Search

Although the categorization of ultrasound using the Breast Imaging Reporting and Data System (BI-RADS) has become widespread worldwide, the problem of inter-observer variability remains. To maintain uniformity in diagnostic accuracy, we have developed a novel artificial intelligence (AI) system in which AI can distinguish whether a static image obtained using a breast ultrasound represents BI-RADS3 or lower, or BI-RADS4a or higher, to determine the medical management that should be performed on a patient whose breast ultrasound shows abnormalities. To establish and validate the AI system, a training dataset consisting of 4,028 images containing 5,014 lesions and a test dataset consisting of 3,166 images containing 3,656 lesions were collected and annotated. We selected a setting that maximized the area under the curve (AUC) and minimized the difference in sensitivity and specificity by adjusting the internal parameters of the AI system, achieving an AUC, sensitivity, and specificity of 0.95, 90.0%, and 88.5%, respectively. Furthermore, based on 30 images extracted from the test data, the diagnostic accuracy of 20 clinicians and the AI system was compared, and the AI system was found to be significantly superior to the clinicians (McNemar test, p < 0.001). Then, we conducted a trial to introduce the system for use in clinical practice. Physicians reviewed the images and determined whether they were BI-RADS3 or lower, or BI-RADS4a or higher. Next, the classification was performed again for the same images concerning the AI diagnosis. At this time, the initial judgment was allowed to be overturned. We checked whether there was any difference in the diagnostic accuracy, sensitivity, and specificity before and after reviewing to the AI diagnosis. Reviews by 24 physicians were evaluated: 4 Japanese Breast Cancer Society breast specialists, 5 non-specialists and physicians with experience treating more than 40 cases of breast cancer, and 15 non-specialists and physicians with no experience treating more than 40 cases of breast cancer. The average rate of accuracy before confirming the AI diagnosis increased to 73.1% after confirming the AI diagnosis (p=0.00548), compared to 69.3% on average before the AI diagnosis. Compared to practice experience, the accuracy increased from an average of 77.1% to 79.6% for the 9 physicians who were breast specialists or who had treated 40 or more cases of breast cancer. For the 15 physicians with less than 40 breast cancer cases, the average rate of accuracy increased from 64.7% to 69.2%. Furthermore, sensitivity increased significantly to an average of 99.7% after reviewing of the AI diagnosis from an average of 88.8% prior to reviewing the AI-diagnosis.(p< 0.01). Specificity increased from an average of 62.4% to 63.8% (p=0.433) after reviewing AI diagnosis. We showed that our AI system, when applied to clinical practice and used by physicians, contributes to the improvement of diagnostic accuracy. Our results indicated that our AI diagnostic system was sufficiently accurate to be used in the clinical practice. Citation Format: Erina Odani, Tetsu Hayashida, masayuki kikuchi, Aiko Nagayama, tomoko seki, maiko takahashi, Akiko Matsumoto, Takeshi Murata, Rurina Watanuki, Takamichi Yokoe, Ayako Nakashoji, Hinako Maeda, Tatsuya Onishi, Sota Asaga, Takashi Hojo, Hiromitsu Jinno, Keiichi Sotome, Akira Matsui, Akihiko Suto, Shigeru Imoto, Yuko Kitagawa. Establishment of the breast ultrasound support system using deep-learning system [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P1-05-06.

Although the categorization of ultrasound using the Breast Imaging Reporting and Data System (BI-RADS) has become widespread worldwide, the problem of inter-observer variability remains. To maintain uniformity in diagnostic accuracy, we have developed a system in which artificial intelligence (AI) can distinguish whether a static image obtained using a breast ultrasound represents BI-RADS3 or lower or BI-RADS4a or higher to determine the medical management that should be performed on a patient whose breast ultrasound shows abnormalities. To establish and validate the AI system, a training dataset consisting of 4028 images containing 5014 lesions and a test dataset consisting of 3166 images containing 3656 lesions were collected and annotated. We selected a setting that maximized the area under the curve (AUC) and minimized the difference in sensitivity and specificity by adjusting the internal parameters of the AI system, achieving an AUC, sensitivity, and specificity of 0.95, 91.2%, and 90.7%, respectively. Furthermore, based on 30 images extracted from the test data, the diagnostic accuracy of 20 clinicians and the AI system was compared, and the AI system was found to be significantly superior to the clinicians (McNemar test, p 0.001). Although deep-learning methods to categorize benign and malignant tumors using breast ultrasound have been extensively reported, our work represents the first attempt to establish an AI system to classify BI-RADS3 or lower and BI-RADS4a or higher successfully, providing important implications for clinical actions. These results suggest that the AI diagnostic system is sufficient to proceed to the next stage of clinical application.

Due to the increasing complexity of cancer treatment, ensuring safety and maintaining the quality of life during treatment are important issues. Patient-reported outcomes (PROs) in oncology are essential for assessing patient symptoms. A feasibility study was undertaken on breast cancer patients by building a PRO data collection system based on LINE, one of the most popular social network service applications in Japan. In this study, one or more predefined PRO questions for each breast cancer patient's clinical situation were sent to the patient's LINE application daily. The patient selected a predefined answer by tapping the screen, but no free-text answers were allowed. Seventy-three patients were enrolled. The median observation period was 435 days (84-656 days), and the total number of PROs collected was 16,417, with a mean of 224.9 reports per patient. Patients on adjuvant endocrine therapy were notified of 2.5 questions per week, and the median number of responses per week and response rate were 2.387 (1.687-11.627) and 95.5%, respectively. Analyzing the results by age group, the number of responses from those aged 60 and above was equal to or higher than that of the younger age group. It was also possible to track each patient's PROs accurately. These results suggested that the design of the system, based on an application used daily, instead of using specifically prepared applications for collecting electronic PROs, was the reason for the favorable acceptance from patients and the satisfactory response rate from all age groups, including the elderly.

Background Anthracyclines are commonly used for the treatment of solid tumors and hematological malignancies because of their inevitable dose-dependent cardiotoxic effects. The study aimed to assess the feasibility of applying a biomarker-based surveillance strategy according to European guidelines for the early prediction of anthracycline-induced cardiotoxicity in patients with breast cancer.Methods From April 2018 to December 2021, 45 women with breast cancer (53.9 ± 11.0 years) treated with anthracycline-based regimens were evaluated for 1 year. We measured and analyzed high-sensitivity cardiac troponin T (hsTnT), B-type natriuretic peptide (BNP), global longitudinal strain (GLS), and left ventricular ejection fraction (LVEF) at baseline, and 3 and 6 months after the initiation of anthracycline-based chemotherapy. Cardiotoxicity was defined as a reduction in LVEF > 10% compared with baseline to LVEF 15% from baseline.Results After initiating anthracycline treatment, hsTnT levels peaked at 3 months, whereas BNP levels were the highest at 6 months. Cardiotoxicity was detected in 18 (20.0%) patients (one patient with LVEF decline), where GLS declined over time yet became significant only after 6 months. Elevated hsTnT at 3 months were significantly associated with a GLS decline at 6 months (P Conclusions Among patients with early-stage breast cancer, an increase in hsTnT at 3 months after initiation of the anthracycline-based regimen predicted a subsequent decline in GLS with high sensitivity and moderate specificity.

Purpose Male breast cancer (MBC) is a rare cancer accounting for only 1% of all male cancers and is, therefore, poorly studied. We aimed to characterize the subtypes of MBC in Japanese patients based on genetic profiling, the presence of tumor-infiltrating cells, and the expression of immunohistochemical markers. Methods This retrospective study included 103 patients with MBC diagnosed between January 2009 and December 2019 at various hospitals in Japan. Clinicopathological patient characteristics were obtained from medical records, and formalin-fixed paraffin-embedded tissue specimens were analyzed for histological markers, mutations of 126 genes, BRCA1 methylation, and stromal tumor-infiltrating lymphocytes. Results The median patient age was 71 (range 31–92) years. T1-stage tumors were the most frequent (47.6%), and most were node negative (77.7%). The majority of tumors were positive for estrogen receptor (98.1%), progesterone receptor (95.1%), and androgen receptor (96.1%), and BRCA2 was the most frequently mutated gene (12.6%). The most common treatment was surgery (99.0%), either total mastectomy (91.1%) or partial mastectomy (7.0%). Survival analysis showed a 5-year recurrence-free survival rate of 64.4% (95% confidence interval [CI] 46.7–88.8) and a 5-year overall survival rate of 54.3% (95% CI 24.1–100.0). Conclusion Japanese MBC is characterized by a high rate of hormonal receptor positivity and BRCA2 somatic mutation. Due to the observed clinicopathological differences in MBC between the Western countries and Japan, further prospective studies are needed to evaluate the most suitable treatment strategies.

Background: Sacituzumab Govitecan (SG), the first antibody-drug conjugate approved for metastatic TNBC (mTNBC), is comprised of SN-38 (active metabolite of irinotecan), a topoisomerase I (TOP1) inhibitor, coupled via a hydrolyzable linker to monoclonal antibody targeting trophoblast cell surface antigen 2 (Trop-2), an antigen overexpressed in mTNBC. Poly (ADP-ribose) polymerase inhibitors (PARPi) block resolution of TOP1 cleavage complexes (TOP1CCs) induced by TOP1 inhibitors, thus unmasking the inability of remaining pathways to repair DNA damage. However, previous clinical trials combining PARPi with standard TOP1 inhibitors (irinotecan, topotecan) were terminated early due to dose-limiting myelosuppression. We evaluated the combination of SG with PARP inhibitor in both pre-clinical models and phase 1b clinical trial. Methods and Results: In pre-clinical models we demonstrated that the targeted antibody-based delivery of SN-38 increased the ratio of tumor-to-normal cell SN-38, resulting in stabilized TOP1CCs, enhanced DNA damage and increased cytotoxicity with the combination, selectively in tumor cells but not normal cells, despite temporal separation of SG and PARPi exposure. To validate the hypothesis, we conducted a phase 1b investigator-initiated clinical trial combining SG with PARPi (talazoparib) in patients with mTNBC (NCT04039230). Inclusion criteria included female patients ≥ 18 years of age with mTNBC (per ASCO/CAP guidelines) and previous treatment with at least one prior therapeutic regimen for mTNBC. Clinical outcomes were assessed by Objective Response Rate per RECIST v1.1. In the phase 1b clinical trial (SG day 18, every 21 days with talazoparib), the staggered schedule with supportive therapy was relatively well-tolerated without DLTs, as predicted by the pre-clinical models. Furthermore, the staggered schedule demonstrated promising clinical activity. Molecular analysis of paired pre-treatment and on-treatment specimens demonstrated γ-H2AX accumulation, confirming pharmacodynamic inhibition with combination therapy. The dose-escalation portion of clinical trial successfully completed enrollment with a recommended phase-2 dose (R2PD) of sequential SG (10 mg/kg on days 1,8) with talazoparib (1 mg on days 15-21), every 21 days. Conclusion: Staggered dosing of SG and PARPi, leveraging the selective drug delivery mechanism of SG to minimize toxicity while maintaining efficacy, was feasible and demonstrated encouraging evidence of clinical activity with objective responses among patients with mTNBC. The translational study highlights how mechanistic insights and innovative scheduling could be utilized to develop promising drug combinations, including previously rejected combinations, for patients with mTNBC. Citation Format: Aditya Bardia, James T. Coates, Laura Spring, Sheng Sun, Dejan Juric, Nayana Thimmiah, Andrzej Niemierko, Phoebe Ryan, Ann Partridge, Jeffrey Peppercorn, Heather Parsons, Seth Wander, Kelsey Pierce, Victoria Attaya, Donna Fitzgerald, Brenda Lormil, Maria Shellock, Aiko Nagayama, Veerle Bossuyt, Bev Moy, Sara Tolaney, Leif Ellisen. Sacituzumab Govitecan, combination with PARP inhibitor, Talazoparib, in metastatic triple-negative breast cancer (TNBC): Translational investigation [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 2638.