Artificial Intelligence-Enhanced Breast MRI: Applications in Breast Cancer Primary Treatment Response Assessment and Prediction

ABSTRACT

Primary systemic therapy (PST) is the treatment of choice in patients with locally advanced breast cancer and is nowadays also often used in patients with early-stage breast cancer. Although imaging remains pivotal to assess response to PST accurately, the use of imaging to predict response to PST has the potential to not only better prognostication but also allow the de-escalation or omission of potentially toxic treatment with undesirable adverse effects, the accelerated implementation of new targeted therapies, and the mitigation of surgical delays in selected patients. In response to the limited ability of radiologists to predict response to PST via qualitative, subjective assessments of tumors on magnetic resonance imaging (MRI), artificial intelligence-enhanced MRI with classical machine learning, and in more recent times, deep learning, have been used with promising results to predict response, both before the start of PST and in the early stages of treatment. This review provides an overview of the current applications of artificial intelligence to MRI in assessing and predicting response to PST, and discusses the challenges and limitations of their clinical implementation.

IOERT as anticipated tumor bed boost during breast-conserving surgery after neoadjuvant chemotherapy in locally advanced breast cancer--results of a case series after 5-year follow-up

To evaluate retrospectively rates of local (LCR) and locoregional tumor control (LRCR) in patients with locally advanced breast cancer (LABC) who were treated with preoperative chemotherapy (primary systemic treatment, PST) followed by breast-conserving surgery (BCS) and either intraoperative radiotherapy with electrons (IOERT) preceding whole-breast irradiation (WBI) (Group 1) or with WBI followed by an external tumor bed boost (electrons or photons) instead of IOERT (Group 2). From 2002 to 2007, 83 patients with clinical Stage II or III breast cancer were enrolled in Group 1 and 26 in Group 2. All patients received PST followed by BCS and axillary lymph node dissection. IOERT boosts were applied by single doses of 9 Gy (90% reference isodose) versus external boosts of 12 Gy (median dose range, 6-16) in 2 Gy/fraction (ICRU). WBI in both groups was performed up to total doses of 51-57 Gy (1.7-1.8 Gy/fraction). The respective median follow-up times for Groups 1 and 2 amount 59 months (range, 3-115) and 67.5 months (range, 13-120). Corresponding 6-year rates for LCR, LRCR, metastasis-free survival, disease-specific survival and overall survival were 98.5, 97.2, 84.7, 89.2 and 86.4% for Group 1 and 88.1, 88.1, 74, 92 and 92% for Group 2, respectively, without any statistical significances. IOERT as boost modality during BCS in LABC after PST shows a trend to be superior in terms of LCR and LRCR in comparison with conventional boosts.

Detection of disseminated tumor cells in locally advanced breast cancer patients before primary systemic therapy

AIM

To assess the prevalence and prognostic power of disseminated tumor cells (DTC) in patients with locally advanced breast cancer (LABC) before primary systemic therapy (PST).

MATERIALS AND METHODS

LABC patients attending our Breast Unit were studied between 2002 and 2012, all of them being considered for PST. To determine the presence of DTC, posterior iliac crest aspirates were obtained and marrow samples were processed by gradient separation with Ficoll (Lymphoprep(®)) and immunohistochemical staining using the antiCK A45-B/B3 (EPIMET) antibody. Clinicopathologic variables were recorded before and after PST to assess response. Disease-free survival (DFS) and overall survival (OS) were determined after follow-up. The presence of DTC as a predictor of response to PST and as a prognostic tool for OS and DSF was evaluated.

RESULTS

DTC were observed in 26% of 47 patients included in the study. PST consisted of chemotherapy in 94% and hormone therapy in 6%. Breast-conserving therapy was attained in 33%. Mean follow-up was 68 months. Complete clinical response (CR) after PST was seen in 26%, disease recurrence in 38%, and cancer-related death in 8%; tumor size and negative estrogen receptors were significant predictors of CR and mastectomy was associated with DFS. Persistent axillary disease after PST and previous recurrence were predictive of OS. DTC were detected more often in patients who did not achieve CR and those who presented recurrence. DTC detection was a significant prognostic factor for a worse OS (OR = 7.62; CI95%: 1.46-39.61; p = 0.009) and a decreased survival time (62 versus 82 months, p = 0.004).

CONCLUSION

Presence of DTC before PST was found in a significant number of patients with LABC. DTC were found to be a significant prognostic factor for cancer-related death. DTC could be a surrogate predictor of response to PST and also of disease recurrence in LABC patients.