Abstract IS-3: Breast Imaging in Resource Constrained Regions: Lessons from Uganda
Bibliographic record
Abstract
Abstract Breast cancer is the leading cause of cancer death in women and the most common cancer among women world-wide. Five-year survival rates in patients with breast cancer in the United States, Australia and Canada approach 90%, while in parts of Africa survival rates are less than 15%. In October 2013 the international New York Times front page reported on “Uganda's Neglected Epidemic of Breast Cancer.” In December 2013 the WHO International Agency for Research on Cancer (IARC) issued an update on the world's cancer statistics with the headline including the alarm that “marked increase in breast cancers must be addressed.” In Uganda, resources for surgical intervention (mastectomy) and medical oncology (hormonal therapy and limited chemotherapy) are available. Strong recent efforts by the National Cancer Institute, American Cancer Society, and global partners will increase the availability of affordable chemotherapy. In parallel, there is a growing community of breast cancer survivors in Uganda who are sharing their stories and emphasizing the importance of early detection and prompt treatment. Women with palpable breast lumps, identified by themselves or their healthcare providers, are encouraged to seek treatment. But with so many women having palpable breast lumps, and no efficient way to sort the majority of lumps that are benign from the minority of lumps that are malignant, systems are overwhelmed. Clinics do not have the capacity to detect the cancers amongst all the women who present with palpable lumps, and breast cancers remain undiagnosed and untreated, and mortality rates continue to rise. The delays in diagnosis can be significantly reduced with ultrasound (US) technology placed in the hands of non-physician healthcare providers, to streamline the diagnostic process and separate women with lumps that have features warranting biopsy from lumps that can be safely followed clinically in the patient's local, healthcare clinic. Mammography has little added value in countries with limited resources. With so many women who have clear symptoms of breast cancer, and with a significantly higher pre-test probability of cancer in women with (rather than without) symptoms, interventions targeted to asymptomatic women are neither logical nor feasible. The need is not to screen for breast cancers in asymptomatic women but rather to detect the breast cancers in women with symptoms, most notably palpable lumps. Innovative, effective, affordable strategies that emphasize prompt and accurate diagnostic methods in women with palpable breast lumps are needed to improve breast cancer survival in LMICs. These programs can be based on inexpensive, portable ultrasound machines that support triage of patients with palpable lumps to those that need biopsy and those that don't. These technologies are already being used by local health care personnel in developing countries for other prenatal and urgent care purposes. Going forward, novel ultrasound techniques for automated sonogram acquisition and machine learning and deep learning methods can combine to extend the impact of ultrasound imaging in breast cancer diagnosis by reducing the need for highly specialized breast imagers in both acquisition and interpretation. Citation Format: Lehman CD. Breast Imaging in Resource Constrained Regions: Lessons from Uganda [abstract]. In: Proceedings of the 2017 San Antonio Breast Cancer Symposium; 2017 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2018;78(4 Suppl):Abstract nr IS-3.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.018 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.004 | 0.002 |
| Scholarly communication | 0.005 | 0.006 |
| Open science | 0.002 | 0.006 |
| Research integrity | 0.003 | 0.006 |
| Insufficient payload (model declined to judge) | 0.011 | 0.002 |
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 source (direct Gemma or distilled Codex), 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".