midi_lab_white_roundedBack.png

Current specific projects include the development of novel deep-learned algorithms and image-enhancement techniques to a) improve the grading of pneumoconiosis on chest radiographs, b) detect pediatric rib fractures, c) evaluate low-grade gliomas on MRI, and d) predict health care utilization for cancer patients.

Sampling of Ongoing Research Directions and Projects in the MIDI Lab:

UNDER CONSTRUCTION

Pediatric Rib Fracture Detection

Goal: Develop AI methods to automatically detect rib fractures on pediatric radiographs, aiding in the identification of non-accidental trauma.

This project aims to leverage artificial intelligence to enhance the detection of rib fractures in pediatric chest radiographs. Rib fractures can be challenging to identify visually, yet they are crucial indicators of potential non-accidental trauma in children.

Some of this project has been presented in:

  1. Burkow, Holste, Otjen, Perez, Junewick, Zbojniewicz, Romberg, Menashe, Frost, Alessio, "High sensitivity methods for automated rib fracture detection in pediatric radiographs." Scientific Reports 14, 8372, 2024. https://doi.org/10.1038/s41598-024-59077-5
  2. Tu, Burkow, Tsai, Junewick, Perez, Otjen, Alessio, "Near-Pair Patch Generative Adversarial Network for Data Augmentation of Focal Pathology Object Detection Models," Journal of Medical Imaging (SPIE), Vol. 11:3, June 2024, https://doi.org/10.1117/1.JMI.11.3.034505

Collaborators:

This research is supported by grant R21HD097609: "Automatic Rib Fracture Detection in Pediatric Radiography to Identify Non-Accidental Trauma"

Screenshot 2024-10-27 at 3.39.19 PM.png

Figure 1: A chest radiograph with arrows to locations of potential rib fractures (left). These fractures are challenged to detect. An automated model analyzes these types of  images to detect fractures with an example case on the right.

Multimodal Learning for Breast Cancer Classification

Goal: Risk stratify breast cancer based on dynamic contrast MR exams and additional patient factors