Machine learning in breast MRI

A feature fusion method based on radiomic features and revised deep features for improving tumor prediction in ultrasound images

BACKGROUND

Radiomic features and deep features are both vitally helpful for the accurate prediction of tumor information in breast ultrasound. However, whether integrating radiomic features and deep features can improve the prediction performance of tumor information is unclear.

METHODS

A feature fusion method based on radiomic features and revised deep features was proposed to predict tumor information. Radiomic features were extracted from the tumor region on ultrasound images, and the optimal radiomic features were subsequently selected based on Gini score. Revised deep features, which were extracted using the revised CNN models integrating prior information, were combined with radiomic features to build a logistic regression classifier for tumor prediction. The performance was evaluated using area under the receiver operating characteristic (ROC) curve (AUC).

RESULTS

The results showed that the proposed feature fusion method (AUC = 0.9845) obtained better prediction performance than that based on radiomic features (AUC = 0.9796) or deep features (AUC = 0.9342).

CONCLUSIONS

Our results demonstrate that the proposed feature fusion framework integrating the radiomic features and revised deep features is an efficient method to improve the prediction performance of tumor information.

Clinical Applications of Artificial Intelligence (AI) in Human Cancer: Is It Time to Update the Diagnostic and Predictive Models in Managing Hepatocellular Carcinoma (HCC)?

In recent years, novel findings have progressively and promisingly supported the potential role of Artificial intelligence (AI) in transforming the management of various neoplasms, including hepatocellular carcinoma (HCC). HCC represents the most common primary liver cancer. Alarmingly, the HCC incidence is dramatically increasing worldwide due to the simultaneous "pandemic" spreading of metabolic dysfunction-associated steatotic liver disease (MASLD). MASLD currently constitutes the leading cause of chronic hepatic damage (steatosis and steatohepatitis), fibrosis, and liver cirrhosis, configuring a scenario where an HCC onset has been reported even in the early disease stage. On the other hand, HCC represents a serious plague, significantly burdening the outcomes of chronic hepatitis B (HBV) and hepatitis C (HCV) virus-infected patients. Despite the recent progress in the management of this cancer, the overall prognosis for advanced-stage HCC patients continues to be poor, suggesting the absolute need to develop personalized healthcare strategies further. In this "cold war", machine learning techniques and neural networks are emerging as weapons, able to identify the patterns and biomarkers that would have normally escaped human observation. Using advanced algorithms, AI can analyze large volumes of clinical data and medical images (including routinely obtained ultrasound data) with an elevated accuracy, facilitating early diagnosis, improving the performance of predictive models, and supporting the multidisciplinary (oncologist, gastroenterologist, surgeon, radiologist) team in opting for the best "tailored" individual treatment. Additionally, AI can significantly contribute to enhancing the effectiveness of metabolomics-radiomics-based models, promoting the identification of specific HCC-pathogenetic molecules as new targets for realizing novel therapeutic regimens. In the era of precision medicine, integrating AI into routine clinical practice appears as a promising frontier, opening new avenues for liver cancer research and treatment.

Application of machine learning in the analysis of multiparametric MRI data for the differentiation of treatment responses in breast cancer: retrospective study

OBJECTIVE

The objective of this study is to develop and validate a multiparametric MRI model employing machine learning to predict the effectiveness of treatment and the stage of breast cancer.

METHODS

The study encompassed 400 female patients diagnosed with breast cancer, with 200 individuals allocated to both the control and experimental groups, undergoing examinations in Shenzhen, China, during the period 2017-2023. This study pertains to retrospective research. Multiparametric MRI was employed to extract data concerning tumor size, blood flow, and metabolism.

RESULTS

The model achieved high accuracy, predicting treatment outcomes with an accuracy of 92%, sensitivity of 88%, and specificity of 95%. The model effectively classified breast cancer stages: stage I, 38% ( P  = 0.027); stage II, 72% ( P  = 0.014); stage III, 50% ( P  = 0.032); and stage IV, 45% ( P  = 0.041).

CONCLUSIONS

The developed model, utilizing multiparametric MRI and machine learning, exhibits high accuracy in predicting the effectiveness of treatment and breast cancer staging. These findings affirm the model's potential to enhance treatment strategies and personalize approaches for patients diagnosed with breast cancer. Our study presents an innovative approach to the diagnosis and treatment of breast cancer, integrating MRI data with machine learning algorithms. We demonstrate that the developed model exhibits high accuracy in predicting treatment efficacy and differentiating cancer stages. This underscores the importance of utilizing MRI and machine learning algorithms to enhance the diagnosis and individualization of treatment for this disease.

Harnessing the power of machine learning into tissue engineering: current progress and future prospects

Tissue engineering is a discipline based on cell biology and materials science with the primary goal of rebuilding and regenerating lost and damaged tissues and organs. Tissue engineering has developed rapidly in recent years, while scaffolds, growth factors, and stem cells have been successfully used for the reconstruction of various tissues and organs. However, time-consuming production, high cost, and unpredictable tissue growth still need to be addressed. Machine learning is an emerging interdisciplinary discipline that combines computer science and powerful data sets, with great potential to accelerate scientific discovery and enhance clinical practice. The convergence of machine learning and tissue engineering, while in its infancy, promises transformative progress. This paper will review the latest progress in the application of machine learning to tissue engineering, summarize the latest applications in biomaterials design, scaffold fabrication, tissue regeneration, and organ transplantation, and discuss the challenges and future prospects of interdisciplinary collaboration, with a view to providing scientific references for researchers to make greater progress in tissue engineering and machine learning.

Radiomics-based predictive model for preoperative risk classification of gastrointestinal stromal tumors using multiparametric magnetic resonance imaging: a retrospective study

OBJECTIVE

The aim of this study was to develop and assess a radiomics model utilizing multiparametric magnetic resonance imaging (MRI) for the prediction of preoperative risk assessment in gastrointestinal stromal tumors (GISTs).

MATERIAL AND METHODS

An analysis was performed retrospectively on a group of 121 patients who received a histological diagnosis of GIST. They were then divided into two sets, with 85 in the training set and 36 in the validation set through random partitioning. Radiomics features from five MRI sequences, totaling 600 per patient, were extracted and subjected to feature selection utilizing a random forest algorithm. The discriminatory efficacy of the models was evaluated through receiver operating characteristic (ROC) and precision-recall (P-R) curve analyses. Model calibration was assessed via calibration curves. Subgroup analysis was performed on GISTs with a pathological maximum diameter equal to or less than 5 cm. Furtherly, Kaplan-Meier (K-M) curves and log-rank tests were used to compare the differences in survival status among different groups. Cox regression analysis was employed to identify independent prognostic factors and to construct a prognostic prediction model.

RESULTS

The clinical model (ModelC) displayed limited predictive efficacy in the context of GIST. Conversely, a radiomics model (ModelR) incorporating five parameters exhibited robust discriminative capabilities across both the training and validation sets, yielding area under the ROC curve (AUC) values of 0.893 (95% confidence interval [CI]: 0.807-0.949) and 0.855 (95% CI: 0.732-0.978), respectively. The F1max scores derived from the P‑R curves were 0.741 and 0.842 for the training and validation sets, respectively. Noteworthy was the exclusion of the two-dimensional tumor diameter and tumor location when constructing a hybrid model (ModelCR) that amalgamated radiomics and clinical features. ModelR demonstrated a substantially enhanced discriminative capacity in the training set compared with ModelC (p < 0.005). The net reclassification improvement (NRI) corroborated the superior performance of ModelR over ModelC, thereby enhancing diagnostic accuracy and clinical applicability. Patients in the high-risk group had significantly worse recurrence-free survival (RFS, p < 0.001) and overall survival (OS, p = 0.004), and the radiomics signature is an independent risk factor for RFS. The extended model incorporating the radiomics signature outperformed the baseline model in terms of risk assessment accuracy (p < 0.001).

CONCLUSION

Our investigation underscores the value of integrating radiomics analysis in conjunction with machine learning algorithms for prognostic risk stratification in GIST, presenting promising implications for informing clinical decision-making processes as well as optimizing management strategies.

A systematic review on artificial intelligence evaluating PSMA PET scan for intraprostatic cancer

OBJECTIVES

To assess artificial intelligence (AI) ability to evaluate intraprostatic prostate cancer (PCa) on prostate-specific membrane antigen positron emission tomography (PSMA PET) scans prior to active treatment (radiotherapy or prostatectomy).

MATERIALS AND METHODS

This systematic review was registered on the International Prospective Register of Systematic Reviews (PROSPERO identifier: CRD42023438706). A search was performed on Medline, Embase, Web of Science, and Engineering Village with the following terms: 'artificial intelligence', 'prostate cancer', and 'PSMA PET'. All articles published up to February 2024 were considered. Studies were included if patients underwent PSMA PET scan to evaluate intraprostatic lesions prior to active treatment. The two authors independently evaluated titles, abstracts, and full text. The Prediction model Risk Of Bias Assessment Tool (PROBAST) was used.

RESULTS

Our search yield 948 articles, of which 14 were eligible for inclusion. Eight studies met the primary endpoint of differentiating high-grade PCa. Differentiating between International Society of Urological Pathology (ISUP) Grade Group (GG) ≥3 PCa had an accuracy between 0.671 to 0.992, sensitivity of 0.91, specificity of 0.35. Differentiating ISUP GG ≥4 PCa had an accuracy between 0.83 and 0.88, sensitivity was 0.89, specificity was 0.87. AI could identify non-PSMA-avid lesions with an accuracy of 0.87, specificity of 0.85, and specificity of 0.89. Three studies demonstrated ability of AI to detect extraprostatic extensions with an area under curve between 0.70 and 0.77. Lastly, AI can automate segmentation of intraprostatic lesion and measurement of gross tumour volume.

CONCLUSION

Although the current state of AI differentiating high-grade PCa is promising, it remains experimental and not ready for routine clinical application. Benefits of using AI to assess intraprostatic lesions on PSMA PET scans include: local staging, identifying otherwise radiologically occult lesions, standardisation and expedite reporting of PSMA PET scans. Larger, prospective, multicentre studies are needed.

Re-attendance in supplemental breast MRI screening rounds of the DENSE trial for women with extremely dense breasts

OBJECTIVES

Supplemental MRI screening improves early breast cancer detection and reduces interval cancers in women with extremely dense breasts in a cost-effective way. Recently, the European Society of Breast Imaging recommended offering MRI screening to women with extremely dense breasts, but the debate on whether to implement it in breast cancer screening programs is ongoing. Insight into the participant experience and willingness to re-attend is important for this discussion.

METHODS

We calculated the re-attendance rates of the second and third MRI screening rounds of the DENSE trial. Moreover, we calculated age-adjusted odds ratios (ORs) to study the association between characteristics and re-attendance. Women who discontinued MRI screening were asked to provide one or more reasons for this.

RESULTS

The re-attendance rates were 81.3% (3458/4252) and 85.2% (2693/3160) in the second and third MRI screening round, respectively. A high age (> 65 years), a very low BMI, lower education, not being employed, smoking, and no alcohol consumption were correlated with lower re-attendance rates. Moderate or high levels of pain, discomfort, or anxiety experienced during the previous MRI screening round were correlated with lower re-attendance rates. Finally, a plurality of women mentioned an examination-related inconvenience as a reason to discontinue screening (39.1% and 34.8% in the second and third screening round, respectively).

CONCLUSIONS

The willingness of women with dense breasts to re-attend an ongoing MRI screening study is high. However, emphasis should be placed on improving the MRI experience to increase the re-attendance rate if widespread supplemental MRI screening is implemented.

CLINICAL RELEVANCE STATEMENT

For many women, MRI is an acceptable screening method, as re-attendance rates were high - even for screening in a clinical trial setting. To further enhance the (re-)attendance rate, one possible approach could be improving the overall MRI experience.

KEY POINTS

• The willingness to re-attend in an ongoing MRI screening study is high. • Pain, discomfort, and anxiety in the previous MRI screening round were related to lower re-attendance rates. • Emphasis should be placed on improving MRI experience to increase the re-attendance rate in supplemental MRI screening.

Automated Breast Density Assessment in MRI Using Deep Learning and Radiomics: Strategies for Reducing Inter-Observer Variability

BACKGROUND

Accurate breast density evaluation allows for more precise risk estimation but suffers from high inter-observer variability.

PURPOSE

To evaluate the feasibility of reducing inter-observer variability of breast density assessment through artificial intelligence (AI) assisted interpretation.

STUDY TYPE

Retrospective.

POPULATION

Six hundred and twenty-one patients without breast prosthesis or reconstructions were randomly divided into training (N = 377), validation (N = 98), and independent test (N = 146) datasets.

FIELD STRENGTH/SEQUENCE

1.5 T and 3.0 T; T1-weighted spectral attenuated inversion recovery.

ASSESSMENT

Five radiologists independently assessed each scan in the independent test set to establish the inter-observer variability baseline and to reach a reference standard. Deep learning and three radiomics models were developed for three classification tasks: (i) four Breast Imaging-Reporting and Data System (BI-RADS) breast composition categories (A-D), (ii) dense (categories C, D) vs. non-dense (categories A, B), and (iii) extremely dense (category D) vs. moderately dense (categories A-C). The models were tested against the reference standard on the independent test set. AI-assisted interpretation was performed by majority voting between the models and each radiologist's assessment.

STATISTICAL TESTS

Inter-observer variability was assessed using linear-weighted kappa (κ) statistics. Kappa statistics, accuracy, and area under the receiver operating characteristic curve (AUC) were used to assess models against reference standard.

RESULTS

In the independent test set, five readers showed an overall substantial agreement on tasks (i) and (ii), but moderate agreement for task (iii). The best-performing model showed substantial agreement with reference standard for tasks (i) and (ii), but moderate agreement for task (iii). With the assistance of the AI models, almost perfect inter-observer variability was obtained for tasks (i) (mean κ = 0.86), (ii) (mean κ = 0.94), and (iii) (mean κ = 0.94).

DATA CONCLUSION

Deep learning and radiomics models have the potential to help reduce inter-observer variability of breast density assessment.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 1.

Multiparametric MRI-based radiomic nomogram for predicting HER-2 2+ status of breast cancer

Objective

To explore the application of multiparametric MRI-based radiomic nomogram for assessing HER-2 2+ status of breast cancer (BC).

Methods

Patients with pathology-proven HER-2 2+ invasive BC, who underwent preoperative MRI were divided into training (72 patients, 21 HER-2-positive and 51 HER-2-negative) and validation (32 patients, 9 HER-2-positive and 23 HER-2-negative) sets by randomization. All were classified as HER-2 2+ FISH-positive (HER-2-positive) or -negative (HER-2-negative) according to IHC and FISH. The 3D VOI was drawn on MR images by two radiologists. ADC, T2WI, and DCE images were analyzed separately to extract features (n = 1906). L1 regularization, F-test, and other methods were used to reduce dimensionality. Binary radiomics prediction models using features from single or combined imaging sequences were constructed using logistic regression (LR) classifier then and validated on a validation dataset. To build a radiomics nomogram, multivariate LR analysis was conducted to identify independent indicators. An evaluation of the model's predictive efficacy was made using AUC.

Results

On the basis of combined ADC, T2WI, and DCE images, ten radiomic features were extracted following feature dimensionality reduction. There was superior diagnostic efficiency of radiomic signature using all three sequences compared to either one or two sequences (AUC for training group: 0.883; AUC for validation group: 0.816). Based on multivariate LR analysis, radiomic signature and peritumoral edema were independent predictors for identifying HER-2 2 +. In both training and validation datasets, nomograms combining peritumoral edema and radiomics signature demonstrated an effective discrimination (AUCs were respectively 0.966 and 0. 884).

Conclusion

The nomogram that incorporated peritumoral edema and multiparametric MRI-based radiomic signature can be used to effectively predict the HER-2 2+ status of BC.

A Review of Machine Learning Algorithms for Biomedical Applications

As the amount and complexity of biomedical data continue to increase, machine learning methods are becoming a popular tool in creating prediction models for the underlying biomedical processes. Although all machine learning methods aim to fit models to data, the methodologies used can vary greatly and may seem daunting at first. A comprehensive review of various machine learning algorithms per biomedical applications is presented. The key concepts of machine learning are supervised and unsupervised learning, feature selection, and evaluation metrics. Technical insights on the major machine learning methods such as decision trees, random forests, support vector machines, and k-nearest neighbors are analyzed. Next, the dimensionality reduction methods like principal component analysis and t-distributed stochastic neighbor embedding methods, and their applications in biomedical data analysis were reviewed. Moreover, in biomedical applications predominantly feedforward neural networks, convolutional neural networks, and recurrent neural networks are utilized. In addition, the identification of emerging directions in machine learning methodology will serve as a useful reference for individuals involved in biomedical research, clinical practice, and related professions who are interested in understanding and applying machine learning algorithms in their research or practice.

Artificial Intelligence-Enhanced Breast MRI: Applications in Breast Cancer Primary Treatment Response Assessment and Prediction

ABSTRACT

Primary systemic therapy (PST) is the treatment of choice in patients with locally advanced breast cancer and is nowadays also often used in patients with early-stage breast cancer. Although imaging remains pivotal to assess response to PST accurately, the use of imaging to predict response to PST has the potential to not only better prognostication but also allow the de-escalation or omission of potentially toxic treatment with undesirable adverse effects, the accelerated implementation of new targeted therapies, and the mitigation of surgical delays in selected patients. In response to the limited ability of radiologists to predict response to PST via qualitative, subjective assessments of tumors on magnetic resonance imaging (MRI), artificial intelligence-enhanced MRI with classical machine learning, and in more recent times, deep learning, have been used with promising results to predict response, both before the start of PST and in the early stages of treatment. This review provides an overview of the current applications of artificial intelligence to MRI in assessing and predicting response to PST, and discusses the challenges and limitations of their clinical implementation.

Deconvolution-Based Pharmacokinetic Analysis to Improve the Prediction of Pathological Information of Breast Cancer

Pharmacokinetic (PK) parameters, revealing changes in the tumor microenvironment, are related to the pathological information of breast cancer. Tracer kinetic models (e.g., Tofts-Kety model) with a nonlinear least square solver are commonly used to estimate PK parameters. However, the method is sensitive to noise in images. To relieve the effects of noise, a deconvolution (DEC) method, which was validated on synthetic concentration-time series, was proposed to accurately calculate PK parameters from breast dynamic contrast-enhanced magnetic resonance imaging. A time-to-peak-based tumor partitioning method was used to divide the whole tumor into three tumor subregions with different kinetic patterns. Radiomic features were calculated from the tumor subregion and whole tumor-based PK parameter maps. The optimal features determined by the fivefold cross-validation method were used to build random forest classifiers to predict molecular subtypes, Ki-67, and tumor grade. The diagnostic performance evaluated by the area under the receiver operating characteristic curve (AUC) was compared between the subregion and whole tumor-based PK parameters. The results showed that the DEC method obtained more accurate PK parameters than the Tofts method. Moreover, the results showed that the subregion-based Ktrans (best AUCs = 0.8319, 0.7032, 0.7132, 0.7490, 0.8074, and 0.6950) achieved a better diagnostic performance than the whole tumor-based Ktrans (AUCs = 0.8222, 0.6970, 0.6511, 0.7109, 0.7620, and 0.5894) for molecular subtypes, Ki-67, and tumor grade. These findings indicate that DEC-based Ktrans in the subregion has the potential to accurately predict molecular subtypes, Ki-67, and tumor grade.

Multiparametric MRI-based radiomics combined with pathomics features for prediction of the efficacy of neoadjuvant chemotherapy in breast cancer

Purpose

The aim of this study is to investigate a new method that combines radiological and pathological breast cancer information to predict discrepancies in pathological responses for individualized treatment planning. We used baseline multiparametric magnetic resonance imaging and hematoxylin and eosin-stained biopsy slides to extract quantitative feature information and predict the pathological response to neoadjuvant chemotherapy in breast cancer patients.

Methods

We retrospectively collected data from breast cancer patients who received neoadjuvant chemotherapy in our hospital from August 2016 to January 2018; multiparametric magnetic resonance imaging (contrast-enhanced T1-weighted imaging and diffusion-weighted imaging) and whole slide image of hematoxylin and eosin-stained biopsy sections were collected. Quantitative imaging features were extracted from the multiparametric magnetic resonance imaging and the whole slide image were used to construct a radiopathomics signature model powered by machine learning methods. Models based on multiparametric magnetic resonance imaging or whole slide image alone were also constructed for comparison and referred to as the radiomics signature and pathomics signature models, respectively. Four modeling methods were used to establish prediction models. Model performances were evaluated using receiver operating characteristic curve analysis and the area under the curve, accuracy, sensitivity, specificity, positive predictive value, and negative predictive value.

Results

The radiopathomics signature model had favourable performance for the prediction of pathological complete response in the training set (the best value: area under the curve 0.83, accuracy 0.84, and sensitivity 0.87), and in the test set (the best value: area under the curve 0.91, accuracy 0.90, and sensitivity 0.88). In the test set, the radiopathomics signature model also significantly outperformed the radiomics signature (the best value: area under the curve 0.83, accuracy 0.64, and sensitivity 0.62), pathomics signature (the best value: area under the curve 0.60, accuracy 0.74, and sensitivity 0.62) (p > 0.05). Decision curve analysis and calibration curves confirmed the excellent performance of these prediction models in discrimination, calibration, and clinical usefulness.

Conclusions

The results of this study suggest that radiopathomics, the combination of both radiological information regarding the whole tumor and pathological information at the cellular level, could potentially predict discrepancies in pathological response and provide evidence for rational treatment plans.

An Informative Review of Radiomics Studies on Cancer Imaging: The Main Findings, Challenges and Limitations of the Methodologies

The aim of this informative review was to investigate the application of radiomics in cancer imaging and to summarize the results of recent studies to support oncological imaging with particular attention to breast cancer, rectal cancer and primitive and secondary liver cancer. This review also aims to provide the main findings, challenges and limitations of the current methodologies. Clinical studies published in the last four years (2019-2022) were included in this review. Among the 19 studies analyzed, none assessed the differences between scanners and vendor-dependent characteristics, collected images of individuals at additional points in time, performed calibration statistics, represented a prospective study performed and registered in a study database, conducted a cost-effectiveness analysis, reported on the cost-effectiveness of the clinical application, or performed multivariable analysis with also non-radiomics features. Seven studies reached a high radiomic quality score (RQS), and seventeen earned additional points by using validation steps considering two datasets from two distinct institutes and open science and data domains (radiomics features calculated on a set of representative ROIs are open source). The potential of radiomics is increasingly establishing itself, even if there are still several aspects to be evaluated before the passage of radiomics into routine clinical practice. There are several challenges, including the need for standardization across all stages of the workflow and the potential for cross-site validation using real-world heterogeneous datasets. Moreover, multiple centers and prospective radiomics studies with more samples that add inter-scanner differences and vendor-dependent characteristics will be needed in the future, as well as the collecting of images of individuals at additional time points, the reporting of calibration statistics and the performing of prospective studies registered in a study database.

MRI-Based Breast Cancer Classification and Localization by Multiparametric Feature Extraction and Combination Using Deep Learning

BACKGROUND

Deep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer detection has not been well investigated.

PURPOSE

To implement a DL method for breast cancer classification and detection using feature extraction and combination from multiple sequences.

STUDY TYPE

Retrospective.

POPULATION

A total of 569 local cases as internal cohort (50.2 ± 11.2 years; 100% female), divided among training (218), validation (73) and testing (278); 125 cases from a public dataset as the external cohort (53.6 ± 11.5 years; 100% female).

FIELD STRENGTH/SEQUENCE

T1-weighted imaging and dynamic contrast-enhanced MRI (DCE-MRI) with gradient echo sequences, T2-weighted imaging (T2WI) with spin-echo sequences, diffusion-weighted imaging with single-shot echo-planar sequence and at 1.5-T.

ASSESSMENT

A convolutional neural network and long short-term memory cascaded network was implemented for lesion classification with histopathology as the ground truth for malignant and benign categories and contralateral breasts as healthy category in internal/external cohorts. BI-RADS categories were assessed by three independent radiologists as comparison, and class activation map was employed for lesion localization in internal cohort. The classification and localization performances were assessed with DCE-MRI and non-DCE sequences, respectively.

STATISTICAL TESTS

Sensitivity, specificity, area under the curve (AUC), DeLong test, and Cohen's kappa for lesion classification. Sensitivity and mean squared error for localization. A P-value <0.05 was considered statistically significant.

RESULTS

With the optimized mpMRI combinations, the lesion classification achieved an AUC = 0.98/0.91, sensitivity = 0.96/0.83 in the internal/external cohorts, respectively. Without DCE-MRI, the DL-based method was superior to radiologists' readings (AUC 0.96 vs. 0.90). The lesion localization achieved sensitivities of 0.97/0.93 with DCE-MRI/T2WI alone, respectively.

DATA CONCLUSION

The DL method achieved high accuracy for lesion detection in the internal/external cohorts. The classification performance with a contrast agent-free combination is comparable to DCE-MRI alone and the radiologists' reading in AUC and sensitivity.

EVIDENCE LEVEL

3.

TECHNICAL EFFICACY

Stage 2.

Efficient estimation of pharmacokinetic parameters from breast dynamic contrast-enhanced MRI based on a convolutional neural network for predicting molecular subtypes

Objective. Tracer kinetic models allow for estimating pharmacokinetic (PK) parameters, which are related to pathological characteristics, from breast dynamic contrast-enhanced magnetic resonance imaging. However, existing tracer kinetic models subject to inaccuracy are time-consuming for PK parameters estimation. This study aimed to accurately and efficiently estimate PK parameters for predicting molecular subtypes based on convolutional neural network (CNN).Approach. A CNN integrating global and local features (GL-CNN) was trained using synthetic data where known PK parameters map was used as the ground truth, and subsequently used to directly estimate PK parameters (volume transfer constantKtransand flux rate constantKep) map. The accuracy assessed by the peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and concordance correlation coefficient (CCC) was compared between the GL-CNN and Tofts-based PK parameters in synthetic data. Radiomic features were calculated from the PK parameters map in 208 breast tumors. A random forest classifier was constructed to predict molecular subtypes using a discovery cohort (n= 144). The diagnostic performance evaluated on a validation cohort (n= 64) using the area under the receiver operating characteristic curve (AUC) was compared between the GL-CNN and Tofts-based PK parameters.Main results. The average PSNR (48.8884), SSIM (0.9995), and CCC (0.9995) between the GL-CNN-basedKtransmap and ground truth were significantly higher than those between the Tofts-basedKtransmap and ground truth. The GL-CNN-basedKtransobtained significantly better diagnostic performance (AUCs = 0.7658 and 0.8528) than the Tofts-basedKtransfor luminal B and HER2 tumors. The GL-CNN method accelerated the computation by speed approximately 79 times compared to the Tofts method for the whole breast of all patients.Significance. Our results indicate that the GL-CNN method can be used to accurately and efficiently estimate PK parameters for predicting molecular subtypes.

Discrimination of benign and malignant breast lesions on dynamic contrast-enhanced magnetic resonance imaging using deep learning

PURPOSE

To evaluate the capability of deep transfer learning (DTL) and fine-tuning methods in differentiating malignant from benign lesions in breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).

METHODS

The diagnostic efficiencies of the VGG19, ResNet50, and DenseNet201 models were tested under the same dataset. The model with the highest performance was selected and modified utilizing three fine-tuning strategies (S1-3). Fifty additional lesions were selected to form the validation set to verify the generalization abilities of these models. The accuracy (Ac) of the different models in the training and test sets, as well as the precision (Pr), recall rate (Rc), F1 score (), and area under the receiver operating characteristic curve (AUC), were primary performance indicators. Finally, the kappa test was used to compare the degree of agreement between the DTL models and pathological diagnosis in differentiating malignant from benign breast lesions.

RESULTS

The Pr, Rc, f1, and AUC of VGG19 (86.0%, 0.81, 0.81, and 0.81, respectively) were higher than those of DenseNet201 (70.0%, 0.61, 0.63, and 0.61, respectively) and ResNet50 (61.0%, 0.59, 0.59, and 0.59). After fine-tuning, the Pr, Rc, f1, and AUC of S1 (87.0%, 0.86, 0.86, and 0.86, respectively) were higher than those of VGG19. Notably, the degree of agreement between S1 and pathological diagnosis in differentiating malignant from benign breast lesions was 0.720 (κ = 0.720), which was higher than that of DenseNet201 (κ = 0.440), VGG19 (κ = 0.640), and ResNet50 (κ = 0.280).

CONCLUSION

The VGG19 model is an effective method for identifying benign and malignant breast lesions on DCE-MRI, and its performance can be further improved via fine-tuning. Overall, our findings insinuate that this technique holds potential clinical application value.

Evaluation of a Deep Learning Reconstruction for High-Quality T2-Weighted Breast Magnetic Resonance Imaging

Deep learning (DL) reconstruction techniques to improve MR image quality are becoming commercially available with the hope that they will be applicable to multiple imaging application sites and acquisition protocols. However, before clinical implementation, these methods must be validated for specific use cases. In this work, the quality of standard-of-care (SOC) T2w and a high-spatial-resolution (HR) imaging of the breast were assessed both with and without prototype DL reconstruction. Studies were performed using data collected from phantoms, 20 retrospectively collected SOC patient exams, and 56 prospectively acquired SOC and HR patient exams. Image quality was quantitatively assessed via signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and edge sharpness. Qualitatively, all in vivo images were scored by either two or four radiologist readers using 5-point Likert scales in the following categories: artifacts, perceived sharpness, perceived SNR, and overall quality. Differences in reader scores were tested for significance. Reader preference and perception of signal intensity changes were also assessed. Application of the DL resulted in higher average SNR (1.2-2.8 times), CNR (1.0-1.8 times), and image sharpness (1.2-1.7 times). Qualitatively, the SOC acquisition with DL resulted in significantly improved image quality scores in all categories compared to non-DL images. HR acquisition with DL significantly increased SNR, sharpness, and overall quality compared to both the non-DL SOC and the non-DL HR images. The acquisition time for the HR data only required a 20% increase compared to the SOC acquisition and readers typically preferred DL images over non-DL counterparts. Overall, the DL reconstruction demonstrated improved T2w image quality in clinical breast MRI.

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.

Developing an Artificial Intelligence Solution to Autosegment the Edentulous Mandibular Bone for Implant Planning

OBJECTIVE

 Dental implants are considered the optimum solution to replace missing teeth and restore the mouth's function and aesthetics. Surgical planning of the implant position is critical to avoid damage to vital anatomical structures; however, the manual measurement of the edentulous (toothless) bone on cone beam computed tomography (CBCT) images is time-consuming and is subject to human error. An automated process has the potential to reduce human errors and save time and costs. This study developed an artificial intelligence (AI) solution to identify and delineate edentulous alveolar bone on CBCT images before implant placement.

MATERIALS AND METHODS

 After obtaining the ethical approval, CBCT images were extracted from the database of the University Dental Hospital Sharjah based on predefined selection criteria. Manual segmentation of the edentulous span was done by three operators using ITK-SNAP software. A supervised machine learning approach was undertaken to develop a segmentation model on a "U-Net" convolutional neural network (CNN) in the Medical Open Network for Artificial Intelligence (MONAI) framework. Out of the 43 labeled cases, 33 were utilized to train the model, and 10 were used for testing the model's performance.

STATISTICAL ANALYSIS

 The degree of 3D spatial overlap between the segmentation made by human investigators and the model's segmentation was measured by the dice similarity coefficient (DSC).

RESULTS

 The sample consisted mainly of lower molars and premolars. DSC yielded an average value of 0.89 for training and 0.78 for testing. Unilateral edentulous areas, comprising 75% of the sample, resulted in a better DSC (0.91) than bilateral cases (0.73).

CONCLUSION

 Segmentation of the edentulous spans on CBCT images was successfully conducted by machine learning with good accuracy compared to manual segmentation. Unlike traditional AI object detection models that identify objects present in the image, this model identifies missing objects. Finally, challenges in data collection and labeling are discussed, together with an outlook at the prospective stages of a larger project for a complete AI solution for automated implant planning.

AI-Enhanced PET and MR Imaging for Patients with Breast Cancer

New challenges are currently faced by clinical and surgical oncologists in the management of patients with breast cancer, mainly related to the need for molecular and prognostic data. Recent technological advances in diagnostic imaging and informatics have led to the introduction of functional imaging modalities, such as hybrid PET/MR imaging, and artificial intelligence (AI) software, aimed at the extraction of quantitative radiomics data, which may reflect tumor biology and behavior. In this article, the most recent applications of radiomics and AI to PET/MR imaging are described to address the new needs of clinical and surgical oncology.

Artificial intelligence applications in computed tomography in gastric cancer: a narrative review

Background and Objective

Artificial intelligence (AI) is a revolutionary technique which is deeply impacting and reshaping clinical practice in oncology. This review aims to summarize the current status of the clinical application of AI-based computed tomography (CT) for gastric cancer (GC), focusing on diagnosis, genetic status detection and risk prediction of metastasis, prognosis and treatment efficacy. The challenges and prospects for future research will also be discussed.

Methods

We searched the PubMed/MEDLINE database to identify clinical studies published between 1990 and November 2022 that investigated AI applications in CT in GC. The major findings of the verified studies were summarized.

Key Content and Findings

AI applications in CT images have attracted considerable attention in various fields such as diagnosis, prediction of metastasis risk, survival, and treatment response. These emerging techniques have shown a high potential to outperform clinicians in diagnostic accuracy and time-saving.

Conclusions

AI-powered tools showed great potential to increase diagnostic accuracy and reduce radiologists' workload. However, the goal of AI is not to replace human ability but to help oncologists make decisions in their practice. Therefore, radiologists should play a predominant role in AI applications and decide the best ways to integrate these complementary techniques within clinical practice.

Disulfidptosis-associated lncRNAs predict breast cancer subtypes

Disulfidptosis is a newly discovered mode of cell death. However, its relationship with breast cancer subtypes remains unclear. In this study, we aimed to construct a disulfidptosis-associated breast cancer subtype prediction model. We obtained 19 disulfidptosis-related genes from published articles and performed correlation analysis with lncRNAs differentially expressed in breast cancer. We then used the random forest algorithm to select important lncRNAs and establish a breast cancer subtype prediction model. We identified 132 lncRNAs significantly associated with disulfidptosis (FDR < 0.01, |R|> 0.15) and selected the first four important lncRNAs to build a prediction model (training set AUC = 0.992). The model accurately predicted breast cancer subtypes (test set AUC = 0.842). Among the key lncRNAs, LINC02188 had the highest expression in the Basal subtype, while LINC01488 and GATA3-AS1 had the lowest expression in Basal. In the Her2 subtype, LINC00511 had the highest expression level compared to other key lncRNAs. GATA3-AS1 had the highest expression in LumA and LumB subtypes, while LINC00511 had the lowest expression in these subtypes. In the Normal subtype, GATA3-AS1 had the highest expression level compared to other key lncRNAs. Our study also found that key lncRNAs were closely related to RNA methylation modification and angiogenesis (FDR < 0.05, |R|> 0.1), as well as immune infiltrating cells (P.adj < 0.01, |R|> 0.1). Our random forest model based on disulfidptosis-related lncRNAs can accurately predict breast cancer subtypes and provide a new direction for research on clinical therapeutic targets for breast cancer.

Multi-parametric MRI for radiotherapy simulation

Magnetic resonance imaging (MRI) has become an important imaging modality in the field of radiotherapy (RT) in the past decade, especially with the development of various novel MRI and image-guidance techniques. In this review article, we will describe recent developments and discuss the applications of multi-parametric MRI (mpMRI) in RT simulation. In this review, mpMRI refers to a general and loose definition which includes various multi-contrast MRI techniques. Specifically, we will focus on the implementation, challenges, and future directions of mpMRI techniques for RT simulation.

Diagnosis of Laryngopharyngeal Reflux Disease Based on Gray and Texture Changes of Laryngoscopic Images

OBJECTIVE

This study aimed to compare the changing trends of gray and texture values of laryngoscopic images in patients with laryngopharyngeal reflux (LPR) and non-LPR.

METHODS

A total of 3428 laryngoscopic images were selected and divided into two groups, non-LPR and LPR groups based on the reflux symptom index. Gray histogram and gray-level co-occurrence matrix (GLCM) were used to quantify gray and texture features, and the model was trained based on these features. The total laryngoscopic images dataset was proportionally split into two parts including the training set and the test set according to the ratio of 7:3. Four different machine learning algorithms, including decision tree, naive Bayes, linear regression, and K-nearest neighbors, were applied to classify non-LPR or LPR laryngoscopic images.

RESULTS

The results showed that different classification algorithms are used to classify laryngoscopic image dataset and promising classification accuracy are obtained. Specifically, the accuracy of K-nearest neighbors was 83.38% for the gray histogram-only classification, that of linear regression was 88.63% for the GLCM-only classification, and that of the decision tree was 98.01% for the combined gray histogram and GLCM analysis.

CONCLUSION

Gray histogram and GLCM analysis of the laryngoscopic images may be used as auxiliary tools to detect laryngopharyngeal mucosal damage in patients with LPR. Measurement of gray and texture feature values is an objective and convenient method, which may serve as a reference baseline for clinicians and have potential clinical usefulness.

Contrast Agents of Magnetic Resonance Imaging and Future Perspective

In recent times, magnetic resonance imaging (MRI) has emerged as a highly promising modality for diagnosing severe diseases. Its exceptional spatiotemporal resolution and ease of use have established it as an indispensable clinical diagnostic tool. Nevertheless, there are instances where MRI encounters challenges related to low contrast, necessitating the use of contrast agents (CAs). Significant efforts have been made by scientists to enhance the precision of observing diseased body parts by leveraging the synergistic potential of MRI in conjunction with other imaging techniques and thereby modifying the CAs. In this work, our focus is on elucidating the rational designing approach of CAs and optimizing their compatibility for multimodal imaging and other intelligent applications. Additionally, we emphasize the importance of incorporating various artificial intelligence tools, such as machine learning and deep learning, to explore the future prospects of disease diagnosis using MRI. We also address the limitations associated with these techniques and propose reasonable remedies, with the aim of advancing MRI as a cutting-edge diagnostic tool for the future.

Prediction of Tumor Progression During Neoadjuvant Chemotherapy and Survival Outcome in Patients With Triple-Negative Breast Cancer

OBJECTIVE

To investigate the association of clinical, pathologic, and magnetic resonance imaging (MRI) variables with progressive disease (PD) during neoadjuvant chemotherapy (NAC) and distant metastasis-free survival (DMFS) in patients with triple-negative breast cancer (TNBC).

MATERIALS AND METHODS

This single-center retrospective study included 252 women with TNBC who underwent NAC between 2010 and 2019. Clinical, pathologic, and treatment data were collected. Two radiologists analyzed the pre-NAC MRI. After random allocation to the development and validation sets in a 2:1 ratio, we developed models to predict PD and DMFS using logistic regression and Cox proportional hazard regression, respectively, and validated them.

RESULTS

Among the 252 patients (age, 48.3 ± 10.7 years; 168 in the development set; 84 in the validation set), PD was occurred in 17 patients and 9 patients in the development and validation sets, respectively. In the clinical-pathologic-MRI model, the metaplastic histology (odds ratio [OR], 8.0; P = 0.032), Ki-67 index (OR, 1.02; P = 0.044), and subcutaneous edema (OR, 30.6; P = 0.004) were independently associated with PD in the development set. The clinical-pathologic-MRI model showed a higher area under the receiver-operating characteristic curve (AUC) than the clinical-pathologic model (AUC: 0.69 vs. 0.54; P = 0.017) for predicting PD in the validation set. Distant metastases occurred in 49 patients and 18 patients in the development and validation sets, respectively. Residual disease in both the breast and lymph nodes (hazard ratio [HR], 6.0; P = 0.005) and the presence of lymphovascular invasion (HR, 3.3; P < 0.001) were independently associated with DMFS. The model consisting of these pathologic variables showed a Harrell's C-index of 0.86 in the validation set.

CONCLUSION

The clinical-pathologic-MRI model, which considered subcutaneous edema observed using MRI, performed better than the clinical-pathologic model for predicting PD. However, MRI did not independently contribute to the prediction of DMFS.

Radiomics model to classify mammary masses using breast DCE-MRI compared to the BI-RADS classification performance

BACKGROUND

Recent advanced in radiomics analysis could help to identify breast cancer among benign mammary masses. The aim was to create a radiomics signature using breast DCE-MRI extracted features to classify tumors and to compare the performances with the BI-RADS classification.

MATERIAL AND METHODS

From September 2017 to December 2019 images, exams and records from consecutive patients with mammary masses on breast DCE-MRI and available histology from one center were retrospectively reviewed (79 patients, 97 masses). Exclusion criterion was malignant uncertainty. The tumors were split in a train-set (70%) and a test-set (30%). From 14 kinetics maps, 89 radiomics features were extracted, for a total of 1246 features per tumor. Feature selection was made using Boruta algorithm, to train a random forest algorithm on the train-set. BI-RADS classification was recorded from two radiologists.

RESULTS

Seventy-seven patients were analyzed with 94 tumors, (71 malignant, 23 benign). Over 1246 features, 17 were selected from eight kinetic maps. On the test-set, the model reaches an AUC = 0.94 95 CI [0.85-1.00] and a specificity of 33% 95 CI [10-70]. There were 43/94 (46%) lesions BI-RADS4 (4a = 12/94 (13%); 4b = 9/94 (10%); and 4c = 22/94 (23%)). The BI-RADS score reached an AUC = 0.84 95 CI [0.73-0.95] and a specificity of 17% 95 CI [3-56]. There was no significant difference between the ROC curves for the model or the BI-RADS score (p = 0.19).

CONCLUSION

A radiomics signature from features extracted using breast DCE-MRI can reach an AUC of 0.94 on a test-set and could provide as good results as BI-RADS to classify mammary masses.

Applications of Deep Learning to Neurodevelopment in Pediatric Imaging: Achievements and Challenges

Deep learning has achieved remarkable progress, particularly in neuroimaging analysis. Deep learning applications have also been extended from adult to pediatric medical images, and thus, this paper aims to present a systematic review of this recent research. We first introduce the commonly used deep learning methods and architectures in neuroimaging, such as convolutional neural networks, auto-encoders, and generative adversarial networks. A non-exhaustive list of commonly used publicly available pediatric neuroimaging datasets and repositories are included, followed by a categorical review of recent works in pediatric MRI-based deep learning studies in the past five years. These works are categorized into recognizing neurodevelopmental disorders, identifying brain and tissue structures, estimating brain age/maturity, predicting neurodevelopment outcomes, and optimizing MRI brain imaging and analysis. Finally, we also discuss the recent achievements and challenges on these applications of deep learning to pediatric neuroimaging.

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.

The road to breast cancer screening with diffusion MRI

Breast cancer is the leading cause of cancer in women with a huge medical, social and economic impact. Mammography (MMG) has been the gold standard method until now because it is relatively inexpensive and widely available. However, MMG suffers from certain limitations, such as exposure to X-rays and difficulty of interpretation in dense breasts. Among other imaging methods, MRI has clearly the highest sensitivity and specificity, and breast MRI is the gold standard for the investigation and management of suspicious lesions revealed by MMG. Despite this performance, MRI, which does not rely on X-rays, is not used for screening except for a well-defined category of women at risk, because of its high cost and limited availability. In addition, the standard approach to breast MRI relies on Dynamic Contrast Enhanced (DCE) MRI with the injection of Gadolinium based contrast agents (GBCA), which have their own contraindications and can lead to deposit of gadolinium in tissues, including the brain, when examinations are repeated. On the other hand, diffusion MRI of breast, which provides information on tissue microstructure and tumor perfusion without the use of contrast agents, has been shown to offer higher specificity than DCE MRI with similar sensitivity, superior to MMG. Diffusion MRI thus appears to be a promising alternative approach to breast cancer screening, with the primary goal of eliminating with a very high probability the existence of a life-threatening lesion. To achieve this goal, it is first necessary to standardize the protocols for acquisition and analysis of diffusion MRI data, which have been found to vary largely in the literature. Second, the accessibility and cost-effectiveness of MRI examinations must be significantly improved, which may become possible with the development of dedicated low-field MRI units for breast cancer screening. In this article, we will first review the principles and current status of diffusion MRI, comparing its clinical performance with MMG and DCE MRI. We will then look at how breast diffusion MRI could be implemented and standardized to optimize accuracy of results. Finally, we will discuss how a dedicated, low-cost prototype of breast MRI system could be implemented and introduced to the healthcare market.

Artificial intelligence in breast cancer imaging: risk stratification, lesion detection and classification, treatment planning and prognosis-a narrative review

The advent of artificial intelligence (AI) represents a real game changer in today's landscape of breast cancer imaging. Several innovative AI-based tools have been developed and validated in recent years that promise to accelerate the goal of real patient-tailored management. Numerous studies confirm that proper integration of AI into existing clinical workflows could bring significant benefits to women, radiologists, and healthcare systems. The AI-based approach has proved particularly useful for developing new risk prediction models that integrate multi-data streams for planning individualized screening protocols. Furthermore, AI models could help radiologists in the pre-screening and lesion detection phase, increasing diagnostic accuracy, while reducing workload and complications related to overdiagnosis. Radiomics and radiogenomics approaches could extrapolate the so-called imaging signature of the tumor to plan a targeted treatment. The main challenges to the development of AI tools are the huge amounts of high-quality data required to train and validate these models and the need for a multidisciplinary team with solid machine-learning skills. The purpose of this article is to present a summary of the most important AI applications in breast cancer imaging, analyzing possible challenges and new perspectives related to the widespread adoption of these new tools.

Differentiation of breast lesions on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) using deep transfer learning based on DenseNet201

In order to achieve better performance, artificial intelligence is used in breast cancer diagnosis. In this study, we evaluated the efficacy of different fine-tuning strategies of deep transfer learning (DTL) based on the DenseNet201 model to differentiate malignant from benign lesions on breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). We collected 4260 images of benign lesions and 4140 images of malignant lesions of the breast pertaining to pathologically confirmed cases. The benign and malignant groups was randomly divided into a training set and a testing set at a ratio of 9:1. A DTL model based on the DenseNet201 model was established, and the effectiveness of 4 fine-tuning strategies (S0: strategy 0, S1: strategy; S2: strategy; and S3: strategy) was compared. Additionally, DCE-MRI images of 48 breast lesions were selected to verify the robustness of the model. Ten images were obtained for each lesion. The classification was considered correct if more than 5 images were correctly classified. The metrics for model performance evaluation included accuracy (Ac) in the training and testing sets, precision (Pr), recall rate (Rc), f1 score (f1), and area under the receiver operating characteristic curve (AUROC) in the validation set. The Ac of the 4 fine-tuning strategies reached 100.00% in the training set. The S2 strategy exhibited good convergence in the testing set. The Ac of S2 was 98.01% in the testing set, which was higher than those of S0 (93.10%), S1 (90.45%), and S3 (93.90%). The average classification Pr, Rc, f1, and AUROC of S2 in the validation set were (89.00%, 80.00%, 0.81, and 0.79, respectively) higher than those of S0 (76.00%, 67.00%, 0.69, and 0.65, respectively), S1 (60.00%, 60.00%, 0.60, 0.66, and respectively), and S3 (77.00%, 73.00%, 0.74, 0.72, respectively). The degree of coincidence between S2 and the histopathological method for differentiating between benign and malignant breast lesions was high (κ = 0.749). The S2 strategy can improve the robustness of the DenseNet201 model in relatively small breast DCE-MRI datasets, and this is a reliable method to increase the Ac of discriminating benign from malignant breast lesions on DCE-MRI.

Deep learning in CT image segmentation of cervical cancer: a systematic review and meta-analysis

Background

This paper attempts to conduct a systematic review and meta-analysis of deep learning (DLs) models for cervical cancer CT image segmentation.

Methods

Relevant studies were systematically searched in PubMed, Embase, The Cochrane Library, and Web of science. The literature on DLs for cervical cancer CT image segmentation were included, a meta-analysis was performed on the dice similarity coefficient (DSC) of the segmentation results of the included DLs models. We also did subgroup analyses according to the size of the sample, type of segmentation (i.e., two dimensions and three dimensions), and three organs at risk (i.e., bladder, rectum, and femur). This study was registered in PROSPERO prior to initiation (CRD42022307071).

Results

A total of 1893 articles were retrieved and 14 articles were included in the meta-analysis. The pooled effect of DSC score of clinical target volume (CTV), bladder, rectum, femoral head were 0.86(95%CI 0.84 to 0.87), 0.91(95%CI 0.89 to 0.93), 0.83(95%CI 0.79 to 0.88), and 0.92(95%CI 0.91to 0.94), respectively. For the performance of segmented CTV by two dimensions (2D) and three dimensions (3D) model, the DSC score value for 2D model was 0.87 (95%CI 0.85 to 0.90), while the DSC score for 3D model was 0.85 (95%CI 0.82 to 0.87). As for the effect of the capacity of sample on segmentation performance, no matter whether the sample size is divided into two groups: greater than 100 and less than 100, or greater than 150 and less than 150, the results show no difference (P > 0.05). Four papers reported the time for segmentation from 15 s to 2 min.

Conclusion

DLs have good accuracy in automatic segmentation of CT images of cervical cancer with a less time consuming and have good prospects for future radiotherapy applications, but still need public high-quality databases and large-scale research verification.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13014-022-02148-6.

A Novel CNN pooling layer for breast cancer segmentation and classification from thermograms

Breast cancer is the second most frequent cancer worldwide, following lung cancer and the fifth leading cause of cancer death and a major cause of cancer death among women. In recent years, convolutional neural networks (CNNs) have been successfully applied for the diagnosis of breast cancer using different imaging modalities. Pooling is a main data processing step in CNN that decreases the feature maps' dimensionality without losing major patterns. However, the effect of pooling layer was not studied efficiently in literature. In this paper, we propose a novel design for the pooling layer called vector pooling block (VPB) for the CCN algorithm. The proposed VPB consists of two data pathways, which focus on extracting features along horizontal and vertical orientations. The VPB makes the CNNs able to collect both global and local features by including long and narrow pooling kernels, which is different from the traditional pooling layer, that gathers features from a fixed square kernel. Based on the novel VPB, we proposed a new pooling module called AVG-MAX VPB. It can collect informative features by using two types of pooling techniques, maximum and average pooling. The VPB and the AVG-MAX VPB are plugged into the backbone CNNs networks, such as U-Net, AlexNet, ResNet18 and GoogleNet, to show the advantages in segmentation and classification tasks associated with breast cancer diagnosis from thermograms. The proposed pooling layer was evaluated using a benchmark thermogram database (DMR-IR) and its results compared with U-Net results which was used as base results. The U-Net results were as follows: global accuracy = 96.6%, mean accuracy = 96.5%, mean IoU = 92.07%, and mean BF score = 78.34%. The VBP-based results were as follows: global accuracy = 98.3%, mean accuracy = 97.9%, mean IoU = 95.87%, and mean BF score = 88.68% while the AVG-MAX VPB-based results were as follows: global accuracy = 99.2%, mean accuracy = 98.97%, mean IoU = 98.03%, and mean BF score = 94.29%. Other network architectures also demonstrate superior improvement considering the use of VPB and AVG-MAX VPB.

Development and validation of a deep learning model for breast lesion segmentation and characterization in multiparametric MRI

Importance

The utilization of artificial intelligence for the differentiation of benign and malignant breast lesions in multiparametric MRI (mpMRI) assists radiologists to improve diagnostic performance.

Objectives

To develop an automated deep learning model for breast lesion segmentation and characterization and to evaluate the characterization performance of AI models and radiologists.

Materials and methods

For lesion segmentation, 2,823 patients were used for the training, validation, and testing of the VNet-based segmentation models, and the average Dice similarity coefficient (DSC) between the manual segmentation by radiologists and the mask generated by VNet was calculated. For lesion characterization, 3,303 female patients with 3,607 pathologically confirmed lesions (2,213 malignant and 1,394 benign lesions) were used for the three ResNet-based characterization models (two single-input and one multi-input models). Histopathology was used as the diagnostic criterion standard to assess the characterization performance of the AI models and the BI-RADS categorized by the radiologists, in terms of sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC). An additional 123 patients with 136 lesions (81 malignant and 55 benign lesions) from another institution were available for external testing.

Results

Of the 5,811 patients included in the study, the mean age was 46.14 (range 11–89) years. In the segmentation task, a DSC of 0.860 was obtained between the VNet-generated mask and manual segmentation by radiologists. In the characterization task, the AUCs of the multi-input and the other two single-input models were 0.927, 0.821, and 0.795, respectively. Compared to the single-input DWI or DCE model, the multi-input DCE and DWI model obtained a significant increase in sensitivity, specificity, and accuracy (0.831 vs. 0.772/0.776, 0.874 vs. 0.630/0.709, 0.846 vs. 0.721/0.752). Furthermore, the specificity of the multi-input model was higher than that of the radiologists, whether using BI-RADS category 3 or 4 as a cutoff point (0.874 vs. 0.404/0.841), and the accuracy was intermediate between the two assessment methods (0.846 vs. 0.773/0.882). For the external testing, the performance of the three models remained robust with AUCs of 0.812, 0.831, and 0.885, respectively.

Conclusions

Combining DCE with DWI was superior to applying a single sequence for breast lesion characterization. The deep learning computer-aided diagnosis (CADx) model we developed significantly improved specificity and achieved comparable accuracy to the radiologists with promise for clinical application to provide preliminary diagnoses.

A deep learning model based on dynamic contrast-enhanced magnetic resonance imaging enables accurate prediction of benign and malignant breast lessons

Objectives

The study aims to investigate the value of a convolutional neural network (CNN) based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in predicting malignancy of breast lesions.

Methods

We developed a CNN model based on DCE-MRI to characterize breast lesions. Between November 2018 and October 2019, 6,165 slices of 364 lesions (234 malignant, 130 benign) in 364 patients were pooled in the training/validation set. Lesions were semi-automatically segmented by two breast radiologists using ITK-SNAP software. The standard of reference was histologic consequences. Algorithm performance was evaluated in an independent testing set of 1,560 slices of 127 lesions in 127 patients using weighted sums of the area under the curve (AUC) scores.

Results

The area under the receiver operating characteristic (ROC) curve was 0.955 for breast cancer prediction while the accuracy, sensitivity, and specificity were 90.3, 96.2, and 79.0%, respectively, in the slice-based method. In the case-based method, the efficiency of the model changed by adjusting the standard for the number of positive slices. When a lesion with three or more positive slices was determined as malignant, the sensitivity was above 90%, with a specificity of nearly 60% and an accuracy higher than 80%.

Conclusion

The CNN model based on DCE-MRI demonstrated high accuracy for predicting malignancy among the breast lesions. This method should be validated in a larger and independent cohort.

MRI in the Setting of Neoadjuvant Treatment of Breast Cancer

Neoadjuvant therapy may reduce tumor burden preoperatively, allowing breast conservation treatment for tumors previously unresectable or requiring mastectomy without reducing disease-free survival. Oncologists can also use the response of the tumor to neoadjuvant chemotherapy (NAC) to identify treatment likely to be successful against any unknown potential distant metastasis. Accurate preoperative estimations of tumor size are necessary to guide appropriate treatment with minimal delays and can provide prognostic information. Clinical breast examination and mammography are inaccurate methods for measuring tumor size after NAC and can over- and underestimate residual disease. While US is commonly used to measure changes in tumor size during NAC due to its availability and low cost, MRI remains more accurate and simultaneously images the entire breast and axilla. No method is sufficiently accurate at predicting complete pathological response that would obviate the need for surgery. Diffusion-weighted MRI, MR spectroscopy, and MRI-based radiomics are emerging fields that potentially increase the predictive accuracy of tumor response to NAC.

MRI as a biomarker for breast cancer diagnosis and prognosis

Breast cancer (BC) is the most frequently diagnosed female invasive cancer in Western countries and the leading cause of cancer-related death worldwide. Nowadays, tumor heterogeneity is a well-known characteristic of BC, since it includes several nosological entities characterized by different morphologic features, clinical course and response to treatment. Thus, with the spread of molecular biology technologies and the growing knowledge of the biological processes underlying the development of BC, the importance of imaging biomarkers as non-invasive information about tissue hallmarks has progressively grown. To date, breast magnetic resonance imaging (MRI) is considered indispensable in breast imaging practice, with widely recognized indications such as BC screening in females at increased risk, locoregional staging and neoadjuvant therapy (NAT) monitoring. Moreover, breast MRI is increasingly used to assess not only the morphologic features of the pathological process but also to characterize individual phenotypes for targeted therapies, building on developments in genomics and molecular biology features. The aim of this review is to explore the role of breast multiparametric MRI in providing imaging biomarkers, leading to an improved differentiation of benign and malignant breast lesions and to a customized management of BC patients in monitoring and predicting response to treatment. Finally, we discuss how breast MRI biomarkers offer one of the most fertile ground for artificial intelligence (AI) applications. In the era of personalized medicine, with the development of omics-technologies, machine learning and big data, the role of imaging biomarkers is embracing new opportunities for BC diagnosis and treatment.

Multi-Classification of Breast Cancer Lesions in Histopathological Images Using DEEP_Pachi: Multiple Self-Attention Head

INTRODUCTION AND BACKGROUND

Despite fast developments in the medical field, histological diagnosis is still regarded as the benchmark in cancer diagnosis. However, the input image feature extraction that is used to determine the severity of cancer at various magnifications is harrowing since manual procedures are biased, time consuming, labor intensive, and error-prone. Current state-of-the-art deep learning approaches for breast histopathology image classification take features from entire images (generic features). Thus, they are likely to overlook the essential image features for the unnecessary features, resulting in an incorrect diagnosis of breast histopathology imaging and leading to mortality.

METHODS

This discrepancy prompted us to develop DEEP_Pachi for classifying breast histopathology images at various magnifications. The suggested DEEP_Pachi collects global and regional features that are essential for effective breast histopathology image classification. The proposed model backbone is an ensemble of DenseNet201 and VGG16 architecture. The ensemble model extracts global features (generic image information), whereas DEEP_Pachi extracts spatial information (regions of interest). Statistically, the evaluation of the proposed model was performed on publicly available dataset: BreakHis and ICIAR 2018 Challenge datasets.

RESULTS

A detailed evaluation of the proposed model's accuracy, sensitivity, precision, specificity, and f1-score metrics revealed the usefulness of the backbone model and the DEEP_Pachi model for image classifying. The suggested technique outperformed state-of-the-art classifiers, achieving an accuracy of 1.0 for the benign class and 0.99 for the malignant class in all magnifications of BreakHis datasets and an accuracy of 1.0 on the ICIAR 2018 Challenge dataset.

CONCLUSIONS

The acquired findings were significantly resilient and proved helpful for the suggested system to assist experts at big medical institutions, resulting in early breast cancer diagnosis and a reduction in the death rate.

Updates in Artificial Intelligence for Breast Imaging

Artificial intelligence (AI) for breast imaging has rapidly moved from the experimental to implementation phase. As of this writing, Food and Drug Administration (FDA)-approved mammographic applications are available for triage, lesion detection and classification, and breast density assessment. For sonography and MRI, FDA-approved applications are available for lesion classification. Numerous other interpretive and noninterpretive AI applications are in the development phase. This article reviews AI applications for mammography, sonography, and MRI that are currently available for clinical use. In addition, clinical implementation and the future of AI for breast imaging are discussed.

Overview of Noninterpretive Artificial Intelligence Models for Safety, Quality, Workflow, and Education Applications in Radiology Practice

Artificial intelligence has become a ubiquitous term in radiology over the past several years, and much attention has been given to applications that aid radiologists in the detection of abnormalities and diagnosis of diseases. However, there are many potential applications related to radiologic image quality, safety, and workflow improvements that present equal, if not greater, value propositions to radiology practices, insurance companies, and hospital systems. This review focuses on six major categories for artificial intelligence applications: study selection and protocoling, image acquisition, worklist prioritization, study reporting, business applications, and resident education. All of these categories can substantially affect different aspects of radiology practices and workflows. Each of these categories has different value propositions in terms of whether they could be used to increase efficiency, improve patient safety, increase revenue, or save costs. Each application is covered in depth in the context of both current and future areas of work. Keywords: Use of AI in Education, Application Domain, Supervised Learning, Safety © RSNA, 2022.

Multi parametric magnetic resonance imaging for radiation treatment planning

In recent years, multi-parametric magnetic resonance imaging (MpMRI) has played a major role in radiation therapy treatment planning. The superior soft tissue contrast, functional or physiological imaging capabilities and the flexibility of site-specific image sequence development has placed MpMRI at the forefront. In this article, the present status of MpMRI for external beam radiation therapy planning is reviewed. Common MpMRI sequences, preprocessing and QA strategies are briefly discussed, and various image registration techniques and strategies are addressed. Image segmentation methods including automatic segmentation and deep learning techniques for organs at risk and target delineation are reviewed. Due to the advancement in MRI guided online adaptive radiotherapy, treatment planning considerations addressing MRI only planning are also discussed. This article is protected by copyright. All rights reserved.