Search

BACKGROUND: It has not been clearly established if skin cancer or melanoma are manifestations of BRCA1 or BRCA2 mutation carrier status. Estimating the risk of skin cancer is an important step towards developing screening recommendations. METHODS: We report the findings of a prospective cohort study of 6,207 women from North America who carry BRCA1 or BRCA2 mutations. Women were followed from the date of baseline questionnaire to the diagnosis of skin cancer, to age 80 years, death from any cause, or the date of last follow-up. RESULTS: During the mean follow-up period of eight years, 3.7% of women with a BRCA1 mutation (133 of 3,623) and 3.8% of women with a BRCA2 mutation (99 of 2,584) reported a diagnosis of skin cancer (including both keratinocyte carcinomas and melanoma). The cumulative risk of all types of skin cancer from age 20 to 80 years was 14.1% for BRCA1 carriers and 10.7% for BRCA2 carriers. The cumulative risk of melanoma was 2.5% for BRCA1 carriers and 2.3% for BRCA2 carriers, compared to 1.5% for women in the general population in the United States. The strongest risk factor for skin cancer was a prior diagnosis of skin cancer. CONCLUSION: The risk of non-melanoma skin cancer in women who carry a mutation in BRCA1 or BRCA2 is similar to that of non-carrier women. The risk of melanoma appears to be slightly elevated. We suggest that a referral to a dermatologist or primary care provider for BRCA mutation carriers for annual skin examination and counselling regarding limiting UV exposure, the use of sunscreen and recognizing the early signs of melanoma might be warranted, but further studies are necessary.

ImportanceMagnetic resonance imaging (MRI) surveillance is offered to women with a pathogenic variant in the BRCA1 or BRCA2 gene who face a high lifetime risk of breast cancer. Surveillance with MRI is effective in downstaging breast cancers, but the association of MRI surveillance with mortality risk has not been well defined.ObjectiveTo compare breast cancer mortality rates in women with a BRCA1 or BRCA2 sequence variation who entered an MRI surveillance program with those who did not.Design, setting, and participantsWomen with a BRCA1 or BRCA2 sequence variation were identified from 59 participating centers in 11 countries. Participants completed a baseline questionnaire between 1995 and 2015 and a follow-up questionnaire every 2 years to document screening histories, incident cancers, and vital status. Women who had breast cancer, a screening MRI examination, or bilateral mastectomy prior to enrollment were excluded. Participants were followed up from age 30 years (or the date of the baseline questionnaire, whichever was later) until age 75 years, the last follow-up, or death from breast cancer. Data were analyzed from January 1 to July 31, 2023.ExposuresEntrance into an MRI surveillance program.Main outcomes and measuresCox proportional hazards modeling was used to estimate the hazard ratios (HRs) and 95% CIs for breast cancer mortality associated with MRI surveillance compared with no MRI surveillance using a time-dependent analysis.ResultsA total of 2488 women (mean [range] age at study entry 41.2 [30-69] years), with a sequence variation in the BRCA1 (n = 2004) or BRCA2 (n = 484) genes were included in the analysis. Of these participants, 1756 (70.6%) had at least 1 screening MRI examination and 732 women (29.4%) did not. After a mean follow-up of 9.2 years, 344 women (13.8%) developed breast cancer and 35 women (1.4%) died of breast cancer. The age-adjusted HRs for breast cancer mortality associated with entering an MRI surveillance program were 0.20 (95% CI, 0.10-0.43; P

ImportancePreventive bilateral salpingo-oophorectomy is offered to women at high risk of ovarian cancer who carry a pathogenic variant in BRCA1 or BRCA2; however, the association of oophorectomy with all-cause mortality has not been clearly defined.ObjectiveTo evaluate the association between bilateral oophorectomy and all-cause mortality among women with a BRCA1 or BRCA2 sequence variation.Design, setting, and participantsIn this international, longitudinal cohort study of women with BRCA sequence variations, information on bilateral oophorectomy was obtained via biennial questionnaire. Participants were women with a BRCA1 or BRCA2 sequence variation, no prior history of cancer, and at least 1 follow-up questionnaire completed. Women were followed up from age 35 to 75 years for incident cancers and deaths. Cox proportional hazards regression was used to estimate the hazard ratios (HRs) and 95% CIs for all-cause mortality associated with a bilateral oophorectomy (time dependent). Data analysis was performed from January 1 to June 1, 2023.ExposuresSelf-reported bilateral oophorectomy (with or without salpingectomy).Main outcomes and measuresAll-cause mortality, breast cancer-specific mortality, and ovarian cancer-specific mortality.ResultsThere were 4332 women (mean age, 42.6 years) enrolled in the cohort, of whom 2932 (67.8%) chose to undergo a preventive oophorectomy at a mean (range) age of 45.4 (23.0-77.0) years. After a mean follow-up of 9.0 years, 851 women had developed cancer and 228 had died; 57 died of ovarian or fallopian tube cancer, 58 died of breast cancer, 16 died of peritoneal cancer, and 97 died of other causes. The age-adjusted HR for all-cause mortality associated with oophorectomy was 0.32 (95% CI, 0.24-0.42; P

BackgroundRisk-reducing mastectomy (RRM) is offered to women with a BRCA1 or BRCA2 pathogenic variant, however, there are limited data on the impact on breast cancer mortality.MethodsParticipants were identified from a registry of women with BRCA1/2 pathogenic variants. We used a pseudo-randomised trial design and matched one woman with a RRM to one woman without a RRM on year of birth, gene, and country. We estimated the hazard ratio (HR) and 95% confidence intervals (CI) for dying of breast cancer in the follow-up period.ResultsThere were 1654 women included; 827 assigned to the RRM arm and 827 assigned to the control arm. After a mean follow-up of 6.3 years, there were 20 incident breast cancers (including 15 occult cancers) and two breast cancer deaths in the RRM arm, and 100 incident breast cancers and 7 breast cancer deaths in the control arm (HR = 0.26; 95% CI 0.05-1.35; p = 0.11). The probability of dying of breast cancer within 15 years after RRM was 0.95%.ConclusionsIn women with a BRCA1 or BRCA2 pathogenic variant, RRM reduces the risk of breast cancer, and the probability of dying of breast cancer is low.

PurposeChemoprevention with a selective estrogen receptor modulator (tamoxifen or raloxifene) is a non-surgical option offered to high-risk women to reduce the risk of breast cancer. The evidence for tamoxifen benefit is based on trials conducted among predominantly postmenopausal women from the general population and on studies of contralateral breast cancer in women with a pathogenic variant (mutation hereafter) in BRCA1 or BRCA2. Tamoxifen has not been assessed as a primary prevention agent in women with an inherited BRCA mutation.MethodsWe conducted a prospective analysis of tamoxifen chemoprevention and the risk of breast cancer in women with a BRCA1 or BRCA2 mutation. Data on tamoxifen (and raloxifene) use was collected by questionnaire and updated biennially. Information on incident cancers was collected by self-report and was confirmed by medical record review. In a matched analysis, we estimated the hazard ratio (HR) and 95% confidence intervals (CI) for developing a first primary breast cancer associated with tamoxifen or raloxifene use, using Cox proportional hazards analysis.ResultsThere were 4578 unaffected women in the cohort, of whom 137 reported tamoxifen use (3%), 83 reported raloxifene use (2%) and 12 used both drugs (0.3%). Women who used tamoxifen or raloxifene were matched 1:3 with women who used neither drug on year of birth, country of residence, year of study entry and gene (BRCA1 or BRCA2). We generated 202 matched pairs. After a mean follow-up of 6.8 years, there were 22 incident breast cancers diagnosed among tamoxifen/raloxifene users (10.9% of users) and 71 cases diagnosed among non-users (14.3% of non-users; HR = 0.64; 95% CI 0.40-1.03; P = 0.07).ConclusionChemoprevention may be an effective risk-reduction option for BRCA mutation carriers, but further studies with longer follow-up are necessary.

BackgroundThe lack of consensus on whether bilateral oophorectomy impacts risk of developing breast cancer among BRCA1 mutation carriers might be attributed to various biases, specifically, cancer-induced testing bias due to inclusion of prevalent cases. We conducted two complementary matched case-control analyses to evaluate the association of oophorectomy and BRCA1 breast cancer.MethodsA research questionnaire was administered every two years to collect information on exposures and disease. In the first analysis, we limited the study to prevalent breast cancer cases (diagnosed prior to study entry; n = 2,962) who were matched to controls on year of birth and country of residence (n = 4,358). In the second approach, we limited to 330 incident cases (diagnosed in the follow-up period) and 1,548 matched controls. Conditional logistic regression was used to estimate the adjusted odds ratios (OR) and 95% confidence intervals (CI) of invasive breast cancer.ResultsIn the first approach, there was a significant inverse association between oophorectomy and the risk of developing breast cancer [OR = 0.43; 95% confidence interval (CI), 0.34-0.55; P < 00001]. In the second approach, there was no association between oophorectomy and risk (OR = 1.21; 95% CI, 0.87-1.70; P = 0.26).ConclusionsThe inclusion of women with a personal history of breast cancer prior to ascertainment likely impacts upon the association of oophorectomy and BRCA1 breast cancer risk.ImpactOophorectomy is unlikely a determinant of breast cancer risk in BRCA1 mutation carriers but should be offered at age 35 to reduce the risk of ovarian and fallopian tube cancer.

Background BRCA1 and BRCA2 (BRCA) mutation carriers face a high lifetime risk of developing ovarian cancer. Oral contraceptives are protective in this population; however, the impact of other types of contraception (e.g. intrauterine devices, implants, injections) is unknown. We undertook a matched case-control study to evaluate the relationship between type of contraception and risk of ovarian cancer among women with BRCA mutations. Methods A total of 1733 matched pairs were included in this analysis. Women were matched according to year of birth, date of study entry, country of residence, BRCA mutation type and history of breast cancer. Detailed information on hormonal, reproductive and lifestyle exposures were collected from a routinely administered questionnaire. Conditional logistic regression was used to estimate odds ratios (OR) and 95% confidence intervals (CI) associated with each contraceptive exposure. Results Ever use of any contraceptive was significantly associated with reduced risk of ovarian cancer (OR = 0.62; 95% CI 0.52-0.75; P

BackgroundWeight gain and other anthropometric measures on the risk of ovarian cancer for women with BRCA mutations are not known. We conducted a prospective analysis of weight change since age 18, height, body mass index (BMI) at age 18, and current BMI and the risk of developing ovarian cancer among BRCA1 and BRCA2 mutation carriers.MethodsIn this prospective cohort study, height, weight, and weight at age 18 were collected at study enrollment. Weight was updated biennially. Cox proportional hazards models were used to estimate the hazard ratio (HR) and 95% confidence intervals (CI) for ovarian cancer.ResultsThis study followed 4,340 women prospectively. There were 121 incident cases of ovarian cancer. Weight gain of more than 20 kg since age 18 was associated with a 2-fold increased risk of ovarian cancer, compared with women who maintained a stable weight (HR, 2.00; 95% CI, 1.13-3.54; P = 0.02). Current BMI of 26.5 kg/m2 or greater was associated with an increased risk of ovarian cancer in BRCA1 mutation carriers, compared with those with a BMI less than 20.8 kg/m2 (Q4 vs. Q1 HR, 2.13; 95% CI, 1.04-4.36; P = 0.04). There were no significant associations between height or BMI at age 18 and risk of ovarian cancer.ConclusionsAdult weight gain is a risk factor for ovarian cancer in women with a BRCA1 or BRCA2 mutation.ImpactThese findings emphasize the importance of maintaining a healthy body weight throughout adulthood in women at high risk for ovarian cancer.

ObjectiveBRCA mutation carriers face a high lifetime risk of developing ovarian cancer. The strong inverse association between breastfeeding and the risk of ovarian cancer is established in the general population but is less well studied among women with a germline BRCA1 or BRCA2 mutation.MethodThus, we conducted a matched case-control analysis to evaluate the association between breastfeeding history and the risk of developing ovarian cancer. After matching for year of birth, country of residence, BRCA gene and personal history of breast cancer, a total of 1650 cases and 2702 controls were included in the analysis. Conditional logistic regression was used to estimate the odds ratio (OR) and 95% confidence intervals (CI) associated with various breastfeeding exposures.ResultsA history of ever-breastfeeding was associated with a 23% reduction in risk (OR = 0.77; 95%CI 0.66-0.90; P = 0.001). The protective effect increased with breastfeeding from one month to seven months after which the association was relatively stable. Compared to women who never breastfed, breastfeeding for seven or more months was associated with a 32% reduction in risk (OR = 0.68; 95%CI 0.57-0.81; P

Background: Rates of contralateral prophylactic mastectomy (CPM) are increasing among women with unilateral breast cancer despite low rates of contralateral recurrence and lack of survival benefit. We aimed to investigate the decisional needs and supports required to ensure adequate and quality decision-making by patients with breast cancer facing the decision regarding CPM. Methods: In this qualitative study, we used semistructured interviews developed with the use of the Ottawa Decision Support Framework to investigate the decisional needs and supports of women (aged > 18 yr) with nonhereditary breast cancer who had previously discussed CPM with their care provider. Patients were recruited from 2 academic cancer centres in Toronto, Ontario. Interviews were conducted between June 2016 and October 2017. We analyzed responses to the open-ended questions iteratively and inductively to establish major themes within the results. Results: Ten patients were recruited. Eight patients reported having initiated the discussion about CPM. Although most patients reported feeling supported, 6 mentioned some degree of decisional conflict. Cancer risk reduction was the most commonly reported perceived benefit of CPM (9 patients), followed by improved psychologic well-being (7). Most patients (8) did not mention the lack of survival benefit of CPM as a disadvantage of the procedure. Patients indicated that information resources (in 8 cases) and improved counselling from their health care team (in 7) would assist in decision-making. Conclusion: Our findings illustrate the disconnect between true and perceived risks (i.e., surgical risk) and benefits (potential recurrence and survival benefit) of CPM, which is not being managed adequately despite support from the health care team. A decision aid may address unmet patient need by providing a reliable resource regarding the benefits and risks of this procedure, while helping patients understand their values and realign their expectations. Contexte : Les taux de mastectomie prophylactique controlaterale (MPC) sont en hausse chez les femmes atteintes d'un cancer du sein unilateral, malgre les faibles taux de recidive controlaterale et l'absence d'avantage sur le plan de la survie. Notre objectif consistait a etudier les outils decisionnels et les mesures de soutien necessaires pour permettre a ces patientes de prendre des decisions adequates relativement a la MPC. Methodes : Dans cette etude qualitative, nous avons eu recours a des entretiens semi-structures elabores a l'aide du Modele d'aide a la decision d'Ottawa pour analyser les outils decisionnels et les mesures de soutien necessaires aux femmes (agees de plus de 18 ans) atteintes d'un cancer du sein non hereditaire ayant deja discute de la MPC avec leur pres-tataire de soins. Les patientes ont ete recrutees dans 2 centres universitaires de cancerologie a Toronto, en Ontario. Les entretiens ont ete realises entre juin 2016 et octobre 2017. Nous avons analyse les reponses aux questions ouvertes de maniere iterative et inductive afin d'etablir des themes majeurs a partir des resultats. Resultats : Au total, 10 patientes ont ete recrutees, dont 8 ont indique avoir deja entame la discussion sur la MPC. La plupart des patientes ont affirme se sentir soutenues, mais 6 ont dit avoir tout de meme de la difficulte a prendre une decision. La reduction du risque de cancer est l'avantage de la MPC le plus souvent evoque (9 patientes), suivi de l'amelioration du bien-etre psychologique (7). La plupart des patientes (8) n'ont pas mentionne l'absence d'avantage sur le plan de la survie de la MPC parmi les inconvenients. Elles ont indique que des ressources d'information (dans 8 cas) et une amelioration du counseling de leur equipe soignante (dans 7 cas) les aideraient a prendre une decision. Conclusion : Nos resultats illustrent un decalage entre les risques et avantages reels et percus (risque operatoire d'une part; recidive potentielle et avantage sur le plan de la survie de l'autre) de la MPC qui n'est pas gere de maniere adequate malgre le soutien de l'equipe soignante. Une aide a la decision pourrait permettre de repondre aux besoins des patientes si elle leur offre une ressource fiable pour mieux comprendre les avantages et les risques de l'intervention, pour apprecier leur valeur et pour moduler leurs attentes., Over the past decade, rates of contralateral prophylactic mastectomy (CPM) have increased by 150% in the United States, and similar trends have been noted in Canada. (1-4) Although CPM has [...]

Despite consensus guidelines, most patients with early-stage triple-negative (TN) and HER2-positive (HER2+) breast cancer do not see a medical oncologist prior to surgery and do not receive neoadjuvant chemotherapy (NAC). To understand barriers to care, we aimed to characterize the relationship between geography (region of residence and cancer centre proximity) and receipt of a pre-treatment medical oncology consultation and NAC for patients with TN and HER2+ breast cancer. Using linked administrative datasets in Ontario, Canada, we performed a retrospective population-based analysis of women diagnosed with stage I–III TN or HER2+ breast cancer from 2012 to 2020. The outcomes were a pre-treatment medical oncology consultation and the initiation of NAC. We created choropleth maps to assess the distribution of the outcomes and cancer centres across census divisions. To assess the relationship between distance to the nearest cancer centre and outcomes, we performed multivariable regression analyses adjusted for relevant factors, including tumour extent and nodal status. Of 14,647 patients, 29.9% received a pre-treatment medical oncology consultation and 77.7% received NAC. Mapping demonstrated high interregional variability, ranging across census divisions from 12.5% to 64.3% for medical oncology consultation and from 8.8% to 64.3% for NAC. In the full cohort, compared to a distance of ≤5 km from the nearest cancer centre, only 10–25 km was significantly associated with lower odds of NAC (OR 0.83, 95% CI 0.70–0.99). Greater distances were not associated with pre-treatment medical oncology consultation. The interregional variability in medical oncology consultation and NAC for patients with TN and HER2+ breast cancer suggests that regional and/or provider practice patterns underlie discrepancies in the referral for and receipt of NAC. These findings can inform interventions to improve equitable access to NAC for eligible patients. [ABSTRACT FROM AUTHOR]

ImportanceProphylactic bilateral salpingo-oophorectomy is recommended for BRCA1 mutation carriers to prevent ovarian cancer. Whether or not hormone replacement therapy (HRT) initiated after oophorectomy is associated with an increased risk of breast cancer has not been evaluated in a prospective study.ObjectiveTo determine the association between HRT use and BRCA1-associated breast cancer.Design, setting, and participantsA prospective, longitudinal cohort study of BRCA1 and BRCA2 mutation carriers from 80 participating centers in 17 countries was conducted between 1995 and 2017 with a mean follow-up of 7.6 years. Participants had sought genetic testing for a BRCA1 or BRCA2 mutation because of a personal or family history of breast and/or ovarian cancer. Carriers of BRCA1 mutation with no personal medical history of cancer who underwent bilateral oophorectomy following enrollment were eligible for the cohort study.ExposuresA follow-up questionnaire was administered every 2 years to obtain detailed information on HRT use. A left-truncated Cox proportional hazard analysis was used to estimate the hazard ratios (HRs) and 95% CIs associated with the initiation of HRT use postoophorectomy.Main outcomes and measuresIncident breast cancer.ResultsA total of 872 BRCA1 mutation carriers with a mean postoophorectomy follow-up period of 7.6 years (range, 0.4-22.1) were included in this study. Mean (SD) age of participants was 43.4 (8.5) years. Among these, 92 (10.6%) incident breast cancers were diagnosed. Overall, HRT use after oophorectomy was not associated with an increased risk of breast cancer. The HR was 0.97 (95% CI, 0.62-1.52; P = .89) for ever use of any type of HRT vs no use; however, the effects of estrogen alone and combination hormonal therapy were different. After 10 years of follow-up, the cumulative incidence of breast cancer among women who used estrogen-alone HRT was 12% compared with 22% among women who used estrogen plus progesterone HRT (absolute difference, 10%; log rank P = .04).Conclusions and relevanceThese findings suggest that use of estrogen after oophorectomy does not increase the risk of breast cancer among women with a BRCA1 mutation and should reassure BRCA1 mutation carriers considering preventive surgery that HRT is safe. The possible adverse effect of progesterone-containing HRT warrants further study.

BACKGROUND:Although evidence suggests that larger body size in early life confers lifelong protection from developing breast cancer, few studies have investigated the relationship between body size and breast cancer risk among BRCA mutation carriers. Therefore, we conducted a prospective evaluation of body size and the risk of breast cancer among BRCA mutation carriers. METHODS:Current height and body mass index (BMI) at age 18 were determined from baseline questionnaires. Current BMI and weight change since age 18 were calculated from updated biennial follow-up questionnaires. Cox proportional hazards models were used to estimate the hazard ratio (HR) and 95% confidence interval (CI). RESULTS:Among 3734 BRCA mutation carriers, there were 338 incident breast cancers over a mean follow-up of 5.5 years. There was no association between height, current BMI or weight change and breast cancer risk. Women with BMI at age 18 ≥22.1 kg/m2 had a decreased risk of developing post-menopausal breast cancer compared with women with a BMI at age 18 between 18.8 and 20.3 kg/m2 (HR 0.49; 95% CI 0.30-0.82; P = 0.006). BMI at age 18 was not associated with risk of pre-menopausal breast cancer. CONCLUSIONS:There was no observed association between height, current BMI and weight change and risk of breast cancer. The inverse relationship between greater BMI at age 18 and post-menopausal breast cancer further supports a role of early rather than current or adulthood exposures for BRCA-associated breast cancer development. Future studies with longer follow-up and additional measures of adiposity are necessary to confirm these findings.

Simple Summary: The current approach to breast cancer screening, which is based on a person's age, overlooks individual-level differences in breast cancer risk. As a result, many people are over- or under-screened according to their actual risk of breast cancer. Risk-stratified breast screening may overcome the limitations of age-based screening, but there are still many knowledge gaps regarding how best to implement it in the population setting. This study will generate the first Canadian evidence on the adoption of breast cancer risk assessment in the population setting, to support the future implementation of risk-stratified breast cancer screening. This study demonstrated that, while risk assessment for risk-stratified screening at the population level is feasible, an equity lens must be considered in implementation to ensure cancer-screening disparities are not widened. Risk-stratified breast screening has been proposed as a strategy to overcome the limitations of age-based screening. A prospective cohort study was undertaken within the PERSPECTIVE I&I project, which will generate the first Canadian evidence on multifactorial breast cancer risk assessment in the population setting to inform the implementation of risk-stratified screening. Recruited females aged 40–69 unaffected by breast cancer, with a previous mammogram, underwent multifactorial breast cancer risk assessment. The adoption of multifactorial risk assessment, the effectiveness of methods for collecting risk factor information and the costs of risk assessment were examined. Associations between participant characteristics and study sites, as well as data collection methods, were assessed using logistic regression; all p-values are two-sided. Of the 4246 participants recruited, 88.4% completed a risk assessment, with 79.8%, 15.7% and 4.4% estimated at average, higher than average and high risk, respectively. The total per-participant cost for risk assessment was CAD 315. Participants who chose to provide risk factor information on paper/telephone (27.2%) vs. online were more likely to be older (p = 0.021), not born in Canada (p = 0.043), visible minorities (p = 0.01) and have a lower attained education (p < 0.0001) and perceived fair/poor health (p < 0.001). The 34.4% of participants requiring risk factor verification for missing/unusual values were more likely to be visible minorities (p = 0.009) and have a lower attained education (p ≤ 0.006). This study demonstrates the feasibility of risk assessment for risk-stratified screening at the population level. Implementation should incorporate an equity lens to ensure cancer-screening disparities are not widened. [ABSTRACT FROM AUTHOR]

Objective: Neoadjuvant chemotherapy (NAC) is a key element of treatment for locally advanced breast cancer (LABC). Predicting the response to NAC for patients with Locally Advanced Breast Cancer (LABC) before treatment initiation could be beneficial to optimize therapy, ensuring the administration of effective treatments. The objective of the work here was to develop a predictive model to predict tumor response to NAC for LABC using deep learning networks and computed tomography (CT). Materials and methods: Several deep learning approaches were investigated including ViT transformer and VGG16, VGG19, ResNet-50, Res-Net-101, Res-Net-152, InceptionV3 and Xception transfer learning networks. These deep learning networks were applied on CT images to assess the response to NAC. Performance was evaluated based on balanced_accuracy, accuracy, sensitivity and specificity classification metrics. A ViT transformer was applied to utilize the attention mechanism in order to increase the weight of important part image which leads to better discrimination between classes. Results: Amongst the 117 LABC patients studied, 82 (70%) had clinical- pathological response and 35 (30%) had no response to NAC. The ViT transformer obtained the best performance range (accuracy = 71 ± 3% to accuracy = 77 ± 4%, specificity = 86 ± 6% to specificity = 76 ± 3%, sensitivity = 56 ± 4% to sensitivity = 52 ± 4%, and balanced_accuracy=69 ± 3% to balanced_accuracy=69 ± 3%) depending on the split ratio of train-data and test¬data. Xception network obtained the second best results (accuracy = 72 ± 4% to accuracy = 65 ± 4, specificity = 81 ± 6% to specificity = 73 ± 3%, sensitivity = 55 ± 4% to sensitivity = 52 ± 5%, and balanced_accuracy = 66 ± 5% to balanced_accuracy = 60 ± 4%). The worst results were obtained using VGG-16 transfer learning network. Conclusion: Deep learning networks in conjunction with CT imaging are able to predict the tumor response to NAC for patients with LABC prior to start. A ViT transformer could obtain the best performance, which demonstrated the importance of attention mechanism. [ABSTRACT FROM AUTHOR]

Background: In patients with locally advanced breast cancer (LABC) receiving neoadjuvant chemotherapy (NAC), quantitative ultrasound (QUS) radiomics can predict final responses early within 4 of 16-18 weeks of treatment. The current study was planned to study the feasibility of a QUS-radiomics model-guided adaptive chemotherapy. Methods: The phase 2 open-label randomized controlled trial included patients with LABC planned for NAC. Patients were randomly allocated in 1:1 ratio to a standard arm or experimental arm stratified by hormonal receptor status. All patients were planned for standard anthracycline and taxane-based NAC as decided by their medical oncologist. Patients underwent QUS imaging using a clinical ultrasound device before the initiation of NAC and after the 1st and 4th weeks of treatment. A support vector machine-based radiomics model developed from an earlier cohort of patients was used to predict treatment response at the 4th week of NAC. In the standard arm, patients continued to receive planned chemotherapy with the treating oncologists blinded to results. In the experimental arm, the QUS-based prediction was conveyed to the responsible oncologist, and any changes to the planned chemotherapy for predicted non-responders were made by the responsible oncologist. All patients underwent surgery following NAC, and the final response was evaluated based on histopathological examination. Results: Between June 2018 and July 2021, 60 patients were accrued in the study arm, with 28 patients in each arm available for final analysis. In patients without a change in chemotherapy regimen (53 of 56 patients total), the QUSradiomics model at week 4 of NAC that was used demonstrated an accuracy of 97%, respectively, in predicting the final treatment response. Seven patients were predicted to be non-responders (observational arm (n=2), experimental arm (n=5)). Three of 5 non-responders in the experimental arm had chemotherapy regimens adapted with an early initiation of taxane therapy or chemotherapy intensification, or early surgery and ended up as responders on final evaluation. Conclusion: The study demonstrates the feasibility of QUS-radiomics adapted guided NAC for patients with breast cancer. The ability of a QUS-based model in the early prediction of treatment response was prospectively validated in the current study. [ABSTRACT FROM AUTHOR]