BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study.

Background The performance of publicly available large language models (LLMs) remains unclear for complex clinical tasks. Purpose To evaluate the agreement between human readers and LLMs for Breast Imaging Reporting and Data System (BI-RADS) categories assigned based on breast imaging reports written in three languages and to assess the impact of discordant category assignments on clinical management. Materials and Methods This retrospective study included reports for women who underwent MRI, mammography, and/or US for breast cancer screening or diagnostic purposes at three referral centers. Reports with findings categorized as BI-RADS 1-5 and written in Italian, English, or Dutch were collected between January 2000 and October 2023. Board-certified breast radiologists and the LLMs GPT-3.5 and GPT-4 (OpenAI) and Bard, now called Gemini (Google), assigned BI-RADS categories using only the findings described by the original radiologists. Agreement between human readers and LLMs for BI-RADS categories was assessed using the Gwet agreement coefficient (AC1 value). Frequencies were calculated for changes in BI-RADS category assignments that would affect clinical management (ie, BI-RADS 0 vs BI-RADS 1 or 2 vs BI-RADS 3 vs BI-RADS 4 or 5) and compared using the McNemar test. Results Across 2400 reports, agreement between the original and reviewing radiologists was almost perfect (AC1 = 0.91), while agreement between the original radiologists and GPT-4, GPT-3.5, and Bard was moderate (AC1 = 0.52, 0.48, and 0.42, respectively). Across human readers and LLMs, differences were observed in the frequency of BI-RADS category upgrades or downgrades that would result in changed clinical management (118 of 2400 [4.9%] for human readers, 611 of 2400 [25.5%] for Bard, 573 of 2400 [23.9%] for GPT-3.5, and 435 of 2400 [18.1%] for GPT-4; P < .001) and that would negatively impact clinical management (37 of 2400 [1.5%] for human readers, 435 of 2400 [18.1%] for Bard, 344 of 2400 [14.3%] for GPT-3.5, and 255 of 2400 [10.6%] for GPT-4; P < .001). Conclusion LLMs achieved moderate agreement with human reader-assigned BI-RADS categories across reports written in three languages but also yielded a high percentage of discordant BI-RADS categories that would negatively impact clinical management. © RSNA, 2024 Supplemental material is available for this article.

Assessment of Hypoxia in Breast Cancer: Emerging Functional MR Imaging and Spectroscopy Techniques and Clinical Applications.

Breast cancer is one of the most prevalent forms of cancer affecting women worldwide. Hypoxia, a condition characterized by insufficient oxygen supply in tumor tissues, is closely associated with tumor aggressiveness, resistance to therapy, and poor clinical outcomes. Accurate assessment of tumor hypoxia can guide treatment decisions, predict therapy response, and contribute to the development of targeted therapeutic interventions. Over the years, functional magnetic resonance imaging (fMRI) and magnetic resonance spectroscopy (MRS) techniques have emerged as promising noninvasive imaging options for evaluating hypoxia in cancer. Such techniques include blood oxygen level-dependent (BOLD) MRI, oxygen-enhanced MRI (OE) MRI, chemical exchange saturation transfer (CEST) MRI, and proton MRS (1H-MRS). These may help overcome the limitations of the routinely used dynamic contrast-enhanced (DCE) MRI and diffusion-weighted imaging (DWI) techniques, contributing to better diagnosis and understanding of the biological features of breast cancer. This review aims to provide a comprehensive overview of the emerging functional MRI and MRS techniques for assessing hypoxia in breast cancer, along with their evolving clinical applications. The integration of these techniques in clinical practice holds promising implications for breast cancer management. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: Stage 1.

AI Applications to Breast MRI: Today and Tomorrow.

In breast imaging, there is an unrelenting increase in the demand for breast imaging services, partly explained by continuous expanding imaging indications in breast diagnosis and treatment. As the human workforce providing these services is not growing at the same rate, the implementation of artificial intelligence (AI) in breast imaging has gained significant momentum to maximize workflow efficiency and increase productivity while concurrently improving diagnostic accuracy and patient outcomes. Thus far, the implementation of AI in breast imaging is at the most advanced stage with mammography and digital breast tomosynthesis techniques, followed by ultrasound, whereas the implementation of AI in breast magnetic resonance imaging (MRI) is not moving along as rapidly due to the complexity of MRI examinations and fewer available dataset. Nevertheless, there is persisting interest in AI-enhanced breast MRI applications, even as the use of and indications of breast MRI continue to expand. This review presents an overview of the basic concepts of AI imaging analysis and subsequently reviews the use cases for AI-enhanced MRI interpretation, that is, breast MRI triaging and lesion detection, lesion classification, prediction of treatment response, risk assessment, and image quality. Finally, it provides an outlook on the barriers and facilitators for the adoption of AI in breast MRI. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 6.

Yield of flow cytometry in addition to cytology for lymph node sampling in patients with incidental axillary adenopathy without a concurrent diagnosis of primary breast malignancy.

PURPOSE: Non-specific lymphadenopathy is increasingly being reported especially given the COVID-19 vaccination campaign and is a diagnostic dilemma especially in oncology patients. The purpose of this study was to evaluate the diagnostic accuracy and discordance rate between fine-needle aspiration (FNA) cytology and flow cytometry (FC) immunophenotyping in axillary FNA in patients with morphologically abnormal axillary lymph nodes on imaging and no concurrent diagnosis of primary breast malignancy. METHODS: This retrospective study included 222 patients who underwent screening or diagnostic axillary ultrasound that yielded suspicious lymphadenopathy without concurrent or recent prior diagnosis of breast cancer and who had subsequent image-guided axillary FNA and FC. Diagnostic accuracy, sensitivity, specificity, and positive and negative predictive value (PPV and NPV) were reported for FNA with cytology alone, and FC alone, and in combination. Discordance rate between FNA cytology and FC was assessed. Discordant cases were evaluated with histology or clinical and imaging follow-up. RESULTS: Diagnostic sensitivity, specificity, PPV, NPV, and diagnostic accuracy were 88%, 92%, 77%, 96%, and 91%, for FNA alone, 98%, 98%, 92%, 99%, and 98% for FC alone, and 100%, 92%, 79%, 100%, and 94% when combined. The overall discordance rate between FNA and FC was 7% (16/222). 7/16 (44%) patients with discordant results were diagnosed with lymphoma, while 9/16 (56%) patients with discordant results had benign findings. CONCLUSION: With a diagnostic accuracy of 91%, FNA with cytology is sufficient to screen patients with indeterminate and incidental lymphadenopathy. Flow cytometry could be initially deferred in patients with low pretest probability of lymphoma.

A survey by the European Society of Breast Imaging on the implementation of breast diffusion-weighted imaging in clinical practice.

OBJECTIVES: To perform a survey among all European Society of Breast Imaging (EUSOBI) radiologist members to gather representative data regarding the clinical use of breast DWI. METHODS: An online questionnaire was developed by two board-certified radiologists, reviewed by the EUSOBI board and committees, and finally distributed among EUSOBI active and associated (not based in Europe) radiologist members. The questionnaire included 20 questions pertaining to technical preferences (acquisition time, magnet strength, breast coils, number of b values), clinical indications, imaging evaluation, and reporting. Data were analyzed using descriptive statistics, the Chi-square test of independence, and Fisher's exact test. RESULTS: Of 1411 EUSOBI radiologist members, 275/1411 (19.5%) responded. Most (222/275, 81%) reported using DWI as part of their routine protocol. Common indications for DWI include lesion characterization (using an ADC threshold of 1.2-1.3 × 10-3 mm2/s) and prediction of response to chemotherapy. Members most commonly acquire two separate b values (114/217, 53%), with b value = 800 s/mm2 being the preferred value for appraisal among those acquiring more than two b values (71/171, 42%). Most did not use synthetic b values (169/217, 78%). While most mention hindered diffusion in the MRI report (161/213, 76%), only 142/217 (57%) report ADC values. CONCLUSION: The utilization of DWI in clinical practice among EUSOBI radiologists who responded to the survey is generally in line with international recommendations, with the main application being the differentiation of benign and malignant enhancing lesions, treatment response assessment, and prediction of response to chemotherapy. Report integration of qualitative and quantitative DWI data is not uniform. KEY POINTS: • Clinical performance of breast DWI is in good agreement with the current recommendations of the EUSOBI International Breast DWI working group. • Breast DWI applications in clinical practice include the differentiation of benign and malignant enhancing, treatment response assessment, and prediction of response to chemotherapy. • Report integration of DWI results is not uniform.

Diagnostic value of radiomics and machine learning with dynamic contrast-enhanced magnetic resonance imaging for patients with atypical ductal hyperplasia in predicting malignant upgrade.

PURPOSE: To investigate whether radiomics features extracted from magnetic resonance imaging (MRI) of patients with biopsy-proven atypical ductal hyperplasia (ADH) coupled with machine learning can differentiate high-risk lesions that will upgrade to malignancy at surgery from those that will not, and to determine if qualitatively and semi-quantitatively assessed imaging features, clinical factors, and image-guided biopsy technical factors are associated with upgrade rate. METHODS: This retrospective study included 127 patients with 139 breast lesions yielding ADH at biopsy who were assessed with multiparametric MRI prior to biopsy. Two radiologists assessed all lesions independently and with a third reader in consensus according to the BI-RADS lexicon. Univariate analysis and multivariate modeling were performed to identify significant radiomic features to be included in a machine learning model to discriminate between lesions that upgraded to malignancy on surgery from those that did not. RESULTS: Of 139 lesions, 28 were upgraded to malignancy at surgery, while 111 were not upgraded. Diagnostic accuracy was 53.6%, specificity 79.2%, and sensitivity 15.3% for the model developed from pre-contrast features, and 60.7%, 86%, and 22.8% for the model developed from delta radiomics datasets. No significant associations were found between any radiologist-assessed lesion parameters and upgrade status. There was a significant correlation between the number of specimens sampled during biopsy and upgrade status (p = 0.003). CONCLUSION: Radiomics analysis coupled with machine learning did not predict upgrade status of ADH. The only significant result from this analysis is between the number of specimens sampled during biopsy procedure and upgrade status at surgery.

Diagnostic value of diffusion-weighted imaging with synthetic b-values in breast tumors: comparison with dynamic contrast-enhanced and multiparametric MRI.

OBJECTIVES: To assess DWI for tumor visibility and breast cancer detection by the addition of different synthetic b-values. METHODS: Eighty-four consecutive women who underwent a breast-multiparametric-MRI (mpMRI) with enhancing lesions on DCE-MRI (BI-RADS 2-5) were included in this IRB-approved retrospective study from September 2018 to March 2019. Three readers evaluated DW acquired b-800 and synthetic b-1000, b-1200, b-1500, and b-1800 s/mm2 images for lesion visibility and preferred b-value based on lesion conspicuity. Image quality (1-3 scores) and breast composition (BI-RADS) were also recorded. Diagnostic parameters for DWI were determined using a 1-5 malignancy score based on qualitative imaging parameters (acquired + preferred synthetic b-values) and ADC values. BI-RADS classification was used for DCE-MRI and quantitative ADC values + BI-RADS were used for mpMRI. RESULTS: Sixty-four malignant (average = 23 mm) and 39 benign (average = 8 mm) lesions were found in 80 women. Although b-800 achieved the best image quality score, synthetic b-values 1200-1500 s/mm2 were preferred for lesion conspicuity, especially in dense breast. b-800 and synthetic b-1000/b-1200 s/mm2 values allowed the visualization of 84-90% of cancers visible with DCE-MRI performing better than b-1500/b-1800 s/mm2. DWI was more specific (86.3% vs 65.7%, p < 0.001) but less sensitive (62.8% vs 90%, p < 0.001) and accurate (71% vs 80.7%, p = 0.003) than DCE-MRI for breast cancer detection, where mpMRI was the most accurate modality accounting for less false positive cases. CONCLUSION: The addition of synthetic b-values enhances tumor conspicuity and could potentially improve tumor visualization particularly in dense breast. However, its supportive role for DWI breast cancer detection is still not definite. KEY POINTS: • The addition of synthetic b-values (1200-1500 s/mm2) to acquired DWI afforded a better lesion conspicuity without increasing acquisition time and was particularly useful in dense breasts. • Despite the use of synthetic b-values, DWI was less sensitive and accurate than DCE-MRI for breast cancer detection. • A multiparametric MRI modality still remains the best approach having the highest accuracy for breast cancer detection and thus reducing the number of unnecessary biopsies.

MRI background parenchymal enhancement, fibroglandular tissue, and mammographic breast density in patients with invasive lobular breast cancer on adjuvant endocrine hormonal treatment: associations with survival.

BACKGROUND: To investigate if baseline and/or changes in contralateral background parenchymal enhancement (BPE) and fibroglandular tissue (FGT) measured on magnetic resonance imaging (MRI) and mammographic breast density (MD) can be used as imaging biomarkers for overall and recurrence-free survival in patients with invasive lobular carcinomas (ILCs) undergoing adjuvant endocrine treatment. METHODS: Women who fulfilled the following inclusion criteria were included in this retrospective HIPAA-compliant IRB-approved study: unilateral ILC, pre-treatment breast MRI and/or mammography from 2000 to 2010, adjuvant endocrine treatment, follow-up MRI, and/or mammography 1-2 years after treatment onset. BPE, FGT, and mammographic MD of the contralateral breast were independently graded by four dedicated breast radiologists according to BI-RADS. Associations between the baseline levels and change in levels of BPE, FGT, and MD with overall survival and recurrence-free survival were assessed using Kaplan-Meier survival curves and Cox regression analysis. RESULTS: Two hundred ninety-eight patients (average age = 54.1 years, range = 31-79) fulfilled the inclusion criteria. The average follow-up duration was 11.8 years (range = 2-19). Baseline and change in levels of BPE, FGT, and MD were not significantly associated with recurrence-free or overall survival. Recurrence-free and overall survival were affected by histological subtype (p < 0.0001), number of metastatic axillary lymph nodes (p < 0.0001), age (p = 0.01), and adjuvant endocrine treatment duration (p < 0.001). CONCLUSIONS: Qualitative evaluation of BPE, FGT, and mammographic MD changes cannot predict which patients are more likely to benefit from adjuvant endocrine treatment.

Improved characterization of sub-centimeter enhancing breast masses on MRI with radiomics and machine learning in BRCA mutation carriers.

OBJECTIVES: To investigate whether radiomics features extracted from MRI of BRCA-positive patients with sub-centimeter breast masses can be coupled with machine learning to differentiate benign from malignant lesions using model-free parameter maps. METHODS: In this retrospective study, BRCA-positive patients who had an MRI from November 2013 to February 2019 that led to a biopsy (BI-RADS 4) or imaging follow-up (BI-RADS 3) for sub-centimeter lesions were included. Two radiologists assessed all lesions independently and in consensus according to BI-RADS. Radiomics features were calculated using open-source CERR software. Univariate analysis and multivariate modeling were performed to identify significant radiomics features and clinical factors to be included in a machine learning model to differentiate malignant from benign lesions. RESULTS: Ninety-six BRCA mutation carriers (mean age at biopsy = 45.5 ± 13.5 years) were included. Consensus BI-RADS classification assessment achieved a diagnostic accuracy of 53.4%, sensitivity of 75% (30/40), specificity of 42.1% (32/76), PPV of 40.5% (30/74), and NPV of 76.2% (32/42). The machine learning model combining five parameters (age, lesion location, GLCM-based correlation from the pre-contrast phase, first-order coefficient of variation from the 1st post-contrast phase, and SZM-based gray level variance from the 1st post-contrast phase) achieved a diagnostic accuracy of 81.5%, sensitivity of 63.2% (24/38), specificity of 91.4% (64/70), PPV of 80.0% (24/30), and NPV of 82.1% (64/78). CONCLUSIONS: Radiomics analysis coupled with machine learning improves the diagnostic accuracy of MRI in characterizing sub-centimeter breast masses as benign or malignant compared with qualitative morphological assessment with BI-RADS classification alone in BRCA mutation carriers. KEY POINTS: • Radiomics and machine learning can help differentiate benign from malignant breast masses even if the masses are small and morphological features are benign. • Radiomics and machine learning analysis showed improved diagnostic accuracy, specificity, PPV, and NPV compared with qualitative morphological assessment alone.

Hereditary lobular breast cancer with an emphasis on E-cadherin genetic defect.

Recent studies have reported germline CDH1 mutations in cases of lobular breast cancer (LBC) not associated with the classical hereditary diffuse gastric cancer syndrome. A multidisciplinary workgroup discussed genetic susceptibility, pathophysiology and clinical management of hereditary LBC (HLBC). The team has established the clinical criteria for CDH1 screening and results' interpretation, and created consensus guidelines regarding genetic counselling, breast surveillance and imaging techniques, clinicopathological findings, psychological and decisional support, as well as prophylactic surgery and plastic reconstruction. Based on a review of current evidence for the identification of HLBC cases/families, CDH1 genetic testing is recommended in patients fulfilling the following criteria: (A) bilateral LBC with or without family history of LBC, with age at onset <50 years, and (B) unilateral LBC with family history of LBC, with age at onset <45 years. In CDH1 asymptomatic mutant carriers, breast surveillance with clinical examination, yearly mammography, contrast-enhanced breast MRI and breast ultrasonography (US) with 6-month interval between the US and the MRI should be implemented as a first approach. In selected cases with personal history, family history of LBC and CDH1 mutations, prophylactic mastectomy could be discussed with an integrative group of clinical experts. Psychodecisional support also plays a pivotal role in the management of individuals with or without CDH1 germline alterations. Ultimately, the definition of a specific protocol for CDH1 genetic screening and ongoing coordinated management of patients with HLBC is crucial for the effective surveillance and early detection of LBC.

Dual-Energy CT: Spectrum of Thoracic Abnormalities.

Recent studies have demonstrated that dual-energy computed tomography (CT) can provide useful information in several chest-related clinical indications. Compared with single-energy CT, dual-energy CT of the chest is feasible with the use of a radiation-dose-neutral scanning protocol. This article highlights the different types of images that can be generated by using dual-energy CT protocols such as virtual monochromatic, virtual unenhanced (ie, water), and pulmonary blood volume (ie, iodine) images. The physical basis of dual-energy CT and material decomposition are explained. The advantages of the use of virtual low-monochromatic images include reduced volume of intravenous contrast material and improved contrast resolution of images. The use of virtual high-monochromatic images can reduce beam hardening and contrast streak artifacts. The pulmonary blood volume images can help differentiate various parenchymal abnormalities, such as infarcts, atelectasis, and pneumonias, as well as airway abnormalities. The pulmonary blood volume images allow quantitative and qualitative assessment of iodine distribution. The estimation of iodine concentration (quantitative assessment) provides objective analysis of enhancement. The advantages of virtual unenhanced images include differentiation of calcifications, talc, and enhanced thoracic structures. Dual-energy CT has applications in oncologic imaging, including diagnosis of thoracic masses, treatment planning, and assessment of response to treatment. Understanding the concept of dual-energy CT and its clinical application in the chest are the goals of this article.

Reliability of body size measurements obtained at autopsy: impact on the pathologic assessment of the heart.

Purpose Assessment of body size at autopsy is important for interpreting organ weight measurements and in some cases body identification. The reliability of post-mortem body size measurements, the causes for perturbations in these measurements from their corresponding pre-mortem values, and the impact of such perturbations on heart weight interpretation have not been fully explored. Methods Autopsy body length and weight measurements and pre-mortem height and body weight measurements were compared in 132 autopsies. Clinical records were evaluated for peripheral edema and serum albumin levels. Causes of death, body cavity fluid collections, and heart weights were obtained from the autopsy reports. A subset of patients underwent quantitative post-mortem computed tomography assessment of anasarca. Results At autopsy, body weight differed from the pre-mortem value by 11 ± 1 %, compared with -0.2 ± 0.3 % for body length (P < 0.0001). The percent change in body weight at autopsy correlated with the presence of peripheral edema (14 ± 2 % vs. 7 ± 2 %, P = 0.01), serum albumin < 3.0 g/dL (16 ± 2 % vs. 7 ± 2 %, P = 0.001), and the degree of anasarca (P = 0.01). In 4 % of autopsies, heart weights were abnormal based on the pre-mortem body weight, but would be classified as normal based on the elevated post-mortem body weight. Conclusions At autopsy, body weight is a less reliable parameter than body length in correlating with the corresponding pre-mortem measurement. Autopsy body weights are elevated in part due to peripheral edema/anasarca. Alterations in body weight at autopsy can confound the interpretation of organ weight measurements.

Quantification of interstitial fluid on whole body CT: comparison with whole body autopsy.

PURPOSE: Interstitial fluid accumulation can occur in pleural, pericardial, and peritoneal spaces, and subcutaneous tissue planes. The purpose of the study was to assess if whole body CT examination in a postmortem setting could help determine the presence and severity of third space fluid accumulation in the body. MATERIALS AND METHODS: Our study included 41 human cadavers (mean age 61 years, 25 males and 16 females) who had whole-body postmortem CT prior to autopsy. All bodies were maintained in the morgue in the time interval between death and autopsy. Two radiologists reviewed the whole-body CT examinations independently to grade third space fluid in the pleura, pericardium, peritoneum, and subcutaneous space using a 5-point grading system. Qualitative CT grading for third space fluid was correlated with the amount of fluid found on autopsy and the quantitative CT fluid volume, estimated using a dedicated software program (Volume, Syngo Explorer, Siemens Healthcare). RESULTS: Moderate and severe peripheral edema was seen in 16/41 and 7/41 cadavers respectively. It is not possible to quantify anasarca at autopsy. Correlation between imaging data for third space fluid and the quantity of fluid found during autopsy was 0.83 for pleural effusion, 0.4 for pericardial effusion and 0.9 for ascites. The degree of anasarca was significantly correlated with the severity of ascites (p < 0.0001) but not with pleural or pericardial effusion. There was strong correlation between volumetric estimation and qualitative grading for anasarca (p < 0.0001) and pleural effusion (p < 0.0001). CONCLUSION: Postmortem CT can help in accurate detection and quantification of third space fluid accumulation. The quantity of ascitic fluid on postmortem CT can predict the extent of anasarca.

Can the unenhanced phase be eliminated from dual-phase CT angiography for chest pain? Implications for diagnostic accuracy in acute aortic intramural hematoma.

OBJECTIVE: The purposes of this study were to retrospectively assess the frequency of acute aortic intramural hematoma and evaluate whether the elimination of the unenhanced imaging acquisition series from the dual-phase MDCT angiography (CTA) protocol for chest pain might affect diagnostic accuracy in detecting intramural hematoma and justify the reduced radiation dose. MATERIALS AND METHODS: From October 2006 to November 2012, 306 patients (mean age, 65.0 years) with acute chest pain underwent emergency CTA with a 64-MDCT scanner. Two experienced cardiovascular radiologists, blinded to the diagnosis, assessed the images in two different sessions in which enhanced (single-phase CTA) and combined unenhanced and contrast-enhanced (dual-phase CTA) findings were evaluated. Sensitivity, specificity, and accuracy along with 95% CIs were calculated. Surgical and pathologic diagnoses, including findings at clinical follow-up and any subsequent imaging modality, were used as reference standards. RESULTS: Thirty-six patients were suspected of having intramural hematoma; 16 patients underwent both surgery and transesophageal echocardiography (TEE), and the remaining 20 underwent TEE. Single-phase CTA showed a higher number of false-negative and false-positive results than dual-phase CTA. With intramural hematoma frequency of 12% (95% CI, 8.38-15.91%), sensitivity, specificity, and accuracy were 94.4% (81.3-99.3%), 99.3% (97.4-99.9%), and 98.7% (96.7-99.6%) for combined dual-phase CTA and 68.4% (51.4-82.5%), 96.3% (93.2-98.2%), and 92.8% (89.3-95.4%) for single-phase CTA. Dual-phase was significantly better than single-phase CTA with respect to sensitivity (p=0.002), specificity (p=0.008), overall accuracy (p<0.001), and interrater agreement (p=0.001). CONCLUSION: The frequency of acute aortic intramural hematoma is similar to that previously reported. The acquisition of unenhanced images during the chest pain dual-phase CTA protocol significantly improves diagnostic accuracy over single-phase CTA.

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.

Current Status of Cancer Genomics and Imaging Phenotypes: What Radiologists Need to Know.

Ongoing discoveries in cancer genomics and epigenomics have revolutionized clinical oncology and precision health care. This knowledge provides unprecedented insights into tumor biology and heterogeneity within a single tumor, among primary and metastatic lesions, and among patients with the same histologic type of cancer. Large-scale genomic sequencing studies also sparked the development of new tumor classifications, biomarkers, and targeted therapies. Because of the central role of imaging in cancer diagnosis and therapy, radiologists need to be familiar with the basic concepts of genomics, which are now becoming the new norm in oncologic clinical practice. By incorporating these concepts into clinical practice, radiologists can make their imaging interpretations more meaningful and specific, facilitate multidisciplinary clinical dialogue and interventions, and provide better patient-centric care. This review article highlights basic concepts of genomics and epigenomics, reviews the most common genetic alterations in cancer, and discusses the implications of these concepts on imaging by organ system in a case-based manner. This information will help stimulate new innovations in imaging research, accelerate the development and validation of new imaging biomarkers, and motivate efforts to bring new molecular and functional imaging methods to clinical radiology. Keywords: Oncology, Cancer Genomics, Epignomics, Radiogenomics, Imaging Markers Supplemental material is available for this article. © RSNA, 2023.

Evaluation of cancer outcome assessment using MRI: A review of deep-learning methods.

Accurate evaluation of tumor response to treatment is critical to allow personalized treatment regimens according to the predicted response and to support clinical trials investigating new therapeutic agents by providing them with an accurate response indicator. Recent advances in medical imaging, computer hardware, and machine-learning algorithms have resulted in the increased use of these tools in the field of medicine as a whole and specifically in cancer imaging for detection and characterization of malignant lesions, prognosis, and assessment of treatment response. Among the currently available imaging techniques, magnetic resonance imaging (MRI) plays an important role in the evaluation of treatment assessment of many cancers, given its superior soft-tissue contrast and its ability to allow multiplanar imaging and functional evaluation. In recent years, deep learning (DL) has become an active area of research, paving the way for computer-assisted clinical and radiological decision support. DL can uncover associations between imaging features that cannot be visually identified by the naked eye and pertinent clinical outcomes. The aim of this review is to highlight the use of DL in the evaluation of tumor response assessed on MRI. In this review, we will first provide an overview of common DL architectures used in medical imaging research in general. Then, we will review the studies to date that have applied DL to magnetic resonance imaging for the task of treatment response assessment. Finally, we will discuss the challenges and opportunities of using DL within the clinical workflow.

Breast Lesion Classification with Multiparametric Breast MRI Using Radiomics and Machine Learning: A Comparison with Radiologists' Performance.

This multicenter retrospective study compared the performance of radiomics analysis coupled with machine learning (ML) with that of radiologists for the classification of breast tumors. A total of 93 consecutive women (mean age: 49 ± 12 years) with 104 histopathologically verified enhancing lesions (mean size: 22.8 ± 15.1 mm), classified as suspicious on multiparametric breast MRIs were included. Two experienced breast radiologists assessed all of the lesions, assigning a Breast Imaging Reporting and Database System (BI-RADS) suspicion category, providing a diffusion-weighted imaging (DWI) score based on lesion signal intensity, and determining the apparent diffusion coefficient (ADC). Ten predictive models for breast lesion discrimination were generated using radiomic features extracted from the multiparametric MRI. The area under the receiver operating curve (AUC) and the accuracy were compared using McNemar's test. Multiparametric radiomics with DWI score and BI-RADS (accuracy = 88.5%; AUC = 0.93) and multiparametric radiomics with ADC values and BI-RADS (accuracy= 88.5%; AUC = 0.96) models showed significant improvements in diagnostic accuracy compared to the multiparametric radiomics (DWI + DCE data) model (p = 0.01 and p = 0.02, respectively), but performed similarly compared to the multiparametric assessment by radiologists (accuracy = 85.6%; AUC = 0.03; p = 0.39). In conclusion, radiomics analysis coupled with the ML of multiparametric MRI could assist in breast lesion discrimination, especially for less experienced readers of breast MRIs.

Limited value of multiparametric MRI with dynamic contrast-enhanced and diffusion-weighted imaging in non-mass enhancing breast tumors.

PURPOSE: To investigate the diagnostic value of multiparametric MRI (mpMRI) including dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and diffusion-weighted imaging (DWI) in non-mass enhancing breast tumors. METHOD: Patients who underwent mpMRI, who were diagnosed with a suspicious non-mass enhancement (NME) on DCE-MRI (BI-RADS 4/5), and who subsequently underwent image-guided biopsy were retrospectively included. Two radiologists independently evaluated all NMEs, on both DCE-MR images and high-b-value DW images. Different mpMRI reading approaches were evaluated: 1) with a fixed apparent diffusion coefficient (ADC) threshold (<1.3 malignant, ≥1.3 benign) based on the recommendation by the European Society of Breast Imaging (EUSOBI); 2) with a fixed ADC threshold (<1.5 malignant, ≥1.5 benign) based on recently published trial data; 3) with an ADC threshold adapted to the assigned BI-RADS classification using a previously published reading method; and 4) with individually determined best thresholds for each reader. RESULTS: The final study sample consisted of 66 lesions in 66 patients. DCE-MRI alone had the highest sensitivity for breast cancer detection (94.8-100 %), outperforming all mpMRI reading approaches (R1 74.4-87.1 %, R2 71.7-94.8 %) and DWI alone (R1 74.4 %, R2 79.4 %). The adapted approach achieved the best specificity for both readers (85.1 %), resulting in the best diagnostic accuracy for R1 (86.5 %) but a moderate diagnostic accuracy for R2 (77.2 %). CONCLUSION: mpMRI has limited added diagnostic value to DCE-MRI in the assessment of NME.

Radiologist-Level Performance by Using Deep Learning for Segmentation of Breast Cancers on MRI Scans.

PURPOSE: To develop a deep network architecture that would achieve fully automated radiologist-level segmentation of cancers at breast MRI. MATERIALS AND METHODS: In this retrospective study, 38 229 examinations (composed of 64 063 individual breast scans from 14 475 patients) were performed in female patients (age range, 12-94 years; mean age, 52 years ± 10 [standard deviation]) who presented between 2002 and 2014 at a single clinical site. A total of 2555 breast cancers were selected that had been segmented on two-dimensional (2D) images by radiologists, as well as 60 108 benign breasts that served as examples of noncancerous tissue; all these were used for model training. For testing, an additional 250 breast cancers were segmented independently on 2D images by four radiologists. Authors selected among several three-dimensional (3D) deep convolutional neural network architectures, input modalities, and harmonization methods. The outcome measure was the Dice score for 2D segmentation, which was compared between the network and radiologists by using the Wilcoxon signed rank test and the two one-sided test procedure. RESULTS: The highest-performing network on the training set was a 3D U-Net with dynamic contrast-enhanced MRI as input and with intensity normalized for each examination. In the test set, the median Dice score of this network was 0.77 (interquartile range, 0.26). The performance of the network was equivalent to that of the radiologists (two one-sided test procedures with radiologist performance of 0.69-0.84 as equivalence bounds, P < .001 for both; n = 250). CONCLUSION: When trained on a sufficiently large dataset, the developed 3D U-Net performed as well as fellowship-trained radiologists in detailed 2D segmentation of breast cancers at routine clinical MRI.Keywords: MRI, Breast, Segmentation, Supervised Learning, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning AlgorithmsPublished under a CC BY 4.0 license. Supplemental material is available for this article.