Artificial intelligence-supported screen reading versus standard double reading in the Mammography Screening with Artificial Intelligence trial (MASAI): a clinical safety analysis of a randomised, controlled, non-inferiority, single-blinded, screening accuracy study

AI-integrated Screening to Replace Double Reading of Mammograms: A Population-wide Accuracy and Feasibility Study

Mammography screening supported by deep learning-based artificial intelligence (AI) solutions can potentially reduce workload without compromising breast cancer detection accuracy, but the site of deployment in the workflow might be crucial. This retrospective study compared three simulated AI-integrated screening scenarios with standard double reading with arbitration in a sample of 249 402 mammograms from a representative screening population. A commercial AI system replaced the first reader (scenario 1: integrated AIfirst), the second reader (scenario 2: integrated AIsecond), or both readers for triaging of low- and high-risk cases (scenario 3: integrated AItriage). AI threshold values were chosen based partly on previous validation and setting the screen-read volume reduction at approximately 50% across scenarios. Detection accuracy measures were calculated. Compared with standard double reading, integrated AIfirst showed no evidence of a difference in accuracy metrics except for a higher arbitration rate (+0.99%, P < .001). Integrated AIsecond had lower sensitivity (-1.58%, P < .001), negative predictive value (NPV) (-0.01%, P < .001), and recall rate (-0.06%, P = .04) but a higher positive predictive value (PPV) (+0.03%, P < .001) and arbitration rate (+1.22%, P < .001). Integrated AItriage achieved higher sensitivity (+1.33%, P < .001), PPV (+0.36%, P = .03), and NPV (+0.01%, P < .001) but lower arbitration rate (-0.88%, P < .001). Replacing one or both readers with AI seems feasible; however, the site of application in the workflow can have clinically relevant effects on accuracy and workload. Keywords: Mammography, Breast, Neoplasms-Primary, Screening, Epidemiology, Diagnosis, Convolutional Neural Network (CNN) Supplemental material is available for this article. Published under a CC BY 4.0 license.

Recommendations for the creation of benchmark datasets for reproducible artificial intelligence in radiology

Various healthcare domains have witnessed successful preliminary implementation of artificial intelligence (AI) solutions, including radiology, though limited generalizability hinders their widespread adoption. Currently, most research groups and industry have limited access to the data needed for external validation studies. The creation and accessibility of benchmark datasets to validate such solutions represents a critical step towards generalizability, for which an array of aspects ranging from preprocessing to regulatory issues and biostatistical principles come into play. In this article, the authors provide recommendations for the creation of benchmark datasets in radiology, explain current limitations in this realm, and explore potential new approaches. CLINICAL RELEVANCE STATEMENT: Benchmark datasets, facilitating validation of AI software performance can contribute to the adoption of AI in clinical practice. KEY POINTS: Benchmark datasets are essential for the validation of AI software performance. Factors like image quality and representativeness of cases should be considered. Benchmark datasets can help adoption by increasing the trustworthiness and robustness of AI.

Initial interpretation scores of screening mammograms and cancer detection in BreastScreen Norway

PURPOSE

To explore the association between radiologists' interpretation scores, early performance measures and cumulative reading volume in mammographic screening.

METHOD

We analyzed 1,689,731 screening examinations (3,379,462 breasts) from BreastScreen Norway 2012-2020, all breasts scored 1-5 by two independent radiologists. Score 1 was considered negative/benign and score ≥2 positive in this scoring system. We performed descriptive analyses of recall, screen-detected cancer, positive predictive value (PPV) 1, mammographic features and histopathological characteristics by breast-based interpretation scores, and cumulative reading volume by examination-based interpretation scores.

RESULTS

Counting breasts and not women, 3.9 % (132,570/3,379,462) had a score of ≥2 by one or both radiologists. Of these, 84.8 % (112,440/132,570) were given a maximum score 2. Total recall rate was 1.6 % (53,735/3,379,462), 69.3 % (37,220/53,735) given maximum score 2. Among the 0.3 % (9733/3,379,462) diagnosed with screen-detected cancer, 34.6 % (3369/9733) had maximum score 3. The percentages of recall, screen-detected cancer and PPV-1 increased by increasing the sum of scores assigned by two radiologists (p < 0.001 for trend). Higher proportions of masses were observed among recalls and screen-detected cancers with low scores, and higher proportions of spiculated masses were observed for high scores (p < 0.001). Proportions of invasive carcinoma, histological grade 3 and lymph node positive tumors were higher for high versus low scores (p < 0.001). The proportion of examinations scored 1 increased by cumulative reading volume.

CONCLUSIONS

We observed higher rates of recall and screen-detected cancer and less favorable histopathological tumor characteristics for high versus low interpretation scores. However, a considerable number of recalls and screen-detected cancers had low interpretation scores.

AI performance by mammographic density in a retrospective cohort study of 99,489 participants in BreastScreen Norway

OBJECTIVE

To explore the ability of artificial intelligence (AI) to classify breast cancer by mammographic density in an organized screening program.

MATERIALS AND METHOD

We included information about 99,489 examinations from 74,941 women who participated in BreastScreen Norway, 2013-2019. All examinations were analyzed with an AI system that assigned a malignancy risk score (AI score) from 1 (lowest) to 10 (highest) for each examination. Mammographic density was classified into Volpara density grade (VDG), VDG1-4; VDG1 indicated fatty and VDG4 extremely dense breasts. Screen-detected and interval cancers with an AI score of 1-10 were stratified by VDG.

RESULTS

We found 10,406 (10.5% of the total) examinations to have an AI risk score of 10, of which 6.7% (704/10,406) was breast cancer. The cancers represented 89.7% (617/688) of the screen-detected and 44.6% (87/195) of the interval cancers. 20.3% (20,178/99,489) of the examinations were classified as VDG1 and 6.1% (6047/99,489) as VDG4. For screen-detected cancers, 84.0% (68/81, 95% CI, 74.1-91.2) had an AI score of 10 for VDG1, 88.9% (328/369, 95% CI, 85.2-91.9) for VDG2, 92.5% (185/200, 95% CI, 87.9-95.7) for VDG3, and 94.7% (36/38, 95% CI, 82.3-99.4) for VDG4. For interval cancers, the percentages with an AI score of 10 were 33.3% (3/9, 95% CI, 7.5-70.1) for VDG1 and 48.0% (12/25, 95% CI, 27.8-68.7) for VDG4.

CONCLUSION

The tested AI system performed well according to cancer detection across all density categories, especially for extremely dense breasts. The highest proportion of screen-detected cancers with an AI score of 10 was observed for women classified as VDG4.

CLINICAL RELEVANCE STATEMENT

Our study demonstrates that AI can correctly classify the majority of screen-detected and about half of the interval breast cancers, regardless of breast density.

KEY POINTS

• Mammographic density is important to consider in the evaluation of artificial intelligence in mammographic screening. • Given a threshold representing about 10% of those with the highest malignancy risk score by an AI system, we found an increasing percentage of cancers with increasing mammographic density. • Artificial intelligence risk score and mammographic density combined may help triage examinations to reduce workload for radiologists.

Artificial Intelligence Algorithm for Subclinical Breast Cancer Detection

Importance

Early breast cancer detection is associated with lower morbidity and mortality.

Objective

To examine whether a commercial artificial intelligence (AI) algorithm for breast cancer detection could estimate the development of future cancer.

Design, Setting, and Participants

This retrospective cohort study of 116 495 women aged 50 to 69 years with no prior history of breast cancer before they underwent at least 3 consecutive biennial screening examinations used scores from an AI algorithm (INSIGHT MMG, version 1.1.7.2; Lunit Inc; used September 28, 2022, to April 5, 2023) for breast cancer detection and screening data from multiple, consecutive rounds of mammography performed from September 13, 2004, to December 21, 2018, at 9 breast centers in Norway. The statistical analyses were performed from September 2023 to August 2024.

Exposure

Artificial intelligence algorithm score indicating suspicion for the presence of breast cancer. The algorithm provided a continuous cancer detection score for each examination ranging from 0 to 100, with increasing values indicating a higher likelihood of cancer being present on the current mammogram.

Main Outcomes and Measures

Maximum AI algorithm score for cancer detection and absolute difference in score among breasts of women developing screening-detected cancer, women with interval cancer, and women who screened negative.

Results

The mean (SD) age at the first study round was 58.5 (4.5) years for 1265 women with screening-detected cancer in the third round, 57.4 (4.6) years for 342 women with interval cancer after 3 negative screening rounds, and 56.4 (4.9) years for 116 495 women without breast cancer all 3 screening rounds. The mean (SD) absolute differences in AI scores among breasts of women developing screening-detected cancer were 21.3 (28.1) at the first study round, 30.7 (32.5) at the second study round, and 79.0 (28.9) at the third study round. The mean (SD) differences prior to interval cancer were 19.7 (27.0) at the first study round, 21.0 (27.7) at the second study round, and 34.0 (33.6) at the third study round. The mean (SD) differences among women who did not develop breast cancer were 9.9 (17.5) at the first study round, 9.6 (17.4) at the second study round, and 9.3 (17.3) at the third study round. Areas under the receiver operating characteristic curve for the absolute difference were 0.63 (95% CI, 0.61-0.65) at the first study round, 0.72 (95% CI, 0.71-0.74) at the second study round, and 0.96 (95% CI, 0.95-0.96) at the third study round for screening-detected cancer and 0.64 (95% CI, 0.61-0.67) at the first study round, 0.65 (95% CI, 0.62-0.68) at the second study round, and 0.77 (95% CI, 0.74-0.79) at the third study round for interval cancers.

Conclusions and Relevance

In this retrospective cohort study of women undergoing screening mammography, mean absolute AI scores were higher for breasts developing vs not developing cancer 4 to 6 years before their eventual detection. These findings suggest that commercial AI algorithms developed for breast cancer detection may identify women at high risk of a future breast cancer, offering a pathway for personalized screening approaches that can lead to earlier cancer diagnosis.

[The possible benefit of artificial intelligence in an organized population-related screening program : Initial results and perspective]

BACKGROUND

Mammography screening programs (MSP) have shown that breast cancer can be detected at an earlier stage enabling less invasive treatment and leading to a better survival rate. The considerable numbers of interval breast cancer (IBC) and the additional examinations required, the majority of which turn out not to be cancer, are critically assessed.

OBJECTIVE

In recent years companies and universities have used machine learning (ML) to develop powerful algorithms that demonstrate astonishing abilities to read mammograms. Can such algorithms be used to improve the quality of MSP?

METHOD

The original screening mammographies of 251 cases with IBC were retrospectively analyzed using the software ProFound AI® (iCAD) and the results were compared (case score, risk score) with a control group. The relevant current literature was also studied.

RESULTS

The distributions of the case scores and the risk scores were markedly shifted to higher risks compared to the control group, comparable to the results of other studies.

CONCLUSION

Retrospective studies as well as our own data show that artificial intelligence (AI) could change our approach to MSP in the future in the direction of personalized screening and could enable a significant reduction in the workload of radiologists, fewer additional examinations and a reduced number of IBCs; however, the results of prospective studies are needed before implementation.

Detection of breast cancer in digital breast tomosynthesis with vision transformers

Digital Breast Tomosynthesis (DBT) has revolutionized more traditional breast imaging through its three-dimensional (3D) visualization capability that significantly enhances lesion discernibility, reduces tissue overlap, and improves diagnostic precision as compared to conventional two-dimensional (2D) mammography. In this study, we propose an advanced Computer-Aided Detection (CAD) system that harnesses the power of vision transformers to augment DBT's diagnostic efficiency. This scheme uses a neural network to glean attributes from the 2D slices of DBT followed by post-processing that considers features from neighboring slices to categorize the entire 3D scan. By leveraging a transfer learning technique, we trained and validated our CAD framework on a unique dataset consisting of 3,831 DBT scans and subsequently tested it on 685 scans. Of the architectures tested, the Swin Transformer outperformed the ResNet101 and vanilla Vision Transformer. It achieved an impressive AUC score of 0.934 ± 0.026 at a resolution of 384 × 384. Increasing the image resolution from 224 to 384 not only maintained vital image attributes but also led to a marked improvement in performance (p-value = 0.0003). The Mean Teacher algorithm, a semi-supervised method using both labeled and unlabeled DBT slices, showed no significant improvement over the supervised approach. Comprehensive analyses across different lesion types, sizes, and patient ages revealed consistent performance. The integration of attention mechanisms yielded a visual narrative of the model's decision-making process that highlighted the prioritized regions during assessments. These findings should significantly propel the methodologies employed in DBT image analysis by setting a new benchmark for breast cancer diagnostic precision.

Current status and prospects of breast cancer imaging-based diagnosis using artificial intelligence

Breast imaging has several modalities, each unique in terms of its imaging position, evaluation index, and imaging method. Breast diagnosis is made by combining a large number of past imaging features with the clinical course and histological findings. Artificial intelligence (AI), which extracts the features from image data and evaluates them based on comprehensive analysis, has been making rapid progress in this regard. Many previous studies have demonstrated the usefulness and development potential of AI, such as machine learning and deep learning, in breast imaging. However, despite studies showing the good performance of AI models, their overall utilization remains low, since a large amount of diverse imaging data is required, and prospective verification is necessary to prove its high reproducibility and robustness. Sharing information and collaborating with multiple institutions to collect and verify images of different conditions and backgrounds are vital. If image diagnosis using AI can indeed ensure a more detailed diagnosis, such as breast cancer subtypes or prognosis, it can help develop personalized medicine, which is urgently required. The positive results of AI research, using such image information, can make each modality more valuable than ever. The current review summarized the results of previous studies using AI in each evaluation field and discussed the related future prospects.

Cost-Effectiveness of AI for Risk-Stratified Breast Cancer Screening

Importance

Previous research has shown good discrimination of short-term risk using an artificial intelligence (AI) risk prediction model (Mirai). However, no studies have been undertaken to evaluate whether this might translate into economic gains.

Objective

To assess the cost-effectiveness of incorporating risk-stratified screening using a breast cancer AI model into the United Kingdom (UK) National Breast Cancer Screening Program.

Design, Setting, and Participants

This study, conducted from January 1, 2023, to January 31, 2024, involved the development of a decision analytical model to estimate health-related quality of life, cancer survival rates, and costs over the lifetime of the female population eligible for screening. The analysis took a UK payer perspective, and the simulated cohort consisted of women aged 50 to 70 years at screening.

Exposures

Mammography screening at 1 to 6 yearly screening intervals based on breast cancer risk and standard care (screening every 3 years).

Main Outcomes and Measures

Incremental net monetary benefit based on quality-adjusted life-years (QALYs) and National Health Service (NHS) costs (given in pounds sterling; to convert to US dollars, multiply by 1.28).

Results

Artificial intelligence-based risk-stratified programs were estimated to be cost-saving and increase QALYs compared with the current screening program. A screening schedule of every 6 years for lowest-risk individuals, biannually and triennially for those below and above average risk, respectively, and annually for those at highest risk was estimated to give yearly net monetary benefits within the NHS of approximately £60.4 (US $77.3) million and £85.3 (US $109.2) million, with QALY values set at £20 000 (US $25 600) and £30 000 (US $38 400), respectively. Even in scenarios where decision-makers hesitate to allocate additional NHS resources toward screening, implementing the proposed strategies at a QALY value of £1 (US $1.28) was estimated to generate a yearly monetary benefit of approximately £10.6 (US $13.6) million.

Conclusions and Relevance

In this decision analytical model study of integrating risk-stratified screening with a breast cancer AI model into the UK National Breast Cancer Screening Program, risk-stratified screening was likely to be cost-effective, yielding added health benefits at reduced costs. These results are particularly relevant for health care settings where resources are under pressure. New studies to prospectively evaluate AI-guided screening appear warranted.

Conceptual review of outcome metrics and measures used in clinical evaluation of artificial intelligence in radiology

Artificial intelligence (AI) has numerous applications in radiology. Clinical research studies to evaluate the AI models are also diverse. Consequently, diverse outcome metrics and measures are employed in the clinical evaluation of AI, presenting a challenge for clinical radiologists. This review aims to provide conceptually intuitive explanations of the outcome metrics and measures that are most frequently used in clinical research, specifically tailored for clinicians. While we briefly discuss performance metrics for AI models in binary classification, detection, or segmentation tasks, our primary focus is on less frequently addressed topics in published literature. These include metrics and measures for evaluating multiclass classification; those for evaluating generative AI models, such as models used in image generation or modification and large language models; and outcome measures beyond performance metrics, including patient-centered outcome measures. Our explanations aim to guide clinicians in the appropriate use of these metrics and measures.

Diagnostic capabilities of artificial intelligence as an additional reader in a breast cancer screening program

OBJECTIVES

We aimed to evaluate the early-detection capabilities of AI in a screening program over its duration, with a specific focus on the detection of interval cancers, the early detection of cancers with the assistance of AI from prior visits, and its impact on workload for various reading scenarios.

MATERIALS AND METHODS

The study included 22,621 mammograms of 8825 women within a 10-year biennial two-reader screening program. The statistical analysis focused on 5136 mammograms from 4282 women due to data retrieval issues, among whom 105 were diagnosed with breast cancer. The AI software assigned scores from 1 to 100. Histopathology results determined the ground truth, and Youden's index was used to establish a threshold. Tumor characteristics were analyzed with ANOVA and chi-squared test, and different workflow scenarios were evaluated using bootstrapping.

RESULTS

The AI software achieved an AUC of 89.6% (86.1-93.2%, 95% CI). The optimal threshold was 30.44, yielding 72.38% sensitivity and 92.86% specificity. Initially, AI identified 57 screening-detected cancers (83.82%), 15 interval cancers (51.72%), and 4 missed cancers (50%). AI as a second reader could have led to earlier diagnosis in 24 patients (average 29.92 ± 19.67 months earlier). No significant differences were found in cancer-characteristics groups. A hybrid triage workflow scenario showed a potential 69.5% reduction in workload and a 30.5% increase in accuracy.

CONCLUSION

This AI system exhibits high sensitivity and specificity in screening mammograms, effectively identifying interval and missed cancers and identifying 23% of cancers earlier in prior mammograms. Adopting AI as a triage mechanism has the potential to reduce workload by nearly 70%.

CLINICAL RELEVANCE STATEMENT

The study proposes a more efficient method for screening programs, both in terms of workload and accuracy.

KEY POINTS

• Incorporating AI as a triage tool in screening workflow improves sensitivity (72.38%) and specificity (92.86%), enhancing detection rates for interval and missed cancers. • AI-assisted triaging is effective in differentiating low and high-risk cases, reduces radiologist workload, and potentially enables broader screening coverage. • AI has the potential to facilitate early diagnosis compared to human reading.

How do AI markings on screening mammograms correspond to cancer location? An informed review of 270 breast cancer cases in BreastScreen Norway

OBJECTIVES

To compare the location of AI markings on screening mammograms with cancer location on diagnostic mammograms, and to classify interval cancers with high AI score as false negative, minimal sign, or true negative.

METHODS

In a retrospective study from 2022, we compared the performance of an AI system with independent double reading according to cancer detection. We found 93% (880/949) of the screen-detected cancers, and 40% (122/305) of the interval cancers to have the highest AI risk score (AI score of 10). In this study, four breast radiologists reviewed mammograms from 126 randomly selected screen-detected cancers and all 120 interval cancers with an AI score of 10. The location of the AI marking was stated as correct/not correct in craniocaudal and mediolateral oblique view. Interval cancers with an AI score of 10 were classified as false negative, minimal sign significant/non-specific, or true negative.

RESULTS

All screen-detected cancers and 78% (93/120) of the interval cancers with an AI score of 10 were correctly located by the AI system. The AI markings matched in both views for 79% (100/126) of the screen-detected cancers and 22% (26/120) of the interval cancers. For interval cancers with an AI score of 10, 11% (13/120) were correctly located and classified as false negative, 10% (12/120) as minimal sign significant, 26% (31/120) as minimal sign non-specific, and 31% (37/120) as true negative.

CONCLUSION

AI markings corresponded to cancer location for all screen-detected cancers and 78% of the interval cancers with high AI score, indicating a potential for reducing the number of interval cancers. However, it is uncertain whether interval cancers with subtle findings in only one view are actionable for recall in a true screening setting.

CLINICAL RELEVANCE STATEMENT

In this study, AI markings corresponded to the location of the cancer in a high percentage of cases, indicating that the AI system accurately identifies the cancer location in mammograms with a high AI score.

KEY POINTS

• All screen-detected and 78% of the interval cancers with high AI risk score (AI score of 10) had AI markings in one or two views corresponding to the location of the cancer on diagnostic images. • Among all 120 interval cancers with an AI score of 10, 21% (25/120) were classified as a false negative or minimal sign significant and had AI markings matching the cancer location, suggesting they may be visible on prior screening. • Most of the correctly located interval cancers matched only in one view, and the majority were classified as either true negative or minimal sign non-specific, indicating low potential for being detected earlier in a real screening setting.

Comparison of AI-integrated pathways with human-AI interaction in population mammographic screening for breast cancer

Artificial intelligence (AI) readers of mammograms compare favourably to individual radiologists in detecting breast cancer. However, AI readers cannot perform at the level of multi-reader systems used by screening programs in countries such as Australia, Sweden, and the UK. Therefore, implementation demands human-AI collaboration. Here, we use a large, high-quality retrospective mammography dataset from Victoria, Australia to conduct detailed simulations of five potential AI-integrated screening pathways, and examine human-AI interaction effects to explore automation bias. Operating an AI reader as a second reader or as a high confidence filter improves current screening outcomes by 1.9-2.5% in sensitivity and up to 0.6% in specificity, achieving 4.6-10.9% reduction in assessments and 48-80.7% reduction in human reads. Automation bias degrades performance in multi-reader settings but improves it for single-readers. This study provides insight into feasible approaches for AI-integrated screening pathways and prospective studies necessary prior to clinical adoption.

Patient perspectives on the use of artificial intelligence in prostate cancer diagnosis on MRI

OBJECTIVES

This study investigated patients' acceptance of artificial intelligence (AI) for diagnosing prostate cancer (PCa) on MRI scans and the factors influencing their trust in AI diagnoses.

MATERIALS AND METHODS

A prospective, multicenter study was conducted between January and November 2023. Patients undergoing prostate MRI were surveyed about their opinions on hypothetical AI assessment of their MRI scans. The questionnaire included nine items: four on hypothetical scenarios of combinations between AI and the radiologist, two on trust in the diagnosis, and three on accountability for misdiagnosis. Relationships between the items and independent variables were assessed using multivariate analysis.

RESULTS

A total of 212 PCa suspicious patients undergoing prostate MRI were included. The majority preferred AI involvement in their PCa diagnosis alongside a radiologist, with 91% agreeing with AI as the primary reader and 79% as the secondary reader. If AI has a high certainty diagnosis, 15% of the respondents would accept it as the sole decision-maker. Autonomous AI outperforming radiologists would be accepted by 52%. Higher educated persons tended to accept AI when it would outperform radiologists (p < 0.05). The respondents indicated that the hospital (76%), radiologist (70%), and program developer (55%) should be held accountable for misdiagnosis.

CONCLUSIONS

Patients favor AI involvement alongside radiologists in PCa diagnosis. Trust in AI diagnosis depends on the patient's education level and the AI performance, with autonomous AI acceptance by a small majority on the condition that AI outperforms a radiologist. Respondents held the hospital, radiologist, and program developers accountable for misdiagnosis in descending order of accountability.

CLINICAL RELEVANCE STATEMENT

Patients show a high level of acceptance for AI-assisted prostate cancer diagnosis on MRI, either alongside radiologists or fully autonomous, particularly if it demonstrates superior performance to radiologists alone.

KEY POINTS

Prostate cancer suspicious patients may accept autonomous AI based on performance. Patients prefer AI involvement alongside a radiologist in diagnosing prostate cancer. Patients indicate accountability for AI should be shared among multiple stakeholders.

Simulated arbitration of discordance between radiologists and artificial intelligence interpretation of breast cancer screening mammograms

Artificial intelligence (AI) algorithms have been retrospectively evaluated as replacement for one radiologist in screening mammography double-reading; however, methods for resolving discordance between radiologists and AI in the absence of 'real-world' arbitration may underestimate cancer detection rate (CDR) and recall. In 108,970 consecutive screens from a population screening program (BreastScreen WA, Western Australia), 20,120 were radiologist/AI discordant without real-world arbitration. Recall probabilities were randomly assigned for these screens in 1000 simulations. Recall thresholds for screen-detected and interval cancers (sensitivity) and no cancer (false-positive proportion, FPP) were varied to calculate mean CDR and recall rate for the entire cohort. Assuming 100% sensitivity, the maximum CDR was 7.30 per 1000 screens. To achieve >95% probability that the mean CDR exceeded the screening program CDR (6.97 per 1000), interval cancer sensitivities ≥63% (at 100% screen-detected sensitivity) and ≥91% (at 80% screen-detected sensitivity) were required. Mean recall rate was relatively constant across sensitivity assumptions, but varied by FPP. FPP > 6.5% resulted in recall rates that exceeded the program estimate (3.38%). CDR improvements depend on a majority of interval cancers being detected in radiologist/AI discordant screens. Such improvements are likely to increase recall, requiring careful monitoring where AI is deployed for screen-reading.

Deep learning versus manual morphology-based embryo selection in IVF: a randomized, double-blind noninferiority trial

To assess the value of deep learning in selecting the optimal embryo for in vitro fertilization, a multicenter, randomized, double-blind, noninferiority parallel-group trial was conducted across 14 in vitro fertilization clinics in Australia and Europe. Women under 42 years of age with at least two early-stage blastocysts on day 5 were randomized to either the control arm, using standard morphological assessment, or the study arm, employing a deep learning algorithm, intelligent Data Analysis Score (iDAScore), for embryo selection. The primary endpoint was a clinical pregnancy rate with a noninferiority margin of 5%. The trial included 1,066 patients (533 in the iDAScore group and 533 in the morphology group). The iDAScore group exhibited a clinical pregnancy rate of 46.5% (248 of 533 patients), compared to 48.2% (257 of 533 patients) in the morphology arm (risk difference -1.7%; 95% confidence interval -7.7, 4.3; P = 0.62). This study was not able to demonstrate noninferiority of deep learning for clinical pregnancy rate when compared to standard morphology and a predefined prioritization scheme. Australian New Zealand Clinical Trials Registry (ANZCTR) registration: 379161 .

Artificial intelligence in liver cancer - new tools for research and patient management

Liver cancer has high incidence and mortality globally. Artificial intelligence (AI) has advanced rapidly, influencing cancer care. AI systems are already approved for clinical use in some tumour types (for example, colorectal cancer screening). Crucially, research demonstrates that AI can analyse histopathology, radiology and natural language in liver cancer, and can replace manual tasks and access hidden information in routinely available clinical data. However, for liver cancer, few of these applications have translated into large-scale clinical trials or clinically approved products. Here, we advocate for the incorporation of AI in all stages of liver cancer management. We present a taxonomy of AI approaches in liver cancer, highlighting areas with academic and commercial potential, and outline a policy for AI-based liver cancer management, including interdisciplinary training of researchers, clinicians and patients. The potential of AI in liver cancer is immense, but effort is required to ensure that AI can fulfil expectations.

Healthcare Violence and the Potential Promises and Harms of Artificial Intelligence

ABSTRACT

Currently, the healthcare workplace is one of the most dangerous in the United States. Over a 3-month period in 2022, two nurses were assaulted every hour. Artificial intelligence (AI) has the potential to prevent workplace violence by developing unique patient insights through accessing almost instantly a patient's medical history, past institutional encounters, and possibly even their social media posts. De-escalating dialog can then be formulated, and hot-button topics avoided. AIs can also monitor patients in waiting areas for potential confrontational behavior.Many have concerns implementing AIs in healthcare. AIs are not expected to be 100% accurate, their performance is not compared with a computer but instead measured against humans. However, AIs are outperforming humans in many tasks. They are especially adept at taking standardized examinations, such as Board Exams, the Uniform Bar Exam, and the SAT and Graduate Record Exam. AIs are also performing diagnosis. Initial reports found that newer models have been observed to equal or outperform physicians in diagnostic accuracy and in the conveyance of empathy.In the area of interdiction, AI robots can both navigate and monitor for confrontational and illegal behavior. A human security agent would then be notified to resolve the situation. Our military is fielding autonomous AI robots to counter potential adversaries. For many, this new arms race has grave implications because of the potential of fielding this same security technology in healthcare and other civil settings.The healthcare delivery sector must determine the future roles of AI in relationship to human workers. AIs should only be used to support a human employee. AIs should not be the primary caregiver and a single human should not be monitoring multiple AIs simultaneously. Similar to not being copyrightable, disinformation produced by AIs should not be afforded 'free speech' protections. Any increase in productivity of an AI will equate with a loss of jobs. We need to ask, If all business sectors utilize AIs, will there be enough paid workers for the purchasing of services and products to keep our economy and society a float?

Developing, Purchasing, Implementing and Monitoring AI Tools in Radiology: Practical Considerations. A Multi-Society Statement From the ACR, CAR, ESR, RANZCR & RSNA

Artificial intelligence (AI) carries the potential for unprecedented disruption in radiology, with possible positive and negative consequences. The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever-growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones. This multi-society paper, presenting the views of Radiology Societies in the USA, Canada, Europe, Australia, and New Zealand, defines the potential practical problems and ethical issues surrounding the incorporation of AI into radiological practice. In addition to delineating the main points of concern that developers, regulators, and purchasers of AI tools should consider prior to their introduction into clinical practice, this statement also suggests methods to monitor their stability and safety in clinical use, and their suitability for possible autonomous function. This statement is intended to serve as a useful summary of the practical issues which should be considered by all parties involved in the development of radiology AI resources, and their implementation as clinical tools. KEY POINTS.

Radiologists' perceptions on AI integration: An in-depth survey study

PURPOSE

To assess the perceptions and attitudes of radiologists toward the adoption of artificial intelligence (AI) in clinical practice.

METHODS

A survey was conducted among members of the SIRM Lombardy. Radiologists' attitudes were assessed comprehensively, covering satisfaction with AI-based tools, propensity for innovation, and optimism for the future. The questionnaire consisted of two sections: the first gathered demographic and professional information using categorical responses, while the second evaluated radiologists' attitudes toward AI through Likert-type responses ranging from 1 to 5 (with 1 representing extremely negative attitudes, 3 indicating a neutral stance, and 5 reflecting extremely positive attitudes). Questionnaire refinement involved an iterative process with expert panels and a pilot phase to enhance consistency and eliminate redundancy. Exploratory data analysis employed descriptive statistics and visual assessment of Likert plots, supported by non-parametric tests for subgroup comparisons for a thorough analysis of specific emerging patterns.

RESULTS

The survey yielded 232 valid responses. The findings reveal a generally optimistic outlook on AI adoption, especially among young radiologist (<30) and seasoned professionals (>60, p<0.01). However, while 36.2 % (84 out 232) of subjects reported daily use of AI-based tools, only a third considered their contribution decisive (30 %, 25 out of 84). AI literacy varied, with a notable proportion feeling inadequately informed (36 %, 84 out of 232), particularly among younger radiologists (46 %, p < 0.01). Positive attitudes towards the potential of AI to improve detection, characterization of anomalies and reduce workload (positive answers > 80 %) and were consistent across subgroups. Radiologists' opinions were more skeptical about the role of AI in enhancing decision-making processes, including the choice of further investigation, and in personalized medicine in general. Overall, respondents recognized AI's significant impact on the radiology profession, viewing it as an opportunity (61 %, 141 out of 232) rather than a threat (18 %, 42 out of 232), with a majority expressing belief in AI's relevance to future radiologists' career choices (60 %, 139 out of 232). However, there were some concerns, particularly among breast radiologists (20 of 232 responders), regarding the potential impact of AI on the profession. Eighty-four percent of the respondents consider the final assessment by the radiologist still to be essential.

CONCLUSION

Our results indicate an overall positive attitude towards the adoption of AI in radiology, though this is moderated by concerns regarding training and practical efficacy. Addressing AI literacy gaps, especially among younger radiologists, is essential. Furthermore, proactively adapting to technological advancements is crucial to fully leverage AI's potential benefits. Despite the generally positive outlook among radiologists, there remains significant work to be done to enhance the integration and widespread use of AI tools in clinical practice.

Accuracy of an Artificial Intelligence System for Interval Breast Cancer Detection at Screening Mammography

Background Artificial intelligence (AI) systems can be used to identify interval breast cancers, although the localizations are not always accurate. Purpose To evaluate AI localizations of interval cancers (ICs) on screening mammograms by IC category and histopathologic characteristics. Materials and Methods A screening mammography data set (median patient age, 57 years [IQR, 52-64 years]) that had been assessed by two human readers from January 2011 to December 2018 was retrospectively analyzed using a commercial AI system. The AI outputs were lesion locations (heatmaps) and the highest per-lesion risk score (range, 0-100) assigned to each case. AI heatmaps were considered false positive (FP) if they occurred on normal screening mammograms or on IC screening mammograms (ie, in patients subsequently diagnosed with IC) but outside the cancer boundary. A panel of consultant radiology experts classified ICs as normal or benign (true negative [TN]), uncertain (minimal signs of malignancy [MS]), or suspicious (false negative [FN]). Several specificity and sensitivity thresholds were applied. Mann-Whitney U tests, Kruskal-Wallis tests, and χ2 tests were used to compare groups. Results A total of 2052 screening mammograms (514 ICs and 1548 normal mammograms) were included. The median AI risk score was 50 (IQR, 32-82) for TN ICs, 76 (IQR, 41-90) for ICs with MS, and 89 (IQR, 81-95) for FN ICs (P = .005). Higher median AI scores were observed for invasive tumors (62 [IQR, 39-88]) than for noninvasive tumors (33 [IQR, 20-55]; P < .01) and for high-grade (grade 2-3) tumors (62 [IQR, 40-87]) than for low-grade (grade 0-1) tumors (45 [IQR, 26-81]; P = .02). At the 96% specificity threshold, the AI algorithm flagged 121 of 514 (23.5%) ICs and correctly localized the IC in 93 of 121 (76.9%) cases, with 48 FP heatmaps on the mammograms for ICs (rate, 0.093 per case) and 74 FP heatmaps on normal mammograms (rate, 0.048 per case). The AI algorithm correctly localized a lower proportion of TN ICs (54 of 427; 12.6%) than ICs with MS (35 of 76; 46%) and FN ICs (four of eight; 50% [95% CI: 13, 88]; P < .001). The AI algorithm localized a higher proportion of node-positive than node-negative cancers (P = .03). However, no evidence of a difference by cancer type (P = .09), grade (P = .27), or hormone receptor status (P = .12) was found. At 89.8% specificity and 79% sensitivity thresholds, AI detection increased to 181 (35.2%) and 256 (49.8%) of the 514 ICs, respectively, with FP heatmaps on 158 (10.2%) and 307 (19.8%) of the 1548 normal mammograms. Conclusion Use of a standalone AI system improved early cancer detection by correctly identifying some cancers missed by two human readers, with no differences based on histopathologic features except for node-positive cancers. © RSNA, 2024 Supplemental material is available for this article.

The potential role for artificial intelligence in fracture risk prediction

Osteoporotic fractures are a major health challenge in older adults. Despite the availability of safe and effective therapies for osteoporosis, these therapies are underused in individuals at high risk for fracture, calling for better case-finding and fracture risk assessment strategies. Artificial intelligence (AI) and machine learning (ML) hold promise for enhancing identification of individuals at high risk for fracture by distilling useful features from high-dimensional data derived from medical records, imaging, and wearable devices. AI-ML could enable automated opportunistic screening for vertebral fractures and osteoporosis, home-based monitoring and intervention targeting lifestyle factors, and integration of multimodal features to leverage fracture prediction, ultimately aiding improved fracture risk assessment and individualised treatment. Optimism must be balanced with consideration for the explainability of AI-ML models, biases (including information inequity in numerically under-represented populations), model limitations, and net clinical benefit and workload impact. Clinical integration of AI-ML algorithms has the potential to transform osteoporosis management, offering a more personalised approach to reduce the burden of osteoporotic fractures.

Organizational impact of systemic implementation of digital breast tomosynthesis as a primary test for breast cancer screening in Italy

PURPOSE

We present a comprehensive investigation into the organizational, social, and ethical impact of implementing digital breast tomosynthesis (DBT) as a primary test for breast cancer screening in Italy. The analyses aimed to assess the feasibility of DBT specifically for all women aged 45-74, women aged 45-49 only, or those with dense breasts only.

METHODS

Questions were framed according to the European Network of Health Technology Assessment (EuNetHTA) Screening Core Model to produce evidence for the resources, equity, acceptability, and feasibility domains of the Grading of Recommendations Assessment, Development and Evaluation (GRADE) decision framework. The study integrated evidence from the literature, the MAITA DBT trials, and Italian pilot programs. Structured interviews, surveys, and systematic reviews were conducted to gather data on organizational impact, acceptability among women, reading and acquisition times, and the technical requirements of DBT in screening.

RESULTS

Implementing DBT could significantly affect the screening program, primarily due to increased reading times and the need for additional human resources (radiologists and radiographers). Participation rates in DBT screening were similar, if not better, to those observed with standard digital mammography, indicating good acceptability among women. The study also highlighted the necessity for specific training for radiographers. The interviewed key persons unanimously considered feasible tailored screening strategies based on breast density or age, but they require effective communication with the target population.

CONCLUSIONS

An increase in radiologists' and radiographers' workload limits the feasibility of DBT screening. Tailored screening strategies may maximize the benefits of DBT while mitigating potential challenges.

Artificial intelligence and endo-histo-omics: new dimensions of precision endoscopy and histology in inflammatory bowel disease

Integrating artificial intelligence into inflammatory bowel disease (IBD) has the potential to revolutionise clinical practice and research. Artificial intelligence harnesses advanced algorithms to deliver accurate assessments of IBD endoscopy and histology, offering precise evaluations of disease activity, standardised scoring, and outcome prediction. Furthermore, artificial intelligence offers the potential for a holistic endo-histo-omics approach by interlacing and harmonising endoscopy, histology, and omics data towards precision medicine. The emerging applications of artificial intelligence could pave the way for personalised medicine in IBD, offering patient stratification for the most beneficial therapy with minimal risk. Although artificial intelligence holds promise, challenges remain, including data quality, standardisation, reproducibility, scarcity of randomised controlled trials, clinical implementation, ethical concerns, legal liability, and regulatory issues. The development of standardised guidelines and interdisciplinary collaboration, including policy makers and regulatory agencies, is crucial for addressing these challenges and advancing artificial intelligence in IBD clinical practice and trials.

Navigating the Metaverse: A New Virtual Tool with Promising Real Benefits for Breast Cancer Patients

BC, affecting both women and men, is a complex disease where early diagnosis plays a crucial role in successful treatment and enhances patient survival rates. The Metaverse, a virtual world, may offer new, personalized approaches to diagnosing and treating BC. Although Artificial Intelligence (AI) is still in its early stages, its rapid advancement indicates potential applications within the healthcare sector, including consolidating patient information in one accessible location. This could provide physicians with more comprehensive insights into disease details. Leveraging the Metaverse could facilitate clinical data analysis and improve the precision of diagnosis, potentially allowing for more tailored treatments for BC patients. However, while this article highlights the possible transformative impacts of virtual technologies on BC treatment, it is important to approach these developments with cautious optimism, recognizing the need for further research and validation to ensure enhanced patient care with greater accuracy and efficiency.

Preoperative prediction of nodal status using clinical data and artificial intelligence derived mammogram features enabling abstention of sentinel lymph node biopsy in breast cancer

Introduction

Patients with clinically node-negative breast cancer have a negative sentinel lymph node status (pN0) in approximately 75% of cases and the necessity of routine surgical nodal staging by sentinel lymph node biopsy (SLNB) has been questioned. Previous prediction models for pN0 have included postoperative variables, thus defeating their purpose to spare patients non-beneficial axillary surgery. We aimed to develop a preoperative prediction model for pN0 and to evaluate the contribution of mammographic breast density and mammogram features derived by artificial intelligence for de-escalation of SLNB.

Materials and methods

This retrospective cohort study included 755 women with primary breast cancer. Mammograms were analyzed by commercially available artificial intelligence and automated systems. The additional predictive value of features was evaluated using logistic regression models including preoperative clinical variables and radiological tumor size. The final model was internally validated using bootstrap and externally validated in a separate cohort. A nomogram for prediction of pN0 was developed. The correlation between pathological tumor size and the preoperative radiological tumor size was calculated.

Results

Radiological tumor size was the strongest predictor of pN0 and included in a preoperative prediction model displaying an area under the curve of 0.68 (95% confidence interval: 0.63-0.72) in internal validation and 0.64 (95% confidence interval: 0.59-0.69) in external validation. Although the addition of mammographic features did not improve discrimination, the prediction model provided a 21% SLNB reduction rate when a false negative rate of 10% was accepted, reflecting the accepted false negative rate of SLNB.

Conclusion

This study shows that the preoperatively available radiological tumor size might replace pathological tumor size as a key predictor in a preoperative prediction model for pN0. While the overall performance was not improved by mammographic features, one in five patients could be omitted from axillary surgery by applying the preoperative prediction model for nodal status. The nomogram visualizing the model could support preoperative patient-centered decision-making on the management of the axilla.

The efficacy of artificial intelligence (AI) in detecting interval cancers in the national screening program of a middle-income country

AIM

We aimed to investigate the efficiency and accuracy of an artificial intelligence (AI) algorithm for detecting interval cancers in a middle-income country's national screening program.

MATERIAL AND METHODS

A total of 2,129,486 mammograms reported as BIRADS 1 and 2 were matched with the national cancer registry for interval cancers (IC). The IC group consisted of 442 cases, of which 36 were excluded due to having mammograms incompatible with the AI system. A control group of 446 women with two negative consequent mammograms was defined as time-proven normal and constituted the normal group. The cancer risk scores of both groups were determined from 1 to 10 with the AI system. The sensitivity and specificity values of the AI system were defined in terms of IC detection. The IC group was divided into subgroups with six-month intervals according to their time from screening to diagnosis: 0-6 months, 6-12 months, 12-18 months, and 18-24 months. The diagnostic performance of the AI system for all patients was evaluated using receiver operating characteristics (ROC) curve analysis. The diagnostic performance of the AI system for major and minor findings that expert readers determined was re-evaluated.

RESULTS

AI labeled 53% of ICs with the highest score of 10. The sensitivity of AI in detecting ICs was 53.7% and 38.5% at specificities of 90% and 95%, respectively. Area under the curve (AUC) of AI in detecting major signs was 0.93 (95% CI: 0.90-0.95) with a sensitivity of 81.6% and 72.4% at specificities of 90% and 95%, respectively (95% CI: 0.73-0.88 and 95% CI: 0.60-0.82 respectively) and minor signs was 0.87 (95% CI: 0.87-0.92) with a sensitivity of 70% and 53% at a specificity of 90% and 95%, respectively (95% CI: 0.65-0.82 and 95% CI: 0.52-0.71 respectively). In subgroup analysis for time to diagnosis, the AUC value of the AI system was higher in the 0-6 month period than in later periods.

CONCLUSION

This study showed the potential of AI in detecting ICs in initial mammograms and reducing human errors and undetected cancers.

Artificial intelligence and radiologists in prostate cancer detection on MRI (PI-CAI): an international, paired, non-inferiority, confirmatory study

BACKGROUND

Artificial intelligence (AI) systems can potentially aid the diagnostic pathway of prostate cancer by alleviating the increasing workload, preventing overdiagnosis, and reducing the dependence on experienced radiologists. We aimed to investigate the performance of AI systems at detecting clinically significant prostate cancer on MRI in comparison with radiologists using the Prostate Imaging-Reporting and Data System version 2.1 (PI-RADS 2.1) and the standard of care in multidisciplinary routine practice at scale.

METHODS

In this international, paired, non-inferiority, confirmatory study, we trained and externally validated an AI system (developed within an international consortium) for detecting Gleason grade group 2 or greater cancers using a retrospective cohort of 10 207 MRI examinations from 9129 patients. Of these examinations, 9207 cases from three centres (11 sites) based in the Netherlands were used for training and tuning, and 1000 cases from four centres (12 sites) based in the Netherlands and Norway were used for testing. In parallel, we facilitated a multireader, multicase observer study with 62 radiologists (45 centres in 20 countries; median 7 [IQR 5-10] years of experience in reading prostate MRI) using PI-RADS (2.1) on 400 paired MRI examinations from the testing cohort. Primary endpoints were the sensitivity, specificity, and the area under the receiver operating characteristic curve (AUROC) of the AI system in comparison with that of all readers using PI-RADS (2.1) and in comparison with that of the historical radiology readings made during multidisciplinary routine practice (ie, the standard of care with the aid of patient history and peer consultation). Histopathology and at least 3 years (median 5 [IQR 4-6] years) of follow-up were used to establish the reference standard. The statistical analysis plan was prespecified with a primary hypothesis of non-inferiority (considering a margin of 0·05) and a secondary hypothesis of superiority towards the AI system, if non-inferiority was confirmed. This study was registered at ClinicalTrials.gov, NCT05489341.

FINDINGS

Of the 10 207 examinations included from Jan 1, 2012, through Dec 31, 2021, 2440 cases had histologically confirmed Gleason grade group 2 or greater prostate cancer. In the subset of 400 testing cases in which the AI system was compared with the radiologists participating in the reader study, the AI system showed a statistically superior and non-inferior AUROC of 0·91 (95% CI 0·87-0·94; p<0·0001), in comparison to the pool of 62 radiologists with an AUROC of 0·86 (0·83-0·89), with a lower boundary of the two-sided 95% Wald CI for the difference in AUROC of 0·02. At the mean PI-RADS 3 or greater operating point of all readers, the AI system detected 6·8% more cases with Gleason grade group 2 or greater cancers at the same specificity (57·7%, 95% CI 51·6-63·3), or 50·4% fewer false-positive results and 20·0% fewer cases with Gleason grade group 1 cancers at the same sensitivity (89·4%, 95% CI 85·3-92·9). In all 1000 testing cases where the AI system was compared with the radiology readings made during multidisciplinary practice, non-inferiority was not confirmed, as the AI system showed lower specificity (68·9% [95% CI 65·3-72·4] vs 69·0% [65·5-72·5]) at the same sensitivity (96·1%, 94·0-98·2) as the PI-RADS 3 or greater operating point. The lower boundary of the two-sided 95% Wald CI for the difference in specificity (-0·04) was greater than the non-inferiority margin (-0·05) and a p value below the significance threshold was reached (p<0·001).

INTERPRETATION

An AI system was superior to radiologists using PI-RADS (2.1), on average, at detecting clinically significant prostate cancer and comparable to the standard of care. Such a system shows the potential to be a supportive tool within a primary diagnostic setting, with several associated benefits for patients and radiologists. Prospective validation is needed to test clinical applicability of this system.

FUNDING

Health~Holland and EU Horizon 2020.

AI-based automated segmentation for ovarian/adnexal masses and their internal components on ultrasound imaging

Purpose

Segmentation of ovarian/adnexal masses from surrounding tissue on ultrasound images is a challenging task. The separation of masses into different components may also be important for radiomic feature extraction. Our study aimed to develop an artificial intelligence-based automatic segmentation method for transvaginal ultrasound images that (1) outlines the exterior boundary of adnexal masses and (2) separates internal components.

Approach

A retrospective ultrasound imaging database of adnexal masses was reviewed for exclusion criteria at the patient, mass, and image levels, with one image per mass. The resulting 54 adnexal masses (36 benign/18 malignant) from 53 patients were separated by patient into training (26 benign/12 malignant) and independent test (10 benign/6 malignant) sets. U-net segmentation performance on test images compared to expert detailed outlines was measured using the Dice similarity coefficient (DSC) and the ratio of the Hausdorff distance to the effective diameter of the outline (R HD - D ) for each mass. Subsequently, in discovery mode, a two-level fuzzy c-means (FCM) unsupervised clustering approach was used to separate the pixels within masses belonging to hypoechoic or hyperechoic components.

Results

The DSC (median [95% confidence interval]) was 0.91 [0.78, 0.96], andR HD - D was 0.04 [0.01, 0.12], indicating strong agreement with expert outlines. Clinical review of the internal separation of masses into echogenic components demonstrated a strong association with mass characteristics.

Conclusion

A combined U-net and FCM algorithm for automatic segmentation of adnexal masses and their internal components achieved excellent results compared with expert outlines and review, supporting future radiomic feature-based classification of the masses by components.

Weakly Supervised Deep Learning in Radiology

Deep learning (DL) is currently the standard artificial intelligence tool for computer-based image analysis in radiology. Traditionally, DL models have been trained with strongly supervised learning methods. These methods depend on reference standard labels, typically applied manually by experts. In contrast, weakly supervised learning is more scalable. Weak supervision comprises situations in which only a portion of the data are labeled (incomplete supervision), labels refer to a whole region or case as opposed to a precisely delineated image region (inexact supervision), or labels contain errors (inaccurate supervision). In many applications, weak labels are sufficient to train useful models. Thus, weakly supervised learning can unlock a large amount of otherwise unusable data for training DL models. One example of this is using large language models to automatically extract weak labels from free-text radiology reports. Here, we outline the key concepts in weakly supervised learning and provide an overview of applications in radiologic image analysis. With more fundamental and clinical translational work, weakly supervised learning could facilitate the uptake of DL in radiology and research workflows by enabling large-scale image analysis and advancing the development of new DL-based biomarkers.

Clinical Integration of Artificial Intelligence for Breast Imaging

This article describes an approach to planning and implementing artificial intelligence products in a breast screening service. It highlights the importance of an in-depth understanding of the end-to-end workflow and effective project planning by a multidisciplinary team. It discusses the need for monitoring to ensure that performance is stable and meets expectations, as well as focusing on the potential for inadvertantly generating inequality. New cross-discipline roles and expertise will be needed to enhance service delivery.

Imaging features and management of focal liver lesions

Notably, the number of incidentally detected focal liver lesions (FLLs) has increased dramatically in recent years due to the increased use of radiological imaging. The diagnosis of FLLs can be made through a well-documented medical history, physical examination, laboratory tests, and appropriate imaging methods. Although benign FLLs are more common than malignant ones in adults, even in patients with primary malignancy, accurate diagnosis of incidental FLLs is of utmost clinical significance. In clinical practice, FLLs are frequently evaluated non-invasively using ultrasound (US), computed tomography (CT), and magnetic resonance imaging (MRI). Although US is a cost-effective and widely used imaging method, its diagnostic specificity and sensitivity for FLL characterization are limited. FLLs are primarily characterized by obtaining enhancement patterns through dynamic contrast-enhanced CT and MRI. MRI is a problem-solving method with high specificity and sensitivity, commonly used for the evaluation of FLLs that cannot be characterized by US or CT. Recent technical advancements in MRI, along with the use of hepatobiliary-specific MRI contrast agents, have significantly improved the success of FLL characterization and reduced unnecessary biopsies. The American College of Radiology (ACR) appropriateness criteria are evidence-based recommendations intended to assist clinicians in selecting the optimal imaging or treatment option for their patients. ACR Appropriateness Criteria Liver Lesion-Initial Characterization guideline provides recommendations for the imaging methods that should be used for the characterization of incidentally detected FLLs in various clinical scenarios. The American College of Gastroenterology (ACG) Clinical Guideline offers evidence-based recommendations for both the diagnosis and management of FLL. American Association for the Study of Liver Diseases (AASLD) Practice Guidance provides an approach to the diagnosis and management of patients with hepatocellular carcinoma. In this article, FLLs are reviewed with a comprehensive analysis of ACR Appropriateness Criteria, ACG Clinical Guideline, AASLD Practice Guidance, and current medical literature from peer-reviewed journals. The article includes a discussion of imaging methods used for the assessment of FLL, current recommended imaging techniques, innovations in liver imaging, contrast agents, imaging features of common nonmetastatic benign and malignant FLL, as well as current management recommendations.

"How I would like AI used for my imaging": children and young persons' perspectives

OBJECTIVES

Artificial intelligence (AI) tools are becoming more available in modern healthcare, particularly in radiology, although less attention has been paid to applications for children and young people. In the development of these, it is critical their views are heard.

MATERIALS AND METHODS

A national, online survey was publicised to UK schools, universities and charity partners encouraging any child or young adult to participate. The survey was "live" for one year (June 2022 to 2023). Questions about views of AI in general, and in specific circumstances (e.g. bone fractures) were asked.

RESULTS

One hundred and seventy-one eligible responses were received, with a mean age of 19 years (6-23 years) with representation across all 4 UK nations. Most respondents agreed or strongly agreed they wanted to know the accuracy of an AI tool that was being used (122/171, 71.3%), that accuracy was more important than speed (113/171, 66.1%), and that AI should be used with human oversight (110/171, 64.3%). Many respondents (73/171, 42.7%) felt AI would be more accurate at finding problems on bone X-rays than humans, with almost all respondents who had sustained a missed fracture strongly agreeing with that sentiment (12/14, 85.7%).

CONCLUSIONS

Children and young people in our survey had positive views regarding AI, and felt it should be integrated into modern healthcare, but expressed a preference for a "medical professional in the loop" and accuracy of findings over speed. Key themes regarding information on AI performance and governance were raised and should be considered prior to future AI implementation for paediatric healthcare.

CLINICAL RELEVANCE STATEMENT

Artificial intelligence (AI) integration into clinical practice must consider all stakeholders, especially paediatric patients who have largely been ignored. Children and young people favour AI involvement with human oversight, seek assurances for safety, accuracy, and clear accountability in case of failures.

KEY POINTS

Paediatric patient's needs and voices are often overlooked in AI tool design and deployment. Children and young people approved of AI, if paired with human oversight and reliability. Children and young people are stakeholders for developing and deploying AI tools in paediatrics.

Artificial Intelligence in Colorectal Cancer: From Patient Screening over Tailoring Treatment Decisions to Identification of Novel Biomarkers

BACKGROUND

Artificial intelligence (AI) is increasingly entering and transforming not only medical research but also clinical practice. In the last 10 years, new AI methods have enabled computers to perform visual tasks, reaching high performance and thereby potentially supporting and even outperforming human experts. This is in particular relevant for colorectal cancer (CRC), which is the 3rd most common cancer type in general, as along the CRC patient journey many complex visual tasks need to be performed: from endoscopy over imaging to histopathology; the screening, diagnosis, and treatment of CRC involve visual image analysis tasks.

SUMMARY

In all these clinical areas, AI models have shown promising results by supporting physicians, improving accuracy, and providing new biological insights and biomarkers. By predicting prognostic and predictive biomarkers from routine images/slides, AI models could lead to an improved patient stratification for precision oncology approaches in the near future. Moreover, it is conceivable that AI models, in particular together with innovative techniques such as single-cell or spatial profiling, could help identify novel clinically as well as biologically meaningful biomarkers that could pave the way to new therapeutic approaches.

KEY MESSAGES

Here, we give a comprehensive overview of AI in colorectal cancer, describing and discussing these developments as well as the next steps which need to be taken to incorporate AI methods more broadly into the clinical care of CRC.

Towards evidence-based practice 2.0: leveraging artificial intelligence in healthcare

Background

Evidence-based practice (EBP) involves making clinical decisions based on three sources of information: evidence, clinical experience and patient preferences. Despite popularization of EBP, research has shown that there are many barriers to achieving the goals of the EBP model. The use of artificial intelligence (AI) in healthcare has been proposed as a means to improve clinical decision-making. The aim of this paper was to pinpoint key challenges pertaining to the three pillars of EBP and to investigate the potential of AI in surmounting these challenges and contributing to a more evidence-based healthcare practice. We conducted a selective review of the literature on EBP and the integration of AI in healthcare to achieve this.

Challenges with the three components of EBP

Clinical decision-making in line with the EBP model presents several challenges. The availability and existence of robust evidence sometimes pose limitations due to slow generation and dissemination processes, as well as the scarcity of high-quality evidence. Direct application of evidence is not always viable because studies often involve patient groups distinct from those encountered in routine healthcare. Clinicians need to rely on their clinical experience to interpret the relevance of evidence and contextualize it within the unique needs of their patients. Moreover, clinical decision-making might be influenced by cognitive and implicit biases. Achieving patient involvement and shared decision-making between clinicians and patients remains challenging in routine healthcare practice due to factors such as low levels of health literacy among patients and their reluctance to actively participate, barriers rooted in clinicians' attitudes, scepticism towards patient knowledge and ineffective communication strategies, busy healthcare environments and limited resources.

AI assistance for the three components of EBP

AI presents a promising solution to address several challenges inherent in the research process, from conducting studies, generating evidence, synthesizing findings, and disseminating crucial information to clinicians to implementing these findings into routine practice. AI systems have a distinct advantage over human clinicians in processing specific types of data and information. The use of AI has shown great promise in areas such as image analysis. AI presents promising avenues to enhance patient engagement by saving time for clinicians and has the potential to increase patient autonomy although there is a lack of research on this issue.

Conclusion

This review underscores AI's potential to augment evidence-based healthcare practices, potentially marking the emergence of EBP 2.0. However, there are also uncertainties regarding how AI will contribute to a more evidence-based healthcare. Hence, empirical research is essential to validate and substantiate various aspects of AI use in healthcare.

Utilizing ChatGPT to Facilitate Referrals for Fetal Echocardiography

INTRODUCTION

OpenAI's GPT-4 (artificial intelligence [AI]) is being studied for its use as a medical decision support tool. This research examines its accuracy in refining referrals for fetal echocardiography (FE) to improve early detection and outcomes related to congenital heart defects (CHDs).

METHODS

Past FE data referred to our institution were evaluated separately by pediatric cardiologist, gynecologist (human experts [experts]), and AI, according to established guidelines. We compared experts and AI's agreement on referral necessity, with experts addressing discrepancies.

RESULTS

Total of 59 FE cases were addressed retrospectively. Cardiologist, gynecologist, and AI recommended performing FE in 47.5%, 49.2%, and 59.0% of cases, respectively. Comparing AI recommendations to experts indicated agreement of around 80.0% with both experts (p < 0.001). Notably, AI suggested more echocardiographies for minor CHD (64.7%) compared to experts (47.1%), and for major CHD, experts recommended performing FE in all cases (100%) while AI recommended in majority of cases (90.9%). Discrepancies between AI and experts are detailed and reviewed.

CONCLUSIONS

The evaluation found moderate agreement between AI and experts. Contextual misunderstandings and lack of specialized medical knowledge limit AI, necessitating clinical guideline guidance. Despite shortcomings, AI's referrals comprised 65% of minor CHD cases versus experts 47%, suggesting its potential as a cautious decision aid for clinicians.

Artificial Intelligence for breast cancer detection: Technology, challenges, and prospects

PURPOSE

This review provides an overview of the current state of artificial intelligence (AI) technology for automated detection of breast cancer in digital mammography (DM) and digital breast tomosynthesis (DBT). It aims to discuss the technology, available AI systems, and the challenges faced by AI in breast cancer screening.

METHODS

The review examines the development of AI technology in breast cancer detection, focusing on deep learning (DL) techniques and their differences from traditional computer-aided detection (CAD) systems. It discusses data pre-processing, learning paradigms, and the need for independent validation approaches.

RESULTS

DL-based AI systems have shown significant improvements in breast cancer detection. They have the potential to enhance screening outcomes, reduce false negatives and positives, and detect subtle abnormalities missed by human observers. However, challenges like the lack of standardised datasets, potential bias in training data, and regulatory approval hinder their widespread adoption.

CONCLUSIONS

AI technology has the potential to improve breast cancer screening by increasing accuracy and reducing radiologist workload. DL-based AI systems show promise in enhancing detection performance and eliminating variability among observers. Standardised guidelines and trustworthy AI practices are necessary to ensure fairness, traceability, and robustness. Further research and validation are needed to establish clinical trust in AI. Collaboration between researchers, clinicians, and regulatory bodies is crucial to address challenges and promote AI implementation in breast cancer screening.

Diagnostic performance with and without artificial intelligence assistance in real-world screening mammography

Purpose

To evaluate artificial intelligence-based computer-aided diagnosis (AI-CAD) for screening mammography, we analyzed the diagnostic performance of radiologists by providing and withholding AI-CAD results alternatively every month.

Methods

This retrospective study was approved by the institutional review board with a waiver for informed consent. Between August 2020 and May 2022, 1819 consecutive women (mean age 50.8 ± 9.4 years) with 2061 screening mammography and ultrasound performed on the same day in a single institution were included. Radiologists interpreted screening mammography in clinical practice with AI-CAD results being provided or withheld alternatively by month. The AI-CAD results were retrospectively obtained for analysis even when withheld from radiologists. The diagnostic performances of radiologists and stand-alone AI-CAD were compared and the performances of radiologists with and without AI-CAD assistance were also compared by cancer detection rate, recall rate, sensitivity, specificity, accuracy and area under the receiver-operating-characteristics curve (AUC).

Results

Twenty-nine breast cancer patients and 1790 women without cancers were included. Diagnostic performances of the radiologists did not significantly differ with and without AI-CAD assistance. Radiologists with AI-CAD assistance showed the same sensitivity (76.5%) and similar specificity (92.3% vs 93.8%), AUC (0.844 vs 0.851), and recall rates (8.8% vs. 7.4%) compared to standalone AI-CAD. Radiologists without AI-CAD assistance showed lower specificity (91.9% vs 94.6%) and accuracy (91.5% vs 94.1%) and higher recall rates (8.6% vs 5.9%, all p < 0.05) compared to stand-alone AI-CAD.

Conclusion

Radiologists showed no significant difference in diagnostic performance when both screening mammography and ultrasound were performed with or without AI-CAD assistance for mammography. However, without AI-CAD assistance, radiologists showed lower specificity and accuracy and higher recall rates compared to stand-alone AI-CAD.

A guide to artificial intelligence for cancer researchers

Artificial intelligence (AI) has been commoditized. It has evolved from a specialty resource to a readily accessible tool for cancer researchers. AI-based tools can boost research productivity in daily workflows, but can also extract hidden information from existing data, thereby enabling new scientific discoveries. Building a basic literacy in these tools is useful for every cancer researcher. Researchers with a traditional biological science focus can use AI-based tools through off-the-shelf software, whereas those who are more computationally inclined can develop their own AI-based software pipelines. In this article, we provide a practical guide for non-computational cancer researchers to understand how AI-based tools can benefit them. We convey general principles of AI for applications in image analysis, natural language processing and drug discovery. In addition, we give examples of how non-computational researchers can get started on the journey to productively use AI in their own work.

[Structured screening for sporadic breast cancer]

BACKGROUND

The aim of secondary prevention of breast cancer is to detect the disease at the earliest curable stage and thus to reduce breast cancer-specific mortality. To this end, the nationwide population-based mammography screening program (MSP) was set up in Germany in 2005 in addition to an interdisciplinary prevention project for high-risk groups.

OBJECTIVE

Overview of the current state of the MSP, the upcoming age expansion, and potential further developments.

MATERIAL AND METHODS

Narrative review article with topic-guided literature and data search.

RESULTS

Approximately 50% of the 70,500 new cases of breast cancer that occur each year are related to the age group of the MSP. 10 years after introduction of the MSP, the incidence of advanced breast cancer stages and breast cancer-related mortality of the screening target group have steadily decreased by about one quarter, while no relevant trends were seen in the neighboring age groups at the population level.

CONCLUSION

The MSP has effectively contributed to a reduction of breast cancer mortality. With the expansion of the age groups to 45-75 years, more women have access to structured, quality assured screening. With the use of advanced stratifications and diagnostics as well as artificial intelligence, the MSP could be further optimized.

Population-wide evaluation of artificial intelligence and radiologist assessment of screening mammograms

OBJECTIVES

To validate an AI system for standalone breast cancer detection on an entire screening population in comparison to first-reading breast radiologists.

MATERIALS AND METHODS

All mammography screenings performed between August 4, 2014, and August 15, 2018, in the Region of Southern Denmark with follow-up within 24 months were eligible. Screenings were assessed as normal or abnormal by breast radiologists through double reading with arbitration. For an AI decision of normal or abnormal, two AI-score cut-off points were applied by matching at mean sensitivity (AIsens) and specificity (AIspec) of first readers. Accuracy measures were sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and recall rate (RR).

RESULTS

The sample included 249,402 screenings (149,495 women) and 2033 breast cancers (72.6% screen-detected cancers, 27.4% interval cancers). AIsens had lower specificity (97.5% vs 97.7%; p < 0.0001) and PPV (17.5% vs 18.7%; p = 0.01) and a higher RR (3.0% vs 2.8%; p < 0.0001) than first readers. AIspec was comparable to first readers in terms of all accuracy measures. Both AIsens and AIspec detected significantly fewer screen-detected cancers (1166 (AIsens), 1156 (AIspec) vs 1252; p < 0.0001) but found more interval cancers compared to first readers (126 (AIsens), 117 (AIspec) vs 39; p < 0.0001) with varying types of cancers detected across multiple subgroups.

CONCLUSION

Standalone AI can detect breast cancer at an accuracy level equivalent to the standard of first readers when the AI threshold point was matched at first reader specificity. However, AI and first readers detected a different composition of cancers.

CLINICAL RELEVANCE STATEMENT

Replacing first readers with AI with an appropriate cut-off score could be feasible. AI-detected cancers not detected by radiologists suggest a potential increase in the number of cancers detected if AI is implemented to support double reading within screening, although the clinicopathological characteristics of detected cancers would not change significantly.

KEY POINTS

• Standalone AI cancer detection was compared to first readers in a double-read mammography screening population. • Standalone AI matched at first reader specificity showed no statistically significant difference in overall accuracy but detected different cancers. • With an appropriate threshold, AI-integrated screening can increase the number of detected cancers with similar clinicopathological characteristics.

Women's attitudes and perspectives on the use of artificial intelligence in the assessment of screening mammograms

PURPOSE

To investigate attitudes and perspectives on the use of artificial intelligence (AI) in the assessment of screening mammograms among women invited to BreastScreen Norway.

METHOD

An anonymous survey was sent to all women invited to BreastScreen Norway during the study period, October 10, 2022, to December 25, 2022 (n = 84,543). Questions were answered on a 10-point Likert scale and as multiple-choice, addressing knowledge of AI, willingness to participate in AI studies, information needs, confidence in AI results and AI assisted reading strategies, and thoughts on concerns and benefits of AI in mammography screening. Analyses were performed using χ2 and logistic regression tests.

RESULTS

General knowledge of AI was reported as extensive by 11.0% of the 8,355 respondents. Respondents were willing to participate in studies using AI either for decision support (64.0%) or triaging (54.9%). Being informed about use of AI-assisted image assessment was considered important, and a reading strategy of AI in combination with one radiologist preferred. Having extensive knowledge of AI was associated with willingness to participate in AI studies (decision support; odds ratio [OR]: 5.1, 95% confidence interval [CI]: 4.1-6.4, and triaging; OR: 3.4, 95% CI: 2.8-4.0) and trust in AI's independent assessment (OR: 6.8, 95% CI: 5.7, 8.3).

CONCLUSIONS

Women invited to BreastScreen Norway had a positive attitude towards the use of AI in image assessment, given that human readers are still involved. Targeted information and increased public knowledge of AI could help achieve high participation in AI studies and successful implementation of AI in mammography screening.