Dataset Information

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

ABSTRACT:

Introduction

Predicting 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 methods

We 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.

Results

The 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).

Conclusion

Our 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.

SUBMITTER: Li B

PROVIDER: S-EPMC9619175 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Li Bao B Li Fengling F Liu Zhenyu Z Xu FangPing F Ye Guolin G Li Wei W Zhang Yimin Y Zhu Teng T Shao Lizhi L Chen Chi C Sun Caixia C Qiu Bensheng B Bu Hong H Wang Kun K Tian Jie J

Breast (Edinburgh, Scotland) 20221019

<h4>Introduction</h4>Predicting 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.<h4>Materials and methods</h4>We retrospectively collected dat ...[more]

PMID: 36308926

Similar Datasets

Project description:ObjectiveEarly predicting response before neoadjuvant chemotherapy (NAC) is crucial for personalized treatment plans for locally advanced breast cancer patients. We aim to develop a multi-task model using multiscale whole slide images (WSIs) features to predict the response to breast cancer NAC more finely.MethodsThis work collected 1,670 whole slide images for training and validation sets, internal testing sets, external testing sets, and prospective testing sets of the weakly-supervised deep learning-based multi-task model (DLMM) in predicting treatment response and pCR to NAC. Our approach models two-by-two feature interactions across scales by employing concatenate fusion of single-scale feature representations, and controls the expressiveness of each representation via a gating-based attention mechanism.ResultsIn the retrospective analysis, DLMM exhibited excellent predictive performance for the prediction of treatment response, with area under the receiver operating characteristic curves (AUCs) of 0.869 [95% confidence interval (95% CI): 0.806-0.933] in the internal testing set and 0.841 (95% CI: 0.814-0.867) in the external testing sets. For the pCR prediction task, DLMM reached AUCs of 0.865 (95% CI: 0.763-0.964) in the internal testing and 0.821 (95% CI: 0.763-0.878) in the pooled external testing set. In the prospective testing study, DLMM also demonstrated favorable predictive performance, with AUCs of 0.829 (95% CI: 0.754-0.903) and 0.821 (95% CI: 0.692-0.949) in treatment response and pCR prediction, respectively. DLMM significantly outperformed the baseline models in all testing sets (P<0.05). Heatmaps were employed to interpret the decision-making basis of the model. Furthermore, it was discovered that high DLMM scores were associated with immune-related pathways and cells in the microenvironment during biological basis exploration.ConclusionsThe DLMM represents a valuable tool that aids clinicians in selecting personalized treatment strategies for breast cancer patients.

Project description:Breast cancer is one of the most prevalent cancers worldwide and pathologists are closely involved in establishing a diagnosis. Tools to assist in making a diagnosis are required to manage the increasing workload. In this context, artificial intelligence (AI) and deep-learning based tools may be used in daily pathology practice. However, it is challenging to develop fast and reliable algorithms that can be trusted by practitioners, whatever the medical center. We describe a patch-based algorithm that incorporates a convolutional neural network to detect and locate invasive carcinoma on breast whole-slide images. The network was trained on a dataset extracted from a reference acquisition center. We then performed a calibration step based on transfer learning to maintain the performance when translating on a new target acquisition center by using a limited amount of additional training data. Performance was evaluated using classical binary measures (accuracy, recall, precision) for both centers (referred to as “test reference dataset” and “test target dataset”) and at two levels: patch and slide level. At patch level, accuracy, recall, and precision of the model on the reference and target test sets were 92.1% and 96.3%, 95% and 87.8%, and 73.9% and 70.6%, respectively. At slide level, accuracy, recall, and precision were 97.6% and 92.0%, 90.9% and 100%, and 100% and 70.8% for test sets 1 and 2, respectively. The high performance of the algorithm at both centers shows that the calibration process is efficient. This is performed using limited training data from the new target acquisition center and requires that the model is trained beforehand on a large database from a reference center. This methodology allows the implementation of AI diagnostic tools to help in routine pathology practice. Author summary Recent developments in digital slide scanner technologies and the need for optimizing histopathologists workflow have led to the rise of digital pathology. Along with digital pathology, artificial intelligence assisted diagnoses are foreseen as the way to further enhance pathologists’ productivity and therefore support them with their ever-growing workload. Although imaging technologies can be digitalized, most of the slide preparation is still a manual process which lacks any sort of standardization. For this reason, digital images appearance is dependent on the center where the slide is prepared and artificial intelligence algorithms will perform poorly on slides from previously unseen medical centers. In this work, we introduce a method, based on transfer learning, for adapting artificial intelligence algorithms to new medical centers. We show that the method allows for algorithm performance preservation with reduced need for training data.

Project description:BackgroundInflammation plays an important role in tumor proliferation, metastasis, and resistance to chemotherapy. The systemic inflammation response index (SIRI), has been reported to be closely related to prognosis in many tumors, such as breast and gastric cancers. However, the predictive value of pretreatment SIRI on pathological complete response (pCR) rates in patients with breast cancer treated with neoadjuvant chemotherapy (NAC) is unknown. This study examined the correlation between SIRI and pCR in patients with breast cancer receiving NAC and identified convenient and accurate predictive indicators for pCR.MethodsWe retrospectively analyzed the clinicopathological parameters and pretreatment peripheral blood characteristics of the 241 patients with breast cancer who received NAC between June 2015 and June 2020. Receiver operating characteristic (ROC) curves were used to determine the optimal cutoff of SIRI. ROC curves were also plotted to verify the accuracy of inflammatory markers for pCR prediction. The chi-squared test was used to explore the relationships of SIRI with pCR and other clinicopathological parameters. Multivariate analyses were performed using a logistic regression model.ResultsAmong the 241 patients, 48 (19.92%) achieved pCR. pCR was significantly related to SIRI, the neutrophil-lymphocyte ratio (NLR), the lymphocyte-monocyte ratio (LMR), molecular subtypes and other clinicopathological parameters, such as BMI, clinical T and N staging, and histological grade. Multivariate analyses indicated that the clinical T and N staging, SIRI, and NLR were independent prognostic factors for pCR in patients with breast cancer. The area under the ROC curve for SIRI was larger than that for NLR. Compared to patients with SIRI ≥0.72, patients with SIRI < 0.72 had a nearly 5-fold higher chance of obtaining pCR (odds ratio = 4.999, 95% confidence interval = 1.510-16.551, p = 0.000).ConclusionsPretreatment SIRI is predictive of pCR in patients with breast cancer receiving NAC, and the index can assist physicians in formulating personalized treatment strategies.

Project description:BackgroundNeoadjuvant chemotherapy (NACT) is a standard approach of the multidisciplinary treatment of breast cancer. Depending on the biological subtype a pathological complete response in the breast (bpCR) can be achieved in up to 60% of the patients. However, only limited accuracy can be reached when using imaging for prediction of bpCR prior to surgery. Due to this diagnostic uncertainty, surgery after NACT is considered to be obligatory for all patients in order to either completely remove residual disease or to diagnose a bpCR histologically. The purpose of this trial is to evaluate the accuracy of a vacuum-assisted biopsy (VAB) to diagnose a bpCR after NACT prior to surgery.MethodsThis study is a multicenter, confirmative, one-armed, intra-individually-controlled, open, diagnostic trial. The study will take place at 21 trial sites in Germany. Six hundred female patients with breast cancer after completed NACT showing at least a partial response to NACT treatment will be enrolled. A vacuum-assisted biopsy (VAB) guided either by ultrasound or mammography will be performed followed by histopathological evaluation of the VAB specimen before standard, guideline-adherent breast surgery. The study is designed to prove that the false negative rate of the VAB is below 10%.DiscussionAs a bpCR is becoming a more frequent result after NACT, the question arises whether breast surgery is therapeutically necessary in such cases. To study this subject further, it will be crucial to develop a reliable test to diagnose a bpCR without surgery. During the study we anticipate possible problems in patient recruitment as the VAB intervention does not provide participating patients with any personal benefit. Hence, a proficient informed consent discussion with the patient and a detailed explanation of the study aim will be crucial for patient recruitment. Another critical issue is the histopathological VAB evaluation of a non-tumorous specimen as this may have been taken either from the former tumor region (bpCR) or outside of the (former) tumor region (non-representative VAB, sampling error).Trial registrationThe trial has been registered at clinicaltrials.gov with the identifier NCT02948764 on October 28, 2016 and at the German Clinical Trials Register ( DRKS00011761 ) on February 20, 2017. The date of enrolment of the first participant to the trial was on March 8, 2017.

Project description:PurposeSentinel lymph node biopsy (SLNB) alone following neoadjuvant chemotherapy (NAC) remains controversial in patients with breast cancer who are initially lymph node-positive. The present study aimed to evaluate the impact of SLNB and axillary lymph node dissection (ALND) on breast cancer recurrence and survival in patients who converted from lymph node-positive to pathological node-negative (ypN0) after NAC.MethodsThis single-center retrospective study included 223 patients who converted to axillary lymph node-negative status after NAC and underwent breast and axillary surgery between January 2006 and December 2015. This study compared the overall survival (OS), disease-free survival (DFS), ipsilateral axillary lymph node recurrence rates and incidence of postoperative complications, especially, arm lymphedema and shoulder stiffness between SLNB and ALND.ResultsThis study included 223 patients with axillary pathological complete response (pCR) after NAC and surgery. The SLNB and ALND groups included 94 and 129 patients, respectively. The median follow-up time was 57 (range, 6-155) in the SLNB group and 99 (range 2-159) months in the ALND group. The corresponding 5-year OS and DFS rates were 96.3% and 94.2% (p = 0.392), and 89.2% and 86.4% (p = 0.671), respectively. Four patients (4.3%) in the SLNB group and nine (7.0%) in the ALND group developed locoregional recurrences. Ipsilateral axillary lymph node recurrence and distant metastasis were observed in one (1.1%) and three (2.3%) patients, and in 10 (10.6%) and 11 (8.5%) patients, respectively. Patients in the ALND group were more likely than their SLNB counterparts to experience complications, such as shoulder stiffness (9 [7.0%] vs. 4 [4.3%] patients, p = 0.57). The rate of lymphedema in the ALND group was three times that in the SLNB group (35 [27.1%] vs. 8 [8.5%] patients, p < 0.001).ConclusionAs an alternative to ALND, SLNB has oncological safety in patients with axillary pathological complete response after NAC.

Dataset Information

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

Introduction

Materials and methods

Results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets