Prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer using a deep learning (DL) method
AbstractBackgroundThe aim of the study was to develop a deep learning (DL) algorithm to evaluate the pathological complete response (pCR) to neoadjuvant chemotherapy in breast cancer.MethodsA total of 302 breast cancer patients in this retrospective study were randomly divided into a training set (n = 244) and a validation set (n = 58). Tumor regions were manually delineated on each slice by two expert radiologists on enhanced T1 ‐weighted images. Pathological results were used as ground truth. Deep learning network contained five repetitions of convolution and max‐pooling layers and ended with three dense layers. The pre‐NAC model and post‐NAC model inputted six phases of pre‐NAC and post‐NAC images, respectivel y. The combined model used 12 channels from six phases of pre‐NAC and six phases of post‐NAC images. All models above included three indexes of molecular type as one additional input channel.ResultsThe training set contained 137 non ‐pCR and 107 pCR participants. The validation set contained 33 non‐pCR and 25 pCR participants. The area under the receiver operating characteristic (ROC) curve (AUC) of three models was 0.553 for pre‐NAC, 0.968 for post‐NAC and 0.970 for the combined data, respectively. A significant differ ence was found in AUC between using pre‐NAC data alone and combined data (P
Conclusions: Docetaxel and epirubicin neoadjuvant chemotherapy showed a good response in locally advanced breast cancer. Pretreatment Ki-67 and change of Ki-67 may play a role as predictive factor for response to neoadjuvant chemotherapy. PMID: 32069523 [PubMed - as supplied by publisher]
AbstractPurposeTo investigate whether monitoring with ultrasound and MR imaging before, during and after neoadjuvant chemotherapy (NAC) can predict axillary response in breast cancer patients.Materials and methodsA total of 131 breast cancer patients with clinically positive axillary lymph node (LN) who underwent NAC and subsequent surgery were enrolled. They had ultrasound and 3.0 T-MR examinations before, during and after NAC. After reviewing ultrasound and MR images, axillary LN features and tumour size (T size) were noted. According to LN status after surgery, imaging features and their diagnostic performances were ana...
ConclusionsThis survey shows a fairly good use of hRT and a moderate practice of PBI in Italy. Some practices like hRT to the chest wall and regional lymph nodes as well as rRT need further verification. Likewise, the management of post-NAC RT is very heterogeneous. Future national clinical collaborative studies are advocated in order to investigate these controversial topics about breast cancer radiotherapy.
Conclusion EORTC criteria and PERCIST had early predictive value to long-term outcome, but moderate value for pCR. Furthermore, PERCIST might show more potential than the EORTC criteria and conventional PET-based parameters to predict prognosis in breast cancer patients following two cycles of neoadjuvant chemotherapy. Video abstract: see http://links.lww.com/NMC/A162.
Conditions: HER2-positive Breast Cancer; Chemotherapy Effect; Circulating Tumor DNA Intervention: Diagnostic Test: LiquidSCAN(Trade Mark) / CancerSCAN(Trade Mark) Sponsor: Samsung Medical Center Active, not recruiting
Authors: Garufi G, Palazzo A, Paris I, Orlandi A, Cassano A, Tortora G, Scambia G, Bria E, Carbognin L Abstract Introduction: Despite recent advances in the molecular characterization of triple-negative breast cancer (TNBC), the standard treatment for early-stage TNBC is represented by the historically used anthracycline and taxane-based chemotherapy. In this modern era of precision medicine, several new therapeutic strategies and novel agents have been investigated in the neoadjuvant setting of TNBC, in order to individualize treatment.Areas covered: This review provides a comprehensive overview of the currently a...
ConclusionesLa colocación de semillas de 125I es una técnica factible para la localización intraoperatoria del ganglio positivo biopsiado en combinación con la BGC. El resultado anatomopatológico del GM permite determinar el estatus axilar posneoadyuvancia.AbstractObjectiveTo present our initial experience in the combined procedure of intraoperative detection of axillary positive node marked with 125I seed (ML) and sentinel node biopsy (SLN) after neoadjuvant chemotherapy (NACT), in breast cancer patients.Material and methodsProspective study, January 2017 – March 2019, 16 breast ca...
ConclusionsIn patients with TNBC-NST, intra-E and intra-N did not correlate with pCR, but intra-E did positively correlate with tumor size. NST may exhibit a greater response to NAC, regardless of whether intra-E or intra-N is present or not on the pretreatment MRI.Key Points• Pathological complete response in TNBC-NST had no correlation with intramammary edema or intratumoral necrosis.• NAC may be justified in TNBC-NST even in the presence of edema or necrosis.• The extension of edema correlated with tumor size of TNBC-NST.
ConclusionAdministration of adjuvant eribulin after neoadjuvant chemotherapy was feasible and well tolerated. The 24-month DFS rate did not reach the study target levels in any of the cohorts and was similar to DFS previously described in these cohorts following neoadjuvant chemotherapy alone.
Conclusion: Our results indicated that DCE-MRI could be considered an important auxiliary method for evaluating the pathological response of breast cancer to NAC and used as an effective method for dynamically monitoring the efficacy during NAC. DCE-MRI also performed well in predicting the pCR of breast cancer to NAC. However, due to the heterogeneity of the included studies, caution should be exercised in applying our results.