Prediction of Upstaging in Ductal Carcinoma in Situ Based on Mammographic Radiomic Features

Preoperative MRI to Predict Upstaging of DCIS to Invasive Cancer at Surgery

BACKGROUND

Ductal carcinoma in situ (DCIS) is overtreated, in part because of inability to predict which DCIS cases diagnosed at core needle biopsy (CNB) will be upstaged at excision. This study aimed to determine whether quantitative magnetic resonance imaging (MRI) features can identify DCIS at risk of upstaging to invasive cancer.

METHODS

This prospective observational clinical trial analyzed women with a diagnosis of DCIS on CNB. All the participants underwent preoperative 3T MRI. Quantitative MRI features from routine dynamic contrast-enhanced (DCE) MR images (e.g., peak percent enhancement [PE]) and from advanced high temporal-resolution DCE MR images (e.g., Ktrans) were measured. Clinical, pathologic, and mammographic features were reviewed. Associations with upstaging were summarized using the area under the receiver operating characteristic curve (AUC).

RESULTS

Of 58 DCIS lesions at CNB, 15 (26%) were upstaged to invasive cancer at surgery. Of the 58 lesions, 46 (79%) enhanced on MRI, although enhancement alone was not significantly associated with upstaging (p = 0.71). Among the DCIS lesions that enhanced, higher PE was most strongly associated with upstaging (AUC, 0.81; adjusted p = 0.009) and outperformed MRI features acquired via high temporal resolution DCE-MRI (AUC, 0.50-0.73). Lesion span on MRI was not significantly associated with upstaging risk (AUC, 0.55; adjusted p = 0.61), nor were any clinical, pathologic, or mammographic features (p > 0.24).

CONCLUSIONS

Quantitative features acquired from routine clinical breast MRI and advanced DCE-MRI demonstrated good performance in identifying which DCIS lesions were upstaged to invasive cancer at excision. These features may prove valuable for appropriate selection of active surveillance in future DCIS de-escalation trials.

MRI-based Radiomic Features for Risk Stratification of Ductal Carcinoma in Situ in a Multicenter Setting (ECOG-ACRIN E4112 Trial)

Background Ductal carcinoma in situ (DCIS) is a nonlethal, preinvasive breast cancer for which breast MRI is best suited for accurate disease extent characterization. DCIS is often overtreated, necessitating robust models for improved risk stratification. Purpose To develop logistic regression models using clinical and MRI-based radiomic features of DCIS and to evaluate the performance of such models in predicting disease upstaging at surgery and DCIS score. Materials and Methods This study is a secondary analysis of dynamic contrast-enhanced (DCE) MRI data from the Eastern Cooperative Oncology Group-American College of Radiology Imaging Network, or ECOG-ACRIN, E4112 trial. Primary analysis focused on predicting disease upstaging (n = 295), and secondary analysis focused on predicting DCIS score (n = 174). Radiologist-drawn lesion segmentations and publicly available Cancer Phenomics Toolkit, or CaPTk, software was used to compute 65 radiomic features. Participants were clustered into groups based on their radiomic features (ie, radiomic phenotypes), and principal component analysis was used to summarize the feature space. Clinical information and qualitative MRI features were available. Associations were tested using χ2 and likelihood ratio tests. Data were split into training and test sets with a 3:2 ratio, and model performance was assessed on the test set using the area under the receiver operating characteristic curve (AUC). Results Data from 297 female participants with median age of 60 years (IQR, 51-67 years) were analyzed. Two radiomic phenotypes were identified that were associated with disease upstaging (P = .007). For predicting disease upstaging, the top three radiomic principal components combined with clinical and qualitative MRI predictors yielded the highest AUC of 0.77 (95% CI: 0.65, 0.88) among all tested models (P = .007), identifying 25% more true-negative (49 of 93 true-negative findings, 53% specificity) findings, compared with using clinical information alone (23 of 93 true-negative findings, 28% specificity). Radiomic models were not predictive of the DCIS score (P > .05). Conclusion In patients with DCIS, combining radiomic metrics with clinical information improved prediction of disease upstaging but not DCIS score. ClinicalTrials.gov Identifier: NCT02352883 Supplemental material is available for this article. ©RSNA, 2025 See also the editorial by Kim and Woo in this issue.

Conquering Overtreatment of DCIS: Lessons from PRECISION

As we cannot reliably distinguish indolent, low-risk ductal carcinoma in situ (DCIS) from potentially progressive, high-risk DCIS, all women with DCIS diagnosis undergo intensive treatment without any benefit. The PREvent ductal Carcinoma In Situ Invasive Overtreatment Now team was established to unravel DCIS biology and develop new multidisciplinary approaches for accurate risk stratification to tackle the global problem of DCIS overdiagnosis and overtreatment. See related article by Bressan et al., p. 16 See related article by Stratton et al., p. 22 See related article by Goodwin et al., p. 34.

A systematic scoping review exploring variation in practice in specimen mammography for Intraoperative Margin Analysis in Breast Conserving Surgery and the role of artificial intelligence in optimising diagnostic accuracy

PURPOSE

Specimen Mammography (SM) is commonly used in Breast Conserving Surgery (BCS) for intraoperative margin analysis. A systematic scoping review was conducted to identify sources of methodological variation in Specimen Mammography Interpretation (SMI) and assess the role of Artificial Intelligence (AI) techniques to optimise Diagnostic Accuracy (DA).

METHODS

Embase, Pubmed, Cochrane and web of science databases were searched. Studies were included if SM was used for margin analysis for BCS with reported DA compared with pathological margin status and data extracted.

RESULTS

1242 unique studies were identified, of which 40 were included. 39/40 studies did not utilise AI for SMI, with 4 studies comparing 2 relevant techniques, giving 43 non-AI study arms for analysis. There was wide variation in SM techniques, including number of views and location of SM. Specialist performing SMI in usual clinical practice was surgeon (13/39 studies;33 %), radiologist(s) (16/39;41 %), surgeon and radiologist (3/39;8 %) or not stated (7/39;18 %) which differed from the study specialist in 15/39 (38 %) of studies. Diagnostic accuracy in studies ranged from sensitivity 19-91.7 % and specificity 25-100 %.

CONCLUSIONS

There is marked variation in current techniques used for SM for intraoperative margin analysis with correspondingly disparate DA. Only 1 study applied AI to SMI, and we identify how AI could optimise SMI and a template for future work to apply AI techniques to SMI, reduce unwarranted variation and optimise DA.

Meta-analysis of contrast-enhanced ultrasound in differential diagnosis of breast adenosis and breast cancer

This systematic review and meta-analysis study aimed to determine the total capacity of contrast-enhanced ultrasound (CEUS) in the differential diagnosis of breast lesions and breast cancer. For collecting papers, four groups of keywords were searched in five databases. The required information was extracted from the selected papers. In addition to the descriptive findings, a meta-analysis was also conducted. Thirty-three of thirty-six studies (91.67%) on the differential diagnosis of various degrees and types of breast lesions showed that CEUS has proper performance. The pooled values related to the sensitivity and specificity of CEUS were computed by 88.00 and 76.17.

Radiology for Ductal Carcinoma In Situ of the Breast: Updates on Invasive Cancer Progression and Active Monitoring

Ductal carcinoma in situ (DCIS) accounts for approximately 30% of new breast cancer diagnoses. However, our understanding of how normal breast tissue evolves into DCIS and invasive cancers remains insufficient. Further, conclusions regarding the mechanisms of disease progression in terms of histopathology, genetics, and radiology are often conflicting and have implications for treatment planning. Moreover, the increase in DCIS diagnoses since the adoption of organized breast cancer screening programs has raised concerns about overdiagnosis and subsequent overtreatment. Active monitoring, a nonsurgical management strategy for DCIS, avoids surgery in favor of close imaging follow-up to de-escalate therapy and provides more treatment options. However, the two major challenges in active monitoring are identifying occult invasive cancer and patients at risk of invasive cancer progression. Subsequently, four prospective active monitoring trials are ongoing to determine the feasibility of active monitoring and refine the patient eligibility criteria and follow-up intervals. Radiologists play a major role in determining eligibility for active monitoring and reviewing surveillance images for disease progression. Trial results published over the next few years would support a new era of multidisciplinary DCIS care.

Ductal carcinoma in situ of the breast: finding the balance between overtreatment and undertreatment

Ductal carcinoma in situ (DCIS) accounts for 15-25% of all breast cancer diagnoses. Its prognosis is excellent overall, the main risk being the occurrence of local breast events, as most cases of DCIS do not progress to invasive cancer. Systematic screening has greatly increased the incidence of this non-obligate precursor of invasion, lending urgency to the need to identify DCIS that is prone to invasive progression and distinguish it from non-invasion-prone DCIS, as the latter can be overdiagnosed and therefore overtreated. Treatment strategies, including surgery, radiotherapy, and optional endocrine therapy, decrease the risk of local events, but have no effect on survival outcomes. Active surveillance is being evaluated as a possible new option for low-risk DCIS. Considerable efforts to decipher the biology of DCIS have led to a better understanding of the factors that determine its variable natural history. Given this variability, shared decision making regarding optimal, personalised treatment strategies is the most appropriate course of action. Well designed, risk-based de-escalation studies remain a major need in this field.

New Frontiers in Breast Cancer Imaging: The Rise of AI

Artificial intelligence (AI) has been implemented in multiple fields of medicine to assist in the diagnosis and treatment of patients. AI implementation in radiology, more specifically for breast imaging, has advanced considerably. Breast cancer is one of the most important causes of cancer mortality among women, and there has been increased attention towards creating more efficacious methods for breast cancer detection utilizing AI to improve radiologist accuracy and efficiency to meet the increasing demand of our patients. AI can be applied to imaging studies to improve image quality, increase interpretation accuracy, and improve time efficiency and cost efficiency. AI applied to mammography, ultrasound, and MRI allows for improved cancer detection and diagnosis while decreasing intra- and interobserver variability. The synergistic effect between a radiologist and AI has the potential to improve patient care in underserved populations with the intention of providing quality and equitable care for all. Additionally, AI has allowed for improved risk stratification. Further, AI application can have treatment implications as well by identifying upstage risk of ductal carcinoma in situ (DCIS) to invasive carcinoma and by better predicting individualized patient response to neoadjuvant chemotherapy. AI has potential for advancement in pre-operative 3-dimensional models of the breast as well as improved viability of reconstructive grafts.

Prediction of Hepatic Encephalopathy After Transjugular Intrahepatic Portosystemic Shunt Based on CT Radiomic Features of Visceral Adipose Tissue

RATIONALE AND OBJECTIVES

To evaluate the performance and clinical utility of CT radiomic features of visceral adipose tissue (VAT) in the prediction of hepatic encephalopathy (HE) after transjugular intrahepatic portosystemic shunt (TIPS).

MATERIALS AND METHODS

This multi-center study was retrospectively designed. Patients with cirrhosis who underwent TIPS were recruited from January 2015 to December 2020. Pre-TIPS contrast-enhanced CT images were collected for VAT segmentation and radiomic feature extraction. Least absolute shrinkage and selection operator regression with ten-fold cross-validation was performed to reduce dimension. Logistic regression with regularization, support vector machine, and random forest were used for model construction.

RESULTS

A total of 130 patients (90 men; mean age, 54 ± 11 years) were finally enrolled. The cohort was split into 85 patients for the training set (58 men; mean age, 53 ± 12 years) with 19 HE, 21 patients for the internal test set (17 men; mean age, 53 ± 11 years) with 5 HE, and 24 patients for the external test set (15 men; mean age, 55 ± 11 years). Ten radiomic features and C-reactive protein constituted radiomic-clinical models with the best performance. The average area under the receiver operating characteristic curve is 0.97 in the training set and 0.84 in the test sets. For a fixed sensitivity of 0.90, the specificity and negative predictive value of the model is 0.63 and 1.00, respectively; while for a fixed specificity of 0.90, the sensitivity and positive predictive value is 0.60 and 0.75, respectively.

CONCLUSION

Machine learning models based on CT radiomic features extracted from VAT can predict post-TIPS HE with satisfactory performance.

CLINICAL RELEVANCE STATEMENT

Our machine learning models based on CT radiomic features of visceral adipose tissue in patients with cirrhosis may assist in predicting hepatic encephalopathy after transjugular intrahepatic portosystemic shunt, indicating its potential in patient selection and clinical decision-making.

KEY POINTS

Radiomics of visceral adipose tissue provide great help in predicting hepatic encephalopathy after transjugular intrahepatic portosystemic shunt. The clinical-radiomic models showed satisfactory performance with an average area under the receiver operating characteristic curve of 0.84. The model can hypothetically provide 90% sensitivity and 100% negative predictive value for guiding patients who are considering transjugular intrahepatic portosystemic shunt.

Artificial intelligence-based classification of breast lesion from contrast enhanced mammography: a multicenter study

PURPOSE

The authors aimed to establish an artificial intelligence (AI)-based method for preoperative diagnosis of breast lesions from contrast enhanced mammography (CEM) and to explore its biological mechanism.

MATERIALS AND METHODS

This retrospective study includes 1430 eligible patients who underwent CEM examination from June 2017 to July 2022 and were divided into a construction set (n=1101), an internal test set (n=196), and a pooled external test set (n=133). The AI model adopted RefineNet as a backbone network, and an attention sub-network, named convolutional block attention module (CBAM), was built upon the backbone for adaptive feature refinement. An XGBoost classifier was used to integrate the refined deep learning features with clinical characteristics to differentiate benign and malignant breast lesions. The authors further retrained the AI model to distinguish in situ and invasive carcinoma among breast cancer candidates. RNA-sequencing data from 12 patients were used to explore the underlying biological basis of the AI prediction.

RESULTS

The AI model achieved an area under the curve of 0.932 in diagnosing benign and malignant breast lesions in the pooled external test set, better than the best-performing deep learning model, radiomics model, and radiologists. Moreover, the AI model has also achieved satisfactory results (an area under the curve from 0.788 to 0.824) for the diagnosis of in situ and invasive carcinoma in the test sets. Further, the biological basis exploration revealed that the high-risk group was associated with the pathways such as extracellular matrix organization.

CONCLUSIONS

The AI model based on CEM and clinical characteristics had good predictive performance in the diagnosis of breast lesions.

The features associated with mammography-occult MRI-detected newly diagnosed breast cancer analysed by comparing machine learning models with a logistic regression model

PURPOSE

To compare machine learning (ML) models with logistic regression model in order to identify the optimal factors associated with mammography-occult (i.e. false-negative mammographic findings) magnetic resonance imaging (MRI)-detected newly diagnosed breast cancer (BC).

MATERIAL AND METHODS

The present single-centre retrospective study included consecutive women with BC who underwent mammography and MRI (no more than 45 days apart) for breast cancer between January 2018 and May 2023. Various ML algorithms and binary logistic regression analysis were utilized to extract features linked to mammography-occult BC. These features were subsequently employed to create different models. The predictive value of these models was assessed using receiver operating characteristic curve analysis.

RESULTS

This study included 1957 malignant lesions from 1914 patients, with an average age of 51.64 ± 9.92 years and a range of 20-86 years. Among these lesions, there were 485 mammography-occult BCs. The optimal features of mammography-occult BC included calcification status, tumour size, mammographic density, age, lesion enhancement type on MRI, and histological type. Among the different ML models (ANN, L1-LR, RF, and SVM) and the LR-based combined model, the ANN model with RF features was found to be the optimal model. It demonstrated the best discriminative performance in predicting mammography false- negative findings, with an AUC of 0.912, an accuracy of 86.90%, a sensitivity of 85.85%, and a specificity of 84.18%.

CONCLUSION

Mammography-occult MRI-detected breast cancers have features that should be considered when performing breast MRI to improve the detection rate for breast cancer and aid in clinician management.

Deep-learning model to improve histological grading and predict upstaging of atypical ductal hyperplasia / ductal carcinoma in situ on breast biopsy

AIMS

Risk stratification of atypical ductal hyperplasia (ADH) and ductal carcinoma in situ (DCIS), diagnosed using breast biopsy, has great clinical significance. Clinical trials are currently exploring the possibility of active surveillance for low-risk lesions, whereas axillary lymph node staging may be considered during surgical planning for high-risk lesions. We aimed to develop a machine-learning algorithm based on whole-slide images of breast biopsy specimens and clinical information to predict the risk of upstaging to invasive breast cancer after wide excision.

METHODS AND RESULTS

Patients diagnosed with ADH/DCIS on breast biopsy were included in this study, comprising 592 (740 slides) and 141 (198 slides) patients in the development and independent testing cohorts, respectively. Histological grading of the lesions was independently evaluated by two pathologists. Clinical information, including biopsy method, lesion size, and Breast Imaging Reporting and Data System (BI-RADS) classification of ultrasound and mammograms, were collected. Deep DCIS consisted of three deep neural networks to evaluate nuclear grade, necrosis, and stromal reactivity. Deep DCIS output comprised five parameters: total patches, lesion extent, Deep Grade, Deep Necrosis, and Deep Stroma. Deep DCIS highly correlated with the pathologists' evaluations of both slide- and patient-level labels. All five parameters of Deep DCIS were significantly associated with upstaging to invasive carcinoma in subsequent wide excisional specimens. Using multivariate logistic regression, Deep DCIS predicted upstaging to invasive carcinoma with an area under the curve (AUC) of 0.81, outperforming pathologists' evaluation (AUC, 0.71 and 0.69). After including clinical and hormone receptor status information, performance further improved (AUC, 0.87). This combined model retained its predictive power in two subgroup analyses: the first subgroup included unequivocal DCIS (excluding cases of ADH and DCIS suspicious for microinvasion) (AUC, 0.83), while the second excluded cases of high-grade DCIS (AUC, 0.81). The model was validated in an independent testing cohort (AUC, 0.81).

CONCLUSION

This study demonstrated that deep-learning models can refine histological evaluation of ADH and DCIS on breast biopsies, which may help guide future treatment planning.

AI analytics can be used as imaging biomarkers for predicting invasive upgrade of ductal carcinoma in situ

OBJECTIVES

To evaluate whether the quantitative abnormality scores provided by artificial intelligence (AI)-based computer-aided detection/diagnosis (CAD) for mammography interpretation can be used to predict invasive upgrade in ductal carcinoma in situ (DCIS) diagnosed on percutaneous biopsy.

METHODS

Four hundred forty DCIS in 420 women (mean age, 52.8 years) diagnosed via percutaneous biopsy from January 2015 to December 2019 were included. Mammographic characteristics were assessed based on imaging features (mammographically occult, mass/asymmetry/distortion, calcifications only, and combined mass/asymmetry/distortion with calcifications) and BI-RADS assessments. Routine pre-biopsy 4-view digital mammograms were analyzed using AI-CAD to obtain abnormality scores (AI-CAD score, ranging 0-100%). Multivariable logistic regression was performed to identify independent predictive mammographic variables after adjusting for clinicopathological variables. A subgroup analysis was performed with mammographically detected DCIS.

RESULTS

Of the 440 DCIS, 117 (26.6%) were upgraded to invasive cancer. Three hundred forty-one (77.5%) DCIS were detected on mammography. The multivariable analysis showed that combined features (odds ratio (OR): 2.225, p = 0.033), BI-RADS 4c or 5 assessments (OR: 2.473, p = 0.023 and OR: 5.190, p < 0.001, respectively), higher AI-CAD score (OR: 1.009, p = 0.007), AI-CAD score ≥ 50% (OR: 1.960, p = 0.017), and AI-CAD score ≥ 75% (OR: 2.306, p = 0.009) were independent predictors of invasive upgrade. In mammographically detected DCIS, combined features (OR: 2.194, p = 0.035), and higher AI-CAD score (OR: 1.008, p = 0.047) were significant predictors of invasive upgrade.

CONCLUSION

The AI-CAD score was an independent predictor of invasive upgrade for DCIS. Higher AI-CAD scores, especially in the highest quartile of ≥ 75%, can be used as an objective imaging biomarker to predict invasive upgrade in DCIS diagnosed with percutaneous biopsy.

CRITICAL RELEVANCE STATEMENT

Noninvasive imaging features including the quantitative results of AI-CAD for mammography interpretation were independent predictors of invasive upgrade in lesions initially diagnosed as ductal carcinoma in situ via percutaneous biopsy and therefore may help decide the direction of surgery before treatment.

KEY POINTS

• Predicting ductal carcinoma in situ upgrade is important, yet there is a lack of conclusive non-invasive biomarkers. • AI-CAD scores-raw numbers, ≥ 50%, and ≥ 75%-predicted ductal carcinoma in situ upgrade independently. • Quantitative AI-CAD results may help predict ductal carcinoma in situ upgrade and guide patient management.

Translating microcalcification biomarker information into the laboratory: A preliminary assessment utilizing core biopsies obtained from sites of mammographic calcification

Rationale and objectives

The potential of breast microcalcification chemistry to provide clinically valuable intelligence is being increasingly studied. However, acquisition of crystallographic details has, to date, been limited to high brightness, synchrotron radiation sources. This study, for the first time, evaluates a laboratory-based system that interrogates histological sections containing microcalcifications. The principal objective was to determine the measurement precision of the laboratory system and assess whether this was sufficient to provide potentially clinical valuable information.

Materials and methods

Sections from 5 histological specimens from breast core biopsies obtained to evaluate mammographic calcification were examined using a synchrotron source and a laboratory-based instrument. The samples were chosen to represent a significant proportion of the known breast tissue, mineralogical landscape. Data were subsequently analysed using conventional methods and microcalcification characteristics such as crystallographic phase, chemical deviation from ideal stoichiometry and microstructure were determined.

Results

The crystallographic phase of each microcalcification (e.g., hydroxyapatite, whitlockite) was easily determined from the laboratory derived data even when a mixed phase was apparent. Lattice parameter values from the laboratory experiments agreed well with the corresponding synchrotron values and, critically, were determined to precisions that were significantly greater than required for potential clinical exploitation.

Conclusion

It has been shown that crystallographic characteristics of microcalcifications can be determined in the laboratory with sufficient precision to have potential clinical value. The work will thus enable exploitation acceleration of these latent microcalcification features as current dependence upon access to limited synchrotron resources is minimized.

Development of a Multi-Parametric ultrasonography nomogram for prediction of invasiveness in ductal carcinoma in situ

OBJECTIVE

To investigate the independent risk variables associated with the potential invasiveness of ductal carcinoma in situ (DCIS) on multi-parametric ultrasonography, and further construct a nomogram for risk assessment.

METHODS

Consecutive patients from January 2017 to December 2022 who were suspected of having ductal carcinoma in situ (DCIS) based on magnetic resonance imaging or mammography were prospectively enrolled. Histopathological findings after surgical resection served as the gold standard. Grayscale ultrasound, Doppler ultrasound, shear wave elastography (SWE), and contrast-enhanced ultrasound (CEUS) examinations were preoperative performed. Binary logistic regression was used for multifactorial analysis to identify independent risk factors from multi-parametric ultrasonography. The correlation between independent risk factors and pathological prognostic markers was analyzed. The predictive efficacy of DCIS associated with invasiveness was assessed by logistic analysis, and a nomogram was established.

RESULTS

A total of 250 DCIS lesions were enrolled from 249 patients, comprising 85 pure DCIS and 165 DCIS with invasion (DCIS-IDC), of which 41 exhibited micro-invasion. The multivariate analysis identified independent risk factors for DCIS with invasion on multi-parametric ultrasonography, including image size (>2cm), Doppler ultrasound RI (≥0.72), SWE's Emax (≥66.4 kPa), hyper-enhancement, centripetal enhancement, increased surrounding vessel, and no contrast agent retention on CEUS. These factors correlated with histological grade, Ki-67, and human epidermal growth factor receptor 2 (HER2) (P < 0.1). The multi-parametric ultrasound approach demonstrated good predictive performance (sensitivity 89.7 %, specificity 73.8 %, AUC 0.903), surpassing single US modality or combinations with SWE or CEUS modalities. Utilizing these factors, a predictive nomogram achieved a respectable performance (AUC of 0.889) for predicting DCIS with invasion. Additionally, a separate nomogram for predicting DCIS with micro-invasion, incorporating independent risk factors such as RI (≥0.72), SWE's Emax (≥65.2 kPa), and centripetal enhancement, demonstrated an AUC of 0.867.

CONCLUSION

Multi-parametric ultrasonography demonstrates good discriminatory ability in predicting both DCIS with invasion and micro-invasion through the analysis of lesion morphology, stiffness, neovascular architecture, and perfusion. The use of a nomogram based on ultrasonographic images offers an intuitive and effective method for assessing the risk of invasion in DCIS. Although the nomogram is not currently considered a clinically applicable diagnostic tool due to its AUC being below the threshold of 0.9, further research and development are anticipated to yield positive outcomes and enhance its viability for clinical utilization.

Sonography-based multimodal information platform for identifying the surgical pathology of ductal carcinoma in situ

BACKGROUND

The risk of ductal carcinoma in situ (DCIS) identified by biopsy often increases during surgery. Therefore, confirming the DCIS grade preoperatively is necessary for clinical decision-making.

PURPOSE

To train a three-classification deep learning (DL) model based on ultrasound (US), combining clinical data, mammography (MG), US, and core needle biopsy (CNB) pathology to predict low-grade DCIS, intermediate-to-high-grade DCIS, and upstaged DCIS.

MATERIALS AND METHODS

Data of 733 patients with 754 DCIS cases confirmed by biopsy were retrospectively collected from May 2013 to June 2022 (N1), and other data (N2) were confirmed by biopsy as low-grade DCIS. The lesions were randomly divided into training (n=471), validation (n=142), and test (n = 141) sets to establish the DCIS-Net. Information on the DCIS-Net, clinical (age and sign), US (size, calcifications, type, breast imaging reporting and data system [BI-RADS]), MG (microcalcifications, BI-RADS), and CNB pathology (nuclear grade, architectural features, and immunohistochemistry) were collected. Logistic regression and random forest analyses were conducted to develop Multimodal DCIS-Net to calculate the specificity, sensitivity, accuracy, receiver operating characteristic curve, and area under the curve (AUC).

RESULTS

In the test set of N1, the accuracy and AUC of the multimodal DCIS-Net were 0.752-0.766 and 0.859-0.907 in the three-classification task, respectively. The accuracy and AUC for discriminating DCIS from upstaged DCIS were 0.751-0.780 and 0.829-0.861, respectively. In the test set of N2, the accuracy and AUC of discriminating low-grade DCIS from upstaged low-grade DCIS were 0.769-0.987 and 0.818-0.939, respectively. DL was ranked from one to five in the importance of features in the multimodal-DCIS-Net.

CONCLUSION

By developing the DCIS-Net and integrating it with multimodal information, diagnosing low-grade DCIS, intermediate-to high-grade DCIS, and upstaged DCIS is possible. It can also be used to distinguish DCIS from upstaged DCIS and low-grade DCIS from upstaged low-grade DCIS, which could pave the way for the DCIS clinical workflow.

Unenhanced computed tomography radiomics help detect endoleaks after endovascular repair of abdominal aortic aneurysm

OBJECTIVES

To explore the feasibility of unenhanced CT images for endoleak detection of abdominal aortic aneurysm (AAA) after endovascular repair (EVAR).

METHODS

Patients who visited our hospital after EVAR from July 2014 to September 2021 were retrospectively collected. Two radiologists evaluated the presence or absence of endoleaks using the combination of contrast-enhanced and unenhanced CT as the referenced standard. After segmenting the aneurysm sac of the unenhanced CT, the radiomic features were automatically extracted from the region of interest. Histogram features of patients with and without endoleak were statistically analyzed to explore the differences between the two groups. Twelve common machine learning (ML) models based on radiomic features were constructed to evaluate the performance of endoleak detection with unenhanced CT images.

RESULTS

The study included 216 patients (69 ± 8 years; 191 men) with AAA, including 64 patients with endoleaks. A total of 1955 radiomic features of unenhanced CT were extracted. Compared with patients without endoleak, the aneurysm sac outside the stent of patients with endoleak had higher CT attenuation (41.7 vs. 33.6, p < 0.001) with smaller dispersion (51.5 vs. 58.8, p < 0.001). The average area under the curve (AUC) of the ML models constructed with unenhanced CT radiomics was 0.86 ± 0.05, the accuracy was 81% ± 4, the sensitivity was 88% ± 10, and the specificity was 78% ± 5. When fixing the sensitivity to > 90% (92% ± 2), the models retained specificity at 72% ± 10.

CONCLUSIONS

Unenhanced CT features exhibit significant differences between patients with and without endoleak and can help detect endoleaks in AAA after EVAR with high sensitivity.

CLINICAL RELEVANCE STATEMENT

Unenhanced CT radiomics can help provide an alternative method of endoleak detection in patients who have adverse reactions to contrast media. This study further exploits the value of unenhanced CT examinations in the clinical management and surveillance of postoperative abdominal aortic aneurysm.

KEY POINTS

• Unenhanced CT features of the aneurysm sac outside the stent exhibit significant differences between patients with and without endoleak. The endoleak group showed higher unenhanced CT attenuation (41.7 vs 33.6, p < .001) with smaller dispersion (51.5 vs 58.8, p < .001) than the nonendoleak group. • Unenhanced CT radiomics can help detect endoleaks after intervention. The average area under the curve (AUC) of twelve common machine learning models constructed with unenhanced CT radiomics was 0.86 ± 0.05, the average accuracy was 81% ± 4. • When fixing the sensitivity to > 90% (92% ± 2), the machine learning models retained average specificity at 72% ± 10.

Classification performance bias between training and test sets in a limited mammography dataset

OBJECTIVES

To assess the performance bias caused by sampling data into training and test sets in a mammography radiomics study.

METHODS

Mammograms from 700 women were used to study upstaging of ductal carcinoma in situ. The dataset was repeatedly shuffled and split into training (n = 400) and test cases (n = 300) forty times. For each split, cross-validation was used for training, followed by an assessment of the test set. Logistic regression with regularization and support vector machine were used as the machine learning classifiers. For each split and classifier type, multiple models were created based on radiomics and/or clinical features.

RESULTS

Area under the curve (AUC) performances varied considerably across the different data splits (e.g., radiomics regression model: train 0.58-0.70, test 0.59-0.73). Performances for regression models showed a tradeoff where better training led to worse testing and vice versa. Cross-validation over all cases reduced this variability, but required samples of 500+ cases to yield representative estimates of performance.

CONCLUSIONS

In medical imaging, clinical datasets are often limited to relatively small size. Models built from different training sets may not be representative of the whole dataset. Depending on the selected data split and model, performance bias could lead to inappropriate conclusions that might influence the clinical significance of the findings.

ADVANCES IN KNOWLEDGE

Performance bias can result from model testing when using limited datasets. Optimal strategies for test set selection should be developed to ensure study conclusions are appropriate.

Ultrafast MRI and T1 and T2 Radiomics for Predicting Invasive Components in Ductal Carcinoma in Situ Diagnosed With Percutaneous Needle Biopsy

OBJECTIVE

This study aimed to investigate the feasibility of ultrafast magnetic resonance imaging (MRI) and radiomic features derived from breast MRI for predicting the upstaging of ductal carcinoma in situ (DCIS) diagnosed using percutaneous needle biopsy.

MATERIALS AND METHODS

Between August 2018 and June 2020, 95 patients with 98 DCIS lesions who underwent preoperative breast MRI, including an ultrafast sequence, and subsequent surgery were included. Four ultrafast MRI parameters were analyzed: time-to-enhancement, maximum slope (MS), area under the curve for 60 s after enhancement, and time-to-peak enhancement. One hundred and seven radiomic features were extracted for the whole tumor on the first post-contrast T1WI and T2WI using PyRadiomics. Clinicopathological characteristics, ultrafast MRI findings, and radiomic features were compared between the pure DCIS and DCIS with invasion groups. Prediction models, incorporating clinicopathological, ultrafast MRI, and radiomic features, were developed. Receiver operating characteristic curve analysis and area under the curve (AUC) were used to evaluate model performance in distinguishing between the two groups using leave-one-out cross-validation.

RESULTS

Thirty-six of the 98 lesions (36.7%) were confirmed to have invasive components after surgery. Compared to the pure DCIS group, the DCIS with invasion group had a higher nuclear grade (P < 0.001), larger mean lesion size (P = 0.038), larger mean MS (P = 0.002), and different radiomic-related characteristics, including a more extensive tumor volume; higher maximum gray-level intensity; coarser, more complex, and heterogeneous texture; and a greater concentration of high gray-level intensity. No significant differences in AUCs were found between the model incorporating nuclear grade and lesion size (0.687) and the models integrating additional ultrafast MRI and radiomic features (0.680-0.732).

CONCLUSION

High nuclear grade, larger lesion size, larger MS, and multiple radiomic features were associated with DCIS upstaging. However, the addition of MS and radiomic features to the prediction model did not significantly improve the prediction performance.

Prediction of Surgical Upstaging Risk of Ductal Carcinoma In Situ Using Machine Learning Models

Objective

The purpose of this study was to build machine learning models to predict surgical upstaging risk of ductal carcinoma in situ (DCIS) to invasive cancer and to compare model performance to eligibility criteria used by the Comparison of Operative versus Monitoring and Endocrine Therapy (COMET) active surveillance trial.

Methods

Medical records were retrospectively reviewed of all women with DCIS at core-needle biopsy who underwent surgery from 2007 to 2016 at an academic medical center. Multivariable regression and machine learning models were developed to evaluate upstaging-related features and their performance was compared with that achieved using the COMET trial eligibility criteria.

Results

Of 1387 women (mean age, 57 years; range, 27-89 years), the upstaging rate of DCIS was 17% (235/1387). On multivariable analysis, upstaging-associated features were presentation of DCIS as a palpable area of concern, imaging finding of a mass, and nuclear grades 2 or 3 at biopsy (P < 0.05). If COMET trial eligibility criteria were applied to our study cohort, then 496 women (42%, 496/1175) would have been eligible for the trial, with an upstaging rate of 12% (61/496). Of the machine learning models, none had a significantly lower upstaging rate than 12%. However, if using the models to determine eligibility, then a significantly larger proportion of women (56%-87%) would have been eligible for active surveillance.

Conclusion

Use of machine learning models to determine eligibility for the COMET trial identified a larger proportion of women eligible for surveillance compared with current eligibility criteria while maintaining similar upstaging rates.

An automated surgical decision-making framework for partial or radical nephrectomy based on 3D-CT multi-level anatomical features in renal cell carcinoma

OBJECTIVES

To determine whether 3D-CT multi-level anatomical features can provide a more accurate prediction of surgical decision-making for partial or radical nephrectomy in renal cell carcinoma.

METHODS

This is a retrospective study based on multi-center cohorts. A total of 473 participants with pathologically proved renal cell carcinoma were split into the internal training and the external testing set. The training set contains 412 cases from five open-source cohorts and two local hospitals. The external testing set includes 61 participants from another local hospital. The proposed automatic analytic framework contains the following modules: a 3D kidney and tumor segmentation model constructed by 3D-UNet, a multi-level feature extractor based on the region of interest, and a partial or radical nephrectomy prediction classifier by XGBoost. The fivefold cross-validation strategy was used to get a robust model. A quantitative model interpretation method called the Shapley Additive Explanations was conducted to explore the contribution of each feature.

RESULTS

In the prediction of partial versus radical nephrectomy, the combination of multi-level features achieved better performance than any single-level feature. For the internal validation, the AUROC was 0.93 ± 0.1, 0.94 ± 0.1, 0.93 ± 0.1, 0.93 ± 0.1, and 0.93 ± 0.1, respectively, as determined by the fivefold cross-validation. The AUROC from the optimal model was 0.82 ± 0.1 in the external testing set. The tumor shape Maximum 3D Diameter plays the most vital role in the model decision.

CONCLUSIONS

The automated surgical decision framework for partial or radical nephrectomy based on 3D-CT multi-level anatomical features exhibits robust performance in renal cell carcinoma. The framework points the way towards guiding surgery through medical images and machine learning.

CLINICAL RELEVANCE STATEMENT

We proposed an automated analytic framework that can assist surgeons in partial or radical nephrectomy decision-making. The framework points the way towards guiding surgery through medical images and machine learning.

KEY POINTS

• The 3D-CT multi-level anatomical features provide a more accurate prediction of surgical decision-making for partial or radical nephrectomy in renal cell carcinoma. • The data from multicenter study and a strict fivefold cross-validation strategy, both internal validation set and external testing set, can be easily transferred to different tasks of new datasets. • The quantitative decomposition of the prediction model was conducted to explore the contribution of each extracted feature.

Artificial Intelligence in Breast Cancer Diagnosis and Personalized Medicine

Breast cancer is a significant cause of cancer-related mortality in women worldwide. Early and precise diagnosis is crucial, and clinical outcomes can be markedly enhanced. The rise of artificial intelligence (AI) has ushered in a new era, notably in image analysis, paving the way for major advancements in breast cancer diagnosis and individualized treatment regimens. In the diagnostic workflow for patients with breast cancer, the role of AI encompasses screening, diagnosis, staging, biomarker evaluation, prognostication, and therapeutic response prediction. Although its potential is immense, its complete integration into clinical practice is challenging. Particularly, these challenges include the imperatives for extensive clinical validation, model generalizability, navigating the "black-box" conundrum, and pragmatic considerations of embedding AI into everyday clinical environments. In this review, we comprehensively explored the diverse applications of AI in breast cancer care, underlining its transformative promise and existing impediments. In radiology, we specifically address AI in mammography, tomosynthesis, risk prediction models, and supplementary imaging methods, including magnetic resonance imaging and ultrasound. In pathology, our focus is on AI applications for pathologic diagnosis, evaluation of biomarkers, and predictions related to genetic alterations, treatment response, and prognosis in the context of breast cancer diagnosis and treatment. Our discussion underscores the transformative potential of AI in breast cancer management and emphasizes the importance of focused research to realize the full spectrum of benefits of AI in patient care.

Active Surveillance for Atypical Ductal Hyperplasia and Ductal Carcinoma In Situ

Atypical ductal hyperplasia (ADH) and ductal carcinoma in situ (DCIS) are relatively common breast lesions on the same spectrum of disease. Atypical ductal hyperblasia is a nonmalignant, high-risk lesion, and DCIS is a noninvasive malignancy. While a benefit of screening mammography is early cancer detection, it also leads to increased biopsy diagnosis of noninvasive lesions. Previously, treatment guidelines for both entities included surgical excision because of the risk of upgrade to invasive cancer after surgery and risk of progression to invasive cancer for DCIS. However, this universal management approach is not optimal for all patients because most lesions are not upgraded after surgery. Furthermore, some DCIS lesions do not progress to clinically significant invasive cancer. Overtreatment of high-risk lesions and DCIS is considered a burden on patients and clinicians and is a strain on the health care system. Extensive research has identified many potential histologic, clinical, and imaging factors that may predict ADH and DCIS upgrade and thereby help clinicians select which patients should undergo surgery and which may be appropriate for active surveillance (AS) with imaging. Additionally, multiple clinical trials are currently underway to evaluate whether AS for DCIS is feasible for a select group of patients. Recent advances in MRI, artificial intelligence, and molecular markers may also have an important role to play in stratifying patients and delineating best management guidelines. This review article discusses the available evidence regarding the feasibility and limitations of AS for ADH and DCIS, as well as recent advances in patient risk stratification.

Ipsilateral Recurrence of DCIS in Relation to Radiomics Features on Contrast Enhanced Breast MRI

The purpose of this retrospective study was to investigate the association between ipsilateral recurrence of ductal carcinoma in situ (DCIS) and radiomics features from DCIS and contralateral normal breast on contrast enhanced breast MR imaging. A total of 163 patients with DCIS who underwent preoperative MR imaging between January 2010 and December 2014 were included (training cohort; n = 117, validation cohort; n = 46). Radiomics features were extracted from whole tumor volume of DCIS on early dynamic T1-subtraction images and from the contralateral normal breast on precontrast T1 and early dynamic T1-subtraction images. After feature selection, a Rad-score was established by LASSO Cox regression model. Performance of Rad-score was evaluated by the receiver operating characteristic (ROC) curve and Kaplan Meier curve with log rank test. The Rad-score was significantly associated with ipsilateral recurrence free survival (RFS). The low-risk group with a low Rad-score showed higher ipsilateral RFS than the high-risk group with a high Rad-score in both training and validation cohorts (p < 0.01). The Rad-score based on radiomics features from DCIS and contralateral normal breast on breast MR imaging showed the potential for prediction of ipsilateral RFS of DCIS.