A multiparametric MRI-based CAD system for accurate diagnosis of bladder cancer staging.

Appropriate treatment of bladder cancer (BC) is widely based on accurate and early BC staging. In this paper, a multiparametric computer-aided diagnostic (MP-CAD) system is developed to differentiate between BC staging, especially T1 and T2 stages, using T2-weighted (T2W) magnetic resonance imaging (MRI) and diffusion-weighted (DW) MRI. Our framework starts with the segmentation of the bladder wall (BW) and localization of the whole BC volume (Vt) and its extent inside the wall (Vw). Our segmentation framework is based on a fully connected convolution neural network (CNN) and utilized an adaptive shape model followed by estimating a set of functional, texture, and morphological features. The functional features are derived from the cumulative distribution function (CDF) of the apparent diffusion coefficient. Texture features are radiomic features estimated from T2W-MRI, and morphological features are used to describe the tumors' geometric. Due to the significant texture difference between the wall and bladder lumen cells, Vt is parcelled into a set of nested equidistance surfaces (i.e., iso-surfaces). Finally, features are estimated for individual iso-surfaces, which are then augmented and used to train and test machine learning (ML) classifier based on neural networks. The system has been evaluated using 42 data sets, and a leave-one-subject-out approach is employed. The overall accuracy, sensitivity, specificity, and area under the receiver operating characteristics (ROC) curve (AUC) are 95.24%, 95.24%, 95.24%, and 0.9864, respectively. The advantage of fusion multiparametric iso-features is highlighted by comparing the diagnostic accuracy of individual MRI modality, which is confirmed by the ROC analysis. Moreover, the accuracy of our pipeline is compared against other statistical ML classifiers (i.e., random forest (RF) and support vector machine (SVM)). Our CAD system is also compared with other techniques (e.g., end-to-end convolution neural networks (i.e., ResNet50).

A New Framework for Performing Cardiac Strain Analysis from Cine MRI Imaging in Mice.

Cardiac magnetic resonance (MR) imaging is one of the most rigorous form of imaging to assess cardiac function in vivo. Strain analysis allows comprehensive assessment of diastolic myocardial function, which is not indicated by measuring systolic functional parameters using with a normal cine imaging module. Due to the small heart size in mice, it is not possible to perform proper tagged imaging to assess strain. Here, we developed a novel deep learning approach for automated quantification of strain from cardiac cine MR images. Our framework starts by an accurate localization of the LV blood pool center-point using a fully convolutional neural network (FCN) architecture. Then, a region of interest (ROI) that contains the LV is extracted from all heart sections. The extracted ROIs are used for the segmentation of the LV cavity and myocardium via a novel FCN architecture. For strain analysis, we developed a Laplace-based approach to track the LV wall points by solving the Laplace equation between the LV contours of each two successive image frames over the cardiac cycle. Following tracking, the strain estimation is performed using the Lagrangian-based approach. This new automated system for strain analysis was validated by comparing the outcome of these analysis with the tagged MR images from the same mice. There were no significant differences between the strain data obtained from our algorithm using cine compared to tagged MR imaging. Furthermore, we demonstrated that our new algorithm can determine the strain differences between normal and diseased hearts.

Hemangiopericytoma in the central nervous system. A study of eight cases.

Most hemangiopericytomas (HPC) are located in the musculoskeletal system and the skin, while the location in the central nervous system (CNS) is rare. The latter represents 2 to 4% in large series of meningeal tumors, thus accounting for less than 1% of all CNS tumors. In the central nervous system, tumors with a hemangiopericytomatous histolopathological pattern can be either hemangiopericytomas or solitary fibrous tumors. CNS-HPCs have a relentless tendency for local recurrence and metastases outside the CNS. Metastasis can also appear many years after adequate treatment of the primary tumor. We present a pathological study of eight patients with CNS-HPC and compare our results with corresponding published data. The CNS-HPC group consisted of three males and five females with a mean age of 36.75 years. The tumors were supratentorial in four cases, infratentorial in two cases, tentorial in one case and located in the spinal cord in the last one. Histologically, CNS-HPCs were similar to their soft tissue counterparts. One case demonstrated increased cellularity, marked nuclear hyperchromasia and marked cellular pleomorphism with infiltration of the cerebellum. All patients underwent surgery with gross-total resection in all cases. No patients received postoperative radiation therapy. Only four patients recurred locally after six, seven and eight months, and five years. Our study presents the pathological features of CNS-HPC as a distinct entity from both meningioma and solitary fibrous tumors. A comparative review of literature with our results is discussed.

Primary central nervous system malignant melanoma: report of 5 cases.

Primary melanocytic neoplasms of the central nervous system consist of a spectrum of lesions ranging from well-differentiated melanocytoma to its overtly malignant counterpart, melanoma. Clinicopathologic features of 5 cases of primary central nervous system malignant melanoma were studied to define histologic appearances, diagnostic criteria, and the clinical behavior of lesions along this spectrum. There were three women and two men (mean age was 35 years) with symptoms of increased intracranial pressure. Radiological findings showed a solitary intra parenchymal lesion with variable enhancement after gadolinium administration. All patients underwent surgical treatment. Histologic examination revealed primary melanoma.

Anaplastic secretory meningioma: a case report.

Secretory meningiomas are rare histological subtypes of meningiomas with benign biological behaviour. In this study, the authors describe the first case of secretory meningioma with many mitotic figures and brain invasion, and discuss the clinicopathologic features including immunohistochemical staining profile and ultrastructural appearance of this tumour. A case of a 54-year-old man diagnosed with an intracranial tumour located in the left frontal lobe is presented. On pre-contrast CT scans, the tumour was hypodense and the contrast enhancement was marked in the pseudo membrane. The tumour was partially removed. The histological diagnosis was secretory meningioma with many mitotic figures, a high MIB-1 labeling index and a brain invasion.

Intrasphenoidal rathke cleft cyst.

Symptomatic Rathke cleft cysts (RCC) are reported in the sellar and suprasellar regions, but no case of sphenoidal RCC has been reported. We report a case of sphenoidal RCC in a 41-year-old man. The lesion was revealed by headaches and diplopia. Symptoms disappeared transiently after a spontaneous rhinorrhea but relapsed 4 months later. MR imaging showed a cystic sphenoidal lesion, isointense on T1-weighted images (WI) with peripheral gadolinium enhancement and hyperintense on T2 WI. The patient underwent surgery through a transrhinoseptal approach. The wall of the sphenoid sinus was paper-thin. The cyst contained a motor-oil-like fluid and communicated widely with the nasal fossa. Its wall was partially extracted. Symptoms and signs ceased after surgery. MR imaging performed 1 year later showed the disappearance of the sphenoidal cyst. Embryological origin of RCCs is discussed. The hypothesis of a continuum between the different epithelial cystic lesions of the sellar and parasellar region is discussed. Imaging has an important impact on the diagnosis; nevertheless, the specific characterization remains difficult.

[Cerebral stereotactic biopsy and surgery: Report of 100 cases]. / La biopsie et la chirurgie cérébrales en conditions stéréotaxiques: a propos de 100 observations.

OBJECTIVE: To report the results of the use of the stereotactic techniques in the management of intra cranial lesions. MATERIALS AND METHODS: Between july 1994 and march 1998, we carried out 117 stereotactic procedures of whom only 100 cases were analyzed. All the procedures were achieved after a CT scan. Patients were separated in two groups: (A) stereotactic biopsy (91 patients), (B) surgery with laser guidance (9 patients). The mean age in group A was 38 years (2-75 years) versus 27 years (11-66 years) in group B. The sex-ratio was 1.3. RESULTS: In the group A, the correct pathological diagnosis was obtained in 91.2% of cases. Glial tumors was the frequent histopathological variety of tumor (67.47%). Only one patient was operated after biopsy for a bilateral meningioma of the anterior 1/3 of the falx. There was only one death (1.09%) and 3.29% of transitory complications. In the group B, all patients were operated with laser guidance. Thirty seven per cent of patients underwent radiotherapy after the stereotactic biopsy or surgery. CONCLUSION: Stereotactic biopsy is a reliable method for the histopathological diagnosis of deep-seated brain lesions. Surgery with laser guidance is a useful alternative for the management of small deep-seated lesions or lesions located in functional areas.