A Call for Controlled Validation Data Sets: Promoting the Safe Introduction of Artificial Intelligence in Breast Imaging

Dentistry increasingly integrates artificial intelligence (AI) to help improve the current state of clinical dental practice. However, this revolutionary technological field raises various complex ethical challenges. The objective of this systematic scoping review is to document the current uses of AI in dentistry and the ethical concerns or challenges they imply. Three health care databases (MEDLINE [PubMed], SciVerse Scopus, and Cochrane Library) and 2 computer science databases (ArXiv, IEEE Xplore) were searched. After identifying 1,553 records, the documents were filtered, and a full-text screening was performed. In total, 178 studies were retained and analyzed by 8 researchers specialized in dentistry, AI, and ethics. The team used Covidence for data extraction and Dedoose for the identification of ethics-related information. PRISMA guidelines were followed. Among the included studies, 130 (73.0%) studies were published after 2016, and 93 (52.2%) were published in journals specialized in computer sciences. The technologies used were neural learning techniques for 75 (42.1%), traditional learning techniques for 76 (42.7%), or a combination of several technologies for 20 (11.2%). Overall, 7 countries contributed to 109 (61.2%) studies. A total of 53 different applications of AI in dentistry were identified, involving most dental specialties. The use of initial data sets for internal validation was reported in 152 (85.4%) studies. Forty-five ethical issues (related to the use AI in dentistry) were reported in 22 (12.4%) studies around 6 principles: prudence (10 times), equity (8), privacy (8), responsibility (6), democratic participation (4), and solidarity (4). The ratio of studies mentioning AI-related ethical issues has remained similar in the past years, showing that there is no increasing interest in the field of dentistry on this topic. This study confirms the growing presence of AI in dentistry and highlights a current lack of information on the ethical challenges surrounding its use. In addition, the scarcity of studies sharing their code could prevent future replications. The authors formulate recommendations to contribute to a more responsible use of AI technologies in dentistry.

Download Full-text

The International Radiomics Platform – An Initiative of the German and Austrian Radiological Societies

RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren ◽

10.1055/a-1244-2775 ◽

2020 ◽

Author(s):

Daniel Overhoff ◽

Peter Kohlmann ◽

Alex Frydrychowicz ◽

Sergios Gatidis ◽

Christian Loewe ◽

...

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Image Data ◽

Quality Parameters ◽

Image Features ◽

Performance Criteria ◽

Data Sets ◽

Proof Of Concept ◽

Concept Study ◽

Artificial Intelligence Methods

Purpose The DRG-ÖRG IRP (Deutsche Röntgengesellschaft-Österreichische Röntgengesellschaft international radiomics platform) represents a web-/cloud-based radiomics platform based on a public-private partnership. It offers the possibility of data sharing, annotation, validation and certification in the field of artificial intelligence, radiomics analysis, and integrated diagnostics. In a first proof-of-concept study, automated myocardial segmentation and automated myocardial late gadolinum enhancement (LGE) detection using radiomic image features will be evaluated for myocarditis data sets. Materials and Methods The DRG-ÖRP IRP can be used to create quality-assured, structured image data in combination with clinical data and subsequent integrated data analysis and is characterized by the following performance criteria: Possibility of using multicentric networked data, automatically calculated quality parameters, processing of annotation tasks, contour recognition using conventional and artificial intelligence methods and the possibility of targeted integration of algorithms. In a first study, a neural network pre-trained using cardiac CINE data sets was evaluated for segmentation of PSIR data sets. In a second step, radiomic features were applied for segmental detection of LGE of the same data sets, which were provided multicenter via the IRP. Results First results show the advantages (data transparency, reliability, broad involvement of all members, continuous evolution as well as validation and certification) of this platform-based approach. In the proof-of-concept study, the neural network demonstrated a Dice coefficient of 0.813 compared to the expert's segmentation of the myocardium. In the segment-based myocardial LGE detection, the AUC was 0.73 and 0.79 after exclusion of segments with uncertain annotation.The evaluation and provision of the data takes place at the IRP, taking into account the FAT (fairness, accountability, transparency) and FAIR (findable, accessible, interoperable, reusable) criteria. Conclusion It could be shown that the DRG-ÖRP IRP can be used as a crystallization point for the generation of further individual and joint projects. The execution of quantitative analyses with artificial intelligence methods is greatly facilitated by the platform approach of the DRG-ÖRP IRP, since pre-trained neural networks can be integrated and scientific groups can be networked.In a first proof-of-concept study on automated segmentation of the myocardium and automated myocardial LGE detection, these advantages were successfully applied.Our study shows that with the DRG-ÖRP IRP, strategic goals can be implemented in an interdisciplinary way, that concrete proof-of-concept examples can be demonstrated, and that a large number of individual and joint projects can be realized in a participatory way involving all groups. Key Points: Citation Format

Download Full-text

Detection and Diagnosis of Breast Cancer Using Artificial Intelligence Based Assessment of Maximum Intensity Projection Dynamic Contrast-Enhanced Magnetic Resonance Images

Diagnostics ◽

10.3390/diagnostics10050330 ◽

2020 ◽

Vol 10 (5) ◽

pp. 330

Author(s):

Mio Adachi ◽

Tomoyuki Fujioka ◽

Mio Mori ◽

Kazunori Kubota ◽

Yuka Kikuchi ◽

...

Keyword(s):

Artificial Intelligence ◽

Magnetic Resonance ◽

Diagnostic Performance ◽

Maximum Intensity Projection ◽

Breast Mri ◽

Magnetic Resonance Images ◽

Maximum Intensity ◽

Validation Data ◽

Dynamic Contrast Enhanced ◽

Contrast Enhanced

We aimed to evaluate an artificial intelligence (AI) system that can detect and diagnose lesions of maximum intensity projection (MIP) in dynamic contrast-enhanced (DCE) breast magnetic resonance imaging (MRI). We retrospectively gathered MIPs of DCE breast MRI for training and validation data from 30 and 7 normal individuals, 49 and 20 benign cases, and 135 and 45 malignant cases, respectively. Breast lesions were indicated with a bounding box and labeled as benign or malignant by a radiologist, while the AI system was trained to detect and calculate possibilities of malignancy using RetinaNet. The AI system was analyzed using test sets of 13 normal, 20 benign, and 52 malignant cases. Four human readers also scored these test data with and without the assistance of the AI system for the possibility of a malignancy in each breast. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were 0.926, 0.828, and 0.925 for the AI system; 0.847, 0.841, and 0.884 for human readers without AI; and 0.889, 0.823, and 0.899 for human readers with AI using a cutoff value of 2%, respectively. The AI system showed better diagnostic performance compared to the human readers (p = 0.002), and because of the increased performance of human readers with the assistance of the AI system, the AUC of human readers was significantly higher with than without the AI system (p = 0.039). Our AI system showed a high performance ability in detecting and diagnosing lesions in MIPs of DCE breast MRI and increased the diagnostic performance of human readers.

Download Full-text

Application of ultrasound artificial intelligence in the differential diagnosis between benign and malignant breast lesions of BI-RADS 4A

BMC Cancer ◽

10.1186/s12885-020-07413-z ◽

2020 ◽

Vol 20 (1) ◽

Author(s):

Sihua Niu ◽

Jianhua Huang ◽

Jia Li ◽

Xueling Liu ◽

Dan Wang ◽

...

Keyword(s):

Artificial Intelligence ◽

Differential Diagnosis ◽

Breast Imaging ◽

Texture Features ◽

Matrix Analysis ◽

Width Ratio ◽

Malignant Group ◽

Malignant Lesions ◽

Occurrence Matrix ◽

Benign Group

Abstract Background The classification of Breast Imaging Reporting and Data System 4A (BI-RADS 4A) lesions is mostly based on the personal experience of doctors and lacks specific and clear classification standards. The development of artificial intelligence (AI) provides a new method for BI-RADS categorisation. We analysed the ultrasonic morphological and texture characteristics of BI-RADS 4A benign and malignant lesions using AI, and these ultrasonic characteristics of BI-RADS 4A benign and malignant lesions were compared to examine the value of AI in the differential diagnosis of BI-RADS 4A benign and malignant lesions. Methods A total of 206 lesions of BI-RADS 4A examined using ultrasonography were analysed retrospectively, including 174 benign lesions and 32 malignant lesions. All of the lesions were contoured manually, and the ultrasonic morphological and texture features of the lesions, such as circularity, height-to-width ratio, margin spicules, margin coarseness, margin indistinctness, margin lobulation, energy, entropy, grey mean, internal calcification and angle between the long axis of the lesion and skin, were calculated using grey level gradient co-occurrence matrix analysis. Differences between benign and malignant lesions of BI-RADS 4A were analysed. Results Significant differences in margin lobulation, entropy, internal calcification and ALS were noted between the benign group and malignant group (P = 0.013, 0.045, 0.045, and 0.002, respectively). The malignant group had more margin lobulations and lower entropy compared with the benign group, and the benign group had more internal calcifications and a greater angle between the long axis of the lesion and skin compared with the malignant group. No significant differences in circularity, height-to-width ratio, margin spicules, margin coarseness, margin indistinctness, energy, and grey mean were noted between benign and malignant lesions. Conclusions Compared with the naked eye, AI can reveal more subtle differences between benign and malignant BI-RADS 4A lesions. These results remind us carefully observation of the margin and the internal echo is of great significance. With the help of morphological and texture information provided by AI, doctors can make a more accurate judgment on such atypical benign and malignant lesions.

Download Full-text

Non-Overlapping and Non–Cell-Type–Specific Gene Expression Signatures Predict Lung Cancer Survival

Journal of Clinical Oncology ◽

10.1200/jco.2007.13.1516 ◽

2008 ◽

Vol 26 (6) ◽

pp. 877-883 ◽

Cited By ~ 74

Author(s):

Zhifu Sun ◽

Dennis A. Wigle ◽

Ping Yang

Keyword(s):

Gene Expression ◽

Squamous Cell Carcinoma ◽

Cell Carcinoma ◽

Squamous Cell ◽

Gene Signature ◽

Data Sets ◽

Cell Type ◽

Validation Data ◽

Adjusted Risk ◽

Gene Expression Signatures

Purpose Gene expression profiling for outcome prediction of non–small-cell lung cancer (NSCLC) remains clouded by heterogeneous and unvalidated results. This study applied multivariate approaches to identify and evaluate value-added gene expression signatures in two types of NSCLC. Materials and Methods Two NSCLC oligonucleotide microarray data sets of adenocarcinoma and squamous cell carcinoma were used as training sets to select prognostic genes independent of conventional predictors. The top 50 genes from each set were used to predict the outcomes of two independent validation data sets of 84 and 91 NSCLC cases. Results Adenocarcinomas with the 50-gene signature from adenocarcinoma in both validation data sets had a 2.4-fold (95% CI, 1.3 to 4.4 and 1.0 to 5.8) increased mortality after adjustment for conventional predictors. Squamous cell carcinoma with this high-risk signature had an adjusted risk of 1.1 (95% CI, 0.4 to 3.2) in one data set and 2.5 (95% CI, 1.1 to 5.8) in another consisting of stage I tumors. Adenocarcinoma with the 50-gene signature from squamous cell carcinoma had an elevated risk of 3.5 (95% CI, 1.4 to 9.0) after adjustment for conventional predictors. Squamous cell carcinoma with this high risk signature had an adjusted risk of 1.8 (95% CI, 0.7 to 4.6). Despite the little overlap in individual genes, the two gene signatures had significant functional connectedness in molecular pathways. Conclusion Two non-overlapping but functionally related gene expression signatures provide consistently improved survival prediction for NSCLC regardless of histologic cell type. Multiple sets of genes may exist for NSCLC with predictive value, but ones with independent predictive value beyond clinical predictors will be required for clinical translation.

Download Full-text

GAINESIS: Generative Artificial Intelligence NEtlists SynthesIS

Electronics ◽

10.3390/electronics11020245 ◽

2022 ◽

Vol 11 (2) ◽

pp. 245

Author(s):

Konstantinos G. Liakos ◽

Georgios K. Georgakilas ◽

Fotis C. Plessas ◽

Paris Kitsos

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Power Analysis ◽

Public Libraries ◽

Data Sets ◽

Hardware Trojan ◽

Generative Adversarial Network ◽

Data Set ◽

Encrypted Data ◽

Adversarial Network

A significant problem in the field of hardware security consists of hardware trojan (HT) viruses. The insertion of HTs into a circuit can be applied for each phase of the circuit chain of production. HTs degrade the infected circuit, destroy it or leak encrypted data. Nowadays, efforts are being made to address HTs through machine learning (ML) techniques, mainly for the gate-level netlist (GLN) phase, but there are some restrictions. Specifically, the number and variety of normal and infected circuits that exist through the free public libraries, such as Trust-HUB, are based on the few samples of benchmarks that have been created from circuits large in size. Thus, it is difficult, based on these data, to develop robust ML-based models against HTs. In this paper, we propose a new deep learning (DL) tool named Generative Artificial Intelligence Netlists SynthesIS (GAINESIS). GAINESIS is based on the Wasserstein Conditional Generative Adversarial Network (WCGAN) algorithm and area–power analysis features from the GLN phase and synthesizes new normal and infected circuit samples for this phase. Based on our GAINESIS tool, we synthesized new data sets, different in size, and developed and compared seven ML classifiers. The results demonstrate that our new generated data sets significantly enhance the performance of ML classifiers compared with the initial data set of Trust-HUB.

Download Full-text

Artificial Intelligence Is a Promising Prospect for the Detection of Prostate Cancer Extracapsular Extension With Mp-mri: A Two-center Comparative Study

10.21203/rs.3.rs-298296/v1 ◽

2021 ◽

Author(s):

Ying Hou ◽

Yi-Hong Zhang ◽

Jie Bao ◽

Mei-Ling Bao ◽

Guang Yang ◽

...

Keyword(s):

Prostate Cancer ◽

Artificial Intelligence ◽

Paired Comparison ◽

Characteristic Curve ◽

Multiparametric Mri ◽

Training Data ◽

Urinary Continence ◽

Data Sets ◽

Extracapsular Extension ◽

Promising Alternative

Abstract Purpose: A balance between preserving urinary continence and achievement of negative margins is of clinical relevance while implementary difficulty. Preoperatively accurate detection of prostate cancer (PCa) extracapsular extension (ECE) is thus crucial for determining appropriate treatment options. We aimed to develop and clinically validate an artificial intelligence (AI)-assisted tool for the detection of ECE in patients with PCa using multiparametric MRI. Methods: 849 patients with localized PCa underwent multiparametric MRI before radical prostatectomy were retrospectively included from two medical centers. The AI tool was built on a ResNeXt network embedded with a spatial attention map of experts’ prior knowledges (PAGNet) from 596 training data sets. The tool was validated in 150 internal and 103 external data sets, respectively; and its clinical applicability was compared with expert-based interpretation and AI-expert interaction.Results: An index PAGNet model using a single-slice image yielded the highest areas under the receiver operating characteristic curve (AUC) of 0.857 (95% confidence interval [CI], 0.827-0.884), 0.807 (95% CI, 0.735-0.867) and 0.728 (95% CI, 0.631-0.811) in the training, internal test and external test cohorts, compared to the conventional ResNeXt networks. For experts, the inter-reader agreement was observed in only 437/849 (51.5%) patients with a Kappa value 0.343. And the performance of two experts (AUC, 0.632 to 0.741 vs 0.715 to 0.857) was lower (paired comparison, all p values < 0.05) than that of AI assessment. When expert’ interpretations were adjusted by the AI assessments, the performance of both two experts was improved.Conclusion: Our AI tool, showing improved accuracy, offers a promising alternative to human experts for imaging staging of PCa ECE using multiparametric MRI.

Download Full-text

The role of artificial intelligence in cancer diagnostics - a review

Journal of Education, Health and Sport ◽

10.12775/jehs.2021.11.09.016 ◽

2021 ◽

Vol 11 (9) ◽

pp. 113-122

Author(s):

Paweł Stanicki ◽

Katarzyna Nowakowska ◽

Michał Piwoński ◽

Klaudia Żak ◽

Sylwiusz Niedobylski ◽

...

Keyword(s):

Artificial Intelligence ◽

Standardized Test ◽

Magnetic Resonance Images ◽

Cancer Diagnostics ◽

Data Sets ◽

Sensitive Information ◽

Biopsy Material ◽

Computer Data ◽

Tumor Diagnostics ◽

Abnormal Cells

Introduction and purposeArtificial intelligence (AI) is more advanced than ever and finds more and more new applications. Attempts are being made to use computer data analysis in medicine. The aim of this study is to summarize the knowledge on the use of AI in the diagnosis of breast, prostate, skin and colorectal cancer with particular emphasis on the applications and effectiveness of AI in making diagnoses. A brief description of the state of knowledgeThe most frequently used form of artificial intelligence in diagnostics are algorithms that analyze databases and recognize patterns. They can capture the features of samples characteristic of tumors, such as abnormal cells in the biopsy material or the alarming size and color of the skin lesion. Additionally, AI is capable of analyzing magnetic resonance images, radiographs, and other standardized test results. In most cases, AI is more effective than clinicians, sometimes as effective as they are, and almost never less effective. As a rule, the most accurate and adequate diagnosis can be obtained by joining the forces of AI and medical specialists. Working with learning algorithms requires the use of very extensive data sets. Every effort should be made to protect sensitive information from patients' medical history. ConclusionsThe results of research on the effectiveness of AI in cancer diagnostics are very promising. Further research and development of information technology systems may positively affect the quality and effectiveness of tumor diagnostics.

Download Full-text

Human Gaze Assisted Artificial Intelligence: A Review

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2020/689 ◽

2020 ◽

Author(s):

Ruohan Zhang ◽

Akanksha Saran ◽

Bo Liu ◽

Yifeng Zhu ◽

Sihang Guo ◽

...

Keyword(s):

Artificial Intelligence ◽

Language Processing ◽

Cognitive State ◽

Data Sets ◽

Common Goal ◽

Research Areas ◽

Future Challenges ◽

Potential Applications ◽

High Level ◽

And Robotics

Human gaze reveals a wealth of information about internal cognitive state. Thus, gaze-related research has significantly increased in computer vision, natural language processing, decision learning, and robotics in recent years. We provide a high-level overview of the research efforts in these fields, including collecting human gaze data sets, modeling gaze behaviors, and utilizing gaze information in various applications, with the goal of enhancing communication between these research areas. We discuss future challenges and potential applications that work towards a common goal of human-centered artificial intelligence.

Download Full-text

Factors Influencing Trainees’ Interest in Breast Imaging

Canadian Association of Radiologists Journal ◽

10.1177/08465371211049553 ◽

2021 ◽

pp. 084653712110495

Author(s):

Tong Wu ◽

Wyanne Law ◽

Nayaar Islam ◽

Charlotte J. Yong-Hing ◽

Supriya Kulkarni ◽

...

Keyword(s):

Artificial Intelligence ◽

Medical Students ◽

Breast Imaging ◽

Current Level ◽

Common Reason ◽

Training Level ◽

Chi Square ◽

Factors Influencing ◽

Radiology Residents ◽

The Impact

Purpose: To gauge the level of interest in breast imaging (BI) and determine factors impacting trainees’ decision to pursue this subspecialty. Methods: Canadian radiology residents and medical students were surveyed from November 2020 to February 2021. Training level, actual vs preferred timing of breast rotations, fellowship choices, perceptions of BI, and how artificial intelligence (AI) will impact BI were collected. Chi-square, Fisher’s exact tests and univariate logistic regression were performed to determine the impact of trainees’ perceptions on interest in pursuing BI/women’s imaging (WI) fellowships. Results: 157 responses from 80 radiology residents and 77 medical students were collected. The top 3 fellowship subspecialties desired by residents were BI/WI (36%), abdominal imaging (35%), and interventional radiology (25%). Twenty-five percent of the medical students were unsure due to lack of exposure. The most common reason that trainees found BI unappealing was repetitiveness (20%), which was associated with lack of interest in BI/WI fellowships (OR = 3.9, 95% CI: 1.6-9.5, P = .002). The most common reason residents found BI appealing was procedures (59%), which was associated with interest in BI/WI fellowships (OR, 3.2, 95% CI, 1.2-8.6, P = .02). Forty percent of residents reported an earlier start of their first breast rotation (PGY1-2) would affect their fellowship choice. Conclusion: This study assessed the current level of Canadian trainees’ interest in BI and identified factors that influenced their decisions to pursue BI. Solutions for increased interest include earlier exposure to breast radiology and addressing inadequacies in residency training.

Download Full-text