An automated algorithm for the detection of cortical interruptions on high resolution peripheral quantitative computed tomography images of finger joints

Abstract

ObjectivesTo introduce a fully-automated algorithm for the detection of small cortical interruptions (≥0.246mm in diameter) on high resolution peripheral quantitative computed tomography (HR-pQCT) images, and to investigate the additional value of manual correction of the automatically obtained contours (semi-automated procedure).MethodsTen metacarpophalangeal joints from seven patients with rheumatoid arthritis (RA) and three healthy controls were imaged with HR-pQCT. The images were evaluated by an algorithm according to the fully- and semi-automated procedure for the number and surface of interruptions per joint. Reliability between the fully- and semi-automated procedure and between two independent operators was tested using intra-class correlation coefficient (ICC) and the proportion of matching interruptions. Validity of single interruptions detected was tested by comparing it to visual scoring, as gold standard. The positive predictive value (PPV) and sensitivity were calculated.ResultsThe median number of interruptions per joint was 14 (range 2 to 59) and did not significantly differ between the fully- and semi-automated procedure (p = 0.37). The median interruption surface per joint was significantly higher with the fully- vs. semi-automated procedure (respectively, 8.6mm2 vs. 5.8mm2 and 6.1mm2, p = 0.01). Reliability was almost perfect between the fully- and semi-automated procedure for both the number and surface of interruptions (ICC≥0.95) and the proportion of matching interruptions was high (≥76%). Also the inter-operator reliability was almost perfect (ICC≥0.97, proportion of matching interruptions 92%). The PPV ranged from 27.6% to 29.9%, and sensitivity from 69.7% to 76.3%. Most interruptions detected with the algorithm, did show an interruption on a 2D grayscale image. However, this interruption did not meet the criteria of an interruption with visual scoring.ConclusionThe algorithm for HR-pQCT images detects cortical interruptions, and its interruption surface. Reliability and validity was comparable for the fully- and semi-automated procedures. However, we advise the use of the semi-automated procedure to assure quality. The algorithm is a promising tool for a sensitive and objective assessment of cortical interruptions in finger joints assessed by HR-pQCT.

Assessment of Cortical Interruptions in the Finger Joints of Patients With Rheumatoid Arthritis Using HR-pQCT, Radiography, and MRI

“…Meanwhile, the second‐generation HR‐pQCT (HR‐pQCT2) has been introduced, which has a higher spatial resolution (95 μm versus 130 μm) and smaller voxel size (61 μm versus 82 μm). This higher resolution enables better distinction between bone and nonbone, which may reduce the number of falsely detected interruptions due to the partial volume effect . Additionally, the minimum interruption diameter will be smaller when applying two dilation steps (≥0.305 mm versus ≥0.410 mm, respectively).…”

“…The outer margin of the cortex was identified using an autocontouring algorithm . The contours were visually inspected and, if necessary, adjusted by an operator.…”

“…The outer margin of the cortex was identified using an autocontouring algorithm. (29) The contours were visually inspected and, if necessary, adjusted by an operator. A segmentation to distinguish bone and nonbone was performed using the standard evaluation protocol from the manufacturer, which included Laplace-Hamming filtering and thresholding.…”

“…(28) Therefore, we developed and validated a semiautomated algorithm that more reliably detects the number, surface area, and volume of (small) cortical interruptions (diameter !0.41 mm) in comparison with visual scoring. (28)(29)(30)(31) Although these earlier studies demonstrated the feasibility, validity, and reliability of our semiautomated algorithm in quantifying (small) cortical interruptions, it remains unknown if these (small) cortical interruptions are more frequently seen in patients with RA compared with controls, and whether they are related to both structural damage on CR and structural damage and inflammatory markers on MRI. Furthermore, it is unknown if HR-pQCT imaging has an added value over findings on CR and MRI in the detection of (small) cortical interruptions and in the distinction between patients with RA and healthy subjects.…”

“…In a previous study, we showed that the interoperator reliability of visually detecting these small cortical interruptions was fair . Therefore, we developed and validated a semiautomated algorithm that more reliably detects the number, surface area, and volume of (small) cortical interruptions (diameter ≥0.41 mm) in comparison with visual scoring …”