Deep learning with biopsy whole slide images for pretreatment prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer：A multicenter study

IntroductionPredicting pathological complete response (pCR) for patients receiving neoadjuvant chemotherapy (NAC) is crucial in establishing individualized treatment. Whole-slide images (WSIs) of tumor tissues reflect the histopathologic information of the tumor, which is important for therapeutic response effectiveness. In this study, we aimed to investigate whether predictive information for pCR could be detected from WSIs.Materials and methodsWe retrospectively collected data from four cohorts of 874 patients diagnosed with biopsy-proven breast cancer. A deep learning pathological model (DLPM) was constructed to predict pCR using biopsy WSIs in the primary cohort, and it was then validated in three external cohorts. The DLPM could generate a deep learning pathological score (DLPs) for each patient; stromal tumor-infiltrating lymphocytes (TILs) were selected for comparison with DLPs.ResultsThe WSI feature-based DLPM showed good predictive performance with the highest area under the curve (AUC) of 0.72 among the cohorts. Alternatively, the combination of the DLPM and clinical characteristics offered a better prediction performance (AUC >0.70) in all cohorts. We also evaluated the performance of DLPM in three different breast subtypes with the best prediction for the triple-negative breast cancer (TNBC) subtype (AUC: 0.73). Moreover, DLPM combined with clinical characteristics and stromal TILs achieved the highest AUC in the primary cohort (AUC: 0.82) and validation cohort 1 (AUC: 0.80).ConclusionOur study suggested that WSIs integrated with deep learning could potentially predict pCR to NAC in breast cancer. The predictive performance will be improved by combining clinical characteristics. DLPs from DLPM can provide more information compared to stromal TILs for pCR prediction.     

Brain impedance variation of directional leads implanted in subthalamic nuclei of Parkinsonian patients

ObjectiveConventional deep brain stimulation (DBS) systems with ring-shaped leads generate spherical electrical fields. In contrast, novel directional leads use segmented electrodes. Aim of this study was to quantify the impedance variations over time in subjects with the directional Cartesia-Boston® system.MethodsImpedance records, programming settings, and clinical data of 11 consecutive Parkinsonian patients implanted with DBS directional leads in two Italian centers (Udine and Vicenza) were retrospectively evaluated. Data were collected before starting stimulation (in the operating room and at days 5 and 40) and after switching stimulation on at the successive follow-up visits (1, 6 and 12 months).ResultsDirectional leads have significantly higher impedance than ring leads. Stimulated contacts had always lower impedance compared to non-stimulated contacts. Before DBS-on, all contacts had higher impedance in the operating room, with an initial decrease five days post-surgery and a subsequent increase at day 40, more evident for directional contacts. The impedance of directional leads increased post-implantation at 1 and 6 months with a plateau at 12 months.ConclusionsThere was a significant difference between the directional and ring leads at baseline (before activation of DBS) and during follow-up (chronic DBS).SignificanceOur study reveals new information about the impedance of segmented electrodes that is useful for patient management during the initial test period, as well as during long-term DBS follow-up.