Diagnosis of Benign and Malignant Breast Lesions on DCE-MRI by Using Radiomics and Deep Learning With Consideration of Peritumor Tissue

Nomogram for preoperative differentiation of benign and malignant breast tumors using contrast-enhanced cone-beam breast CT (CE CB-BCT) quantitative imaging and assessment features

PURPOSE

Breast cancer's impact necessitates refined diagnostic approaches. This study develops a nomogram using radiology quantitative features from contrast-enhanced cone-beam breast CT for accurate preoperative classification of benign and malignant breast tumors.

MATERIAL AND METHODS

A retrospective study enrolled 234 females with breast tumors, split into training and test sets. Contrast-enhanced cone-beam breast CT-images were acquired using Koning Breast CT-1000. Quantitative assessment features were extracted via 3D-slicer software, identifying independent predictors. The nomogram was constructed to preoperative differentiation benign and malignant breast tumors. Calibration curve was used to assess whether the model showed favorable correspondence with pathological confirmation. Decision curve analysis confirmed the model's superiority.

RESULTS

The study enrolled 234 female patients with a mean age of 50.2 years (SD ± 9.2). The training set had 164 patients (89 benign, 75 malignant), and the test set had 70 patients (29 benign, 41 malignant). The nomogram achieved excellent predictive performance in distinguishing benign and malignant breast lesions with an AUC of 0.940 (95% CI 0.900-0.940) in the training set and 0.970 (95% CI 0.940-0.970) in the test set.

CONCLUSION

This study illustrates the effectiveness of quantitative radiology features derived from contrast-enhanced cone-beam breast CT in distinguishing between benign and malignant breast tumors. Incorporating these features into a nomogram-based diagnostic model allows for breast tumor diagnoses that are objective and possess good accuracy. The application of these insights could substantially increase reliability and efficacy in the management of breast tumors, offering enhanced diagnostic capability.

Machine learning based on optimal VOI of multi-sequence MR images to predict lymphovascular invasion in invasive breast cancer

Objectives

Lymphovascular invasion serves as a crucial prognostic indicator in invasive breast cancer, influencing treatment decisions. We aimed to develop a machine learning model utilizing optimal volumes of interest extracted from multisequence magnetic resonance images to predict lymphovascular invasion in patients with invasive breast cancer.

Materials and methods

This study comprised 191 patients postoperatively diagnosed with invasive breast cancer through multi-sequence magnetic resonance imaging. Independent predictors were identified through univariate and multivariate logistic regression analyses, culminating in the construction of a clinical model. Radiomic features were extracted from multi-sequence magnetic resonance imaging images across various volume of interest scales (-2 mm, entire, +2 mm, +4 mm, and +6 mm). Subsequently, various radiomic models were developed using machine learning model algorithms, including logistic regression, support vector machine, k-nearest neighbor, gradient boosting machine, classification and regression tree, and random forest. A hybrid model was then formulated, amalgamating optimal radiomic and clinical models.

Results

The area under the curve of the clinical model was 0.757. Among the radiomic models, the most efficient diagnosis was achieved by the k-nearest neighbor-based radiomics-volume of interest (+2 mm), resulting in an area under the curve of 0.780. The hybrid model, integrating the k-nearest neighbor-based radiomics-volume of interest (+2 mm), and the clinical model surpassed the individual clinical and radiomics models, exhibiting a superior area under the curve of 0.864.

Conclusion

Utilizing a hybrid approach integrating clinical data and multi-sequence magnetic resonance imaging-derived radiomics models based on the multiscale tumor region volume of interest (+2 mm) proved effective in determining lymphovascular invasion status in patients with invasive breast cancer. This innovative methodology may offer valuable insights for treatment planning and disease management.

An improved breast cancer classification with hybrid chaotic sand cat and Remora Optimization feature selection algorithm

Breast cancer is one of the most often diagnosed cancers in women, and identifying breast cancer histological images is an essential challenge in automated pathology analysis. According to research, the global BrC is around 12% of all cancer cases. Furthermore, around 25% of women suffer from BrC. Consequently, the prediction of BrC depends critically on the quick and precise processing of imaging data. The primary reason deep learning models are used in breast cancer detection is that they can produce findings more quickly and accurately than current machine learning-based techniques. Using a BreakHis dataset, we demonstrated in this work the viability of automatically identifying and classifying BrC. The first stage is pre-processing, which employs an Adaptive Switching Modified Decision Based Unsymmetrical Trimmed Median Filter (ASMDBUTMF) to remove high-density noise. After the image has been pre-processed, it is segmented using the Thresholding Level set approach. Next, we propose a hybrid chaotic sand cat optimization technique, together with the Remora Optimization Algorithm (ROA) for feature selection. The suggested strategy facilitates the acquisition of precise functionality attributes, hence simplifying the detection procedure. Additionally, it aids in resolving problems pertaining to global optimization. Following the selection, the best characteristics proceed to the categorization procedure. A DL classifier called the Conditional Variation Autoencoder is used to discriminate between cancerous and benign tumors while categorizing them. Consequently, a classification accuracy of 99.4%, Precision of 99.2%, Recall of 99.1%, F- score of 99%, Specificity of 99.14%, FDR of 0.54, FNR of 0.001, FPR of 0.002, MCC of 0.98 and NPV of 0.99 were obtained using the proposed approach. Furthermore, compared to other research using the current BreakHis dataset, the results of our research are more desirable.

Clinical study on the prediction of ALN metastasis based on intratumoral and peritumoral DCE-MRI radiomics and clinico-radiological characteristics in breast cancer

Objective

To investigate the value of predicting axillary lymph node (ALN) metastasis based on intratumoral and peritumoral dynamic contrast-enhanced MRI (DCE-MRI) radiomics and clinico-radiological characteristics in breast cancer.

Methods

A total of 473 breast cancer patients who underwent preoperative DCE-MRI from Jan 2017 to Dec 2020 were enrolled. These patients were randomly divided into training (n=378) and testing sets (n=95) at 8:2 ratio. Intratumoral regions (ITRs) of interest were manually delineated, and peritumoral regions of 3 mm (3 mmPTRs) were automatically obtained by morphologically dilating the ITR. Radiomics features were extracted, and ALN metastasis-related radiomics features were selected by the Mann-Whitney U test, Z score normalization, variance thresholding, K-best algorithm and least absolute shrinkage and selection operator (LASSO) algorithm. Clinico-radiological risk factors were selected by logistic regression and were also used to construct predictive models combined with radiomics features. Then, 5 models were constructed, including ITR, 3 mmPTR, ITR+3 mmPTR, clinico-radiological and combined (ITR+3 mmPTR+ clinico-radiological) models. The performance of models was assessed by sensitivity, specificity, accuracy, F1 score and area under the curve (AUC) of receiver operating characteristic (ROC), calibration curves and decision curve analysis (DCA).

Results

A total of 2264 radiomics features were extracted from each region of interest (ROI), 3 and 10 radiomics features were selected for the ITR and 3 mmPTR, respectively. 5 clinico-radiological risk factors were selected, including lesion size, human epidermal growth factor receptor 2 (HER2) expression, vascular cancer thrombus status, MR-reported ALN status, and time-signal intensity curve (TIC) type. In the testing set, the combined model showed the highest AUC (0.839), specificity (74.2%), accuracy (75.8%) and F1 Score (69.3%) among the 5 models. DCA showed that it had the greatest net clinical benefit compared to the other models.

Conclusion

The intra- and peritumoral radiomics models based on DCE-MRI could be used to predict ALN metastasis in breast cancer, especially for the combined model with clinico-radiological characteristics showing promising clinical application value.

Shallow and deep learning classifiers in medical image analysis

An increasingly strong connection between artificial intelligence and medicine has enabled the development of predictive models capable of supporting physicians' decision-making. Artificial intelligence encompasses much more than machine learning, which nevertheless is its most cited and used sub-branch in the last decade. Since most clinical problems can be modeled through machine learning classifiers, it is essential to discuss their main elements. This review aims to give primary educational insights on the most accessible and widely employed classifiers in radiology field, distinguishing between "shallow" learning (i.e., traditional machine learning) algorithms, including support vector machines, random forest and XGBoost, and "deep" learning architectures including convolutional neural networks and vision transformers. In addition, the paper outlines the key steps for classifiers training and highlights the differences between the most common algorithms and architectures. Although the choice of an algorithm depends on the task and dataset dealing with, general guidelines for classifier selection are proposed in relation to task analysis, dataset size, explainability requirements, and available computing resources. Considering the enormous interest in these innovative models and architectures, the problem of machine learning algorithms interpretability is finally discussed, providing a future perspective on trustworthy artificial intelligence.Relevance statement The growing synergy between artificial intelligence and medicine fosters predictive models aiding physicians. Machine learning classifiers, from shallow learning to deep learning, are offering crucial insights for the development of clinical decision support systems in healthcare. Explainability is a key feature of models that leads systems toward integration into clinical practice. Key points • Training a shallow classifier requires extracting disease-related features from region of interests (e.g., radiomics).• Deep classifiers implement automatic feature extraction and classification.• The classifier selection is based on data and computational resources availability, task, and explanation needs.

Hype or hope? A review of challenges in balancing tumor control and treatment toxicity in breast cancer from the perspective of the radiation oncologist

The aim of this article is to discuss the challenges and new strategies in managing breast cancer patients, with a specific focus on radiation oncology and the importance of balancing oncologic outcomes with quality of life and post-treatment morbidity. A comprehensive literature review was conducted to identify advances in the management of breast cancer, exploring de-escalation strategies, hypofractionation schemes, predictors and tools for reducing toxicity (radiation-induced lymphocyte apoptosis, deep inspiration breath-hold, adaptive radiotherapy), enhancer treatments (hyperthermia, immunotherapy) and innovative diagnostic modalities (PET-MRI, omics). Balancing oncologic outcomes with quality of life and post-treatment morbidity is crucial in the era of personalized medicine. Radiotherapy plays a critical role in the management of breast cancer patients. Large randomized trials are necessary to generalize some practices and cost remains the main obstacle for many innovations that are already applicable.

A Novel Interpretable Radiomics Model to Distinguish Nodular Goiter From Malignant Thyroid Nodules

OBJECTIVES

The purpose of this study is to inquire about the potential association between radiomics features and the pathological nature of thyroid nodules (TNs), and to propose an interpretable radiomics-based model for predicting the risk of malignant TN.

METHODS

In this retrospective study, computed tomography (CT) imaging and pathological data from 141 patients with TN were collected. The data were randomly stratified into a training group (n = 112) and a validation group (n = 29) at a ratio of 4:1. A total of 1316 radiomics features were extracted by using the pyradiomics tool. The redundant features were removed through correlation testing, and the least absolute shrinkage and selection operator (LASSO) or the minimum redundancy maximum relevance standard was used to select features. Finally, 4 different machine learning models (RF Hybrid Feature, SVM Hybrid Feature, RF, and LASSO) were constructed. The performance of the 4 models was evaluated using the receiver operating characteristic curve. The calibration curve, decision curve analysis, and SHapley Additive exPlanations method were used to evaluate or explain the best radiomics machine learning model.

RESULTS

The optimal radiomics model (RF Hybrid Feature model) demonstrated a relatively high degree of discrimination with an area under the receiver operating characteristic curve (AUC) of 0.87 (95% CI, 0.70-0.97; P < 0.001) for the validation cohort. Compared with the commonly used LASSO model (AUC, 0.78; 95% CI, 0.60-0.91; P < 0.01), there is a significant improvement in AUC in the validation set, net reclassification improvement, 0.79 (95% CI, 0.13-1.46; P < 0.05), and integrated discrimination improvement, 0. 20 (95% CI, 0.10-0.30; P < 0.001).

CONCLUSION

The interpretable radiomics model based on CT performs well in predicting benign and malignant TNs by using quantitative radiomics features of the unilateral total thyroid. In addition, the data preprocessing method incorporating different layers of features has achieved excellent experimental results.

CLINICAL RELEVANCE STATEMENT

As the detection rate of TNs continues to increase, so does the diagnostic burden on radiologists. This study establishes a noninvasive, interpretable and accurate machine learning model to rapidly identify the nature of TN found in CT.

Intra- and peritumoral radiomics features based on multicenter automatic breast volume scanner for noninvasive and preoperative prediction of HER2 status in breast cancer: a model ensemble research

The aim to investigate the predictive efficacy of automatic breast volume scanner (ABVS), clinical and serological features alone or in combination at model level for predicting HER2 status. The model weighted combination method was developed to identify HER2 status compared with single data source model method and feature combination method. 271 patients with invasive breast cancer were included in the retrospective study, of which 174 patients in our center were randomized into the training and validation sets, and 97 patients in the external center were as the test set. Radiomics features extracted from the ABVS-based tumor, peritumoral 3 mm region, and peritumoral 5 mm region and clinical features were used to construct the four types of the optimal single data source models, Tumor, R3mm, R5mm, and Clinical model, respectively. Then, the model weighted combination and feature combination methods were performed to optimize the combination models. The proposed weighted combination models in predicting HER2 status achieved better performance both in validation set and test set. For the validation set, the single data source model, the feature combination model, and the weighted combination model achieved the highest area under the curve (AUC) of 0.803 (95% confidence interval [CI] 0.660-947), 0.739 (CI 0.556,0.921), and 0.826 (95% CI 0.689,0.962), respectively; with the sensitivity and specificity were 100%, 62.5%; 81.8%, 66.7%; 90.9%,75.0%; respectively. For the test set, the single data source model, the feature combination model, and the weighted combination model attained the best AUC of 0.695 (95% CI 0.583, 0.807), 0.668 (95% CI 0.555,0.782), and 0.700 (95% CI 0.590,0.811), respectively; with the sensitivity and specificity were 86.1%, 41.9%; 61.1%, 71.0%; 86.1%, 41.9%; respectively. The model weighted combination was a better method to construct a combination model. The optimized weighted combination models composed of ABVS-based intratumoral and peritumoral radiomics features and clinical features may be potential biomarkers for the noninvasive and preoperative prediction of HER2 status in breast cancer.

Prediction model based on MRI morphological features for distinguishing benign and malignant thyroid nodules

BACKGROUND

The low specificity of Thyroid Imaging Reporting and Data System (TI-RADS) for preoperative benign-malignant diagnosis leads to a large number of unnecessary biopsies. This study developed and validated a predictive model based on MRI morphological features to improve the specificity.

METHODS

A retrospective analysis was conducted on 825 thyroid nodules pathologically confirmed postoperatively. Univariate and multivariate logistic regression were used to obtain β coefficients, construct predictive models and nomogram incorporating MRI morphological features in the training cohort, and validated in the validation cohort. The discrimination, calibration, and decision curve analysis of the nomogram were performed. The diagnosis efficacy, area under the curve (AUC) and net reclassification index (NRI) were calculated and compared with TI-RADS.

RESULTS

572 thyroid nodules were included (training cohort: n = 397, validation cohort: n = 175). Age, low signal intensity on T2WI, restricted diffusion, reversed halo sign in delay phase, cystic degeneration and wash-out pattern were independent predictors of malignancy. The nomogram demonstrated good discrimination and calibration both in the training cohort (AUC = 0.972) and the validation cohort (AUC = 0.968). The accuracy, sensitivity, specificity, PPV, NPV and AUC of MRI-based prediction were 94.4%, 96.0%, 93.4%, 89.9%, 96.5% and 0.947, respectively. The MRI-based prediction model exhibited enhanced accuracy (NRI>0) in comparison to TI-RADSs.

CONCLUSIONS

The prediction model for diagnosis of benign and malignant thyroid nodules demonstrated a more notable diagnostic efficacy than TI-RADS. Compared with the TI-RADSs, predictive model had better specificity along with a high sensitivity and can reduce overdiagnosis and unnecessary biopsies.

Diagnosis of benign and malignant nodules with a radiomics model integrating features from nodules and mammary regions on DCE-MRI

Objectives

To establish a radiomics model for distinguishing between the benign and malignant mammary gland nodules via combining the features from nodule and mammary regions on DCE-MRI.

Methods

In this retrospective study, a total of 103 cases with mammary gland nodules (malignant/benign = 80/23) underwent DCE-MRI, and was confirmed by biopsy pathology. Features were extracted from both nodule region and mammary region on DCE-MRI. Three SVM classifiers were built for diagnosis of benign and malignant nodules as follows: the model with the features only from nodule region (N model), with the features only from mammary region (M model) and the model combining the features from nodule region and mammary region (NM model). The performance of models was evaluated with the area under the curve of receiver operating characteristic (AUC).

Results

One radiomic features is selected from nodule region and 3 radiomic features is selected from mammary region. Compared with N or M model, NM model exhibited the best performance with an AUC of 0.756.

Conclusions

Compared with the model only using the features from nodule or mammary region, the radiomics-based model combining the features from nodule and mammary region outperformed in the diagnosis of benign and malignant nodules.

Anti-HER2 therapy response assessment for guiding treatment (de-)escalation in early HER2-positive breast cancer using a novel deep learning radiomics model

OBJECTIVES

Anti-HER2 targeted therapy significantly reduces risk of relapse in HER2 + breast cancer. New measures are needed for a precise risk stratification to guide (de-)escalation of anti-HER2 strategy.

METHODS

A total of 726 HER2 + cases who received no/single/dual anti-HER2 targeted therapies were split into three respective cohorts. A deep learning model (DeepTEPP) based on preoperative breast magnetic resonance (MR) was developed. Patients were scored and categorized into low-, moderate-, and high-risk groups. Recurrence-free survival (RFS) was compared in patients with different risk groups according to the anti-HER2 treatment they received, to validate the value of DeepTEPP in predicting treatment efficacy and guiding anti-HER2 strategy.

RESULTS

DeepTEPP was capable of risk stratification and guiding anti-HER2 treatment strategy: DeepTEPP-Low patients (60.5%) did not derive significant RFS benefit from trastuzumab (p = 0.144), proposing an anti-HER2 de-escalation. DeepTEPP-Moderate patients (19.8%) significantly benefited from trastuzumab (p = 0.048), but did not obtain additional improvements from pertuzumab (p = 0.125). DeepTEPP-High patients (19.7%) significantly benefited from dual HER2 blockade (p = 0.045), suggesting an anti-HER2 escalation.

CONCLUSIONS

DeepTEPP represents a pioneering MR-based deep learning model that enables the non-invasive prediction of adjuvant anti-HER2 effectiveness, thereby providing valuable guidance for anti-HER2 (de-)escalation strategies. DeepTEPP provides an important reference for choosing the appropriate individualized treatment in HER2 + breast cancer patients, warranting prospective validation.

CLINICAL RELEVANCE STATEMENT

We built an MR-based deep learning model DeepTEPP, which enables the non-invasive prediction of adjuvant anti-HER2 effectiveness, thus guiding anti-HER2 (de-)escalation strategies in early HER2-positive breast cancer patients.

KEY POINTS

• DeepTEPP is able to predict anti-HER2 effectiveness and to guide treatment (de-)escalation. • DeepTEPP demonstrated an impressive prognostic efficacy for recurrence-free survival and overall survival. • To our knowledge, this is one of the very few, also the largest study to test the efficacy of a deep learning model extracted from breast MR images on HER2-positive breast cancer survival and anti-HER2 therapy effectiveness prediction.

Intra- and Peritumoral Based Radiomics for Assessment of Lymphovascular Invasion in Invasive Breast Cancer

BACKGROUND

Radiomics has been applied for assessing lymphovascular invasion (LVI) in patients with breast cancer. However, associations between features from peritumoral regions and the LVI status were not investigated.

PURPOSE

To investigate the value of intra- and peritumoral radiomics for assessing LVI, and to develop a nomogram to assist in making treatment decisions.

STUDY TYPE

Retrospective.

POPULATION

Three hundred and sixteen patients were enrolled from two centers and divided into training (N = 165), internal validation (N = 83), and external validation (N = 68) cohorts.

FIELD STRENGTH/SEQUENCE

1.5 T and 3.0 T/dynamic contrast-enhanced (DCE) and diffusion-weighted imaging (DWI).

ASSESSMENT

Radiomics features were extracted and selected based on intra- and peritumoral breast regions in two magnetic resonance imaging (MRI) sequences to create the multiparametric MRI combined radiomics signature (RS-DCE plus DWI). The clinical model was built with MRI-axillary lymph nodes (MRI ALN), MRI-reported peritumoral edema (MPE), and apparent diffusion coefficient (ADC). The nomogram was constructed with RS-DCE plus DWI, MRI ALN, MPE, and ADC.

STATISTICAL TESTS

Intra- and interclass correlation coefficient analysis, Mann-Whitney U test, and least absolute shrinkage and selection operator regression were used for feature selection. Receiver operating characteristic and decision curve analyses were applied to compare performance of the RS-DCE plus DWI, clinical model, and nomogram.

RESULTS

A total of 10 features were found to be associated with LVI, 3 from intra- and 7 from peritumoral areas. The nomogram showed good performance in the training (AUCs, nomogram vs. clinical model vs. RS-DCE plus DWI, 0.884 vs. 0.695 vs. 0.870), internal validation (AUCs, nomogram vs. clinical model vs. RS-DCE plus DWI, 0.813 vs. 0.695 vs. 0.794), and external validation (AUCs, nomogram vs. clinical model vs. RS-DCE plus DWI, 0.862 vs. 0.601 vs. 0.849) cohorts.

DATA CONCLUSION

The constructed preoperative nomogram might effectively assess LVI.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

An Automated Breast Volume Scanner-Based Intra- and Peritumoral Radiomics Nomogram for the Preoperative Prediction of Expression of Ki-67 in Breast Malignancy

RATIONALE AND OBJECTIVES

This study aimed to create and verify a nomogram for preoperative prediction of Ki-67 expression in breast malignancy to assist in the development of personalized treatment strategies.

MATERIALS AND METHODS

This retrospective study received approval from the institutional review board and included a cohort of 197 patients with breast malignancy who were admitted to our hospital. Ki-67 expression was divided into two groups based on a 14% threshold: low and high. A radiomics signature was built utilizing 1702 radiomics features based on an intra- and peritumoral (10 mm) regions of interest. Using multivariate logistic regression, radiomics signature, and ultrasound (US) characteristics, the nomogram was developed. To evaluate the model's calibration, clinical application, and predictive ability, decision curve analysis (DCA), the calibration curve, and the receiver operating characteristic curve were used, respectively.

RESULTS

The final nomogram included three independent predictors: tumor size (P = .037), radiomics signature (P < .001), and US-reported lymph node status (P = .018). The nomogram exhibited satisfactory performance in the training cohort, demonstrating a specificity of 0.944, a sensitivity of 0.745, and an area under the curve (AUC) of 0.905. The validation cohort recorded a specificity of 0.909, a sensitivity of 0.727, and an AUC of 0.882. The DCA showed the nomogram's clinical utility, and the calibration curve revealed a high consistency among the expected and detected values.

CONCLUSION

The nomogram used in this investigation can accurately predict Ki-67 expression in people with malignant breast tumors, helping to develop personalized treatment approaches.

Cross-Parametric Generative Adversarial Network-Based Magnetic Resonance Image Feature Synthesis for Breast Lesion Classification

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) contains information on tumor morphology and physiology for breast cancer diagnosis and treatment. However, this technology requires contrast agent injection with more acquisition time than other parametric images, such as T2-weighted imaging (T2WI). Current image synthesis methods attempt to map the image data from one domain to another, whereas it is challenging or even infeasible to map the images with one sequence into images with multiple sequences. Here, we propose a new approach of cross-parametric generative adversarial network (GAN)-based feature synthesis (CPGANFS) to generate discriminative DCE-MRI features from T2WI with applications in breast cancer diagnosis. The proposed approach decodes the T2W images into latent cross-parameter features to reconstruct the DCE-MRI and T2WI features by balancing the information shared between the two. A Wasserstein GAN with a gradient penalty is employed to differentiate the T2WI-generated features from ground-truth features extracted from DCE-MRI. The synthesized DCE-MRI feature-based model achieved significantly (p = 0.036) higher prediction performance (AUC = 0.866) in breast cancer diagnosis than that based on T2WI (AUC = 0.815). Visualization of the model shows that our CPGANFS method enhances the predictive power by levitating attention to the lesion and the surrounding parenchyma areas, which is driven by the interparametric information learned from T2WI and DCE-MRI. Our proposed CPGANFS provides a framework for cross-parametric MR image feature generation from a single-sequence image guided by an information-rich, time-series image with kinetic information. Extensive experimental results demonstrate its effectiveness with high interpretability and improved performance in breast cancer diagnosis.

Radiomics to Differentiate Malignant and Benign Breast Lesions: A Systematic Review and Diagnostic Test Accuracy Meta-Analysis

Breast cancer is a prevalent global health concern, necessitating accurate diagnostic tools for effective management. Diagnostic imaging plays a pivotal role in breast cancer diagnosis, staging, treatment planning, and outcome evaluation. Radiomics is an emerging field of study in medical imaging that contains a broad set of computational methods to extract quantitative features from radiographic images. This can be utilized to guide diagnosis, treatment response, and prognosis in clinical settings.  A systematic review was performed in concordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and the Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy. Quality was assessed using the radiomics quality score. Diagnostic sensitivity and specificity of radiomics analysis, with 95% confidence intervals (CIs), were included for meta-analysis. The area under the curve analysis was recorded. An extensive statistical analysis was performed following the Cochrane guidelines. Statistical significance was determined if p-values were less than 0.05. Statistical analyses were conducted using Review Manager (RevMan), Version 5.4.1. A total of 31 manuscripts involving 8,773 patients were included, with 17 contributing to the meta-analysis. The cohort comprised 56.2% malignant breast cancers and 43.8% benign breast lesions. MRI demonstrated a sensitivity of 0.91 (95% CI: 0.89-0.92) and a specificity of 0.84 (95% CI: 0.82-0.86) in differentiating between benign and malignant breast cancers. Mammography-based radiomic features predicted breast cancer subtype with a sensitivity of 0.79 (95% CI: 0.76-0.82) and a specificity of 0.81 (95% CI: 0.79-0.84). Ultrasound-based analysis yielded a sensitivity of 0.92 (95% CI: 0.90-0.94) and a specificity of 0.85 (95% CI: 0.83-0.88). Only one study reported the results of radiomic evaluation from CT, which had a sensitivity of 0.95 (95% CI: 0.88-0.99) and a specificity of 0.56 (95% CI: 0.45-0.67).  Across different imaging modalities, radiomics exhibited robust diagnostic accuracy in differentiating benign and malignant breast lesions. The results underscore the potential of radiomic assessment as a minimally invasive alternative or adjunctive diagnostic tool for breast cancer. This is pioneering data that reports on a novel diagnostic approach that is understudied and underreported. However, due to study limitations, the complexity of this technology, and the need for future development, biopsy still remains the current gold standard method of determining breast cancer type.

Artificial intelligence in breast cancer: application and future perspectives

Breast cancer is one of the most common cancers and is one of the leading causes of cancer-related deaths in women worldwide. Early diagnosis and treatment are the key for a favorable prognosis. The application of artificial intelligence technology in the medical field is increasingly extensive, including image analysis, automated diagnosis, intelligent pharmaceutical system, personalized treatment and so on. AI-based breast cancer imaging, pathology and adjuvant therapy technology cannot only reduce the workload of clinicians, but also continuously improve the accuracy and sensitivity of breast cancer diagnosis and treatment. This paper reviews the application of AI in breast cancer, as well as looks ahead and poses challenges to the future development of AI for breast cancer detection and therapeutic, so as to provide ideas for future research.

A Comprehensive Model Based on Dynamic Contrast-Enhanced Magnetic Resonance Imaging Can Better Predict the Preoperative Histological Grade of Breast Cancer Than a Radiomics Model

Background

Histological grade is an important prognostic factor for patients with breast cancer and can affect clinical decision-making. From a clinical perspective, developing an efficient and non-invasive method for evaluating histological grading is desirable, facilitating improved clinical decision-making by physicians. This study aimed to develop an integrated model based on radiomics and clinical imaging features for preoperative prediction of histological grade invasive breast cancer.

Methods

In this retrospective study, we recruited 211 patients with invasive breast cancer and randomly assigned them to either a training group (n=147) or a validation group (n=64) with a 7:3 ratio. Patients were classified as having low-grade tumors, which included grade I and II tumors, or high-grade tumors, which included grade III tumors. Three models were constructed based on basic clinical features, radiomics features, and the sum of the two. To assess diagnostic performance of the radiomics models, we employed measures such as receiver operating characteristic (ROC) curve, decision curve analysis (DCA), accuracy, sensitivity, and specificity, and the predictive performance of the three models was compared using the DeLong test and net reclassification improvement (NRI).

Results

The area under the curve (AUC) of the clinical model, radiomics model, and comprehensive model was 0.682, 0.833, and 0.882 in the training set and 0.741, 0.751, and 0.836 in the validation set, respectively. NRI analysis confirmed that the combined model was better than the other two models in predicting the histological grade of breast cancer (NRI=21.4% in the testing cohort).

Conclusion

Compared with the other models, the comprehensive model based on the combination of basic clinical features and radiomics features exhibits more significant potential for predicting histological grade and can better assist clinicians in optimal decision-making.

Use of a deep learning algorithm for non-mass enhancement on breast MRI: comparison with radiologists' interpretations at various levels

PURPOSE

To evaluate the diagnostic performance of deep learning using the Residual Networks 50 (ResNet50) neural network constructed from different segmentations for distinguishing malignant and benign non-mass enhancement (NME) on breast magnetic resonance imaging (MRI) and conduct a comparison with radiologists with various levels of experience.

MATERIALS AND METHODS

A total of 84 consecutive patients with 86 lesions (51 malignant, 35 benign) presenting NME on breast MRI were analyzed. Three radiologists with different levels of experience evaluated all examinations, based on the Breast Imaging-Reporting and Data System (BI-RADS) lexicon and categorization. For the deep learning method, one expert radiologist performed lesion annotation manually using the early phase of dynamic contrast-enhanced (DCE) MRI. Two segmentation methods were applied: a precise segmentation was carefully set to include only the enhancing area, and a rough segmentation covered the whole enhancing region, including the intervenient non-enhancing area. ResNet50 was implemented using the DCE MRI input. The diagnostic performance of the radiologists' readings and deep learning were then compared using receiver operating curve analysis.

RESULTS

The ResNet50 model from precise segmentation achieved diagnostic accuracy equivalent [area under the curve (AUC) = 0.91, 95% confidence interval (CI) 0.90, 0.93] to that of a highly experienced radiologist (AUC = 0.89, 95% CI 0.81, 0.96; p = 0.45). Even the model from rough segmentation showed diagnostic performance equivalent to a board-certified radiologist (AUC = 0.80, 95% CI 0.78, 0.82 vs. AUC = 0.79, 95% CI 0.70, 0.89, respectively). Both ResNet50 models from the precise and rough segmentation exceeded the diagnostic accuracy of a radiology resident (AUC = 0.64, 95% CI 0.52, 0.76).

CONCLUSION

These findings suggest that the deep learning model from ResNet50 has the potential to ensure accuracy in the diagnosis of NME on breast MRI.

Risk stratification by nomogram of deep learning radiomics based on multiparametric magnetic resonance imaging in knee meniscus injury

PURPOSE

To construct and validate a nomogram model that integrated deep learning radiomic features based on multiparametric MRI and clinical features for risk stratification of meniscus injury.

METHODS

A total of 167 knee MR images were collected from two institutions. All patients were classified into two groups based on the MR diagnostic criteria proposed by Stoller et al. The automatic meniscus segmentation model was constructed through V-net. LASSO regression was performed to extract the optimal features correlated to risk stratification. A nomogram model was constructed by combining the Radscore and clinical features. The performance of the models was evaluated by ROC analysis and calibration curve. Subsequently, the model was simulated by junior doctors in order to test its practical application effect.

RESULTS

The Dice similarity coefficients of automatic meniscus segmentation models were all over 0.8. Eight optimal features, identified by LASSO regression, were employed to calculate the Radscore. The combined model showed a better performance in both the training cohort (AUC = 0.90, 95%CI: 0.84-0.95) and the validation cohort (AUC = 0.84, 95%CI: 0.72-0.93). The calibration curve indicated a better accuracy of the combined model than either the Radscore or clinical model alone. The simulation results showed that the diagnostic accuracy of junior doctors increased from 74.9 to 86.2% after using the model.

CONCLUSION

Deep learning V-net demonstrated great performance in automatic meniscus segmentation of the knee joint. It was reliable for stratifying the risk of meniscus injury of the knee by nomogram which integrated the Radscores and clinical features.

Retrospective quantification of clinical abdominal DCE-MRI using pharmacokinetics-informed deep learning: a proof-of-concept study

Introduction

Dynamic contrast-enhanced (DCE) MRI has important clinical value for early detection, accurate staging, and therapeutic monitoring of cancers. However, conventional multi-phasic abdominal DCE-MRI has limited temporal resolution and provides qualitative or semi-quantitative assessments of tissue vascularity. In this study, the feasibility of retrospectively quantifying multi-phasic abdominal DCE-MRI by using pharmacokinetics-informed deep learning to improve temporal resolution was investigated.

Method

Forty-five subjects consisting of healthy controls, pancreatic ductal adenocarcinoma (PDAC), and chronic pancreatitis (CP) were imaged with a 2-s temporal-resolution quantitative DCE sequence, from which 30-s temporal-resolution multi-phasic DCE-MRI was synthesized based on clinical protocol. A pharmacokinetics-informed neural network was trained to improve the temporal resolution of the multi-phasic DCE before the quantification of pharmacokinetic parameters. Through ten-fold cross-validation, the agreement between pharmacokinetic parameters estimated from synthesized multi-phasic DCE after deep learning inference was assessed against reference parameters from the corresponding quantitative DCE-MRI images. The ability of the deep learning estimated parameters to differentiate abnormal from normal tissues was assessed as well.

Results

The pharmacokinetic parameters estimated after deep learning have a high level of agreement with the reference values. In the cross-validation, all three pharmacokinetic parameters (transfer constant K trans , fractional extravascular extracellular volume v e , and rate constant k ep ) achieved intraclass correlation coefficient and R2 between 0.84-0.94, and low coefficients of variation (10.1%, 12.3%, and 5.6%, respectively) relative to the reference values. Significant differences were found between healthy pancreas, PDAC tumor and non-tumor, and CP pancreas.

Discussion

Retrospective quantification (RoQ) of clinical multi-phasic DCE-MRI is possible by deep learning. This technique has the potential to derive quantitative pharmacokinetic parameters from clinical multi-phasic DCE data for a more objective and precise assessment of cancer.

BreastDM: A DCE-MRI dataset for breast tumor image segmentation and classification

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has shown high sensitivity to diagnose breast cancer. However, few computer-aided algorithms focus on employing DCE-MR images for breast cancer diagnosis due to the lack of publicly available DCE-MRI datasets. To address this issue, our work releases a new DCE-MRI dataset called BreastDM for breast tumor segmentation and classification. In particular, a dataset of 232 patients selected with DCE-MR images for benign and malignant cases is established. Each case consists of three types of sequences: pre-contrast, post-contrast, and subtraction sequences. To show the difficulty of breast DCE-MRI tumor image segmentation and classification tasks, benchmarks are achieved by state-of-the-art image segmentation and classification algorithms, including conventional hand-crafted based methods and recently-emerged deep learning-based methods. More importantly, a local-global cross attention fusion network (LG-CAFN) is proposed to further improve the performance of breast tumor images classification. Specifically, LG-CAFN achieved the highest accuracy (88.20%, 83.93%) and AUC value (0.9154,0.8826) in both groups of experiments. Extensive experiments are conducted to present strong baselines based on various typical image segmentation and classification algorithms. Experiment results also demonstrate the superiority of the proposed LG-CAFN to other breast tumor images classification methods. The related dataset and evaluation codes are publicly available at smallboy-code/Breast-cancer-dataset.

Deep Learning-based Automatic Diagnosis of Breast Cancer on MRI Using Mask R-CNN for Detection Followed by ResNet50 for Classification

RATIONALE AND OBJECTIVES

Diagnosis of breast cancer on MRI requires, first, the identification of suspicious lesions; second, the characterization to give a diagnostic impression. We implemented Mask Reginal-Convolutional Neural Network (R-CNN) to detect abnormal lesions, followed by ResNet50 to estimate the malignancy probability.

MATERIALS AND METHODS

Two datasets were used. The first set had 176 cases, 103 cancer, and 73 benign. The second set had 84 cases, 53 cancer, and 31 benign. For detection, the pre-contrast image and the subtraction images of left and right breasts were used as inputs, so the symmetry could be considered. The detected suspicious area was characterized by ResNet50, using three DCE parametric maps as inputs. The results obtained using slice-based analyses were combined to give a lesion-based diagnosis.

RESULTS

In the first dataset, 101 of 103 cancers were detected by Mask R-CNN as suspicious, and 99 of 101 were correctly classified by ResNet50 as cancer, with a sensitivity of 99/103 = 96%. 48 of 73 benign lesions and 131 normal areas were identified as suspicious. Following classification by ResNet50, only 16 benign and 16 normal areas remained as malignant. The second dataset was used for independent testing. The sensitivity was 43/53 = 81%. Of the total of 121 identified non-cancerous lesions, only 6 of 31 benign lesions and 22 normal tissues were classified as malignant.

CONCLUSION

ResNet50 could eliminate approximately 80% of false positives detected by Mask R-CNN. Combining Mask R-CNN and ResNet50 has the potential to develop a fully-automatic computer-aided diagnostic system for breast cancer on MRI.

Predictive value of radiomics-based machine learning for the disease-free survival in breast cancer: a systematic review and meta-analysis

Purpose

This study summarized the previously-published studies regarding the use of radiomics-based predictive models for the identification of breast cancer-associated prognostic factors, which can help clinical decision-making and follow-up strategy.

Materials and methods

This study has been pre-registered on PROSPERO. PubMed, Embase, Cochrane Library, and Web of Science were searched, from inception to April 23, 2022, for studies that used radiomics for prognostic prediction of breast cancer patients. Then the search was updated on July 18, 2023. Quality assessment was conducted using the Radiomics Quality Score, and meta-analysis was performed using R software.

Results

A total of 975 articles were retrieved, and 13 studies were included, involving 5014 participants and 35 prognostic models. Among the models, 20 models were radiomics-based and the other 15 were based on clinical or pathological information. The primary outcome was Disease-free Survival (DFS). The retrieved studies were screened using LASSO, and Cox Regression was applied for modeling. The mean RQS was 18. The c-index of radiomics-based models for DFS prediction was 0.763 (95%CI 0.718-0.810) in the training set and 0.702 (95%CI 0.637-0.774) in the validation set. The c-index of combination models was 0.807 (95%CI0.736-0.885) in the training set and 0.840 (95%CI 0.794-0.888) in the validation set. There was no significant change in the c-index of DFS at 1, 2, 3, and over 5 years of follow-up.

Conclusion

This study has proved that radiomics-based prognostic models are of great predictive performance for the prognosis of breast cancer patients. combination model shows significantly enhanced predictive performance.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/, identifier CRD42022332392.

Intra- and peritumoral radiomics for predicting malignant BiRADS category 4 breast lesions on contrast-enhanced spectral mammography: a multicenter study

OBJECTIVE

To construct and test a nomogram based on intra- and peritumoral radiomics and clinical factors for predicting malignant BiRADS 4 lesions on contrast-enhanced spectral mammography.

METHODS

A total of 884 patients with BiRADS 4 lesions were enrolled from two centers. For each lesion, five ROIs were defined using the intratumoral region (ITR), peritumoral regions (PTRs) of 5 and 10 mm around the tumor, and ITR plus PTRs of 5 mm and 10 mm. Five radiomics signatures were established by LASSO after selecting features. A nomogram was built using selected signatures and clinical factors by multivariable logistic regression analysis. The performance of the nomogram was assessed with the AUC, decision curve analysis, and calibration curves, and also compared with the radiomics model, clinical model, and radiologists.

RESULTS

The nomogram built by three radiomics signatures (constructed from ITR, 5 mm PTR, and ITR + 10 mm PTR) and two clinical factors (age and BiRADS category) showed powerful predictive ability in internal and external test sets with AUCs of 0.907 and 0.904, respectively. The calibration curves, decision curve analysis, showed favorable predictive performance of the nomogram. In addition, radiologists improved the diagnostic performance with the help of nomogram.

CONCLUSION

The nomogram established via intratumoral and peritumoral radiomics features and clinical risk factors had the best performance in distinguishing benign and malignant BiRADS 4 lesions, which could help radiologists improve diagnostic capabilities.

KEY POINTS

• Radiomics features from peritumoral regions in contrast-enhanced spectral mammography images may provide valuable information for the diagnosis of benign and malignant breast imaging reporting and data system category 4 breast lesions. • The nomogram incorporated intra- and peritumoral radiomics features and clinical variables have good application prospects in assisting clinical decision-makers.

Deep Learning Radiomics of Preoperative Breast MRI for Prediction of Axillary Lymph Node Metastasis in Breast Cancer

The objective of this study is to develop a radiomic signature constructed from deep learning features and a nomogram for prediction of axillary lymph node metastasis (ALNM) in breast cancer patients. Preoperative magnetic resonance imaging data from 479 breast cancer patients with 488 lesions were studied. The included patients were divided into two cohorts by time (training/testing cohort, n = 366/122). Deep learning features were extracted from diffusion-weighted imaging-quantitatively measured apparent diffusion coefficient (DWI-ADC) imaging and dynamic contrast-enhanced MRI (DCE-MRI) by a pretrained neural network of DenseNet121. After the selection of both radiomic and clinicopathological features, deep learning signature and a nomogram were built for independent validation. Twenty-three deep learning features were automatically selected in the training cohort to establish the deep learning signature of ALNM. Three clinicopathological factors, including LN palpability (odds ratio (OR) = 6.04; 95% confidence interval (CI) = 3.06-12.54, P = 0.004), tumor size in MRI (OR = 1.45, 95% CI = 1.18-1.80, P = 0.104), and Ki-67 (OR = 1.01; 95% CI = 1.00-1.02, P = 0.099), were selected and combined with radiomic signature to build a combined nomogram. The nomogram showed excellent predictive ability for ALNM (AUC 0.80 and 0.71 in training and testing cohorts, respectively). The sensitivity, specificity, and accuracy were 65%, 80%, and 75%, respectively, in the testing cohort. MRI-based deep learning radiomics in patients with breast cancer could be used to predict ALNM, providing a noninvasive approach to structuring the treatment strategy.

Deep learning applications to breast cancer detection by magnetic resonance imaging: a literature review

Deep learning analysis of radiological images has the potential to improve diagnostic accuracy of breast cancer, ultimately leading to better patient outcomes. This paper systematically reviewed the current literature on deep learning detection of breast cancer based on magnetic resonance imaging (MRI). The literature search was performed from 2015 to Dec 31, 2022, using Pubmed. Other database included Semantic Scholar, ACM Digital Library, Google search, Google Scholar, and pre-print depositories (such as Research Square). Articles that were not deep learning (such as texture analysis) were excluded. PRISMA guidelines for reporting were used. We analyzed different deep learning algorithms, methods of analysis, experimental design, MRI image types, types of ground truths, sample sizes, numbers of benign and malignant lesions, and performance in the literature. We discussed lessons learned, challenges to broad deployment in clinical practice and suggested future research directions.

Deep learning-enhanced radiomics for histologic classification and grade stratification of stage IA lung adenocarcinoma: a multicenter study

Background

Preoperative prediction models for histologic subtype and grade of stage IA lung adenocarcinoma (LUAD) according to the update of the WHO Classification of Tumors of the Lung in 2021 and the 2020 new grade system are yet to be explored. We aim to develop the noninvasive pathology and grade evaluation approach for patients with stage IA LUAD via CT-based radiomics approach and evaluate their performance in clinical practice.

Methods

Chest CT scans were retrospectively collected from patients who were diagnosed with stage IA LUAD and underwent complete resection at two hospitals. A deep learning segmentation algorithm was first applied to assist lesion delineation. Expansion strategies such as bounding-box annotations were further applied. Radiomics features were then extracted and selected followed by radiomics modeling based on four classic machine learning algorithms for histologic subtype classification and grade stratification. The area under the receiver operating characteristic curve (AUC) was used to evaluate model performance.

Results

The study included 294 and 145 patients with stage IA LUAD from two hospitals for radiomics analysis, respectively. For classification of four histological subtypes, multilayer perceptron (MLP) algorithm presented no annotation strategy preference and achieved the average AUC of 0.855, 0.922, and 0.720 on internal, independent, and external test sets with 1-pixel expansion annotation. Bounding-box annotation strategy also enabled MLP an acceptable and stable accuracy among test sets. Meanwhile, logistic regression was selected for grade stratification and achieved the average AUC of 0.928, 0.837, and 0.748 on internal, independent, and external test sets with optimal annotation strategies.

Conclusions

DL-enhanced radiomics models had great potential to predict the fine histological subtypes and grades of early-stage LUADs based on CT images, which might serve as a promising noninvasive approach for the diagnosis and management of early LUADs.

Multiparametric MRI radiomics in prostate cancer for predicting Ki-67 expression and Gleason score: a multicenter retrospective study

PURPOSE

Prostate cancer (PCa) with high Ki-67 expression and high Gleason Scores (GS) tends to have aggressive clinicopathological characteristics and a dismal prognosis. In order to predict the Ki-67 expression status and the GS in PCa, we sought to construct and verify MRI-based radiomics signatures.

METHODS AND MATERIALS

We collected T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) images from 170 PCa patients at three institutions and extracted 321 original radiomic features from each image modality. We used support vector machine (SVM) and least absolute shrinkage and selection operator (LASSO) logistic regression to select the most informative radiomic features and built predictive models using up sampling and feature selection techniques. Using receiver operating characteristic (ROC) analysis, the discriminating power of this feature was determined. Subsequent decision curve analysis (DCA) assessed the clinical utility of the radiomic features. The Kaplan-Meier (KM) test revealed that the radiomics-predicted Ki-67 expression status and GS were prognostic factors for PCa survival.

RESULT

The hypothesized radiomics signature, which included 15 and 9 selected radiomics features, respectively, was significantly correlated with pathological Ki-67 and GS outcomes in both the training and validation datasets. Areas under the curve (AUC) for the developed model were 0.813 (95% CI 0.681,0.930) and 0.793 (95% CI 0.621, 0.929) for the training and validation datasets, respectively, demonstrating discrimination and calibration performance. The model's clinical usefulness was verified using DCA. In both the training and validation sets, high Ki-67 expression and high GS predicted by radiomics using SVM models were substantially linked with poor overall survival (OS).

CONCLUSIONS

Both Ki-67 expression status and high GS correlate with PCa patient survival outcomes; therefore, the ability of the SVM classifier-based model to estimate Ki-67 expression status and the Lasso classifier-based model to assess high GS may enhance clinical decision-making.

Characterization of Breast Tumors from MR Images Using Radiomics and Machine Learning Approaches

Determining histological subtypes, such as invasive ductal and invasive lobular carcinomas (IDCs and ILCs) and immunohistochemical markers, such as estrogen response (ER), progesterone response (PR), and the HER2 protein status is important in planning breast cancer treatment. MRI-based radiomic analysis is emerging as a non-invasive substitute for biopsy to determine these signatures. We explore the effectiveness of radiomics-based and CNN (convolutional neural network)-based classification models to this end. T1-weighted dynamic contrast-enhanced, contrast-subtracted T1, and T2-weighted MR images of 429 breast cancer tumors from 323 patients are used. Various combinations of input data and classification schemes are applied for ER⁺ vs. ER^-, PR⁺ vs. PR^-, HER2⁺ vs. HER2^-, and IDC vs. ILC classification tasks. The best results were obtained for the ER⁺ vs. ER^- and IDC vs. ILC classification tasks, with their respective AUCs reaching 0.78 and 0.73 on test data. The results with multi-contrast input data were generally better than the mono-contrast alone. The radiomics and CNN-based approaches generally exhibited comparable results. ER and IDC/ILC classification results were promising. PR and HER2 classifications need further investigation through a larger dataset. Better results by using multi-contrast data might indicate that multi-parametric quantitative MRI could be used to achieve more reliable classifiers.

Diagnostic value of mammography density of breast masses by using deep learning

Objective

In order to explore the relationship between mammographic density of breast mass and its surrounding area and benign or malignant breast, this paper proposes a deep learning model based on C2FTrans to diagnose the breast mass using mammographic density.

Methods

This retrospective study included patients who underwent mammographic and pathological examination. Two physicians manually depicted the lesion edges and used a computer to automatically extend and segment the peripheral areas of the lesion (0, 1, 3, and 5 mm, including the lesion). We then obtained the mammary glands' density and the different regions of interest (ROI). A diagnostic model for breast mass lesions based on C2FTrans was constructed based on a 7: 3 ratio between the training and testing sets. Finally, receiver operating characteristic (ROC) curves were plotted. Model performance was assessed using the area under the ROC curve (AUC) with 95% confidence intervals (CI), sensitivity, and specificity.

Results

In total, 401 lesions (158 benign and 243 malignant) were included in this study. The probability of breast cancer in women was positively correlated with age and mass density and negatively correlated with breast gland classification. The largest correlation was observed for age (r = 0.47). Among all models, the single mass ROI model had the highest specificity (91.8%) with an AUC = 0.823 and the perifocal 5mm ROI model had the highest sensitivity (86.9%) with an AUC = 0.855. In addition, by combining the cephalocaudal and mediolateral oblique views of the perifocal 5 mm ROI model, we obtained the highest AUC (AUC = 0.877 P < 0.001).

Conclusions

Deep learning model of mammographic density can better distinguish benign and malignant mass-type lesions in digital mammography images and may become an auxiliary diagnostic tool for radiologists in the future.

Value for combination of T1WI starVIBE with TWISTVIBE dynamic contrastenhanced MRI in distinguishing lung nodules

OBJECTIVES

With the increasing detection rate of lung nodules, the qualitative problem of lung nodules has become one of the key clinical issues. This study aims to evaluate the value of combining dynamic contrast-enhanced (DCE) MRI based on time-resolved imaging with interleaved stochastic trajectories-volume interpolated breath hold examination (TWIST-VIBE) with T1 weighted free-breathing star-volumetric interpolated breath hold examination (T1WI star-VIBE) in identifying benign and malignant lung nodules.

METHODS

We retrospectively analyzed 79 adults with undetermined lung nodules before the operation. All nodules of patients included were classified into malignant nodules (n=58) and benign nodules (n=26) based on final diagnosis. The unenhanced T1WI-VIBE, the contrast-enhanced T1WI star-VIBE, and the DCE curve based on TWIST-VIBE were performed. The corresponding qualitative [wash-in time, wash-out time, time to peak (TTP), arrival time (AT), positive enhancement integral (PEI)] and quantitative parameters [volume transfer constant (Ktrans), interstitium-to-plasma rate constant (Kep), and fractional extracellular space volume (Ve)] were evaluated. Besides, the diagnostic efficacy (sensitivity and specificity) of enhanced CT and MRI were compared.

RESULTS

There were significant differences in unenhanced T1WI-VIBE hypo-intensity, and type of A, B, C DCE curve type between benign and malignant lung nodules (all P<0.001). Pulmonary malignant nodules had a shorter wash-out time than benign nodules (P=0.001), and the differences of the remaining parameters were not statistically significant (all P>0.05). After T1WI star-VIBE contrast-enhanced MRI, the image quality was further improved. Compared with enhanced CT scan, the sensitivity (82.76% vs 80.50%) and the specificity (69.23% vs 57.10%) based on MRI were higher than that of CT (both P<0.001).

CONCLUSIONS

T1WI star-VIBE and dynamic contrast-enhanced MRI based on TWIST-VIBE were helpful to improve the image resolution and provide more information for clinical differentiation between benign and malignant lung nodules.

Application of DCE-MRI radiomics signature analysis in differentiating molecular subtypes of luminal and non-luminal breast cancer

Background

The goal of this study was to develop and validate a radiomics signature based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) preoperatively differentiating luminal and non-luminal molecular subtypes in patients with invasive breast cancer.

Methods

One hundred and thirty-five invasive breast cancer patients with luminal (n = 78) and non-luminal (n = 57) molecular subtypes were divided into training set (n = 95) and testing set (n = 40) in a 7:3 ratio. Demographics and MRI radiological features were used to construct clinical risk factors. Radiomics signature was constructed by extracting radiomics features from the second phase of DCE-MRI images and radiomics score (rad-score) was calculated. Finally, the prediction performance was evaluated in terms of calibration, discrimination, and clinical usefulness.

Results

Multivariate logistic regression analysis showed that no clinical risk factors were independent predictors of luminal and non-luminal molecular subtypes in invasive breast cancer patients. Meanwhile, the radiomics signature showed good discrimination in the training set (AUC, 0.86; 95% CI, 0.78-0.93) and the testing set (AUC, 0.80; 95% CI, 0.65-0.95).

Conclusion

The DCE-MRI radiomics signature is a promising tool to discrimination luminal and non-luminal molecular subtypes in invasive breast cancer patients preoperatively and noninvasively.

Machine learning on MRI radiomic features: identification of molecular subtype alteration in breast cancer after neoadjuvant therapy

OBJECTIVES

Recent studies have revealed the change of molecular subtypes in breast cancer (BC) after neoadjuvant therapy (NAT). This study aims to construct a non-invasive model for predicting molecular subtype alteration in breast cancer after NAT.

METHODS

Eighty-two estrogen receptor (ER)-negative/ human epidermal growth factor receptor 2 (HER2)-negative or ER-low-positive/HER2-negative breast cancer patients who underwent NAT and completed baseline MRI were retrospectively recruited between July 2010 and November 2020. Subtype alteration was observed in 21 cases after NAT. A 2D-DenseUNet machine-learning model was built to perform automatic segmentation of breast cancer. 851 radiomic features were extracted from each MRI sequence (T2-weighted imaging, ADC, DCE, and contrast-enhanced T1-weighted imaging), both in the manual and auto-segmentation masks. All samples were divided into a training set (n = 66) and a test set (n = 16). XGBoost model with 5-fold cross-validation was performed to predict molecular subtype alterations in breast cancer patients after NAT. The predictive ability of these models was subsequently evaluated by the AUC of the ROC curve, sensitivity, and specificity.

RESULTS

A model consisting of three radiomics features from the manual segmentation of multi-sequence MRI achieved favorable predictive efficacy in identifying molecular subtype alteration in BC after NAT (cross-validation set: AUC = 0.908, independent test set: AUC = 0.864); whereas an automatic segmentation approach of BC lesions on the DCE sequence produced good segmentation results (Dice similarity coefficient = 0.720).

CONCLUSIONS

A machine learning model based on baseline MRI is proven useful for predicting molecular subtype alterations in breast cancer after NAT.

KEY POINTS

• Machine learning models using MRI-based radiomics signature have the ability to predict molecular subtype alterations in breast cancer after neoadjuvant therapy, which subsequently affect treatment protocols. • The application of deep learning in the automatic segmentation of breast cancer lesions from MRI images shows the potential to replace manual segmentation..

CT-based deep learning model for the prediction of DNA mismatch repair deficient colorectal cancer: a diagnostic study

BACKGROUND

Stratification of DNA mismatch repair (MMR) status in patients with colorectal cancer (CRC) enables individual clinical treatment decision making. The present study aimed to develop and validate a deep learning (DL) model based on the pre-treatment CT images for predicting MMR status in CRC.

METHODS

1812 eligible participants (training cohort: n = 1124; internal validation cohort: n = 482; external validation cohort: n = 206) with CRC were enrolled from two institutions. All pretherapeutic CT images from three dimensions were trained by the ResNet101, then integrated by Gaussian process regression (GPR) to develop a full-automatic DL model for MMR status prediction. The predictive performance of the DL model was evaluated using the area under the receiver operating characteristic curve (AUC) and then tested in the internal and external validation cohorts. Additionally, the participants from institution 1 were sub-grouped by various clinical factors for subgroup analysis, then the predictive performance of the DL model for identifying MMR status between participants in different groups were compared.

RESULTS

The full-automatic DL model was established in the training cohort to stratify the MMR status, which presented promising discriminative ability with the AUCs of 0.986 (95% CI 0.971-1.000) in the internal validation cohort and 0.915 (95% CI 0.870-0.960) in the external validation cohort. In addition, the subgroup analysis based on the thickness of CT images, clinical T and N stages, gender, the longest diameter, and the location of tumors revealed that the DL model showed similar satisfying prediction performance.

CONCLUSIONS

The DL model may potentially serve as a noninvasive tool to facilitate the pre-treatment individualized prediction of MMR status in patients with CRC, which could promote the personalized clinical-making decision.

Clinical applications of deep learning in breast MRI

Deep learning (DL) is one of the most powerful data-driven machine-learning techniques in artificial intelligence (AI). It can automatically learn from raw data without manual feature selection. DL models have led to remarkable advances in data extraction and analysis for medical imaging. Magnetic resonance imaging (MRI) has proven useful in delineating the characteristics and extent of breast lesions and tumors. This review summarizes the current state-of-the-art applications of DL models in breast MRI. Many recent DL models were examined in this field, along with several advanced learning approaches and methods for data normalization and breast and lesion segmentation. For clinical applications, DL-based breast MRI models were proven useful in five aspects: diagnosis of breast cancer, classification of molecular types, classification of histopathological types, prediction of neoadjuvant chemotherapy response, and prediction of lymph node metastasis. For subsequent studies, further improvement in data acquisition and preprocessing is necessary, additional DL techniques in breast MRI should be investigated, and wider clinical applications need to be explored.

Intratumoral and peritumoral radiomics for preoperatively predicting the axillary non-sentinel lymph node metastasis in breast cancer on the basis of contrast-enhanced mammography: a multicenter study

OBJECTIVE

To develop and test a contrast-enhanced mammography (CEM)-based radiomics model using intratumoral and peritumoral regions to predict non-sentinel lymph node (NSLN) metastasis in breast cancer before surgery.

METHODS

This multicenter study included 365 breast cancer patients with sentinel lymph node metastasis. Intratumoral regions of interest (ROIs) were manually delineated, and peritumoral ROIs (5 and 10 mm) were automatically obtained. Five models, including intratumoral model, peritumoral (5 and 10 mm) models, and intratumoral+peritumoral (5 and 10 mm) models, were constructed by support vector machine classifier on the basis of optimal features selected by variance threshold, SelectKbest, and least absolute shrinkage and selection operator algorithms. The predictive performance of radiomics models was evaluated by receiver operating characteristic curves. An external testing set was used to test the model. The Memorial Sloan Kettering Cancer Center (MSKCC) model was used to compare the predictive performance with radiomics model.

RESULTS

The intratumoral ROI and intratumoral+peritumoral 10-mm ROI-based radiomics model achieved the best performance with an area under the curve (AUC) of 0.8000 (95% confidence interval [CI]: 0.6871-0.8266) in the internal testing set. In the external testing set, the AUC of radiomics model was 0.7567 (95% CI: 0.6717-0.8678), higher than that of MSKCC model (AUC = 0.6681, 95% CI: 0.5148-0.8213) (p = 0.361).

CONCLUSIONS

The intratumoral and peritumoral radiomics based on CEM had an acceptable predictive performance in predicting NSLN metastasis in breast cancer, which could be seen as a supplementary predicting tool to help clinicians make appropriate surgical plans.

ADVANCES IN KNOWLEDGE

The intratumoral and peritumoral CEM-based radiomics model could noninvasively predict NSLN metastasis in breast cancer patients before surgery.

Multi-algorithms analysis for pre-treatment prediction of response to transarterial chemoembolization in hepatocellular carcinoma on multiphase MRI

OBJECTIVES

This study compared the accuracy of predicting transarterial chemoembolization (TACE) outcomes for hepatocellular carcinoma (HCC) patients in the four different classifiers, and comprehensive models were constructed to improve predictive performance.

METHODS

The subjects recruited for this study were HCC patients who had received TACE treatment from April 2016 to June 2021. All participants underwent enhanced MRI scans before and after intervention, and pertinent clinical information was collected. Registry data for the 144 patients were randomly assigned to training and test datasets. The robustness of the trained models was verified by another independent external validation set of 28 HCC patients. The following classifiers were employed in the radiomics experiment: machine learning classifiers k-nearest neighbor (KNN), support vector machine (SVM), the least absolute shrinkage and selection operator (Lasso), and deep learning classifier deep neural network (DNN).

RESULTS

DNN and Lasso models were comparable in the training set, while DNN performed better in the test set and the external validation set. The CD model (Clinical & DNN merged model) achieved an AUC of 0.974 (95% CI: 0.951-0.998) in the training set, superior to other models whose AUCs varied from 0.637 to 0.943 (p < 0.05). The CD model generalized well on the test set (AUC = 0.831) and external validation set (AUC = 0.735).

CONCLUSIONS

DNN model performs better than other classifiers in predicting TACE response. Integrating with clinically significant factors, the CD model may be valuable in pre-treatment counseling of HCC patients who may benefit the most from TACE intervention.

How Radiomics Can Improve Breast Cancer Diagnosis and Treatment

Recent technological advances in the field of artificial intelligence hold promise in addressing medical challenges in breast cancer care, such as early diagnosis, cancer subtype determination and molecular profiling, prediction of lymph node metastases, and prognostication of treatment response and probability of recurrence. Radiomics is a quantitative approach to medical imaging, which aims to enhance the existing data available to clinicians by means of advanced mathematical analysis using artificial intelligence. Various published studies from different fields in imaging have highlighted the potential of radiomics to enhance clinical decision making. In this review, we describe the evolution of AI in breast imaging and its frontiers, focusing on handcrafted and deep learning radiomics. We present a typical workflow of a radiomics analysis and a practical "how-to" guide. Finally, we summarize the methodology and implementation of radiomics in breast cancer, based on the most recent scientific literature to help researchers and clinicians gain fundamental knowledge of this emerging technology. Alongside this, we discuss the current limitations of radiomics and challenges of integration into clinical practice with conceptual consistency, data curation, technical reproducibility, adequate accuracy, and clinical translation. The incorporation of radiomics with clinical, histopathological, and genomic information will enable physicians to move forward to a higher level of personalized management of patients with breast cancer.

The utilization of artificial intelligence applications to improve breast cancer detection and prognosis

Breast imaging faces challenges with the current increase in medical imaging requests and lesions that breast screening programs can miss. Solutions to improve these challenges are being sought with the recent advancement and adoption of artificial intelligent (AI)-based applications to enhance workflow efficiency as well as patient-healthcare outcomes. rtificial intelligent tools have been proposed and used to analyze different modes of breast imaging, in most of the published studies, mainly for the detection and classification of breast lesions, breast lesion segmentation, breast density evaluation, and breast cancer risk assessment. This article reviews the background of the Conventional Computer-aided Detection system and AI, AI-based applications in breast medical imaging for the identification, segmentation, and categorization of lesions, breast density and cancer risk evaluation. In addition, the challenges, and limitations of AI-based applications in breast imaging are also discussed.

Fully automatic classification of breast lesions on multi-parameter MRI using a radiomics model with minimal number of stable, interpretable features

PURPOSE

To build an automatic computer-aided diagnosis (CAD) pipeline based on multiparametric magnetic resonance imaging (mpMRI) and explore the role of different imaging features in the classification of breast cancer.

MATERIALS AND METHODS

A total of 222 histopathology-confirmed breast lesions, together with their BI-RADS scores, were included in the analysis. The cohort was randomly split into training (159) and test (63) cohorts, and another 50 lesions were collected as an external cohort. An nnUNet-based lesion segmentation model was trained to automatically segment lesion ROI, from which radiomics features were extracted for diffusion-weighted imaging (DWI), T2-weighted imaging (T2WI), and contrast-enhanced (DCE) pharmacokinetic parametric maps. Models based on combinations of sequences were built using support vector machine (SVM) and logistic regression (LR). Also, the performance of these sequence combinations and BI-RADS scores were compared. The Dice coefficient and AUC were calculated  to evaluate the segmentation and classification results. Decision curve analysis (DCA) was used to assess clinical utility.

RESULTS

The segmentation model achieved a Dice coefficient of 0.831 in the test cohort. The radiomics model used only three features from diffusion coefficient (ADC) images, T2WI, and DCE-derived kinetic mapping, and achieved an AUC of 0.946 [0.883-0.990], AUC of 0.842 [0.6856-0.998] in the external cohort, which was higher than the BI-RADS score with an AUC of 0.872 [0.752-0.975]. The joint model using both radiomics score and BI-RADS score achieved the highest test AUC of 0.975 [0.935-1.000], with a sensitivity of 0.920 and a specificity of 0.923.

CONCLUSION

Three radiomics features can be used to construct an automatic radiomics-based pipeline to improve the diagnosis of breast lesions and reduce unnecessary biopsies, especially when using jointly with BI-RADS scores.

Personalized intrahepatic cholangiocarcinoma prognosis prediction using radiomics: Application and development trend

Radiomics was proposed by Lambin et al. in 2012 and since then there has been an explosion of related research. There has been significant interest in developing high-throughput methods that can automatically extract a large number of quantitative image features from medical images for better diagnostic or predictive performance. There have also been numerous radiomics investigations on intrahepatic cholangiocarcinoma in recent years, but no pertinent review materials are readily available. This work discusses the modeling analysis of radiomics for the prediction of lymph node metastasis, microvascular invasion, and early recurrence of intrahepatic cholangiocarcinoma, as well as the use of deep learning. This paper briefly reviews the current status of radiomics research to provide a reference for future studies.

Magnetic resonance imaging analysis of embryonal rhabdomyosarcoma of the prostate

BACKGROUND

Rhabdomyosarcoma (RMS) is a highly malignant tumor that originates from myogenic progenitor cells.

OBJECTIVE

To investigate the magnetic resonance imaging (MRI) characteristics of prostate embryonal rhabdomyosarcoma (ERMS).

METHODS

We retrospectively analyzed the clinical and MRI imaging data of 9 cases of prostate ERMS that were confirmed pathologically. The patients were aged between 14∼49 years with a median age of 27 years, and they all underwent MRI, diffusion-weighted imaging (DWI), and dynamic contrast-enhanced MRI (DCE-MRI).

RESULTS

The MRI scan of the lesions showed an irregular shape, mixed signals, uneven equal/long T1 signal and an equal/long T2 signal, cystic necrosis in 9 cases and hemorrhage in 6 cases; DWI and ADC images showed a mixed high/low signal, and the tumor parenchyma showed ADC low signal, with an average ADC value of 0.666 × 10-3 mm2/s. There were 5 cases of DCE-MRI TIC type II and 4 cases of DCE-MRI TIC type I. The average value of Tpeak was 120 s and the average value of MCER was 172.3%. After the enhancement, the signal of tumor enhancement was uneven, and showed patchy and reticular enhancement, however, the cyst degeneration, necrosis area, and hemorrhage focus were not enhanced. There were 3 cases with multiple pelvic lymph nodes and 1 case with multiple bone metastases.

CONCLUSION

The MRI manifestations of prostate ERMS have certain characteristics, and the combination of DWI and DCE-MRI are helpful in the diagnosis.

Research on automatic classification technology of kidney tumor and normal kidney tissue based on computed tomography radiomics

Purpose

By using a radiomics-based approach, multiple radiomics features can be extracted from regions of interest in computed tomography (CT) images, which may be applied to automatically classify kidney tumors and normal kidney tissues. The study proposes a method based on CT radiomics and aims to use extracted radiomics features to automatically classify of kidney tumors and normal kidney tissues and to establish an automatic classification model.

Methods

CT data were retrieved from the 2019 Kidney and Kidney Tumor Segmentation Challenge (KiTS19) in The Cancer Imaging Archive (TCIA) open access database. Arterial phase-enhanced CT images from 210 cases were used to establish an automatic classification model. These CT images of patients were randomly divided into training (168 cases) and test (42 cases) sets. Furthermore, the radiomics features of gross tumor volume (GTV) and normal kidney tissues in the training set were extracted and screened, and a binary logistic regression model was established. For the test set, the radiomic features and cutoff value of P were consistent with the training set.

Results

Three radiomics features were selected to establish the binary logistic regression model. The accuracy (ACC), sensitivity (SENS), specificity (SPEC), area under the curve (AUC), and Youden index of the training and test sets based on the CT radiomics classification model were all higher than 0.85.

Conclusion

The automatic classification model of kidney tumors and normal kidney tissues based on CT radiomics exhibited good classification ability. Kidney tumors could be distinguished from normal kidney tissues. This study may complement automated tumor delineation techniques and warrants further research.

Pathological Diagnosis of Adult Craniopharyngioma on MR Images: An Automated End-to-End Approach Based on Deep Neural Networks Requiring No Manual Segmentation

PURPOSE

The goal of this study was to develop end-to-end convolutional neural network (CNN) models that can noninvasively discriminate papillary craniopharyngioma (PCP) from adamantinomatous craniopharyngioma (ACP) on MR images requiring no manual segmentation.

MATERIALS AND METHODS

A total of 97 patients diagnosed with ACP or PCP were included. Pretreatment contrast-enhanced T1-weighted images were collected and used as the input of the CNNs. Six models were established based on six networks, including VGG16, ResNet18, ResNet50, ResNet101, DenseNet121, and DenseNet169. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were used to assess the performances of these deep neural networks. A five-fold cross-validation was applied to evaluate the performances of the models.

RESULTS

The six networks yielded feasible performances, with area under the receiver operating characteristic curves (AUCs) of at least 0.78 for classification. The model based on Resnet50 achieved the highest AUC of 0.838 ± 0.062, with an accuracy of 0.757 ± 0.052, a sensitivity of 0.608 ± 0.198, and a specificity of 0.845 ± 0.034, respectively. Moreover, the results also indicated that the CNN method had a competitive performance compared to the radiomics-based method, which required manual segmentation for feature extraction and further feature selection.

CONCLUSIONS

MRI-based deep neural networks can noninvasively differentiate ACP from PCP to facilitate the personalized assessment of craniopharyngiomas.

Diagnosis of architectural distortion on digital breast tomosynthesis using radiomics and deep learning

Purpose

To implement two Artificial Intelligence (AI) methods, radiomics and deep learning, to build diagnostic models for patients presenting with architectural distortion on Digital Breast Tomosynthesis (DBT) images.

Materials and Methods

A total of 298 patients were identified from a retrospective review, and all of them had confirmed pathological diagnoses, 175 malignant and 123 benign. The BI-RADS scores of DBT were obtained from the radiology reports, classified into 2, 3, 4A, 4B, 4C, and 5. The architectural distortion areas on craniocaudal (CC) and mediolateral oblique (MLO) views were manually outlined as the region of interest (ROI) for the radiomics analysis. Features were extracted using PyRadiomics, and then the support vector machine (SVM) was applied to select important features and build the classification model. Deep learning was performed using the ResNet50 algorithm, with the binary output of malignancy and benignity. The Gradient-weighted Class Activation Mapping (Grad-CAM) method was utilized to localize the suspicious areas. The predicted malignancy probability was used to construct the ROC curves, compared by the DeLong test. The binary diagnosis was made using the threshold of ≥ 0.5 as malignant.

Results

The majority of malignant lesions had BI-RADS scores of 4B, 4C, and 5 (148/175 = 84.6%). In the benign group, a substantial number of patients also had high BI-RADS ≥ 4B (56/123 = 45.5%), and the majority had BI-RADS ≥ 4A (102/123 = 82.9%). The radiomics model built using the combined CC+MLO features yielded an area under curve (AUC) of 0.82, the sensitivity of 0.78, specificity of 0.68, and accuracy of 0.74. If only features from CC were used, the AUC was 0.77, and if only features from MLO were used, the AUC was 0.72. The deep-learning model yielded an AUC of 0.61, significantly lower than all radiomics models (p<0.01), which was presumably due to the use of the entire image as input. The Grad-CAM could localize the architectural distortion areas.

Conclusion

The radiomics model can achieve a satisfactory diagnostic accuracy, and the high specificity in the benign group can be used to avoid unnecessary biopsies. Deep learning can be used to localize the architectural distortion areas, which may provide an automatic method for ROI delineation to facilitate the development of a fully-automatic computer-aided diagnosis system using combined AI strategies.

Intra- and peri-tumoral radiomics for predicting the sentinel lymph node metastasis in breast cancer based on preoperative mammography and MRI

Purpose

This study aims to investigate values of intra- and peri-tumoral regions in the mammography and magnetic resonance imaging (MRI) image for prediction of sentinel lymph node metastasis (SLNM) in invasive breast cancer (BC).

Methods

This study included 208 patients with invasive BC between Spe. 2017 and Apr. 2021. All patients underwent preoperative digital mammography (DM), digital breast tomosynthesis (DBT), dynamic contrast-enhanced MRI (DCE-MRI) and diffusion-weighted MRI (DWI) scans. Radiomics features were extracted from manually outlined intratumoral regions, and automatically dilated peritumoral tumor regions in each modality. The least absolute shrinkage and selection operator (LASSO) regression was used to select key features from each region to develop radiomics signatures (RSs). Area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity and negative predictive value (NPV) were calculated to evaluate performance of the RSs.

Results

Intra- and peri-tumoral regions of BC can provide complementary information on the SLN status. In each modality, the Com-RSs derived from combined intra- and peri-tumoral regions always yielded higher AUCs than the Intra-RSs or Peri-RSs. A total of 10 and 11 features were identified as the most important predictors from mammography (DM plus DBT) and MRI (DCE-MRI plus DWI), respectively. The DCE-MRI plus DWI generated higher AUCs compared with DM plus DBT in the training (AUCs, DCE-MRI plus DWI vs. DM plus DBT, 0.897 vs. 0.846) and validation (AUCs, DCE-MRI plus DWI vs. DM plus DBT, 0.826 vs. 0.786) cohort.

Conclusions

Radiomics features from intra- and peri-tumoral regions can provide complementary information to identify the SLNM in both mammography and MRI. The DCE-MRI plus DWI generated lower specificity, but higher AUC, accuracy, sensitivity and negative predictive value compared with DM plus DBT.

Feasibility of using AI to auto-catch responsible frames in ultrasound screening for breast cancer diagnosis

The research of AI-assisted breast diagnosis has primarily been based on static images. It is unclear whether it represents the best diagnosis image.To explore the method of capturing complementary responsible frames from breast ultrasound screening by using artificial intelligence. We used feature entropy breast network (FEBrNet) to select responsible frames from breast ultrasound screenings and compared the diagnostic performance of AI models based on FEBrNet-recommended frames, physician-selected frames, 5-frame interval-selected frames, all frames of video, as well as that of ultrasound and mammography specialists. The AUROC of AI model based on FEBrNet-recommended frames outperformed other frame set based AI models, as well as ultrasound and mammography physicians, indicating that FEBrNet can reach level of medical specialists in frame selection.FEBrNet model can extract video responsible frames for breast nodule diagnosis, whose performance is equivalent to the doctors selected responsible frames.

Deep learning and radiomics to predict the mitotic index of gastrointestinal stromal tumors based on multiparametric MRI

Introduction

Preoperative evaluation of the mitotic index (MI) of gastrointestinal stromal tumors (GISTs) represents the basis of individualized treatment of patients. However, the accuracy of conventional preoperative imaging methods is limited. The aim of this study was to develop a predictive model based on multiparametric MRI for preoperative MI prediction.

Methods

A total of 112 patients who were pathologically diagnosed with GIST were enrolled in this study. The dataset was subdivided into the development (n = 81) and test (n = 31) sets based on the time of diagnosis. With the use of T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) map, a convolutional neural network (CNN)-based classifier was developed for MI prediction, which used a hybrid approach based on 2D tumor images and radiomics features from 3D tumor shape. The trained model was tested on an internal test set. Then, the hybrid model was comprehensively tested and compared with the conventional ResNet, shape radiomics classifier, and age plus diameter classifier.

Results

The hybrid model showed good MI prediction ability at the image level; the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and accuracy in the test set were 0.947 (95% confidence interval [CI]: 0.927-0.968), 0.964 (95% CI: 0.930-0.978), and 90.8 (95% CI: 88.0-93.0), respectively. With the average probabilities from multiple samples per patient, good performance was also achieved at the patient level, with AUROC, AUPRC, and accuracy of 0.930 (95% CI: 0.828-1.000), 0.941 (95% CI: 0.792-1.000), and 93.6% (95% CI: 79.3-98.2) in the test set, respectively.

Discussion

The deep learning-based hybrid model demonstrated the potential to be a good tool for the operative and non-invasive prediction of MI in GIST patients.

Evaluation of the peritumoral features using radiomics and deep learning technology in non-spiculated and noncalcified masses of the breast on mammography

OBJECTIVE

To assess the significance of peritumoral features based on deep learning in classifying non-spiculated and noncalcified masses (NSNCM) on mammography.

METHODS

We retrospectively screened the digital mammography data of 2254 patients who underwent surgery for breast lesions in Harbin Medical University Cancer Hospital from January to December 2018. Deep learning and radiomics models were constructed. The classification efficacy in ROI and patient levels of AUC, accuracy, sensitivity, and specificity were compared. Stratified analysis was conducted to analyze the influence of primary factors on the AUC of the deep learning model. The image filter and CAM were used to visualize the radiomics and depth features.

RESULTS

For 1298 included patients, 771 (59.4%) were benign, and 527 (40.6%) were malignant. The best model was the deep learning combined model (2 mm), in which the AUC was 0.884 (P < 0.05); especially the AUC of breast composition B reached 0.941. All the deep learning models were superior to the radiomics models (P < 0.05), and the class activation map (CAM) showed a high expression of signals around the tumor of the deep learning model. The deep learning model achieved higher AUC for large size, age >60 years, and breast composition type B (P < 0.05).

CONCLUSION

Combining the tumoral and peritumoral features resulted in better identification of malignant NSNCM on mammography, and the performance of the deep learning model exceeded the radiomics model. Age, tumor size, and the breast composition type are essential for diagnosis.

Predicting hormone receptors and PAM50 subtypes of breast cancer from multi-scale lesion images of DCE-MRI with transfer learning technique

BACKGROUND

The recent development of artificial intelligence (AI) technologies coupled with medical imaging data has gained considerable attention, and offers a non-invasive approach for cancer diagnosis and prognosis. In this context, improved breast cancer (BC) molecular characteristics assessment models are foreseen to enable personalized strategies with better clinical outcomes compared to existing screening strategies. And it is a promising approach to developing models for hormone receptors (HR) and subtypes of BC patients from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data.

METHODS

In this institutional review board-approved study, 174 BC patients with both DCE-MRI and RNA-seq data in the local database were analyzed. Slice images from tumor lesions and multi-scale peri-tumor regions were used as model inputs, and five representative pre-trained transfer learning (TF) networks, such as Inception-v3 and Xception, were employed to establish prediction models. A comprehensive analysis was performed using five-fold cross-validation to avoid overfitting, and accuracy (ACC) and area under the receiver operating characteristic curve (AUROC) to evaluate model performance.

RESULTS

Xception achieved the superior results when using solely tumor regions, with highest AUROCs of 0.844 (95% CI: [0.841, 0.847]) and 0.784 (95% CI: [0.781, 0.788]) for estrogen receptor (ER) and progesterone receptor (PR), respectively, and best ACC of 0.467 (95% CI: [0.462, 0.470]) for PAM50 subtypes. A significant improvement in the model performance was observed when images of the peri-tumor region were included, with optimal results achieved using images of the tumor and the 10 mm peri-tumor regions. Xception-based TF models performed most effectively in predicting ER and PR statuses, with the AUROCs were 0.942 (95% CI: [0.940, 0.944]) and 0.920 (95% CI: [0.917, 0.922]), respectively, whereas for PAM50 subtypes, the Inception-v3-based network yielded the highest ACC as 0.742 (95% CI: [0.738, 0.746]).

CONCLUSIONS

Transfer learning analysis based on DCE-MRI data of tumor and peri-tumor regions was helpful to the non-invasive assessment of molecular characteristics of BC.