Computer Tools to Analyze Lung CT Changes after Radiotherapy

Computer-assisted evaluation of small airway disease in CT scans of Iran-Iraq war victims of chemical warfare by a locally developed software: comparison between different quantitative methods

OBJECTIVE

Diagnosis of small airway disease on computed tomography (CT) scans is challenging in patients with a history of chemical warfare exposure. We developed a software package based on different methodologies to identify and quantify small airway disease in CT images. The primary aim was to identify the best automatic methodology for detecting small airway disease in CT scans of Iran-Iraq War victims of chemical warfare.

METHODS

This retrospective case-control study enrolled 46 patients with a history of chemical warfare exposure and 27 controls with inspiratory/expiratory (I/E) CT scans and spirometry tests. Image data were automatically segmented, and inspiratory images were registered into the expiratory images' frame using the locally developed software. Parametric response mapping (PRM) and air trapping index (ATI) mapping were performed on the CT images. Conventional QCT methods, including expiratory/inspiratory mean lung attenuation (E/I MLA) ratio, normal density E/I (ND E/I) MLA ratio, attenuation volume Index (AVI), %low attenuation areas (LAA) < -856 in exhale scans, and %LAA < -950 in inhale scans were also computed. QCT measurements were correlated with spirometry results and compared across the two study groups.

RESULTS

The correlation analysis showed a significant negative relationship between three air trapping (AT) measurements (PRM, ATI, and %LAAExp < -856) and spirometry parameters (Fev1, Fvc, Fev1/Fvc, and MMEF). Moreover, %LAAExp < -856 had the highest significant negative correlation with Fev1/Fvc (r = -0.643, P-value < 0.001). Three AT measurements demonstrated a significant difference between the study groups. The E/I ratio was also significantly different between the two groups (P-value < 0.001). Binary logistic regression models showed PRMFsad, %LAAExp < -856, and ATI as significant and strong predictors of the study outcome. Optimal cut-points for PRMFsad = 19%, %LAAExp < -856 = 23%, and ATI = 27% were identified to classify the participants into two groups with high accuracy.

CONCLUSION

QCT methods, including PRM, ATI, and %LAAExp < -856 can greatly advance the identification and quantification of SAD in chemical warfare victims. The results should be verified in well-designed prospective studies involving a large population.

Multiple instance learning for lung pathophysiological findings detection using CT scans

Lung diseases affect the lives of billions of people worldwide, and 4 million people, each year, die prematurely due to this condition. These pathologies are characterized by specific imagiological findings in CT scans. The traditional Computer-Aided Diagnosis (CAD) approaches have been showing promising results to help clinicians; however, CADs normally consider a small part of the medical image for analysis, excluding possible relevant information for clinical evaluation. Multiple Instance Learning (MIL) approach takes into consideration different small pieces that are relevant for the final classification and creates a comprehensive analysis of pathophysiological changes. This study uses MIL-based approaches to identify the presence of lung pathophysiological findings in CT scans for the characterization of lung disease development. This work was focus on the detection of the following: Fibrosis, Emphysema, Satellite Nodules in Primary Lesion Lobe, Nodules in Contralateral Lung and Ground Glass, being Fibrosis and Emphysema the ones with more outstanding results, reaching an Area Under the Curve (AUC) of 0.89 and 0.72, respectively. Additionally, the MIL-based approach was used for EGFR mutation status prediction - the most relevant oncogene on lung cancer, with an AUC of 0.69. The results showed that this comprehensive approach can be a useful tool for lung pathophysiological characterization.

Normal Lung Tissue CT Density Changes after Volumetric-Arc Radiotherapy (VMAT) for Lung Cancer

Radiation-induced lung injury remains a significant toxicity in thoracic radiotherapy. Because a precise diagnosis is difficult and commonly used assessment scales are unclear and subjective, there is a need to establish quantitative and sensitive grading methods. The lung tissue density change expressed in Hounsfield units (HUs) derived from CT scans seems a useful numeric surrogate. The study aimed to confirm a dose-response effect on HU value changes (ΔHU), their evolution in time, and the impact of selected clinical and demographic factors. We used dedicated, self-developed software to register and analyze 120 pairs of initial and follow-up CT scans of 47 lung cancer patients treated with dynamic arc radiotherapy. The differences in HU values between CT scans were calculated within discretized dose-bins limited by isodose lines. We have proved the dose-effect relationship, which is well described with a sigmoid model. We found the time evolution of HU changes to suit a typical clinical presentation of radiation-induced toxicity. Some clinical factors were found to correlate with ΔHU degree: planning target volume (PTV), V35 in the lung, patient’s age and a history of arterial hypertension, and initial lung ventilation intensity. Lung density change assessment turned out to be a sensitive and valuable method of grading post-RT lung toxicity.

Machine Learning for Biomedical Application

The tremendous development of technology also affects medical science, including imaging diagnostics [...]

Low Radiation Dose Implications in Obese Abdominal Computed Tomography Imaging

The aim of this study was to evaluate the implications of low radiation dose in abdominal computed tomography (CT) when combined with noise reduction filters and to see if this approach can overcome the challenges that arise while scanning obese patients. Anthropomorphic phantoms layered with and without 3-cm-thick circumferential animal fat packs to simulate different sized patients were scanned using a 128-slice multidetector CT (MDCT) scanner. Abdominal protocols (n = 12) were applied using various tube currents (150, 200, 250, and 300 mA) and tube voltages (100, 120, and 140 kVp). MOSFET dosimeters measured the internal organ dose. All images were reconstructed with filtered back projection (FBP) and different iterative reconstruction (IR) strengths (SAFIRE 3, SAFIRE 4, and SAFIRE 5) techniques and objective noise was measured within three regions of interests (ROIs) at the level of L4–L5. Organ doses varied from 0.34–56.2 mGy; the colon received the highest doses for both phantom sizes. Compared to the normal-weighted phantom, the obese phantom was associated with an approximately 20% decrease in effective dose. The 100 kVp procedure resulted in a 40% lower effective dose (p < 0.05) compared to at 120 kVp and the associated noise increase was improved by increasing the IR (5) use, which resulted in a 60% noise reduction compared to when using FBP (p < 0.05). When combined with iterative reconstruction, the low-kVp approach is feasible for obese patients in order to optimize radiation dose and maintain objective image quality.