Differential Diagnosis of Diabetic Foot Osteomyelitis and Charcot Neuropathic Osteoarthropathy with Deep Learning Methods.

Our study aims to evaluate the potential of a deep learning (DL) algorithm for differentiating the signal intensity of bone marrow between osteomyelitis (OM), Charcot neuropathic osteoarthropathy (CNO), and trauma (TR). The local ethics committee approved this retrospective study. From 148 patients, segmentation resulted in 679 labeled regions for T1-weighted images (comprising 151 CNO, 257 OM, and 271 TR) and 714 labeled regions for T2-weighted images (consisting of 160 CNO, 272 OM, and 282 TR). We employed both multi-class classification (MCC) and binary-class classification (BCC) approaches to compare the classification outcomes of CNO, TR, and OM. The ResNet-50 and the EfficientNet-b0 accuracy values were computed at 96.2% and 97.1%, respectively, for T1-weighted images. Additionally, accuracy values for ResNet-50 and the EfficientNet-b0 were determined at 95.6% and 96.8%, respectively, for T2-weighted images. Also, according to BCC for CNO, OM, and TR, the sensitivity of ResNet-50 is 91.1%, 92.4%, and 96.6% and the sensitivity of EfficientNet-b0 is 93.2%, 97.6%, and 98.1% for T1, respectively. For CNO, OM, and TR, the sensitivity of ResNet-50 is 94.9%, 83.6%, and 97.9% and the sensitivity of EfficientNet-b0 is 95.6%, 85.2%, and 98.6% for T2, respectively. The specificity values of ResNet-50 for CNO, OM, and TR in T1-weighted images are 98.1%, 97.9%, and 94.7% and 98.6%, 97.5%, and 96.7% in T2-weighted images respectively. Similarly, for EfficientNet-b0, the specificity values are 98.9%, 98.7%, and 98.4% and 99.1%, 98.5%, and 98.7% for T1-weighted and T2-weighted images respectively. In the diabetic foot, deep learning methods serve as a non-invasive tool to differentiate CNO, OM, and TR with high accuracy.

Novel radiomic features versus deep learning: differentiating brain metastases from pathological lung cancer types in small datasets.

OBJECTIVE: Accurate diagnosis and early treatment are crucial for survival in patients with brain metastases. This study aims to expand the capability of radiomics-based classification algorithms with novel features and compare results with deep learning-based algorithms to differentiate the subtypes of lung cancer from MRI of metastatic lesions in the brain. METHODS: This study includes 75 small cell lung carcinoma, 72 squamous cell carcinoma, and 75 adenocarcinoma segments. For the radiomics-based algorithm, novel features from the original Laplacian of Gaussian filtered and two-dimensional wavelet transformed images were extracted, and a new three-stage feature selection algorithm was proposed for feature selection. Two classification methods were applied to images to identify the subtypes of lung cancer. Additionally, EfficientNet and ResNet with transfer learning were used as classifiers to compare the results of the proposed algorithm. RESULTS: The sensitivity and specificity values of the radiomics-based classifier are 94.44 and 95.33%, and for the second classifier are 87.67% and 92.62%, respectively. Besides, a one-vs-all approach comparison was made utilizing two deep learning-based classifiers; The sensitivity and specificity values of 94.29 and 94.08% were obtained from ResNet-50. Moreover, mentioned metrics for EfficientNet-b0 are 92.86 and 93.42%. Furthermore, the accuracies of two radiomics-based and two deep learning-based models were 84.68%, 78.37%, 92.34%, and 90.99%, respectively for one-vs-one approach. CONCLUSION: The results suggest that the proposed radiomics-based algorithm is a helpful diagnostic assistant to improve decision-making for treating patients with brain metastases in small datasets. ADVANCES IN KNOWLEDGE: Firstly, the proposed method of this study extracts novel features from transformations of the original images, such as wavelet and Laplacian of Gaussian filter for the first time in literature. Secondly, this is the first study that investigates the classification performance of the shallow and deep learning approaches to identify subtypes of lung cancer.

Radiomics method in the differential diagnosis of diabetic foot osteomyelitis and charcot neuroarthropathy.

OBJECTIVES: Our study used a radiomics method to differentiate bone marrow signal abnormality (BMSA) between Charcot neuroarthropathy (CN) and osteomyelitis (OM). METHODS AND MATERIALS: The records of 166 patients with diabetic foot suspected CN or OM between January 2020 and March 2022 were retrospectively examined. A total of 41 patients with BMSA on MRI were included in this study. The diagnosis of OM was confirmed histologically in 24 of 41 patients. We clinically followed 17 patients as CN with laboratory tests. We also included 29 nondiabetic patients with traumatic (TR) BMSA on MRI as the third group. Contours of all BMSA on T 2 - and T1 -weighted images in three patient groups were segmented semi-automatically on ManSeg (v.2.7d). The T1 and T2 features of three groups in radiomics were statistically evaluated. We applied the multi-class classification (MCC) and binary-class classification (BCC) methodologies to compare results. RESULTS: For MCC, the accuracy of Multi-Layer Perceptron (MLP) was 76.92% and 84.38% for T1 and T2, respectively. According to BCC, for CN, OM, and TR BMSA, the sensitivity of MLP is 74%, 89.23%, and 76.19% for T1, and 90.57%, 85.92%, 86.81% for T2, respectively. For CN, OM, and TR BMSA, the specificity of MLP is 89.16%, 87.57%, and 90.72% for T1 and 93.55%, 89.94%, and 90.48% for T2 images, respectively. CONCLUSION: In diabetic foot, the radiomics method can differentiate the BMSA of CN and OM with high accuracy. ADVANCES IN KNOWLEDGE: The radiomics method can differentiate the BMSA of CN and OM with high accuracy.

Comparison of tomographic kidney volumes measured by semiautomatic segmentation method with scintigraphic split renal function in predicting posttransplant kidney functions.

INTRODUCTION: In this study, it was aimed to compare scintigraphic split renal function (SRF) and computed tomographic (CT) kidney volumes by semiautomatic segmentation method in predicting graft functions after kidney transplantation. METHODS: One hundred and twelve patients (77 males, 35 females) who had a living-donor kidney transplant between 2015 and 2017 in our centre were included in the study. While SRF was calculated with technetium-99m-diethylenetriaminepentaacetic acid (99m Tc-DTPA) scintigraphy, CT angiography was used for volumetric calculations. RESULTS: CT-volumetric measurements, especially renal cortical volume (RCV: 103.8 ± 20 ml) and ratio to body mass index (RCV/BMI: 4.45 ± 1.3) were found to be more significant than 99m Tc-DTPA-SRF in predicting graft functions. The correlations between SRF and RCV with 6th-month estimated glomerular filtration rate (eGFR) (rSRF: 0.052, rRCV: 0.317, p = 0.041) and 1st-year eGFR (rSRF: 0.104, rRCV: 0.374, p = 0.033) were found to be more significant in favour of RCV. The correlation between SRF/BMI and RCV/BMI with 1st-, 6th- and 12th-month eGFR (respectively, p = 0.02/0.048/0.024) were found to be more significant in favour of RCV/BMI. Although univariate analysis showed a significant relationship between most volumetric measurements and 1st-year graft functions, in multivariate analysis only RCV [odds ratio (OR): 1.04 (1.01-1.07), p = 0.023] and RCV/BMI [OR: 2.5 (1.27-5.39), p = 0.013] showed a significant relationship between graft functions. CONCLUSION: In our study, it was shown that CT-based renal volumetric measurements, especially RCV and RCV/BMI, predicted graft functions more strongly than scintigraphic 99m Tc-DTPA-SRF.

A New Practical Intracerebral Hematoma Volume Calculation Method and Comparison to simple ABC/2.

AIM: To find a more practical and effective formula than simple ABC/2 (sABC/2) to calculate the hematoma volume in patients with subdural and parenchymal haemorrhage. MATERIAL AND METHODS: We reviewed the records of 157 patients who underwent brain computed tomography examinations for stroke from January to October 2017. Our method, sABC/2 formula, and the planimetric method (the gold standard) were used for measuring the volumes of hematoma. RESULTS: The concordance in brain hematoma volumes calculated by sABC/2 and the proposed method as compared to planimetry were 0.92 and 0.93, respectively (p < 0.05). The proposed method calculates the subdural hematoma volumes much better than the conventional one, and the root mean square error (RMSE) values were 32.17 and 20.62 ml for sABC/2 and our new method, respectively, whereas the RMSE values for parenchymal hematomas were 25.01 and 20.46 ml for sABC/2 and our new method, respectively. CONCLUSION: Our new formula for calculating the volume of subdural and parenchymal hematomas is as practical as sABC/2 and allows the clinician to apply the method bedside.

Automated segmentation of the injured kidney due to abdominal trauma.

The objective of this study is to propose and validate a computer-aided segmentation system which performs the automated segmentation of injured kidney in the presence of contusion, peri-, intra-, sub-capsular hematoma, laceration, active extravasation and urine leak due to abdominal trauma. In the present study, total multi-phase CT scans of thirty-seven cases were used; seventeen of them for the development of the method and twenty of them for the validation of the method. The proposed algorithm contains three steps: determination of the kidney mask using Circular Hough Transform, segmentation of the renal parenchyma of the kidney applying the symmetry property to the histogram, and estimation of the kidney volume. The results of the proposed method were compared using various metrics. The kidney quantification led to 92.3 ± 4.2% Dice coefficient, 92.8 ± 7.4%/92.3 ± 5.1% precision/sensitivity, 1.4 ± 0.6 mm/2.0 ± 1.0 mm average surface distance/root-mean-squared error for intact and 87.3 ± 8.4% Dice coefficient, 84.3 ± 13.8%/92.2 ± 3.8% precision/sensitivity and 2.4 ± 2.2 mm/4.0 ± 4.2 mm average surface distance/root-mean-squared error for injured kidneys. The segmentation of the injured kidney was satisfactorily performed in all cases. This method may lead to the automated detection of renal lesions due to abdominal trauma and estimate the intraperitoneal blood amount, which is vital for trauma patients.

A CAD of fully automated colonic polyp detection for contrasted and non-contrasted CT scans.

PURPOSE: Computer-aided detection (CAD) systems are developed to help radiologists detect colonic polyps over CT scans. It is possible to reduce the detection time and increase the detection accuracy rates by using CAD systems. In this paper, we aimed to develop a fully integrated CAD system for automated detection of polyps that yields a high polyp detection rate with a reasonable number of false positives. METHODS: The proposed CAD system is a multistage implementation whose main components are: automatic colon segmentation, candidate detection, feature extraction and classification. The first element of the algorithm includes a discrete segmentation for both air and fluid regions. Colon-air regions were determined based on adaptive thresholding, and the volume/length measure was used to detect air regions. To extract the colon-fluid regions, a rule-based connectivity test was used to detect the regions belong to the colon. Potential polyp candidates were detected based on the 3D Laplacian of Gaussian filter. The geometrical features were used to reduce false-positive detections. A 2D projection image was generated to extract discriminative features as the inputs of an artificial neural network classifier. RESULTS: Our CAD system performs at 100% sensitivity for polyps larger than 9 mm, 95.83% sensitivity for polyps 6-10 mm and 85.71% sensitivity for polyps smaller than 6 mm with 5.3 false positives per dataset. Also, clinically relevant polyps ([Formula: see text]6 mm) were identified with 96.67% sensitivity at 1.12 FP/dataset. CONCLUSIONS: To the best of our knowledge, the novel polyp candidate detection system which determines polyp candidates with LoG filters is one of the main contributions. We also propose a new 2D projection image calculation scheme to determine the distinctive features. We believe that our CAD system is highly effective for assisting radiologist interpreting CT.

Automated segmentation of the injured spleen.

PURPOSE: To develop a novel automated method for segmentation of the injured spleen using morphological properties following abdominal trauma. Average attenuation of a normal spleen in computed tomography (CT) does not vary significantly between subjects. However, in the case of solid organ injury, the shape and attenuation of the spleen on CT may vary depending on the time and severity of the injury. Timely assessment of the severity and extent of the injury is of vital importance in the setting of trauma. METHODS: We developed an automated computer-aided method for segmenting the injured spleen from CT scans of patients who had splenectomy due to abdominal trauma. We used ten subjects to train our computer-aided diagnosis (CAD) method. To validate the CAD method, we used twenty subjects in our testing group. Probabilistic atlases of the spleens were created using manually segmented data from ten CT scans. The organ location was modeled based on the position of the spleen with respect to the left side of the spine followed by the extraction of shape features. We performed the spleen segmentation in three steps. First, we created a mask of the spleen, and then we used this mask to segment the spleen. The third and final step was the estimation of the spleen edges in the presence of an injury such as laceration or hematoma. RESULTS: The traumatized spleens were segmented with a high degree of agreement with the radiologist-drawn contours. The spleen quantification led to [Formula: see text] volume overlap, [Formula: see text] Dice similarity index, [Formula: see text] precision/sensitivity, [Formula: see text] volume estimation error rate, [Formula: see text] average surface distance/root-mean-squared error. CONCLUSIONS: Our CAD method robustly segments the spleen in the presence of morphological changes such as laceration, contusion, pseudoaneurysm, active bleeding, periorgan and parenchymal hematoma, including subcapsular hematoma due to abdominal trauma. CAD of the splenic injury due to abdominal trauma can assist in rapid diagnosis and assessment and guide clinical management. Our segmentation method is a general framework that can be adapted to segment other injured solid abdominal organs.