Deep Learning Based on MR Imaging for Predicting Outcome of Uterine Fibroid Embolization

AI-Supported Autonomous Uterus Reconstructions: First Application in MRI Using 3D SPACE with Iterative Denoising

RATIONALE AND OBJECTIVES

T2-weighted imaging in at least two orthogonal planes is recommended for assessment of the uterus. To determine whether a convolutional neural network-based algorithm could be used for the re-constructions of uterus axes derived from a 3D SPACE with iterative denoising.

MATERIALS AND METHODS

50 patients aged 18-81 (mean: 42) years who underwent an MRI examination of the uterus participated voluntarily in this prospective study after informed consent. In addition to a standard MRI pelvis protocol, a 3D SPACE research application sequence was acquired in sagittal orientation. Reconstructions for both the cervix and the cavum in the short and long axes were performed by a research trainee (T), an experienced radiologist (E), and the prototype software (P). In the next step, the reconstructions were evaluated anonymously by two experienced readers according to 5-point-Likert-Scales. In addition, the length of the cervical canal, the length of the cavum and the distance between the tube angles were measured on all reconstructions. Interobserver agreement was assessed for all ratings.

RESULTS

For all axes, significant differences were found between the scores of the reconstructions by research T, E and P. P received higher scores and was preferred significantly more often with the exception of the comparison of the reconstruction Cervix short of E (Cervix short: P vs. T: p = 0.02; P vs. E: p = 0.26; Cervix long: P vs. T: p = 0.01; P vs. E: p < 0.01; Cavum short: P vs. T: p = 0.01; P vs. E: p = 0.02; Cavum long: P vs. T: p < 0.01; P vs. E: p < 0.01). Regarding the measured diameters, (length of cervical canal/cavum/distance between tube angles) significantly larger diameters were recorded for P compared to E and T (Cervix long (mm): T: 25.43; E: 25.65; P: 26.65; Cavum short (mm): T: 26.24; E: 25.04; P: 27.33; Cavum long (mm): T: 31.98; E: 32.91; P: 34.41; P vs. T: p < 0.01); P vs. E: p = 0.04). Moderate to substantial agreement was found between Reader 1 and Reader 2 (range: 0.39-0.67).

CONCLUSION

P was able to reconstruct the axes at least as well as or better than E and T. P could thereby lead to workflow facilitation and enable more efficient reporting of uterine MRI.

Update on Endovascular Therapy for Fibroids and Adenomyosis

Uterine fibroids and adenomyosis are prevalent benign neoplasms that can lead to serious deleterious health effects including life-threatening anemia, prolonged menses, and pelvic pain; however, up to 40% of women remain undiagnosed. Traditional treatment options such as myomectomy or hysterectomy can effectively manage symptoms but may entail longer hospital stays and hinder future fertility. Endovascular treatment, such as uterine artery embolization (UAE), is a minimally invasive procedure that has emerged as a well-validated alternative to surgical options while preserving the uterus and offering shorter hospital stays. Careful patient selection and appropriate techniques are crucial to achieving optimal outcomes. There have been advancements in recent times that encompass pre- and postprocedural care aimed at enhancing results and alleviating discomfort prior to, during, and after UAE. Furthermore, success and reintervention rates may also depend on the size and location of the fibroids. This article reviews the current state of endovascular treatments of uterine fibroids and adenomyosis.

Automated Uterine Fibroids Detection in Ultrasound Images Using Deep Convolutional Neural Networks

Fibroids of the uterus are a common benign tumor affecting women of childbearing age. Uterine fibroids (UF) can be effectively treated with earlier identification and diagnosis. Its automated diagnosis from medical images is an area where deep learning (DL)-based algorithms have demonstrated promising results. In this research, we evaluated state-of-the-art DL architectures VGG16, ResNet50, InceptionV3, and our proposed innovative dual-path deep convolutional neural network (DPCNN) architecture for UF detection tasks. Using preprocessing methods including scaling, normalization, and data augmentation, an ultrasound image dataset from Kaggle is prepared for use. After the images are used to train and validate the DL models, the model performance is evaluated using different measures. When compared to existing DL models, our suggested DPCNN architecture achieved the highest accuracy of 99.8 percent. Findings show that pre-trained deep-learning model performance for UF diagnosis from medical images may significantly improve with the application of fine-tuning strategies. In particular, the InceptionV3 model achieved 90% accuracy, with the ResNet50 model achieving 89% accuracy. It should be noted that the VGG16 model was found to have a lower accuracy level of 85%. Our findings show that DL-based methods can be effectively utilized to facilitate automated UF detection from medical images. Further research in this area holds great potential and could lead to the creation of cutting-edge computer-aided diagnosis systems. To further advance the state-of-the-art in medical imaging analysis, the DL community is invited to investigate these lines of research. Although our proposed innovative DPCNN architecture performed best, fine-tuned versions of pre-trained models like InceptionV3 and ResNet50 also delivered strong results. This work lays the foundation for future studies and has the potential to enhance the precision and suitability with which UF is detected.

Automated Detection of Endometrial Polyps from Hysteroscopic Videos Using Deep Learning

Endometrial polyps are common gynecological lesions. The standard treatment for this condition is hysteroscopic polypectomy. However, this procedure may be accompanied by misdetection of endometrial polyps. To improve the diagnostic accuracy and reduce the risk of misdetection, a deep learning model based on YOLOX is proposed to detect endometrial polyps in real time. Group normalization is employed to improve its performance with large hysteroscopic images. In addition, we propose a video adjacent-frame association algorithm to address the problem of unstable polyp detection. Our proposed model was trained on a dataset of 11,839 images from 323 cases provided by a hospital and was tested on two datasets of 431 cases from two hospitals. The results show that the lesion-based sensitivity of the model reached 100% and 92.0% for the two test sets, compared with 95.83% and 77.33%, respectively, for the original YOLOX model. This demonstrates that the improved model may be used effectively as a diagnostic tool during clinical hysteroscopic procedures to reduce the risk of missing endometrial polyps.

Automated detection of IVC filters on radiographs with deep convolutional neural networks

PURPOSE

To create an algorithm able to accurately detect IVC filters on radiographs without human assistance, capable of being used to screen radiographs to identify patients needing IVC filter retrieval.

METHODS

A primary dataset of 5225 images, 30% of which included IVC filters, was assembled and annotated. 85% of the data was used to train a Cascade R-CNN (Region Based Convolutional Neural Network) object detection network incorporating a pre-trained ResNet-50 backbone. The remaining 15% of the data, independently annotated by three radiologists, was used as a test set to assess performance. The algorithm was also assessed on an independently constructed 1424-image dataset, drawn from a different institution than the primary dataset.

RESULTS

On the primary test set, the algorithm achieved a sensitivity of 96.2% (95% CI 92.7-98.1%) and a specificity of 98.9% (95% CI 97.4-99.5%). Results were similar on the external test set: sensitivity 97.9% (95% CI 96.2-98.9%), specificity 99.6 (95% CI 98.9-99.9%).

CONCLUSION

Fully automated detection of IVC filters on radiographs with high sensitivity and excellent specificity required for an automated screening system can be achieved using object detection neural networks. Further work will develop a system for identifying patients for IVC filter retrieval based on this algorithm.

Systematic Review of Radiologist and Medical Student Attitudes on the Role and Impact of AI in Radiology

RATIONALE AND OBJECTIVES

The introduction of AI in radiology has prompted both excitement and hesitation within the field. We performed a systematic review of original studies evaluating the attitudes of radiologists, radiology trainees, and medical students towards AI in radiology.

MATERIALS AND METHODS

We searched PubMed for studies published as of August 24, 2021 for original studies evaluating attitudes of radiologists (attendings and trainees) and medical students towards AI in radiology. We summarized the baseline article characteristics and performed thematic analysis of the questions asked in each study.

RESULTS

Nineteen studies were included evaluating attitudes across different levels of training (medical students, radiology trainees, and radiology attendings) with representation from nearly every continent. Medical students and radiologists alike favored increased educational initiatives, and displayed interest in learning about and implementing AI solutions themselves, despite reporting of a current gap in formal AI training. There was general optimism about the role of AI in radiology, although radiologists and trainees had greater consensus than medical students.

CONCLUSION

Although there is interest in incorporating AI into medical education and optimism among radiologists towards AI, medical students are more divided in their views. We propose that outreach to and AI education for medical students may help improve their attitudes towards the potentially transformative technology of AI for radiology.

Artificial intelligence: A rapid case for advancement in the personalization of Gynaecology/Obstetric and Mental Health care

To evaluate and holistically treat the mental health sequelae and potential psychiatric comorbidities associated with obstetric and gynaecological conditions, it is important to optimize patient care, ensure efficient use of limited resources and improve health-economic models. Artificial intelligence applications could assist in achieving the above. The World Health Organization and global healthcare systems have already recognized the use of artificial intelligence technologies to address 'system gaps' and automate some of the more cumbersome tasks to optimize clinical services and reduce health inequalities. Currently, both mental health and obstetric and gynaecological services independently use artificial intelligence applications. Thus, suitable solutions are shared between mental health and obstetric and gynaecological clinical practices, independent of one another. Although, to address complexities with some patients who may have often interchanging sequelae with mental health and obstetric and gynaecological illnesses, 'holistically' developed artificial intelligence applications could be useful. Therefore, we present a rapid review to understand the currently available artificial intelligence applications and research into multi-morbid conditions, including clinical trial-based validations. Most artificial intelligence applications are intrinsically data-driven tools, and their validation in healthcare can be challenging as they require large-scale clinical trials. Furthermore, most artificial intelligence applications use rate-limiting mock data sets, which restrict their applicability to a clinical population. Some researchers may fail to recognize the randomness in the data generating processes in clinical care from a statistical perspective with a potentially minimal representation of a population, limiting their applicability within a real-world setting. However, novel, innovative trial designs could pave the way to generate better data sets that are generalizable to the entire global population. A collaboration between artificial intelligence and statistical models could be developed and deployed with algorithmic and domain interpretability to achieve this. In addition, acquiring big data sets is vital to ensure these artificial intelligence applications provide the highest accuracy within a real-world setting, especially when used as part of a clinical diagnosis or treatment.

Uterine Artery Embolization for Uterine Fibroids: A Closer Look at Misperceptions and Challenges

Uterine artery embolization (UAE) has been shown to be a safe and effective treatment for symptomatic uterine fibroids, with over 25 years of supporting data. Although UAE is a well-established treatment option, several misperceptions exist that may limit the number of patients who are considered candidates for UAE. There are also challenges that may affect the ability of interventional radiologists to effectively treat some patients and offer the best possible experience. This article will discuss these misperceptions and challenges, which represent opportunities for further growth and innovation that will allow interventional radiologists to better serve this patient population.

Deep learning-based classification of primary bone tumors on radiographs: A preliminary study

BACKGROUND

To develop a deep learning model to classify primary bone tumors from preoperative radiographs and compare performance with radiologists.

METHODS

A total of 1356 patients (2899 images) with histologically confirmed primary bone tumors and pre-operative radiographs were identified from five institutions' pathology databases. Manual cropping was performed by radiologists to label the lesions. Binary discriminatory capacity (benign versus not-benign and malignant versus not-malignant) and three-way classification (benign versus intermediate versus malignant) performance of our model were evaluated. The generalizability of our model was investigated on data from external test set. Final model performance was compared with interpretation from five radiologists of varying level of experience using the Permutations tests.

FINDINGS

For benign vs. not benign, model achieved area under curve (AUC) of 0•894 and 0•877 on cross-validation and external testing, respectively. For malignant vs. not malignant, model achieved AUC of 0•907 and 0•916 on cross-validation and external testing, respectively. For three-way classification, model achieved 72•1% accuracy vs. 74•6% and 72•1% for the two subspecialists on cross-validation (p = 0•03 and p = 0•52, respectively). On external testing, model achieved 73•4% accuracy vs. 69•3%, 73•4%, 73•1%, 67•9%, and 63•4% for the two subspecialists and three junior radiologists (p = 0•14, p = 0•89, p = 0•93, p = 0•02, p < 0•01 for radiologists 1-5, respectively).

INTERPRETATION

Deep learning can classify primary bone tumors using conventional radiographs in a multi-institutional dataset with similar accuracy compared to subspecialists, and better performance than junior radiologists.

FUNDING

The project described was supported by RSNA Research & Education Foundation, through grant number RSCH2004 to Harrison X. Bai.