Comparison of Computed Tomography-Based Artificial Intelligence Modeling and Magnetic Resonance Imaging in Diagnosis of Cholesteatoma

BACKGROUND

In this study, we aimed to compare the success rates of computed tomography image-based artificial intelligence models and magnetic resonance imaging in the diagnosis of preoperative cholesteatoma.

METHODS

The files of 75 patients who underwent tympanomastoid surgery with the diagnosis of chronic otitis media between January 2010 and January 2021 in our clinic were reviewed retrospectively. The patients were classified into the chronic otitis group without cholesteatoma (n=34) and the chronic otitis group with cholesteatoma (n=41) according to the presence of cholesteatoma at surgery. A dataset was created from the preoperative computed tomography images of the patients. In this dataset, the success rates of artificial intelligence in the diagnosis of cholesteatoma were determined by using the most frequently used artificial intelligence models in the literature. In addition, preoperative MRI were evaluated and the success rates were compared.

RESULTS

Among the artificial intelligence architectures used in the paper, the lowest result was obtained in MobileNetV2 with an accuracy of 83.30%, while the highest result was obtained in DenseNet201 with an accuracy of 90.99%. In our paper, the specificity of preoperative magnetic resonance imaging in the diagnosis of cholesteatoma was 88.23% and the sensitivity was 87.80%.

CONCLUSION

In this study, we showed that artificial intelligence can be used with similar reliability to magnetic resonance imaging in the diagnosis of cholesteatoma. This is the first study that, to our knowledge, compares magnetic resonance imaging with artificial intelligence models for the purpose of identifying preoperative cholesteatomas.

A rare entity in a pediatric patient: coexistence of emphysematous cystitis and emphysematous pyelonephritis

BACKGROUND

Emphysematous cystitis (EC) and emphysematous pyelonephritis (EPN) are rare urinary tract infections. They have a wide spectrum of clinical manifestations; ranging from asymptomatic to septic shock at presentation. In children, EC and EPN are rare complications of urinary tract infections (UTIs). Their diagnosis is based on clinical manifestations, laboratory results and characteristic radiological findings of gas within the collecting system, renal parenchyma and/or perinephric tissue. Computed tomography is the best radiological option in the diagnosis of EC and EPN. Despite the availability of various treatment modalities including medical and/or surgical treatment alternatives, these life-threatening conditions have high mortality rates reaching up to 70 percent.

CASE

Urinary tract infection was detected in the examinations of an 11-year-old female patient suffering from lower abdominal pain, vomiting and dysuria for two days. Air was detected in the bladder wall on X-ray. EC was detected in the abdominal ultrasonography. Air formations in the bladder lumen and calyces of both kidneys in abdominal computed tomography confirmed the presence of EPN.

CONCLUSIONS

Individualized treatment should be instituted according to the severity of EC and EPN, and the overall health condition of the patient.

Evaluation of the corpus callosum using magnetic resonance imaging histogram analysis in autism spectrum disorder

BACKGROUND

Histogram analysis is a texture analysis method that can be used in medical images. Quantitative values of the intensity of images can be obtained with histogram analysis. It aimed to evaluate corpus callosum in magnetic resonance images (MRIs) using histogram analysis of pediatric patients with autism spectrum disorder (ASD) to compare them with healthy controls.

METHODS

This study included 29 children with ASD and 29 healthy children with normal brain MRI. High-resolution three-dimensional turbo field echo images were obtained with a 1.5 T scanner device for brain magnetic resonance imaging. On the corpus callosum in the sagittal T1-weighted images obtained, mean gray level density (mean), the standard deviation, median, minimum, maximum, entropy, variance, skewness, kurtosis, uniformity, size % L, size % M, size % U, and percentile parameters were measured.

RESULTS

In ASD patients, mean, standard deviation, maximum, median, variance, entropy, 25%, 75%, 90%, 97%, and 99% values were found to be lower than the control group, and size % U value was higher. In addition, the corpus callosum area was significantly lower in the ASD compared to the controls.

CONCLUSION

According to our study, corpus callosum of patients with ASD showed differences compared to healthy controls by histogram analysis, even though they were seen as normal in brain MRI. We think that histogram analysis can be used to evaluate possibly affected areas of brain in ASD patients.

Application of different methods used to measure the apparent diffusion coefficient of renal cell carcinoma on the same lesion and its correlation with ISUP nuclear grading

PURPOSE

To determine the most frequently used different apparent diffusion coefficient (ADC) measurement methods in renal cell carcinoma (RCC), and their correlation with the International Society of Urological Pathology (ISUP) histologic grading system.

METHODS

A total of 99 patients who underwent diffusion-weighted imaging and whose pathologic diagnosis of RCC was confirmed were included in the study. As a result of a literature review, region of interest (ROI) selection and measurement methods were determined in five ways. These included a small ROI (ADC1) on the solid part of the lesion showing the most restriction; a large ROI (ADC2) on the solid part of the lesion showing restriction; ROI (ADC3) that covered the lesion in the cross-section with the largest diameter, which was obtained by placing ROIs (ADC4) covering the lesion on all sections of the lesion; three small ROIs (ADC5) on solid parts of the lesion showing the most restriction. Then, ADC measurements were made from the contralateral normal kidney parenchyma. Tumors were pathologically subdivided [71 clear cell RCCs (ccRCC), 17 chromophobe RCCs (chRCC), 11 papillary RCCs (pRCC)], and graded according to the ISUP nuclear grading system (42 high-grade, 57 low-grade). Data were analyzed statistically.

RESULTS

In all measurement methods, ADC values of RCCs were statistically significantly lower than normal kidney ADC values. There were no differences between the ADC3 and ADC4 measurements of RCCs (p = 0.999). There was a statistical difference in other measurement methods (p < 0.001). There were differences between ccRCCs and pRCCs and chRCCs in all measurement methods. In all measurement methods, pRCC and chRCC ADC values ​​were lower than ccRCC ADC values. When ISUP nuclear grading and ADC values ​​were compared, there was a statistically inverse correlation between all ADC measurements. The strongest correlation was found in the ADC1 and ADC5 measurements. When the ADC values ​​of ISUP low and high-grade groups were compared, a significant difference was found in the ADC5 measurement method (p = 0.046).

CONCLUSION

According to the findings of the study, ADC5 is the measurement method that shows the best correlation with the ISUP histologic grading system. Therefore, we think that ADC5 can be the primary measurement method for determining the ADC value of RCCs.

Is it useful to use computerized tomography image-based artificial intelligence modelling in the differential diagnosis of chronic otitis media with and without cholesteatoma?

OBJECTIVE

Cholesteatoma is an aggressive form of chronic otitis media (COM). For this reason, it is important to distinguish between COM with and without cholesteatoma. In this study, the role of artificial intelligence modelling in differentiating COM with and without cholesteatoma on computed tomography images was evaluated.

METHODS

The files of 200 patients who underwent mastoidectomy and/or tympanoplasty for COM in our clinic between January 2016 and January 2021 were retrospectively reviewed. According to the presence of cholesteatoma, the patients were divided into two groups as chronic otitis with cholesteatoma (n = 100) and chronic otitis without cholesteatoma (n = 100). The control group (n = 100) consisted of patients who did not have any previous ear disease and did not have any active complaints about the ear. Temporal bone computed tomography (CT) images of all patients were analyzed. The distinction between cholesteatoma and COM was evaluated by using 80% of the CT images obtained for the training of artificial intelligence modelling and the remaining 20% for testing purposes.

RESULTS

The accuracy rate obtained in the hybrid model we used in our study was 95.4%. The proposed model correctly predicted 2952 out of 3093 CT images, while it predicted 141 incorrectly. It correctly predicted 936 (93.78%) of 998 images in the COM group with cholesteatoma, 835 (92.77%) of 900 images in the COM group without cholesteatoma, and 1181 (98.82%) of 1195 images in the normal group.

CONCLUSION

In our study, it has been shown that the differentiation of COM with and without cholesteatoma with artificial intelligence modelling can be made with highly accurate diagnosis rates by using CT images. With the deep learning modelling we proposed, the highest correct diagnosis rate in the literature was obtained. According to the results of our study, we think that with the use of artificial intelligence in practice, the diagnosis of cholesteatoma can be made earlier, it will help in the selection of the most appropriate treatment approach, and the complications can be reduced.

Convolutional Neural Networks based classification of breast ultrasonography images by hybrid method with respect to benign, malignant, and normal using mRMR

Early diagnosis of breast lesions and differentiation of malignant lesions from benign lesions are important for the prognosis of breast cancer. In the diagnosis of this disease ultrasound is an extremely important radiological imaging method because it enables biopsy as well as lesion characterization. Since ultrasonographic diagnosis depends on the expert, the knowledge level and experience of the user is very important. In addition, the contribution of computer aided systems is quite high, as these systems can reduce the workload of radiologists and reinforce their knowledge and experience when considered together with a dense patient population in hospital conditions. In this paper, a hybrid based CNN system is developed for diagnosing breast cancer lesions with respect to benign, malignant and normal. Alexnet, MobilenetV2, and Resnet50 models are used as the base for the Hybrid structure. The features of these models used are obtained and concatenated separately. Thus, the number of features used are increased. Later, the most valuable of these features are selected by the mRMR (Minimum Redundancy Maximum Relevance) feature selection method and classified with machine learning classifiers such as SVM, KNN. The highest rate is obtained in the SVM classifier with 95.6% in accuracy.

The effect of probiotics on prevention of upper respiratory tract infections in the paediatric community - a systematic review

Prevention of acute upper respiratory tract infections (URTIs) is becoming an increasingly important concept in public health application due to the increase in antibiotic resistance. Probiotics have been shown to have some effect on prevention in various reviews. In this study we aimed to re-asses the effect of probiotics as there has been a substantial increase in literature regarding the effects and safety of probiotics in the paediatric population. Two major databases were systematically searched to identify clinical trials eligible for inclusion. Study selection, data extraction and quality assessment were carried out by two reviewers. This review comprises 33 randomised controlled trials (RCTs) applied to a paediatric population with high-quality methodology. The primary outcome for this review was the incidence of respiratory tract infections. Secondary outcomes were severity of symptoms, missed days of school, incidence of antibiotic use and safety of prebiotic use. This review showed that probiotics have an impact on decreasing the incidence of URTIs and the severity of symptoms. The use of probiotics is extremely safe and as studies increase in evaluation of the effect of probiotics more and more show a significant beneficiary effect. Although still a long way from becoming a unanimous treatment modality, the small positive changes that probiotics have on URTIs is important to consider and the use of probiotics should be encouraged more.

Determination of genistein in the Turkish Genista L. species by LC-MS

In this study, Genista species growing in Turkey were analysed for their total and free genistein content by using LC-MS method. The highest amount of total and free genistein was found in Genista tinctoria as 1.05% and 0.27% respectively and trace amount in G. libanotica. Total and free genistein content of the aerial parts of other Genista species varied from 0.01 to 0.18% and from 0.01 to 0.13% respectively.

Combination of steroid with azathioprine in treatment of giant cell autoimmune hepatitis

Giant cell hepatitis is a rare disorder after the newborn period. Drugs, autoimmunity, and viruses (lately, paramyxovirus infection) have been implicated in its etiology. Without treatment, liver dysfunction is progressive and fatal. Immunosuppression with steroids and azathioprine has been demonstrated to sustain improvement in the disease. In this report, a one-year-old boy who has giant cell hepatitis with Coombs' positive hemolytic anemia and anti-smooth muscle antibodies is presented, and the course of the disease and the patient's response to treatment with steroid and azathioprine is reviewed.

Renal, gastric and thyroidal amyloidosis due to familial Mediterranean fever

Chronic renal failure developed in a 10-year-old girl due to renal amyloidosis secondary to familial Mediterranean fever (FMF). During management of the chronic renal failure by hemodialysis and of FMF with colchicine, goiter and hypothroidism were observed. Thyroid fine-needle aspiration and gastric endoscopical biopsies, performed when recurrent abdominal pain could not be controlled, revealed amyloid deposits in both thyroid and gastric tissues. After 6 months' therapy with colchicine and levothyroxine, there was no significant change in the thyroid volume. This is the first case in which gastric amyloidosis secondary to FMF in childhood has been demonstrated. Patients with amyloidosis secondary to FMF who have thyroid enlargement and unexplained gastrointestinal symptoms despite adequate therapy should be evaluated with imaging studies and biopsy examinations.

A case of juvenile ankylosing spondylitis and Crohn's disease

Juvenile ankylosing spondylitis (JAS) is a chronic inflammatory arthritis of the peripheral and axial skeleton, frequently accompanied by enthesitis. About four percent of patients with JAS have ulcerative colitis or Crohn's disease. Crohn's disease is the more common of the two and is diagnosed in 26 percent of patients with chronic spondyloarthropathy. In this paper, a 14-year-old male patient is presented as a typical case of juvenile ankylosing spondylitis and Crohn's disease with low back pain, morning stiffness, limited motion in anterior and lateral flexion and extension, left sacroiliitis, ankylosis in the apophyseal joints of the lumbar vertebrae, abdominal pain, bloody diarrhea, characteristic histopathologic changes of colonic involvement such as lymphoid follicles, fissures, submucosal polymorphonuclear cell infiltration and definite ganglion cells. The current therapy with mesalazin, having fewer side effects than sulfosalazin, and its applicability in combination with naproxen sodium is also discussed.

Tricho-rhino-phalangeal syndrome type I

Tricho-rhino-phalangeal syndrome type I (TRPS I) is characterized by a bulbous nose, sparse hair and epiphyseal coning. Autosomal dominant and recessive transmission are suggested. The presence of cone-shaped epiphyses, the major complaint of patients due to swelling over the phalangeal joints, requires differential diagnosis among various syndromes. This paper, describing a ten-year-old girl with TRPS I, aims to bring the features of the syndrome to medical attention.

Single photon emission computed tomography in adrenoleukodystrophy. A case report

Adrenoleukodystrophy (ALD) is a genetic disorder leading to progressive dysfunction of the adrenal cortex and nervous system white matter. Accumulation of fatty acids in cerebral white matter results in some anatomical and functional changes which are detectable by imaging studies. Lately, single photon emission computed tomography (SPECT) has been suggested for evaluation of cerebral perfusion changes. In this report, magnetic resonance imaging (MRI) and SPECT neurolmaging of an eight-year-old boy with ALD are presented. SPECT revealed more extensive involvement than that demonstrated by MRI. Its role in early prediction of the extention of disease is stressed.

Mcardle's disease. A case report

McArdle's disease is a hereditary, metabolic myopathy characterized by weakness and muscle cramps after exercise, appearing mostly in the second or third decade of life. Due to myophosphorylase deficiency in skeletal muscle, glycogen cannot be used and deposited in the sarcolemmal spaces, leading to lack of endurance to sustained work. The ischemic exercise test is a screening procedure for muscle energy disorders, and the diagnosis is confirmed by reduced enzyme activity in muscle biopsy. In this report, a family with one child having enzyme assay-proven McArdle's disease and two other children demonstrating a positive ischemic exercise test is presented.

Anthropometric and nutritional evaluation of short statured children from low socio-economic class

The objective of this study was to evaluate the anthropometric parameters of short statured children examined in our outpatient clinic. 367 children were evaluated. Body weight for age, weight for height, height for age and body mass index of subjects were expressed as percent of standards. Wasting and stunting were established according to Waterlow's criteria /4/. Of 367 children, 27.8% were wasted and stunted; 59.1% were stunted; 3.8% had constitutional delay of growth and 9.3% had growth hormone deficiency. Ninety-seven percent of growth hormone deficient children had deficiency in weight as well as height. This study indicates that most short statured children and some growth hormone deficient children present with anthropometric indices of chronic nutritional deficiency in a country where nutritional deprivation is frequent.

Maroteaux-Lamy syndrome associated with growth hormone deficiency

Growth retardation is a common feature of mucopolysaccharide storage disorders, mostly considered to be a consequence of skeletal changes, Maroteaux-Lamy disease is a subtype of mucopolysaccharidosis, demonstrating somatic changes and skeletal deformities. We present a case with Maroteaux-Lamy disease associated with growth hormone deficiency. Magnetic resonance imaging study revealed marked signal changes in white matter due to the storage in brain and empty sella appearance in sellar region. In the presence of empty sella syndrome, hypothalamic-pituitary dysfunction due to the storage material may have led to growth hormone deficiency in this patient. Therefore, we recommend patients with mucopolysaccharidosis, especially those who have growth retardation, to be evaluated by hormonal and radiological studies.

True precocious puberty associated with phenylketonuria

We studied a girl with phenylketonuria who demonstrated signs of precocious puberty. At the age of 7.5 years she had premature telarche. Her height age was 7-9/12 years and her bone age was 9 years. Gonadotropin responses to LHRH administration were consistent with central precocious puberty. Elevated serum phenylalanine levels in this patient, due to poor compliance with the phenylalanine restricted diet, may be related to the early onset of puberty.