MRI cytometry imaging for cervical cancer differential diagnosis: a preliminary study

Precise noninvasive detection and differentiation of pathological subtypes in cervical cancer remains challenging. Diffusion MRI (dMRI)-based cytometry, an imaging technique quantifying tumor microenvironments, shows diagnostic potential but requires clinical validation.

74 patients with cervical cancer and 44 healthy volunteers underwent diffusion-weighted imaging using oscillating gradient spin-echo (OGSE) and pulsed gradient spin-echo (PGSE) sequences at 3T. Three radiologists independently scored image quality on a 5-point scale. Time-dependent apparent diffusion coefficients (ADCs) as well as information from 'imaging microstructural parameters using limited spectrally edited diffusion' (IMPULSED) alone or incorporating transcytolemmal water exchange (JOINT) were used to distinguish cancerous from normal tissues and identify tumor subtypes. The microstructural parameters included intracellular volume fraction ([Formula: see text]), cell diameter ([Formula: see text]), extracellular diffusivity ([Formula: see text]), and water exchange rate constant ([Formula: see text]). Receiver operating characteristic (ROC) curves were used to assess the effectiveness.

Kendall's W statistics showed strong inter-reader reliability for assessing OGSE and PGSE images (W = 0.819, P < 0.0001). Microstructural parameters can effectively distinguish cervical cancer from normal tissues, with higher [Formula: see text] (P < 0.01), lower [Formula: see text] (P < 0.0001), and higher [Formula: see text] (P < 0.0001) values for tumors. Additionally, squamous carcinomas were characterized by lower [Formula: see text] and [Formula: see text] values (P < 0.01 and P < 0.05). The area under ROC curve of the combined regression model can reach up to 0.967 and 0.853 for diagnosing cervical cancer and differentiating the subtypes, respectively.

MRI cytometry-derived microstructural parameters can reliably detect cervical cancer and further differentiate its pathological subtypes. This improves the accuracy of noninvasive preoperative assessment and shows considerable clinical potential.