Global Radiomic Features from Mammography for Predicting Difficult-To-Interpret Normal Cases.

This work aimed to investigate whether global radiomic features (GRFs) from mammograms can predict difficult-to-interpret normal cases (NCs). Assessments from 537 readers interpreting 239 normal mammograms were used to categorise cases as 120 difficult-to-interpret and 119 easy-to-interpret based on cases having the highest and lowest difficulty scores, respectively. Using lattice- and squared-based approaches, 34 handcrafted GRFs per image were extracted and normalised. Three classifiers were constructed: (i) CC and (ii) MLO using the GRFs from corresponding craniocaudal and mediolateral oblique images only, based on the random forest technique for distinguishing difficult- from easy-to-interpret NCs, and (iii) CC + MLO using the median predictive scores from both CC and MLO models. Useful GRFs for the CC and MLO models were recognised using a scree test. The CC and MLO models were trained and validated using the leave-one-out-cross-validation. The models' performances were assessed by the AUC and compared using the DeLong test. A Kruskal-Wallis test was used to examine if the 34 GRFs differed between difficult- and easy-to-interpret NCs and if difficulty level based on the traditional breast density (BD) categories differed among 115 low-BD and 124 high-BD NCs. The CC + MLO model achieved higher performance (0.71 AUC) than the individual CC and MLO model alone (0.66 each), but statistically non-significant difference was found (all p > 0.05). Six GRFs were identified to be valuable in describing difficult-to-interpret NCs. Twenty features, when compared between difficult- and easy-to-interpret NCs, differed significantly (p < 0.05). No statistically significant difference was observed in difficulty between low- and high-BD NCs (p = 0.709). GRF mammographic analysis can predict difficult-to-interpret NCs.

Risk stratification of indeterminate thyroid nodules using ultrasound and machine learning algorithms.

BACKGROUND: Indeterminate thyroid nodules (Bethesda III) are challenging to characterize without diagnostic surgery. Auxiliary strategies including molecular analysis, machine learning models, and ultrasound grading with Thyroid Imaging, Reporting and Data System (TI-RADS) can help to triage accordingly, but further refinement is needed to prevent unnecessary surgeries and increase positive predictive values. DESIGN: Retrospective review of 88 patients with Bethesda III nodules who had diagnostic surgery with final pathological diagnosis. MEASUREMENTS: Each nodule was retrospectively scored through TI-RADS. Two deep learning models were tested, one previously developed and trained on another data set, mainly containing determinate cases and then validated on our data set while the other one trained and tested on our data set (indeterminate cases). RESULTS: The mean TI-RADS score was 3 for benign and 4 for malignant nodules (p = .0022). Radiological high risk (TI-RADS 4,5) and low risk (TI-RADS 2,3) categories were established. The PPV for the high radiological risk category in those with >10 mm nodules was 85% (CI: 70%-93%). The NPV for low radiological risk in patients >60 years (mean age was 100% (CI: 83%-100%). The area under the curve (AUC) value of our novel classifier was 0.75 (CI: 0.62-0.84) and differed significantly from the chance-level (p < .00001). CONCLUSIONS: Novel radiomic and radiologic strategies can be employed to assist with preoperative diagnosis of indeterminate thyroid nodules.

Global and local shape features of the hippocampus based on Laplace-Beltrami eigenvalues and eigenfunctions: a potential application in the lateralization of temporal lobe epilepsy.

Using magnetic resonance (MR) images to evaluate changes in the shape of the hippocampus has been an active research topic. This paper presents a new shape analysis approach to quantify and visualize deformations of the hippocampus in epilepsy. The proposed method is based on Laplace-Beltrami (LB) eigenvalues and eigenfunctions as isometric invariant shape features, and thus, the procedure does not require any image registration. In addition to the LB-based shape features, total hippocampal volume and surface area are calculated using manually segmented images. Theses shape and volumetric descriptors are used to distinguish the patients with temporal lobe epilepsy (TLE) (N = 55) from healthy control subjects (N = 12, age = 32.2 ± 9.1, sex (M/F) = 6/6) and patients with right TLE (N = 26, age = 45.1 ± 11.0, sex (M/F) = 9/17) from left TLE (N = 29, age = 45.4 ± 11.9, sex (M/F) = 10/19). Experimental results illustrate the usefulness of the proposed approach for the diagnosis and lateralization of TLE with 93.0% and 86.4% of the cases, respectively. Moreover, the proposed method outperforms the volumetric analysis in terms of both sensitivity (94.9% vs. 88.1%) and specificity (83.3% vs. 50.0%) of the lateralization. The analysis of local hippocampal thickness variations suggests significant deformation in both ipsilateral and contralateral hippocampi of epileptic patients, while there were no differences between right and left hippocampi in controls. It is anticipated that the proposed method could be advantageous in the presurgical evaluation of patients with drug-resistant epilepsy; however, further validation of the method using a larger dataset is required.

Using Occlusion-Based Saliency Maps to Explain an Artificial Intelligence Tool in Lung Cancer Screening: Agreement Between Radiologists, Labels, and Visual Prompts.

Occlusion-based saliency maps (OBSMs) are one of the approaches for interpreting decision-making process of an artificial intelligence (AI) system. This study explores the agreement among text responses from a cohort of radiologists to describe diagnostically relevant areas on low-dose CT (LDCT) images. It also explores if radiologists' descriptions of cases misclassified by the AI provide a rationale for ruling out the AI's output. The OBSM indicating the importance of different pixels on the final decision made by an AI were generated for 10 benign cases (3 misclassified by the AI tool as malignant) and 10 malignant cases (2 misclassified by the AI tool as benign). Thirty-six radiologists were asked to use radiological vocabulary, typical to reporting LDCT scans, to describe the mapped regions of interest (ROI). The radiologists' annotations were then grouped by using a clustering-based technique. Topics were extracted from the annotations and for each ROI, a percentage of annotations containing each topic were found. Radiologists annotated 17 and 24 unique ROIs on benign and malignant cases, respectively. Agreement on the main label (e.g., "vessel," "nodule") by radiologists was only seen in only in 12% of all areas (5/41 ROI). Topic analyses identified six descriptors which are commonly associated with a lower malignancy likelihood. Eight common topics related to a higher malignancy likelihood were also determined. Occlusion-based saliency maps were used to explain an AI decision-making process to radiologists, who in turn have provided insight into the level of agreement between the AI's decision and radiological lexicon.

Computer-Assisted Nuclear Atypia Scoring of Breast Cancer: a Preliminary Study.

Inter-pathologist agreement for nuclear atypia scoring of breast cancer is poor. To address this problem, previous studies suggested some criteria for describing the variations appearance of tumor cells relative to normal cells. However, these criteria were still assessed subjectively by pathologists. Previous studies used quantitative computer-extracted features for scoring. However, application of these tools is limited as further improvement in their accuracy is required. This study proposes COMPASS (COMputer-assisted analysis combined with Pathologist's ASSessment) for reproducible nuclear atypia scoring. COMPASS relies on both cytological criteria assessed subjectively by pathologists as well as computer-extracted textural features. Using machine learning, COMPASS combines these two sets of features and output nuclear atypia score. COMPASS's performance was evaluated using 300 images for which expert-consensus derived reference nuclear pleomorphism scores were available, and they were scanned by two scanners from different vendors. A personalized model was built for three pathologists who gave scores to six atypia-related criteria for each image. Leave-one-out cross validation (LOOCV) was used. COMPASS was trained and tested for each pathologist separately. Percentage agreement between COMPASS and the reference nuclear scores was 93.8%, 92.9%, and 93.1% for three pathologists. COMPASS's performance in nuclear grading was almost identical for both scanners, with Cohen's kappa ranging from 0.80 to 0.86 for different pathologists and different scanners. Independently, the images were also assessed by two experienced senior pathologists. Cohen's kappa of COMPASS was comparable to the Cohen's kappa for two senior pathologists (0.79 and 0.68).

Computer-extracted global radiomic features can predict the radiologists' first impression about the abnormality of a screening mammogram.

OBJECTIVE: Radiologists can detect the gist of abnormal based on their rapid initial impression on a mammogram (ie, global gist signal [GGS]). This study explores (1) whether global radiomic (ie, computer-extracted) features can predict the GGS; and if so, (ii) what features are the most important drivers of the signals. METHODS: The GGS of cases in two extreme conditions was considered: when observers detect a very strong gist (high-gist) and when the gist of abnormal was not/poorly perceived (low-gist). Gist signals/scores from 13 observers reading 4191 craniocaudal mammograms were collected. As gist is a noisy signal, the gist scores from all observers were averaged and assigned to each image. The high-gist and low-gist categories contained all images in the fourth and first quartiles, respectively. One hundred thirty handcrafted global radiomic features (GRFs) per mammogram were extracted and utilized to construct eight separate machine learning random forest classifiers (All, Normal, Cancer, Prior-1, Prior-2, Missed, Prior-Visible, and Prior-Invisible) for characterizing high-gist from low-gist images. The models were trained and validated using the 10-fold cross-validation approach. The models' performances were evaluated by the area under receiver operating characteristic curve (AUC). Important features for each model were identified through a scree test. RESULTS: The Prior-Visible model achieved the highest AUC of 0.84 followed by the Prior-Invisible (0.83), Normal (0.82), Prior-1 (0.81), All (0.79), Prior-2 (0.77), Missed (0.75), and Cancer model (0.69). Cluster shade, standard deviation, skewness, kurtosis, and range were identified to be the most important features. CONCLUSIONS: Our findings suggest that GRFs can accurately classify high- from low-gist images. ADVANCES IN KNOWLEDGE: Global mammographic radiomic features can accurately predict high- from low-gist images with five features identified to be valuable in describing high-gist images. These are critical in providing better understanding of the mammographic image characteristics that drive the strength of the GGSs which could be exploited to advance breast cancer (BC) screening and risk prediction, enabling early detection and treatment of BC thereby further reducing BC-related deaths.

AI for interpreting screening mammograms: implications for missed cancer in double reading practices and challenging-to-locate lesions.

Although the value of adding AI as a surrogate second reader in various scenarios has been investigated, it is unknown whether implementing an AI tool within double reading practice would capture additional subtle cancers missed by both radiologists who independently assessed the mammograms. This paper assesses the effectiveness of two state-of-the-art Artificial Intelligence (AI) models in detecting retrospectively-identified missed cancers within a screening program employing double reading practices. The study also explores the agreement between AI and radiologists in locating the lesions, considering various levels of concordance among the radiologists in locating the lesions. The Globally-aware Multiple Instance Classifier (GMIC) and Global-Local Activation Maps (GLAM) models were fine-tuned for our dataset. We evaluated the sensitivity of both models on missed cancers retrospectively identified by a panel of three radiologists who reviewed prior examinations of 729 cancer cases detected in a screening program with double reading practice. Two of these experts annotated the lesions, and based on their concordance levels, cases were categorized as 'almost perfect,' 'substantial,' 'moderate,' and 'poor.' We employed Similarity or Histogram Intersection (SIM) and Kullback-Leibler Divergence (KLD) metrics to compare saliency maps of malignant cases from the AI model with annotations from radiologists in each category. In total, 24.82% of cancers were labeled as "missed." The performance of GMIC and GLAM on the missed cancer cases was 82.98% and 79.79%, respectively, while for the true screen-detected cancers, the performances were 89.54% and 87.25%, respectively (p-values for the difference in sensitivity < 0.05). As anticipated, SIM and KLD from saliency maps were best in 'almost perfect,' followed by 'substantial,' 'moderate,' and 'poor.' Both GMIC and GLAM (p-values < 0.05) exhibited greater sensitivity at higher concordance. Even in a screening program with independent double reading, adding AI could potentially identify missed cancers. However, the challenging-to-locate lesions for radiologists impose a similar challenge for AI.

Familiarity, confidence and preference of artificial intelligence feedback and prompts by Australian breast cancer screening readers.

Objectives This study explored the familiarity, perceptions and confidence of Australian radiology clinicians involved in reading screening mammograms, regarding artificial intelligence (AI) applications in breast cancer detection. Methods Sixty-five radiologists, breast physicians and radiology trainees participated in an online survey that consisted of 23 multiple choice questions asking about their experience and familiarity with AI products. Furthermore, the survey asked about their confidence in using AI outputs and their preference for AI modes applied in a breast screening context. Participants' responses to questions were compared using Pearson's χ 2 test. Bonferroni-adjusted significance tests were used for pairwise comparisons. Results Fifty-five percent of respondents had experience with AI in their workplaces, with automatic density measurement powered by machine learning being the most familiar AI product (69.4%). The top AI outputs with the highest ranks of perceived confidence were 'Displaying suspicious areas on mammograms with the percentage of cancer possibility' (67.8%) and 'Automatic mammogram classification (normal, benign, cancer, uncertain)' (64.6%). Radiology and breast physicians preferred using AI as second-reader mode (75.4% saying 'somewhat happy' to 'extremely happy') over triage (47.7%), pre-screening and first-reader modes (both with 26.2%) (P < 0.001). Conclusion The majority of screen readers expressed increased confidence in utilising AI for highlighting suspicious areas on mammograms and for automatically classifying mammograms. They considered AI as an optimal second-reader mode being the most ideal use in a screening program. The findings provide valuable insights into the familiarities and expectations of radiologists and breast clinicians for the AI products that can enhance the effectiveness of the breast cancer screening programs, benefitting both healthcare professionals and patients alike.

Evaluating Recalibrating AI Models for Breast Cancer Diagnosis in a New Context: Insights from Transfer Learning, Image Enhancement and High-Quality Training Data Integration.

This paper investigates the adaptability of four state-of-the-art artificial intelligence (AI) models to the Australian mammographic context through transfer learning, explores the impact of image enhancement on model performance and analyses the relationship between AI outputs and histopathological features for clinical relevance and accuracy assessment. A total of 1712 screening mammograms (n = 856 cancer cases and n = 856 matched normal cases) were used in this study. The 856 cases with cancer lesions were annotated by two expert radiologists and the level of concordance between their annotations was used to establish two sets: a 'high-concordances subset' with 99% agreement of cancer location and an 'entire dataset' with all cases included. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of Globally aware Multiple Instance Classifier (GMIC), Global-Local Activation Maps (GLAM), I&H and End2End AI models, both in the pretrained and transfer learning modes, with and without applying the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. The four AI models with and without transfer learning in the high-concordance subset outperformed those in the entire dataset. Applying the CLAHE algorithm to mammograms improved the performance of the AI models. In the high-concordance subset with the transfer learning and CLAHE algorithm applied, the AUC of the GMIC model was highest (0.912), followed by the GLAM model (0.909), I&H (0.893) and End2End (0.875). There were significant differences (p < 0.05) in the performances of the four AI models between the high-concordance subset and the entire dataset. The AI models demonstrated significant differences in malignancy probability concerning different tumour size categories in mammograms. The performance of AI models was affected by several factors such as concordance classification, image enhancement and transfer learning. Mammograms with a strong concordance with radiologists' annotations, applying image enhancement and transfer learning could enhance the accuracy of AI models.

Investigating the impact of cognitive biases in radiologists' image interpretation: A scoping review.

RATIONALE AND OBJECTIVE: Image interpretation is a fundamental aspect of radiology. The treatment and management of patients relies on accurate and timely imaging diagnosis. However, errors in radiological reports can negatively impact on patient health outcomes. These misdiagnoses can be caused by several different errors, but cognitive biases account for 74 % of all image interpretation errors. There are many biases that can impact on a radiologist's perception and cognitive processes. Several recent narrative reviews have discussed these cognitive biases and have offered possible strategies to mitigate their effects. However, these strategies remain untested. Therefore, the purpose of this scoping review is to evaluate the current knowledge on the extent that cognitive biases impact on medical image interpretation. MATERIAL AND METHODS: Scopus and Medline Databases were searched using relevant keywords to identify papers published between 2012 and 2022. A subsequent hand search of the narrative reviews was also performed. All studies collected were screened and assessed against the inclusion and exclusion criteria. RESULTS: Twenty-four publications were included and categorised into five main themes: satisfaction of search, availability bias, hindsight bias, framing bias and other biases. From these studies, there were mixed results regarding the impact of cognitive biases, highlighting the need for further investigation in this area. Moreover, the limited and untested debiasing methods offered by a minority of the publications and narrative reviews also suggests the need for further research. The potential of role of artificial intelligence is also highlighted to further assist radiologists in identifying and mitigating these cognitive biases. CONCLUSION: Cognitive biases can impact radiologists' image interpretation, however the effectiveness of debiasing strategies remain largely untested.

The use of radiomics in magnetic resonance imaging for the pre-treatment characterisation of breast cancers: A scoping review.

Radiomics is an emerging field that aims to extract and analyse a comprehensive set of quantitative features from medical images. This scoping review is focused on MRI-based radiomic features for the molecular profiling of breast tumours and the implications of this work for predicting patient outcomes. A thorough systematic literature search and outcome extraction were performed to identify relevant studies published in MEDLINE/PubMed (National Centre for Biotechnology Information), EMBASE and Scopus from 2015 onwards. The following information was retrieved from each article: study purpose, study design, extracted radiomic features, machine learning technique(s), sample size/characteristics, statistical result(s) and implications on patient outcomes. Based on the study purpose, four key themes were identified in the included 63 studies: tumour subtype classification (n = 35), pathologically complete response (pCR) prediction (n = 15), lymph node metastasis (LNM) detection (n = 7) and recurrence rate prediction (n = 6). In all four themes, reported accuracies widely varied among the studies, for example, area under receiver characteristics curve (AUC) for detecting LNM ranged from 0.72 to 0.91 and the AUC for predicting pCR ranged from 0.71 to 0.99. In all four themes, combining radiomic features with clinical data improved the predictive models. Preliminary results of this study showed radiomics potential to characterise the whole tumour heterogeneity, with clear implications for individual-targeted treatment. However, radiomics is still in the pre-clinical phase, currently with an insufficient number of large multicentre studies and those existing studies are often limited by insufficient methodological transparency and standardised workflow. Consequently, the clinical translation of existing studies is currently limited.

Using Radiomics-Based Machine Learning to Create Targeted Test Sets to Improve Specific Mammography Reader Cohort Performance: A Feasibility Study.

Mammography interpretation is challenging with high error rates. This study aims to reduce the errors in mammography reading by mapping diagnostic errors against global mammographic characteristics using a radiomics-based machine learning approach. A total of 36 radiologists from cohort A (n = 20) and cohort B (n = 16) read 60 high-density mammographic cases. Radiomic features were extracted from three regions of interest (ROIs), and random forest models were trained to predict diagnostic errors for each cohort. Performance was evaluated using sensitivity, specificity, accuracy, and AUC. The impact of ROI placement and normalization on prediction was investigated. Our approach successfully predicted both the false positive and false negative errors of both cohorts but did not consistently predict location errors. The errors produced by radiologists from cohort B were less predictable compared to those in cohort A. The performance of the models did not show significant improvement after feature normalization, despite the mammograms being produced by different vendors. Our novel radiomics-based machine learning pipeline focusing on global radiomic features could predict false positive and false negative errors. The proposed method can be used to develop group-tailored mammographic educational strategies to help improve future mammography reader performance.

Incidence, mortality, survival, and disease burden of breast cancer in China compared to other developed countries.

Breast cancer was the most diagnosed malignant neoplasm and the second leading cause of cancer mortality among Chinese females in 2020. Increased risk factors and widespread adoption of westernized lifestyles have resulted in an upward trend in the occurrence of breast cancer. Up to date knowledge on the incidence, mortality, survival, and burden of breast cancer is essential for optimized cancer prevention and control. To better understand the status of breast cancer in China, this narrative literature review collected data from multiple sources, including studies obtained from the PubMed database and text references, national annual cancer report, government cancer database, Global Cancer Statistics 2020, and Global Burden of Disease study (2019). This review provides an overview of the incidence, mortality, and survival rates of breast cancer, as well as a summary of disability-adjusted life years associated with breast cancer in China from 1990 to 2019, with comparisons to Japan, South Korea, Australia and the United States.

Do Reader Characteristics Affect Diagnostic Efficacy in Screening Mammography? A Systematic Review.

To examine reader characteristics associated with diagnostic efficacy in the interpretation of screening mammograms. A systematic search of the literature was conducted using databases such as Cochrane, Scopus, Medline, Embase, Web of Science, and PubMed. Search terms were combined with "AND" or "OR" and included: "Radiologist's characteristics AND performance"; "radiologist experience AND screening mammography"; "annual volume read AND diagnostic efficacy"; "screening mammography performance OR diagnostic efficacy". Studies were included if they assessed reader performance in screening mammography interpretation, breast readers, used a reference standard to assess the performance, and were published in the English language. Twenty-eight studies were reviewed. Increasing reader's age was associated with lower false positive rates. No association was found between gender and performance. Half of the studies showed no association between years of reading mammograms and performance. Most studies showed that high reading volume was more likely to be associated with increased sensitivity, cancer detection rates (CDR), lower recall rate, and lower false positive rates. Inconsistent associations were found between fellowship training in breast imaging and reader performance. Specialization in breast imaging was associated with better CDR, sensitivity, and specificity. Limited studies were available to establish the association between performance and factors such as time spent in breast imaging (n = 2), screening focus (n = 1), formal rotation in mammography (n = 1), owner of practice (n = 1), and practice type (n = 1). No individual characteristics is associated with versatility in diagnostic efficacy, albeit reading volume and specialization in breast imaging appear to be associated with with increased sensitivity and CDR without significantly affecting other performance metrics.

Associations of Breast Arterial Calcifications with Cardiovascular Disease.

Cardiovascular diseases (CVD), including coronary artery disease (CAD), continue to be the leading cause of global mortality among women. While traditional CVD/CAD prevention tools play a significant role in reducing morbidity and mortality among both men and women, current tools for preventing CVD/CAD rely on traditional risk factor-based algorithms that often underestimate CVD/CAD risk in women compared with men. In recent years, some studies have suggested that breast arterial calcifications (BAC), which are benign calcifications seen in mammograms, may be linked to CVD/CAD. Considering that millions of women older than 40 years undergo annual screening mammography for breast cancer as a regular activity, innovative risk prediction factors for CVD/CAD involving mammographic data could offer a gender-specific and convenient solution. Such factors that may be independent of, or complementary to, current risk models without extra cost or radiation exposure are worthy of detailed investigation. This review aims to discuss relevant studies examining the association between BAC and CVD/CAD and highlights some of the issues related to previous studies' design such as sample size, population types, method of assessing BAC and CVD/CAD, definition of cardiovascular events, and other confounding factors. The work may also offer insights for future CVD risk prediction research directions using routine mammograms and radiomic features other than BAC such as breast density and macrocalcifications.

Forecasting and Optimizing Dual Media Filter Performance via Machine Learning.

Four different machine learning algorithms, including Decision Tree (DT), Random Forest (RF), Multivariable Linear Regression (MLR), Support Vector Regressions (SVR), and Gaussian Process Regressions (GPR), were applied to predict the performance of a multi-media filter operating as a function of raw water quality and plant operating variables. The models were trained using data collected over a seven year period covering water quality and operating variables, including true colour, turbidity, plant flow, and chemical dose for chlorine, KMnO4, FeCl3, and Cationic Polymer (PolyDADMAC). The machine learning algorithms have shown that the best prediction is at a 1-day time lag between input variables and unit filter run volume (UFRV). Furthermore, the RF algorithm with grid search using the input metrics mentioned above with a 1-day time lag has provided the highest reliability in predicting UFRV with a RMSE and R2 of 31.58 and 0.98, respectively. Similarly, RF with grid search has shown the shortest training time, prediction accuracy, and forecasting events using a ROC-AUC curve analysis (AUC over 0.8) in extreme wet weather events. Therefore, Random Forest with grid search and a 1-day time lag is an effective and robust machine learning algorithm that can predict the filter performance to aid water treatment operators in their decision makings by providing real-time warning of the potential turbidity breakthrough from the filters.

Reliability of radiologists' first impression when interpreting a screening mammogram.

Previous studies showed that radiologists can detect the gist of an abnormality in a mammogram based on a half-second image presentation through global processing of screening mammograms. This study investigated the intra- and inter-observer reliability of the radiologists' initial impressions about the abnormality (or "gist signal"). It also examined if a subset of radiologists produced more reliable and accurate gist signals. Thirty-nine radiologists provided their initial impressions on two separate occasions, viewing each mammogram for half a second each time. The intra-class correlation (ICC) values showed poor to moderate intra-reader reliability. Only 13 radiologists had an ICC of 0.6 or above, which is considered the minimum standard for reliability, and only three radiologists had an ICC exceeding 0.7. The median value for the weighted Cohen's Kappa was 0.478 (interquartile range = 0.419-0.555). The Mann-Whitney U-test showed that the "Gist Experts", defined as those who outperformed others, had significantly higher ICC values (p = 0.002) and weighted Cohen's Kappa scores (p = 0.026). However, even for these experts, the intra-radiologist agreements were not strong, as an ICC of at least 0.75 indicates good reliability and the signal from none of the readers reached this level of reliability as determined by ICC values. The inter-reader reliability of the gist signal was poor, with an ICC score of 0.31 (CI = 0.26-0.37). The Fleiss Kappa score of 0.106 (CI = 0.105-0.106), indicating only slight inter-reader agreement, confirms the findings from the ICC analysis. The intra- and inter-reader reliability analysis showed that the radiologists' initial impressions are not reliable signals. In particular, the absence of an abnormal gist does not reliably signal a normal case, so radiologists should keep searching. This highlights the importance of "discovery scanning," or coarse screening to detect potential targets before ending the visual search.

Mammography-based Radiomics in Breast Cancer: A Scoping Review of Current Knowledge and Future Needs.

RATIONALE AND OBJECTIVES: Breast cancer is a highly complex heterogeneous disease. Current validated prognostic factors (e.g., histological grade, lymph node involvement, receptor status, and proliferation index), as well as multigene tests (e.g., Oncotype DX and PAM50) are helpful to describe breast cancer characteristics and predict the chance of recurrence risk and survival. Nevertheless, they are invasive and cannot capture a complete heterogeneity of the entire breast tumor resulting in up to 30% of patients being either over- or under-treated for breast cancer. Furthermore, multigene testings are time consuming and expensive. Radiomics is emerging as a reliable, accurate, non-invasive, and cost-effective approach of using quantitative image features to classify breast cancer characteristics and predict patient outcomes. Several recent radiomics reviews have been conducted in breast cancer, however, specific mammography-based radiomics studies have not been well discussed. This scoping review aims to assess and summarize the current evidence on the potential usefulness of mammography-based (i.e., digital mammography, digital breast tomosynthesis, and contrast-enhanced mammography) radiomics in predicting factors that describe breast cancer characteristics, recurrence, and survival. MATERIALS AND METHODS: PubMed database and eligible text reference were searched using relevant keywords to identify studies published between 2015 and December 19, 2020. Studies collected were screened and assessed based on the inclusion and exclusion criteria. RESULTS: Eighteen eligible studies were included and organized into three main sections: radiomics predicting breast cancer characteristics, radiomics predicting breast cancer recurrence and survival, and radiomics integrating with clinical data. Majority of publications reported retrospective studies while three studies examined prospective cohorts. Encouraging results were reported, suggesting the potential clinical value of mammography-based radiomics. Further efforts are required to standardize radiomics approaches and catalogue reproducible and relevant mammographic radiomic features. The role of integrating radiomics with other information is discussed. CONCLUSION: The potential role of mammography-based radiomics appears promising but more efforts are required to further evaluate its reliability as a routine clinical tool.

A machine learning model based on readers' characteristics to predict their performances in reading screening mammograms.

OBJECTIVES: Proposing a machine learning model to predict readers' performances, as measured by the area under the receiver operating characteristics curve (AUC) and lesion sensitivity, using the readers' characteristics. METHODS: Data were collected from 905 radiologists and breast physicians who completed at least one case-set of 60 mammographic images containing 40 normal and 20 biopsy-proven cancer cases. Nine different case-sets were available. Using a questionnaire, we collected radiologists' demographic details, such as reading volume and years of experience. These characteristics along with a case set difficulty measure were fed into two ensemble of regression trees to predict the readers' AUCs and lesion sensitivities. We calculated the Pearson correlation coefficient between the predicted values by the model and the actual AUC and lesion sensitivity. The usefulness of the model to categorize readers as low and high performers based on different criteria was also evaluated. The performances of the models were evaluated using leave-one-out cross-validation. RESULTS: The Pearson correlation coefficient between the predicted AUC and actual one was 0.60 (p < 0.001). The model's performance for differentiating the reader in the first and fourth quartile based on the AUC values was 0.86 (95% CI 0.83-0.89). The model reached an AUC of 0.91 (95% CI 0.88-0.93) for distinguishing the readers in the first quartile from the fourth one based on the lesion sensitivity. CONCLUSION: A machine learning model can be used to categorize readers as high- or low-performing. Such model could be useful for screening programs for designing a targeted quality assurance and optimizing the double reading practice.