.1%), CD79B mutation (42.9%), and CDKN2A/B loss (71.4%) were found at high frequencies, which were similar to the mutation patterns of DLBCL of immune-privileged sites compared with DLBCL NOS. DLBCL in the ileocecal area showed a characteristic mutation pattern with the most frequent TP53 mutation (52.6%) and 18q21 gain (42.1%). This was also different from the mutational pattern observed in the stomach or other intestines. In discriminant analysis, DLBCL of the breast and ileocecal area tended to form separate genetic constellations from other DLBCL NOS. DLBCL NOS has a characteristic mutational profile that depends on the primary organ. In particular, the mutational signature of DLBCL in the breast and ileocecal area was heterogeneous compared with that of other DLBCL NOS. Further research is needed to determine whether primary DLBCL in the breast and ileocecal area can be classified as an independent subtype.

An Innovative Scoring System to Select the Optimal Surgery in Breast Cancer after Neoadjuvant Chemotherapy.

The selection of surgery post-neoadjuvant chemotherapy (NACT) is difficult and based on surgeons' expertise. The aim of this study was to create a post-NEoadjuvant Score System (pNESSy) to choose surgery, optimizing oncological and aesthetical outcomes. Patients (stage I-III) underwent surgery post-NACT (breast-conserving surgery (BCS), oncoplastic surgery (OPS), and conservative mastectomy (CMR) were included. Data selected were BRCA mutation, ptosis, breast volume, radiological response, MRI, and mammography pre- and post-NACT prediction of excised breast area. pNESSy was created using the association between these data and surgery. Area under the curve (AUC) was assessed. Patients were divided into groups according to correspondence (G1) or discrepancy (G2) between score and surgery; oncological and aesthetic outcomes were analyzed. A total of 255 patients were included (118 BCS, 49 OPS, 88 CMR). pNESSy between 6.896-8.724 was predictive for BCS, 8.725-9.375 for OPS, and 9.376-14.245 for CMR; AUC was, respectively, 0.835, 0.766, and 0.825. G1 presented a lower incidence of involved margins (5-14.7%; p = 0.010), a better locoregional disease-free survival (98.8-88.9%; p < 0.001) and a better overall survival (96.1-86.5%; p = 0.017), and a better satisfaction with breasts (39.8-27.5%; p = 0.017) and physical wellbeing (93.5-73.6%; p = 0.001). A score system based on clinical and radiological features was created to select the optimal surgery post-NACT and improve oncological and aesthetic outcomes.

Trends in Radiation Dose to the Contralateral Breast During Breast Cancer Radiation Therapy.

Over 4 million survivors of breast cancer live in the United States, 35% of whom were treated before 2009. Approximately half of patients with breast cancer receive radiation therapy, which exposes the untreated contralateral breast to radiation and increases the risk of a subsequent contralateral breast cancer (CBC). Radiation oncology has strived to reduce unwanted radiation dose, but it is unknown whether a corresponding decline in actual dose received to the untreated contralateral breast has occurred. The purpose of this study was to evaluate trends in unwanted contralateral breast radiation dose to inform risk assessment of second primary cancer in the contralateral breast for long-term survivors of breast cancer. Individually estimated radiation absorbed doses to the four quadrants and areola central area of the contralateral breast were estimated for 2,132 women treated with radiation therapy for local/regional breast cancers at age <55 years diagnosed between 1985 and 2008. The two inner quadrant doses and two outer quadrant doses were averaged. Trends in dose to each of the three areas of the contralateral breast were evaluated in multivariable models. The population impact of reducing contralateral breast dose on the incidence of radiation-associated CBC was assessed by estimating population attributable risk fraction (PAR) in a multivariable model. The median dose to the inner quadrants of the contralateral breast was 1.70 Gy; to the areola, 1.20 Gy; and to the outer quadrants, 0.72 Gy. Ninety-two percent of patients received ≥1 Gy to the inner quadrants. For each calendar year of diagnosis, dose declined significantly for each location, most rapidly for the inner quadrants (0.04 Gy/year). Declines in dose were similar across subgroups defined by age at diagnosis and body mass index. The PAR for CBC due to radiation exposure >1 Gy for women <40 years of age was 17%. Radiation dose-reduction measures have reduced dose to the contralateral breast during breast radiation therapy. Reducing the dose to the contralateral breast to <1 Gy could prevent an estimated 17% of subsequent radiation-associated CBCs for women treated under 40 years of age. These dose estimates inform CBC surveillance for the growing number of breast cancer survivors who received radiation therapy as young women in recent decades. Continued reductions in dose to the contralateral breast could further reduce the incidence of radiation-associated CBC.

Usefulness of Harmonic ACE+7 Scalpel in Breast Reconstruction with Extended Latissimus Dorsi Flap: An Open-label Single Institution Pilot Study.

We compared 27 patients who underwent breast reconstruction with the ELD flap using the Harmonic ACE +7 scalpel, and 28 patients who underwent breast reconstruction using an electrocautery scalpel, between May 2019 and March 2022. Data on patient demographics, surgery, and postoperative complications were collected. Surgical outcomes were compared between electrocautery (EC) and Harmonic ACE+7 (HA) groups. The median age of the patients was 50.2 years. The patient demographics between the groups did not show significant differences. Flap necrosis and hematomas did not occur, and seroma was the major postoperative complication (65.7% in the EC group and 70% in the HA group). The time required for flap elevation was significantly shorter in the HA group than in the EC group (286.0 minutes and 179.0 minutes, respectively). Blood loss reduced significantly in the HA and EC groups (138.5 mL and 78.2 mL, respectively). Moreover, decreased drainage was observed for the breast area. There were no significant differences in other end points. In breast reconstruction with ELD flaps, using the Harmonic ACE+7 can help reduce the rate of seroma, operative time, and intraoperative bleeding without further disadvantages.

Association of Proliferative Indices With Various Grades of Breast Carcinoma.

Various grades of breast carcinoma and proliferative indices used as nuclear protein Ki-67 and argyrophilic nucleolar organizer regions (AgNOR) are being compared to each other. In this observational cross-sectional investigation, 42 breast biopsies from questionable breast areas were collected and preserved in formalin and paraffin before the tissue blocks were made. A thorough medical history regarding the breast tumor and thorough physical examination results were recorded. Two sections were produced, one stained with an immunohistochemical marker called Ki-67 and the other with a unique stain called AgNOR. Grade I in Nottingham was found to be highest in subjects with Ki-67 1%, grade II in subjects with Ki-67 1-10%, and grade III in subjects with Ki-67>10%. Therefore, a higher Ki-67 score and a higher Nottingham grade were more closely associated. The mean AgNOR score was determined to be highest in Nottingham grade III and lowest in Nottingham grade I. In contrast to grade I and grade II of carcinoma (CA) breast, where there was no statistically significant association between Ki-67 and AgNOR, grade III of CA breast showed a statistically significant link between Ki-67 and AgNOR. Proliferation has been identified as a distinctive feature of cancer and as a key factor in the prognosis of the disease.

Upaya Pencegahan Kejadian Kanker Payudara Dengan Edukasi Pemeriksaan Payudara Sendiri (Sadari) pada Wanita di Kabupaten Kapuas

The Ministry of Health of the Republic of Indonesia stated that the prevalence of cancer in 2003 was only 221 cases, in 2008 it had tripled to 657 cases and there were 1,722 total cases in 2010-2011. As many as 60-70% of breast cancer patients come with advanced stages (stage III or IV), so almost half of the incidence of breast cancer ends in death. Breast self-examination (BSE) is very important as a first step to find out whether you have breast cancer or not. The existence of information about BSE and breast cancer is a motivation for women to increase knowledge about the breast area. This is the main basis for increasing knowledge about breast examination Purpose This activity increases understanding of how to check BSE with leafliat media. The Activity Method provides health education and distributes leaflets. Activity Results: how to know the incidence of cancer is to know early the abnormalities of the female body itself, especially the breast. Conclusion: Health education with leafeat can increase knowledge and understanding of early detection of abnormalities in the woman's own body parts.

Abstract 89: Translation and Linguistic Validation of the Mastectomy Module of the BREAST-Q Questionnaire for Use in Nigeria

Abstract Purpose: The majority of breast cancer patients in sub-Saharan Africa are recommended to have mastectomy; The impact of mastectomy on a predominantly young African patient population requires evaluation. The BREAST-Q is a validated patient-reported outcome measure of quality-of-life following breast surgery that has been translated into 30 languages-none in Africa. This study aimed to translate and validate the mastectomy module of the BREAST-Q for use in Nigeria. Methods: The BREAST-Q mastectomy module was translated from English to Yoruba (a major Nigerian language) and linguistically validated using best practice guidelines. Translation was performed in 4 steps: forward translation (x 2), back translation, back translation review, and cognitive interviews with post-mastectomy patients. The translated BREAST-Q instrument was administered to post-mastectomy patients (n=21) alongside the EORTC-QLQ BR23 to evaluate construct validity. Results: The translation process identified phrases not amenable to direct translation, including “emotionally healthy” and descriptions of pain (“nagging,” “throbbing,” “sharp”). Translations were amended to reflect local context and question intent. Patients provided suggestions to simplify complex phrases, such as “discomfort in your breast area.”during cognitive interviews. Internal consistency within scales was over the 0.70 threshold for psychosocial wellbeing (α=0.84-0.87), sexual wellbeing (α =0.98-0.99), physical wellbeing in chest (α =0.84-0.86), and satisfaction with care (α =0.89-0.93). ICC for test-retest reliability was moderate (0.46-0.63). Conclusion: The Yoruba version of the BREAST-Q mastectomy module in Yoruba presents a conceptually equivalent version in a language that is easy to understand.. We will use this validated instrument in a pilot study of Nigerian patients to identify targets for intervention to improve the patient experience and compliance with breast cancer surgery. Citation Format: Olalekan Olasehinde, Anya Romanoff. Translation and Linguistic Validation of the Mastectomy Module of the BREAST-Q Questionnaire for Use in Nigeria [abstract]. In: Proceedings of the 11th Annual Symposium on Global Cancer Research; Closing the Research-to-Implementation Gap; 2023 Apr 4-6. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2023;32(6_Suppl):Abstract nr 89.

Screening of Breast Cancer from Sweat Samples Analyzed by 2-Dimensional Gas Chromatography-Mass Spectrometry: A Preliminary Study.

Breast cancer (BC) remains one of the most commonly diagnosed malignancies in women. There is increasing interest in the development of non-invasive screening methods. Volatile organic compounds (VOCs) emitted through the metabolism of cancer cells are possible novel cancer biomarkers. This study aims to identify the existence of BC-specific VOCs in the sweat of BC patients. Sweat samples from the breast and hand area were collected from 21 BC participants before and after breast tumor ablation. Thermal desorption coupled with two-dimensional gas chromatography and mass spectrometry was used to analyze VOCs. A total of 761 volatiles from a homemade human odor library were screened on each chromatogram. From those 761 VOCs, a minimum of 77 VOCs were detected within the BC samples. Principal component analysis showed that VOCs differ between the pre- and post-surgery status of the BC patients. The Tree-based Pipeline Optimization Tool identified logistic regression as the best-performing machine learning model. Logistic regression modeling identified VOCs that distinguish the pre-and post-surgery state in BC patients on both the breast and hand area with sensitivities close to 1. Further, Shapley additive explanations and the probe variable method identified the most important and pertinent VOCs distinguishing pre- and post-operative status which are mostly of distinct origin for the hand and breast region. Results suggest the possibility to identify endogenous metabolites linked to BC, hence proposing this innovative pipeline as a stepstone to discovering potential BC biomarkers. Large-scale studies in a multi-centered VOC analysis setting must be carried out to validate obtained findings.

Missed and Detected Incidental Breast Cancers on Contrast Enhanced Chest CT: Detection Rates and CT Features.

This study investigated the rate at which radiologists miss or detect incidental breast cancers on chest CT and to compare the CT features between the two groups. This retrospective study evaluated chest CT examinations and medical records of patients who registered with the diagnosis code of "breast cancer" between January 2016 and December 2020, and who had undergone contrast enhanced chest CT 3-18 months before registration, during which they were unaware of any breast lesions. This study found that out of 84 patients, incidental breast cancer lesions were missed in 54 (64.3%) and detected in 30 (53.7%). The initial treatment was delayed in the missed breast lesions group (p = 0.004). Breast lesions of smaller sizes (<9.0 mm, p = 0.01), or with lower enhancement ratios (<1.4, p = 0.009), were more likely to be missed. When three radiologists re-read the CTs with more attention to breast area, they detected breast cancers with higher accuracies (90.1%, 87.9%, and 81.3%). In summary, this study revealed that radiologists miss 64.3% of incidental breast cancers on chest CT, especially those of sub-centimeter sizes and weak enhancements.

An in silico study on the detectability of field cancerization through parenchymal analysis of digital mammograms.

Parenchymal analysis has shown promising performance for the assessment of breast cancer risk through the characterization of the texture features of mammography images. However, the working principles behind this practice are yet not well understood. Field cancerization is a phenomenon associated with genetic and epigenetic alterations in large volumes of cells, putting them on a path of malignancy before the appearance of recognizable cancer signs. Evidence suggests that it can induce changes in the biochemical and optical properties of thetissue. The aim of this work was to study whether the extended genetic mutations and epigenetic changes due to field cancerization, and the impact they have on the biochemistry of breast tissues are detecTable in the radiological patterns of mammography images. An in silico experiment was designed, which implied the development of a field cancerization model to modify the optical tissue properties of a cohort of 60 voxelized virtual breast phantoms. Mammography images from these phantoms were generated and compared with images obtained from their non-modified counterparts, i.e. without field cancerization. We extracted 33 texture features from the breast area to quantitatively assess the impact of the field cancerization model. We analyzed the similarity and statistical equivalence of texture features with and without field cancerization using the t-test, Wilcoxon sign rank test and Kolmogorov-Smirnov test, and performed a discrimination test using multinomial logistic regression analysis with lasso regularization. With modifications of the optical tissue properties on 3.9% of the breast volume, some texture features started to fail to show equivalence (p\le0.05). At 7.9% volume modification, a high percent of texture features showed statistically significant differences (p\le0.05) and non-equivalence. At this level, multinomial logistic regression analysis of texture features showed a statistically significant performance in the discrimination of mammograms from breasts with and without field cancerization (AUC= 0.89, 95% CI: 0.75 - 1.00). These results support the idea that field cancerization is a feasible underlying working principle behind the distinctive performance of parenchymal analysis in breast cancer riskassessment. This article is protected by copyright. All rights reserved.

Abstract 6221: Support for targeted therapy selection in triple negative breast cancer patients using aberrant signal transduction pathway activity profiles

Abstract Introduction: Success of therapeutic interventions largely rely on the pathological and biological characteristics of the tumor and varies due to the heterogeneous nature of breast cancers. Triple negative breast cancers (TNBC) stain IHC negative for both hormone receptors (ER, PR) and HER-2. TNBC is usually treated with chemotherapy because of absence of any molecular target. This study is initiated to characterize TNBC based on a new methodology that measures and quantifies signal transduction pathways (STPs) activities to reveal potential tumor-driving STPs in TNBC and create new options for targeted therapy. Method: Using the mRNA-based OncoSIGNal pathway activity profiling PCR test (InnoSIGN) STP activities of 7 pathways (AR, ER, PI3K, MAPK, HH, TGFβ and Notch) in 39 samples from normal breast tissue and 12 TNBC patients were quantified and expressed on a scale from 0-100. Normal healthy breast tissue was obtained from breast reduction surgery and areas where epithelial cells content was at least 50% were annotated and harvested for mRNA isolation and STP analyses. The normal STP activity is representing the normal physiological activity and is used as reference value. Aberrant high pathway activity in a patient tumor sample was concluded when this score was higher than twice the standard deviation above the mean of normal breast tissue STP activity. Results: STP thresholds for interpretation of high aberrant activity were determined from 39 normal breast samples. Using these thresholds, STP activities in 12 TNBC samples were analyzed. In these TNBC samples, MAPK was in 75%, HH in 67%, PI3K in 58%, and AR, Notch and TGFβ were in 17% of the cases above the thresholds. In 50% of the cases a combination of MAPK and HH or a combination of PI3K and HH were found above thresholds. In 42% of the cases MAPK in combination with PI3K were above thresholds. Increased activity of AR was never observed in combination with increased HH activity. Conclusion: By using the OncoSIGNal test high aberrant STP activities could be determined in TNBC patient samples. Results show that different pathways are aberrantly active, depending on the patient sample, which opens the opportunity for personalized targeted treatment of individual TNBC patients. Next steps: The TNBC data set will be extended to further profile the STP activity in relation to different clinical outcomes and to investigate new opportunities for targeted therapies. Citation Format: Diederick M. Keizer, Yvonne J. Wesseling, Dianne A. van Strijp, Saskia M. Vermeer, Eveline C. den Biezen. Support for targeted therapy selection in triple negative breast cancer patients using aberrant signal transduction pathway activity profiles [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 6221.

SurVolT: Surface to Volume conversion Tool. A proof of concept

Purpose:To develop SurVolT, a conversion tool able to apply volumetric changes to DICOM Computed Tomography (CT) data using daily surface (obj) data acquired with AlignRT® (VisionRT Ltd.), primarily designed and validated for breast treatments. Materials and Methods:SurVolT proceeds in 4 steps: 1. AlignRT .obj files extraction, 2. Contour deformation where the surface data points are matched to the initial external contour on a Region Of Interest, ROImatch, on which the anatomy is supposed to be unchanged. Then, external contour substitution is performed on the ROIttt covering the treated breast area. This is validated on a female torso phantom with a tissue-equivalent bolus mimicking an edema. The Planning Treatment Volume (PTV) contour from the initial CT is also deformed according to the new external contour in the ROIttt. 3. Volumetric data estimation according to the new external contour, validated on an anthropomorphic pelvis phantom. 4. Import of new DICOM data into the Treatment Planning System (TPS). Finally, the workflow is applied on a first patient presenting an anatomical change during the treatment. Results:The validation of step 2 and 3 shows a bolus thickness estimation of 5.8±1.2mm (expected 5 mm) and the non-rigid deformation of initial CT images follows the new external contour at the ROIttt bolus site while revealing negligible deformation elsewhere. Conclusion:This first proof of concept introducing a Surface Guided Radiotherapy (SGRT) tool allowing daily surface data to volume conversion is a fundamental step toward SGRT-based adaptive radiotherapy.

Identifying regions of interest in mammogram images.

Screening mammography is the primary preventive strategy for early detection of breast cancer and an essential input to breast cancer risk prediction and application of prevention/risk management guidelines. Identifying regions of interest within mammogram images that are associated with 5- or 10-year breast cancer risk is therefore clinically meaningful. The problem is complicated by the irregular boundary issue posed by the semi-circular domain of the breast area within mammograms. Accommodating the irregular domain is especially crucial when identifying regions of interest, as the true signal comes only from the semi-circular domain of the breast region, and noise elsewhere. We address these challenges by introducing a proportional hazards model with imaging predictors characterized by bivariate splines over triangulation. The model sparsity is enforced with the group lasso penalty function. We apply the proposed method to the motivating Joanne Knight Breast Health Cohort to illustrate important risk patterns and show that the proposed method is able to achieve higher discriminatory performance.

Clinical assessment of a novel machine-learning automated contouring tool for radiotherapy planning.

Contouring has become an increasingly important aspect of radiotherapy due to inverse planning. Several studies have suggested that the clinical implementation of automated contouring tools can reduce inter-observer variation while increasing contouring efficiency, thereby improving the quality of radiotherapy treatment and reducing the time between simulation and treatment. In this study, a novel, commercial automated contouring tool based on machine learning, the AI-Rad Companion Organs RT™ (AI-Rad) software (Version VA31) (Siemens Healthineers, Munich, Germany), was assessed against both manually delineated contours and another commercially available automated contouring software, Varian Smart Segmentation™ (SS) (Version 16.0) (Varian, Palo Alto, CA, United States). The quality of contours generated by AI-Rad in Head and Neck (H&N), Thorax, Breast, Male Pelvis (Pelvis_M), and Female Pelvis (Pevis_F) anatomical areas was evaluated both quantitatively and qualitatively using several metrics. A timing analysis was subsequently performed to explore potential time savings achieved by AI-Rad. Results showed that most automated contours generated by AI-Rad were not only clinically acceptable and required minimal editing, but also superior in quality to contours generated by SS in multiple structures. In addition, timing analysis favored AI-Rad over manual contouring, indicating the largest time saving (753s per patient) in the Thorax area. AI-Rad was concluded to be a promising automated contouring solution that generated clinically acceptable contours and achieved time savings, thereby greatly benefiting the radiotherapy process.