Aidan Boyd

Aidan Boyd

Auto-generated profile, based on publicly available information

Aidan Boyd

University of Notre Dame, Notre Dame, IN, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2024 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
DTDivyanshu Tak
Divyanshu Tak
ZYZezhong Ye
Zezhong Ye
AZAnna Zapaischykova
Anna Zapaischykova
YZYining Zha
Yining Zha
ABAidan Boyd
Aidan Boyd
BKBenjamin H. Kann
Benjamin H. Kann
"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop and externally test a scan-to-prediction deep-learning pipeline for noninvasive, MRI-based BRAF mutational status classification for pediatric low-grade glioma (pLGG). Materials and Methods This retrospective study included two pLGG datasets with linked genomic and diagnostic T2-weighted MRI data of patients: BCH (development dataset, n = 214 [60 (28%) BRAF-Fusion, 50 (23%) BRAF V600E, 104 (49%) wild-type), and the Children's Brain Tumor Network (external testing, n = 112 [60 (53%) with BRAF-Fusion, 17 (15%) BRAF-V600E, 35 (32%) wild-type]). A deep learning pipeline was developed to classify BRAF mutational status (V600E versus Fusion versus Wild-Type) via a two-stage process: 1) 3D tumor segmentation and extraction of axial tumor images, and 2) slice-wise, deep learning-based classification of mutational status. Knowledge-transfer and self-supervised approaches were investigated to prevent model overfitting, with a primary endpoint of the area under the receiver operating characteristic curve (AUC). To enhance model interpretability, we developed a novel metric, COMDist (Center of Mass Distance), that quantifies the model attention around the tumor. Results A combination of transfer learning from a pretrained medical imaging-specific network and self-supervised label cross-training (TransferX) coupled with consensus logic yielded the highest classification performance with AUC of 0.82 [95% CI: 0.72-0.91], 0.87 [95% CI: 0.61-0.97], and 0.85[95% CI: 0.66-0.95] for Wild-Type, BRAF-Fusion and BRAF-V600E, respectively, on internal testing. On external testing, the pipeline yielded AUC of 0.72 [95% CI: 0.64-0.86], 0.78 [95% CI: 0.61-0.89], and 0.72 [95% CI: 0.64-0.88] for Wild-Type, BRAF-Fusion and BRAF-V600E classes, respectively. Conclusion Transfer learning and self-supervised cross-training improved classification performance and generalizability for noninvasive pLGG mutational status prediction in a limited data scenario. ©RSNA, 2024.

1 October 2020 in Pattern Recognition Letters
Verified
Journal Article
Closed access
ABAidan Boyd
Aidan Boyd
ZFZhaoyuan Fang
Zhaoyuan Fang
ACAdam Czajka
Adam Czajka
KBKevin W. Bowyer
Kevin W. Bowyer

22 July 2020 in IEEE Access
Verified
Journal Article
Open access
ABAidan Boyd
Aidan Boyd
SYShivangi Yadav
Shivangi Yadav
TSThomas Swearingen
Thomas Swearingen
AKAndrey Kuehlkamp
Andrey Kuehlkamp
MTMateusz Trokielewicz
Mateusz Trokielewicz
ACAdam Czajka
Adam Czajka
Post-mortem biometrics entails utilizing the biometric data of a deceased individual for determining or verifying human identity. Due to fundamental biological changes that occur in a person’s biometric traits after death, post-mortem data can be significantly different from ante-mortem data, introducing new challenges for biometric sensors, feature extractors and matchers. This paper surveys research to date on the problem of using iris images acquired after death for automated human recognition. A comprehensive review of existing literature is complemented by a summary of the most recent results and observations offered in these publications. This survey is unique in several elements. Firstly, it is the first publication to consider iris recognition where gallery images are acquired before death (perimortem images) and the probe images are acquired after death from the same subjects. Secondly, results are presented from the largest database of peri-mortem and post-mortem iris images, collected from 213 subjects by two independent institutions located in the U.S. and Poland. Thirdly, post-mortem recognition viability is assessed using more than 20 iris recognition algorithms, ranging from the classic (e.g., Gabor filteringbased) to the modern (e.g., deep learning-based). Finally, we provide a medically informed commentary on post-mortem iris, analyze the reasons for recognition failures, and identify key directions for future research.

1 July 2024 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
ABAidan Boyd
Aidan Boyd
ZYZezhong Ye
Zezhong Ye
SPSanjay P Prabhu
Sanjay P Prabhu
MTMichael C. Tjong
Michael C. Tjong
YZYining Zha
Yining Zha
BKBenjamin H. Kann
Benjamin H. Kann
"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop, externally test, and evaluate clinical acceptability of a deep learning (DL) pediatric brain tumor segmentation model using stepwise transfer learning. Materials and Methods In this retrospective study, the authors leveraged two T2-weighted MRI datasets (May 2001-December 2015) from a national brain tumor consortium (n = 184; median age, 7 years (range: 1-23 years); 94 male) and a pediatric cancer center (n = 100; median age, 8 years (range: 1-19 years); 47 male) to develop and evaluate DL neural networks for pediatric low-grade glioma segmentation using a novel stepwise transfer learning approach to maximize performance in a limited data scenario. The best model was externally-tested on an independent test set and subjected to randomized, blinded evaluation by three clinicians, wherein they assessed clinical acceptability of expert- and artificial intelligence (AI)-generated segmentations via 10-point Likert scales and Turing tests. Results The best AI model used in-domain, stepwise transfer learning (median DSC: 0.88 [IQR 0.72-0.91] versus 0.812 [0.56-0.89] for baseline model; P = .049). On external testing, AI model yielded excellent accuracy using reference standards from three clinical experts (Expert-1: 0.83 [0.75-0.90]; Expert-2: 0.81 [0.70-0.89]; Expert-3: 0.81 [0.68-0.88]; mean accuracy: 0.82)). On clinical benchmarking (n = 100 scans), experts rated AI-based segmentations higher on average compared with other experts (median Likert score: median 9 [IQR 7-9]) versus 7 [IQR 7-9]) and rated more AI segmentations as clinically acceptable (80.2% versus 65.4%). Experts correctly predicted the origin of AI segmentations in an average of 26.0% of cases. Conclusion Stepwise transfer learning enabled expert-level, automated pediatric brain tumor auto-segmentation and volumetric measurement with a high level of clinical acceptability. ©RSNA, 2024.

9 May 2023 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
ABAidan Boyd
Aidan Boyd
JSJeremy Speth
Jeremy Speth
LPLucas Parzianello
Lucas Parzianello
KBKevin W. Bowyer
Kevin W. Bowyer
ACAdam Czajka
Adam Czajka
Research in presentation attack detection (PAD) for iris recognition has largely moved beyond evaluation in “closed-set” scenarios, to emphasize ability to generalize to presentation attack types not present in the training data. This paper offers multiple contributions to understand and extend the state-of-the-art in open-set iris PAD. First, it describes the most authoritative evaluation to date of iris PAD. We have curated the largest publicly-available image dataset for this problem, drawing from 26 benchmarks previously released by various groups, and adding 150,000 images being released with this paper, to create a set of 450,000 images representing authentic iris and seven types of presentation attack instrument (PAI). We formulate a leave-one-PAI-out evaluation protocol, and show that even the best algorithms in the closed-set evaluations exhibit catastrophic failures on multiple attack types in the open-set scenario. This includes algorithms performing well in the most recent LivDet-Iris 2020 competition, which may come from the fact that the LivDet-Iris protocol emphasizes sequestered images rather than unseen attack types. Second, we evaluate the accuracy of five open-source iris presentation attack algorithms available today, one of which is newly-proposed in this paper, and build an ensemble method that beats the winner of the LivDet-Iris 2020 by a substantial margin. This paper demonstrates that closed-set iris PAD, when all PAIs are known during training, is a solved problem, with multiple algorithms showing very high accuracy, while open-set iris PAD, when evaluated correctly, is far from being solved. The newly-created dataset, new open-source algorithms, and evaluation protocol, all made publicly available with this paper, provide experimental artifacts that researchers can use to measure progress on this important problem.

1 December 2023 in IEEE Transactions on Artificial Intelligence
Verified
Journal Article
Open access
CCColton R. Crum
Colton R. Crum
PTPatrick Tinsley
Patrick Tinsley
ABAidan Boyd
Aidan Boyd
JPJacob Piland
Jacob Piland
CSChristopher Sweet
Christopher Sweet
ACAdam Czajka
Adam Czajka
The performance of convolutional neural networks has continued to improve over the last decade. At the same time, as model complexity grows, it becomes increasingly more difficult to explain model decisions. Such explanations may be of critical importance for reliable operation of human-machine pairing setups, or for model selection when the ”best’” model among many equally-accurate models must be established. Saliency maps represent one popular way of explaining model decisions by highlighting image regions models deem important when making a prediction. However, examining salience maps at scale is not practical. In this paper, we propose five novel methods of leveraging model salience to explain a model behavior at scale. These methods ask: (a) what is the average entropy for a model’s salience maps, (b) how does model salience change when fed out-of-set samples, (c) how closely does model salience follow geometrical transformations, (d) what is the stability of model salience across independent training runs, and (e) how does model salience react to salience-guided image degradations. To assess the proposed measures on a concrete and topical problem, we conducted a series of experiments for the task of synthetic face detection with two types of models: those trained traditionally with cross-entropy loss, and those guided by human salience when training to increase model generalizability. These two types of models are characterized by different, interpretable properties of their salience maps, which allows for the evaluation of the correctness of the proposed measures. We offer source codes for each measure along with this paper.