Radiographic imaging is routinely used to evaluate treatment response in solid tumors. Current imaging response metrics do not reliably predict the underlying biological response. Here, we present a multi-task deep learning approach that allows simultaneous tumor segmentation and response prediction. We design two Siamese subnetworks that are joined at multiple layers, which enables integration of multi-scale feature representations and in-depth comparison of pre-treatment and post-treatment images. The network is trained using 2568 magnetic resonance imaging scans of 321 rectal cancer patients for predicting pathologic complete response after neoadjuvant chemoradiotherapy. In multi-institution validation, the imaging-based model achieves AUC of 0.95 (95% confidence interval: 0.91–0.98) and 0.92 (0.87–0.96) in two independent cohorts of 160 and 141 patients, respectively. When combined with blood-based tumor markers, the integrated model further improves prediction accuracy with AUC 0.97 (0.93–0.99). Our approach to capturing dynamic information in longitudinal images may be broadly used for screening, treatment response evaluation, disease monitoring, and surveillance.
Objective The aim of this study was to investigate whether pretherapeutic, multiparametric magnetic resonance imaging (MRI) radiomic features can be used for predicting non-response to neoadjuvant therapy in patients with locally advanced rectal cancer (LARC). Methods We retrospectively enrolled 425 patients with LARC [allocated in a 3:1 ratio to a primary ( n = 318) or validation ( n = 107) cohort] who received neoadjuvant therapy before surgery. All patients underwent T1-weighted, T2-weighted, diffusion-weighted, and contrast-enhanced T1-weighted MRI scans before receiving neoadjuvant therapy. We extracted 2424 radiomic features from the pretherapeutic, multiparametric MR images of each patient. The Wilcoxon rank-sum test, Spearman correlation analysis, and least absolute shrinkage and selection operator regression were successively performed for feature selection, whereupon a multiparametric MRI-based radiomic model was established by means of multivariate logistic regression analysis. This feature selection and multivariate logistic regression analysis was also performed on all single-modality MRI data to establish four single-modality radiomic models. The performance of the five radiomic models was evaluated by receiver operating characteristic (ROC) curve analysis in both cohorts. Results The multiparametric, MRI-based radiomic model based on 16 features showed good predictive performance in both the primary ( p < 0.01) and validation ( p < 0.05) cohorts, and performed better than all single-modality models. The area under the ROC curve of this multiparametric MRI-based radiomic model achieved a score of 0.822 (95% CI 0.752–0.891). Conclusions We demonstrated that pretherapeutic, multiparametric MRI radiomic features have potential in predicting non-response to neoadjuvant therapy in patients with LARC. Electronic supplementary material The online version of this article (10.1245/s10434-019-07300-3) contains supplementary material, which is available to authorized users.
In the present study, 90 patients with newly diagnosed acute promyelocytic leukemia (APL) were studied for all-trans retinoic acid (ATRA) and arsenic trioxide (As2O3) combination treatment in remission induction and postremission therapy. In addition, 20 APL patients who had achieved complete remission (CR) with an ATRA-based regimen received ATRA/As2O3 combination for consolidation and maintenance were also enrolled. The results showed that ATRA/As2O3 combination therapy yielded a high CR rate of 93.3% and a significantly shorter time to enter CR (median: 31 days; range: 18–59 days) compared to the ATRA-based regimen (n = 72; median: 39 days; range: 25–62 days). With the ATRA/As2O3 combination for CR maintaining, regardless of the way by which CR was attained, the relapse-free survival was significantly better than with an ATRA plus cytotoxic chemotherapy regimen (92.9 ± 3.2% vs. 72.4 ± 7.6%, for the 3-year Kaplan-Meier estimate of relapse-free survival). The drug toxicity profile showed that with the use of As2O3, the incidence of hepatotoxicity was obviously high during remission induction but decreased significantly during postremission treatment. We conclude that APL patients may benefit from the early use of the combination of ATRA and As2O3, in either remission induction or consolidation/maintenance.
BackgroundAlthough Caesarean scar pregnancy (CSP) is rare, it can cause life-threatening complications. The increasing rate of Cesarean delivery plus rapid development of in vitro fertilization-embryo transfer (IVF-ET) may increase the occurrence of CSP as well as the ratio of heterotopic CSP (HCSP)/CSP. Therefore, early diagnosis and management of CSP are necessary to avoid serious complications. And the purpose of this article is to evaluate the importance and feasibility of the first-trimester diagnosis and management of CSP after IVF-ET.MethodsAll the 12 cases were secondary infertility patients who had a history of Cesarean section and underwent IVF-ET in our reproductive center. All cases with CSP were diagnosed using transvaginal color Doppler sonography (TVS). Medical, surgical and expectant managements were implemented, and the management results were traced.ResultsPatients with CSP (n = 12) were diagnosed from January 2011 to April 2015, 6 (50 %) of which were HCSP. The prevalence of CSP was 1:1688 pregnancies. The gestational age ranged from 5 + 3 to 7 + 4 weeks in all CSP, and from 5 + 6 to 7 + 4 weeks in HCSP at diagnosis. Five patients received successful surgical treatment. The success rate of medical and expectant management was 50 % (1/2) and 100 % (5/5), respectively. One patient with failed medical management needed an emergency laparotomy to evacuate CSP. The uterus was preserved in all 12 patients.ConclusionsThe Caesarean section and IVF-ET may increase the ratio of HCSP/CSP. TVS is a noninvasive and effective tool for use in diagnosing CSP. CSP should be carefully excluded in patients who have had a history of Caesarean section. Early diagnosis of CSP in the first trimester may contribute towards the preservation of uterus as well as intrauterine pregnancy (IUP) in HCSP.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.