Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 6 de 6
Filter
Add more filters










Database
Language
Publication year range
1.
Sci Rep ; 13(1): 14522, 2023 09 04.
Article in English | MEDLINE | ID: mdl-37666922

ABSTRACT

The detection of meningioma tumors is the most crucial task compared with other tumors because of their lower pixel intensity. Modern medical platforms require a fully automated system for meningioma detection. Hence, this study proposes a novel and highly efficient hybrid Convolutional neural network (HCNN) classifier to distinguish meningioma brain images from non-meningioma brain images. The HCNN classification technique consists of the Ridgelet transform, feature computations, classifier module, and segmentation algorithm. Pixel stability during the decomposition process was improved by the Ridgelet transform, and the features were computed from the coefficient of the Ridgelet. These features were classified using the HCNN classification approach, and tumor pixels were detected using the segmentation algorithm. The experimental results were analyzed for meningioma tumor images by applying the proposed method to the BRATS 2019 and Nanfang dataset. The proposed HCNN-based meningioma detection system achieved 99.31% sensitivity, 99.37% specificity, and 99.24% segmentation accuracy for the BRATS 2019 dataset. The proposed HCNN technique achieved99.35% sensitivity, 99.22% specificity, and 99.04% segmentation accuracy on brain Magnetic Resonance Imaging (MRI) in the Nanfang dataset. The proposed system obtains 99.81% classification accuracy, 99.2% sensitivity, 99.7% specificity and 99.8% segmentation accuracy on BRATS 2022 dataset. The experimental results of the proposed HCNN algorithm were compared with those of the state-of-the-art meningioma detection algorithms in this study.


Subject(s)
Brain Neoplasms , Meningeal Neoplasms , Meningioma , Humans , Meningioma/diagnostic imaging , Algorithms , Neural Networks, Computer , Meningeal Neoplasms/diagnostic imaging , Brain Neoplasms/diagnostic imaging
2.
Indian J Surg Oncol ; 11(4): 653-661, 2020 Dec.
Article in English | MEDLINE | ID: mdl-33281405

ABSTRACT

Emerging techniques in minimally invasive rectal resection include robotic total mesorectal excision (R-TME). The Da Vinci Surgical System offers precise dissection in narrow and deep confined spaces and is gaining increasing acceptance during recent times. The aim of this study is to analyse our initial experience of R-TME with Da Vinci Xi platform in terms of perioperative and oncological outcomes in the context of data from recently published randomised ROLARR trial amongst minimally invasive novice surgeons. Patients who underwent R-TME or tumour specific mesorectal excision for rectal cancer between May 2016 and November 2019 were identified from a prospectively maintained single institution colorectal database. Demographic, clinical-pathological and short-term oncological outcomes were analysed. Of the 178 patients, 117 (65.7%) and 31 (17.4%) patients had lower and mid third rectal cancer. Most of the tumours were locally advanced, cT3-T4: 138 (77.5%). One hundred/178 (56.2%) underwent sphincter preserving TME. Eighty-seven (48.8%) were grade II adenocarcinoma. Nonmucinous adenocarcinoma was the predominant histology, 138 (78.4%). One hundred one cases (56.7%) were pT3. The mean number of lymph node yield was 13 ± 5. Distal resection margin and circumferential resection margin were positive in 2 (1.12%), 12 cases (6.74%) respectively. Eleven cases (6.7%) had to be converted to open TME. Mean blood loss and duration of surgery was 170 ± 60 ml and 286 ± 45 min respectively. Five percent cases had an anastomotic leak. Grade IIIa-IIIb Clavien Dindo (CD) morbidity score was reported to be in 12 (6.75%) and 10 (5.61%) cases. Median length of hospitalisation was 7 days (range 4-14 days). Perioperative and pathologic outcomes following robotic rectal resection is associated with good short-term oncological outcomes and is safe, effective, and reproducible by a minimally invasive novice surgeon.

4.
Ann Maxillofac Surg ; 9(2): 364-370, 2019.
Article in English | MEDLINE | ID: mdl-31909017

ABSTRACT

BACKGROUND: Oral squamous cell carcinoma (OSCC) is the sixth most common malignancy worldwide and is the major public health problem in the Indian subcontinent, where it ranks among the top three types of cancer in the country. Here, we aimed to analyze the clinical and tumor characteristics which impact the survival of OSCC patients. METHODS: A retrospective analysis of clinical records of all patients who underwent treatment for OSCC at Kidwai Memorial Institute of Oncology, between January 2009 and January 2012 was analyzed. Age, gender, site of the primary lesion, tumor size (T), nodal status (N), stage of the disease, marginal status, and modality of treatment data were collected and analyzed. RESULTS: Data of 147 patients with OSCC were included in the study and analyzed. Of the patients analyzed 61% were male, with 56% were <65 years, and 40% presented with buccal mucosa cancer followed by 30% with tongue cancer. Of all patients, 30% of them presented with Stage 1 and rest were Stage 2 and above. In our study, 40% underwent surgery only followed by regular follow-up and 60% needed surgery with postoperative adjuvant treatment based on the marginal status, the lymph node status, and T status of the disease. CONCLUSION: Our data suggest that age <65 years, female patients, alveolus lesion and tongue lesion and the early T Stage and N0 and negative margin had a significant positive impact on disease-free and overall survival of oral cancer patients.

6.
J Indian Med Assoc ; 107(2): 100, 102-3, 2009 Feb.
Article in English | MEDLINE | ID: mdl-19585819

ABSTRACT

Erythoderma first described by Hebra in 1868 is a reaction pattern, characterised by generalised and confluent erythema with desquamation affecting more than 90% of body surface and is usually accompanied by systemic manifestation including some metabolic changes. Tile study was envisaged to assess their profile of aetiology, clinical features and to correlate with histopathological findings. Twenty-four patients (18 males and 6 females) with erythroderma were considered for the study. All patients were hospitalised, detailed history was taken and were subjected to relevant investigations--haemogram, serum proteins, liver and renal function tests, routine and microscopic urine tests, HIV screening, x-ray chest, ultrasound abdomen, FNAC of enlarged lymph nodes and skin biopsy. The age group affected ranged between 7 and 70 years, peak incidence between 50 and 60 years. The male to female ratio was 3:1. Scaling, erythema and pruritus were predominant clinical manifestations. In 12 clinically suspected psoriatic erythroderma, only in 6 cases the histopathological features were correlated to psoriasis and remaining showed non-specific chronic dermatitis. Two patients were found to be HIV-positive. There is good clinicopathological correlation in erythroderma caused by lichen planus, atopic dermatitis, seborroeic dermatitis, non-bullous congenital ichthyosiform erythroderma. Drugs were found to be aetiological factor in 3 cases. The study was conducted to assess variations in clinical, aetiological and histopathological profile of erythroderma. The present series had high percentage of erythroderma secondary to preexisting dermatoses. The onset of disease was insidious except in drug-induced erythroderma where it was acute.


Subject(s)
Dermatitis, Exfoliative/etiology , Dermatitis, Exfoliative/pathology , Adolescent , Adult , Aged , Child , Cohort Studies , Dermatitis, Exfoliative/therapy , Female , Humans , India , Male , Middle Aged , Risk Factors , Young Adult
SELECTION OF CITATIONS
SEARCH DETAIL
...