Deep Learning for Automated Delineation of Pediatric Cerebral Arteries on Pre-operative Brain Magnetic Resonance Imaging

A 2.5D Self-Training Strategy for Carotid Artery Segmentation in T1-Weighted Brain Magnetic Resonance Images

Precise annotations for large medical image datasets can be time-consuming. Additionally, when dealing with volumetric regions of interest, it is typical to apply segmentation techniques on 2D slices, compromising important information for accurately segmenting 3D structures. This study presents a deep learning pipeline that simultaneously tackles both challenges. Firstly, to streamline the annotation process, we employ a semi-automatic segmentation approach using bounding boxes as masks, which is less time-consuming than pixel-level delineation. Subsequently, recursive self-training is utilized to enhance annotation quality. Finally, a 2.5D segmentation technique is adopted, wherein a slice of a volumetric image is segmented using a pseudo-RGB image. The pipeline was applied to segment the carotid artery tree in T1-weighted brain magnetic resonance images. Utilizing 42 volumetric non-contrast T1-weighted brain scans from four datasets, we delineated bounding boxes around the carotid arteries in the axial slices. Pseudo-RGB images were generated from these slices, and recursive segmentation was conducted using a Res-Unet-based neural network architecture. The model's performance was tested on a separate dataset, with ground truth annotations provided by a radiologist. After recursive training, we achieved an Intersection over Union (IoU) score of (0.68 ± 0.08) on the unseen dataset, demonstrating commendable qualitative results.

Cataract-1K Dataset for Deep-Learning-Assisted Analysis of Cataract Surgery Videos

In recent years, the landscape of computer-assisted interventions and post-operative surgical video analysis has been dramatically reshaped by deep-learning techniques, resulting in significant advancements in surgeons' skills, operation room management, and overall surgical outcomes. However, the progression of deep-learning-powered surgical technologies is profoundly reliant on large-scale datasets and annotations. In particular, surgical scene understanding and phase recognition stand as pivotal pillars within the realm of computer-assisted surgery and post-operative assessment of cataract surgery videos. In this context, we present the largest cataract surgery video dataset that addresses diverse requisites for constructing computerized surgical workflow analysis and detecting post-operative irregularities in cataract surgery. We validate the quality of annotations by benchmarking the performance of several state-of-the-art neural network architectures for phase recognition and surgical scene segmentation. Besides, we initiate the research on domain adaptation for instrument segmentation in cataract surgery by evaluating cross-domain instrument segmentation performance in cataract surgery videos. The dataset and annotations are publicly available in Synapse.

All answers are in the images: A review of deep learning for cerebrovascular segmentation

Cerebrovascular imaging is a common examination. Its accurate cerebrovascular segmentation become an important auxiliary method for the diagnosis and treatment of cerebrovascular diseases, which has received extensive attention from researchers. Deep learning is a heuristic method that encourages researchers to derive answers from the images by driving datasets. With the continuous development of datasets and deep learning theory, it has achieved important success for cerebrovascular segmentation. Detailed survey is an important reference for researchers. To comprehensively analyze the newest cerebrovascular segmentation, we have organized and discussed researches centered on deep learning. This survey comprehensively reviews deep learning for cerebrovascular segmentation since 2015, it mainly includes sliding window based models, U-Net based models, other CNNs based models, small-sample based models, semi-supervised or unsupervised models, fusion based models, Transformer based models, and graphics based models. We organize the structures, improvement, and important parameters of these models, as well as analyze development trends and quantitative assessment. Finally, we have discussed the challenges and opportunities of possible research directions, hoping that our survey can provide researchers with convenient reference.

Diagnostic value of artificial intelligence automatic detection systems for breast BI-RADS 4 nodules

BACKGROUND

The incidence rate of breast cancer has exceeded that of lung cancer, and it has become the most malignant type of cancer in the world. BI-RADS 4 breast nodules have a wide range of malignant risks and are associated with challenging clinical decision-making.

AIM

To explore the diagnostic value of artificial intelligence (AI) automatic detection systems for BI-RADS 4 breast nodules and to assess whether conventional ultrasound BI-RADS classification with AI automatic detection systems can reduce the probability of BI-RADS 4 biopsy.

METHODS

A total of 107 BI-RADS breast nodules confirmed by pathology were selected between June 2019 and July 2020 at Hwa Mei Hospital, University of Chinese Academy of Sciences. These nodules were classified by ultrasound doctors and the AI-SONIC breast system. The diagnostic values of conventional ultrasound, the AI automatic detection system, conventional ultrasound combined with the AI automatic detection system and adjusted BI-RADS classification diagnosis were statistically analyzed.

RESULTS

Among the 107 breast nodules, 61 were benign (57.01%), and 46 were malignant (42.99%). The pathology results were considered the gold standard; furthermore, the sensitivity, specificity, accuracy, Youden index, and positive and negative predictive values were 84.78%, 67.21%, 74.77%, 0.5199, 66.10% and 85.42% for conventional ultrasound BI-RADS classification diagnosis, 86.96%, 75.41%, 80.37%, 0.6237, 72.73%, and 88.46% for automatic AI detection, 80.43%, 90.16%, 85.98%, 0.7059, 86.05%, and 85.94% for conventional ultrasound BI-RADS classification with automatic AI detection and 93.48%, 67.21%, 78.50%, 0.6069, 68.25%, and 93.18% for adjusted BI-RADS classification, respectively. The biopsy rate, cancer detection rate and malignancy risk were 100%, 42.99% and 0% and 67.29%, 61.11%, and 1.87% before and after BI-RADS adjustment, respectively.

CONCLUSION

Automatic AI detection has high accuracy in determining benign and malignant BI-RADS 4 breast nodules. Conventional ultrasound BI-RADS classification combined with AI automatic detection can reduce the biopsy rate of BI-RADS 4 breast nodules.

Relationship between Circle of Willis Variations and Cerebral or Cervical Arteries Stenosis Investigated by Computer Tomography Angiography and Multitask Convolutional Neural Network

Circle of Willis (CoW) is the most critical collateral pathway that supports the redistribution of blood supply in the brain. The variation of CoW is closely correlated with cerebral hemodynamic and cerebral vessel-related diseases. But what is responsible for CoW variation remains unclear. Moreover, the visual evaluation for CoW variation is highly time-consuming. In the present study, based on the computer tomography angiography (CTA) dataset from 255 patients, the correlation between the CoW variations with age, gender, and cerebral or cervical artery stenosis was investigated. A multitask convolutional neural network (CNN) was used to segment cerebral arteries automatically. The results showed the prevalence of variation of the anterior communicating artery (Aco) was higher in the normal senior group than in the normal young group and in females than in males. The changes in the prevalence of variations of individual segments were not demonstrated in the population with stenosis of the afferent and efferent arteries, so the critical factors for variation are related to genetic or physiological factors rather than pathological lesions. Using the multitask CNN model, complete cerebral and cervical arteries could be segmented and reconstructed in 120 seconds, and an average Dice coefficient of 78.2% was achieved. The segmentation accuracy for precommunicating part of anterior cerebral artery and posterior cerebral artery, the posterior communicating arteries, and Aco in CoW was 100%, 99.2%, 94%, and 69%, respectively. Artificial intelligence (AI) can be considered as an adjunct tool for detecting the CoW, particularly related to reducing workload and improving the accuracy of the visual evaluation. The study will serve as a basis for the following research to determine an individual's risk of stroke with the aid of AI.

Clinical Artificial Intelligence Applications in Radiology: Neuro

Radiologists have been at the forefront of the digitization process in medicine. Artificial intelligence (AI) is a promising area of innovation, particularly in medical imaging. The number of applications of AI in neuroradiology has also grown. This article illustrates some of these applications. This article reviews machine learning challenges related to neuroradiology. The first approval of reimbursement for an AI algorithm by the Centers for Medicare and Medicaid Services, covering a stroke software for early detection of large vessel occlusion, is also discussed.

Magnetic resonance angiographic study of variations in course of paraclival and parasellar internal carotid artery in relation to expanded endonasal endoscopic approaches

AIMS

To study the variations in the course of the paraclival and parasellar carotid arteries in normal subjects using magnetic resonance angiography as is relevant from an endoscopic endonasal perspective.

METHODS

Two hundred MR angiographies of normal subjects were analyzed in a prospective study. The intercarotid distances were measured at fixed points along the paraclival and parasellar segments of the internal carotid artery. The intercarotid spaces thus obtained were categorized into trapezoid, square and hourglass shapes. The angle between the posterior ascending vertical and horizontal bend of the parasellar ICA was also measured and analyzed.

RESULTS

The trapezoid shape of intercarotid space is the most common (52.5%), followed by the square (35%) and the hourglass (12.5%) shaped spaces. Angle of < 80° between the posterior ascending vertical and horizontal bend of the parasellar ICA was found in 39% of subjects, angle between 80° and 100° was found in 9% subjects, angle > 100° was found in 43% while asymmetric angles on the two sides was found in 9% of subjects.

CONCLUSION

A thorough understanding of the course of the ICA is important in planning the approach and preventing injury to the ICA.