AI in Pathology: What could possibly go wrong?

<h3>Introduction</h3> CT angiography (CTA), the modality of choice for detection of intracranial aneurysms (IA), is widely available at all care levels. Implementing deep learning algorithms (DLA) in the radiologists’ workflow could result in higher detection rates, particularly in smaller centers. We present results of multicenter pre-clinical experience with a new IA detection DLA. <h3>Methods</h3> A DLA was developed at Site 1 to predict the existence and locations of IAs &gt;2 mm in 3D head CTA volumes. It localizes IAs using an improved 3D UNet to regress the bounding boxes of suspicious locations. IA presence is confirmed by a multi-resolution 3D DenseNet at each suspicious location. The model was trained on 436 studies and tested on 696 studies from site 1. To validate robustness against protocol variability, it was retrospectively tested on 337 volumes (149 positives, 188 negatives) from 4 additional sites with various types of scanners. A neuroradiologist/trained fellow from each site annotated bounding boxes around the IAs with 3DSlicer. The model’s performance was assessed by comparing its predicted aneurysm locations to the annotated boxes. <h3>Results</h3> The model achieved a lesion-level sensitivity of 0.72 (95% CI: 0.66 - 0.75) with 1.4 false positives per volume (FPPV, 95% CI: 1.22 - 1.57). Sensitivity ranged 0.84 (1.72 FPPV) - 0.67 (1.40 FPPV) amongst 5 sites. Performance variation was secondary to testing on images from scanners the model had not been trained on (unseen). Removing unseen scanners, the model achieved sensitivity of 0.77 (95% CI: 0.68 - 0.84) with 1.51 FPPV (95% CI: 1.24 - 1.82). Patient-level area under curves (AUCs) on the external sites were comparable to that of site 1 dataset, which was 0.88 (95% CI: 0.84 - 0.92). The model performed better in the detection of internal carotid and anterior communicating artery IAs &gt; 3 mm. <h3>Conclusions</h3> This DLA for IA detection showed robust performance in detecting IAs &gt; 3 mm. DLAs may reliably help detection of IAs on CTA, particularly in the community practices less familiar with intracranial vascular imaging. Different scanners can lead to performance variability. This can be avoided by training with data from different scanners. <h3>Disclosures</h3> <b>D. Wu:</b> 1; C; National Institute of Health. <b>E. Orru’:</b> None. <b>S. Ferraciolli:</b> None. <b>A. Ashok:</b> 1; C; NIHR Academic Clinical Fellowship. <b>A. Sorby-Adams:</b> None. <b>M. Guindy:</b> None. <b>D. Montes:</b> None. <b>A. Medina:</b> None. <b>G. Bianco:</b> None. <b>J. Kaggie:</b> 1; C; NIHR Cambridge BRC. <b>D. Rabina:</b> None. <b>O. Ashush:</b> None. <b>X. Han:</b> None. <b>Y. Baror:</b> None. <b>M. Patel:</b> 4; C; Rhino HealthTech Inc. <b>I. Dayan:</b> 4; C; Rhino HealthTech Inc.. <b>J. Romero:</b> None. <b>R. González:</b> 1; C; National Institute of Health. 2; C; MR Access, Inc.. 4; C; MR Access, Inc.. <b>C. Wald:</b> None. <b>F. Kitamura:</b> 2; C; MD.ai, GE Healthcare. <b>P. Kuriki:</b> None. <b>T. Matys:</b> 1; C; NIHR Cambridge BRC. 2; C; NHS. <b>Q. Li:</b> 1; C; National Institute of Health. 

/pdf/e-107-multi-center-study-of-a-deep-learning-model-for-eqbin8mv.pdf

E-107 Multi-center study of a deep learning model for intracranial aneurysm detection in computed tomography angiography

Solar energy production has significantly increased in recent years in the European Union (EU), accounting for 12% of the total in 2022. The growth in solar energy production can be attributed to the increasing adoption of solar photovoltaic (PV) panels, which have become cost-effective and efficient means of energy production, supported by government policies and incentives. The maturity of solar technologies has also led to a decrease in the cost of solar energy, making it more competitive with other energy sources. As a result, there is a growing need for efficient methods for detecting and mapping the locations of PV panels. Automated detection can in fact save time and resources compared to manual inspection. Moreover, the resulting information can also be used by governments, environmental agencies and other companies to track the adoption of renewable sources or to optimize energy distribution across the grid. However, building effective models to support the automated detection and mapping of solar photovoltaic (PV) panels presents several challenges, including the availability of high-resolution aerial imagery and high-quality, manually-verified labels and annotations. In this study, we address these challenges by first constructing a dataset of PV panels using very-high-resolution (VHR) aerial imagery, specifically focusing on the region of Piedmont in Italy. The dataset comprises 105 large-scale images, providing more than 9,000 accurate and detailed manual annotations, including additional attributes such as the PV panel category. We first conduct a comprehensive evaluation benchmark on the newly constructed dataset, adopting various well-established deep-learning techniques. Specifically, we experiment with instance and semantic segmentation approaches, such as Rotated Faster RCNN and Unet, comparing strengths and weaknesses on the task at hand. Second, we apply ad-hoc modifications to address the specific issues of this task, such as the wide range of scales of the installations and the sparsity of the annotations, considerably improving upon the baseline results. Last, we introduce a robust and efficient post-processing polygonization algorithm that is tailored to PV panels. This algorithm converts the rough raster predictions into cleaner and more precise polygons for practical use. Our benchmark evaluation shows that both semantic and instance segmentation techniques can be effective for detecting and mapping PV panels. Instance segmentation techniques are well-suited for estimating the localization of panels, while semantic solutions excel at surface delineation. We also demonstrate the effectiveness of our ad-hoc solutions and post-processing algorithm, which can provide an improvement up to +10% on the final scores, and can accurately convert coarse raster predictions into usable polygons.

G. Bianco

Papers

E-107 Multi-center study of a deep learning model for intracranial aneurysm detection in computed tomography angiography

A Comparative Evaluation of Deep Learning Techniques for Photovoltaic Panel Detection From Aerial Images