Multi-center validation of an artificial intelligence system for detection of COVID-19 on chest radiographs in symptomatic patients.

OBJECTIVES: While chest radiograph (CXR) is the first-line imaging investigation in patients with respiratory symptoms, differentiating COVID-19 from other respiratory infections on CXR remains challenging. We developed and validated an AI system for COVID-19 detection on presenting CXR. METHODS: A deep learning model (RadGenX), trained on 168,850 CXRs, was validated on a large international test set of presenting CXRs of symptomatic patients from 9 study sites (US, Italy, and Hong Kong SAR) and 2 public datasets from the US and Europe. Performance was measured by area under the receiver operator characteristic curve (AUC). Bootstrapped simulations were performed to assess performance across a range of potential COVID-19 disease prevalence values (3.33 to 33.3%). Comparison against international radiologists was performed on an independent test set of 852 cases. RESULTS: RadGenX achieved an AUC of 0.89 on 4-fold cross-validation and an AUC of 0.79 (95%CI 0.78-0.80) on an independent test cohort of 5,894 patients. Delong's test showed statistical differences in model performance across patients from different regions (p < 0.01), disease severity (p < 0.001), gender (p < 0.001), and age (p = 0.03). Prevalence simulations showed the negative predictive value increases from 86.1% at 33.3% prevalence, to greater than 98.5% at any prevalence below 4.5%. Compared with radiologists, McNemar's test showed the model has higher sensitivity (p < 0.001) but lower specificity (p < 0.001). CONCLUSION: An AI model that predicts COVID-19 infection on CXR in symptomatic patients was validated on a large international cohort providing valuable context on testing and performance expectations for AI systems that perform COVID-19 prediction on CXR. KEY POINTS: • An AI model developed using CXRs to detect COVID-19 was validated in a large multi-center cohort of 5,894 patients from 9 prospectively recruited sites and 2 public datasets. • Differences in AI model performance were seen across region, disease severity, gender, and age. • Prevalence simulations on the international test set demonstrate the model's NPV is greater than 98.5% at any prevalence below 4.5%.

PET/CT morphology and cardiac conduction disorders help discriminate primary cardiac lymphoma from primary cardiac sarcoma.

BACKGROUND: Primary cardiac lymphoma (PCL) and primary cardiac sarcoma (PCS) are similar in clinical presentation but differ in management and outcomes. We aim to explore the role of PET morphology and clinical characteristics in distinguishing PCL from PCS. METHODS: Pretreatment 18F-FDG PET/CT and contrast-enhanced CT were performed in PCL (n = 14) and PCS (n = 15) patients. Patient demographics, overall survival, and progression-free survival were reviewed. PET/CT morphological and metabolic features were extracted. Specifically, R_Kurtosis, a PET-morphology parameter reflecting the tumor expansion within the heart, was calculated. RESULTS: Compared with PCS, PCL occurred at an older age, resulted in more cardiac dysfunctions and arrhythmias, and showed higher glucometabolism (SUVmax, SUVpeak, SUVmean, MTV, and TLG). Curative treatments improved survival for PCL but not for PCS. Multivariable logistic regression identified R_Kurtosis (OR = 27.025, P = .007) and cardiac conduction disorders (OR = 37.732, P = .016) independently predictive of PCL, and classification and regression tree analysis stratified patients into three subgroups: R_Kurtosis ≥ 0.044 (probability of PCL 88.9%), R_Kurtosis < 0.044 with conduction disorders (80.0%), and R_Kurtosis < 0.044 without conduction disorders (13.3%). CONCLUSION: PET-derived tumor expansion pattern (R_Kurtosis) and cardiac conduction disorders were helpful in distinguishing PCL from PCS, which might assist the clinical management.

Association between High Diffusion-Weighted Imaging-Derived Functional Tumor Burden of Peritoneal Carcinomatosis and Overall Survival in Patients with Advanced Ovarian Carcinoma.

OBJECTIVE: To investigate the association between functional tumor burden of peritoneal carcinomatosis (PC) derived from diffusion-weighted imaging (DWI) and overall survival in patients with advanced ovarian carcinoma (OC). MATERIALS AND METHODS: This prospective study was approved by the local research ethics committee, and informed consent was obtained. Fifty patients (mean age ± standard deviation, 57 ± 12 years) with stage III-IV OC scheduled for primary or interval debulking surgery (IDS) were recruited between June 2016 and December 2021. DWI (b values: 0, 400, and 800 s/mm²) was acquired with a 16-channel phased-array torso coil. The functional PC burden on DWI was derived based on K-means clustering to discard fat, air, and normal tissue. A score similar to the surgical peritoneal cancer index was assigned to each abdominopelvic region, with additional scores assigned to the involvement of critical sites, denoted as the functional peritoneal cancer index (fPCI). The apparent diffusion coefficient (ADC) of the largest lesion was calculated. Patients were dichotomized by immediate surgical outcome into high- and low-risk groups (with and without residual disease, respectively) with subsequent survival analysis using the Kaplan-Meier curve and log-rank test. Multivariable Cox proportional hazards regression was used to evaluate the association between DWI-derived results and overall survival. RESULTS: Fifteen (30.0%) patients underwent primary debulking surgery, and 35 (70.0%) patients received neoadjuvant chemotherapy followed by IDS. Complete tumor debulking was achieved in 32 patients. Patients with residual disease after debulking surgery had reduced overall survival (p = 0.043). The fPCI/ADC was negatively associated with overall survival when accounted for clinicopathological information with a hazard ratio of 1.254 for high fPCI/ADC (95% confidence interval, 1.007-1.560; p = 0.043). CONCLUSION: A high DWI-derived functional tumor burden was associated with decreased overall survival in patients with advanced OC.

Machine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph.

Triaging and prioritising patients for RT-PCR test had been essential in the management of COVID-19 in resource-scarce countries. In this study, we applied machine learning (ML) to the task of detection of SARS-CoV-2 infection using basic laboratory markers. We performed the statistical analysis and trained an ML model on a retrospective cohort of 5148 patients from 24 hospitals in Hong Kong to classify COVID-19 and other aetiology of pneumonia. We validated the model on three temporal validation sets from different waves of infection in Hong Kong. For predicting SARS-CoV-2 infection, the ML model achieved high AUCs and specificity but low sensitivity in all three validation sets (AUC: 89.9-95.8%; Sensitivity: 55.5-77.8%; Specificity: 91.5-98.3%). When used in adjunction with radiologist interpretations of chest radiographs, the sensitivity was over 90% while keeping moderate specificity. Our study showed that machine learning model based on readily available laboratory markers could achieve high accuracy in predicting SARS-CoV-2 infection.

Computed tomography-based deep-learning prediction of neoadjuvant chemoradiotherapy treatment response in esophageal squamous cell carcinoma.

BACKGROUND: Deep learning is promising to predict treatment response. We aimed to evaluate and validate the predictive performance of the CT-based model using deep learning features for predicting pathologic complete response to neoadjuvant chemoradiotherapy (nCRT) in esophageal squamous cell carcinoma (ESCC). MATERIALS AND METHODS: Patients were retrospectively enrolled between April 2007 and December 2018 from two institutions. We extracted deep learning features of six pre-trained convolutional neural networks, respectively, from pretreatment CT images in the training cohort (n = 161). Support vector machine was adopted as the classifier. Validation was performed in an external testing cohort (n = 70). We assessed the performance using the area under the receiver operating characteristics curve (AUC) and selected an optimal model, which was compared with a radiomics model developed from the training cohort. A clinical model consisting of clinical factors only was also built for baseline comparison. We further conducted a radiogenomics analysis using gene expression profiles to reveal underlying biology associated with radiological prediction. RESULTS: The optimal model with features extracted from ResNet50 achieved an AUC and accuracy of 0.805 (95% CI, 0.696-0.913) and 77.1% (65.6%-86.3%) in the testing cohort, compared with 0.725 (0.605-0.846)) and 67.1% (54.9%-77.9%) for the radiomics model. All the radiological models showed better predictive performance than the clinical model. Radiogenomics analysis suggested a potential association mainly with WNT signaling pathway and tumor microenvironment. CONCLUSIONS: The novel and noninvasive deep learning approach could provide efficient and accurate prediction of treatment response to nCRT in ESCC, and benefit clinical decision making of therapeutic strategy.

Assessment of Intratumoral and Peritumoral Computed Tomography Radiomics for Predicting Pathological Complete Response to Neoadjuvant Chemoradiation in Patients With Esophageal Squamous Cell Carcinoma.

Importance: For patients with locally advanced esophageal squamous cell carcinoma, neoadjuvant chemoradiation has been shown to improve long-term outcomes, but the treatment response varies among patients. Accurate pretreatment prediction of response remains an urgent need. Objective: To determine whether peritumoral radiomics features derived from baseline computed tomography images could provide valuable information about neoadjuvant chemoradiation response and enhance the ability of intratumoral radiomics to estimate pathological complete response. Design, Setting, and Participants: A total of 231 patients with esophageal squamous cell carcinoma, who underwent baseline contrast-enhanced computed tomography and received neoadjuvant chemoradiation followed by surgery at 2 institutions in China, were consecutively included. This diagnostic study used single-institution data between April 2007 and December 2018 to extract radiomics features from intratumoral and peritumoral regions and established intratumoral, peritumoral, and combined radiomics models using different classifiers. External validation was conducted using independent data collected from another hospital during the same period. Radiogenomics analysis using gene expression profile was done in a subgroup of the training set for pathophysiological explanation. Data were analyzed from June to December 2019. Exposures: Computed tomography-based radiomics. Main Outcomes and Measures: The discriminative performances of radiomics models were measured by area under the receiver operating characteristic curve. Results: Among the 231 patients included (192 men [83.1%]; mean [SD] age, 59.8 [8.7] years), the optimal intratumoral and peritumoral radiomics models yielded similar areas under the receiver operating characteristic curve of 0.730 (95% CI, 0.609-0.850) and 0.734 (0.613-0.854), respectively. The combined model was composed of 7 intratumoral and 6 peritumoral features and achieved better discriminative performance, with an area under the receiver operating characteristic curve of 0.852 (95% CI, 0.753-0.951), accuracy of 84.3%, sensitivity of 90.3%, and specificity of 79.5% in the test set. Gene sets associated with the combined model mainly involved lymphocyte-mediated immunity. The association of peritumoral area with response identification might be partially attributed to type I interferon-related biological process. Conclusions and Relevance: A combination of peritumoral radiomics features appears to improve the predictive performance of intratumoral radiomics to estimate pathological complete response after neoadjuvant chemoradiation in patients with esophageal squamous cell carcinoma. This study underlines the significant application of peritumoral radiomics to assess treatment response in clinical practice.

Functional tumour burden of peritoneal carcinomatosis derived from DWI could predict incomplete tumour debulking in advanced ovarian carcinoma.

OBJECTIVES: To investigate the predictive value of peritoneal carcinomatosis (PC) quantification by DWI in determining incomplete tumour debulking in ovarian carcinoma (OC). METHODS: Prospective patients with suspected stage III-IV or recurrent OC were recruited for DWI before surgery. PC on DWI was segmented semi-automatically by k-means clustering, retaining voxels with intermediate apparent diffusion coefficient (ADC) to quantify PC burden. A scoring system, functional peritoneal cancer index (fPCI), was proposed based on the segmentation of tumour volume in 13 abdominopelvic regions with additional point given to involvement of critical sites. ADC of the largest PC was recorded. The surgical complexity and outcomes (complete vs. incomplete tumour debulking) were documented. fPCI was correlated with surgical PCI (sPCI), surgical complexity, and its ability to predict incomplete tumour debulking. RESULTS: Fifty-three patients with stage III-IV or recurrent OC were included with a mean age of 56.1 ± 11.8 years old. Complete tumour debulking was achieved in 38/53 patients (71.7%). Significant correlation was found between fPCI and sPCI (r > 0.757, p < 0.001). Patients with high-fPCI (fPCI ≥ 6) had a high surgical complexity score (p = 0.043) with 84.2% received radical or supra-radical surgery. The mean fPCI was significantly higher in patients with incomplete tumour debulking than in those with complete debulking (10.27 vs. 4.71, p < 0.001). fPCI/ADC combined with The International Federation of Gynecology and Obstetrics stage achieved 92.5% accuracy in predicting incomplete tumour debulking (AUC 0.947). CONCLUSIONS: DWI-derived fPCI offered a semi-automated estimation of PC burden. fPCI/ADC could predict the likelihood of incomplete tumour debulking with high accuracy. KEY POINTS: • Functional peritoneal cancer index (fPCI) derived from DWI offered a semi-automated estimation of tumour burden in ovarian carcinoma. • fPCI was highly correlated with surgical PCI (sPCI). • fPCI/ADC could predict the likelihood of incomplete tumour debulking with high accuracy.

Metabolic active peritoneal sites affect tumor debulking in ovarian and peritoneal cancers.

RATIONALE AND OBJECTIVES: To evaluate the impact of metabolic parameters in the peritoneal cavity on the likelihood of achieving complete tumor debulking in patients with ovarian and peritoneal cancers. MATERIALS AND METHODS: Forty-nine patients with ovarian and peritoneal cancers were included, who underwent pre-operative 18F-fluorodeoxyglucose Positron Emission Tomography/Computed Tomography (18F-FDG PET/CT). The immediate surgical outcome was dichotomized into complete and incomplete tumor debulking. 18F-FDG PET/CT was qualitatively and quantitatively assessed by scrutinizing 15 anatomical sites for the presence of peritoneal carcinomatosis (PC). Patient-based and site-based diagnostic characteristics were described. Metabolic parameters (SUVmax, metabolic tumor volume and total lesion glycolysis) and the number of 18F-FDG avid peritoneal sites were evaluated between the two groups. Receiver operating curve (ROC) analysis was performed to determine the optimal cut-off value in predicting incomplete tumor debulking. RESULTS: Twenty-seven out of the 49 patients had PC and 11 had incomplete debulking. Patient-based and site-based accuracies for detection of PC were 87.8 and 97.6%, respectively. The number of 18F-FDG avid peritoneal sites was significantly different between complete and incomplete debulking groups (0.6 ± 0.8 versus 2.3 ± 1.7 sites respectively, p = 0.001), and the only independent significant risk factor among other metabolic parameters tested (odd ratio = 2.983, 95% CI 1.104-8.062) for incomplete tumor debulking with an optimal cut-off value of ≥4 (AUC = 0.816). CONCLUSION: The number of 18F-FDG avid peritoneal sites increased the risk of incomplete tumor debulking after surgery and potentially useful in assisting treatment stratification in patients with ovarian and peritoneal cancers.

The Value of Contrast-Enhanced CT in the Detection of Residual Disease After Neo-Adjuvant Chemotherapy in Ovarian Cancer.

RATIONALE AND OBJECTIVES: To evaluate the diagnostic performance of contrast-enhanced computed tomography (CT) in predicting residual disease following neo-adjuvant chemotherapy (NACT) in stage III/IV ovarian cancer. MATERIALS AND METHODS: This was a retrospective observational cohort study including consecutive patients with primary stage III/IV ovarian cancer who received NACT before interval debulking surgery. CT findings before interval debulking surgerywere correlated with histological/surgical findings. Diagnostic characteristics were calculated on patient-based and lesion-based analyses. False negative results on peritoneal carcinomatosis detection were correlated with lesion size and site. RESULTS: On patient-based analysis, CT (n = 58) had a sensitivity, specificity, positive predictive value, negative predictive value and accuracy of 92.16%, 57.14%, 94.00%, 50.00%, and 87.93%. On lesion-based analysis, the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 63.01%, 73.47%, 82.51%, 50.00%, and 66.51%. False negative results were associated with lesion size (p < 0.001). The diagnostic performance of CT on the detection of peritoneal carcinomatosis was low at the subdiaphragmatic spaces, bowel serosa and mesentery (p < 0.001). CONCLUSION: CT had low negative predictive value in determining residual disease following NACT on both patient-based and lesion-based analyses, especially for non-measurable lesions and at the subdiaphragmatic spaces, bowel serosa and mesentery.

Combined Stereotactic Body Radiotherapy and Checkpoint Inhibition in Unresectable Hepatocellular Carcinoma: A Potential Synergistic Treatment Strategy.

Background: Current treatments of unresectable hepatocellular carcinoma (HCC) are trans-arterial chemo-embolization (TACE), stereotactic body radiotherapy (SBRT), and targeted therapy. However, these treatments are limited in efficacy and safety for patients with large tumor sizes. Here, we report a case series of combined SBRT and anti-PD-1 therapy in patients with unresectable HCC of large tumors. Methods: This is a retrospective case series of five patients with unresectable hepatocellular carcinoma who were treated with SBRT followed by anti-PD1 antibodies. Four patients (80%) received a single dose of TACE prior to SBRT. All patients had advanced HCC ineligible of curative intervention. In this study, we report their treatment responses according to modified RECIST (response evaluation criteria in solid tumor) criteria, 1-year local control (LC), progression-free survival (PFS), 1-year overall survival (OS) rate, and toxicities. Results: Among the five evaluated patients, three patients had underlying diseases of hepatitis B and four patients had Barcelona clinic liver cancer stage C. The median size of their tumors was 9.8 cm (range: 9-16.1 cm). In addition, two patients had tumor vascular thrombosis and one had extra-hepatic disease. Five out of five patients (100%) responded to treatment, with two complete responses (CR) and three partial responses (PR). Among the partial responders, one had a down-staged tumor that became amenable for radiofrequency ablation for tumor clearance. No patient developed tumor progression at the time of analysis during the median follow-up of 14.9 months (range 8.6-19 months). The median PFS was 14.9 months (range: 8.6-19 months); 1-year LC and OS rate were both 100%. One patient had grade ≥ 3 toxicities (pneumonitis and skin reaction). There was no classical radiation-induced liver disease. Conclusions: The results obtained from these 5 cases demonstrate impressive tumor control from the combination of SBRT and checkpoint inhibitors in patients with large tumors of advanced HCC. Further prospective trials are warranted.

Long-term outcomes and recurrence pattern of 18F-FDG PET-CT complete metabolic response in the first-line treatment of metastatic colorectal cancer: a lesion-based and patient-based analysis.

BACKGROUND: 18F-FDG PET-CT is commonly used to monitor treatment response in patients with metastatic colorectal cancer (mCRC). With improvement in systemic therapy, complete metabolic response (CMR) is increasingly encountered but its clinical significance is undefined. The study examined the long-term outcomes and recurrence patterns in these patients. METHODS: Consecutive patients with mCRC who achieved CMR on PET-CT during first-line systemic therapy were retrospectively analysed. Measurable and non-measurable lesions identified on baseline PET-CT were compared with Response Criteria in Solid Tumors (RECIST) on CT on a per-lesion basis. Progression free (PFS) and Overall Survival (OS) were compared with clinical parameters and treatment characteristics on a per-patient basis. RESULTS: Between 2008 and 2011, 40 patients with 192 serial PET-CT scans were eligible for analysis involving 44 measurable and 38 non-measurable lesions in 59 metastatic sites. On a per-lesion basis, 46% also achieved Complete Response (CR) on RECIST criteria and sustained CMR was more frequent in these lesions (OR 1.727, p = 0.0031). Progressive metabolic disease (PMD) was seen in 12% of lesions, with liver metastasis the most common. Receiver operating characteristics (ROC) curve analysis revealed the optimal value of SUVmax for predicting PMD of a lesion was 4.4 (AUC 0.734, p = 0.004). On a per-patient basis, 14 patients achieved sustained CMR and their outcomes were better than those with PMD (median OS not reached vs 37.7 months p = 0.0001). No statistical difference was seen in OS between patients who achieved PR or CR (median OS 51.4 vs 44.2 months p = 0.766). CONCLUSION: Our results provided additional information of long-term outcomes and recurrence patterns of patients with mCRC after achieving CMR. They had improved survival and sustained CMR using systemic therapy alone is possible. Discordance between morphological and metabolic response was consistent with reported literature but in the presence of CMR the two groups had comparable outcomes.

Association Patterns of Ontological Features Signify Electronic Health Records in Liver Cancer.

Electronic Health Record (EHR) system enables clinical decision support. In this study, a set of 112 abdominal computed tomography imaging examination reports, consisting of 59 cases of hepatocellular carcinoma (HCC) or liver metastases (so-called HCC group for simplicity) and 53 cases with no abnormality detected (NAD group), were collected from four hospitals in Hong Kong. We extracted terms related to liver cancer from the reports and mapped them to ontological features using Systematized Nomenclature of Medicine (SNOMED) Clinical Terms (CT). The primary predictor panel was formed by these ontological features. Association levels between every two features in the HCC and NAD groups were quantified using Pearson's correlation coefficient. The HCC group reveals a distinct association pattern that signifies liver cancer and provides clinical decision support for suspected cases, motivating the inclusion of new features to form the augmented predictor panel. Logistic regression analysis with stepwise forward procedure was applied to the primary and augmented predictor sets, respectively. The obtained model with the new features attained 84.7% sensitivity and 88.4% overall accuracy in distinguishing HCC from NAD cases, which were significantly improved when compared with that without the new features.

The percentage of serum thyroglobulin rise in the first-week did not predict the eventual success of high-intensity focussed ablation (HIFU) for benign thyroid nodules.

BACKGROUND: Given that high-intensity focussed ultrasound (HIFU) of benign thyroid nodules often causes a massive release of thyroglobulin (Tg) into the circulation, we hypothesised a greater initial Tg rise may result in a greater nodule shrinkage 6 months after ablation. METHODS: One hundred and five patients who underwent HIFU for symptomatic benign thyroid nodule from 2015 to 2016 were analysed. Serum Tg and anti-Tg autoantibody were checked on treatment day (baseline) and 4 d after treatment. The % of Tg rise = [serum Tg on day-4 - baseline serum Tg]/[baseline serum Tg] * 100 while the nodule shrinkage as measured by volume reduction ratio (VRR) = [baseline volume - volume at 6-month]/[baseline volume] * 100. Treatment success was defined as VRR >50%. RESULTS: At 6-month, the mean VRR was 62.2 ± 25.0% and 59 (76.6%) patients had treatment success. The mean baseline Tg level increased from 292.8 ± 672.7 ng/mL to 2022.7 ± 1759.8 ng/mL in the first-week. The % of Tg rise did not significantly correlate with either 3-month or 6-month VRR (p = 0.920 and p = 0.699, respectively). The mean % of Tg rise in the first week was not different between those with and without 6-month treatment success (368.2% vs. 1068.7%, p = 0.381). No clinical factors significantly correlated with treatment success. CONCLUSIONS: There was an almost seven-fold increase in the mean Tg level 4 d after HIFU ablation. The % of Tg rise in the first week did not appear to correlate with the 6-month nodule shrinkage or treatment success.

PET/CT in the evaluation of treatment response to neoadjuvant chemoradiotherapy and prognostication in patients with locally advanced esophageal squamous cell carcinoma.

OBJECTIVE: To investigate the role of fluorine-18-fluorodeoxyglucose PET/computed tomography for the prognostication and evaluation of neoadjuvant chemoradiotherapy response in locally advanced esophageal squamous cell carcinoma. METHODS: All consecutive biopsy-proven esophageal squamous cell carcinoma patients with PET/computed tomography at baseline (PET0) and 1 month after the completion of neoadjuvant chemoradiotherapy (PET1) between January 2008 and December 2013, followed by esophagectomy, were included. Maximum and mean standard uptake values (SUVmax and SUVmean), metabolic tumor volume, and total lesion glycolysis of all lesions at PET0 and PET1 were analyzed. Logistic and Cox regressions were used to identify factors predictive of pathological complete remission (pCR), overall survival, and recurrence-free survival. Cut-offs were identified using leave-one-out cross-validation adjusted receiver operator curve-based methods. A Kaplan-Meier model was adopted to compare survivals between groups using log-rank tests. RESULTS: Of a total of 52 patients (45 men, age 21-78 years), pCR was achieved in 21 (40.4%). SUVmax of primary tumor at PET1 was independently predictive of pCR [P=0.013, odds ratio=0.736, 95% confidence interval (CI): 0.578-0.937]; using a leave-one-out cross-validation-adjusted cut-off of 2.7, pCR could be predicted with a sensitivity of 71.0%, a specificity of 66.7%, a positive predictive value of 75.9%, and a negative predictive value of 60.9%. In the subset of 40 patients with standardized treatment included in survival analysis, total lesion glycolysis (P=0.002, hazard ratio: 1.029, 95% CI: 1.01-1.048) and SUVmax (P=0.003, hazard ratio: 1.167, 95% CI: 1.055-1.290) of nodal metastasis at PET0 were independently predictive of overall survival and recurrence-free survival, respectively. CONCLUSION: Baseline total lesion glycolysis and SUVmax of nodal metastases are significant independent predictors of survival, whereas post-treatment SUVmax of the primary tumor is predictive of pCR. However, the predictive value of the latter is modest, which may limit its clinical utility.