Quantitative Phase Imaging (QPI) holds immense promise as a powerful label-free and non-invasive clinical diagnostic tool, leveraging its exceptional sensitivity to phase shifts to capture high-quality and unique morphological data. However, as the adoption of deep learning algorithms becomes increasingly enticing for medical image analysis, clinicians’ apprehensions towards their black-box nature is a deterrent for the adoption of novel methods that rely on them. This study advocates for the integration of explainable AI techniques with QPI-based diagnostics to effectively interpret deep learning models' predictions, enabling them in aiding clinician decisions. Using radiation resistance in head and neck cancer as a model system, we investigate cells that have survived exposure to varying levels of radiation. We aim to identify subtle phenotypic differences induced by DNA damage, which might not be readily apparent without the application of sophisticated deep learning analysis. This investigation has the potential to provide valuable insights into the cellular responses to radiation and unravel intricate patterns that traditional analysis methods might overlook, possibly leading to actionable biomarkers. In addition, we compare the results of classical rule based interpretable methods with modern feature importance based explainability to answer - is the trade-off between interpretability and accuracy actually worth it? By providing transparent insights into the decision making process, explainable deep learning empowers clinicians to validate, interpret, and refine diagnostic outcomes, bridging the gap between cutting-edge technology and clinical practice.
Cotton balls are used in neurosurgical procedures to assist with hemostasis and improve vision within the operative field. Although the surgeon can reshape pieces of cotton for multiple intraoperative uses, this customizability and scale also places them at perpetual risk of being lost, as blood-soaked cotton balls are visually similar to raw brain tissue. Retained surgical cotton can induce potentially life-threatening immunologic responses, impair postoperative imaging, lead to a textiloma or misdiagnosis, and/or require reoperation. This study investigated three imaging modalities (optical, acoustic, and radiographic) to find the most effective method of identifying foreign bodies during neurosurgery. First, we examined the use of dyes to increase contrast between cotton and surrounding parenchyma (optical approach). Second, we explored the ability to distinguish surgical cotton on or below the tissue surface from brain parenchyma using ultrasound imaging (acoustic approach). Lastly, we analyzed the ability of radiography to differentiate between brain parenchyma and cotton. Our preliminary testing demonstrated that dark-colored cotton is significantly more identifiable than white cotton on the surface level. Additional testing revealed that cotton has noticeable different acoustic characteristics (eg, speed of sound, absorption) from neural tissue, allowing for enhanced contrast in applied ultrasound imaging. Radiography, however, did not present sufficient contrast, demanding further examination. These solutions have the potential to significantly reduce the possibility of intraoperative cotton retention both on and below the surface of the brain, while still providing surgeons with traditional cotton material properties without affecting the surgical workflow.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.