Hyperspectral imaging (HSI) is an emerging imaging modality for medical applications. HSI acquires two dimensional images at various wavelengths. The combination of both spectral and spatial information provides quantitative information for cancer detection and diagnosis. This paper proposes using superpixels, principal component analysis (PCA), and support vector machine (SVM) to distinguish regions of tumor from healthy tissue. The classification method uses 2 principal components decomposed from hyperspectral images and obtains an average sensitivity of 93% and an average specificity of 85% for 11 mice. The hyperspectral imaging technology and classification method can have various applications in cancer research and management.

Purpose Intermolecular multiple quantum coherences (iMQCs) are a source of MR contrast with applications including temperature imaging, anisotropy mapping, and brown fat imaging. Because all applications are limited by SNR, this study develops a pulse sequence that detects iZQCs with improved SNR. Methods A previously developed pulse sequence that detects iMQCs (HOT) is modified with a multi-spin-echo spatial encoding scheme (MSE-HOT). MSE-HOT uses a series of refocusing pulses to generate a stack of images which are averaged in post-processing for higher SNR. MSE-HOT performance is quantified by measuring its temperature accuracy and precision during hyperthermia of ex vivo red bone marrow (RBM) samples. Results MSE-HOT yielded a three-fold improvement in temperature precision relative to previous pulse sequences. Sources of improved precision were 1) echo averaging and 2) suppression of J-coupling in the methylene protons of fat. MSE-HOT measured temperature change with an accuracy of 0.6 °C. Conclusion MSE-HOT improved the temperature accuracy and precision of HOT to a level that is sufficient for hyperthermia of bone marrow.

No abstract