Rapid review: radiomics and breast cancer

MRI-based vector radiomics for predicting breast cancer HER2 status and its changes after neoadjuvant therapy

PURPOSE

To develop a novel MRI-based vector radiomic approach to predict breast cancer (BC) human epidermal growth factor receptor 2 (HER2) status (zero, low, and positive; task 1) and its changes after neoadjuvant therapy (NAT) (positive-to-positive, positive-to-negative, and positive-to-pathologic complete response; task 2).

MATERIALS AND METHODS

Both dynamic contrast-enhanced (DCE) MRI data and multi-b-value (MBV) diffusion-weighted imaging (DWI) data were acquired in BC patients at two centers. Vector-radiomic and conventional-radiomic features were extracted from both DCE-MRI and MBV-DWI. After feature selection, the following models were built using the retained features and logistic regression: vector model, conventional model, and combined model that integrates the vector-radiomic and conventional-radiomic features. The models' performances were quantified by the area under the receiver-operating characteristic curve (AUC).

RESULTS

The training/external test set (center 1/2) included 483/361 women. For task 1, the vector model (AUCs=0.73∼0.86) was superior to (p<.05) the conventional model (AUCs=0.68∼0.81), and the addition of vector-radiomic features to conventional-radiomic features yielded an incremental predictive value (AUCs=0.80∼0.90, p<.05). For task 2, the combined MBV-DWI model (AUCs=0.85∼0.89) performed better than (p<.05) the conventional MBV-DWI model (AUCs=0.73∼0.82). In addition, for the combined DCE-MRI model and the combined MBV-DWI model, the former (AUCs=0.85∼0.90) outperformed (p<.05) the latter (AUCs=0.80∼0.85) in task 1, whereas the latter (AUCs=0.85∼0.89) outperformed (p<.05) the former (AUCs=0.76∼0.81) in task 2. The above results are true for the training and external test sets.

CONCLUSIONS

MRI-based vector radiomics may predict BC HER2 status and its changes after NAT and provide significant incremental prediction over and above conventional radiomics.

LncRNA XIST/miR-455-3p/HOXC4 axis promotes breast cancer development by activating TGF-β/SMAD signaling pathway

Breast cancer is the second primary cause of cancer death among women. Long non-coding RNA (lncRNA) X-inactive specific transcript (XIST) is a central regulator for X chromosome inactivation, and its abnormal expression is a primary feature of breast cancer. So far, the mechanism of XIST in breast cancer has not been fully elucidated. We attempted to illustrate the mechanism of XIST in breast cancer. The expressions of XIST, microRNA-455-3p (miR-455-3p) in breast cancer were measured using quantitative real-time PCR. The expressions of homeobox C4 (HOXC4) were assessed with immunohistochemical and Western blot. Also, the functions of XIST in breast cancer were assessed by Cell Counting Kit-8 analysis, colony formation assay, flow cytometry, Western blot, Transwell, and cell scratch assays. Meanwhile, the mechanism of XIST in breast cancer was validated using database analysis and dual-luciferase reporter assay. Furthermore, the function of XIST in breast cancer in vivo was estimated by tumor xenograft model, immunohistochemical assay, and hematoxylin-eosin staining. XIST and HOXC4 expressions were increased, but miR-455-3p expressions were decreased in breast cancer tissues and cells. Knocking down XIST restrained breast cancer cell proliferation, invasion, migration, epithelial-mesenchymal transformation (EMT), and induced cell cycle arrest at G0/G1. Meanwhile, XIST interacted with miR-455-3p, while miR-455-3p interacted with HOXC4. XIST knockdown repressed breast cancer cell proliferation, invasion, and EMT, while miR-455-3p inhibitor or HOXC4 overexpression abolished those impacts. HOXC4 overexpression also blocked the impacts of miR-455-3p mimic on breast cancer cell malignant behavior. In vivo experimental data further indicated that XIST knockdown repressed breast cancer cell tumorigenic ability, and decreased HOXC4 and p-SMAD3 (TGF-β/SMAD-related protein) expressions.XIST/miR-455-3p/HOXC4 facilitated breast cancer development by activating the TGF-β/SMAD pathway.

Antibiotic profile classification of Proteus mirabilis using machine learning: An investigation into multidimensional radiomics features

Antimicrobial resistance (AMR) presents a significant threat to global healthcare. Proteus mirabilis causes catheter-associated urinary tract infections (CAUTIs) and exhibits increased antibiotic resistance. Traditional diagnostics still rely on culture-based approaches, which remain time-consuming. Here, we study the use of machine learning (ML) to classify bacterial resistance profiles using straightforward microscopic imaging of P. mirabilis for resistance classification integrated with radiomics feature analysis and ML models. From 150 P. mirabilis strains isolated from catheters of patients diagnosed with a CAUTI, 30 % displayed multidrug resistance using the standardized disk diffusion method, and 60 % showed strong biofilm activity in microtiter plate assays. As a more rapid alternative, we introduce wavelet-based and regular microscopy imaging with feature extraction/selection, following image preprocessing steps (image denoising, normalization, and mask creation). These features enable training and testing different ML models with 5-fold cross-validation for P. mirabilis resistance classification. From these models, the Random Forest (RF) algorithm exhibited the highest performance with ACC = 0.95, specificity = 0.97, sensitivity = 0.88, and AUC = 0.98 among the other ML algorithms considered in this study for P. mirabilis resistance classification. This successful application of wavelet-based feature Radiomics analysis with RF model represents a crucial step towards a precise, rapid, and cost-effective method to distinguish antibiotic resistant P. mirabilis strains.

Neurological prognosis prediction for cardiac arrest patients using quantitative imaging biomarkers from brain computed tomography

PURPOSE

We aimed to predict the neurological prognosis of cardiac arrest (CA) patients using quantitative imaging biomarkers extracted from brain computed tomography images.

METHODS

We retrospectively enrolled 86 CA patients (good prognosis, 32; poor prognosis, 54) who were treated at three hospitals between 2017 and 2019. We then extracted 1131 quantitative imaging biomarkers from whole-brain and local volumes of interest in the computed tomography images of the patients. The data were split into training and test sets containing 60 and 26 samples, respectively, and the training set was used to select representative quantitative imaging biomarkers for classification. In univariate analysis, the classification was evaluated using the p-value of the Brunner-Munzel test and area under the receiver operating characteristic curve (AUC) for the test set. In multivariate analysis, machine learning models reflecting nonlinear and complex relations were trained, and they were evaluated using the AUC on the test set.

RESULTS

The best performance provided p = 0.009 (<0.01) and an AUC of 0.775 (95% confidence interval, 0.590-0.960) for the univariate analysis and an AUCof0.813 (95% confidence interval, 0.640-0.985) for the multivariate analysis. Overall, the gray level with the maximum gradient in the histogram of the three-dimensionally low-pass-filtered image was an important feature for prediction across the analyses.

CONCLUSIONS

Quantitative imaging biomarkers can be used in neurological prognosis prediction for CA patients. Relevant biomarkers may contribute to protocolized computed tomography image acquisition to ensure proper decision support in acute care.

Research on the application of radiomics in breast cancer: A bibliometrics and visualization analysis

Breast cancer is the most prevalent form of cancer worldwide. Therefore, improved disease detection has emerged as a focal point in clinical studies. At the forefront of innovation, radiomics has the capability to extract comprehensive insights from medical images, ultimately enhancing the accuracy of diagnostic procedures. There has been rapid growth in the field of radiomics research on breast cancer in the past few years. We explored pertinent research articles in the Web of Science Core Collection database to gain a thorough understanding of breast cancer radiomics. We used CiteSpace to conduct a bibliometric analysis of the annual distribution of different nations, institutions, journals, authors, keywords, and references in the field of breast cancer radiomics. GraphPad Prism software was used to examine and graph yearly and country-specific trends and the proportions of publications. The tools utilized for the visualization of science mapping included CiteSpace and VOSviewer. Of the 891 publications, most were original articles (731, 91.09%) and a few were reviews (160, 8.91%). Most academic research has been published in China and the United States. The study centers predominantly consisted of major academic institutions, such as Fudan University and the Chinese Academy of Sciences, with some of their members being prominent figures in the field. Pinker, Katja has published the largest number of research papers. The majority of these studies have been published in medical journals focusing on radiology and oncology in recent years. In the realm of cutting-edge medical research, the top two keywords, magnetic resonance imaging and machine learning stand at the forefront as current areas of intense focus. Breast cancer radiomics is advancing rapidly, presenting numerous opportunities and obstacles. Our study of the literature in this academic area aimed to pinpoint the primary themes addressed in the studies and anticipate prospective avenues for research.

Prediction of the axillary lymph-node metastatic burden of breast cancer by 18F-FDG PET/CT-based radiomics

BACKGROUND

The axillary lymph-node metastatic burden is closely associated with treatment decisions and prognosis in breast cancer patients. This study aimed to explore the value of 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT)-based radiomics in combination with ultrasound and clinical pathological features for predicting axillary lymph-node metastatic burden in breast cancer.

METHODS

A retrospective analysis was conducted and involved 124 patients with pathologically confirmed early-stage breast cancer who had undergone 18F-FDG PET/CT examination. The ultrasound, PET/CT, and clinical pathological features of all patients were analysed, and radiomic features from PET images were extracted to establish a multi-parameter predictive model.

RESULTS

The ultrasound lymph-node positivity rate and PET lymph-node positivity rate in the high nodal burden group were significantly higher than those in the low nodal burden group (χ2 = 19.867, p < 0.001; χ2 = 33.025, p < 0.001). There was a statistically significant difference in the PET-based radiomics score (RS) for predicting axillary lymph-node burden between the high and low lymph-node burden groups. (-1.04 ± 0.41 vs. -1.47 ± 0.41, t = -4.775, p < 0.001). The ultrasound lymph-node positivity (US_LNM) (odds ratio [OR] = 3.264, 95% confidence interval [CI] = 1.022-10.423), PET lymph-node positivity (PET_LNM) (OR = 14.242, 95% CI = 2.960-68.524), and RS (OR = 5.244, 95% CI = 3.16-20.896) are all independent factors associated with high lymph-node burden (p < 0.05). The area under the curve (AUC) of the multi-parameter (MultiP) model was 0.895, which was superior to those of US_LNM, PET_LNM, and RS models (AUC = 0.703, 0.814, 0.773, respectively), with statistically significant differences (Z = 2.888, 3.208, 3.804, respectively; p = 0.004, 0.002, < 0.001, respectively). Decision curve analysis indicated that the MultiP model provided a higher net benefit for all patients.

CONCLUSION

A MultiP model based on PET-based radiomics was able to effectively predict axillary lymph-node metastatic burden in breast cancer.

TRIAL REGISTRATION

This study was registered with ClinicalTrials.gov (registration number: NCT05826197) on May 7, 2023.

The diagnostic value of multimodal imaging based on MR combined with ultrasound in benign and malignant breast diseases

We aimed to construct and validate a multimodality MRI combined with ultrasound based on radiomics for the evaluation of benign and malignant breast diseases. The preoperative enhanced MRI and ultrasound images of 131 patients with breast diseases confirmed by pathology in Aerospace Center Hospital from January 2021 to August 2023 were retrospectively analyzed, including 73 benign diseases and 58 malignant diseases. Ultrasound and 3.0 T multiparameter MRI scans were performed in all patients. Then, all the data were divided into training set and validation set in a 7:3 ratio. Regions of interest were drawn layer by layer based on ultrasound and MR enhanced sequences to extract radiomics features. The optimal radiomic features were selected by the best feature screening method. Logistic Regression classifier was used to establish models according to the best features, including ultrasound model, MRI model, ultrasound combined with MRI model. The model efficacy was evaluated by the area under the curve (AUC) of the receiver operating characteristic, sensitivity, specificity, and accuracy. The F-test based on ANOVA was used to screen out 20 best ultrasonic features, 11 best MR Features, and 14 best features from the combined model. Among them, texture features accounted for the largest proportion, accounting for 79%.The ultrasound combined with MR Image fusion model based on logistic regression classifier had the best diagnostic performance. The AUC of the training group and the validation group were 0.92 and 091, the sensitivity was 0.80 and 0.67, the specificity was 0.90 and 0.94, and the accuracy was 0.84 and 0.79, respectively. It was better than the simple ultrasound model (AUC of validation set was 0.82) or the simple MR model (AUC of validation set was 0.85). Compared with the traditional ultrasound or magnetic resonance diagnosis of breast diseases, the multimodal model of MRI combined with ultrasound based on radiomics can more accurately predict the benign and malignant breast diseases, thus providing a better basis for clinical diagnosis and treatment.

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.

Spectral CT image reconstruction using a constrained optimization approach-An algorithm for AAPM 2022 spectral CT grand challenge and beyond

BACKGROUND

CT reconstruction is of essential importance in medical imaging. In 2022, the American Association of Physicists in Medicine (AAPM) sponsored a Grand Challenge to investigate the challenging inverse problem of spectral CT reconstruction, with the aim of achieving the most accurate reconstruction results. The authors of this paper participated in the challenge and won as a runner-up team.

PURPOSE

This paper reports details of our PROSPECT algorithm (Prior-based Restricted-variable Optimization for SPEctral CT) and follow-up studies regarding the algorithm's accuracy and enhancement of its convergence speed.

METHODS

We formulated the reconstruction task as an optimization problem. PROSPECT employed a one-step backward iterative scheme to solve this optimization problem by allowing estimation of and correction for the difference between the actual polychromatic projection model and the monochromatic model used in the optimization problem. PROSPECT incorporated various forms of prior information derived by analyzing training data provided by the Grand Challenge to reduce the number of unknown variables. We investigated the impact of projection data precision on the resulting solution accuracy and improved convergence speed of the PROSPECT algorithm by incorporating a beam-hardening correction (BHC) step in the iterative process. We also studied the algorithm's performance under noisy projection data.

RESULTS

Prior knowledge allowed a reduction of the number of unknown variables by85.9 % $85.9\%$ . PROSPECT algorithm achieved the average root of mean square error (RMSE) of3.3 × 10 - 6 $3.3\,\times \,10^{-6}$ in the test data set provided by the Grand Challenge. Performing the reconstruction with the same algorithm but using double-precision projection data reduced RMSE to1.2 × 10 - 11 $1.2\,\times \,10^{-11}$ . Including the BHC step in the PROSPECT algorithm accelerated the iteration process with a 40% reduction in computation time.

CONCLUSIONS

PROSPECT algorithm achieved a high degree of accuracy and computational efficiency.

Comparative Effectiveness of Mammography, Ultrasound, and MRI in the Detection of Breast Carcinoma in Dense Breast Tissue: A Systematic Review

This systematic review aimed to critically assess the effectiveness of mammography, ultrasound, and magnetic resonance imaging (MRI) in the detection of breast carcinoma within dense breast tissue. An exhaustive search of contemporary literature was undertaken, focusing on the diagnostic accuracy, false positive and negative rates, and clinical implications of the aforementioned imaging modalities. Each modality was assessed in isolation and side by side against the others to draw comparative inferences. While mammography remains a foundational imaging modality, its effectiveness waned within the context of dense breast tissue. Ultrasound demonstrated a strong differentiation prowess, especially among specific demographic cohorts. MRI, despite its exceptional precision and differentiation capabilities, exhibited a tendency for slightly elevated false positive rates. No single modality emerged as singularly superior for all cases. Instead, an integrated approach, combining the strengths of each modality based on individual patient profiles and clinical scenarios, is recommended. This tailored approach ensures optimized detection rates and minimizes diagnostic ambiguities, underscoring the significance of individualized patient care in the field of diagnostic radiology.

Differentiation of invasive ductal and lobular carcinoma of the breast using MRI radiomic features: a pilot study

Background

Breast cancer (BC) is one of the main causes of cancer-related mortality among women. For clinical management to help patients survive longer and spend less time on treatment, early and precise cancer identification and differentiation of breast lesions are crucial. To investigate the accuracy of radiomic features (RF) extracted from dynamic contrast-enhanced Magnetic Resonance Imaging (DCE MRI) for differentiating invasive ductal carcinoma (IDC) from invasive lobular carcinoma (ILC).

Methods

This is a retrospective study. The IDC of 30 and ILC of 28 patients from Dukes breast cancer MRI data set of The Cancer Imaging Archive (TCIA), were included. The RF categories such as shape based, Gray level dependence matrix (GLDM), Gray level co-occurrence matrix (GLCM), First order, Gray level run length matrix (GLRLM), Gray level size zone matrix (GLSZM), NGTDM (Neighbouring gray tone difference matrix) were extracted from the DCE-MRI sequence using a 3D slicer. The maximum relevance and minimum redundancy (mRMR) was applied using Google Colab for identifying the top fifteen relevant radiomic features. The Mann-Whitney U test was performed to identify significant RF for differentiating IDC and ILC. Receiver Operating Characteristic (ROC) curve analysis was performed to ascertain the accuracy of RF in distinguishing between IDC and ILC.

Results

Ten DCE MRI-based RFs used in our study showed a significant difference (p <0.001) between IDC and ILC. We noticed that DCE RF, such as Gray level run length matrix (GLRLM) gray level variance (sensitivity (SN) 97.21%, specificity (SP) 96.2%, area under curve (AUC) 0.998), Gray level co-occurrence matrix (GLCM) difference average (SN 95.72%, SP 96.34%, AUC 0.983), GLCM interquartile range (SN 95.24%, SP 97.31%, AUC 0.968), had the strongest ability to differentiate IDC and ILC.

Conclusions

MRI-based RF derived from DCE sequences can be used in clinical settings to differentiate malignant lesions of the breast, such as IDC and ILC, without requiring intrusive procedures.

Machine learning-based radiomics nomograms to predict number of fields in postoperative IMRT for breast cancer

BACKGROUND

Breast cancer is now the most commonly diagnosed cancer in women worldwide. Radiotherapy is an important part of the treatment for breast cancer, while setting proper number of fields dramatically affects the benefits one can receive. Machine learning and radiomics have been widely investigated in the management of breast cancer. This study aims to provide models to predict the best number of fields based on machine learning and improve the prediction performance by adding clinical factors.

METHODS

Two-hundred forty-two breast cancer patients were retrospectively enrolled for this study, all of whom received postoperative intensity modulated radiation therapy. The patients were randomized into a training set and a validation set at a ratio of 7:3. Radiomics shape features were extracted for eight machine learning algorithms to predict the number of fields. Univariate and multivariable logistic regression were implemented to screen clinical factors. A combined model of rad-score and clinical factors were finally constructed. The area under receiver operating characteristic curve, precision, recall, F1 measure and accuracy were used to evaluate the model.

RESULTS

Random Forest outperformed from eight machine learning algorithms while predicting the number of fields. Prediction performance of the radiomics model was better than the clinical model, while the predictive nomogram combining the rad-score and clinical factors performed the best.

CONCLUSIONS

The model combining rad-score and clinical factors performed the best. Nomograms constructed from the combined models can be of reliable references for medical dosimetrists.

Combined radiomics-clinical model to predict platinum-sensitivity in advanced high-grade serous ovarian carcinoma using multimodal MRI

Introduction

We aimed to predict platinum sensitivity using routine baseline multimodal magnetic resonance imaging (MRI) and established clinical data in a radiomics framework.

Methods

We evaluated 96 patients with ovarian cancer who underwent multimodal MRI and routine laboratory tests between January 2016 and December 2020. The patients underwent diffusion-weighted, contrast-enhanced T1-weighted, and T2-weighted MRI. Subsequently, 293 radiomic features were extracted by manually identifying tumor regions of interest. The features were subjected to the least absolute shrinkage and selection operators, leaving only a few selected features. We built the first prediction model with a tree-based classifier using selected radiomics features. A second prediction model was built by combining the selected radiomic features with four established clinical factors: age, disease stage, initial tumor marker level, and treatment course. Both models were built and tested using a five-fold cross-validation.

Results

Our radiomics model predicted platinum sensitivity with an AUC of 0.65 using a few radiomics features related to heterogeneity. The second combined model had an AUC of 0.77, confirming the incremental benefits of the radiomics model in addition to models using established clinical factors.

Conclusion

Our combined radiomics-clinical data model was effective in predicting platinum sensitivity in patients with advanced ovarian cancer.

AI-powered interpretable imaging phenotypes noninvasively characterize tumor microenvironment associated with diverse molecular signatures and survival in breast cancer

BACKGROUND AND OBJECTIVES

Tumor microenvironment (TME) is a determining factor in decision-making and personalized treatment for breast cancer, which is highly intra-tumor heterogeneous (ITH). However, the noninvasive imaging phenotypes of TME are poorly understood, even invasive genotypes have been largely known in breast cancer.

METHODS

Here, we develop an artificial intelligence (AI)-driven approach for noninvasively characterizing TME by integrating the predictive power of deep learning with the explainability of human-interpretable imaging phenotypes (IMPs) derived from 4D dynamic imaging (DCE-MRI) of 342 breast tumors linked to genomic and clinical data, which connect cancer phenotypes to genotypes. An unsupervised dual-attention deep graph clustering model (DGCLM) is developed to divide bulk tumor into multiple spatially segregated and phenotypically consistent subclusters. The IMPs ranging from spatial heterogeneity to kinetic heterogeneity are leveraged to capture architecture, interaction, and proximity between intratumoral subclusters.

RESULTS

We demonstrate that our IMPs correlate with well-known markers of TME and also can predict distinct molecular signatures, including expression of hormone receptor, epithelial growth factor receptor and immune checkpoint proteins, with the performance of accuracy, reliability and transparency superior to recent state-of-the-art radiomics and 'black-box' deep learning methods. Moreover, prognostic value is confirmed by survival analysis accounting for IMPs.

CONCLUSIONS

Our approach provides an interpretable, quantitative, and comprehensive perspective to characterize TME in a noninvasive and clinically relevant manner.

The value of radiomics model based on ultrasound image features in the differentiation between minimal breast cancer and small benign breast masses

BACKGROUND

Female breast cancer has surpassed lung cancer as the most common cancer, and is also the main cause of cancer death for women worldwide. Breast cancer <1 cm showed excellent survival rate. However, the diagnosis of minimal breast cancer (MBC) is challenging.

OBJECTIVE

The purpose of our research is to develop and validate an radiomics model based on ultrasound images for early recognition of MBC.

METHODS

302 breast masses with a diameter of <10 mm were retrospectively studied, including 159 benign and 143 malignant breast masses. The radiomics features were extracted from the gray-scale ultrasound image of the largest face of each breast mass. The maximum relevance minimum reduncancy and recursive feature elimination methods were used to screen. Finally, 10 features with the most discriminating value were selected for modeling. The random forest was used to establish the prediction model, and the rad-score of each mass was calculated. In order to evaluate the effectiveness of the model, we calculated and compared the area under the curve (AUC) value, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of the model and three groups with different experience in predicting small breast masses, and drew calibration curves and decision curves to test the stability and consistency of the model.

RESULTS

When we selected 10 radiomics features to calculate the rad-score, the prediction efficiency was the best, the AUC values for the training set and testing set were 0.840 and 0.793, which was significantly better than the insufficient experience group (AUC = 0.673), slightly better than the moderate experience group (AUC = 0.768), and was inferior to the experienced group (AUC = 0.877). The calibration curve and decision curve also showed that the radiomics model had satisfied stability and clinical application value.

CONCLUSION

The radiomics model based on ultrasound image features has a satisfied predictive ability for small breast masses, and is expected to become a potential tool for the diagnosis of MBC, and it is a zero cost (in terms of patient participation and imaging time).

Construction of a comprehensive predictive model for axillary lymph node metastasis in breast cancer: a retrospective study

PURPOSE

The accurate assessment of axillary lymph node metastasis (LNM) in early-stage breast cancer (BC) is of great importance. This study aimed to construct an integrated model based on clinicopathology, ultrasound, PET/CT, and PET radiomics for predicting axillary LNM in early stage of BC.

MATERIALS AND METHODS

124 BC patients who underwent 18 F-fluorodeoxyglucose (18 F-FDG) PET/CT and whose diagnosis were confirmed by surgical pathology were retrospectively analyzed and included in this study. Ultrasound, PET and clinicopathological features of all patients were analyzed, and PET radiomics features were extracted to establish an ultrasound model (clinicopathology and ultrasound; model 1), a PET model (clinicopathology, ultrasound, and PET; model 2), and a comprehensive model (clinicopathology, ultrasound, PET, and radiomics; model 3), and the diagnostic efficacy of each model was evaluated and compared.

RESULTS

The T stage, US_BIRADS, US_LNM, and PET_LNM in the positive axillary LNM group was significantly higher than that of in the negative LNM group (P = 0.013, P = 0.049, P < 0.001, P < 0.001, respectively). Radiomics score for predicting LNM (RS_LNM) for the negative LNM and positive LNM were statistically significant difference (-1.090 ± 0.448 vs. -0.693 ± 0.344, t = -4.720, P < 0.001), and the AUC was 0.767 (95% CI: 0.674-0.861). The ROC curves showed that model 3 outperformed model 1 for the sensitivity (model 3 vs. model 1, 82.86% vs. 48.57%), and outperformed model 2 for the specificity (model 3 vs. model 2, 82.02% vs. 68.54%) in the prediction of LNM. The AUC of mode 1, model 2 and model 3 was 0.687, 0.826 and 0.874, and the Delong test showed the AUC of model 3 was significantly higher than that of model 1 and model 2 (P < 0.05). Decision curve analysis showed that model 3 resulted in a higher degree of net benefit for all the patients than model 1 and model 2.

CONCLUSION

The use of a comprehensive model based on clinicopathology, ultrasound, PET/CT, and PET radiomics can effectively improve the diagnostic efficacy of axillary LNM in BC.

TRIAL REGISTRATION

This study was registered at ClinicalTrials Gov (number NCT05826197) on 7th, May 2023.

Contrasts Between Diffusion-Weighted Imaging and Dynamic Contrast-Enhanced MR in Diagnosing Malignancies of Breast Nonmass Enhancement Lesions Based on Morphologic Assessment

BACKGROUND

Nonmass enhancement (NME) breast lesions are considered to be the leading cause of unnecessary biopsies. Diffusion-weighted imaging (DWI) or dynamic contrast-enhanced (DCE) sequences are typically used to differentiate between benign and malignant NMEs. It is important to know which one is more effective and reliable.

PURPOSE

To compare the diagnostic performance of DCE curves and DWI in discriminating benign and malignant NME lesions on the basis of morphologic characteristics assessment on contrast-enhanced (CE)-MRI images.

STUDY TYPE

Retrospective.

SUBJECTS

A total of 180 patients with 184 lesions in the training cohort and 75 patients with 77 lesions in the validation cohort with pathological results.

FIELD STRENGTH/SEQUENCE

A 3.0 T/multi-b-value DWI (b values = 0, 50, 1000, and 2000 sec/mm2 ) and time-resolved angiography with stochastic trajectories and volume-interpolated breath-hold examination (TWIST-VIBE) sequence.

ASSESSMENT

In the training cohort, a diagnostic model for morphology based on the distribution and internal enhancement characteristics was first constructed. The apparent diffusion coefficient (ADC) model (ADC + morphology) and the time-intensity curves (TIC) model (TIC + morphology) were then established using binary logistic regression with pathological results as the reference standard. Both models were compared for sensitivity, specificity, and area under the curve (AUC) in the training and the validation cohort.

STATISTICAL TESTS

Receiver operating characteristic (ROC) curve analysis and two-sample t-tests/Mann-Whitney U-test/Chi-square test were performed. P < 0.05 was considered statistically significant.

RESULTS

For the TIC/ADC model in the training cohort, sensitivities were 0.924/0.814, specificities were 0.615/0.615, and AUCs were 0.811 (95%, 0.727, 0.894)/0.769 (95%, 0.681, 0.856). The AUC of the TIC-ADC combined model was significantly higher than ADC model alone, while comparable with the TIC model (P = 0.494). In the validation cohort, the AUCs of TIC/ADC model were 0.799/0.635.

DATA CONCLUSION

Based on the morphologic analyses, the performance of the TIC model was found to be superior than the ADC model for differentiating between benign and malignant NME lesions.

EVIDENCE LEVEL

4.

TECHNICAL EFFICACY

Stage 2.

Adversarial Attack and Defense in Breast Cancer Deep Learning Systems

Deep-learning-assisted medical diagnosis has brought revolutionary innovations to medicine. Breast cancer is a great threat to women's health, and deep-learning-assisted diagnosis of breast cancer pathology images can save manpower and improve diagnostic accuracy. However, researchers have found that deep learning systems based on natural images are vulnerable to attacks that can lead to errors in recognition and classification, raising security concerns about deep systems based on medical images. We used the adversarial attack algorithm FGSM to reveal that breast cancer deep learning systems are vulnerable to attacks and thus misclassify breast cancer pathology images. To address this problem, we built a deep learning system for breast cancer pathology image recognition with better defense performance. Accurate diagnosis of medical images is related to the health status of patients. Therefore, it is very important and meaningful to improve the security and reliability of medical deep learning systems before they are actually deployed.

A novel collaborative self-supervised learning method for radiomic data

The computer-aided disease diagnosis from radiomic data is important in many medical applications. However, developing such a technique relies on labeling radiological images, which is a time-consuming, labor-intensive, and expensive process. In this work, we present the first novel collaborative self-supervised learning method to solve the challenge of insufficient labeled radiomic data, whose characteristics are different from text and image data. To achieve this, we present two collaborative pretext tasks that explore the latent pathological or biological relationships between regions of interest and the similarity and dissimilarity of information between subjects. Our method collaboratively learns the robust latent feature representations from radiomic data in a self-supervised manner to reduce human annotation efforts, which benefits the disease diagnosis. We compared our proposed method with other state-of-the-art self-supervised learning methods on a simulation study and two independent datasets. Extensive experimental results demonstrated that our method outperforms other self-supervised learning methods on both classification and regression tasks. With further refinement, our method will have the potential advantage in automatic disease diagnosis with large-scale unlabeled data available.

Progress in research on ultrasound radiomics for predicting the prognosis of breast cancer

Breast cancer is the most common malignant tumor and the leading cause of cancer-related deaths in women worldwide. Effective means of predicting the prognosis of breast cancer are very helpful in guiding treatment and improving patients' survival. Features extracted by radiomics reflect the genetic and molecular characteristics of a tumor and are related to its biological behavior and the patient's prognosis. Thus, radiomics provides a new approach to noninvasive assessment of breast cancer prognosis. Ultrasound is one of the commonest clinical means of examining breast cancer. In recent years, some results of research into ultrasound radiomics for diagnosing breast cancer, predicting lymph node status, treatment response, recurrence and survival times, and other aspects, have been published. In this article, we review the current research status and technical challenges of ultrasound radiomics for predicting breast cancer prognosis. We aim to provide a reference for radiomics researchers, promote the development of ultrasound radiomics, and advance its clinical application.

Radiomic signatures based on pretreatment 18F-FDG PET/CT, combined with clinicopathological characteristics, as early prognostic biomarkers among patients with invasive breast cancer

Purpose

The aim of this study was to investigate the predictive role of fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) in the prognostic risk stratification of patients with invasive breast cancer (IBC). To achieve this, we developed a clinicopathologic-radiomic-based model (C-R model) and established a nomogram that could be utilized in clinical practice.

Methods

We retrospectively enrolled a total of 91 patients who underwent preoperative 18F-FDG PET/CT and randomly divided them into training (n=63) and testing cohorts (n=28). Radiomic signatures (RSs) were identified using the least absolute shrinkage and selection operator (LASSO) regression algorithm and used to compute the radiomic score (Rad-score). Patients were assigned to high- and low-risk groups based on the optimal cut-off value of the receiver operating characteristic (ROC) curve analysis for both Rad-score and clinicopathological risk factors. Univariate and multivariate Cox regression analyses were performed to determine the association between these variables and progression-free survival (PFS) or overall survival (OS). We then plotted a nomogram integrating all these factors to validate the predictive performance of survival status.

Results

The Rad-score, age, clinical M stage, and minimum standardized uptake value (SUVmin) were identified as independent prognostic factors for predicting PFS, while only Rad-score, age, and clinical M stage were found to be prognostic factors for OS in the training cohort. In the testing cohort, the C-R model showed superior performance compared to single clinical or radiomic models. The concordance index (C-index) values for the C-R model, clinical model, and radiomic model were 0.816, 0.772, and 0.647 for predicting PFS, and 0.882, 0.824, and 0.754 for OS, respectively. Furthermore, decision curve analysis (DCA) and calibration curves demonstrated that the C-R model had a good ability for both clinical net benefit and application.

Conclusion

The combination of clinicopathological risks and baseline PET/CT-derived Rad-score could be used to evaluate the prognosis in patients with IBC. The predictive nomogram based on the C-R model further enhanced individualized estimation and allowed for more accurate prediction of patient outcomes.

Assessment of androgen receptor expression in breast cancer patients using 18 F-FDG PET/CT radiomics and clinicopathological characteristics

OBJECTIVE

In the present study, we mainly aimed to predict the expression of androgen receptor (AR) in breast cancer (BC) patients by combing radiomic features and clinicopathological factors in a non-invasive machine learning way.

MATERIALS AND METHODS

A total of 48 BC patients, who were initially diagnosed by ¹⁸F-FDG PET/CT, were retrospectively enrolled in this study. LIFEx software was used to extract radiomic features based on PET and CT data. The most useful predictive features were selected by the LASSO (least absolute shrinkage and selection operator) regression and t-test. Radiomic signatures and clinicopathologic characteristics were incorporated to develop a prediction model using multivariable logistic regression analysis. The receiver operating characteristic (ROC) curve, Hosmer-Lemeshow (H-L) test, and decision curve analysis (DCA) were conducted to assess the predictive efficiency of the model.

RESULTS

In the univariate analysis, the metabolic tumor volume (MTV) was significantly correlated with the expression of AR in BC patients (p < 0.05). However, there only existed feeble correlations between estrogen receptor (ER), progesterone receptor (PR), and AR status (p = 0.127, p = 0.061, respectively). Based on the binary logistic regression method, MTV, SHAPE_Sphericity_CT (CT Sphericity from SHAPE), and GLCM_Contrast_CT (CT Contrast from grey-level co-occurrence matrix) were included in the prediction model for AR expression. Among them, GLCM_Contrast_CT was an independent predictor of AR status (OR = 9.00, p = 0.018). The area under the curve (AUC) of ROC in this model was 0.832. The p-value of the H-L test was beyond 0.05.

CONCLUSIONS

A prediction model combining radiomic features and clinicopathological characteristics could be a promising approach to predict the expression of AR and noninvasively screen the BC patients who could benefit from anti-AR regimens.

What benefit can be obtained from magnetic resonance imaging diagnosis with artificial intelligence in prostate cancer compared with clinical assessments?

The present study aimed to explore the potential of artificial intelligence (AI) methodology based on magnetic resonance (MR) images to aid in the management of prostate cancer (PCa). To this end, we reviewed and summarized the studies comparing the diagnostic and predictive performance for PCa between AI and common clinical assessment methods based on MR images and/or clinical characteristics, thereby investigating whether AI methods are generally superior to common clinical assessment methods for the diagnosis and prediction fields of PCa. First, we found that, in the included studies of the present study, AI methods were generally equal to or better than the clinical assessment methods for the risk assessment of PCa, such as risk stratification of prostate lesions and the prediction of therapeutic outcomes or PCa progression. In particular, for the diagnosis of clinically significant PCa, the AI methods achieved a higher summary receiver operator characteristic curve (SROC-AUC) than that of the clinical assessment methods (0.87 vs. 0.82). For the prediction of adverse pathology, the AI methods also achieved a higher SROC-AUC than that of the clinical assessment methods (0.86 vs. 0.75). Second, as revealed by the radiomics quality score (RQS), the studies included in the present study presented a relatively high total average RQS of 15.2 (11.0-20.0). Further, the scores of the individual RQS elements implied that the AI models in these studies were constructed with relatively perfect and standard radiomics processes, but the exact generalizability and clinical practicality of the AI models should be further validated using higher levels of evidence, such as prospective studies and open-testing datasets.

An integrated radiomics nomogram based on conventional ultrasound improves discriminability between fibroadenoma and pure mucinous carcinoma in breast

Objective

To evaluate the ability of integrated radiomics nomogram based on ultrasound images to distinguish between breast fibroadenoma (FA) and pure mucinous carcinoma (P-MC).

Methods

One hundred seventy patients with FA or P-MC (120 in the training set and 50 in the test set) with definite pathological confirmation were retrospectively enrolled. Four hundred sixty-four radiomics features were extracted from conventional ultrasound (CUS) images, and radiomics score (Radscore) was constructed using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. Different models were developed by a support vector machine (SVM), and the diagnostic performance of the different models was assessed and validated. A comparison of the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) was performed to evaluate the incremental value of the different models.

Results

Finally, 11 radiomics features were selected, and then Radscore was developed based on them, which was higher in P-MC in both cohorts. In the test group, the clinic + CUS + radiomics (Clin + CUS + Radscore) model achieved a significantly higher area under the curve (AUC) value (AUC = 0.86, 95% CI, 0.733-0.942) when compared with the clinic + radiomics (Clin + Radscore) (AUC = 0.76, 95% CI, 0.618-0.869, P > 0.05), clinic + CUS (Clin + CUS) (AUC = 0.76, 95% CI, 0.618-0.869, P< 0.05), Clin (AUC = 0.74, 95% CI, 0.600-0.854, P< 0.05), and Radscore (AUC = 0.64, 95% CI, 0.492-0.771, P< 0.05) models, respectively. The calibration curve and DCA also suggested excellent clinical value of the combined nomogram.

Conclusion

The combined Clin + CUS + Radscore model may help improve the differentiation of FA from P-MC.

MRI-Based Radiomics Approach Predicts Tumor Recurrence in ER + /HER2 - Early Breast Cancer Patients

Oncotype Dx Recurrence Score (RS) has been validated in patients with ER + /HER2 - invasive breast carcinoma to estimate patient risk of recurrence and guide the use of adjuvant chemotherapy. We investigated the role of MRI-based radiomics features extracted from the tumor and the peritumoral tissues to predict the risk of tumor recurrence. A total of 62 patients with biopsy-proved ER + /HER2 - breast cancer who underwent pre-treatment MRI and Oncotype Dx were included. An RS > 25 was considered discriminant between low-intermediate and high risk of tumor recurrence. Two readers segmented each tumor. Radiomics features were extracted from the tumor and the peritumoral tissues. Partial least square (PLS) regression was used as the multivariate machine learning algorithm. PLS β-weights of radiomics features included the 5% features with the largest β-weights in magnitude (top 5%). Leave-one-out nested cross-validation (nCV) was used to achieve hyperparameter optimization and evaluate the generalizable performance of the procedure. The diagnostic performance of the radiomics model was assessed through receiver operating characteristic (ROC) analysis. A null hypothesis probability threshold of 5% was chosen (p < 0.05). The exploratory analysis for the complete dataset revealed an average absolute correlation among features of 0.51. The nCV framework delivered an AUC of 0.76 (p = 1.1∙10-3). When combining "early" and "peak" DCE images of only T or TST, a tendency toward statistical significance was obtained for TST with an AUC of 0.61 (p = 0.05). The 47 features included in the top 5% were balanced between T and TST (23 and 24, respectively). Moreover, 33/47 (70%) were texture-related, and 25/47 (53%) were derived from high-resolution images (1 mm). A radiomics-based machine learning approach shows the potential to accurately predict the recurrence risk in early ER + /HER2 - breast cancer patients.

Radiomics Analysis of Breast Lesions in Combination with Coronal Plane of ABVS and Strain Elastography

Background

Breast cancer is the most common tumor globally. Automated Breast Volume Scanner (ABVS) and strain elastography (SE) can provide more useful breast information. The use of radiomics combined with ABVS and SE images to predict breast cancer has become a new focus. Therefore, this study developed and validated a radiomics analysis of breast lesions in combination with coronal plane of ABVS and SE to improve the differential diagnosis of benign and malignant breast diseases.

Patients and Methods

620 pathologically confirmed breast lesions from January 2017 to August 2021 were retrospectively analyzed and randomly divided into a training set (n=434) and a validation set (n=186). Radiomic features of the lesions were extracted from ABVS, B-ultrasound, and strain elastography (SE) images, respectively. These were then filtered by Gradient Boosted Decision Tree (GBDT) and multiple logistic regression. The ABVS model is based on coronal plane features for the breast, B+SE model is based on features of B-ultrasound and SE, and the multimodal model is based on features of three examinations. The evaluation of the predicted performance of the three models used the receiver operating characteristic (ROC) and decision curve analysis (DCA).

Results

The area under the curve, accuracy, specificity, and sensitivity of the multimodal model in the training set are 0.975 (95% CI:0.959-0.991),93.78%, 92.02%, and 96.49%, respectively, and 0.946 (95% CI:0.913 -0.978), 87.63%, 83.93%, and 93.24% in the validation set, respectively. The multimodal model outperformed the ABVS model and B+SE model in both the training (P < 0.001, P = 0.002, respectively) and validation sets (P < 0.001, P = 0.034, respectively).

Conclusion

Radiomics from the coronal plane of the breast lesion provide valuable information for identification. A multimodal model combination with radiomics from ABVS, B-ultrasound, and SE could improve the diagnostic efficacy of breast masses.

Conventional ultrasound and contrast-enhanced ultrasound radiomics in breast cancer and molecular subtype diagnosis

Objectives

This study aimed to explore the value of conventional ultrasound (CUS) and contrast-enhanced ultrasound (CEUS) radiomics to diagnose breast cancer and predict its molecular subtype.

Method

A total of 170 lesions (121 malignant, 49 benign) were selected from March 2019 to January 2022. Malignant lesions were further divided into six categories of molecular subtype: (non-)Luminal A, (non-)Luminal B, (non-)human epidermal growth factor receptor 2 (HER2) overexpression, (non-)triple-negative breast cancer (TNBC), hormone receptor (HR) positivity/negativity, and HER2 positivity/negativity. Participants were examined using CUS and CEUS before surgery. Regions of interest images were manually segmented. The pyradiomics toolkit and the maximum relevance minimum redundancy algorithm were utilized to extract and select features, multivariate logistic regression models of CUS, CEUS, and CUS combined with CEUS radiomics were then constructed and evaluated by fivefold cross-validation.

Results

The accuracy of the CUS combined with CEUS model was superior to CUS model (85.4% vs. 81.3%, p<0.01). The accuracy of the CUS radiomics model in predicting the six categories of breast cancer is 68.2% (82/120), 69.3% (83/120), 83.7% (100/120), 86.7% (104/120), 73.5% (88/120), and 70.8% (85/120), respectively. In predicting breast cancer of Luminal A, HER2 overexpression, HR-positivity, and HER2 positivity, CEUS video improved the predictive performance of CUS radiomics model [accuracy=70.2% (84/120), 84.0% (101/120), 74.5% (89/120), and 72.5% (87/120), p<0.01].

Conclusion

CUS radiomics has the potential to diagnose breast cancer and predict its molecular subtype. Moreover, CEUS video has auxiliary predictive value for CUS radiomics.

PTC-MAS: A Deep Learning-Based Preoperative Automatic Assessment of Lymph Node Metastasis in Primary Thyroid Cancer

BACKGROUND

Identifying cervical lymph node metastasis (LNM) in primary thyroid cancer preoperatively using ultrasound is challenging. Therefore, a non-invasive method is needed to assess LNM accurately.

PURPOSE

To address this need, we developed the Primary Thyroid Cancer Lymph Node Metastasis Assessment System (PTC-MAS), a transfer learning-based and B-mode ultrasound images-based automatic assessment system for assessing LNM in primary thyroid cancer.

METHODS

The system has two parts: YOLO Thyroid Nodule Recognition System (YOLOS) for obtaining regions of interest (ROIs) of nodules, and LMM assessment system for building the LNM assessment system using transfer learning and majority voting with extracted ROIs as input. We retained the relative size features of nodules to improve the system's performance.

RESULTS

We evaluated three transfer learning-based neural networks (DenseNet, ResNet, and GoogLeNet) and majority voting, which had the area under the curves (AUCs) of 0.802, 0.837, 0.823, and 0.858, respectively. Method III preserved relative size features and achieved higher AUCs than Method II, which fixed nodule size. YOLOS achieved high precision and sensitivity on a test set, indicating its potential for ROIs extraction.

CONCLUSIONS

Our proposed PTC-MAS system effectively assesses primary thyroid cancer LNM based on preserving nodule relative size features. It has potential for guiding treatment modalities and avoiding inaccurate ultrasound results due to tracheal interference.

18F-FDG PET/CT radiomics signature and clinical parameters predict progression-free survival in breast cancer patients: A preliminary study

Introduction

This study aimed to investigate the feasibility of predicting progression-free survival (PFS) in breast cancer patients using pretreatment 18F-fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) radiomics signature and clinical parameters.

Methods

Breast cancer patients who underwent 18F-FDG PET/CT imaging before treatment from January 2012 to December 2020 were eligible for study inclusion. Eighty-seven patients were randomly divided into training (n = 61) and internal test sets (n = 26) and an additional 25 patients were used as the external validation set. Clinical parameters, including age, tumor size, molecularsubtype, clinical TNM stage, and laboratory findings were collected. Radiomics features were extracted from preoperative PET/CT images. Least absolute shrinkage and selection operators were applied to shrink feature size and build a predictive radiomics signature. Univariate and multivariate Cox proportional hazards models and Kaplan-Meier analysis were used to assess the association of rad-score and clinical parameter with PFS. Nomograms were constructed to visualize survival prediction. C-index and calibration curve were used to evaluate nomogram performance.

Results

Eleven radiomics features were selected to generate rad-score. The clinical model comprised three parameters: clinical M stage, CA125, and pathological N stage. Rad-score and clinical-model were significantly associated with PFS in the training set (P&lt; 0.01) but not the test set. The integrated clinical-radiomics (ICR) model was significantly associated with PFS in both the training and test sets (P&lt; 0.01). The ICR model nomogram had a significantly higher C-index than the clinical model and rad-score in the training and test sets. The C-index of the ICR model in the external validation set was 0.754 (95% confidence interval, 0.726–0.812). PFS significantly differed between the low- and high-risk groups stratified by the nomogram (P = 0.009). The calibration curve indicated the ICR model provided the greatest clinical benefit.

Conclusion

The ICR model, which combined clinical parameters and preoperative 18F-FDG PET/CT imaging, was able to independently predict PFS in breast cancer patients and was superior to the clinical model alone and rad-score alone.

Freehand 1.5T MR-Guided Vacuum-Assisted Breast Biopsy (MR-VABB): Contribution of Radiomics to the Differentiation of Benign and Malignant Lesions

Radiomics and artificial intelligence have been increasingly applied in breast MRI. However, the advantages of using radiomics to evaluate lesions amenable to MR-guided vacuum-assisted breast biopsy (MR-VABB) are unclear. This study includes patients scheduled for MR-VABB, corresponding to subjects with MRI-only visible lesions, i.e., with a negative second-look ultrasound. The first acquisition of the multiphase dynamic contrast-enhanced MRI (DCE-MRI) sequence was selected for image segmentation and radiomics analysis. A total of 80 patients with a mean age of 55.8 years ± 11.8 (SD) were included. The dataset was then split into a training set (50 patients) and a validation set (30 patients). Twenty out of the 30 patients with a positive histology for cancer were in the training set, while the remaining 10 patients with a positive histology were included in the test set. Logistic regression on the training set provided seven features with significant p values (<0.05): (1) ‘AverageIntensity’, (2) ‘Autocorrelation’, (3) ‘Contrast’, (4) ‘Compactness’, (5) ‘StandardDeviation’, (6) ‘MeanAbsoluteDeviation’ and (7) ‘InterquartileRange’. AUC values of 0.86 (95% C.I. 0.73–0.94) for the training set and 0.73 (95% C.I. 0.54–0.87) for the test set were obtained for the radiomics model. Radiological evaluation of the same lesions scheduled for MR-VABB had AUC values of 0.42 (95% C.I. 0.28–0.57) for the training set and 0.4 (0.23–0.59) for the test set. In this study, a radiomics logistic regression model applied to DCE-MRI images increased the diagnostic accuracy of standard radiological evaluation of MRI suspicious findings in women scheduled for MR-VABB. Confirming this performance in large multicentric trials would imply that using radiomics in the assessment of patients scheduled for MR-VABB has the potential to reduce the number of biopsies, in suspicious breast lesions where MR-VABB is required, with clear advantages for patients and healthcare resources.

Systematic review of the radiomics quality score applications: an EuSoMII Radiomics Auditing Group Initiative

OBJECTIVE

The main aim of the present systematic review was a comprehensive overview of the Radiomics Quality Score (RQS)-based systematic reviews to highlight common issues and challenges of radiomics research application and evaluate the relationship between RQS and review features.

METHODS

The literature search was performed on multiple medical literature archives according to PRISMA guidelines for systematic reviews that reported radiomic quality assessment through the RQS. Reported scores were converted to a 0-100% scale. The Mann-Whitney and Kruskal-Wallis tests were used to compare RQS scores and review features.

RESULTS

The literature research yielded 345 articles, from which 44 systematic reviews were finally included in the analysis. Overall, the median of RQS was 21.00% (IQR = 11.50). No significant differences of RQS were observed in subgroup analyses according to targets (oncological/not oncological target, neuroradiology/body imaging focus and one imaging technique/more than one imaging technique, characterization/prognosis/detection/other).

CONCLUSIONS

Our review did not reveal a significant difference of quality of radiomic articles reported in systematic reviews, divided in different subgroups. Furthermore, low overall methodological quality of radiomics research was found independent of specific application domains. While the RQS can serve as a reference tool to improve future study designs, future research should also be aimed at improving its reliability and developing new tools to meet an ever-evolving research space.

KEY POINTS

• Radiomics is a promising high-throughput method that may generate novel imaging biomarkers to improve clinical decision-making process, but it is an inherently complex analysis and often lacks reproducibility and generalizability. • The Radiomics Quality Score serves a necessary role as the de facto reference tool for assessing radiomics studies. • External auditing of radiomics studies, in addition to the standard peer-review process, is valuable to highlight common limitations and provide insights to improve future study designs and practical applicability of the radiomics models.

Application of radiomics in precision prediction of diagnosis and treatment of gastric cancer

Gastric cancer is one of the most common malignant tumors. Although some progress has been made in chemotherapy and surgery, it is still one of the highest mortalities in the world. Therefore, early detection, diagnosis and treatment are very important to improve the prognosis of patients. In recent years, with the proposal of the concept of radiomics, it has been gradually applied to histopathological grading, differential diagnosis, therapeutic efficacy and prognosis evaluation of gastric cancer, whose advantage is to comprehensively quantify the tumor phenotype using a large number of quantitative image features, so as to predict and diagnose the lesion area of gastric cancer early. The purpose of this review is to evaluate the research status and progress of radiomics in gastric cancer, and reviewed the workflow and clinical application of radiomics. The 27 original studies on the application of radiomics in gastric cancer were included from web of science database search results from 2017 to 2021, the number of patients included ranged from 30 to 1680, and the models used were based on the combination of radiomics signature and clinical factors. Most of these studies showed positive results, the median radiomics quality score (RQS) for all studies was 36.1%, and the development prospect and challenges of radiomics development were prospected. In general, radiomics has great potential in improving the early prediction and diagnosis of gastric cancer, and provides an unprecedented opportunity for clinical practice to improve the decision support of gastric cancer treatment at a low cost.

Radiomics-Based Machine Learning Model for Predicting Overall and Progression-Free Survival in Rare Cancer: A Case Study for Primary CNS Lymphoma Patients

Primary Central Nervous System Lymphoma (PCNSL) is an aggressive neoplasm with a poor prognosis. Although therapeutic progresses have significantly improved Overall Survival (OS), a number of patients do not respond to HD–MTX-based chemotherapy (15–25%) or experience relapse (25–50%) after an initial response. The reasons underlying this poor response to therapy are unknown. Thus, there is an urgent need to develop improved predictive models for PCNSL. In this study, we investigated whether radiomics features can improve outcome prediction in patients with PCNSL. A total of 80 patients diagnosed with PCNSL were enrolled. A patient sub-group, with complete Magnetic Resonance Imaging (MRI) series, were selected for the stratification analysis. Following radiomics feature extraction and selection, different Machine Learning (ML) models were tested for OS and Progression-free Survival (PFS) prediction. To assess the stability of the selected features, images from 23 patients scanned at three different time points were used to compute the Interclass Correlation Coefficient (ICC) and to evaluate the reproducibility of each feature for both original and normalized images. Features extracted from Z-score normalized images were significantly more stable than those extracted from non-normalized images with an improvement of about 38% on average (p-value < 10−12). The area under the ROC curve (AUC) showed that radiomics-based prediction overcame prediction based on current clinical prognostic factors with an improvement of 23% for OS and 50% for PFS, respectively. These results indicate that radiomics features extracted from normalized MR images can improve prognosis stratification of PCNSL patients and pave the way for further study on its potential role to drive treatment choice.

Radiomics in Lung Metastases: A Systematic Review

Due to the rich vascularization and lymphatic drainage of the pulmonary tissue, lung metastases (LM) are not uncommon in patients with cancer. Radiomics is an active research field aimed at the extraction of quantitative data from diagnostic images, which can serve as useful imaging biomarkers for a more effective, personalized patient care. Our purpose is to illustrate the current applications, strengths and weaknesses of radiomics for lesion characterization, treatment planning and prognostic assessment in patients with LM, based on a systematic review of the literature.

Risk assessment of external apical root resorption associated with orthodontic treatment using computed tomography texture analysis

OBJECTIVES

This study aimed to quantitatively assess maxillary central incisor roots using pre-orthodontics computed tomography (CT) texture analysis as part of a radiomics quantitative analysis.

METHODS

This retrospective case-control study included 16 patients with external apical root resorption (EARR) and 16 age- and sex-matched patients without EARR, after orthodontic treatment who underwent pre-orthodontics CT for jaw deformities. All patients were treated with a fixed orthodontic appliance before and after surgical orthodontic treatment. EARR was defined as root resorption ≥ 2 mm of the left and right maxillary central incisors on CT images more than 2 years after the start of orthodontic treatment. Texture features of the maxillary central incisor with and without EARR after orthodontic treatment were analyzed using the open-access software, MaZda Ver. 3.3. Ten texture features were selected using the Fisher method in MaZda from 279 original parameters, which were calculated for each of the maxillary central incisors with and without EARR. The results were tested using the Student's t test, Welch's t test, or Mann-Whitney U test.

RESULTS

Four gray-level run length matrix features and six gray-level co-occurrence matrix features displayed significant differences between both the groups (p < 0.01).

CONCLUSIONS

CT texture analysis was able to quantitatively assess maxillary central incisor roots and distinguish between maxillary central incisor roots with and without EARR. CT texture analysis may be a useful method for predicting EARR after orthodontic treatment.

Integration of Clinical and CT-Based Radiomic Features for Pretreatment Prediction of Pathologic Complete Response to Neoadjuvant Systemic Therapy in Breast Cancer

The purpose of the present study was to examine the potential of a machine learning model with integrated clinical and CT-based radiomics features in predicting pathologic complete response (pCR) to neoadjuvant systemic therapy (NST) in breast cancer. Contrast-enhanced CT was performed in 329 patients with breast tumors (n = 331) before NST. Pyradiomics was used for feature extraction, and 107 features of seven classes were extracted. Feature selection was performed on the basis of the intraclass correlation coefficient (ICC), and six ICC thresholds (0.7−0.95) were examined to identify the feature set resulting in optimal model performance. Clinical factors, such as age, clinical stage, cancer cell type, and cell surface receptors, were used for prediction. We tried six machine learning algorithms, and clinical, radiomics, and clinical−radiomics models were trained for each algorithm. Radiomics and clinical−radiomics models with gray level co-occurrence matrix (GLCM) features only were also built for comparison. The linear support vector machine (SVM) regression model trained with radiomics features of ICC ≥0.85 in combination with clinical factors performed the best (AUC = 0.87). The performance of the clinical and radiomics linear SVM models showed statistically significant difference after correction for multiple comparisons (AUC = 0.69 vs. 0.78; p < 0.001). The AUC of the radiomics model trained with GLCM features was significantly lower than that of the radiomics model trained with all seven classes of radiomics features (AUC = 0.85 vs. 0.87; p = 0.011). Integration of clinical and CT-based radiomics features was helpful in the pretreatment prediction of pCR to NST in breast cancer.

Prediction of distant metastasis in esophageal cancer using a radiomics-clinical model

BACKGROUND

Distant metastasis, which occurs at a rate of 25% in patients with esophageal cancer (EC), has a poor prognosis, with previous studies reporting an overall survival of only 3-10 months. However, few studies have been conducted to predict distant metastasis in EC, owing to a dearth of reliable biomarkers. The purpose of this study was to develop and validate an accurate model for predicting distant metastasis in patients with EC.

METHODS

A total of 299 EC patients were enrolled and randomly assigned to a training cohort (n = 207) and a validation cohort (n = 92). Logistic univariate and multivariate regression analyses were used to identify clinical independent predictors and create a clinical nomogram. Radiomic features were extracted from contrast-enhanced computed tomography (CT) images taken prior to treatment, and least absolute shrinkage and selection operator (Lasso) regression was used to screen the associated features, which were then used to develop a radiomic signature. Based on the screened features, four machine learning algorithms were used to build radiomics models. The joint nomogram with radiomic signature and clinically independent risk factors was developed using the logical regression algorithm. All models were validated and compared by discrimination, calibration, reclassification, and clinical benefit.

RESULTS

Multivariable analyses revealed that age, N stage, and degree of pathological differentiation were independent predictors of distant metastasis, and a clinical nomogram incorporating these factors was established. A radiomic signature was developed by a set of sixteen features chosen from 851 radiomic features. The joint nomogram incorporating clinical factors and radiomic signature performed better [AUC(95% CI) 0.827(0.742-0.912)] than the clinical nomogram [AUC(95% CI) 0.731(0.626-0.836)] and radiomics predictive models [AUC(95% CI) 0.754(0.652-0.855), LR algorithms]. Calibration and decision curve analyses revealed that the radiomics-clinical nomogram outperformed the other models. In comparison with the clinical nomogram, the joint nomogram's NRI was 0.114 (95% CI 0.075-0.345), and its IDI was 0.071 (95% CI 0.030-0.112), P = 0.001.

CONCLUSIONS

We developed and validated the first radiomics-clinical nomogram for distant metastasis in EC which may aid clinicians in identifying patients at high risk of distant metastasis.

A Variable-Clustering-Based Feature Selection to Improve Positive and Negative Discrimination of P53 Protein in Colorectal Cancer Patients

P53 protein tumor suppressor gene plays a guiding role in the treatment and prognosis of colorectal cancer (CRC). This paper aimed at proposing a feature selection method based on variable clustering to improve positive and negative discrimination of P53 protein in CRC patients. In this approach, we cluster the preprocessed dataset with variables, and then find the features with the largest information value (IV) for each cluster to form a feature subset. We call this method as IV_Cluster. In the actual medical data test, compared with the information value feature selection method, the accuracy of the 10-fold cross-validation logistic regression model increased by 4.4%, 2.0%, and 5.8%, and Kappa values increased by 21.8%, 8.6%, and 22.4%, respectively, under 5, 10, and 15 feature sets.

Mammography radiomics features at diagnosis and progression-free survival among patients with breast cancer

BACKGROUND

The associations between mammographic radiomics and breast cancer clinical endpoints are unclear. We aimed to identify mammographic radiomics features associated with breast cancer prognosis.

METHODS

Nested from a large breast cancer cohort in our institution, we conducted an extreme case-control study consisting of 207 cases with any invasive disease-free survival (iDFS) endpoint <5 years and 207 molecular subtype-matched controls with >5-year iDFS. A total of 632 radiomics features in craniocaudal (CC) and mediolateral oblique (MLO) views were extracted from pre-treatment mammography. Logistic regression was used to identify iDFS-associated features with multiple testing corrections (Benjamini-Hochberg method). In a subsample with RNA-seq data (n = 96), gene set enrichment analysis was employed to identify pathways associated with lead features.

RESULTS

We identified 15 iDFS-associated features from CC-view yet none from MLO-view. S(1,-1)SumAverg and WavEnLL_s-6 were the lead ones and associated with favourable (OR 0.64, 95% CI 0.42-0.87, P = 0.01) and poor iDFS (OR 1.53, 95% CI 1.31-1.76, P = 0.01), respectively. Both features were associated with eight pathways (primarily involving cell cycle regulation) in tumour but not adjacent normal tissues.

CONCLUSION

Our findings suggest mammographic radiomics features are associated with breast cancer iDFS, potentially through pathways involving cell cycle regulation.

Application of Deep Learning to Reduce the Rate of Malignancy Among BI-RADS 4A Breast Lesions Based on Ultrasonography

The aim of the work described here was to develop an ultrasound (US) image-based deep learning model to reduce the rate of malignancy among breast lesions diagnosed as category 4A of the Breast Imaging-Reporting and Data System (BI-RADS) during the pre-operative US examination. A total of 479 breast lesions diagnosed as BI-RADS 4A in pre-operative US examination were enrolled. There were 362 benign lesions and 117 malignant lesions confirmed by postoperative pathology with a malignancy rate of 24.4%. US images were collected from the database server. They were then randomly divided into training and testing cohorts at a ratio of 4:1. To correctly classify malignant and benign tumors diagnosed as BI-RADS 4A in US, four deep learning models, including MobileNet, DenseNet121, Xception and Inception V3, were developed. The performance of deep learning models was compared using the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Meanwhile, the robustness of the models was evaluated by five-fold cross-validation. Among the four models, the MobileNet model turned to be the optimal model with the best performance in classifying benign and malignant lesions among BI-RADS 4A breast lesions. The AUROC, accuracy, sensitivity, specificity, PPV and NPV of the optimal model in the testing cohort were 0.897, 0.913, 0.926, 0.899, 0.958 and 0.784, respectively. About 14.4% of patients were expected to be upgraded to BI-RADS 4B in US with the assistance of the MobileNet model. The deep learning model MobileNet can help to reduce the rate of malignancy among BI-RADS 4A breast lesions in pre-operative US examinations, which is valuable to clinicians in tailoring treatment for suspicious breast lesions identified on US.

Diagnostic value of radiomics model based on gray-scale and contrast-enhanced ultrasound for inflammatory mass stage periductal mastitis/duct ectasia

Objective

The present study aimed to investigate the clinical application value of the radiomics model based on gray-scale ultrasound (GSUS) and contrast-enhanced ultrasound (CEUS) images in the differentiation of inflammatory mass stage periductal mastitis/duct ectasia (IMSPDM/DE) and invasive ductal carcinoma (IDC).

Methods

In this retrospective study, 254 patients (IMSPDM/DE: 129; IDC:125) were enrolled between January 2018 and December 2020 as a training cohort to develop the classification models. The radiomics features were extracted from the GSUS and CEUS images. The least absolute shrinkage and selection operator (LASSO) regression model was employed to select the corresponding features. Based on these selected features, logistic regression analysis was used to aid the construction of these three radiomics signatures (GSUS, CEUS and GSCEUS radiomics signature). In addition, 80 patients (IMSPDM/DE:40; IDC:40) were recruited between January 2021 and November 2021 and were used as the validation cohort. The best radiomics signature was selected. Based on the clinical parameters and the radiomics signature, a classification model was built. Finally, the classification model was assessed using nomogram and decision curve analyses.

Results

Three radiomics signatures were able to differentiate IMSPDM/DE from IDC. The GSCEUS radiomics signature outperformed the other two radiomics signatures and the AUC, sensitivity, specificity, and accuracy were estimated to be 0.876, 0.756, 0.804, and 0.798 in the training cohort and 0.796, 0.675, 0.838 and 0.763 in the validation cohort, respectively. The lower patient age (p&lt;0.001), higher neutrophil count (p&lt;0.001), lack of pausimenia (p=0.023) and GSCEUS radiomics features (p&lt;0.001) were independent risk factors of IMSPDM/DE. The classification model that included the clinical factors and the GSCEUS radiomics signature outperformed the GSCEUS radiomics signature alone (the AUC values of the training and validation cohorts were 0.962 and 0.891, respectively). The nomogram was applied to the validation cohort, reaching optimal discrimination, with an AUC value of 0.891, a sensitivity of 0.888, and a specificity of 0.750.

Conclusions

The present study combined the clinical parameters with the GSCEUS radiomics signature and developed a nomogram. This GSCEUS radiomics-based classification model could be used to differentiate IMSPDM/DE from IDC in a non-invasive manner.

The impact of inter-observer variation in delineation on robustness of radiomics features in non-small cell lung cancer

Artificial intelligence and radiomics have the potential to revolutionise cancer prognostication and personalised treatment. Manual outlining of the tumour volume for extraction of radiomics features (RF) is a subjective process. This study investigates robustness of RF to inter-observer variation (IOV) in contouring in lung cancer. We utilised two public imaging datasets: ‘NSCLC-Radiomics’ and ‘NSCLC-Radiomics-Interobserver1’ (‘Interobserver’). For ‘NSCLC-Radiomics’, we created an additional set of manual contours for 92 patients, and for ‘Interobserver’, there were five manual and five semi-automated contours available for 20 patients. Dice coefficients (DC) were calculated for contours. 1113 RF were extracted including shape, first order and texture features. Intraclass correlation coefficient (ICC) was computed to assess robustness of RF to IOV. Cox regression analysis for overall survival (OS) was performed with a previously published radiomics signature. The median DC ranged from 0.81 (‘NSCLC-Radiomics’) to 0.85 (‘Interobserver’—semi-automated). The median ICC for the ‘NSCLC-Radiomics’, ‘Interobserver’ (manual) and ‘Interobserver’ (semi-automated) were 0.90, 0.88 and 0.93 respectively. The ICC varied by feature type and was lower for first order and gray level co-occurrence matrix (GLCM) features. Shape features had a lower median ICC in the ‘NSCLC-Radiomics’ dataset compared to the ‘Interobserver’ dataset. Survival analysis showed similar separation of curves for three of four RF apart from ‘original_shape_Compactness2’, a feature with low ICC (0.61). The majority of RF are robust to IOV, with first order, GLCM and shape features being the least robust. Semi-automated contouring improves feature stability. Decreased robustness of a feature is significant as it may impact upon the features’ prognostic capability.

Expert tumor annotations and radiomics for locally advanced breast cancer in DCE-MRI for ACRIN 6657/I-SPY1

Breast cancer is one of the most pervasive forms of cancer and its inherent intra- and inter-tumor heterogeneity contributes towards its poor prognosis. Multiple studies have reported results from either private institutional data or publicly available datasets. However, current public datasets are limited in terms of having consistency in: a) data quality, b) quality of expert annotation of pathology, and c) availability of baseline results from computational algorithms. To address these limitations, here we propose the enhancement of the I-SPY1 data collection, with uniformly curated data, tumor annotations, and quantitative imaging features. Specifically, the proposed dataset includes a) uniformly processed scans that are harmonized to match intensity and spatial characteristics, facilitating immediate use in computational studies, b) computationally-generated and manually-revised expert annotations of tumor regions, as well as c) a comprehensive set of quantitative imaging (also known as radiomic) features corresponding to the tumor regions. This collection describes our contribution towards repeatable, reproducible, and comparative quantitative studies leading to new predictive, prognostic, and diagnostic assessments.

The Effect of PACS in Breast Tumor Diagnosis Based on Numerical Analysis

The incidence and mortality rates are increasing year by year, and the incidence of the disease is gradually becoming younger. The purpose of this study was to investigate the clinical diagnostic value of PACS in breast tumor patients. Methods. 20 patients with breast tumor diagnosed by PACS were selected for the study, and the diagnosis was confirmed by pathological puncture or surgery. Results. The detection rates of breast tumor by MRI and CT were 94.44% and 96.67%, the sensitivities were 18.82% breast tumor and 96.67%, and the specificities were 53.84% and 54.54%, with no statistically significant difference ( $P>0.05$ ). There was no statistically significant difference in the detection rate of invasive lobular carcinoma (LDC) and PACS ( $P>0.05$ ). Conclusion. PACS has a greater detection rate for breast tumor and offers some diagnostic usefulness in diagnosing malignant breast tumor. The detection rate of breast tumors can be increased by selecting the most appropriate diagnostic tool for the patient’s current circumstances.

Development of a radiomics and machine learning model for predicting occult cervical lymph node metastasis in patients with tongue cancer

OBJECTIVE

We aimed to develop a predictive model for occult cervical lymph node metastasis in patients with tongue cancer using radiomics and machine learning from pretreatment contrast-enhanced computed tomography.

STUDY DESIGN

This study included 161 patients with tongue cancer who received local treatment. Computed tomography images were transferred to a radiomics platform. The volume of interest was the total neck node level, including levels Ia, Ib, II, III, and IVa at the ipsilateral side, and each neck node level. The dimensionality of the radiomics features was reduced using least absolute shrinkage and selection operator logistic regression analysis. We compared 5 classifiers with or without the synthetic minority oversampling technique (SMOTE).

RESULTS

For the analysis at the total neck node level, random forest with SMOTE was the best model, with an accuracy of 0.85 and an area under the curve score of 0.92. For the analysis at each neck node level, a support vector machine with SMOTE was the best model, with an accuracy of 0.96 and an area under the curve score of 0.98.

CONCLUSIONS

Predictive models using radiomics and machine learning have potential as clinical decision support tools in the management of patients with tongue cancer for prediction of occult cervical lymph node metastasis.

Radiomics-guided radiation therapy: opportunities and challenges

Radiomics is an advanced image-processing framework, which extracts image features and considers them as biomarkers towards personalized medicine. Applications include disease detection, diagnosis, prognosis, and therapy response assessment/prediction. As radiation therapy aims for further individualized treatments, radiomics could play a critical role in various steps before, during and after treatment. Elucidation of the concept of radiomics-guided radiation therapy (RGRT) is the aim of this review, attempting to highlight opportunities and challenges underlying the use of radiomics to guide clinicians and physicists towards more effective radiation treatments. This work identifies the value of RGRT in various steps of radiotherapy from patient selection to follow-up, and subsequently provides recommendations to improve future radiotherapy using quantitative imaging features.

Analysis of Cross-Combinations of Feature Selection and Machine-Learning Classification Methods Based on [18F]F-FDG PET/CT Radiomic Features for Metabolic Response Prediction of Metastatic Breast Cancer Lesions

Simple Summary

Breast cancer is a leading cause of morbidity and mortality worldwide. The metastatic disease is largely responsible for cancer patient deaths, and its treatment implies usually different therapies. In this context, the prediction of response to treatment or depiction of treatment-resistant phenotypes is essential in clinical practice, especially in the new era of precision medicine. In this study, we used several combinations of feature selection methods and machine-learning classifiers to construct predictive models of the metabolic response to the treatment of metastatic breast cancer lesions. These models were based on clinical variables and radiomic features extracted from 2-deoxy-2-[¹⁸F]fluoro-D-glucose positron emission tomography/computed tomography ([¹⁸F]F-FDG PET/CT) images, obtained prior to the treatment. Our main goal was to know if this prediction was feasible and to identify those combinations with better predictive performance. We found that several combinations were successful to predict the metabolic response to treatment, of which the least absolute shrinkage and selection operator (Lasso) + support vector machines (SVM) had the best mean performance in terms of area under the curve, in both training and validation cohorts. Model performances depended largely on the selected combinations.

Abstract

Background: This study aimed to identify optimal combinations between feature selection methods and machine-learning classifiers for predicting the metabolic response of individual metastatic breast cancer lesions, based on clinical variables and radiomic features extracted from pretreatment [¹⁸F]F-FDG PET/CT images. Methods: A total of 48 patients with confirmed metastatic breast cancer, who received different treatments, were included. All patients had an [¹⁸F]F-FDG PET/CT scan before and after the treatment. From 228 metastatic lesions identified, 127 were categorized as responders (complete or partial metabolic response) and 101 as non-responders (stable or progressive metabolic response), by using the percentage changes in SULpeak (peak standardized uptake values normalized for body lean body mass). The lesion pool was divided into training (n = 182) and testing cohorts (n = 46); for each lesion, 101 image features from both PET and CT were extracted (202 features per lesion). These features, along with clinical and pathological information, allowed the prediction model’s construction by using seven popular feature selection methods in cross-combination with another seven machine-learning (ML) classifiers. The performance of the different models was investigated with the receiver-operating characteristic curve (ROC) analysis, using the area under the curve (AUC) and accuracy (ACC) metrics. Results: The combinations, least absolute shrinkage and selection operator (Lasso) + support vector machines (SVM), or random forest (RF) had the highest AUC in the cross-validation, with 0.93 ± 0.06 and 0.92 ± 0.03, respectively, whereas Lasso + neural network (NN) or SVM, and mutual information (MI) + RF, had the higher AUC and ACC in the validation cohort, with 0.90/0.72, 0.86/0.76, and 87/85, respectively. On average, the models with Lasso and models with SVM had the best mean performance for both AUC and ACC in both training and validation cohorts. Conclusions: Image features obtained from a pretreatment [¹⁸F]F-FDG PET/CT along with clinical vaiables could predict the metabolic response of metastatic breast cancer lesions, by their incorporation into predictive models, whose performance depends on the selected combination between feature selection and ML classifier methods.

A Machine Learning and Radiomics Approach in Lung Cancer for Predicting Histological Subtype

Lung cancer is one of the deadliest diseases worldwide. Computed Tomography (CT) images are a powerful tool for investigating the structure and texture of lung nodules. For a long time, trained radiologists have performed the grading and staging of cancer severity by relying on radiographic images. Recently, radiomics has been changing the traditional workflow for lung cancer staging by providing the technical and methodological means to analytically quantify lesions so that more accurate predictions could be performed while reducing the time required from each specialist to perform such tasks. In this work, we implemented a pipeline for identifying a radiomic signature composed of a reduced number of features to discriminate between adenocarcinomas and other cancer types. In addition, we also investigated the reproducibility of this radiomic study analysing the performances of the classification models on external validation data. In detail, we first considered two publicly available datasets, namely D1 and D2, composed of n = 262 and n = 89 samples, respectively. Ten significant features, according to univariate AUC evaluated on D1, were retained. Mann–Whitney U tests recognised three of these features to have a statistically different distribution, with a p-value < 0.05. Then, we collected n = 51 CT images from patients with lung nodules at the Azienda Ospedaliero—Universitaria “Policlinico Riuniti” in Foggia. Resident radiologists manually annotated the lung lesions in images to allow the subsequent analysis of the malignancy regions. We designed a pipeline for feature extraction from the Volumes of Interest in order to generate a third dataset, i.e., D3. Several experiments have been performed showing that the selected radiomic signature not only allowed the discrimination of lung adenocarcinoma from other cancer types independently from the input dataset used for training the models, but also allowed reaching good classification performances also on external validation data; in fact, the radiomic signature computed on D1 and evaluated on the local cohort allowed reaching an AUC of 0.70 (p<0.001) for the task of predicting the histological subtype.