RESUMO
Breast cancer in women is the second most common cancer worldwide. Early detection of breast cancer can reduce the risk of human life. Non-invasive techniques such as mammograms and ultrasound imaging are popularly used to detect the tumour. However, histopathological analysis is necessary to determine the malignancy of the tumour as it analyses the image at the cellular level. Manual analysis of these slides is time consuming, tedious, subjective and are susceptible to human errors. Also, at times the interpretation of these images are inconsistent between laboratories. Hence, a Computer-Aided Diagnostic system that can act as a decision support system is need of the hour. Moreover, recent developments in computational power and memory capacity led to the application of computer tools and medical image processing techniques to process and analyze breast cancer histopathological images. This review paper summarizes various traditional and deep learning based methods developed to analyze breast cancer histopathological images. Initially, the characteristics of breast cancer histopathological images are discussed. A detailed discussion on the various potential regions of interest is presented which is crucial for the development of Computer-Aided Diagnostic systems. We summarize the recent trends and choices made during the selection of medical image processing techniques. Finally, a detailed discussion on the various challenges involved in the analysis of BCHI is presented along with the future scope.
Assuntos
Neoplasias da Mama , Mama , Mama/diagnóstico por imagem , Neoplasias da Mama/diagnóstico por imagem , Feminino , Humanos , Processamento de Imagem Assistida por Computador , MamografiaRESUMO
INTRODUCTION: Hodgkin's lymphoma (HL) is one of the most curable malignancies with cure rates of above 85% across all stages. Bleomycin containing regimen is routinely employed in the treatment of HL. Pulmonary toxicity due to this drug is the most feared side effect in these regimens where the mortality rate is approximately 2%-3%. We have conducted this study to assess the genetic susceptibility among the Indian HL patients to bleomycin pulmonary toxicity (BPT). MATERIALS AND METHODS: In a retrospective study conducted at a tertiary care hospital from South India between January 2013 and May 2019, we reviewed 100 HL patients who were treated with bleomycin-containing regimen (adriamycin, bleomycin, vinblastine, and dacarbazine or cyclophosphamide, vincristine, procarbazine, and prednisone/adriamycin, bleomycin, and vinblastine) for BPT. RESULTS: A total of 100 patients with HL who had received bleomycin-containing regimen were analyzed, which included 23 females and 77 males. Twenty-nine patients had BPT and five deaths were attributed to the same. Radiology reports showed that 15 patients had acute BPT and eight patients had chronic changes. Four patients had rare findings of bleomycin-induced lung damage and computed tomography of the chest could not be done for two patients, whose chest X-ray showed features suggestive of BPT. CONCLUSION: The incidence of bleomycin induced pulmonary toxicity and mortality was significantly higher in our study compared to that of other Western studies. This could be probably due to the increased susceptibility of the Indian patients to bleomycin induced lung damage. In a highly curable cancer such as HL, it is unacceptable to have such a high life-threating toxicity. Hence, an alternative chemotherapy regimen without bleomycin is to be explored which would prevent toxicity and hence the compromise on survival.
RESUMO
To study adenoid tissue eosinophilia in allergic rhinitis. A single-centre clinical case-control prospective study with 66 subjects enrolled for the study after taking written informed consent from all the participants. All patients underwent adenoidectomy with histopathological evaluation of adenoid tissue samples for eosinophils. 36 patients (cases) with Symptoms for Allergic Rhinitis (SFAR) score indicative of allergic rhinitis. 30 patients (control) with SFAR scores not indicative of allergic rhinitis. All patients were evaluated for serum absolute eosinophil count and total serum immunoglobulin E (Ig-E). There was a significant relationship between allergic rhinitis and serum Ig-E levels using the Kruskal-Wallis rank sum test amongst case and control groups with a p-value of 0.031. Pathologically examined slides of adenoid tissue eosinophil count per 10 random high power fields in these patients showed significant results with a p-value of 0.002432, via the Kruskal-Wallis rank sum test. Statistical analysis, shows that adenoid tissue eosinophil count and serum Ig-E levels can somewhat predict the presence of clinical features of allergic rhinitis. Based on several similar studies with similar results, allergic rhinitis can be gauged with adenoid tissue histopathology and routine evaluation should be considered as a standard of care.
RESUMO
Breast cancer among women is the second most common cancer worldwide. Non-invasive techniques such as mammograms and ultrasound imaging are used to detect the tumor. However, breast histopathological image analysis is inevitable for the detection of malignancy of the tumor. Manual analysis of breast histopathological images is subjective, tedious, laborious and is prone to human errors. Recent developments in computational power and memory have made automation a popular choice for the analysis of these images. One of the key challenges of breast histopathological image classification at 100× magnification is to extract the features of the potential regions of interest to decide on the malignancy of the tumor. The current state-of-the-art CNN based methods for breast histopathological image classification extract features from the entire image (global features) and thus may overlook the features of the potential regions of interest. This can lead to inaccurate diagnosis of breast histopathological images. This research gap has motivated us to propose BCHisto-Net to classify breast histopathological images at 100× magnification. The proposed BCHisto-Net extracts both global and local features required for the accurate classification of breast histopathological images. The global features extract abstract image features while local features focus on potential regions of interest. Furthermore, a feature aggregation branch is proposed to combine these features for the classification of 100× images. The proposed method is quantitatively evaluated on red a private dataset and publicly available BreakHis dataset. An extensive evaluation of the proposed model showed the effectiveness of the local and global features for the classification of these images. The proposed method achieved an accuracy of 95% and 89% on KMC and BreakHis datasets respectively, outperforming state-of-the-art classifiers.
Assuntos
Neoplasias da Mama , Redes Neurais de Computação , Mama/diagnóstico por imagem , Neoplasias da Mama/diagnóstico por imagem , Feminino , Humanos , Processamento de Imagem Assistida por ComputadorRESUMO
T he pathologist determines the malignancy of a breast tumor by studying the histopathological images. In particular, the characteristics and distribution of nuclei contribute greatly to the decision process. Hence, the segmentation of nuclei constitutes a crucial task in the classification of breast histopathological images. Manual analysis of these images is subjective, tedious and susceptible to human error. Consequently, the development of computer-aided diagnostic systems for analysing these images have become a vital factor in the domain of medical imaging. However, the usage of medical image processing techniques to segment nuclei is challenging due to the diverse structure of the cells, poor staining process, the occurrence of artifacts, etc. Although supervised computer-aided systems for nuclei segmentation is popular, it is dependent on the availability of standard annotated datasets. In this regard, this work presents an unsupervised method based on Chan-Vese model to segment nuclei from breast histopathological images. The proposed model utilizes multi-channel color information to efficiently segment the nuclei. Also, this study proposes a pre-processing step to select appropriate color channel such that it discriminates nuclei from the background region. An extensive evaluation of the proposed model on two challenging datasets demonstrates its validity and effectiveness.
RESUMO
Infections that affect the intervertebral discs and vertebrae are known as spondylodiscitis. Such infections are commonly caused by pyogenic organisms, particularly Staphylococcus aureus, and hematogenous spread is the most common route. Non-pyogenic infections include Mycobacterium tuberculosis and Brucellosis. Mycotic infections are becoming more common, in line with the growing number of immunodeficiency disorders. Cryptococcus is included among these mycotic infections. We present a case of such an infection in a non-immunocompromised patient with a known history of treatment with antitubercular therapy. A 52-year-old man came to our hospital with a backache of one-month duration and progressive neurological deficits of the lower limbs of one-week duration. His imaging studies were suggestive of spondylodiscitis at the D10-11 and D11-12 levels with a left paraspinal abscess. The patient underwent anterolateral decompression, biopsy, and instrumented posterior spinal fusion. The pus grew Cryptococcus, and histopathology confirmed Cryptococcal spondylodiscitis. The patient was treated with parenteral amphotericin B and fluconazole. A mycotic infection must be considered in the differential diagnosis of infectious spondylodiscitis.
RESUMO
BACKGROUND & OBJECTIVE: Cytogenetic abnormalities in Multiple myeloma (MM) has emerged as the most important factor that determine the prognosis and survival. Fluorescence in situ hybridization (FISH) can detect a greater number of cytogenetic abnormalities as compared to conventional karyotyping and hence has become the standard test in determining genetic abnormalities in MM. The present study was planned as there is an unmet need to find out various cytogenetic abnormalities and to implement them in prognostic stratification by Revised International Staging System (R-ISS) among Indian population. METHODS: A single institution retrospective study was conducted among a total of 117 patients newly diagnosed as Multiple Myeloma. They were analyzed for various cytogenetic abnormalities by using interphase FISH (iFISH) and were staged according to Revised International Staging System (R- ISS). RESULTS: Out of the 117 patients studied, deletion 17p13 (p53) was present in 16 patients (13.67%). Thirty patients (25.64%) showed deletion 13q14.3. Three patients (2.56%) were detected to have t(4:14).Two patients (1.7%) had t(11:14) and t(14:16), respectively. Total of 19 patients (16.23%) in our study exhibited high risk cytogenetics and two among them had more than one high risk cytogenetic abnormalities. There was a 66.4% moderate correlation between ISS-III and high-risk cytogenetics which was statistically insignificant. Of the total 117 patients, 37 (31.62%) were staged R-ISS III. CONCLUSION: High risk cytogenetics was found in 16.23 % of our study population and del 17p13 was the most common high-risk cytogenetic abnormality. Of the studied subjects, 31.62% had R-ISS III, which is significantly higher compared to western population.