Christine P. Hendon

Near‐Infrared Spectroscopy Mapping for Uterine Cancer and Fibroid Detection

ABSTRACTEndometrial cancer and uterine leiomyomas (fibroid) are common uterine pathologies that require early diagnosis to improve a patient's symptoms and increase the success rate of interventional procedures. In this work, we report on near‐infrared spectroscopy (NIRS) spectral features of uterine cancer and fibroids from 69 surgical specimens obtained from 24 patients following hysterectomies. Normal uterus, cancer, and fibroid tissue were identified by NIR spectral contrast parameters based on the differences in spectrum morphology. Using the significant optical features and spectral principal components, a classification model was able to classify uterus tissue with a prediction accuracy higher than 70%, identifying cancer specimens with 70% sensitivity and 93% specificity, and fibroid samples with 86% sensitivity and 83% specificity. These results demonstrated NIRS mapping has promise as a complementary method for gynecologic imaging.

Hyperspectral Imaging of Uterine Fibroids

ABSTRACTUterine fibroids are non‐cancerous growths of the uterus that affect nearly 70%–80% of women in their lifetimes. Fibroids can cause severe pain, bleeding, and infertility. The main risk of recurrence is smaller fibroids, which are notoriously hard to detect, being missed during a surgical removal procedure, only to enlarge afterwards. In this work, hyperspectral imaging (HSI) datasets were acquired from samples from 10 patients after receiving a hysterectomy. Optical properties including absorption, scattering, and spectral morphology were extracted and fed into machine learning to classify regions as fibroid and myometrium. Top extracted optical features had significant contrast between fibroid and myometrium (p < 0.0001) and were used to train Random Forest (AUC: 0.9985 ± 0.001, Sensitivity: 0.9534 ± 0.019, Specificity: 0.9936 ± 0.009) and Logistic Regression (AUC: 0.9397 ± 0.013, Sensitivity: 0.8405 ± 0.023, Specificity: 0.8895 ± 0.032) with strong performance across testing splits. With HSI, there is contrast between fibroid and myometrium in the human uterus.