Hybrid classification of pulmonary nodules

Automated classification of lung nodules is challenging because of the variation in shape and size of lung nodules, as well as their associated differences in their images. Ensemble based learners have demonstrated the potentialof good performance. Random forests are employed for pulmonary nodule classification where each tree in the forest produces a classification decision, and an integrated output is calculated. A classification aided by clustering approach is proposed to improve the lung nodule classification performance. Three experiments are performed using the LIDC lung image database of 32 cases. The classification performance and execution times are presented and discussed.

Formation of multiple pulmonary nodules during treatment with leflunomide

O comprometimento pulmonar é uma das manifestações extra-articulares da artrite reumatóide e pode ser devido à própria doença ou secundário às medicações utilizadas para seu tratamento. Este trabalho relata um caso de uma paciente de 60 anos de idade com diagnóstico de artrite reumatoide que evoluiu com múltiplos nódulos pulmonares durante o tratamento com leflunomida.

Improved detection of pulmonary nodules on energy-subtracted chest radiographs with a commercial computer-aided diagnosis software: comparison with human observers

To retrospectively analyze the performance of a commercial computer-aided diagnosis (CAD) software in the detection of pulmonary nodules in original and energy-subtracted (ES) chest radiographs.

Single-exposure dual-energy subtraction chest radiography: detection of pulmonary nodules and masses in clinical practice

The purpose of this retrospective study was to evaluate the impact of energy subtraction (ES) chest radiography on the detection of pulmonary nodules and masses in daily routine. Seventy-seven patients and 25 healthy subjects were examined with a single exposure digital radiography system. Five blinded readers evaluated first the non-subtracted PA and lateral chest radiographs alone and then together with the subtracted PA soft tissue images. The size, location and number of lung nodules or masses were registered with the confidence level. CT was used as standard of reference. For the 200 total lesions, a sensitivity of 33.5-52.5% was found at non-subtracted and a sensitivity of 43.5-58.5% at energy-subtracted radiography, corresponding to a significant improvement in four of five readers (p < 0.05). However, in three of five readers the rate of false positives was higher with ES. With ES, sensitivity, but not the area under the alternative free-response receiver operating characteristics (AFROC) curve, showed a good correlation with reader experience (R = 0.90, p = 0.026). In four of five readers, the diagnostic confidence improved with ES (p = 0.0036). We conclude that single-exposure digital ES chest radiography improves detection of most pulmonary nodules and masses, but identification of nodules <1 cm and false-positive findings remain a problem.

[Pulmonary nodules in a patient on long-term steroid treatment]

We report on a patient who was chronically treated with steroids. She simultaneously developed pulmonary nocardiosis as well as a soft tissue infection and osteomyelitis by mycobacterium abscessus. Both infections are rare, but more frequently occur in immunocompromised hosts. The patient was healed after 12 month of adequate antibiotic treatment.

Automated detection of lung nodules in computed tomography images: a review

Lung nodules refer to a range of lung abnormalities the detection of which can facilitate early treatment for lung patients. Lung nodules can be detected by radiologists through examining lung images. Automated detection systems that locate nodules of various sizes within lung images can assist radiologists in their decision making. This paper presents a study of the existing methods on automated lung nodule detection. It introduces a generic structure for lung nodule detection that can be used to represent and describe the existing methods. The structure consists of a number of components including: acquisition, pre-processing, lung segmentation, nodule detection, and false positives reduction. The paper describes the algorithms used to realise each component in different systems. It also provides a comparison of the performance of the existing approaches.

Proposal to utilize simplified Swensen protocol in diagnosis of isolated pulmonary nodule

Background: The problem of diagnosing whether a solitary pulmonary nodule is benign or malignant is even greater in developing countries due to a higher prevalence of infectious diseases. These infections generate a large number of patients who are generally asymptomatic and with a pulmonary nodule that cannot be accurately defined as having benign or malignant etiology.Purpose: To verify the percentages of benign versus malignant non-calcified nodules, the length of time after contrast agent injection is spiral computed tomography (CT) most sensitive and specific, and whether three postcontrast phases are necessary.Material and Methods: We studied 23 patients with solitary pulmonary nodules identified on chest radiographs or CT. Spiral scans were obtained with Swensen protocol, but at 3, 4, and 5 min after contrast injection onset. Nodules were classified as benign or malignant by histopathological examination or by an absence or presence of growth after 2 years of follow-up CT.Results: Of the 23 patients studied, 18 (78.2%) showed a final diagnosis of benign and five (21.7%) malignant nodules. Despite the small sample size, we obtained results similar to those of Swensen et al., with 80.0% sensitivity, 55.5% specificity, and 60.8% accuracy. Four minutes gave the greatest mean enhancement in both malignant and benign lesions.Conclusion: Small non-calcified benign nodules were much more frequent than malignant nodules. The best time for dynamic contrast-enhanced CT density analysis was 4 min postcontrast. As well as saving time and money, this simplified Swensen protocol with only precontrast and 4 min postcontrast phases also reduces patient exposure to ionizing radiation.

Postmortem ventilation: A new method for improved detection of pulmonary pathologies in forensic imaging

Postmortem imaging has gained prominence in the field of forensic pathology. Even with experience in this procedure, difficulties arise in evaluating pathologies of the postmortem lung. The effect of postmortem ventilation with applied pressures of 10, 20, 30 and 40mbar was evaluated in 10 corpses using simultaneous postmortem computed tomography (pmCT) scans. Ventilation was performed via a continuous positive airway pressure mask (n=5), an endotracheal tube (n=4) and a laryngeal mask (n=1) using a portable home care ventilator. The lung volumes were measured and evaluated by a segmentation technique based on reconstructed CT data. The resulting changes to the lungs were analyzed. Postmortem ventilation at 40mbar induced a significant (p<0.05) unfolding of the lungs, with a mean volume increase of 1.32l. Small pathologies of the lung such as scarring and pulmonary nodules as well as emphysema were revealed, while inner livores were reduced. Even though lower ventilation pressures resulted in a significant (p<0.05) volume increase, pathologies were best evaluated when a pressure of 40mbar was applied, due to the greater reduction of the inner livores. With the ventilation-induced expansion of the lungs, a decrease in the heart diameter and gaseous distension of the stomach was recognized. In conclusion, postmortem ventilation is a feasible method for improving evaluation of the lungs and detection of small lung pathologies. This is because of the volume increase in the air-filled portions of the lung and reduced appearance of inner livores.

Volumetric analysis of lung nodules in computed tomography (CT): comparison of two different segmentation algorithm softwares and two different reconstruction filters on automated volume calculation.

BACKGROUND A precise detection of volume change allows for better estimating the biological behavior of the lung nodules. Postprocessing tools with automated detection, segmentation, and volumetric analysis of lung nodules may expedite radiological processes and give additional confidence to the radiologists. PURPOSE To compare two different postprocessing software algorithms (LMS Lung, Median Technologies; LungCARE®, Siemens) in CT volumetric measurement and to analyze the effect of soft (B30) and hard reconstruction filter (B70) on automated volume measurement. MATERIAL AND METHODS Between January 2010 and April 2010, 45 patients with a total of 113 pulmonary nodules were included. The CT exam was performed on a 64-row multidetector CT scanner (Somatom Sensation, Siemens, Erlangen, Germany) with the following parameters: collimation, 24x1.2 mm; pitch, 1.15; voltage, 120 kVp; reference tube current-time, 100 mAs. Automated volumetric measurement of each lung nodule was performed with the two different postprocessing algorithms based on two reconstruction filters (B30 and B70). The average relative volume measurement difference (VME%) and the limits of agreement between two methods were used for comparison. RESULTS At soft reconstruction filters the LMS system produced mean nodule volumes that were 34.1% (P < 0.0001) larger than those by LungCARE® system. The VME% was 42.2% with a limit of agreement between -53.9% and 138.4%.The volume measurement with soft filters (B30) was significantly larger than with hard filters (B70); 11.2% for LMS and 1.6% for LungCARE®, respectively (both with P < 0.05). LMS measured greater volumes with both filters, 13.6% for soft and 3.8% for hard filters, respectively (P < 0.01 and P > 0.05). CONCLUSION There is a substantial inter-software (LMS/LungCARE®) as well as intra-software variability (B30/B70) in lung nodule volume measurement; therefore, it is mandatory to use the same equipment with the same reconstruction filter for the follow-up of lung nodule volume.

Computer technology in detection and staging of prostate carcinoma: a review

Y. Zhu, S. Williams and R. Zwiggelaar, 'Computer technology in detection and staging of prostate carcinoma: a review', Medical Image Analysis 10 (2), 178-199 (2006)

Integrated Chest Image Analysis System "BU-MIA"

We introduce "BU-MIA," a Medical Image Analysis system that integrates various advanced chest image analysis methods for detection, estimation, segmentation, and registration. BU-MIA evaluates repeated computed tomography (CT) scans of the same patient to facilitate identification and evaluation of pulmonary nodules for interval growth. It provides a user-friendly graphical user interface with a number of interaction tools for development, evaluation, and validation of chest image analysis methods. The structures that BU-MIA processes include the thorax, lungs, and trachea, pulmonary structures, such as lobes, fissures, nodules, and vessels, and bones, such as sternum, vertebrae, and ribs.

Random forest based lung nodule classification aided by clustering

An automated lung nodule detection system can help spot lung abnormalities in CT lung images. Lung nodule detection can be achieved using template-based, segmentation-based, and classification-based methods. The existing systems that include a classification component in their structures have demonstrated better performances than their counterparts. Ensemble learners combine decisions of multiple classifiers to form an integrated output. To improve the performance of automated lung nodule detection, an ensemble classification aided by clustering (CAC) method is proposed. The method takes advantage of the random forest algorithm and offers a structure for a hybrid random forest based lung nodule classification aided by clustering. Several experiments are carried out involving the proposed method as well as two other existing methods. The parameters of the classifiers are varied to identify the best performing classifiers. The experiments are conducted using lung scans of 32 patients including 5721 images within which nodule locations are marked by expert radiologists. Overall, the best sensitivity of 98.33% and specificity of 97.11% have been recorded for proposed system. Also, a high receiver operating characteristic (ROC) A_z of 0.9786 has been achieved.

Primary diffuse large B-cell lymphoma or lymphomatoid granulomatosis grade 3: a still-puzzling diagnosis in autopsy

Primary lung lymphoma is a rare entity accounting for approximately 0.3% of all primary neoplasia of the lung and includes diffuse large B-cell lymphoma (DLBL) and lymphomatoid granulomatosis (LYG). Considering that clinical features may be similar, whereas epidemiology, morphology, and radiological features are different, the authors report a case of a middle-aged man who presented multiple pulmonary nodules in the lower lobes and groundglass opacities scattered bilaterally on computed tomography. Clinically, he presented a consumptive syndrome with respiratory failure and pleurisy, which progressed until death. The autopsy findings were consistent with lymphomatoid granulomatosis (LYG) grade 3/ diffuse large B-cell lymphoma (DLBL). The authors call attention to the difficulty of establishing an accurate diagnosis, mainly when the demonstration of EBV-infected atypical B-cells fails.

Canine heartworm disease in Porto Velho: first record, distribution map and occurrence of positive mosquitoes

The aim of this study was to make the first report on canine heartworm disease in the state of Rondônia and confirm its transmission in this state. Blood samples were randomly collected from 727 dogs in the city of Porto Velho. The samples were analyzed to search for microfilariae and circulating antigens, using three different techniques: optical microscopy on thick blood smears stained with Giemsa; immunochromatography; and PCR. Mosquitoes were collected inside and outside the homes of all the cases of positive dogs and were tested using PCR to search for DNA of Dirofilaria immitis. Ninety-three blood samples out of 727 (12.8%) were positive according to the immunoassay technique and none according to the thick smear method. Among the 93 positive dogs, 89 (95.7%) were born in Porto Velho. No difference in the frequency of infection was observed between dogs raised indoors and in the yard. PCR on the mosquitoes resulted in only one positive pool. This result shows that the transmission of canine heartworm disease is occurring in the city of Porto Velho and that there is moderate prevalence among the dogs. The techniques of immunochromatography and PCR were more effective for detecting canine heartworm than thick blood smears. The confirmation of canine heartworm disease transmission in Porto Velho places this disease in the ranking for differential diagnosis of pulmonary nodules in humans in Rondônia.