Mr. Jonathan Burkow Profile

Jonathan Burkow

at Michigan State Univ

SPIE Involvement:

Author

Publications (3)

SPIE Journal Paper | 4 June 2024

Near-pair patch generative adversarial network for data augmentation of focal pathology object detection models

Ethan Tu, Jonathan Burkow, Andy Tsai, Joseph Junewick, Francisco A. Perez, Jeffrey Otjen, Adam M. Alessio

JMI, Vol. 11, Issue 03, 034505, (June 2024) https://doi.org/10.1117/12.10.1117/1.JMI.11.3.034505

KEYWORDS: Education and training, Object detection, Radiography, Sensors, Data modeling, Pathology, Gallium nitride, Visualization, Machine learning, Feature extraction

Read Abstract +

PurposeThe limited volume of medical training data remains one of the leading challenges for machine learning for diagnostic applications. Object detectors that identify and localize pathologies require training with a large volume of labeled images, which are often expensive and time-consuming to curate. To reduce this challenge, we present a method to support distant supervision of object detectors through generation of synthetic pathology-present labeled images.ApproachOur method employs the previously proposed cyclic generative adversarial network (cycleGAN) with two key innovations: (1) use of “near-pair” pathology-present regions and pathology-absent regions from similar locations in the same subject for training and (2) the addition of a realism metric (Fréchet inception distance) to the generator loss term. We trained and tested this method with 2800 fracture-present and 2800 fracture-absent image patches from 704 unique pediatric chest radiographs. The trained model was then used to generate synthetic pathology-present images with exact knowledge of location (labels) of the pathology. These synthetic images provided an augmented training set for an object detector.ResultsIn an observer study, four pediatric radiologists used a five-point Likert scale indicating the likelihood of a real fracture (1 = definitely not a fracture and 5 = definitely a fracture) to grade a set of real fracture-absent, real fracture-present, and synthetic fracture-present images. The real fracture-absent images scored 1.7±1.0, real fracture-present images 4.1±1.2, and synthetic fracture-present images 2.5±1.2. An object detector model (YOLOv5) trained on a mix of 500 real and 500 synthetic radiographs performed with a recall of 0.57±0.05 and an F2 score of 0.59±0.05. In comparison, when trained on only 500 real radiographs, the recall and F2 score were 0.49±0.06 and 0.53±0.06, respectively.ConclusionsOur proposed method generates visually realistic pathology and that provided improved object detector performance for the task of rib fracture detection.

Proceedings Article | 4 April 2022 Poster + Paper

Avalanche decision schemes to improve pediatric rib fracture detection

Jonathan Burkow, Gregory Holste, Jeffrey Otjen, Francisco Perez, Joseph Junewick, Adam Alessio

Proceedings Volume 12033, 120332A (2022) https://doi.org/10.1117/12.2611013

KEYWORDS: Performance modeling, Chest imaging, Radiography, X-ray computed tomography, Visualization, X-rays, Convolutional neural networks, Object recognition

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Deep learning methods for segmentation of lines in pediatric chest radiographs

Ryan Sullivan, Greg Holste, Jonathan Burkow, Adam Alessio

Proceedings Volume 11314, 113142I (2020) https://doi.org/10.1117/12.2550686

KEYWORDS: Image segmentation, Computer programming, Chest imaging, Statistical modeling, Data modeling, Performance modeling, Image classification

Read Abstract +

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years