Early prediction of treatment response to neoadjuvant chemotherapy based on longitudinal ultrasound images of HER2-positive breast cancer patients by Siamese multi-task network: A multicentre, retrospective cohort study

The Potential Role of C4 MYH11+ Fibroblasts and the MDK-SDC2 Ligand-Receptor Pair in Lung Adenocarcinoma: Implications for Prognosis and Therapeutic Strategies

BACKGROUND

Lung adenocarcinoma (LUAD) posed a significant threat to global human health. This study employed single-cell RNA sequencing (scRNA-seq) to analyze transcriptomic data from nine LUAD patients at different stages of tumor infiltration, aiming to elucidate the tumor microenvironment and key biological processes of LUAD.

METHODS

In this study, we processed the scRNA-seq data using the Seurat package and sequentially applied principal component analysis followed by the Harmony package to effectively correct for batch effects, identifying 105,725 high-quality cells. Through cell clustering and gene expression profiling, we identified critical cell subpopulations and gene expression patterns in LUAD patients.

RESULTS

Our analysis revealed that the C4 MYH11+ Fibroblasts subtype was primarily involved in biological processes related to muscle function. Further investigations uncovered the MDK-SDC2 ligand-receptor pair as a critical regulator of tumor cell invasion, proliferation, and migration, driving LUAD progression. Additionally, we developed a gene-based prognostic model that effectively predicted patient survival, providing valuable clinical insights.

CONCLUSION

This study provided a comprehensive atlas of the LUAD tumor microenvironment, highlighted the role of the C4 MYH11+ Fibroblasts in tumor progression. It also proposed the MDK-SDC2 ligand-receptor pair as a novel mechanism, addressing a significant gap in this area of research. And presented a gene-based prognostic model as a novel perspective for research into immunotherapy and drug sensitivity in LUAD.

Validation of Quantitative Ultrasound and Texture Derivative Analyses-Based Model for Upfront Prediction of Neoadjuvant Chemotherapy Response in Breast Cancer

This work was conducted in order to validate a pre-treatment quantitative ultrasound (QUS) and texture derivative analyses-based prediction model proposed in our previous study to identify responders and non-responders to neoadjuvant chemotherapy in patients with breast cancer. The validation cohort consisted of 56 breast cancer patients diagnosed between the years 2018 and 2021. Among all patients, 53 were treated with neoadjuvant chemotherapy and three had unplanned changes in their chemotherapy cycles. Radio Frequency (RF) data were collected volumetrically prior to the start of chemotherapy. In addition to tumour region (core), a 5 mm tumour-margin was also chosen for parameters estimation. The prediction model, which was developed previously based on quantitative ultrasound, texture derivative, and tumour molecular subtypes, was used to identify responders and non-responders. The actual response, which was determined by clinical and pathological assessment after lumpectomy or mastectomy, was then compared to the predicted response. The sensitivity, specificity, positive predictive value, negative predictive value, and F1 score for determining chemotherapy response of all patients in the validation cohort were 94%, 67%, 96%, 57%, and 95%, respectively. Removing patients who had unplanned changes in their chemotherapy resulted in a sensitivity, specificity, positive predictive value, negative predictive value, and F1 score of all patients in the validation cohort of 94%, 100%, 100%, 50%, and 97%, respectively. Explanations for the misclassified cases included unplanned modifications made to the type of chemotherapy during treatment, inherent limitations of the predictive model, presence of DCIS in tumour structure, and an ill-defined tumour border in a minority of cases. Validation of a model was conducted in an independent cohort of patient for the first time to predict the tumour response to neoadjuvant chemotherapy using quantitative ultrasound, texture derivate, and molecular features in patients with breast cancer. Further research is needed to improve the positive predictive value and evaluate whether the treatment outcome can be improved in predicted non-responders by switching to other treatment options.

Predicting Pathological Characteristics of HER2-Positive Breast Cancer from Ultrasound Images: a Deep Ensemble Approach

The objective is to evaluate the feasibility of utilizing ultrasound images in identifying critical prognostic biomarkers for HER2-positive breast cancer (HER2 + BC). This study enrolled 512 female patients diagnosed with HER2-positive breast cancer through pathological validation at our institution from January 2016 to December 2021. Five distinct deep convolutional neural networks (DCNNs) and a deep ensemble (DE) approach were trained to classify axillary lymph node involvement (ALNM), lymphovascular invasion (LVI), and histological grade (HG). The efficacy of the models was evaluated based on accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), receiver operating characteristic (ROC) curves, areas under the ROC curve (AUCs), and heat maps. DeLong test was applied to compare differences in AUC among different models. The deep ensemble approach, as the most effective model, demonstrated AUCs and accuracy of 0.869 (95% CI: 0.802-0.936) and 69.7% in LVI, 0.973 (95% CI: 0.949-0.998) and 73.8% in HG, thus providing superior classification performance in the context of imbalanced data (p < 0.05 by the DeLong test). On ALNM, AUC and accuracy were 0.780 (95% CI: 0.688-0.873) and 77.5%, which were comparable to other single models. The pretreatment US-based DE model could hold promise as a clinical guidance for predicting pathological characteristics of patients with HER2-positive breast cancer, thereby providing benefit of facilitating timely adjustments in treatment strategies.

Radiomics of Multimodal Ultrasound for Early Prediction of Pathologic Complete Response to Neoadjuvant Chemotherapy in Breast Cancer

RATIONALE AND OBJECTIVES

To construct and validate a clinical-radiomics model based on radiomics features extracted from two-stage multimodal ultrasound and clinicopathologic information for early predicting pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer patients treated with NAC.

MATERIALS AND METHODS

Consecutive women with biopsy-proven breast cancer undergoing multimodal US pretreatment and after two cycles of NAC and followed by surgery between January 2014 and November 2023 were retrospectively collected for clinical-radiomics model construction (n = 274) and retrospective test (n = 134). The predictive performance of it was further tested in a subsequent prospective internal test set recruited between January 2024 to July 2024 (n = 76). Finally, a total of 484 patients were enrolled. The clinical-radiomics model predictive performance was compared with radiomics model, clinical model and radiologists' visual assessment by area under the receiver operating characteristic curve (AUC) analysis and DeLong test.

RESULTS

The proposed clinical-radiomics model obtained the AUC values of 0.92 (95%CI: 0.88, 0.94) and 0.85 (95%CI: 0.79, 0.89) in retrospective and prospective test sets, respectively, which were significantly higher than that those of the radiomics model (AUCs: 0.75-0.85), clinical model (AUCs: 0.68-0.72) and radiologists' visual assessments (AUCs:0.59-0.68) (all p < 0.05). In addition, the predictive efficacy of the radiologists was improved under the assistance of the clinical-radiomics model significantly.

CONCLUSION

The clinical-radiomics model developed in this study, which integrated clinicopathologic information and two-stage multimodal ultrasound features, was able to early predict pCR to NAC in breast cancer patients with favorable predictive effectiveness.

Multimodal deep-learning model using pre-treatment endoscopic images and clinical information to predict efficacy of neoadjuvant chemotherapy in esophageal squamous cell carcinoma

BACKGROUND

Neoadjuvant chemotherapy is standard for advanced esophageal squamous cell carcinoma, though often ineffective. Therefore, predicting the response to chemotherapy before treatment is desirable. However, there is currently no established method for predicting response to neoadjuvant chemotherapy. This study aims to build a deep-learning model to predict the response of esophageal squamous cell carcinoma to preoperative chemotherapy by utilizing multimodal data integrating esophageal endoscopic images and clinical information.

METHODS

170 patients with locally advanced esophageal squamous cell carcinoma were retrospectively studied, and endoscopic images and clinical information before neoadjuvant chemotherapy were collected. Endoscopic images alone and endoscopic images plus clinical information were each analyzed with a deep-learning model based on ResNet50. The clinical information alone was analyzed using logistic regression machine learning models, and the area under a receiver operating characteristic curve was calculated to compare the accuracy of each model. Gradient-weighted Class Activation Mapping was used on the endoscopic images to analyze the trend of the regions of interest in this model.

RESULTS

The area under the curve by clinical information alone, endoscopy alone, and both combined were 0.64, 0.55, and 0.77, respectively. The endoscopic image plus clinical information group was statistically more significant than the other models. This model focused more on the tumor when trained with clinical information.

CONCLUSIONS

The deep-learning model developed suggests that gastrointestinal endoscopic imaging, in combination with other clinical information, has the potential to predict the efficacy of neoadjuvant chemotherapy in locally advanced esophageal squamous cell carcinoma before treatment.

Study of absorbable dural sealant to improve complications after craniocerebral surgery and its application strategy and standardized operation procedure

Background

Infection after craniocerebral operation has always been a very focused problem, and dural closure can reduce perioperative infection by reducing drainage volume and subcutaneous effusion, so how to effectively perform dural closure seems to be a small but not negligible problem.

Methods

We proposed a classification and grading system for dural incisions based on the type and degree of suture, and based on the system, a standardized operation process for ADS (absorbable dural sealant) was developed. Then, we conducted a retrospective study. We divided the included patients into 3 groups. Normalized group follows the ADS standard use process proposed by us, while Empirical group does not meet or only partially meets the ADS standard use process, or uses ADS based on its own experience, and Non-sealant group were patients who did not use ADS. And perioperative infection was used as the primary assessment metric to verify the effectiveness of ADS in blocking the dural membrane, and to try to propose a standardized use plan.

Results

A retrospective collection of 383 patients' clinical data was conducted between October 2019 and April 2023 in the Department of Neurosurgery of Qilu Hospital of Shandong University. Of them, 128 belonged to the non-sealant group, 126 to the normalized group, and 129 to the empirical group. In our study, we discovered that, in comparison to the normalized group, postoperative cerebral infection rose by 17.2 % (OR = 2.437, P = 0.004) and 21.9 % (OR = 3.227, P < 0.001), respectively, in the empirical group and non-sealant group. In comparison to the normalized group, the empirical group and non-sealant group experienced a 13.2 % (OR = 1.882, P = 0.037) and 24.8 % (OR = 3.346, P < 0.001) increase in subcutaneous effusion development, respectively. Furthermore, when compared to the normalized group, the empirical group's (β = 48.556, P = 0.003) and non-sealant group's (β = 91.960, P < 0.001) subcutaneous or epidural drainage volume was significantly higher.

Conclusions

Correct and standardized use of ADS can improve the watertight suturing of the dura mater and reduce the incidence of postoperative complications such as infection, and is of great significance for perioperative management of neurosurgery.

A diagnostic test of two-dimensional ultrasonic feature extraction based on artificial intelligence combined with blood flow Adler classification and contrast-enhanced ultrasound for predicting HER-2-positive breast cancer

Background

Human epidermal growth factor receptor 2 (HER-2) was an important driver gene for breast cancer which had high degree of malignancy and poor prognosis. Ultrasonography was an important imaging method for the diagnosis of breast cancer, but its diagnostic efficacy of HER-2-positive breast cancer was not satisfactory. To assess the predictive value of two-dimensional ultrasonic feature extraction based on artificial intelligence (AI) combined with blood flow Adler classification and contrast-enhanced ultrasound (CEUS) for HER-2-positive breast cancer, we compared the value of the area under the receiver operating characteristic (ROC) curve (AUC) of the combined diagnosis model and single-factor models.

Methods

A retrospective analysis was performed on 140 patients (88 HER-2-positive and 52 HER-2-negative). These patients were divided into internal test samples and external validation samples in a ratio of 7:3 randomly. The two samples were divided into HER-2-positive group and HER-2-negative group. All the patients were examined by two-dimensional ultrasound, color Doppler ultrasound, and CEUS, and AI was used to extract two-dimensional ultrasonic image features. Features of two-dimensional ultrasound included not parallel to the skin, irregular shape, unclear boundary, posterior echo attenuated, solid or cystic-solid mixed, microcalcification or coarse calcification were treated as HER-2-positive. Levels of Doppler ultrasound included level 3 and level 4 were treated as HER-2-positive. Features of CEUS included high enhancement, fast forward, centrifugal or diffuse, uneven, lesion range increased after CEUS, with perforating branches, unclear nodule boundary after CEUS were treated as HER-2-positive. The ultrasonography characteristics in different ultrasonography methods were analyzed, the parameters with statistically significant differences between groups of internal test samples were incorporated to establish a joint diagnosis model. The sensitivity, specificity and accuracy of the combined diagnosis model and single-factor models were calculated, the ROC curve was drawn to evaluate the diagnostic efficacy of the combined diagnosis model.

Results

Long diameter direction, Adler grade of blood flow, contrast agent distribution characteristics, and nodule boundary after CEUS were statistically significant different between the positive and negative groups in internal test and external validation samples (P<0.05). The sensitivity, specificity, accuracy of the combined diagnosis model were significantly higher than single-parameter diagnosis method both in internal test and external validation samples, and the kappa values of combined diagnosis model were highest. The AUC of the combined diagnosis model of internal test and external validation samples was 0.861 and 0.969, which was significantly higher (P<0.05) than that in the long diameter direction (0.717 and 0.732), blood flow Adler grade (0.674 and 0.786), CEUS distribution characteristics (0.666 and 0.750), and the nodule boundary after CEUS (0.684 and 0.786).

Conclusions

The combined diagnosis model based on two-dimensional ultrasonic feature extraction, blood flow, and CEUS can effectively predict the expression of HER-2 in breast cancer.

Nomogram based on dual-energy computed tomography to predict the response to induction chemotherapy in patients with nasopharyngeal carcinoma: a two-center study

BACKGROUND

Previous studies utilizing dual-energy CT (DECT) for evaluating treatment efficacy in nasopharyngeal cancinoma (NPC) are limited. This study aimed to investigate whether the parameters from DECT can predict the response to induction chemotherapy in NPC patients in two centers.

METHODS

This two-center retrospective study included patients diagnosed with NPC who underwent contrast-enhanced DECT between March 2019 and November 2023. The clinical and DECT-derived parameters of tumor lesions were calculated to predict the response. We employed univariate and multivariate analysis to identify significant factors. Subsequently, the clinical, DECT, and clinical-DECT nomogram models were developed using independent predictors in the training cohort and validated in the test cohort. Receiver operating characteristic analysis was performed to evaluate the models' performance.

RESULTS

A total of 321 patients were included in the study, predominantly male [247 (76.9%)] with an average age of 52.04 ± 10.87 years. The training cohort (Center 1) comprised 252 patients, while the test cohort (Center 2) comprised 69 patients. Of these, 233 out of 321 patients (72.6%) were responders to induction chemotherapy. The clinical-DECT nomogram showed an AUC of 0.805 (95% CI, 0.688-0.906), outperforming both the DECT model (Extracellular volume fraction [ECVf]) (AUC, 0.706 [95% CI, 0.571-0.825]) and the clinical model (Ki67) (AUC, 0.693 [95% CI, 0.580-0.806]) in the test cohort.

CONCLUSIONS

Ki67 and ECVf emerged as independent predictive factors for response to induction chemotherapy in NPC patients. The proposed nomogram, incorporating ECVf, demonstrated accurate prediction of treatment response.

Deep learning-based multi-task prediction of response to neoadjuvant chemotherapy using multiscale whole slide images in breast cancer: A multicenter study

Objective

Early 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.

Methods

This 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.

Results

In 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.

Conclusions

The DLMM represents a valuable tool that aids clinicians in selecting personalized treatment strategies for breast cancer patients.

Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions

Breast cancer has reached the highest incidence rate worldwide among all malignancies since 2020. Breast imaging plays a significant role in early diagnosis and intervention to improve the outcome of breast cancer patients. In the past decade, deep learning has shown remarkable progress in breast cancer imaging analysis, holding great promise in interpreting the rich information and complex context of breast imaging modalities. Considering the rapid improvement in deep learning technology and the increasing severity of breast cancer, it is critical to summarize past progress and identify future challenges to be addressed. This paper provides an extensive review of deep learning-based breast cancer imaging research, covering studies on mammograms, ultrasound, magnetic resonance imaging, and digital pathology images over the past decade. The major deep learning methods and applications on imaging-based screening, diagnosis, treatment response prediction, and prognosis are elaborated and discussed. Drawn from the findings of this survey, we present a comprehensive discussion of the challenges and potential avenues for future research in deep learning-based breast cancer imaging.

Dynamic ultrasound-based modeling predictive of response to neoadjuvant chemotherapy in patients with early breast cancer

Early prediction of patient responses to neoadjuvant chemotherapy (NACT) is essential for the precision treatment of early breast cancer (EBC). Therefore, this study aims to noninvasively and early predict pathological complete response (pCR). We used dynamic ultrasound (US) imaging changes acquired during NACT, along with clinicopathological features, to create a nomogram and construct a machine learning model. This retrospective study included 304 EBC patients recruited from multiple centers. All enrollees had completed NACT regimens, and underwent US examinations at baseline and at each NACT cycle. We subsequently determined that percentage reduction of tumor maximum diameter from baseline to third cycle of NACT serves to independent predictor for pCR, enabling creation of a nomogram ([Formula: see text]). Our predictive accuracy further improved ([Formula: see text]) by combining dynamic US data and clinicopathological features in a machine learning model. Such models may offer a means of accurately predicting NACT responses in this setting, helping to individualize patient therapy. Our study may provide additional insights into the US-based response prediction by focusing on the dynamic changes of the tumor in the early and full NACT cycle.

Integration of Longitudinal and Transverse Radiomics from Ultrasound Images with Clinical Factors for HER-2 Status Prediction in Invasive Breast Cancer Patients

OBJECTIVE

This study developed a nomogram combining longitudinal and transverse ultrasound radiomics with clinical factors to identify human epidermal growth factor receptor 2 (HER2) status in invasive breast cancer (BC).

MATERIALS AND METHODS

We analyzed 537 invasive BC patients from two hospitals: 436 in the training cohort (Hospital A) and 101 in the test cohort (Hospital B). From longitudinal and transverse ultrasound planes, 788 radiomics features were extracted, with dimensionality reduced using least absolute shrinkage and selection operator regression. A radiomics nomogram integrating clinical predictors and radiomics scores (Rad-scores) was constructed.

RESULTS

Fifteen and sixteen features from longitudinal and transverse ultrasound planes, respectively, were selected to generate Rad-scores, which differed significantly between HER2-positive and HER2-negative groups in both cohorts (p < 0.05). The combined radiomics model outperformed individual models with AUCs of 0.783 and 0.762 in the training and external test cohorts, respectively. Tumor size was an independent clinical predictor. The nomogram, incorporating Rad-scores and tumor size, achieved AUCs of 0.790 (training cohort) and 0.774 (test cohort). Decision curve analysis demonstrated its potential clinical utility.

CONCLUSION

A biplanar ultrasound radiomics nomogram effectively predicts HER2 status in invasive BC, potentially reducing the need for biopsies and supporting personalized treatment strategies.

A digital pathology model for predicting radioiodine-avid metastases on initial post-therapeutic 131I scan in patients with papillary thyroid cancer

Accurate postoperative assessment is critical for optimizing 131I therapy in patients with papillary thyroid cancer (PTC). This study aimed to develop a pathology model utilizing postoperative digital pathology slides to predict lymph node and/or distant metastases on post-therapeutic 131I scan after initial 131I treatment in PTC patients. A retrospective analysis was conducted on 229 PTC patients who underwent total or near-total thyroidectomy and subsequent 131I treatment after levothyroxine (LT4) withdrawal between January 2022 and August 2023. The pathology model was developed through two stages: patch-level prediction and WSI-level prediction. The clinical model was constructed using statistically significant variables identified from univariate and multivariate logistic regression analysis. Of the 229 patients, 19.6% (45/229) exhibited 131I-avid metastatic foci in post-therapeutic 131I scan. Multifactorial analysis identified stimulated thyroglobulin (sTg) as the sole independent risk factor. The AUC of the pathology model in the training and test cohorts were 0.976 (95% CI 0.948-1.000) and 0.805 (95% CI 0.660-0.951), respectively, which were significantly higher than the clinical model (AUC 0.652 and 0.548, Pall < 0.05). This model has the potential to serve as a valuable tool for clinicians in tailoring treatment strategies, thereby optimizing therapeutic outcomes for PTC patients.

Multitask machine learning-based tumor-associated collagen signatures predict peritoneal recurrence and disease-free survival in gastric cancer

BACKGROUND

Accurate prediction of peritoneal recurrence for gastric cancer (GC) is crucial in clinic. The collagen alterations in tumor microenvironment affect the migration and treatment response of cancer cells. Herein, we proposed multitask machine learning-based tumor-associated collagen signatures (TACS), which are composed of quantitative collagen features derived from multiphoton imaging, to simultaneously predict peritoneal recurrence (TACSPR) and disease-free survival (TACSDFS).

METHODS

Among 713 consecutive patients, with 275 in training cohort, 222 patients in internal validation cohort, and 216 patients in external validation cohort, we developed and validated a multitask machine learning model for simultaneously predicting peritoneal recurrence (TACSPR) and disease-free survival (TACSDFS). The accuracy of the model for prediction of peritoneal recurrence and prognosis as well as its association with adjuvant chemotherapy were evaluated.

RESULTS

The TACSPR and TACSDFS were independently associated with peritoneal recurrence and disease-free survival in three cohorts, respectively (all P < 0.001). The TACSPR demonstrated a favorable performance for peritoneal recurrence in all three cohorts. In addition, the TACSDFS also showed a satisfactory accuracy for disease-free survival among included patients. For stage II and III diseases, adjuvant chemotherapy improved the survival of patients with low TACSPR and low TACSDFS, or high TACSPR and low TACSDFS, or low TACSPR and high TACSDFS, but had no impact on patients with high TACSPR and high TACSDFS.

CONCLUSIONS

The multitask machine learning model allows accurate prediction of peritoneal recurrence and survival for GC and could distinguish patients who might benefit from adjuvant chemotherapy.

Deep learning-assisted distinguishing breast phyllodes tumours from fibroadenomas based on ultrasound images: a diagnostic study

OBJECTIVES

To evaluate the performance of ultrasound-based deep learning (DL) models in distinguishing breast phyllodes tumours (PTs) from fibroadenomas (FAs) and their clinical utility in assisting radiologists with varying diagnostic experiences.

METHODS

We retrospectively collected 1180 ultrasound images from 539 patients (247 PTs and 292 FAs). Five DL network models with different structures were trained and validated using nodule regions annotated by radiologists on breast ultrasound images. DL models were trained using the methods of transfer learning and 3-fold cross-validation. The model demonstrated the best evaluation index in the 3-fold cross-validation was selected for comparison with radiologists' diagnostic decisions. Two-round reader studies were conducted to investigate the value of DL model in assisting 6 radiologists with different levels of experience.

RESULTS

Upon testing, Xception model demonstrated the best diagnostic performance (area under the receiver-operating characteristic curve: 0.87; 95% CI, 0.81-0.92), outperforming all radiologists (all P < .05). Additionally, the DL model enhanced the diagnostic performance of radiologists. Accuracy demonstrated improvements of 4%, 4%, and 3% for senior, intermediate, and junior radiologists, respectively.

CONCLUSIONS

The DL models showed superior predictive abilities compared to experienced radiologists in distinguishing breast PTs from FAs. Utilizing the model led to improved efficiency and diagnostic performance for radiologists with different levels of experience (6-25 years of work).

ADVANCES IN KNOWLEDGE

We developed and validated a DL model based on the largest available dataset to assist in diagnosing PTs. This model has the potential to allow radiologists to discriminate 2 types of breast tumours which are challenging to identify with precision and accuracy, and subsequently to make more informed decisions about surgical plans.

Non-invasive prediction of axillary lymph node dissection exemption in breast cancer patients post-neoadjuvant therapy: A radiomics and deep learning analysis on longitudinal DCE-MRI data

PURPOSE

In breast cancer (BC) patients with clinical axillary lymph node metastasis (cN+) undergoing neoadjuvant therapy (NAT), precise axillary lymph node (ALN) assessment dictates therapeutic strategy. There is a critical demand for a precise method to assess the axillary lymph node (ALN) status in these patients.

MATERIALS AND METHODS

A retrospective analysis was conducted on 160 BC patients undergoing NAT at Fujian Medical University Union Hospital. We analyzed baseline and two-cycle reassessment dynamic contrast-enhanced MRI (DCE-MRI) images, extracting 3668 radiomic and 4096 deep learning features, and computing 1834 delta-radiomic and 2048 delta-deep learning features. Light Gradient Boosting Machine (LightGBM), Support Vector Machine (SVM), RandomForest, and Multilayer Perceptron (MLP) algorithms were employed to develop risk models and were evaluated using 10-fold cross-validation.

RESULTS

Of the patients, 61 (38.13 %) achieved ypN0 status post-NAT. Univariate and multivariable logistic regression analyses revealed molecular subtypes and Ki67 as pivotal predictors of achieving ypN0 post-NAT. The SVM-based "Data Amalgamation" model that integrates radiomic, deep learning features, and clinical data, exhibited an outstanding AUC of 0.986 (95 % CI: 0.954-1.000), surpassing other models.

CONCLUSION

Our study illuminates the challenges and opportunities inherent in breast cancer management post-NAT. By introducing a sophisticated, SVM-based "Data Amalgamation" model, we propose a way towards accurate, dynamic ALN assessments, offering potential for personalized therapeutic strategies in BC.

Early Identification of Pathologic Complete Response to Neoadjuvant Chemotherapy Using Multiphase DCE-MRI by Siamese Network in Breast Cancer: A Longitudinal Multicenter Study

BACKGROUND

Siamese network (SN) using longitudinal DCE-MRI for pathologic complete response (pCR) identification lack a unified approach to phases selection.

PURPOSE

To identify pCR in early-stage NAC, using SN with longitudinal DCE-MRI and introducing IPS for phases selection.

STUDY TYPE

Multicenter, longitudinal.

POPULATION

Center A: 162 female patients (50.63 ± 8.41 years) divided 7:3 into training and internal validation cohorts. Center B: 61 female patients (50.08 ± 7.82 years) were used as an external validation cohort.

FIELD STRENGTH/SEQUENCE

Center A: single vendor 3.0 T with a compressed-sensing volume interpolated breath-hold examination sequence. Center B: single vendor 1.5 T with volume interpolated breath-hold examination sequence.

ASSESSMENT

Patients underwent DCE-MRI before and after two NAC cycles, with tumor regions of interest (ROI) manually delineated. Histopathology was the reference for pCR identification. Models developed included a clinical one, four SN models based on IPS-selected phases, and integrated models combining clinical and SN features.

STATISTICAL TESTS

Model performance was evaluated using the area under the receiver operating characteristic curve (AUC). The DeLong test was used to compare AUCs. Net reclassification improvement and integrated discrimination improvement (IDI) tests were employed for performance comparison. P < 0.05 was considered significant.

RESULTS

In internal and external validation cohorts, the clinical model showed AUCs of 0.760 and 0.718. SN and integrated models, with increasing phases via IPS, achieved AUCs ranging from 0.813 to 0.951 and 0.818 to 0.922. Notably, SN-3 and integrated-3 and integrated-4 outperformed the clinical model. However, input phases beyond 20% did not significantly enhance performance (IDI test: SN-4 vs. SN-3, P = 0.314 and 0.630; integrated-4 vs. integrated-3, P = 0.785 and 0.709).

DATA CONCLUSION

The longitudinal multiphase DCE-MRI based on the SN demonstrates promise for identifying pCR in breast cancer.

EVIDENCE LEVEL

1 TECHNICAL EFFICACY: Stage 4.

Cross-modal deep learning model for predicting pathologic complete response to neoadjuvant chemotherapy in breast cancer

Pathological complete response (pCR) serves as a critical measure of the success of neoadjuvant chemotherapy (NAC) in breast cancer, directly influencing subsequent therapeutic decisions. With the continuous advancement of artificial intelligence, methods for early and accurate prediction of pCR are being extensively explored. In this study, we propose a cross-modal multi-pathway automated prediction model that integrates temporal and spatial information. This model fuses digital pathology images from biopsy specimens and multi-temporal ultrasound (US) images to predict pCR status early in NAC. The model demonstrates exceptional predictive efficacy. Our findings lay the foundation for developing personalized treatment paradigms based on individual responses. This approach has the potential to become a critical auxiliary tool for the early prediction of NAC response in breast cancer patients.

The prediction of pCR and chemosensitivity for breast cancer patients using DLG3, RADL and Pathomics signatures based on machine learning and deep learning

BACKGROUND

Limited studies have investigated the predictive value of multiomics signatures (radiomics, deep learning features, pathological features and DLG3) in breast cancer patients who underwent neoadjuvant chemotherapy (NAC). However, no study has explored the relationships among radiomic, pathomic signatures and chemosensitivity. This study aimed to predict pathological complete response (pCR) using multiomics signatures, and to evaluate the predictive utility of radiomic and pathomic signatures for guiding chemotherapy selection.

METHODS

The oncogenic function of DLG3 was explored in breast cancer cells via DLG3 knockdown. Immunohistochemistry (IHC) was used to evaluate the relationship between DLG3 expression and docetaxel/epirubin sensitivity. Machine learning (ML) and deep learning (DL) algorithms were used to develop multiomics signatures. Survival analysis was conducted by K-M curves and log-rank. Multivariate logistic regression analysis was used to develop nomograms.

RESULTS

A total of 311 patients with malignant breast tumours who underwent NAC were retrospectively included in this multicentre study. Multiomics (DLG3, RADL and PATHO) signatures could accurately predict pCR (AUC: training: 0.900; testing: 0.814; external validation: 0.792). Its performance is also superior to that of clinical TNM staging and the single RADL signature in different cohorts. Patients in the low DLG3 group more easily achieved pCR, and those in the high RADL Signature_pCR and PATHO_Signature_pCR (OR = 7.93, 95 % CI: 3.49-18, P < 0.001) groups more easily achieved pCR. In the TEC regimen NAC group, patients who achieved pCR had a lower DLG3 score (4.00 ± 2.33 vs. 6.43 ± 3.01, P < 0.05). Patients in the low RADL_Signature_DLG3 and PATHO_Signature_DLG3 groups had lower DLG3 IHC scores (P < 0.05). Patients in the high RADL signature, PATHO signature and DLG3 signature groups had worse DFS and OS.

CONCLUSIONS

Multiomics signatures (RADL, PATHO and DLG3) demonstrated great potential in predicting the pCR of breast cancer patients who underwent NAC. The RADL and PATHO signatures are associated with DLG3 status and could help doctors or patients choose proper neoadjuvant chemotherapy regimens (TEC regimens). This simple, structured, convenient and inexpensive multiomics model could help clinicians and patients make treatment decisions.

Multimodal data integration using machine learning to predict the risk of clear cell renal cancer metastasis: a retrospective multicentre study

PURPOSE

To develop and validate a predictive combined model for metastasis in patients with clear cell renal cell carcinoma (ccRCC) by integrating multimodal data.

MATERIALS AND METHODS

In this retrospective study, the clinical and imaging data (CT and ultrasound) of patients with ccRCC confirmed by pathology from three tertiary hospitals in different regions were collected from January 2013 to January 2023. We developed three models, including a clinical model, a radiomics model, and a combined model. The performance of the model was determined based on its discriminative power and clinical utility. The evaluation indicators included area under the receiver operating characteristic curve (AUC) value, accuracy, sensitivity, specificity, negative predictive value, positive predictive value and decision curve analysis (DCA) curve.

RESULTS

A total of 251 patients were evaluated. Patients (n = 166) from Shandong University Qilu Hospital (Jinan) were divided into the training cohort, of which 50 patients developed metastases; patients (n = 37) from Shandong University Qilu Hospital (Qingdao) were used as internal testing, of which 15 patients developed metastases; patients (n = 48) from Changzhou Second People's Hospital were used as external testing, of which 13 patients developed metastases. In the training set, the combined model showed the highest performance (AUC, 0.924) in predicting lymph node metastasis (LNM), while the clinical and radiomics models both had AUCs of 0.845 and 0.870, respectively. In the internal testing, the combined model had the highest performance (AUC, 0.877) for predicting LNM, while the AUCs of the clinical and radiomics models were 0.726 and 0.836, respectively. In the external testing, the combined model had the highest performance (AUC, 0.849) for predicting LNM, while the AUCs of the clinical and radiomics models were 0.708 and 0.804, respectively. The DCA curve showed that the combined model had a significant prediction probability in predicting the risk of LNM in ccRCC patients compared with the clinical model or the radiomics model.

CONCLUSION

The combined model was superior to the clinical and radiomics models in predicting LNM in ccRCC patients.

Delta Radiomics Based on Longitudinal Dual-modal Ultrasound Can Early Predict Response to Neoadjuvant Chemotherapy in Breast Cancer Patients

RATIONALE AND OBJECTIVES

To develop a monitoring model using radiomics analysis based on longitudinal B-mode ultrasound (BUS) and shear wave elastography (SWE) to early predict pathological response to neoadjuvant chemotherapy (NAC) in breast cancer patients.

MATERIALS AND METHODS

In this prospective study, 112 breast cancer patients who received NAC between September 2016 and March 2022 were included. The BUS and SWE data of breast cancer were obtained prior to treatment as well as after two and four cycles of NAC. Radiomics features were extracted followed by measuring the changes in radiomics features compared to baseline after the second and fourth cycles of NAC (△R [C2], △R [C4]), respectively. The delta radiomics signatures were established using a support vector machine classifier.

RESULTS

The area under receiver operating characteristic curve (AUC) values of △RBUS (C2) and △RBUS (C4) for predicting the response to NAC were 0.83 and 0.84, while those of △RSWE (C2) and △RSWE (C4) were 0.88 and 0.90, respectively. △RSWE exhibited significantly superior performance to △RBUS for predicting NAC response (Delong test, p < 0.01). No significant differences were observed in the performances between △R (C2) and △R (C4) based on BUS or SWE data. The longitudinal dual-modal ultrasound radiomics (LDUR) model had an excellent discrimination, good calibration and clinical usefulness, with the AUC, sensitivity and specificity of 0.97, 95.52% and 91.11%, respectively.

CONCLUSION

The LDUR model achieved excellent performance in predicting the pathological response to chemotherapy during the early stages of NAC for breast cancer.

Automated and reusable deep learning (AutoRDL) framework for predicting response to neoadjuvant chemotherapy and axillary lymph node metastasis in breast cancer using ultrasound images: a retrospective, multicentre study

Background

Previous deep learning models have been proposed to predict the pathological complete response (pCR) and axillary lymph node metastasis (ALNM) in breast cancer. Yet, the models often leveraged multiple frameworks, required manual annotation, and discarded low-quality images. We aimed to develop an automated and reusable deep learning (AutoRDL) framework for tumor detection and prediction of pCR and ALNM using ultrasound images with diverse qualities.

Methods

The AutoRDL framework includes a You Only Look Once version 5 (YOLOv5) network for tumor detection and a progressive multi-granularity (PMG) network for pCR and ALNM prediction. The training cohort and the internal validation cohort were recruited from Guangdong Provincial People's Hospital (GPPH) between November 2012 and May 2021. The two external validation cohorts were recruited from the First Affiliated Hospital of Kunming Medical University (KMUH), between January 2016 and December 2019, and Shunde Hospital of Southern Medical University (SHSMU) between January 2014 and July 2015. Prior to model training, super-resolution via iterative refinement (SR3) was employed to improve the spatial resolution of low-quality images from the KMUH. We developed three models for predicting pCR and ALNM: a clinical model using multivariable logistic regression analysis, an image model utilizing the PMG network, and a combined model that integrates both clinical and image data using the PMG network.

Findings

The YOLOv5 network demonstrated excellent accuracy in tumor detection, achieving average precisions of 0.880-0.921 during validation. In terms of pCR prediction, the combined modelpost-SR3 outperformed the combined modelpre-SR3, image modelpost-SR3, image modelpre-SR3, and clinical model (AUC: 0.833 vs 0.822 vs 0.806 vs 0.790 vs 0.712, all p < 0.05) in the external validation cohort (KMUH). Consistently, the combined modelpost-SR3 exhibited the highest accuracy in ALNM prediction, surpassing the combined modelpre-SR3, image modelpost-SR3, image modelpre-SR3, and clinical model (AUC: 0.825 vs 0.806 vs 0.802 vs 0.787 vs 0.703, all p < 0.05) in the external validation cohort 1 (KMUH). In the external validation cohort 2 (SHSMU), the combined model also showed superiority over the clinical and image models (0.819 vs 0.712 vs 0.806, both p < 0.05).

Interpretation

Our proposed AutoRDL framework is feasible in automatically predicting pCR and ALNM in real-world settings, which has the potential to assist clinicians in optimizing individualized treatment options for patients.

Funding

National Key Research and Development Program of China (2023YFF1204600); National Natural Science Foundation of China (82227802, 82302306); Clinical Frontier Technology Program of the First Affiliated Hospital of Jinan University, China (JNU1AF-CFTP-2022-a01201); Science and Technology Projects in Guangzhou (202201020022, 2023A03J1036, 2023A03J1038); Science and Technology Youth Talent Nurturing Program of Jinan University (21623209); and Postdoctoral Science Foundation of China (2022M721349).

Development of a machine learning-based radiomics signature for estimating breast cancer TME phenotypes and predicting anti-PD-1/PD-L1 immunotherapy response

BACKGROUNDS

Since breast cancer patients respond diversely to immunotherapy, there is an urgent need to explore novel biomarkers to precisely predict clinical responses and enhance therapeutic efficacy. The purpose of our present research was to construct and independently validate a biomarker of tumor microenvironment (TME) phenotypes via a machine learning-based radiomics way. The interrelationship between the biomarker, TME phenotypes and recipients' clinical response was also revealed.

METHODS

In this retrospective multi-cohort investigation, five separate cohorts of breast cancer patients were recruited to measure breast cancer TME phenotypes via a radiomics signature, which was constructed and validated by integrating RNA-seq data with DCE-MRI images for predicting immunotherapy response. Initially, we constructed TME phenotypes using RNA-seq of 1089 breast cancer patients in the TCGA database. Then, parallel DCE-MRI images and RNA-seq of 94 breast cancer patients obtained from TCIA were applied to develop a radiomics-based TME phenotypes signature using random forest in machine learning. The repeatability of the radiomics signature was then validated in an internal validation set. Two additional independent external validation sets were analyzed to reassess this signature. The Immune phenotype cohort (n = 158) was divided based on CD8 cell infiltration into immune-inflamed and immune-desert phenotypes; these data were utilized to examine the relationship between the immune phenotypes and this signature. Finally, we utilized an Immunotherapy-treated cohort with 77 cases who received anti-PD-1/PD-L1 treatment to evaluate the predictive efficiency of this signature in terms of clinical outcomes.

RESULTS

The TME phenotypes of breast cancer were separated into two heterogeneous clusters: Cluster A, an "immune-inflamed" cluster, containing substantial innate and adaptive immune cell infiltration, and Cluster B, an "immune-desert" cluster, with modest TME cell infiltration. We constructed a radiomics signature for the TME phenotypes ([AUC] = 0.855; 95% CI 0.777-0.932; p < 0.05) and verified it in an internal validation set (0.844; 0.606-1; p < 0.05). In the known immune phenotypes cohort, the signature can identify either immune-inflamed or immune-desert tumor (0.814; 0.717-0.911; p < 0.05). In the Immunotherapy-treated cohort, patients with objective response had higher baseline radiomics scores than those with stable or progressing disease (p < 0.05); moreover, the radiomics signature achieved an AUC of 0.784 (0.643-0.926; p < 0.05) for predicting immunotherapy response.

CONCLUSIONS

Our imaging biomarker, a practicable radiomics signature, is beneficial for predicting the TME phenotypes and clinical response in anti-PD-1/PD-L1-treated breast cancer patients. It is particularly effective in identifying the "immune-desert" phenotype and may aid in its transformation into an "immune-inflamed" phenotype.

Using time-series chest radiographs and laboratory data by machine learning for identifying pulmonary infection and colonization of Acinetobacter baumannii

BACKGROUND

Accurately distinguishing between pulmonary infection and colonization in patients with Acinetobacter baumannii is of utmost importance to optimize treatment and prevent antibiotic abuse or inadequate therapy. An efficient automated sorting tool could prompt individualized interventions and enhance overall patient outcomes. This study aims to develop a robust machine learning classification model using a combination of time-series chest radiographs and laboratory data to accurately classify pulmonary status caused by Acinetobacter baumannii.

METHODS

We proposed nested logistic regression models based on different time-series data to automatically classify the pulmonary status of patients with Acinetobacter baumannii. Advanced features were extracted from the time-series data of hospitalized patients, encompassing dynamic pneumonia indicators observed on chest radiographs and laboratory indicator values recorded at three specific time points.

RESULTS

Data of 152 patients with Acinetobacter baumannii cultured from sputum or alveolar lavage fluid were retrospectively analyzed. Our model with multiple time-series data demonstrated a higher performance of AUC (0.850, with a 95% confidence interval of [0.638-0.873]), an accuracy of 0.761, a sensitivity of 0.833. The model, which only incorporated a single time point feature, achieved an AUC of 0.741. The influential model variables included difference in the chest radiograph pneumonia score.

CONCLUSION

Dynamic assessment of time-series chest radiographs and laboratory data using machine learning allowed for accurate classification of colonization and infection with Acinetobacter baumannii. This demonstrates the potential to help clinicians provide individualized treatment through early detection.

Exploring Neoadjuvant Chemotherapy, Predictive Models, Radiomic, and Pathological Markers in Breast Cancer: A Comprehensive Review

Breast cancer retains its position as the most prevalent form of malignancy among females on a global scale. The careful selection of appropriate treatment for each patient holds paramount importance in effectively managing breast cancer. Neoadjuvant chemotherapy (NACT) plays a pivotal role in the comprehensive treatment of this disease. Administering chemotherapy before surgery, NACT becomes a powerful tool in reducing tumor size, potentially enabling fewer invasive surgical procedures and even rendering initially inoperable tumors amenable to surgery. However, a significant challenge lies in the varying responses exhibited by different patients towards NACT. To address this challenge, researchers have focused on developing prediction models that can identify those who would benefit from NACT and those who would not. Such models have the potential to reduce treatment costs and contribute to a more efficient and accurate management of breast cancer. Therefore, this review has two objectives: first, to identify the most effective radiomic markers correlated with NACT response, and second, to explore whether integrating radiomic markers extracted from radiological images with pathological markers can enhance the predictive accuracy of NACT response. This review will delve into addressing these research questions and also shed light on the emerging research direction of leveraging artificial intelligence techniques for predicting NACT response, thereby shaping the future landscape of breast cancer treatment.

Recent advancements in artificial intelligence for breast cancer: Image augmentation, segmentation, diagnosis, and prognosis approaches

Breast cancer is a significant global health burden, with increasing morbidity and mortality worldwide. Early screening and accurate diagnosis are crucial for improving prognosis. Radiographic imaging modalities such as digital mammography (DM), digital breast tomosynthesis (DBT), magnetic resonance imaging (MRI), ultrasound (US), and nuclear medicine techniques, are commonly used for breast cancer assessment. And histopathology (HP) serves as the gold standard for confirming malignancy. Artificial intelligence (AI) technologies show great potential for quantitative representation of medical images to effectively assist in segmentation, diagnosis, and prognosis of breast cancer. In this review, we overview the recent advancements of AI technologies for breast cancer, including 1) improving image quality by data augmentation, 2) fast detection and segmentation of breast lesions and diagnosis of malignancy, 3) biological characterization of the cancer such as staging and subtyping by AI-based classification technologies, 4) prediction of clinical outcomes such as metastasis, treatment response, and survival by integrating multi-omics data. Then, we then summarize large-scale databases available to help train robust, generalizable, and reproducible deep learning models. Furthermore, we conclude the challenges faced by AI in real-world applications, including data curating, model interpretability, and practice regulations. Besides, we expect that clinical implementation of AI will provide important guidance for the patient-tailored management.

Ultrasound and clinicopathological characteristics-based model for prediction of pathologic response to neoadjuvant chemotherapy in HER2-positive breast cancer: a case-control study

BACKGROUND

The objective of this study was to develop a model combining ultrasound (US) and clinicopathological characteristics to predict the pathologic response to neoadjuvant chemotherapy (NACT) in human epidermal growth factor receptor 2 (HER2)-positive breast cancer.

MATERIALS AND METHODS

This is a retrospective study that included 248 patients with HER2-positive breast cancer who underwent NACT from March 2018 to March 2022. US and clinicopathological characteristics were collected from all patients in this study, and characteristics obtained using univariate analysis at p < 0.1 were subjected to multivariate analysis and then the conventional US and clinicopathological characteristics independently associated with pathologic complete response (pCR) from the analysis were used to develop US models, clinicopathological models, and their combined models by the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, and specificity to assess their predictive efficacy.

RESULTS

The combined model had an AUC of 0.808, a sensitivity of 88.72%, a specificity of 60.87%, and an accuracy of 75.81% in predicting pCR of HER2-positive breast cancer after NACT, which was significantly better than the clinicopathological model (AUC = 0.656) and the US model (AUC = 0.769). In addition, six characteristics were screened as independent predictors, namely the Clinical T stage, Clinical N stage, PR status, posterior acoustic, margin, and calcification.

CONCLUSION

The conventional US combined with clinicopathological characteristics to construct a combined model has a good diagnostic effect in predicting pCR in HER2-positive breast cancer and is expected to be a useful tool to assist clinicians in effectively determining the efficacy of NACT in HER2-positive breast cancer patients.

Pretreatment ultrasound-based deep learning radiomics model for the early prediction of pathologic response to neoadjuvant chemotherapy in breast cancer

OBJECTIVES

To investigate the predictive performance of the deep learning radiomics (DLR) model integrating pretreatment ultrasound imaging features and clinical characteristics for evaluating therapeutic response after neoadjuvant chemotherapy (NAC) in patients with breast cancer.

METHODS

A total of 603 patients who underwent NAC were retrospectively included between January 2018 and June 2021 from three different institutions. Four different deep convolutional neural networks (DCNNs) were trained by pretreatment ultrasound images using annotated training dataset (n = 420) and validated in a testing cohort (n = 183). Comparing the predictive performance of these models, the best one was selected for image-only model structure. Furthermore, the integrated DLR model was constructed based on the image-only model combined with independent clinical-pathologic variables. Areas under the curve (AUCs) of these models and two radiologists were compared by using the DeLong method.

RESULTS

As the optimal basic model, Resnet50 achieved an AUC and accuracy of 0.879 and 82.5% in the validation set. The integrated DLR model, yielding the highest classification performance in predicting response to NAC (AUC 0.962 and 0.939 in the training and validation cohort), outperformed the image-only model and the clinical model and also performed better than two radiologists' prediction (all p < 0.05). In addition, predictive efficacy of the radiologists was improved under the assistance of the DLR model significantly.

CONCLUSION

The pretreatment US-based DLR model could hold promise as a clinical guidance for predicting NAC response of patients with breast cancer, thereby providing benefit of timely treatment strategy adjustment to potential poor NAC responders.

KEY POINTS

• Multicenter retrospective study showed that deep learning radiomics (DLR) model based on pretreatment ultrasound image and clinical parameter achieved satisfactory prediction of tumor response to neoadjuvant chemotherapy (NAC) in breast cancer. • The integrated DLR model could become an effective tool to guide clinicians in identifying potential poor pathological responders before chemotherapy. • The predictive efficacy of the radiologists was improved under the assistance of the DLR model.

Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort study

Background

Early diagnosis of breast cancer has always been a difficult clinical challenge. We developed a deep-learning model EDL-BC to discriminate early breast cancer with ultrasound (US) benign findings. This study aimed to investigate how the EDL-BC model could help radiologists improve the detection rate of early breast cancer while reducing misdiagnosis.

Methods

In this retrospective, multicentre cohort study, we developed an ensemble deep learning model called EDL-BC based on deep convolutional neural networks. The EDL-BC model was trained and internally validated on B-mode and color Doppler US image of 7955 lesions from 6795 patients between January 1, 2015 and December 31, 2021 in the First Affiliated Hospital of Army Medical University (SW), Chongqing, China. The model was assessed by internal and external validations, and outperformed radiologists. The model performance was validated in two independent external validation cohorts included 448 lesions from 391 patients between January 1 to December 31, 2021 in the Tangshan People's Hospital (TS), Chongqing, China, and 245 lesions from 235 patients between January 1 to December 31, 2021 in the Dazu People's Hospital (DZ), Chongqing, China. All lesions in the training and total validation cohort were US benign findings during screening and biopsy-confirmed malignant, benign, and benign with 3-year follow-up records. Six radiologists performed the clinical diagnostic performance of EDL-BC, and six radiologists independently reviewed the retrospective datasets on a web-based rating platform.

Findings

The area under the receiver operating characteristic curve (AUC) of the internal validation cohort and two independent external validation cohorts for EDL-BC was 0.950 (95% confidence interval [CI]: 0.909-0.969), 0.956 (95% [CI]: 0.939-0.971), and 0.907 (95% [CI]: 0.877-0.938), respectively. The sensitivity values were 94.4% (95% [CI]: 72.7%-99.9%), 100% (95% [CI]: 69.2%-100%), and 80% (95% [CI]: 28.4%-99.5%), respectively, at 0.76. The AUC for accurate diagnosis of EDL-BC (0.945 [95% [CI]: 0.933-0.965]) and radiologists with artificial intelligence (AI) assistance (0.899 [95% [CI]: 0.883-0.913]) was significantly higher than that of the radiologists without AI assistance (0.716 [95% [CI]: 0.693-0.738]; p < 0.0001). Furthermore, there were no significant differences between the EDL-BC model and radiologists with AI assistance (p = 0.099).

Interpretation

EDL-BC can identify subtle but informative elements on US images of breast lesions and can significantly improve radiologists' diagnostic performance for identifying patients with early breast cancer and benefiting the clinical practice.

Funding

The National Key R&D Program of China.

Development and validation of a radiopathomic model for predicting pathologic complete response to neoadjuvant chemotherapy in breast cancer patients

BACKGROUND

Neoadjuvant chemotherapy (NAC) has become the standard therapeutic option for early high-risk and locally advanced breast cancer. However, response rates to NAC vary between patients, causing delays in treatment and affecting the prognosis for patients who do not sensitive to NAC.

MATERIALS AND METHODS

In total, 211 breast cancer patients who completed NAC (training set: 155, validation set: 56) were retrospectively enrolled. we developed a deep learning radiopathomics model(DLRPM) by Support Vector Machine (SVM) method based on clinicopathological features, radiomics features, and pathomics features. Furthermore, we comprehensively validated the DLRPM and compared it with three single-scale signatures.

RESULTS

DLRPM had favourable performance for the prediction of pathological complete response (pCR) in the training set (AUC 0.933[95% CI 0.895-0.971]), and in the validation set (AUC 0.927 [95% CI 0.858-0.996]). In the validation set, DLRPM also significantly outperformed the radiomics signature (AUC 0.821[0.700-0.942]), pathomics signature (AUC 0.766[0.629-0.903]), and deep learning pathomics signature (AUC 0.804[0.683-0.925]) (all p < 0.05). The calibration curves and decision curve analysis also indicated the clinical effectiveness of the DLRPM.

CONCLUSIONS

DLRPM can help clinicians accurately predict the efficacy of NAC before treatment, highlighting the potential of artificial intelligence to improve the personalized treatment of breast cancer patients.

Longitudinal MRI-based fusion novel model predicts pathological complete response in breast cancer treated with neoadjuvant chemotherapy: a multicenter, retrospective study

Background

Accurate identification of pCR to neoadjuvant chemotherapy (NAC) is essential for determining appropriate surgery strategy and guiding resection extent in breast cancer. However, a non-invasive tool to predict pCR accurately is lacking. Our study aims to develop ensemble learning models using longitudinal multiparametric MRI to predict pCR in breast cancer.

Methods

From July 2015 to December 2021, we collected pre-NAC and post-NAC multiparametric MRI sequences per patient. We then extracted 14,676 radiomics and 4096 deep learning features and calculated additional delta-value features. In the primary cohort (n = 409), the inter-class correlation coefficient test, U-test, Boruta and the least absolute shrinkage and selection operator regression were used to select the most significant features for each subtype of breast cancer. Five machine learning classifiers were then developed to predict pCR accurately for each subtype. The ensemble learning strategy was used to integrate the single-modality models. The diagnostic performances of models were evaluated in the three external cohorts (n = 343, 170 and 340, respectively).

Findings

A total of 1262 patients with breast cancer from four centers were enrolled in this study, and pCR rates were 10.6% (52/491), 54.3% (323/595) and 37.5% (66/176) in HR+/HER2-, HER2+ and TNBC subtype, respectively. Finally, 20, 15 and 13 features were selected to construct the machine learning models in HR+/HER2-, HER2+ and TNBC subtypes, respectively. The multi-Layer Perception (MLP) yields the best diagnostic performances in all subtypes. For the three subtypes, the stacking model integrating pre-, post- and delta-models yielded the highest AUCs of 0.959, 0.974 and 0.958 in the primary cohort, and AUCs of 0.882-0.908, 0.896-0.929 and 0.837-0.901 in the external validation cohorts, respectively. The stacking model had accuracies of 85.0%-88.9%, sensitivities of 80.0%-86.3%, and specificities of 87.4%-91.5% in the external validation cohorts.

Interpretation

Our study established a novel tool to predict the responses of breast cancer to NAC and achieve excellent performance. The models could help to determine post-NAC surgery strategy for breast cancer.

Funding

This study is supported by grants from the National Natural Science Foundation of China (82171898, 82103093), the Deng Feng project of high-level hospital construction (DFJHBF202109), the Guangdong Basic and Applied Basic Research Foundation (grant number, 2020A1515010346, 2022A1515012277), the Science and Technology Planning Project of Guangzhou City (202002030236), the Beijing Medical Award Foundation (YXJL-2020-0941-0758), and the Beijing Science and Technology Innovation Medical Development Foundation (KC2022-ZZ-0091-5). Funding sources were not involved in the study design, data collection, analysis and interpretation, writing of the report, or decision to submit the article for publication.