A soft-segmentation visualization scheme for magnetic resonance images

Optimization of CT windowing for diagnosing invasiveness of adenocarcinoma presenting as sub-solid nodules

PURPOSE

To evaluate the optimal window setting to diagnose the invasiveness of lung adenocarcinoma in sub-solid nodules (SSNs).

METHODS

We retrospectively included 437 SSNs and randomly divided them 3:1 into a training group (327) and a testing group (110). The presence of a solid component was regarded as indicator of invasiveness. At fixed window level (WL) of 35 Hounsfield Units (HU), two readers adjusted the window width (WW) in the training group and recorded once a solid component appeared or disappeared on CT images acquired at 120 kVp. The optimal WW cut-off value to differentiate between invasive and pre-invasive lesions, based on the receiver operating characteristic (ROC) curve, was defined as "core" WW. The diagnostic performances of the mediastinal window setting (WW/WL, 350/35 HU) and core window setting were then compared in the testing group.

RESULTS

Of the 437 SSNs, 88 were pre-invasive [17 atypical adenomatous hyperplasia (AAH) and 71 adenocarcinoma in situ (AIS)], 349 were invasive [233 minimally invasive adenocarcinoma (MIA), 116 invasive adenocarcinoma (IA)]. In training group, the core WW of 1175 HU was the optimal cut-off to detect solid components of SSNs (AUC:0.79). In testing group, the sensitivity, specificity, positive, negative predictive value, and diagnostic accuracy for SSN invasiveness were 49.4%, 90.5%, 95.7%, 29.7%, and 57.3% for mediastinal window setting, and 87.6%, 76.2%, 91.6%, 76.2%, and 85.5% for core window setting.

CONCLUSION

At 120 kVp, core window setting (WW/WL, 1175/35 HU) outperformed the traditional mediastinal window setting to diagnose the invasiveness of SSNs.

Histogram Matching Extends Acceptable Signal Strength Range on Optical Coherence Tomography Images

PURPOSE

We minimized the influence of image quality variability, as measured by signal strength (SS), on optical coherence tomography (OCT) thickness measurements using the histogram matching (HM) method.

METHODS

We scanned 12 eyes from 12 healthy subjects with the Cirrus HD-OCT device to obtain a series of OCT images with a wide range of SS (maximal range, 1-10) at the same visit. For each eye, the histogram of an image with the highest SS (best image quality) was set as the reference. We applied HM to the images with lower SS by shaping the input histogram into the reference histogram. Retinal nerve fiber layer (RNFL) thickness was automatically measured before and after HM processing (defined as original and HM measurements), and compared to the device output (device measurements). Nonlinear mixed effects models were used to analyze the relationship between RNFL thickness and SS. In addition, the lowest tolerable SSs, which gave the RNFL thickness within the variability margin of manufacturer recommended SS range (6-10), were determined for device, original, and HM measurements.

RESULTS

The HM measurements showed less variability across a wide range of image quality than the original and device measurements (slope = 1.17 vs. 4.89 and 1.72 μm/SS, respectively). The lowest tolerable SS was successfully reduced to 4.5 after HM processing.

CONCLUSIONS

The HM method successfully extended the acceptable SS range on OCT images. This would qualify more OCT images with low SS for clinical assessment, broadening the OCT application to a wider range of subjects.

Diagnosis of the invasiveness of lung adenocarcinoma manifesting as ground glass opacities on high-resolution computed tomography

BACKGROUND

To explore the diagnostic method in assessing the malignancy of pulmonary adenocarcinoma characterized by ground glass opacities (GGO) on computed tomography (CT).

METHODS

Preoperative CT data for preinvasive and invasive lung adenocarcinomas were analyzed retrospectively. GGO lesions that were detected on lung windows but absent using the mediastinal window were subject to adjustment of the window width, which was reduced with the fixed interval of 100 HU until the lesions were no longer evident, with a fixed mediastinal window level of 40 HU. The shape, smoking habits, size of the lesion on the lung window, and window width at which lesions disappeared were compared and receiver operating characteristic curves were used to determine the optimal cut-off of the lesion size and window width to differentiate between these invasive and preinvasive lesions.

RESULTS

Of the 209 lung adenocarcinomas, 102 were preinvasive (25 atypical adenomatous hyperplasia and 77 adenocarcinoma in situ), while 107 were invasive (78 minimally invasive adenocarcinoma and 29 invasive adenocarcinoma). The shape, lesion size, and window width at which lesions were no longer evident differed significantly between the two groups (P < 0.05). The size of 8.9 mm and a window width of 1250 HU were the optimal cut-off to differentiate between preinvasive and invasive lesions.

CONCLUSION

The shape, size of the lesion, and window width on high-resolution CT may be useful in assessing the invasiveness of lung adenocarcinoma that manifests as GGO. Irregular lesions that disappear at window width <1250 HU, with a diameter of > 8.9 mm are more likely to be invasive.

Bayesian mixture models of variable dimension for image segmentation

We present Bayesian methodologies and apply Markov chain sampling techniques for exploring normal mixture models with an unknown number of components in the context of magnetic resonance imaging (MRI) segmentation. The experiments show that by estimating the number of components using sample-based approaches based on variable dimension models the discriminating power of the estimated components is improved. Two different MCMC methods are compared to perform the segmentation of simulated magnetic resonance brain scans, the reversible jump MCMC model and the Dirichlet process (DP) mixture model. The preference given to the Dirichlet process mixture model is discussed.