Deep Learning for Automatic Bone Marrow Apparent Diffusion Coefficient Measurements From Whole-Body Magnetic Resonance Imaging in Patients With Multiple Myeloma

Abstract

ObjectivesDiffusion-weighted magnetic resonance imaging (MRI) is increasingly important in patients with multiple myeloma (MM). The objective of this study was to train and test an algorithm for automatic pelvic bone marrow analysis from whole-body apparent diffusion coefficient (ADC) maps in patients with MM, which automatically segments pelvic bones and subsequently extracts objective, representative ADC measurements from each bone.Materials and MethodsIn this retrospective multicentric study, 180 MRIs from 54 patients were annotated (semi)manually and used to train an nnU-Net for automatic, individual segmentation of the right hip bone, the left hip bone, and the sacral bone. The quality of the automatic segmentation was evaluated on 15 manually segmented whole-body MRIs from 3 centers using the dice score. In 3 independent test sets from 3 centers, which comprised a total of 312 whole-body MRIs, agreement between automatically extracted mean ADC values from the nnU-Net segmentation and manual ADC measurements from 2 independent radiologists was evaluated. Bland-Altman plots were constructed, and absolute bias, relative bias to mean, limits of agreement, and coefficients of variation were calculated. In 56 patients with newly diagnosed MM who had undergone bone marrow biopsy, ADC measurements were correlated with biopsy results using Spearman correlation.ResultsThe ADC-nnU-Net achieved automatic segmentations with mean dice scores of 0.92, 0.93, and 0.85 for the right pelvis, the left pelvis, and the sacral bone, whereas the interrater experiment gave mean dice scores of 0.86, 0.86, and 0.77, respectively. The agreement between radiologists' manual ADC measurements and automatic ADC measurements was as follows: the bias between the first reader and the automatic approach was 49 × 10−6 mm2/s, 7 × 10−6 mm2/s, and −58 × 10−6 mm2/s, and the bias between the second reader and the automatic approach was 12 × 10−6 mm2/s, 2 × 10−6 mm2/s, and −66 × 10−6 mm2/s for the right pelvis, the left pelvis, and the sacral bone, respectively. The bias between reader 1 and reader 2 was 40 × 10−6 mm2/s, 8 × 10−6 mm2/s, and 7 × 10−6 mm2/s, and the mean absolute difference between manual readers was 84 × 10−6 mm2/s, 65 × 10−6 mm2/s, and 75 × 10−6 mm2/s. Automatically extracted ADC values significantly correlated with bone marrow plasma cell infiltration (R = 0.36, P = 0.007).ConclusionsIn this study, a nnU-Net was trained that can automatically segment pelvic bone marrow from whole-body ADC maps in multicentric data sets with a quality comparable to manual segmentations. This approach allows automatic, objective bone marrow ADC measurements, which agree well with manual ADC measurements and can help to overcome interrater variability or nonrepresentative measurements. Automatically extracted ADC values significantly correlate with bone marrow plasma cell infiltration and might be of value for automatic staging, risk stratification, or therapy response assessment.

Prediction of Bone Marrow Biopsy Results From MRI in Multiple Myeloma Patients Using Deep Learning and Radiomics

“…A connection between stages of diffuse infiltration severity in MRI and PCI, 39,44–47 as well as between signal intensities/ADC-values and PCI, 43,48,49 has been described. However, to the best of our knowledge, these have not yet been used to predict PCI from MRI.…”

“…Earlier approaches on automatic BM segmentation [40][41][42] reported results that were markedly worse than the benchmark for manual segmentation set by interrater experiments. Recently, first BM segmentation algorithms were presented which allowed BM segmentation from T1w images 25 and ADC-maps 43 with a quality similar to manual segmentations by a radiologist, and performed relatively robust even in external multicentric test sets. In the current study, we trained a nnU-Net on 470 cases with a wide variety of pathologies and several different MRI protocols and scanners represented in the training data sets, to perform individual segmentation of the right and left hip bone from T1-w images.…”

Deep learning-based automated high-accuracy location and identification of fresh vertebral compression fractures from spinal radiographs: a multicenter cohort study

“…In addition, many DL models are dedicated to segmenting bones and vertebrae from radiological images ( Huang et al, 2020 ; Wennmann et al, 2022a ). Klinder et al ( Klinder et al, 2009 ) reported an automated model-based vertebral detection, identification, and segmentation method; this model can achieve an identification success of more than 70% for a single vertebra.…”

Radiomics Analysis for Multiple Myeloma: A Systematic Review with Radiomics Quality Scoring

“…Therefore, in order to implement radiomics in clinical practice for MM patients, methods that allow the segmentation of multiple focal lesions and extended areas of diffuse infiltration or whole bones are required since the manual segmentation of this scale is extremely tedious and potentially unreliable. Methods such as the atlas-based semi-automatic segmentation of whole-body diffusion-weighted imaging and deep learning applications combined with radiomics have already been proposed [ 31 , 42 , 43 , 44 ] and may be the solution to the future translation of radiomics research to the clinic.…”