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.     

Anomalous Origin of the Left Coronary Artery from the Pulmonary Artery: Diagnoses and Surgical Results in 12 Pediatric Patients

Anomalous origin of the left coronary artery from the pulmonary artery (ALCAPA) is a rare congenital condition. It responds well to early diagnosis and treatment, but otherwise the prognosis is poor. We present our case series of 12 patients (mean age, 2 ± 2.58 yr; age range, 2 mo–8 yr), emphasizing the diagnostic process and discussing our surgical results. The diagnosis of ALCAPA should be suspected in infants who have dilated cardiomyopathy with electrocardiographic changes that suggest ischemia, and in older children who have isolated mitral regurgitation. When clinical suspicion is high, the results of 2-dimensional echocardiography combined with color-flow Doppler studies in expert hands can establish the diagnosis, thus avoiding angiography in critically ill infants. The treatment of choice in our patients was transfer and reimplantation of the left coronary artery onto the ascending aorta. There were 2 deaths: both were infants in extremis who underwent emergency surgery. An older child with severe ventricular dysfunction was given mechanical ventricular assistance and then heart transplantation. As of this report, all 10 survivors remained well and asymptomatic.     

Sudden Cardiac Death in Patients With Type 1 Versus Type 2 Diabetes

ObjectiveTo investigate the association between type 1 diabetes mellitus (T1D) and type 2 diabetes mellitus (T2D) with risk of sudden cardiac arrest (SCA).MethodsIn a prospective community-based study of SCA from February 1, 2002, through November 30, 2019, we ascertained 2771 cases age 18 years of age or older and matched them to 8313 controls based on geography, age, sex, and race/ethnicity. We used logistic regression to evaluate the independent association between diabetes, T1D, T2D, and SCA.ResultsPatients had a mean age of 64.5±15.9 years, were 33.3% female and 23.9% non-White race. Overall, 36.7% (n=1016) of cases and 23.8% (n=1981) of controls had diabetes. Among individuals with diabetes, the proportion of T1D was 6.5% (n=66) among cases and 2.0% among controls (n=40). Diabetes was associated with 1.5-times higher odds of SCA. Compared with those without diabetes, the odds ratio and 95% CI for SCA was 4.36 (95% CI, 2.81 to 6.75; P<.001) in T1D and 1.45 (95% CI, 1.30 to 1.63; P<.001) in T2D after multivariable adjustment. Among those with diabetes, the odds of having SCA were 2.41 times higher in T1D than in T2D (95% CI, 1.53 to 3.80; P<.001). Cases of SCA with T1D were more likely to have an unwitnessed arrest, less likely to receive resuscitation, and less likely to survive compared with those with T2D.ConclusionType 1 diabetes was more strongly associated with SCA compared with T2D and had less favorable outcomes following resuscitation. Diabetes type could influence the approach to risk stratification and prevention of SCA.