Deep learning for detection of iso-dense, obscure masses in mammographically dense breasts.

OBJECTIVES: To analyze the performance of deep learning in isodense/obscure masses in dense breasts. To build and validate a deep learning (DL) model using core radiology principles and analyze its performance in isodense/obscure masses. To show performance on screening mammography as well as diagnostic mammography distribution. METHODS: This was a retrospective, single-institution, multi-centre study with external validation. For model building, we took a 3-pronged approach. First, we explicitly taught the network to learn features other than density differences: such as spiculations and architectural distortion. Second, we used the opposite breast to enable the detection of asymmetries. Third, we systematically enhanced each image by piece-wise-linear transformation. We tested the network on a diagnostic mammography dataset (2569 images with 243 cancers, January to June 2018) and a screening mammography dataset (2146 images with 59 cancers, patient recruitment from January to April 2021) from a different centre (external validation). RESULTS: When trained with our proposed technique (and compared with baseline network), sensitivity for malignancy increased from 82.7 to 84.7% at 0.2 False positives per image (FPI) in the diagnostic mammography dataset, 67.9 to 73.8% in the subset of patients with dense breasts, 74.6 to 85.3 in the subset of patients with isodense/obscure cancers and 84.9 to 88.7 in an external validation test set with a screening mammography distribution. We showed that our sensitivity exceeded currently reported values (0.90 at 0.2 FPI) on a public benchmark dataset (INBreast). CONCLUSION: Modelling traditional mammographic teaching into a DL framework can help improve cancer detection accuracy in dense breasts. CLINICAL RELEVANCE STATEMENT: Incorporating medical knowledge into neural network design can help us overcome some limitations associated with specific modalities. In this paper, we show how one such deep neural network can help improve performance on mammographically dense breasts. KEY POINTS: • Although state-of-the-art deep learning networks achieve good results in cancer detection in mammography in general, isodense, obscure masses and mammographically dense breasts posed a challenge to deep learning networks. • Collaborative network design and incorporation of traditional radiology teaching into the deep learning approach helped mitigate the problem. • The accuracy of deep learning networks may be translatable to different patient distributions. We showed the results of our network on screening as well as diagnostic mammography datasets.

A review of virtual reality simulators for neuroendoscopy.

Neurosurgery is a challenging surgical specialty that demands many technical and cognitive skills. The traditional surgical training approach of having a trainee coached in the operating room by the faculty is time-consuming, costly, and involves patient risk factors. Simulation-based training methods are suitable to impart the surgical skills outside the operating room. Virtual simulators allow high-fidelity repeatable environment for surgical training. Neuroendoscopy, a minimally invasive neurosurgical technique, demands additional skills for limited maneuverability and eye-hand coordination. This study provides a review of the existing virtual reality simulators for training neuroendoscopic skills. Based on the screening, the virtual training methods developed for neuroendoscopy surgical skills were classified into endoscopic third ventriculostomy and endonasal transsphenoidal surgery trainers. The study revealed that a variety of virtual reality simulators have been developed by various institutions. Although virtual reality simulators are effective for procedure-based skills training, the simulators need to include anatomical variations and variety of cases for improved fidelity. The review reveals that there should be multi-centric prospective and retrospective cohort studies to establish concurrent and predictive validation for their incorporation in the surgical educational curriculum.

Functional and Neuropsychological Outcome After Surgical Treatment of Moyamoya Disease.

BACKGROUND: Moyamoya disease (MMD) is a rare cerebrovascular disease characterized by progressive stenosis of the supraclinoid internal carotid artery. As a result of chronically decreased brain perfusion, eloquent areas of the brain become hypoperfused, leading to cognitive changes in patients. Repeated infarcts and bleeds produce clinically apparent neurologic deficits. OBJECTIVES: 1) To study the functional and neuropsychological outcome in MMD after revascularization surgery. 2) To find postrevascularization correlation between functional and neuropsychological improvement and radiologic improvement. METHODS: A single-center prospective and analytic study was carried out including 21 patients with MMD during the study period from March 2021 to December 2022. Patients were evaluated and compared before and after revascularization for functional, neuropsychological, and radiologic status. RESULTS: Postoperative functional outcome in terms of modified Rankin Scale score showed improvement in 33.33% of cases (P = 0.0769). An overall improving trend was observed in different neuropsychological domains in both adult and pediatric age groups. However, the trend of neuropsychological improvement was better in adults compared with pediatric patients. Radiologic outcome in the form of the Angiographic Outcome Score (AOS) significantly improved after revascularization (P = 0.0001). There was a trend toward improvement in magnetic resonance imaging (MRI) perfusion in the middle cerebral artery and anterior cerebral artery territories, 4.7% (P = 0.075) and 9.33% (P = 0.058) respectively, compared with preoperative MRI perfusion. CONCLUSIONS: After revascularization, significant improvement occurred in functional and neuropsychological status. This result was also shown radiologically as evidenced by improvement in MRI perfusion and cerebral angiography.

Basic principles of AI simplified for a Medical Practitioner: Pearls and Pitfalls in Evaluating AI algorithms.

With the rapid integration of artificial intelligence into medical practice, there has been an exponential increase in the number of scientific papers and industry players offering models designed for various tasks. Understanding these, however, is difficult for a radiologist in practice, given the core mathematical principles and complicated terminology involved. This review aims to elucidate the core mathematical concepts of both machine learning and deep learning models, explaining the various steps and common terminology in common layman language. Thus, by the end of this article, the reader should be able to understand the basics of how prediction models are built and trained, including challenges faced and how to avoid them. The reader would also be equipped to adequately evaluate various models, and take a decision on whether a model is likely to perform adequately in the real-world setting.