BackgroundNumerous studies have shown that older women with endometrial cancer have a higher risk of recurrence and cancer-related death. However, it remains unclear whether older age is a causal p...Show moreBackgroundNumerous studies have shown that older women with endometrial cancer have a higher risk of recurrence and cancer-related death. However, it remains unclear whether older age is a causal prognostic factor, or whether other risk factors become increasingly common with age. We aimed to address this question with a unique multimethod study design using state-of-the-art statistical and causal inference techniques on datasets of three large, randomised trials.MethodsIn this multimethod analysis, data from 1801 women participating in the randomised PORTEC-1, PORTEC-2, and PORTEC-3 trials were used for statistical analyses and causal inference. The cohort included 714 patients with intermediate-risk endometrial cancer, 427 patients with high-intermediate risk endometrial cancer, and 660 patients with high-risk endometrial cancer. Associations of age with clinicopathological and molecular features were analysed using non-parametric tests. Multivariable competing risk analyses were performed to determine the independent prognostic value of age. To analyse age as a causal prognostic variable, a deep learning causal inference model called AutoCI was used.FindingsMedian follow-up as estimated using the reversed Kaplan-Meier method was 12·3 years (95% CI 11·9–12·6) for PORTEC-1, 10·5 years (10·2–10·7) for PORTEC-2, and 6·1 years (5·9–6·3) for PORTEC-3. Both overall recurrence and endometrial cancer-specific death significantly increased with age. Moreover, older women had a higher frequency of deep myometrial invasion, serous tumour histology, and p53-abnormal tumours. Age was an independent risk factor for both overall recurrence (hazard ratio [HR] 1·02 per year, 95% CI 1·01–1·04; p=0·0012) and endometrial cancer-specific death (HR 1·03 per year, 1·01–1·05; p=0·0012) and was identified as a significant causal variable.InterpretationThis study showed that advanced age was associated with more aggressive tumour features in women with endometrial cancer, and was independently and causally related to worse oncological outcomes. Therefore, our findings suggest that older women with endometrial cancer should not be excluded from diagnostic assessments, molecular testing, and adjuvant therapy based on their age alone. Show less
Predicting distant recurrence of endometrial cancer (EC) is crucial for personalized adjuvant treatment. The current gold standard of combined pathological and molecular profiling is costly,... Show morePredicting distant recurrence of endometrial cancer (EC) is crucial for personalized adjuvant treatment. The current gold standard of combined pathological and molecular profiling is costly, hampering implementation. Here we developed HECTOR (histopathology-based endometrial cancer tailored outcome risk), a multimodal deep learning prognostic model using hematoxylin and eosin-stained, whole-slide images and tumor stage as input, on 2,072 patients from eight EC cohorts including the PORTEC-1/-2/-3 randomized trials. HECTOR demonstrated C-indices in internal (n = 353) and two external (n = 160 and n = 151) test sets of 0.789, 0.828 and 0.815, respectively, outperforming the current gold standard, and identified patients with markedly different outcomes (10-year distant recurrence-free probabilities of 97.0%, 77.7% and 58.1% for HECTOR low-, intermediate- and high-risk groups, respectively, by Kaplan–Meier analysis). HECTOR also predicted adjuvant chemotherapy benefit better than current methods. Morphological and genomic feature extraction identified correlates of HECTOR risk groups, some with therapeutic potential. HECTOR improves on the current gold standard and may help delivery of personalized treatment in EC. Show less
PURPOSEThe molecular classification of endometrial cancer (EC) has proven to have prognostic value and is predictive of response to adjuvant chemotherapy. Here, we investigate its predictive value... Show morePURPOSEThe molecular classification of endometrial cancer (EC) has proven to have prognostic value and is predictive of response to adjuvant chemotherapy. Here, we investigate its predictive value for response to external beam radiotherapy (EBRT) and vaginal brachytherapy (VBT) in early-stage endometrioid EC (EEC).METHODSData of the randomized PORTEC-1 trial (n = 714) comparing pelvic EBRT with no adjuvant therapy in early-stage intermediate-risk EC and the PORTEC-2 trial (n = 427) comparing VBT with EBRT in early-stage high-intermediate-risk EC were used. Locoregional (including vaginal and pelvic) recurrence-free survival was compared between treatment groups across the four molecular classes using Kaplan-Meier's methodology and log-rank tests.RESULTSA total of 880 molecularly classified ECs, 484 from PORTEC-1 and 396 from PORTEC-2, were included. The majority were FIGO-2009 stage I EEC (97.2%). The median follow-up was 11.3 years. No locoregional recurrences were observed in EC with a pathogenic mutation of DNA polymerase-ε (POLEmut EC). In mismatch repair–deficient (MMRd) EC, locoregional recurrence-free survival was similar after EBRT (94.2%), VBT (94.2%), and no adjuvant therapy (90.3%; P = .74). In EC with a p53 abnormality (p53abn EC), EBRT (96.9%) had a substantial benefit over VBT (64.3%) and no adjuvant therapy (72.2%; P = .048). In EC with no specific molecular profile (NSMP EC), both EBRT (98.3%) and VBT (96.2%) yielded better locoregional control than no adjuvant therapy (87.7%; P < .0001).CONCLUSIONThe molecular classification of EC predicts response to radiotherapy in stage I EEC and may guide adjuvant treatment decisions. Omitting radiotherapy seems to be safe in POLEmut EC. The benefit of radiotherapy seems to be limited in MMRd EC. EBRT yields a significantly better locoregional recurrence-free survival than VBT or no adjuvant therapy in p53abn EC. VBT is the treatment of choice for NSMP EC as it is as effective as EBRT and significantly better than no adjuvant therapy for locoregional tumor control. Show less
Background Endometrial cancer can be molecularly classified into POLEmut , mismatch repair deficient (MMRd), p53 abnormal (p53abn), and no specific molecular profile (NSMP) subgroups. We aimed to... Show moreBackground Endometrial cancer can be molecularly classified into POLEmut , mismatch repair deficient (MMRd), p53 abnormal (p53abn), and no specific molecular profile (NSMP) subgroups. We aimed to develop an interpretable deep learning pipeline for whole-slide-image-based prediction of the four molecular classes in endometrial cancer (im4MEC), to identify morpho-molecular correlates, and to refine prognostication. Methods This combined analysis included diagnostic haematoxylin and eosin-stained slides and molecular and clinicopathological data from 2028 patients with intermediate-to-high-risk endometrial cancer from the PORTEC-1 (n=466), PORTEC-2 (n=375), and PORTEC-3 (n=393) randomised trials and the TransPORTEC pilot study (n=110), the Medisch Spectrum Twente cohort (n=242), a case series of patients with POLEmut endometrial cancer in the Leiden Endometrial Cancer Repository (n=47), and The Cancer Genome Atlas-Uterine Corpus Endometrial Carcinoma cohort (n=395). PORTEC-3 was held out as an independent test set and a four-fold cross validation was performed. Performance was measured with the macro and class-wise area under the receiver operating characteristic curve (AUROC). Whole-slide images were segmented into tiles of 360 & mu;m resized to 224 x 224 pixels. im4MEC was trained to learn tile-level morphological features with self-supervised learning and to molecularly classify whole-slide images with an attention mechanism. The top 20 tiles with the highest attention scores were reviewed to identify morpho-molecular correlates. Predictions of a nuclear classification deep learning model serve to derive interpretable morphological features. We analysed 5-year recurrence-free survival and explored prognostic refinement by molecular class using the Kaplan-Meier method. Findings im4MEC attained macro-average AUROCs of 0 & BULL;874 (95% CI 0 & BULL;856-0 & BULL;893) on four-fold cross-validation and 0 & BULL;876 on the independent test set. The class-wise AUROCs were 0 & BULL;849 for POLEmut (n=51), 0 & BULL;844 for MMRd (n=134), 0 & BULL;883 for NSMP (n=120), and 0 & BULL;928 for p53abn (n=88). POLEmut and MMRd tiles had a high density of lymphocytes, p53abn tiles had strong nuclear atypia, and the morphology of POLEmut and MMRd endometrial cancer overlapped. im4MEC highlighted a low tumour-to-stroma ratio as a potentially novel characteristic feature of the NSMP class. 5-year recurrence-free survival was significantly different between im4MEC predicted molecular classes in PORTEC-3 (log-rank p<0 & BULL;0001). The ten patients with aggressive p53abn endometrial cancer that was predicted as MMRd showed inflammatory morphology and appeared to have a better prognosis than patients with correctly predicted p53abn endometrial cancer (p=0 & BULL;30). The four patients with NSMP endometrial cancer that was predicted as p53abn showed higher nuclear atypia and appeared to have a worse prognosis than patients with correctly predicted NSMP (p=0 & BULL;13). Patients with MMRd endometrial cancer predicted as POLEmut had an excellent prognosis, as do those with true POLEmut endometrial cancer. Interpretation We present the first interpretable deep learning model, im4MEC, for haematoxylin and eosin-based prediction of molecular endometrial cancer classification. im4MEC robustly identified morpho-molecular correlates and could enable further prognostic refinement of patients with endometrial cancer. Copyright & COPY; 2022 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Show less
Randomized controlled trials (RCTs) are considered the gold standard for testing causal hypotheses in the clinical domain; however, the investigation of prognostic variables of patient outcome in a... Show moreRandomized controlled trials (RCTs) are considered the gold standard for testing causal hypotheses in the clinical domain; however, the investigation of prognostic variables of patient outcome in a hypothesized cause-effect route is not feasible using standard statistical methods. Here we propose a new automated causal inference method (AutoCI) built on the invariant causal prediction (ICP) framework for the causal reinterpretation of clinical trial data. Compared with existing methods, we show that the proposed AutoCI allows one to clearly determine the causal variables of two real-world RCTs of patients with endometrial cancer with mature outcome and extensive clinicopathological and molecular data. This is achieved via suppressing the causal probability of non-causal variables by a wide margin. In ablation studies, we further demonstrate that the assignment of causal probabilities by AutoCI remains consistent in the presence of confounders. In conclusion, these results confirm the robustness and feasibility of AutoCI for future applications in real-world clinical analysis.The invariant causal prediction (ICP) framework tries to determine the causal variables given an outcome variable, but considerable effort is needed to adapt existing ICP methods to the clinical domain. The authors propose an automated causal inference method that could potentially address the challenges of applying the ICP framework to complex clinical datasets. Show less
Wortman, B.G.; Post, C.C.B.; Powell, M.E.; Khaw, P.; Fyles, A.; D'Amico, R.; ... ; Boer, S.M. de 2022
Purpose: Radiation therapy techniques have developed from 3-dimensional conformal radiation therapy (3DCRT) to intensity modulated radiation therapy (IMRT), with better sparing of the surrounding... Show morePurpose: Radiation therapy techniques have developed from 3-dimensional conformal radiation therapy (3DCRT) to intensity modulated radiation therapy (IMRT), with better sparing of the surrounding normal tissues. The current analysis aimed to investigate whether IMRT, compared to 3DCRT, resulted in fewer adverse events (AEs) and patient-reported symptoms in the randomized PORTEC-3 trial for high-risk endometrial cancer.Methods and materials: Data on AEs and patient-reported quality of life (QoL) of the PORTEC-3 trial were available for analysis. Physician-reported AEs were graded using Common Terminology Criteria for Adverse Events v3.0. QoL was assessed by the European Organisation for Research and Treatment of Cancer QLQC30, CX24, and OV28 questionnaires. Data were compared between 3DCRT and IMRT. A P value of = .01 was considered statistically significant due to the risk of multiple testing. For QoL, combined scores 1 to 2 ("not at all" and "a little") versus 3 to 4 ("quite a bit" and "very much") were compared between the techniques.Results: Of 658 evaluable patients, 559 received 3DCRT and 99 IMRT. Median follow-up was 74.6 months. During treatment no significant differences were observed, with a trend for more grade =3 AEs, mostly hematologic and gastrointestinal, after 3DCRT (37.7% vs 26.3%, P = .03). During follow-up, 15.4% (vs 4%) had grade >= 2 diarrhea, and 26.1% (vs 13.1%) had grade >= 2 hematologic AEs after 3DCRT (vs IMRT) (both P < .01). Among 574 (87%) patients evaluable for QoL, 494 received 3DCRT and 80 IMRT. During treatment, 37.5% (vs 28.6%) reported diarrhea after 3DCRT (vs IMRT) (P = .125); 22.1% (versus 10.0%) bowel urgency (P = 0039), and 18.2% and 8.6% abdominal cramps (P = .058). Other QoL scores showed no differences.Conclusions: IMRT resulted in fewer grade >= 3 AEs during treatment and significantly lower rates of grade >= 2 diarrhea and hematologic AEs during follow-up. Trends toward fewer patient-reported bowel urgency and abdominal cramps were observed after IMRT compared to 3DCRT. (C) 2021 The Authors. Published by Elsevier Inc. Show less
Objective: Microcystic, elongated fragmented (MELF) pattern of myometrial invasion is a distinct histologic feature occasionally seen in low-grade endometrial carcinomas (EC). The prognostic... Show moreObjective: Microcystic, elongated fragmented (MELF) pattern of myometrial invasion is a distinct histologic feature occasionally seen in low-grade endometrial carcinomas (EC). The prognostic relevance of MELF invasion was uncertain due to conflicting data, and it had not yet appropriately been studied in the context of the molecular EC classification. We aimed to determine the relation of MELF invasion with clinicopathological and molecular characteristics, and define its prognostic relevance in early-stage low/intermediate risk EC. Methods: Single whole tumor slides of 979 (85.8%) out of 1141 (high)intermediate-risk EC of women who participated in the PORTEC-1/−2 trials were available for review. Clinicopathological and molecular features were compared between MELF invasion positive and negative cases. Time-to-event analyses were done by Kaplan-Meier method, log-rank tests and Cox’ proportional hazards models. Results: MELF invasion was found in 128 (13.1%) cases, and associated with grade 1–2 histology, deep myometrial invasion and substantial lymph-vascular space invasion (LVSI). 85.6% of MELF invasion positive tumors were no-specific-molecular-profile (NSMP) EC. NSMP EC with MELF invasion were CTNNB1 wild type in 92.2% and KRAS mutated in 24.4% of cases. Risk of recurrence was lower for MELF invasion positive as compared to MELF invasion negative cases (4.9% vs. 12.7%, p = 0.026). However, MELF invasion had no independent impact on risk of recurrence (HR 0.65, p = 0.30) after correction for clinicopathological and molecular factors. Conclusions: MELF invasion has no independent impact on risk of recurrence in early-stage EC, and is frequently observed in low-grade NSMP tumors. Routine assessment of MELF invasion has no clinical implications and is not recommended. Show less
Purpose: The survival results of the PORTEC-3 trial showed a significant improvement in both overall and failure-free survival with chemoradiation therapy versus pelvic radiation therapy alone. The... Show morePurpose: The survival results of the PORTEC-3 trial showed a significant improvement in both overall and failure-free survival with chemoradiation therapy versus pelvic radiation therapy alone. The present analysis was performed to compare long-term adverse events (AE) and health-related quality of life (HRQOL).Methods and Materials: In the study, 660 women with high-risk endometrial cancer were randomly assigned to receive chemoradiation therapy (2 concurrent cycles of cisplatin followed by 4 cycles of carboplatin/paclitaxel) or radiation therapy alone. Toxicity was graded using Common Terminology Criteria for Adverse Events, version 3.0. HRQOL was measured using EORTC QLQ-C30 and CX24/OV28 subscales and compared with normative data. An as-treated analysis was performed.Results: Median follow-up was 74.6 months; 574 (87%) patients were evaluable for HRQOL. At 5 years, grade >= 2 AE were scored for 78 (38%) patients who had received chemoradiation therapy versus 46 (24%) who had received radiation therapy alone (P = .008). Grade 3 AE did not differ significantly between the groups (8% vs 5%, P = .18) at 5 years, and only one new late grade 4 toxicity had been reported. At 3 and 5 years, sensory neuropathy toxicity grade >= 2 persisted after chemoradiation therapy in 6% (vs 0% after radiation therapy, P < .001) and more patients reported significant tingling or numbness at HRQOL (27% vs 8%, P < .001 at 3 years; 24% vs 9%, P = .002 at 5 years). Up to 3 years, more patients who had chemoradiation therapy reported limb weakness (21% vs 5%, P < .001) and lower physical (79 vs 87, P < .001) and role functioning (78 vs 88, P < .001) scores. Both treatment groups reported similar long-term global health/quality of life scores, which were better than those of the normative population.Conclusions: This study shows a long-lasting, clinically relevant, negative impact of chemoradiation therapy on toxicity and HRQOL, most importantly persistent peripheral sensory neuropathy. Physical and role functioning impairments were seen until 3 years. These long-term data are essential for patient information and shared decision-making regarding adjuvant chemotherapy for high-risk endometrial cancer. (C) 2020 The Author(s). Published by Elsevier Inc. Show less
Wortman, B.G.; Astreinidou, E.; Laman, M.S.; Steen-Banasik, E.M. van der; Lutgens, L.C.H.W.; Westerveld, H.; ... ; PORTEC Study Grp 2021
Optimum risk stratification in early-stage endometrial cancer combines clinicopathologic factors and the molecular endometrial cancer classification defined by The Cancer Genome Atlas (TCGA). It is... Show moreOptimum risk stratification in early-stage endometrial cancer combines clinicopathologic factors and the molecular endometrial cancer classification defined by The Cancer Genome Atlas (TCGA). It is unclear whether analysis of intratumoral immune infiltrate improves this. We developed a machine-learning, image-based algorithm to quantify density of CD8(+) and CD103(+) immune cells in tumor epithelium and stroma in 695 stage I endometrioid endometrial cancers from the PORTEC-1 and -2 trials. The relationship between immune cell density and clinicopathologic/molecular factors was analyzed by hierarchical clustering and multiple regression. The prognostic value of immune infiltrate by cell type and location was analyzed by univariable and multivariable Cox regression, incorporating the molecular endometrial cancer classification. Tumor-infiltrating immune cell density varied substantially between cases, and more modestly by immune cell type and location. Clustering revealed three groups with high, intermediate, and low densities, with highly significant variation in the proportion of molecular endometrial cancer subgroups between them. Univariable analysis revealed intraepithelial CD8(+) cell density as the strongest predictor of endometrial cancer recurrence; multivariable analysis confirmed this was independent of pathologic factors and molecular subgroup. Exploratory analysis suggested this association was not uniform across molecular subgroups, but greatest in tumors with mutant p53 and absent in DNA mismatch repair-deficient cancers. Thus, this work identified that quantification of intraepithelial CD8thorn cells improved upon the prognostic utility of the molecular endometrial cancer classification in early-stage endometrial cancer. Show less
