Automated Kidney Segmentation in 3D Ultrasound Imagery, and its Application in Computer-Assisted Trauma Diagnosis
Bibliographic record
Abstract
Due to the limitations of emergency healthcare/technology, blunt abdominal bleeding causes a large number of preventable deaths each year. To save a trauma patient's life, a rapid diagnosis is required, which is not always available in emergency situations. This is the thesis of this PhD research that a computer-assisted algorithm based on 3D ultrasound imagery, as a portable imaging modality, provides a systematic solution to facilitate rapid diagnosis of trauma patients in emergency situations by first responders (ie. paramedics).\n3D ultrasound imagery, which is a portable imaging system, is selected as the preferred imaging modality for trauma diagnosis, because it can be carried to the location of emergency situation. Therefore, by eliminating the need of moving an unstable patient to an imaging room, rapid trauma diagnosis is achievable. Compared to 2D sonography, 3D ultrasound imaging facilitates automated detection and localization of internal organs. This is essential, specifically in the sense that ultrasonographers are not always present at emergency situations. Hence, a computer-assisted solution is essential to guide first responders to perform trauma diagnosis using a 3D ultrasound device.\nAn abdominal bleeding has a high tendency to align around the right kidney. The right-upper-quadrant view of sonography shows the entire kidney shape, and therefore, it is considered as the most relevant internal view to trauma diagnosis. Paramedics usually lack proper knowledge to find the right-upper-quadrant view, to detect the kidney shape, and to detect an internal bleeding using an ultrasound imaging device. Hence, computer-assisted algorithms are required to perform these tasks. The focus of this thesis is to introduce automated methods to detect and segment the kidney shape. The detected kidney shape will be used for two purposes: (a) it is used to calculate the ultrasound probe's misalignment with respect to the right-upper-quadrant view, which is used to guide the operator to move the probe toward the correct alignment on the patient's body; (b) the detected kidney shape is used to initialize the kidney segmentation process, and thereby, an automated kidney segmentation approach is achieved. The kidney segmentation output can be used to automatically detect an internal bleeding.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".