“Freezing the Snowman”: (How) can We do Performance Criticism?

Smith, Emma

doi:10.1002/9780470694114.ch12

Cited by 5 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of PTX, air accumulation between the visceral and parietal pleura separates these membranes and eliminates the sliding motion between them, as well as the cardiophasic movement at the parietal pleura. 1 We focused our model on these pleural line characteristics based on the think-aloud analysis by Smith, Zhang, and MacLellan (2022).…”

Section: Application Contextmentioning

confidence: 99%

“…Before constructing the system, we sought to gain insight into the process that experts use to make their di-agnoses and inject this information into our architecture. Smith, Zhang, and MacLellan (2022) conducted a thinkaloud analysis where two subject matter experts (SMEs) analyzed and diagnosed videos of patients that potentially had PTX. Their study determined that the pleural line (where the lung comes into contact with the chest wall) and its movement were the most important features for PTX diagnosis.…”

Section: Introductionmentioning

confidence: 99%

“…This places a larger burden on the model, making it more difficult to execute on a mobile device. Another difference is that we leveraged expert knowledge expressed in a think-aloud analysis (Smith, Zhang, and MacLellan 2022) to construct our pipeline. This leads to a greater degree of interpretability in the form of an ROI bounding box around the pleural line.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

MobilePTX: Sparse Coding for Pneumothorax Detection Given Limited Training Examples

Hannan

Nesbit

Wen

et al. 2023

AAAI

View full text Add to dashboard Cite

Point-of-Care Ultrasound (POCUS) refers to clinician-performed and interpreted ultrasonography at the patient's bedside. Interpreting these images requires a high level of expertise, which may not be available during emergencies. In this paper, we support POCUS by developing classifiers that can aid medical professionals by diagnosing whether or not a patient has pneumothorax. We decomposed the task into multiple steps, using YOLOv4 to extract relevant regions of the video and a 3D sparse coding model to represent video features. Given the difficulty in acquiring positive training videos, we trained a small-data classifier with a maximum of 15 positive and 32 negative examples. To counteract this limitation, we leveraged subject matter expert (SME) knowledge to limit the hypothesis space, thus reducing the cost of data collection. We present results using two lung ultrasound datasets and demonstrate that our model is capable of achieving performance on par with SMEs in pneumothorax identification. We then developed an iOS application that runs our full system in less than 4 seconds on an iPad Pro, and less than 8 seconds on an iPhone 13 Pro, labeling key regions in the lung sonogram to provide interpretable diagnoses.

show abstract

Section: Application Contextmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation